From 3c1fece8819ed25257461b71e7c75a1f33eaa61d Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Mon, 20 Feb 2017 17:52:27 +0100 Subject: [PATCH 001/399] netfilter: nft_exthdr: Allow checking TCP option presence, too Honor NFT_EXTHDR_F_PRESENT flag so we check if the TCP option is present. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_exthdr.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index c308920b194c..d212a85d2f33 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -98,14 +98,21 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr, goto err; offset = i + priv->offset; - dest[priv->len / NFT_REG32_SIZE] = 0; - memcpy(dest, opt + offset, priv->len); + if (priv->flags & NFT_EXTHDR_F_PRESENT) { + *dest = 1; + } else { + dest[priv->len / NFT_REG32_SIZE] = 0; + memcpy(dest, opt + offset, priv->len); + } return; } err: - regs->verdict.code = NFT_BREAK; + if (priv->flags & NFT_EXTHDR_F_PRESENT) + *dest = 0; + else + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { From 511040eea2234d9add3f33ba0e6c2e17944fdfb6 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Thu, 23 Feb 2017 12:10:15 +0100 Subject: [PATCH 002/399] netfilter: nft_hash: rename nft_hash to nft_jhash This patch renames the local nft_hash structure and functions to nft_jhash in order to prepare the nft_hash module code to add new hash functions. Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_hash.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index eb2721af898d..ccb834ef049b 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -17,7 +17,7 @@ #include #include -struct nft_hash { +struct nft_jhash { enum nft_registers sreg:8; enum nft_registers dreg:8; u8 len; @@ -26,11 +26,11 @@ struct nft_hash { u32 offset; }; -static void nft_hash_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void nft_jhash_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { - struct nft_hash *priv = nft_expr_priv(expr); + struct nft_jhash *priv = nft_expr_priv(expr); const void *data = ®s->data[priv->sreg]; u32 h; @@ -47,11 +47,11 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, }; -static int nft_hash_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_jhash_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { - struct nft_hash *priv = nft_expr_priv(expr); + struct nft_jhash *priv = nft_expr_priv(expr); u32 len; int err; @@ -92,10 +92,10 @@ static int nft_hash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_hash_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_jhash_dump(struct sk_buff *skb, + const struct nft_expr *expr) { - const struct nft_hash *priv = nft_expr_priv(expr); + const struct nft_jhash *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg)) goto nla_put_failure; @@ -117,17 +117,17 @@ static int nft_hash_dump(struct sk_buff *skb, } static struct nft_expr_type nft_hash_type; -static const struct nft_expr_ops nft_hash_ops = { +static const struct nft_expr_ops nft_jhash_ops = { .type = &nft_hash_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_hash)), - .eval = nft_hash_eval, - .init = nft_hash_init, - .dump = nft_hash_dump, + .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)), + .eval = nft_jhash_eval, + .init = nft_jhash_init, + .dump = nft_jhash_dump, }; static struct nft_expr_type nft_hash_type __read_mostly = { .name = "hash", - .ops = &nft_hash_ops, + .ops = &nft_jhash_ops, .policy = nft_hash_policy, .maxattr = NFTA_HASH_MAX, .owner = THIS_MODULE, From 3206caded81ad9bdb2e7ff4c0b94ec5913df8618 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Thu, 2 Mar 2017 17:00:14 +0100 Subject: [PATCH 003/399] netfilter: nft_hash: support of symmetric hash This patch provides symmetric hash support according to source ip address and port, and destination ip address and port. For this purpose, the __skb_get_hash_symmetric() is used to identify the flow as it uses FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL flag by default. The new attribute NFTA_HASH_TYPE has been included to support different types of hashing functions. Currently supported NFT_HASH_JENKINS through jhash and NFT_HASH_SYM through symhash. The main difference between both types are: - jhash requires an expression with sreg, symhash doesn't. - symhash supports modulus and offset, but not seed. Examples: nft add rule ip nat prerouting ct mark set jhash ip saddr mod 2 nft add rule ip nat prerouting ct mark set symhash mod 2 By default, jenkins hash will be used if no hash type is provided for compatibility reasons. Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 13 ++++ net/netfilter/nft_hash.c | 99 +++++++++++++++++++++++- 2 files changed, 111 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 05215d30fe5c..4f7d75682c59 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -815,6 +815,17 @@ enum nft_rt_keys { NFT_RT_NEXTHOP6, }; +/** + * enum nft_hash_types - nf_tables hash expression types + * + * @NFT_HASH_JENKINS: Jenkins Hash + * @NFT_HASH_SYM: Symmetric Hash + */ +enum nft_hash_types { + NFT_HASH_JENKINS, + NFT_HASH_SYM, +}; + /** * enum nft_hash_attributes - nf_tables hash expression netlink attributes * @@ -824,6 +835,7 @@ enum nft_rt_keys { * @NFTA_HASH_MODULUS: modulus value (NLA_U32) * @NFTA_HASH_SEED: seed value (NLA_U32) * @NFTA_HASH_OFFSET: add this offset value to hash result (NLA_U32) + * @NFTA_HASH_TYPE: hash operation (NLA_U32: nft_hash_types) */ enum nft_hash_attributes { NFTA_HASH_UNSPEC, @@ -833,6 +845,7 @@ enum nft_hash_attributes { NFTA_HASH_MODULUS, NFTA_HASH_SEED, NFTA_HASH_OFFSET, + NFTA_HASH_TYPE, __NFTA_HASH_MAX, }; #define NFTA_HASH_MAX (__NFTA_HASH_MAX - 1) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index ccb834ef049b..a6a4633725bb 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -38,6 +38,25 @@ static void nft_jhash_eval(const struct nft_expr *expr, regs->data[priv->dreg] = h + priv->offset; } +struct nft_symhash { + enum nft_registers dreg:8; + u32 modulus; + u32 offset; +}; + +static void nft_symhash_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_symhash *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + u32 h; + + h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus); + + regs->data[priv->dreg] = h + priv->offset; +} + static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SREG] = { .type = NLA_U32 }, [NFTA_HASH_DREG] = { .type = NLA_U32 }, @@ -45,6 +64,7 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_MODULUS] = { .type = NLA_U32 }, [NFTA_HASH_SEED] = { .type = NLA_U32 }, [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, + [NFTA_HASH_TYPE] = { .type = NLA_U32 }, }; static int nft_jhash_init(const struct nft_ctx *ctx, @@ -92,6 +112,32 @@ static int nft_jhash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } +static int nft_symhash_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_symhash *priv = nft_expr_priv(expr); + + if (!tb[NFTA_HASH_DREG] || + !tb[NFTA_HASH_MODULUS]) + return -EINVAL; + + if (tb[NFTA_HASH_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); + + priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); + + priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); + if (priv->modulus <= 1) + return -ERANGE; + + if (priv->offset + priv->modulus - 1 < priv->offset) + return -EOVERFLOW; + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); +} + static int nft_jhash_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -110,6 +156,28 @@ static int nft_jhash_dump(struct sk_buff *skb, if (priv->offset != 0) if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static int nft_symhash_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_symhash *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) + goto nla_put_failure; + if (priv->offset != 0) + if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM))) + goto nla_put_failure; return 0; nla_put_failure: @@ -125,9 +193,38 @@ static const struct nft_expr_ops nft_jhash_ops = { .dump = nft_jhash_dump, }; +static const struct nft_expr_ops nft_symhash_ops = { + .type = &nft_hash_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), + .eval = nft_symhash_eval, + .init = nft_symhash_init, + .dump = nft_symhash_dump, +}; + +static const struct nft_expr_ops * +nft_hash_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + u32 type; + + if (!tb[NFTA_HASH_TYPE]) + return &nft_jhash_ops; + + type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE])); + switch (type) { + case NFT_HASH_SYM: + return &nft_symhash_ops; + case NFT_HASH_JENKINS: + return &nft_jhash_ops; + default: + break; + } + return ERR_PTR(-EOPNOTSUPP); +} + static struct nft_expr_type nft_hash_type __read_mostly = { .name = "hash", - .ops = &nft_jhash_ops, + .select_ops = &nft_hash_select_ops, .policy = nft_hash_policy, .maxattr = NFTA_HASH_MAX, .owner = THIS_MODULE, From 13fa745da251606fcdbf58acd6b4a551bea6ae99 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 28 Feb 2017 14:09:24 -0800 Subject: [PATCH 004/399] netfilter: Use pr_cont where appropriate Logging output was changed when simple printks without KERN_CONT are now emitted on a new line and KERN_CONT is required to continue lines so use pr_cont. Miscellanea: o realign arguments o use print_hex_dump instead of a local variant Signed-off-by: Joe Perches Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebt_log.c | 34 +++++++++++++------------- net/ipv4/netfilter/nf_nat_snmp_basic.c | 15 ++---------- 2 files changed, 19 insertions(+), 30 deletions(-) diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 98b9c8e8615e..707caea39743 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -62,10 +62,10 @@ print_ports(const struct sk_buff *skb, uint8_t protocol, int offset) pptr = skb_header_pointer(skb, offset, sizeof(_ports), &_ports); if (pptr == NULL) { - printk(" INCOMPLETE TCP/UDP header"); + pr_cont(" INCOMPLETE TCP/UDP header"); return; } - printk(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst)); + pr_cont(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst)); } } @@ -100,11 +100,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); if (ih == NULL) { - printk(" INCOMPLETE IP header"); + pr_cont(" INCOMPLETE IP header"); goto out; } - printk(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d", - &ih->saddr, &ih->daddr, ih->tos, ih->protocol); + pr_cont(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d", + &ih->saddr, &ih->daddr, ih->tos, ih->protocol); print_ports(skb, ih->protocol, ih->ihl*4); goto out; } @@ -120,11 +120,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); if (ih == NULL) { - printk(" INCOMPLETE IPv6 header"); + pr_cont(" INCOMPLETE IPv6 header"); goto out; } - printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d", - &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr); + pr_cont(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d", + &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr); nexthdr = ih->nexthdr; offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off); if (offset_ph == -1) @@ -142,12 +142,12 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL) { - printk(" INCOMPLETE ARP header"); + pr_cont(" INCOMPLETE ARP header"); goto out; } - printk(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d", - ntohs(ah->ar_hrd), ntohs(ah->ar_pro), - ntohs(ah->ar_op)); + pr_cont(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d", + ntohs(ah->ar_hrd), ntohs(ah->ar_pro), + ntohs(ah->ar_op)); /* If it's for Ethernet and the lengths are OK, * then log the ARP payload @@ -161,17 +161,17 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp); if (ap == NULL) { - printk(" INCOMPLETE ARP payload"); + pr_cont(" INCOMPLETE ARP payload"); goto out; } - printk(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4", - ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst); + pr_cont(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4", + ap->mac_src, ap->ip_src, + ap->mac_dst, ap->ip_dst); } } out: - printk("\n"); + pr_cont("\n"); spin_unlock_bh(&ebt_log_lock); - } static unsigned int diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index c9b52c361da2..ef49989c93b1 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -998,18 +998,6 @@ static unsigned char snmp_trap_decode(struct asn1_ctx *ctx, * *****************************************************************************/ -static void hex_dump(const unsigned char *buf, size_t len) -{ - size_t i; - - for (i = 0; i < len; i++) { - if (i && !(i % 16)) - printk("\n"); - printk("%02x ", *(buf + i)); - } - printk("\n"); -} - /* * Parse and mangle SNMP message according to mapping. * (And this is the fucking 'basic' method). @@ -1026,7 +1014,8 @@ static int snmp_parse_mangle(unsigned char *msg, struct snmp_object *obj; if (debug > 1) - hex_dump(msg, len); + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 16, 1, + msg, len, 0); asn1_open(&ctx, msg, len); From 74664cf286dc0d2bf6960293cb219e5f741ac92b Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 28 Feb 2017 11:31:15 +0000 Subject: [PATCH 005/399] netfilter: arp_tables: remove redundant check on ret being non-zero ret is initialized to zero and if it is set to non-zero in the xt_entry_foreach loop then we exit via the out_free label. Hence the check for ret being non-zero is redundant and can be removed. Detected by CoverityScan, CID#1357132 ("Logically Dead Code") Signed-off-by: Colin Ian King Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 6241a81fd7f5..f17dab1dee6e 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -562,8 +562,6 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } - if (ret != 0) - goto out_free; ret = -EINVAL; if (i != repl->num_entries) From c56e3956c17bb24d18470122c0513d963e332205 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 5 Mar 2017 21:02:23 +0800 Subject: [PATCH 006/399] netfilter: nf_tables: validate the expr explicitly after init successfully When we want to validate the expr's dependency or hooks, we must do two things to accomplish it. First, write a X_validate callback function and point ->validate to it. Second, call X_validate in init routine. This is very common, such as fib, nat, reject expr and so on ... It is a little ugly, since we will call X_validate in the expr's init routine, it's better to do it in nf_tables_newexpr. So we can avoid to do this again and again. After doing this, the second step listed above is not useful anymore, remove them now. Patch was tested by nftables/tests/py/nft-test.py and nftables/tests/shell/run-tests.sh. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/nft_reject_bridge.c | 6 +----- net/netfilter/nf_tables_api.c | 11 +++++++++++ net/netfilter/nft_compat.c | 8 -------- net/netfilter/nft_fib.c | 2 +- net/netfilter/nft_masq.c | 4 ---- net/netfilter/nft_meta.c | 4 ---- net/netfilter/nft_nat.c | 4 ---- net/netfilter/nft_redir.c | 4 ---- net/netfilter/nft_reject.c | 5 ----- net/netfilter/nft_reject_inet.c | 6 +----- 10 files changed, 14 insertions(+), 40 deletions(-) diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 206dc266ecd2..346ef6b00b8f 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -375,11 +375,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code, err; - - err = nft_reject_bridge_validate(ctx, expr, NULL); - if (err < 0) - return err; + int icmp_code; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5e0ccfd5bb37..fd8789eccc92 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1772,8 +1772,19 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx, goto err1; } + if (ops->validate) { + const struct nft_data *data = NULL; + + err = ops->validate(ctx, expr, &data); + if (err < 0) + goto err2; + } + return 0; +err2: + if (ops->destroy) + ops->destroy(ctx, expr); err1: expr->ops = NULL; return err; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index c21e7eb8dce0..fab6bf3f955e 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -230,10 +230,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, union nft_entry e = {}; int ret; - ret = nft_compat_chain_validate_dependency(target->table, ctx->chain); - if (ret < 0) - goto err; - target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info); if (ctx->nla[NFTA_RULE_COMPAT]) { @@ -419,10 +415,6 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, union nft_entry e = {}; int ret; - ret = nft_compat_chain_validate_dependency(match->table, ctx->chain); - if (ret < 0) - goto err; - match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info); if (ctx->nla[NFTA_RULE_COMPAT]) { diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 29a4906adc27..fd0b19303b0d 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -112,7 +112,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; - return nft_fib_validate(ctx, expr, NULL); + return 0; } EXPORT_SYMBOL_GPL(nft_fib_init); diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 11ce016cd479..6ac03d4266c9 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -46,10 +46,6 @@ int nft_masq_init(const struct nft_ctx *ctx, struct nft_masq *priv = nft_expr_priv(expr); int err; - err = nft_masq_validate(ctx, expr, NULL); - if (err) - return err; - if (tb[NFTA_MASQ_FLAGS]) { priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); if (priv->flags & ~NF_NAT_RANGE_MASK) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e1f5ca9b423b..d14417aaf5d4 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -370,10 +370,6 @@ int nft_meta_set_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nft_meta_set_validate(ctx, expr, NULL); - if (err < 0) - return err; - priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 19a7bf3236f9..26a74dfb3b7a 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -138,10 +138,6 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; } - err = nft_nat_validate(ctx, expr, NULL); - if (err < 0) - return err; - if (tb[NFTA_NAT_FAMILY] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 40dcd05146d5..1e66538bf0ff 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -47,10 +47,6 @@ int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - err = nft_redir_validate(ctx, expr, NULL); - if (err < 0) - return err; - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { priv->sreg_proto_min = diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index c64de3f7379d..29f5bd2377b0 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -42,11 +42,6 @@ int nft_reject_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int err; - - err = nft_reject_validate(ctx, expr, NULL); - if (err < 0) - return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 9e90a02cb104..5a7fb5ff867d 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -66,11 +66,7 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code, err; - - err = nft_reject_validate(ctx, expr, NULL); - if (err < 0) - return err; + int icmp_code; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; From c7a72e3fdb5d77486ca3a0ac942c0a2e0d80d5bb Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 6 Mar 2017 17:46:20 +0100 Subject: [PATCH 007/399] netfilter: nf_tables: add nft_set_lookup() This new function consolidates set lookup via either name or ID by introducing a new nft_set_lookup() function. Replace existing spots where we can use this too. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 9 +++++---- net/netfilter/nf_tables_api.c | 31 ++++++++++++++++++++++++------- net/netfilter/nft_dynset.c | 14 ++++---------- net/netfilter/nft_lookup.c | 14 ++++---------- net/netfilter/nft_objref.c | 14 ++++---------- 5 files changed, 41 insertions(+), 41 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2aa8a9d80fbe..f0d46726d06e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -385,10 +385,11 @@ static inline struct nft_set *nft_set_container_of(const void *priv) return (void *)priv - offsetof(struct nft_set, data); } -struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla, u8 genmask); -struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla, u8 genmask); +struct nft_set *nft_set_lookup(const struct net *net, + const struct nft_table *table, + const struct nlattr *nla_set_name, + const struct nlattr *nla_set_id, + u8 genmask); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fd8789eccc92..4559f5d66bcc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2534,8 +2534,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, return 0; } -struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +static struct nft_set *nf_tables_set_lookup(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_set *set; @@ -2549,11 +2549,10 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table, } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_set_lookup); -struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla, - u8 genmask) +static struct nft_set *nf_tables_set_lookup_byid(const struct net *net, + const struct nlattr *nla, + u8 genmask) { struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); @@ -2568,7 +2567,25 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net, } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_set_lookup_byid); + +struct nft_set *nft_set_lookup(const struct net *net, + const struct nft_table *table, + const struct nlattr *nla_set_name, + const struct nlattr *nla_set_id, + u8 genmask) +{ + struct nft_set *set; + + set = nf_tables_set_lookup(table, nla_set_name, genmask); + if (IS_ERR(set)) { + if (!nla_set_id) + return set; + + set = nf_tables_set_lookup_byid(net, nla_set_id, genmask); + } + return set; +} +EXPORT_SYMBOL_GPL(nft_set_lookup); static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, const char *name) diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 049ad2d9ee66..3948da380259 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -133,16 +133,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx, priv->invert = true; } - set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME], - genmask); - if (IS_ERR(set)) { - if (tb[NFTA_DYNSET_SET_ID]) - set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_DYNSET_SET_ID], - genmask); - if (IS_ERR(set)) - return PTR_ERR(set); - } + set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME], + tb[NFTA_DYNSET_SET_ID], genmask); + if (IS_ERR(set)) + return PTR_ERR(set); if (set->ops->update == NULL) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index e21aea7e5ec8..475570e89ede 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -71,16 +71,10 @@ static int nft_lookup_init(const struct nft_ctx *ctx, tb[NFTA_LOOKUP_SREG] == NULL) return -EINVAL; - set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET], genmask); - if (IS_ERR(set)) { - if (tb[NFTA_LOOKUP_SET_ID]) { - set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_LOOKUP_SET_ID], - genmask); - } - if (IS_ERR(set)) - return PTR_ERR(set); - } + set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET], + tb[NFTA_LOOKUP_SET_ID], genmask); + if (IS_ERR(set)) + return PTR_ERR(set); if (set->flags & NFT_SET_EVAL) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 1ae8c49ca4a1..1dd428fbaaa3 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -116,16 +116,10 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, struct nft_set *set; int err; - set = nf_tables_set_lookup(ctx->table, tb[NFTA_OBJREF_SET_NAME], genmask); - if (IS_ERR(set)) { - if (tb[NFTA_OBJREF_SET_ID]) { - set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_OBJREF_SET_ID], - genmask); - } - if (IS_ERR(set)) - return PTR_ERR(set); - } + set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME], + tb[NFTA_OBJREF_SET_ID], genmask); + if (IS_ERR(set)) + return PTR_ERR(set); if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; From df6f37225d62316f8505f10ef1099ee40fa3978b Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Wed, 22 Feb 2017 08:50:27 +0100 Subject: [PATCH 008/399] net: realtek: 8139cp: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/8139cp.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 672f6b696069..72233ab9474b 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -1406,27 +1406,29 @@ static int cp_get_sset_count (struct net_device *dev, int sset) } } -static int cp_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cp_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct cp_private *cp = netdev_priv(dev); int rc; unsigned long flags; spin_lock_irqsave(&cp->lock, flags); - rc = mii_ethtool_gset(&cp->mii_if, cmd); + rc = mii_ethtool_get_link_ksettings(&cp->mii_if, cmd); spin_unlock_irqrestore(&cp->lock, flags); return rc; } -static int cp_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cp_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct cp_private *cp = netdev_priv(dev); int rc; unsigned long flags; spin_lock_irqsave(&cp->lock, flags); - rc = mii_ethtool_sset(&cp->mii_if, cmd); + rc = mii_ethtool_set_link_ksettings(&cp->mii_if, cmd); spin_unlock_irqrestore(&cp->lock, flags); return rc; @@ -1578,8 +1580,6 @@ static const struct ethtool_ops cp_ethtool_ops = { .get_drvinfo = cp_get_drvinfo, .get_regs_len = cp_get_regs_len, .get_sset_count = cp_get_sset_count, - .get_settings = cp_get_settings, - .set_settings = cp_set_settings, .nway_reset = cp_nway_reset, .get_link = ethtool_op_get_link, .get_msglevel = cp_get_msglevel, @@ -1593,6 +1593,8 @@ static const struct ethtool_ops cp_ethtool_ops = { .get_eeprom = cp_get_eeprom, .set_eeprom = cp_set_eeprom, .get_ringparam = cp_get_ringparam, + .get_link_ksettings = cp_get_link_ksettings, + .set_link_ksettings = cp_set_link_ksettings, }; static int cp_ioctl (struct net_device *dev, struct ifreq *rq, int cmd) From 182ed075e3c706e5e272b0b0135c8d02df59572f Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 23 Feb 2017 00:14:08 +0100 Subject: [PATCH 009/399] net: realtek: 8139too: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/8139too.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 89631753e799..ca22f2898664 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2384,21 +2384,23 @@ static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo * strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info)); } -static int rtl8139_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8139_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8139_private *tp = netdev_priv(dev); spin_lock_irq(&tp->lock); - mii_ethtool_gset(&tp->mii, cmd); + mii_ethtool_get_link_ksettings(&tp->mii, cmd); spin_unlock_irq(&tp->lock); return 0; } -static int rtl8139_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8139_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct rtl8139_private *tp = netdev_priv(dev); int rc; spin_lock_irq(&tp->lock); - rc = mii_ethtool_sset(&tp->mii, cmd); + rc = mii_ethtool_set_link_ksettings(&tp->mii, cmd); spin_unlock_irq(&tp->lock); return rc; } @@ -2480,8 +2482,6 @@ static void rtl8139_get_strings(struct net_device *dev, u32 stringset, u8 *data) static const struct ethtool_ops rtl8139_ethtool_ops = { .get_drvinfo = rtl8139_get_drvinfo, - .get_settings = rtl8139_get_settings, - .set_settings = rtl8139_set_settings, .get_regs_len = rtl8139_get_regs_len, .get_regs = rtl8139_get_regs, .nway_reset = rtl8139_nway_reset, @@ -2493,6 +2493,8 @@ static const struct ethtool_ops rtl8139_ethtool_ops = { .get_strings = rtl8139_get_strings, .get_sset_count = rtl8139_get_sset_count, .get_ethtool_stats = rtl8139_get_ethtool_stats, + .get_link_ksettings = rtl8139_get_link_ksettings, + .set_link_ksettings = rtl8139_set_link_ksettings, }; static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) From 6fa1ba61520576cf1346c4ff09a056f2950cb3bf Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 23 Feb 2017 22:34:43 +0100 Subject: [PATCH 010/399] net: realtek: r8169: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 41 +++++++++++++++++----------- 1 file changed, 25 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 81f18a833527..24b045b777b6 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -817,7 +817,8 @@ struct rtl8169_private { } csi_ops; int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv); - int (*get_settings)(struct net_device *, struct ethtool_cmd *); + int (*get_link_ksettings)(struct net_device *, + struct ethtool_link_ksettings *); void (*phy_reset_enable)(struct rtl8169_private *tp); void (*hw_start)(struct net_device *); unsigned int (*phy_reset_pending)(struct rtl8169_private *tp); @@ -2115,41 +2116,49 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff)); } -static int rtl8169_gset_tbi(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8169_get_link_ksettings_tbi(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; u32 status; + u32 supported, advertising; - cmd->supported = + supported = SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE; - cmd->port = PORT_FIBRE; - cmd->transceiver = XCVR_INTERNAL; + cmd->base.port = PORT_FIBRE; status = RTL_R32(TBICSR); - cmd->advertising = (status & TBINwEnable) ? ADVERTISED_Autoneg : 0; - cmd->autoneg = !!(status & TBINwEnable); + advertising = (status & TBINwEnable) ? ADVERTISED_Autoneg : 0; + cmd->base.autoneg = !!(status & TBINwEnable); - ethtool_cmd_speed_set(cmd, SPEED_1000); - cmd->duplex = DUPLEX_FULL; /* Always set */ + cmd->base.speed = SPEED_1000; + cmd->base.duplex = DUPLEX_FULL; /* Always set */ + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int rtl8169_gset_xmii(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8169_get_link_ksettings_xmii(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); - return mii_ethtool_gset(&tp->mii, cmd); + return mii_ethtool_get_link_ksettings(&tp->mii, cmd); } -static int rtl8169_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8169_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); int rc; rtl_lock_work(tp); - rc = tp->get_settings(dev, cmd); + rc = tp->get_link_ksettings(dev, cmd); rtl_unlock_work(tp); return rc; @@ -2356,7 +2365,6 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { .get_drvinfo = rtl8169_get_drvinfo, .get_regs_len = rtl8169_get_regs_len, .get_link = ethtool_op_get_link, - .get_settings = rtl8169_get_settings, .set_settings = rtl8169_set_settings, .get_msglevel = rtl8169_get_msglevel, .set_msglevel = rtl8169_set_msglevel, @@ -2368,6 +2376,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { .get_ethtool_stats = rtl8169_get_ethtool_stats, .get_ts_info = ethtool_op_get_ts_info, .nway_reset = rtl8169_nway_reset, + .get_link_ksettings = rtl8169_get_link_ksettings, }; static void rtl8169_get_mac_version(struct rtl8169_private *tp, @@ -8351,14 +8360,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rtl_tbi_enabled(tp)) { tp->set_speed = rtl8169_set_speed_tbi; - tp->get_settings = rtl8169_gset_tbi; + tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi; tp->phy_reset_enable = rtl8169_tbi_reset_enable; tp->phy_reset_pending = rtl8169_tbi_reset_pending; tp->link_ok = rtl8169_tbi_link_ok; tp->do_ioctl = rtl_tbi_ioctl; } else { tp->set_speed = rtl8169_set_speed_xmii; - tp->get_settings = rtl8169_gset_xmii; + tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii; tp->phy_reset_enable = rtl8169_xmii_reset_enable; tp->phy_reset_pending = rtl8169_xmii_reset_pending; tp->link_ok = rtl8169_xmii_link_ok; From de48015054fa697f647826ecee94d8f34633809f Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 26 Feb 2017 19:00:29 +0100 Subject: [PATCH 011/399] net: rocker: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker_main.c | 55 +++++++++++++---------- 1 file changed, 32 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 0f63a44a955d..b712ec23075b 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -1115,7 +1115,7 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port, const struct rocker_desc_info *desc_info, void *priv) { - struct ethtool_cmd *ecmd = priv; + struct ethtool_link_ksettings *ecmd = priv; const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; u32 speed; @@ -1137,13 +1137,14 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port, duplex = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX]); autoneg = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG]); - ecmd->transceiver = XCVR_INTERNAL; - ecmd->supported = SUPPORTED_TP; - ecmd->phy_address = 0xff; - ecmd->port = PORT_TP; - ethtool_cmd_speed_set(ecmd, speed); - ecmd->duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF; - ecmd->autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE; + ethtool_link_ksettings_zero_link_mode(ecmd, supported); + ethtool_link_ksettings_add_link_mode(ecmd, supported, TP); + + ecmd->base.phy_address = 0xff; + ecmd->base.port = PORT_TP; + ecmd->base.speed = speed; + ecmd->base.duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF; + ecmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE; return 0; } @@ -1250,7 +1251,7 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) { - struct ethtool_cmd *ecmd = priv; + struct ethtool_link_ksettings *ecmd = priv; struct rocker_tlv *cmd_info; if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, @@ -1263,13 +1264,13 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port, rocker_port->pport)) return -EMSGSIZE; if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_SPEED, - ethtool_cmd_speed(ecmd))) + ecmd->base.speed)) return -EMSGSIZE; if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX, - ecmd->duplex)) + ecmd->base.duplex)) return -EMSGSIZE; if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG, - ecmd->autoneg)) + ecmd->base.autoneg)) return -EMSGSIZE; rocker_tlv_nest_end(desc_info, cmd_info); return 0; @@ -1347,8 +1348,9 @@ rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port, return 0; } -static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, - struct ethtool_cmd *ecmd) +static int +rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, + struct ethtool_link_ksettings *ecmd) { return rocker_cmd_exec(rocker_port, false, rocker_cmd_get_port_settings_prep, NULL, @@ -1373,12 +1375,17 @@ static int rocker_cmd_get_port_settings_mode(struct rocker_port *rocker_port, rocker_cmd_get_port_settings_mode_proc, p_mode); } -static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, - struct ethtool_cmd *ecmd) +static int +rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, + const struct ethtool_link_ksettings *ecmd) { + struct ethtool_link_ksettings copy_ecmd; + + memcpy(©_ecmd, ecmd, sizeof(copy_ecmd)); + return rocker_cmd_exec(rocker_port, false, rocker_cmd_set_port_settings_ethtool_prep, - ecmd, NULL, NULL); + ©_ecmd, NULL, NULL); } static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, @@ -2237,16 +2244,18 @@ static int rocker_router_fib_event(struct notifier_block *nb, * ethtool interface ********************/ -static int rocker_port_get_settings(struct net_device *dev, - struct ethtool_cmd *ecmd) +static int +rocker_port_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *ecmd) { struct rocker_port *rocker_port = netdev_priv(dev); return rocker_cmd_get_port_settings_ethtool(rocker_port, ecmd); } -static int rocker_port_set_settings(struct net_device *dev, - struct ethtool_cmd *ecmd) +static int +rocker_port_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *ecmd) { struct rocker_port *rocker_port = netdev_priv(dev); @@ -2388,13 +2397,13 @@ static int rocker_port_get_sset_count(struct net_device *netdev, int sset) } static const struct ethtool_ops rocker_port_ethtool_ops = { - .get_settings = rocker_port_get_settings, - .set_settings = rocker_port_set_settings, .get_drvinfo = rocker_port_get_drvinfo, .get_link = ethtool_op_get_link, .get_strings = rocker_port_get_strings, .get_ethtool_stats = rocker_port_get_stats, .get_sset_count = rocker_port_get_sset_count, + .get_link_ksettings = rocker_port_get_link_ksettings, + .set_link_ksettings = rocker_port_set_link_ksettings, }; /***************** From b61a26f8d495edea3795079c87b3e4ad8ee93e1c Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 26 Feb 2017 22:48:59 +0100 Subject: [PATCH 012/399] net: sgi: ioc3-eth: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sgi/ioc3-eth.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 57e6cef81ebe..52ead5524de7 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -1558,25 +1558,27 @@ static void ioc3_get_drvinfo (struct net_device *dev, strlcpy(info->bus_info, pci_name(ip->pdev), sizeof(info->bus_info)); } -static int ioc3_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ioc3_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct ioc3_private *ip = netdev_priv(dev); int rc; spin_lock_irq(&ip->ioc3_lock); - rc = mii_ethtool_gset(&ip->mii, cmd); + rc = mii_ethtool_get_link_ksettings(&ip->mii, cmd); spin_unlock_irq(&ip->ioc3_lock); return rc; } -static int ioc3_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ioc3_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct ioc3_private *ip = netdev_priv(dev); int rc; spin_lock_irq(&ip->ioc3_lock); - rc = mii_ethtool_sset(&ip->mii, cmd); + rc = mii_ethtool_set_link_ksettings(&ip->mii, cmd); spin_unlock_irq(&ip->ioc3_lock); return rc; @@ -1608,10 +1610,10 @@ static u32 ioc3_get_link(struct net_device *dev) static const struct ethtool_ops ioc3_ethtool_ops = { .get_drvinfo = ioc3_get_drvinfo, - .get_settings = ioc3_get_settings, - .set_settings = ioc3_set_settings, .nway_reset = ioc3_nway_reset, .get_link = ioc3_get_link, + .get_link_ksettings = ioc3_get_link_ksettings, + .set_link_ksettings = ioc3_set_link_ksettings, }; static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) From a972c3062f982c63525f20cbce00a6f329406c0a Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Mon, 27 Feb 2017 22:50:25 +0100 Subject: [PATCH 013/399] net: silan: sc92031: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/silan/sc92031.c | 83 ++++++++++++++++------------ 1 file changed, 47 insertions(+), 36 deletions(-) diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c index 6c2e2b311c16..751c81848f35 100644 --- a/drivers/net/ethernet/silan/sc92031.c +++ b/drivers/net/ethernet/silan/sc92031.c @@ -1122,14 +1122,16 @@ static void sc92031_poll_controller(struct net_device *dev) } #endif -static int sc92031_ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int +sc92031_ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct sc92031_priv *priv = netdev_priv(dev); void __iomem *port_base = priv->port_base; u8 phy_address; u32 phy_ctrl; u16 output_status; + u32 supported, advertising; spin_lock_bh(&priv->lock); @@ -1142,68 +1144,77 @@ static int sc92031_ethtool_get_settings(struct net_device *dev, spin_unlock_bh(&priv->lock); - cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full + supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII; - cmd->advertising = ADVERTISED_TP | ADVERTISED_MII; + advertising = ADVERTISED_TP | ADVERTISED_MII; if ((phy_ctrl & (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10)) == (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10)) - cmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; if ((phy_ctrl & PhyCtrlSpd10) == PhyCtrlSpd10) - cmd->advertising |= ADVERTISED_10baseT_Half; + advertising |= ADVERTISED_10baseT_Half; if ((phy_ctrl & (PhyCtrlSpd10 | PhyCtrlDux)) == (PhyCtrlSpd10 | PhyCtrlDux)) - cmd->advertising |= ADVERTISED_10baseT_Full; + advertising |= ADVERTISED_10baseT_Full; if ((phy_ctrl & PhyCtrlSpd100) == PhyCtrlSpd100) - cmd->advertising |= ADVERTISED_100baseT_Half; + advertising |= ADVERTISED_100baseT_Half; if ((phy_ctrl & (PhyCtrlSpd100 | PhyCtrlDux)) == (PhyCtrlSpd100 | PhyCtrlDux)) - cmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; if (phy_ctrl & PhyCtrlAne) - cmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; - ethtool_cmd_speed_set(cmd, - (output_status & 0x2) ? SPEED_100 : SPEED_10); - cmd->duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF; - cmd->port = PORT_MII; - cmd->phy_address = phy_address; - cmd->transceiver = XCVR_INTERNAL; - cmd->autoneg = (phy_ctrl & PhyCtrlAne) ? AUTONEG_ENABLE : AUTONEG_DISABLE; + cmd->base.speed = (output_status & 0x2) ? SPEED_100 : SPEED_10; + cmd->base.duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF; + cmd->base.port = PORT_MII; + cmd->base.phy_address = phy_address; + cmd->base.autoneg = (phy_ctrl & PhyCtrlAne) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int sc92031_ethtool_set_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int +sc92031_ethtool_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct sc92031_priv *priv = netdev_priv(dev); void __iomem *port_base = priv->port_base; - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; u32 phy_ctrl; u32 old_phy_ctrl; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); if (!(speed == SPEED_10 || speed == SPEED_100)) return -EINVAL; - if (!(cmd->duplex == DUPLEX_HALF || cmd->duplex == DUPLEX_FULL)) + if (!(cmd->base.duplex == DUPLEX_HALF || + cmd->base.duplex == DUPLEX_FULL)) return -EINVAL; - if (!(cmd->port == PORT_MII)) + if (!(cmd->base.port == PORT_MII)) return -EINVAL; - if (!(cmd->phy_address == 0x1f)) + if (!(cmd->base.phy_address == 0x1f)) return -EINVAL; - if (!(cmd->transceiver == XCVR_INTERNAL)) - return -EINVAL; - if (!(cmd->autoneg == AUTONEG_DISABLE || cmd->autoneg == AUTONEG_ENABLE)) + if (!(cmd->base.autoneg == AUTONEG_DISABLE || + cmd->base.autoneg == AUTONEG_ENABLE)) return -EINVAL; - if (cmd->autoneg == AUTONEG_ENABLE) { - if (!(cmd->advertising & (ADVERTISED_Autoneg + if (cmd->base.autoneg == AUTONEG_ENABLE) { + if (!(advertising & (ADVERTISED_Autoneg | ADVERTISED_100baseT_Full | ADVERTISED_100baseT_Half | ADVERTISED_10baseT_Full @@ -1213,15 +1224,15 @@ static int sc92031_ethtool_set_settings(struct net_device *dev, phy_ctrl = PhyCtrlAne; // FIXME: I'm not sure what the original code was trying to do - if (cmd->advertising & ADVERTISED_Autoneg) + if (advertising & ADVERTISED_Autoneg) phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10; - if (cmd->advertising & ADVERTISED_100baseT_Full) + if (advertising & ADVERTISED_100baseT_Full) phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100; - if (cmd->advertising & ADVERTISED_100baseT_Half) + if (advertising & ADVERTISED_100baseT_Half) phy_ctrl |= PhyCtrlSpd100; - if (cmd->advertising & ADVERTISED_10baseT_Full) + if (advertising & ADVERTISED_10baseT_Full) phy_ctrl |= PhyCtrlSpd10 | PhyCtrlDux; - if (cmd->advertising & ADVERTISED_10baseT_Half) + if (advertising & ADVERTISED_10baseT_Half) phy_ctrl |= PhyCtrlSpd10; } else { // FIXME: Whole branch guessed @@ -1232,7 +1243,7 @@ static int sc92031_ethtool_set_settings(struct net_device *dev, else /* cmd->speed == SPEED_100 */ phy_ctrl |= PhyCtrlSpd100; - if (cmd->duplex == DUPLEX_FULL) + if (cmd->base.duplex == DUPLEX_FULL) phy_ctrl |= PhyCtrlDux; } @@ -1368,8 +1379,6 @@ static void sc92031_ethtool_get_ethtool_stats(struct net_device *dev, } static const struct ethtool_ops sc92031_ethtool_ops = { - .get_settings = sc92031_ethtool_get_settings, - .set_settings = sc92031_ethtool_set_settings, .get_wol = sc92031_ethtool_get_wol, .set_wol = sc92031_ethtool_set_wol, .nway_reset = sc92031_ethtool_nway_reset, @@ -1377,6 +1386,8 @@ static const struct ethtool_ops sc92031_ethtool_ops = { .get_strings = sc92031_ethtool_get_strings, .get_sset_count = sc92031_ethtool_get_sset_count, .get_ethtool_stats = sc92031_ethtool_get_ethtool_stats, + .get_link_ksettings = sc92031_ethtool_get_link_ksettings, + .set_link_ksettings = sc92031_ethtool_set_link_ksettings, }; From fb70eb20fea66426aee0a21cfa35ab79d3d10e1c Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Mon, 27 Feb 2017 23:06:41 +0100 Subject: [PATCH 014/399] net: sis: sis190: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sis/sis190.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 210e35d079dd..02da106c6e04 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1734,18 +1734,20 @@ static void sis190_set_speed_auto(struct net_device *dev) BMCR_ANENABLE | BMCR_ANRESTART | BMCR_RESET); } -static int sis190_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int sis190_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct sis190_private *tp = netdev_priv(dev); - return mii_ethtool_gset(&tp->mii_if, cmd); + return mii_ethtool_get_link_ksettings(&tp->mii_if, cmd); } -static int sis190_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int sis190_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct sis190_private *tp = netdev_priv(dev); - return mii_ethtool_sset(&tp->mii_if, cmd); + return mii_ethtool_set_link_ksettings(&tp->mii_if, cmd); } static void sis190_get_drvinfo(struct net_device *dev, @@ -1797,8 +1799,6 @@ static void sis190_set_msglevel(struct net_device *dev, u32 value) } static const struct ethtool_ops sis190_ethtool_ops = { - .get_settings = sis190_get_settings, - .set_settings = sis190_set_settings, .get_drvinfo = sis190_get_drvinfo, .get_regs_len = sis190_get_regs_len, .get_regs = sis190_get_regs, @@ -1806,6 +1806,8 @@ static const struct ethtool_ops sis190_ethtool_ops = { .get_msglevel = sis190_get_msglevel, .set_msglevel = sis190_set_msglevel, .nway_reset = sis190_nway_reset, + .get_link_ksettings = sis190_get_link_ksettings, + .set_link_ksettings = sis190_set_link_ksettings, }; static int sis190_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) From 7d59e319d94f2cffaf5d9d3604bbd841baec933f Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Mon, 27 Feb 2017 23:17:37 +0100 Subject: [PATCH 015/399] net: sis: sis900: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sis/sis900.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 1b6f6171d078..40bd88362e3d 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -2035,23 +2035,23 @@ static u32 sis900_get_link(struct net_device *net_dev) return mii_link_ok(&sis_priv->mii_info); } -static int sis900_get_settings(struct net_device *net_dev, - struct ethtool_cmd *cmd) +static int sis900_get_link_ksettings(struct net_device *net_dev, + struct ethtool_link_ksettings *cmd) { struct sis900_private *sis_priv = netdev_priv(net_dev); spin_lock_irq(&sis_priv->lock); - mii_ethtool_gset(&sis_priv->mii_info, cmd); + mii_ethtool_get_link_ksettings(&sis_priv->mii_info, cmd); spin_unlock_irq(&sis_priv->lock); return 0; } -static int sis900_set_settings(struct net_device *net_dev, - struct ethtool_cmd *cmd) +static int sis900_set_link_ksettings(struct net_device *net_dev, + const struct ethtool_link_ksettings *cmd) { struct sis900_private *sis_priv = netdev_priv(net_dev); int rt; spin_lock_irq(&sis_priv->lock); - rt = mii_ethtool_sset(&sis_priv->mii_info, cmd); + rt = mii_ethtool_set_link_ksettings(&sis_priv->mii_info, cmd); spin_unlock_irq(&sis_priv->lock); return rt; } @@ -2129,11 +2129,11 @@ static const struct ethtool_ops sis900_ethtool_ops = { .get_msglevel = sis900_get_msglevel, .set_msglevel = sis900_set_msglevel, .get_link = sis900_get_link, - .get_settings = sis900_get_settings, - .set_settings = sis900_set_settings, .nway_reset = sis900_nway_reset, .get_wol = sis900_get_wol, - .set_wol = sis900_set_wol + .set_wol = sis900_set_wol, + .get_link_ksettings = sis900_get_link_ksettings, + .set_link_ksettings = sis900_set_link_ksettings, }; /** From 60269ae1b01e640aac8fc879aaf1e3dc98beb83b Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Mon, 27 Feb 2017 23:43:14 +0100 Subject: [PATCH 016/399] net: smsc: epic100: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/smsc/epic100.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 5f2737189c72..db6dcb06193d 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1387,25 +1387,27 @@ static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo * strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info)); } -static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct epic_private *np = netdev_priv(dev); int rc; spin_lock_irq(&np->lock); - rc = mii_ethtool_gset(&np->mii, cmd); + rc = mii_ethtool_get_link_ksettings(&np->mii, cmd); spin_unlock_irq(&np->lock); return rc; } -static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct epic_private *np = netdev_priv(dev); int rc; spin_lock_irq(&np->lock); - rc = mii_ethtool_sset(&np->mii, cmd); + rc = mii_ethtool_set_link_ksettings(&np->mii, cmd); spin_unlock_irq(&np->lock); return rc; @@ -1460,14 +1462,14 @@ static void ethtool_complete(struct net_device *dev) static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, - .get_settings = netdev_get_settings, - .set_settings = netdev_set_settings, .nway_reset = netdev_nway_reset, .get_link = netdev_get_link, .get_msglevel = netdev_get_msglevel, .set_msglevel = netdev_set_msglevel, .begin = ethtool_begin, - .complete = ethtool_complete + .complete = ethtool_complete, + .get_link_ksettings = netdev_get_link_ksettings, + .set_link_ksettings = netdev_set_link_ksettings, }; static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) From 88da73a3a5da989cc986a4b1f6a40e3292fc93d1 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Fri, 3 Mar 2017 23:39:35 +0100 Subject: [PATCH 017/399] net: smsc: smc91c92_cs: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/smsc/smc91c92_cs.c | 98 +++++++++++++------------ 1 file changed, 52 insertions(+), 46 deletions(-) diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c index 97280daba27f..976aa876789a 100644 --- a/drivers/net/ethernet/smsc/smc91c92_cs.c +++ b/drivers/net/ethernet/smsc/smc91c92_cs.c @@ -1843,56 +1843,60 @@ static int smc_link_ok(struct net_device *dev) } } -static int smc_netdev_get_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_netdev_get_ecmd(struct net_device *dev, + struct ethtool_link_ksettings *ecmd) { - u16 tmp; - unsigned int ioaddr = dev->base_addr; + u16 tmp; + unsigned int ioaddr = dev->base_addr; + u32 supported; - ecmd->supported = (SUPPORTED_TP | SUPPORTED_AUI | - SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full); - - SMC_SELECT_BANK(1); - tmp = inw(ioaddr + CONFIG); - ecmd->port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP; - ecmd->transceiver = XCVR_INTERNAL; - ethtool_cmd_speed_set(ecmd, SPEED_10); - ecmd->phy_address = ioaddr + MGMT; + supported = (SUPPORTED_TP | SUPPORTED_AUI | + SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full); - SMC_SELECT_BANK(0); - tmp = inw(ioaddr + TCR); - ecmd->duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF; + SMC_SELECT_BANK(1); + tmp = inw(ioaddr + CONFIG); + ecmd->base.port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP; + ecmd->base.speed = SPEED_10; + ecmd->base.phy_address = ioaddr + MGMT; - return 0; + SMC_SELECT_BANK(0); + tmp = inw(ioaddr + TCR); + ecmd->base.duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF; + + ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported, + supported); + + return 0; } -static int smc_netdev_set_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_netdev_set_ecmd(struct net_device *dev, + const struct ethtool_link_ksettings *ecmd) { - u16 tmp; - unsigned int ioaddr = dev->base_addr; + u16 tmp; + unsigned int ioaddr = dev->base_addr; - if (ethtool_cmd_speed(ecmd) != SPEED_10) - return -EINVAL; - if (ecmd->duplex != DUPLEX_HALF && ecmd->duplex != DUPLEX_FULL) - return -EINVAL; - if (ecmd->port != PORT_TP && ecmd->port != PORT_AUI) - return -EINVAL; - if (ecmd->transceiver != XCVR_INTERNAL) - return -EINVAL; + if (ecmd->base.speed != SPEED_10) + return -EINVAL; + if (ecmd->base.duplex != DUPLEX_HALF && + ecmd->base.duplex != DUPLEX_FULL) + return -EINVAL; + if (ecmd->base.port != PORT_TP && ecmd->base.port != PORT_AUI) + return -EINVAL; - if (ecmd->port == PORT_AUI) - smc_set_xcvr(dev, 1); - else - smc_set_xcvr(dev, 0); + if (ecmd->base.port == PORT_AUI) + smc_set_xcvr(dev, 1); + else + smc_set_xcvr(dev, 0); - SMC_SELECT_BANK(0); - tmp = inw(ioaddr + TCR); - if (ecmd->duplex == DUPLEX_FULL) - tmp |= TCR_FDUPLX; - else - tmp &= ~TCR_FDUPLX; - outw(tmp, ioaddr + TCR); - - return 0; + SMC_SELECT_BANK(0); + tmp = inw(ioaddr + TCR); + if (ecmd->base.duplex == DUPLEX_FULL) + tmp |= TCR_FDUPLX; + else + tmp &= ~TCR_FDUPLX; + outw(tmp, ioaddr + TCR); + + return 0; } static int check_if_running(struct net_device *dev) @@ -1908,7 +1912,8 @@ static void smc_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } -static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *ecmd) { struct smc_private *smc = netdev_priv(dev); unsigned int ioaddr = dev->base_addr; @@ -1919,7 +1924,7 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) spin_lock_irqsave(&smc->lock, flags); SMC_SELECT_BANK(3); if (smc->cfg & CFG_MII_SELECT) - ret = mii_ethtool_gset(&smc->mii_if, ecmd); + ret = mii_ethtool_get_link_ksettings(&smc->mii_if, ecmd); else ret = smc_netdev_get_ecmd(dev, ecmd); SMC_SELECT_BANK(saved_bank); @@ -1927,7 +1932,8 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) return ret; } -static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) +static int smc_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *ecmd) { struct smc_private *smc = netdev_priv(dev); unsigned int ioaddr = dev->base_addr; @@ -1938,7 +1944,7 @@ static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) spin_lock_irqsave(&smc->lock, flags); SMC_SELECT_BANK(3); if (smc->cfg & CFG_MII_SELECT) - ret = mii_ethtool_sset(&smc->mii_if, ecmd); + ret = mii_ethtool_set_link_ksettings(&smc->mii_if, ecmd); else ret = smc_netdev_set_ecmd(dev, ecmd); SMC_SELECT_BANK(saved_bank); @@ -1982,10 +1988,10 @@ static int smc_nway_reset(struct net_device *dev) static const struct ethtool_ops ethtool_ops = { .begin = check_if_running, .get_drvinfo = smc_get_drvinfo, - .get_settings = smc_get_settings, - .set_settings = smc_set_settings, .get_link = smc_get_link, .nway_reset = smc_nway_reset, + .get_link_ksettings = smc_get_link_ksettings, + .set_link_ksettings = smc_set_link_ksettings, }; static int smc_ioctl (struct net_device *dev, struct ifreq *rq, int cmd) From df789fe752065f2ce761ba434125e335b514899f Mon Sep 17 00:00:00 2001 From: David Forster Date: Thu, 23 Feb 2017 16:27:18 +0000 Subject: [PATCH 018/399] ipv6: Provide ipv6 version of "disable_policy" sysctl This provides equivalent functionality to the existing ipv4 "disable_policy" systcl. ie. Allows IPsec processing to be skipped on terminating packets on a per-interface basis. Signed-off-by: David Forster Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 114 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 116 insertions(+) diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 71be5b330d21..f0d79bd054ca 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -70,6 +70,7 @@ struct ipv6_devconf { #endif __u32 enhanced_dad; __u32 addr_gen_mode; + __s32 disable_policy; struct ctl_table_header *sysctl_header; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 8ef9e75e004e..d8f6a1ac9af4 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -183,6 +183,7 @@ enum { DEVCONF_SEG6_REQUIRE_HMAC, DEVCONF_ENHANCED_DAD, DEVCONF_ADDR_GEN_MODE, + DEVCONF_DISABLE_POLICY, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 363172527e43..8c69768a5c46 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -245,6 +245,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, + .disable_policy = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -297,6 +298,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, + .disable_policy = 0, }; /* Check if a valid qdisc is available */ @@ -944,6 +946,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, const struct in6_addr *peer_addr, int pfxlen, int scope, u32 flags, u32 valid_lft, u32 prefered_lft) { + struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; unsigned int hash; @@ -990,6 +993,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out; } + if (net->ipv6.devconf_all->disable_policy || + idev->cnf.disable_policy) + rt->dst.flags |= DST_NOPOLICY; + neigh_parms_data_state_setall(idev->nd_parms); ifa->addr = *addr; @@ -5003,6 +5010,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #endif array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; + array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; } static inline size_t inet6_ifla6_size(void) @@ -5827,6 +5835,105 @@ int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, return ret; } +static +void addrconf_set_nopolicy(struct rt6_info *rt, int action) +{ + if (rt) { + if (action) + rt->dst.flags |= DST_NOPOLICY; + else + rt->dst.flags &= ~DST_NOPOLICY; + } +} + +static +void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) +{ + struct inet6_ifaddr *ifa; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + spin_lock(&ifa->lock); + if (ifa->rt) { + struct rt6_info *rt = ifa->rt; + struct fib6_table *table = rt->rt6i_table; + int cpu; + + read_lock(&table->tb6_lock); + addrconf_set_nopolicy(ifa->rt, val); + if (rt->rt6i_pcpu) { + for_each_possible_cpu(cpu) { + struct rt6_info **rtp; + + rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu); + addrconf_set_nopolicy(*rtp, val); + } + } + read_unlock(&table->tb6_lock); + } + spin_unlock(&ifa->lock); + } + read_unlock_bh(&idev->lock); +} + +static +int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) +{ + struct inet6_dev *idev; + struct net *net; + + if (!rtnl_trylock()) + return restart_syscall(); + + *valp = val; + + net = (struct net *)ctl->extra2; + if (valp == &net->ipv6.devconf_dflt->disable_policy) { + rtnl_unlock(); + return 0; + } + + if (valp == &net->ipv6.devconf_all->disable_policy) { + struct net_device *dev; + + for_each_netdev(net, dev) { + idev = __in6_dev_get(dev); + if (idev) + addrconf_disable_policy_idev(idev, val); + } + } else { + idev = (struct inet6_dev *)ctl->extra1; + addrconf_disable_policy_idev(idev, val); + } + + rtnl_unlock(); + return 0; +} + +static +int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int *valp = ctl->data; + int val = *valp; + loff_t pos = *ppos; + struct ctl_table lctl; + int ret; + + lctl = *ctl; + lctl.data = &val; + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); + + if (write && (*valp != val)) + ret = addrconf_disable_policy(ctl, valp, val); + + if (ret) + *ppos = pos; + + return ret; +} + static int minus_one = -1; static const int one = 1; static const int two_five_five = 255; @@ -6184,6 +6291,13 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = addrconf_sysctl_addr_gen_mode, }, + { + .procname = "disable_policy", + .data = &ipv6_devconf.disable_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_disable_policy, + }, { /* sentinel */ } From 1a4691b204e75a853ec74947bed0dd6966558d29 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 24 Feb 2017 17:30:32 +0000 Subject: [PATCH 019/399] tools: hv: Add clean up function for Ubuntu config This patch adds a function to clean up duplicate config info on Ubuntu. Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- tools/hv/bondvf.sh | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh index 4aa5369ffa4e..d85968cb1bf2 100755 --- a/tools/hv/bondvf.sh +++ b/tools/hv/bondvf.sh @@ -101,9 +101,25 @@ function create_bond_cfg_redhat { echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn } +function del_eth_cfg_ubuntu { + local fn=$cfgdir/interfaces + local tmpfl=$(mktemp) + + local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1 + local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)' + + awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1" $fn >$tmpfl + + cp $tmpfl $fn + + rm $tmpfl +} + function create_eth_cfg_ubuntu { local fn=$cfgdir/interfaces + del_eth_cfg_ubuntu $1 + echo $'\n'auto $1 >>$fn echo iface $1 inet manual >>$fn echo bond-master $2 >>$fn @@ -119,6 +135,8 @@ function create_eth_cfg_pri_ubuntu { function create_bond_cfg_ubuntu { local fn=$cfgdir/interfaces + del_eth_cfg_ubuntu $1 + echo $'\n'auto $1 >>$fn echo iface $1 inet dhcp >>$fn echo bond-mode active-backup >>$fn From 50698d80f8bb1db989b7b9fa433f588fade5e382 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 27 Feb 2017 10:26:47 -0800 Subject: [PATCH 020/399] netvsc: don't overload variable in same function There are two variables named packet in the same function. One is the metadata descriptor from host (vmpacket_descriptor) and the other is the control block in the skb used to hold metadata from send. Change name to avoid possible confusion and bugs. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d35ebd993b38..5dedbc36c326 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -600,9 +600,9 @@ static inline void netvsc_free_send_slot(struct netvsc_device *net_device, static void netvsc_send_tx_complete(struct netvsc_device *net_device, struct vmbus_channel *incoming_channel, struct hv_device *device, - struct vmpacket_descriptor *packet) + const struct vmpacket_descriptor *desc) { - struct sk_buff *skb = (struct sk_buff *)(unsigned long)packet->trans_id; + struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id; struct net_device *ndev = hv_get_drvdata(device); struct net_device_context *net_device_ctx = netdev_priv(ndev); struct vmbus_channel *channel = device->channel; From f3dd3f4797652c311df9c074436d420f1ad3566e Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 27 Feb 2017 10:26:48 -0800 Subject: [PATCH 021/399] vmbus: introduce in-place packet iterator This is mostly just a refactoring of previous functions (get_pkt_next_raw, put_pkt_raw and commit_rd_index) to make it easier to use for other drivers and NAPI. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/hv/ring_buffer.c | 94 ++++++++++++++++++++++++++++++- drivers/net/hyperv/netvsc.c | 34 ++++-------- include/linux/hyperv.h | 108 ++++++++++++------------------------ 3 files changed, 139 insertions(+), 97 deletions(-) diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 87799e81af97..c3f1a9e33cef 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -32,6 +32,8 @@ #include "hyperv_vmbus.h" +#define VMBUS_PKT_TRAILER 8 + /* * When we write to the ring buffer, check if the host needs to * be signaled. Here is the details of this protocol: @@ -336,6 +338,12 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, return 0; } +static inline void +init_cached_read_index(struct hv_ring_buffer_info *rbi) +{ + rbi->cached_read_index = rbi->ring_buffer->read_index; +} + int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, u64 *requestid, bool raw) @@ -366,7 +374,8 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, return ret; } - init_cached_read_index(channel); + init_cached_read_index(inring_info); + next_read_location = hv_get_next_read_location(inring_info); next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc, sizeof(desc), @@ -410,3 +419,86 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, return ret; } + +/* + * Determine number of bytes available in ring buffer after + * the current iterator (priv_read_index) location. + * + * This is similar to hv_get_bytes_to_read but with private + * read index instead. + */ +static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) +{ + u32 priv_read_loc = rbi->priv_read_index; + u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index); + + if (write_loc >= priv_read_loc) + return write_loc - priv_read_loc; + else + return (rbi->ring_datasize - priv_read_loc) + write_loc; +} + +/* + * Get first vmbus packet from ring buffer after read_index + * + * If ring buffer is empty, returns NULL and no other action needed. + */ +struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + + /* set state for later hv_signal_on_read() */ + init_cached_read_index(rbi); + + if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) + return NULL; + + return hv_get_ring_buffer(rbi) + rbi->priv_read_index; +} +EXPORT_SYMBOL_GPL(hv_pkt_iter_first); + +/* + * Get next vmbus packet from ring buffer. + * + * Advances the current location (priv_read_index) and checks for more + * data. If the end of the ring buffer is reached, then return NULL. + */ +struct vmpacket_descriptor * +__hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *desc) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + u32 packetlen = desc->len8 << 3; + u32 dsize = rbi->ring_datasize; + + /* bump offset to next potential packet */ + rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER; + if (rbi->priv_read_index >= dsize) + rbi->priv_read_index -= dsize; + + /* more data? */ + if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) + return NULL; + else + return hv_get_ring_buffer(rbi) + rbi->priv_read_index; +} +EXPORT_SYMBOL_GPL(__hv_pkt_iter_next); + +/* + * Update host ring buffer after iterating over packets. + */ +void hv_pkt_iter_close(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + + /* + * Make sure all reads are done before we update the read index since + * the writer may start writing to the read area once the read index + * is updated. + */ + virt_rmb(); + rbi->ring_buffer->read_index = rbi->priv_read_index; + + hv_signal_on_read(channel); +} +EXPORT_SYMBOL_GPL(hv_pkt_iter_close); diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 5dedbc36c326..3681fb59bdbe 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -647,14 +647,11 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device, static void netvsc_send_completion(struct netvsc_device *net_device, struct vmbus_channel *incoming_channel, struct hv_device *device, - struct vmpacket_descriptor *packet) + const struct vmpacket_descriptor *desc) { - struct nvsp_message *nvsp_packet; + struct nvsp_message *nvsp_packet = hv_pkt_data(desc); struct net_device *ndev = hv_get_drvdata(device); - nvsp_packet = (struct nvsp_message *)((unsigned long)packet + - (packet->offset8 << 3)); - switch (nvsp_packet->hdr.msg_type) { case NVSP_MSG_TYPE_INIT_COMPLETE: case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE: @@ -668,7 +665,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device, case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE: netvsc_send_tx_complete(net_device, incoming_channel, - device, packet); + device, desc); break; default: @@ -1071,9 +1068,11 @@ static void netvsc_receive(struct net_device *ndev, struct net_device_context *net_device_ctx, struct hv_device *device, struct vmbus_channel *channel, - struct vmtransfer_page_packet_header *vmxferpage_packet, + const struct vmpacket_descriptor *desc, struct nvsp_message *nvsp) { + const struct vmtransfer_page_packet_header *vmxferpage_packet + = container_of(desc, const struct vmtransfer_page_packet_header, d); char *recv_buf = net_device->recv_buf; u32 status = NVSP_STAT_SUCCESS; int i; @@ -1185,12 +1184,10 @@ static void netvsc_process_raw_pkt(struct hv_device *device, struct netvsc_device *net_device, struct net_device *ndev, u64 request_id, - struct vmpacket_descriptor *desc) + const struct vmpacket_descriptor *desc) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - struct nvsp_message *nvmsg - = (struct nvsp_message *)((unsigned long)desc - + (desc->offset8 << 3)); + struct nvsp_message *nvmsg = hv_pkt_data(desc); switch (desc->type) { case VM_PKT_COMP: @@ -1199,9 +1196,7 @@ static void netvsc_process_raw_pkt(struct hv_device *device, case VM_PKT_DATA_USING_XFER_PAGES: netvsc_receive(ndev, net_device, net_device_ctx, - device, channel, - (struct vmtransfer_page_packet_header *)desc, - nvmsg); + device, channel, desc, nvmsg); break; case VM_PKT_DATA_INBAND: @@ -1223,7 +1218,6 @@ void netvsc_channel_cb(void *context) struct netvsc_device *net_device; struct vmpacket_descriptor *desc; struct net_device *ndev; - bool need_to_commit = false; if (channel->primary_channel != NULL) device = channel->primary_channel->device_obj; @@ -1239,20 +1233,12 @@ void netvsc_channel_cb(void *context) netvsc_channel_idle(net_device, q_idx)) return; - /* commit_rd_index() -> hv_signal_on_read() needs this. */ - init_cached_read_index(channel); - - while ((desc = get_next_pkt_raw(channel)) != NULL) { + foreach_vmbus_pkt(desc, channel) { netvsc_process_raw_pkt(device, channel, net_device, ndev, desc->trans_id, desc); - put_pkt_raw(channel, desc); - need_to_commit = true; } - if (need_to_commit) - commit_rd_index(channel); - netvsc_chk_recv_comp(net_device, channel, q_idx); } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 62bbf3c1aa4a..36162485d663 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1504,14 +1504,6 @@ static inline void hv_signal_on_read(struct vmbus_channel *channel) return; } -static inline void -init_cached_read_index(struct vmbus_channel *channel) -{ - struct hv_ring_buffer_info *rbi = &channel->inbound; - - rbi->cached_read_index = rbi->ring_buffer->read_index; -} - /* * Mask off host interrupt callback notifications */ @@ -1545,76 +1537,48 @@ static inline u32 hv_end_read(struct hv_ring_buffer_info *rbi) /* * An API to support in-place processing of incoming VMBUS packets. */ -#define VMBUS_PKT_TRAILER 8 +/* Get data payload associated with descriptor */ +static inline void *hv_pkt_data(const struct vmpacket_descriptor *desc) +{ + return (void *)((unsigned long)desc + (desc->offset8 << 3)); +} + +/* Get data size associated with descriptor */ +static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) +{ + return (desc->len8 << 3) - (desc->offset8 << 3); +} + + +struct vmpacket_descriptor * +hv_pkt_iter_first(struct vmbus_channel *channel); + +struct vmpacket_descriptor * +__hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt); + +void hv_pkt_iter_close(struct vmbus_channel *channel); + +/* + * Get next packet descriptor from iterator + * If at end of list, return NULL and update host. + */ static inline struct vmpacket_descriptor * -get_next_pkt_raw(struct vmbus_channel *channel) +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) { - struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 priv_read_loc = ring_info->priv_read_index; - void *ring_buffer = hv_get_ring_buffer(ring_info); - u32 dsize = ring_info->ring_datasize; - /* - * delta is the difference between what is available to read and - * what was already consumed in place. We commit read index after - * the whole batch is processed. - */ - u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ? - priv_read_loc - ring_info->ring_buffer->read_index : - (dsize - ring_info->ring_buffer->read_index) + priv_read_loc; - u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta); + struct vmpacket_descriptor *nxt; - if (bytes_avail_toread < sizeof(struct vmpacket_descriptor)) - return NULL; + nxt = __hv_pkt_iter_next(channel, pkt); + if (!nxt) + hv_pkt_iter_close(channel); - return ring_buffer + priv_read_loc; -} - -/* - * A helper function to step through packets "in-place" - * This API is to be called after each successful call - * get_next_pkt_raw(). - */ -static inline void put_pkt_raw(struct vmbus_channel *channel, - struct vmpacket_descriptor *desc) -{ - struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 packetlen = desc->len8 << 3; - u32 dsize = ring_info->ring_datasize; - - /* - * Include the packet trailer. - */ - ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER; - ring_info->priv_read_index %= dsize; -} - -/* - * This call commits the read index and potentially signals the host. - * Here is the pattern for using the "in-place" consumption APIs: - * - * init_cached_read_index(); - * - * while (get_next_pkt_raw() { - * process the packet "in-place"; - * put_pkt_raw(); - * } - * if (packets processed in place) - * commit_rd_index(); - */ -static inline void commit_rd_index(struct vmbus_channel *channel) -{ - struct hv_ring_buffer_info *ring_info = &channel->inbound; - /* - * Make sure all reads are done before we update the read index since - * the writer may start writing to the read area once the read index - * is updated. - */ - virt_rmb(); - ring_info->ring_buffer->read_index = ring_info->priv_read_index; - - hv_signal_on_read(channel); + return nxt; } +#define foreach_vmbus_pkt(pkt, channel) \ + for (pkt = hv_pkt_iter_first(channel); pkt; \ + pkt = hv_pkt_iter_next(channel, pkt)) #endif /* _HYPERV_H */ From 15a863bf7436124e799ba175a801e25f7b57191e Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 27 Feb 2017 10:26:49 -0800 Subject: [PATCH 022/399] netvsc: implement NAPI Use NAPI (softirq), to handle receive packets and send completions. Previously this was handled by tasklet. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/hyperv_net.h | 2 + drivers/net/hyperv/netvsc.c | 140 +++++++++++++++++++++--------- drivers/net/hyperv/netvsc_drv.c | 5 -- drivers/net/hyperv/rndis_filter.c | 2 + 4 files changed, 102 insertions(+), 47 deletions(-) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index d3e73ac158ae..7433b164e513 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -196,6 +196,7 @@ int netvsc_recv_callback(struct net_device *net, const struct ndis_tcp_ip_checksum_info *csum_info, const struct ndis_pkt_8021q_info *vlan); void netvsc_channel_cb(void *context); +int netvsc_poll(struct napi_struct *napi, int budget); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); int rndis_filter_device_add(struct hv_device *dev, @@ -720,6 +721,7 @@ struct net_device_context { /* Per channel data */ struct netvsc_channel { struct vmbus_channel *channel; + struct napi_struct napi; struct multi_send_data msd; struct multi_recv_comp mrc; atomic_t queue_sends; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 3681fb59bdbe..b1328cef9d5a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -556,6 +556,7 @@ void netvsc_device_remove(struct hv_device *device) struct net_device *ndev = hv_get_drvdata(device); struct net_device_context *net_device_ctx = netdev_priv(ndev); struct netvsc_device *net_device = net_device_ctx->nvdev; + int i; netvsc_disconnect_vsp(device); @@ -570,6 +571,9 @@ void netvsc_device_remove(struct hv_device *device) /* Now, we can close the channel safely */ vmbus_close(device->channel); + for (i = 0; i < VRSS_CHANNEL_MAX; i++) + napi_disable(&net_device->chan_table[0].napi); + /* Release all resources */ free_netvsc_device(net_device); } @@ -1063,7 +1067,7 @@ static inline struct recv_comp_data *get_recv_comp_slot( return rcd; } -static void netvsc_receive(struct net_device *ndev, +static int netvsc_receive(struct net_device *ndev, struct netvsc_device *net_device, struct net_device_context *net_device_ctx, struct hv_device *device, @@ -1073,20 +1077,19 @@ static void netvsc_receive(struct net_device *ndev, { const struct vmtransfer_page_packet_header *vmxferpage_packet = container_of(desc, const struct vmtransfer_page_packet_header, d); + u16 q_idx = channel->offermsg.offer.sub_channel_index; char *recv_buf = net_device->recv_buf; u32 status = NVSP_STAT_SUCCESS; int i; int count = 0; int ret; - struct recv_comp_data *rcd; - u16 q_idx = channel->offermsg.offer.sub_channel_index; /* Make sure this is a valid nvsp packet */ if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) { netif_err(net_device_ctx, rx_err, ndev, "Unknown nvsp packet type received %u\n", nvsp->hdr.msg_type); - return; + return 0; } if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) { @@ -1094,7 +1097,7 @@ static void netvsc_receive(struct net_device *ndev, "Invalid xfer page set id - expecting %x got %x\n", NETVSC_RECEIVE_BUFFER_ID, vmxferpage_packet->xfer_pageset_id); - return; + return 0; } count = vmxferpage_packet->range_cnt; @@ -1110,26 +1113,26 @@ static void netvsc_receive(struct net_device *ndev, channel, data, buflen); } - if (!net_device->chan_table[q_idx].mrc.buf) { + if (net_device->chan_table[q_idx].mrc.buf) { + struct recv_comp_data *rcd; + + rcd = get_recv_comp_slot(net_device, channel, q_idx); + if (rcd) { + rcd->tid = vmxferpage_packet->d.trans_id; + rcd->status = status; + } else { + netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n", + q_idx, vmxferpage_packet->d.trans_id); + } + } else { ret = netvsc_send_recv_completion(channel, vmxferpage_packet->d.trans_id, status); if (ret) netdev_err(ndev, "Recv_comp q:%hd, tid:%llx, err:%d\n", q_idx, vmxferpage_packet->d.trans_id, ret); - return; } - - rcd = get_recv_comp_slot(net_device, channel, q_idx); - - if (!rcd) { - netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n", - q_idx, vmxferpage_packet->d.trans_id); - return; - } - - rcd->tid = vmxferpage_packet->d.trans_id; - rcd->status = status; + return count; } static void netvsc_send_table(struct hv_device *hdev, @@ -1179,12 +1182,12 @@ static inline void netvsc_receive_inband(struct hv_device *hdev, } } -static void netvsc_process_raw_pkt(struct hv_device *device, - struct vmbus_channel *channel, - struct netvsc_device *net_device, - struct net_device *ndev, - u64 request_id, - const struct vmpacket_descriptor *desc) +static int netvsc_process_raw_pkt(struct hv_device *device, + struct vmbus_channel *channel, + struct netvsc_device *net_device, + struct net_device *ndev, + u64 request_id, + const struct vmpacket_descriptor *desc) { struct net_device_context *net_device_ctx = netdev_priv(ndev); struct nvsp_message *nvmsg = hv_pkt_data(desc); @@ -1195,8 +1198,8 @@ static void netvsc_process_raw_pkt(struct hv_device *device, break; case VM_PKT_DATA_USING_XFER_PAGES: - netvsc_receive(ndev, net_device, net_device_ctx, - device, channel, desc, nvmsg); + return netvsc_receive(ndev, net_device, net_device_ctx, + device, channel, desc, nvmsg); break; case VM_PKT_DATA_INBAND: @@ -1208,22 +1211,64 @@ static void netvsc_process_raw_pkt(struct hv_device *device, desc->type, request_id); break; } + + return 0; +} + +static struct hv_device *netvsc_channel_to_device(struct vmbus_channel *channel) +{ + struct vmbus_channel *primary = channel->primary_channel; + + return primary ? primary->device_obj : channel->device_obj; +} + +int netvsc_poll(struct napi_struct *napi, int budget) +{ + struct netvsc_channel *nvchan + = container_of(napi, struct netvsc_channel, napi); + struct vmbus_channel *channel = nvchan->channel; + struct hv_device *device = netvsc_channel_to_device(channel); + u16 q_idx = channel->offermsg.offer.sub_channel_index; + struct net_device *ndev = hv_get_drvdata(device); + struct netvsc_device *net_device = net_device_to_netvsc_device(ndev); + const struct vmpacket_descriptor *desc; + int work_done = 0; + + desc = hv_pkt_iter_first(channel); + while (desc) { + int count; + + count = netvsc_process_raw_pkt(device, channel, net_device, + ndev, desc->trans_id, desc); + work_done += count; + desc = __hv_pkt_iter_next(channel, desc); + + /* If receive packet budget is exhausted, reschedule */ + if (work_done >= budget) { + work_done = budget; + break; + } + } + hv_pkt_iter_close(channel); + + /* If ring is empty and NAPI is not doing polling */ + if (work_done < budget && + napi_complete_done(napi, work_done) && + hv_end_read(&channel->inbound) != 0) + napi_reschedule(napi); + + netvsc_chk_recv_comp(net_device, channel, q_idx); + return work_done; } void netvsc_channel_cb(void *context) { struct vmbus_channel *channel = context; + struct hv_device *device = netvsc_channel_to_device(channel); u16 q_idx = channel->offermsg.offer.sub_channel_index; - struct hv_device *device; struct netvsc_device *net_device; - struct vmpacket_descriptor *desc; struct net_device *ndev; - if (channel->primary_channel != NULL) - device = channel->primary_channel->device_obj; - else - device = channel->device_obj; - ndev = hv_get_drvdata(device); if (unlikely(!ndev)) return; @@ -1233,13 +1278,9 @@ void netvsc_channel_cb(void *context) netvsc_channel_idle(net_device, q_idx)) return; - foreach_vmbus_pkt(desc, channel) { - netvsc_process_raw_pkt(device, channel, net_device, - ndev, desc->trans_id, desc); - - } - - netvsc_chk_recv_comp(net_device, channel, q_idx); + /* disable interupts from host */ + hv_begin_read(&channel->inbound); + napi_schedule(&net_device->chan_table[q_idx].napi); } /* @@ -1261,6 +1302,11 @@ int netvsc_device_add(struct hv_device *device, net_device->ring_size = ring_size; + /* Because the device uses NAPI, all the interrupt batching and + * control is done via Net softirq, not the channel handling + */ + set_channel_read_mode(device->channel, HV_CALL_ISR); + /* Open the channel */ ret = vmbus_open(device->channel, ring_size * PAGE_SIZE, ring_size * PAGE_SIZE, NULL, 0, @@ -1278,8 +1324,16 @@ int netvsc_device_add(struct hv_device *device, * chn_table with the default channel to use it before subchannels are * opened. */ - for (i = 0; i < VRSS_CHANNEL_MAX; i++) - net_device->chan_table[i].channel = device->channel; + for (i = 0; i < VRSS_CHANNEL_MAX; i++) { + struct netvsc_channel *nvchan = &net_device->chan_table[i]; + + nvchan->channel = device->channel; + netif_napi_add(ndev, &nvchan->napi, + netvsc_poll, NAPI_POLL_WEIGHT); + } + + /* Enable NAPI handler for init callbacks */ + napi_enable(&net_device->chan_table[0].napi); /* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is * populated. @@ -1299,6 +1353,8 @@ int netvsc_device_add(struct hv_device *device, return ret; close: + napi_disable(&net_device->chan_table[0].napi); + /* Now, we can close the channel safely */ vmbus_close(device->channel); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index bc05c895d958..65d738b783cb 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -690,11 +690,6 @@ int netvsc_recv_callback(struct net_device *net, ++rx_stats->multicast; u64_stats_update_end(&rx_stats->syncp); - /* - * Pass the skb back up. Network stack will deallocate the skb when it - * is done. - * TODO - use NAPI? - */ netif_receive_skb(skb); rcu_read_unlock(); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 19356f56b7b1..d7b6311e6c19 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1012,6 +1012,8 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) if (ret == 0) nvscdev->chan_table[chn_index].channel = new_sc; + napi_enable(&nvscdev->chan_table[chn_index].napi); + spin_lock_irqsave(&nvscdev->sc_lock, flags); nvscdev->num_sc_offered--; spin_unlock_irqrestore(&nvscdev->sc_lock, flags); From 742fe54c7b03c83ce8067822a8739a4091c319ed Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 27 Feb 2017 10:26:50 -0800 Subject: [PATCH 023/399] netvsc: enable GRO Use GRO when receiving packets. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc_drv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 65d738b783cb..1345f34b6baf 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -642,11 +642,11 @@ int netvsc_recv_callback(struct net_device *net, { struct net_device_context *net_device_ctx = netdev_priv(net); struct netvsc_device *net_device = net_device_ctx->nvdev; + u16 q_idx = channel->offermsg.offer.sub_channel_index; + struct netvsc_channel *nvchan = &net_device->chan_table[q_idx]; struct net_device *vf_netdev; struct sk_buff *skb; struct netvsc_stats *rx_stats; - u16 q_idx = channel->offermsg.offer.sub_channel_index; - if (net->reg_state != NETREG_REGISTERED) return NVSP_STAT_FAIL; @@ -679,7 +679,7 @@ int netvsc_recv_callback(struct net_device *net, * on the synthetic device because modifying the VF device * statistics will not work correctly. */ - rx_stats = &net_device->chan_table[q_idx].rx_stats; + rx_stats = &nvchan->rx_stats; u64_stats_update_begin(&rx_stats->syncp); rx_stats->packets++; rx_stats->bytes += len; @@ -690,7 +690,7 @@ int netvsc_recv_callback(struct net_device *net, ++rx_stats->multicast; u64_stats_update_end(&rx_stats->syncp); - netif_receive_skb(skb); + napi_gro_receive(&nvchan->napi, skb); rcu_read_unlock(); return 0; From e91e7dd71dedbf4508513c8a66212248a853ecbe Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 27 Feb 2017 10:26:51 -0800 Subject: [PATCH 024/399] netvsc: replace netdev_alloc_skb_ip_align with napi_alloc_skb Gives potential performance gain. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc_drv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 1345f34b6baf..617dd90803c9 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -589,13 +589,14 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj, } static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, + struct napi_struct *napi, const struct ndis_tcp_ip_checksum_info *csum_info, const struct ndis_pkt_8021q_info *vlan, void *data, u32 buflen) { struct sk_buff *skb; - skb = netdev_alloc_skb_ip_align(net, buflen); + skb = napi_alloc_skb(napi, buflen); if (!skb) return skb; @@ -664,7 +665,8 @@ int netvsc_recv_callback(struct net_device *net, net = vf_netdev; /* Allocate a skb - TODO direct I/O to pages? */ - skb = netvsc_alloc_recv_skb(net, csum_info, vlan, data, len); + skb = netvsc_alloc_recv_skb(net, &nvchan->napi, + csum_info, vlan, data, len); if (unlikely(!skb)) { ++net->stats.rx_dropped; rcu_read_unlock(); From 452349c3235252aaccaf30cc75402827d43b72d4 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 28 Feb 2017 12:21:12 +0100 Subject: [PATCH 025/399] net: axienet: use eth_hw_addr_random() Use eth_hw_addr_random() to set a random MAC address in order to make sure ndev->addr_assign_type will be properly set to NET_ADDR_RANDOM. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index b96e96919e31..33c595f4691d 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -301,7 +301,7 @@ static void axienet_set_mac_address(struct net_device *ndev, if (address) memcpy(ndev->dev_addr, address, ETH_ALEN); if (!is_valid_ether_addr(ndev->dev_addr)) - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); /* Set up unicast MAC address filter set its mac address */ axienet_iow(lp, XAE_UAW0_OFFSET, From 02083c3aeda7b5fab49920b7fd9277b2c9ec50a9 Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Tue, 28 Feb 2017 13:50:59 -0500 Subject: [PATCH 026/399] net: ethernet: bgmac: use #defines for MAX size The maximum frame size is really just the standard ethernet frame size and FCS. So use those existing defines to make the code a little more beautiful. Signed-off-by: Jon Mason Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bgmac.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index 6d1c6ff1ed96..a75ed3538e5c 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -402,7 +402,7 @@ #define BGMAC_WEIGHT 64 -#define ETHER_MAX_LEN 1518 +#define ETHER_MAX_LEN (ETH_FRAME_LEN + ETH_FCS_LEN) /* Feature Flags */ #define BGMAC_FEAT_TX_MASK_SETUP BIT(0) From cb1b0f90acfedd2164e524b327d9e60b097646cc Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Tue, 28 Feb 2017 13:51:00 -0500 Subject: [PATCH 027/399] net: ethernet: bgmac: unify code of the same family BCM471X and BCM535X are of the same family (from what I can derive from internal documents). Group them into the case statement together, which results in more code reuse. Also, use existing helper variables to make the code a little more readable too. Signed-off-by: Jon Mason Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bgmac-bcma.c | 76 ++++++++++------------ 1 file changed, 34 insertions(+), 42 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index d59cfcc4c4d5..cf15b7e2929c 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -192,48 +192,16 @@ static int bgmac_probe(struct bcma_device *core) goto err1; } - bgmac->has_robosw = !!(core->bus->sprom.boardflags_lo & - BGMAC_BFL_ENETROBO); + bgmac->has_robosw = !!(sprom->boardflags_lo & BGMAC_BFL_ENETROBO); if (bgmac->has_robosw) dev_warn(bgmac->dev, "Support for Roboswitch not implemented\n"); - if (core->bus->sprom.boardflags_lo & BGMAC_BFL_ENETADM) + if (sprom->boardflags_lo & BGMAC_BFL_ENETADM) dev_warn(bgmac->dev, "Support for ADMtek ethernet switch not implemented\n"); /* Feature Flags */ - switch (core->bus->chipinfo.id) { - case BCMA_CHIP_ID_BCM5357: - bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; - bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47186) { - bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; - } - if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM5358) - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII; - break; - case BCMA_CHIP_ID_BCM53572: - bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; - bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47188) { - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; - bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; - } - break; - case BCMA_CHIP_ID_BCM4749: - bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; - bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (core->bus->chipinfo.pkg == 10) { - bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; - bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; - } - break; + switch (ci->id) { + /* BCM 471X/535X family */ case BCMA_CHIP_ID_BCM4716: bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; /* fallthrough */ @@ -241,13 +209,19 @@ static int bgmac_probe(struct bcma_device *core) bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2; bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; break; - /* bcm4707_family */ - case BCMA_CHIP_ID_BCM4707: - case BCMA_CHIP_ID_BCM47094: - case BCMA_CHIP_ID_BCM53018: + case BCMA_CHIP_ID_BCM5357: + case BCMA_CHIP_ID_BCM53572: + bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; - bgmac->feature_flags |= BGMAC_FEAT_NO_RESET; - bgmac->feature_flags |= BGMAC_FEAT_FORCE_SPEED_2500; + bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; + bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; + if (ci->pkg == BCMA_PKG_ID_BCM47188 || + ci->pkg == BCMA_PKG_ID_BCM47186) { + bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; + bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; + } + if (ci->pkg == BCMA_PKG_ID_BCM5358) + bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII; break; case BCMA_CHIP_ID_BCM53573: bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; @@ -264,6 +238,24 @@ static int bgmac_probe(struct bcma_device *core) bgmac->feature_flags |= BGMAC_FEAT_CC7_IF_TYPE_RGMII; } break; + case BCMA_CHIP_ID_BCM4749: + bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; + bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; + bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; + bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; + if (ci->pkg == 10) { + bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; + bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; + } + break; + /* bcm4707_family */ + case BCMA_CHIP_ID_BCM4707: + case BCMA_CHIP_ID_BCM47094: + case BCMA_CHIP_ID_BCM53018: + bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; + bgmac->feature_flags |= BGMAC_FEAT_NO_RESET; + bgmac->feature_flags |= BGMAC_FEAT_FORCE_SPEED_2500; + break; default: bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK; From f3537b3494c06a98a8636c375b6d7a5060c5ac2d Mon Sep 17 00:00:00 2001 From: Joey Zhong Date: Tue, 28 Feb 2017 13:51:01 -0500 Subject: [PATCH 028/399] net: ethernet: bgmac: driver power manangement Implement suspend/resume callbacks in the bgmac driver. This makes sure that we de-initialize and re-initialize the hardware correctly before entering suspend and when resuming. Signed-off-by: Joey Zhong Signed-off-by: Jon Mason Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bgmac-platform.c | 34 +++++++++++++ drivers/net/ethernet/broadcom/bgmac.c | 51 +++++++++++++++++++ drivers/net/ethernet/broadcom/bgmac.h | 2 + 3 files changed, 87 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index da1b8b225eb9..73aca97a96bc 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -21,8 +21,12 @@ #include #include "bgmac.h" +#define NICPM_PADRING_CFG 0x00000004 #define NICPM_IOMUX_CTRL 0x00000008 +#define NICPM_PADRING_CFG_INIT_VAL 0x74000000 +#define NICPM_IOMUX_CTRL_INIT_VAL_AX 0x21880000 + #define NICPM_IOMUX_CTRL_INIT_VAL 0x3196e000 #define NICPM_IOMUX_CTRL_SPD_SHIFT 10 #define NICPM_IOMUX_CTRL_SPD_10M 0 @@ -113,6 +117,10 @@ static void bgmac_nicpm_speed_set(struct net_device *net_dev) if (!bgmac->plat.nicpm_base) return; + /* SET RGMII IO CONFIG */ + writel(NICPM_PADRING_CFG_INIT_VAL, + bgmac->plat.nicpm_base + NICPM_PADRING_CFG); + val = NICPM_IOMUX_CTRL_INIT_VAL; switch (bgmac->net_dev->phydev->speed) { default: @@ -244,6 +252,31 @@ static int bgmac_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM +static int bgmac_suspend(struct device *dev) +{ + struct bgmac *bgmac = dev_get_drvdata(dev); + + return bgmac_enet_suspend(bgmac); +} + +static int bgmac_resume(struct device *dev) +{ + struct bgmac *bgmac = dev_get_drvdata(dev); + + return bgmac_enet_resume(bgmac); +} + +static const struct dev_pm_ops bgmac_pm_ops = { + .suspend = bgmac_suspend, + .resume = bgmac_resume +}; + +#define BGMAC_PM_OPS (&bgmac_pm_ops) +#else +#define BGMAC_PM_OPS NULL +#endif /* CONFIG_PM */ + static const struct of_device_id bgmac_of_enet_match[] = { {.compatible = "brcm,amac",}, {.compatible = "brcm,nsp-amac",}, @@ -257,6 +290,7 @@ static struct platform_driver bgmac_enet_driver = { .driver = { .name = "bgmac-enet", .of_match_table = bgmac_of_enet_match, + .pm = BGMAC_PM_OPS }, .probe = bgmac_probe, .remove = bgmac_remove, diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index fd66fca00e01..e1a24ee6ab8b 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1480,6 +1480,7 @@ int bgmac_enet_probe(struct bgmac *bgmac) net_dev->irq = bgmac->irq; SET_NETDEV_DEV(net_dev, bgmac->dev); + dev_set_drvdata(bgmac->dev, bgmac); if (!is_valid_ether_addr(net_dev->dev_addr)) { dev_err(bgmac->dev, "Invalid MAC addr: %pM\n", @@ -1552,5 +1553,55 @@ void bgmac_enet_remove(struct bgmac *bgmac) } EXPORT_SYMBOL_GPL(bgmac_enet_remove); +int bgmac_enet_suspend(struct bgmac *bgmac) +{ + if (!netif_running(bgmac->net_dev)) + return 0; + + phy_stop(bgmac->net_dev->phydev); + + netif_stop_queue(bgmac->net_dev); + + napi_disable(&bgmac->napi); + + netif_tx_lock(bgmac->net_dev); + netif_device_detach(bgmac->net_dev); + netif_tx_unlock(bgmac->net_dev); + + bgmac_chip_intrs_off(bgmac); + bgmac_chip_reset(bgmac); + bgmac_dma_cleanup(bgmac); + + return 0; +} +EXPORT_SYMBOL_GPL(bgmac_enet_suspend); + +int bgmac_enet_resume(struct bgmac *bgmac) +{ + int rc; + + if (!netif_running(bgmac->net_dev)) + return 0; + + rc = bgmac_dma_init(bgmac); + if (rc) + return rc; + + bgmac_chip_init(bgmac); + + napi_enable(&bgmac->napi); + + netif_tx_lock(bgmac->net_dev); + netif_device_attach(bgmac->net_dev); + netif_tx_unlock(bgmac->net_dev); + + netif_start_queue(bgmac->net_dev); + + phy_start(bgmac->net_dev->phydev); + + return 0; +} +EXPORT_SYMBOL_GPL(bgmac_enet_resume); + MODULE_AUTHOR("RafaÅ‚ MiÅ‚ecki"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index a75ed3538e5c..c1818766c501 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -537,6 +537,8 @@ int bgmac_enet_probe(struct bgmac *bgmac); void bgmac_enet_remove(struct bgmac *bgmac); void bgmac_adjust_link(struct net_device *net_dev); int bgmac_phy_connect_direct(struct bgmac *bgmac); +int bgmac_enet_suspend(struct bgmac *bgmac); +int bgmac_enet_resume(struct bgmac *bgmac); struct mii_bus *bcma_mdio_mii_register(struct bgmac *bgmac); void bcma_mdio_mii_unregister(struct mii_bus *mii_bus); From 57dacfedf856c475a10890c1f8ebcc1c63473cd1 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Tue, 28 Feb 2017 17:16:02 -0600 Subject: [PATCH 029/399] net: qcom/emac: optimize QDF2400 SGMII RX/TX impedence values Adjust the impedance values of the RX and TX lanes in the SGMII block so that they are closer to optimal values. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c index f62c215be779..7116be485e61 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c @@ -26,6 +26,7 @@ /* SGMII digital lane registers */ #define EMAC_SGMII_LN_DRVR_CTRL0 0x000C +#define EMAC_SGMII_LN_DRVR_CTRL1 0x0010 #define EMAC_SGMII_LN_DRVR_TAP_EN 0x0018 #define EMAC_SGMII_LN_TX_MARGINING 0x001C #define EMAC_SGMII_LN_TX_PRE 0x0020 @@ -48,6 +49,7 @@ #define EMAC_SGMII_LN_RX_EN_SIGNAL 0x02AC #define EMAC_SGMII_LN_RX_MISC_CNTRL0 0x02B8 #define EMAC_SGMII_LN_DRVR_LOGIC_CLKDIV 0x02C8 +#define EMAC_SGMII_LN_RX_RESECODE_OFFSET 0x02CC /* SGMII digital lane register values */ #define UCDR_STEP_BY_TWO_MODE0 BIT(7) @@ -73,6 +75,8 @@ #define CML_GEAR_MODE(x) (((x) & 7) << 3) #define CML2CMOS_IBOOST_MODE(x) ((x) & 7) +#define RESCODE_OFFSET(x) ((x) & 0x1f) + #define MIXER_LOADB_MODE(x) (((x) & 0xf) << 2) #define MIXER_DATARATE_MODE(x) ((x) & 3) @@ -159,6 +163,8 @@ static const struct emac_reg_write sgmii_laned[] = { {EMAC_SGMII_LN_PARALLEL_RATE, PARALLEL_RATE_MODE0(1)}, {EMAC_SGMII_LN_TX_BAND_MODE, BAND_MODE0(1)}, {EMAC_SGMII_LN_RX_BAND, BAND_MODE0(2)}, + {EMAC_SGMII_LN_DRVR_CTRL1, RESCODE_OFFSET(7)}, + {EMAC_SGMII_LN_RX_RESECODE_OFFSET, RESCODE_OFFSET(9)}, {EMAC_SGMII_LN_LANE_MODE, LANE_MODE(26)}, {EMAC_SGMII_LN_RX_RCVR_PATH1_MODE0, CDR_PD_SEL_MODE0(2) | EN_DLL_MODE0 | EN_IQ_DCC_MODE0 | EN_IQCAL_MODE0}, From 9c28286b1b4b9bce6e35dd4c8a1265f03802a89a Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Sat, 4 Mar 2017 22:10:28 +0800 Subject: [PATCH 030/399] decnet: Use TCP nagle macro instead of literal number in decnet Use existing TCP nagle macro TCP_NAGLE_OFF and TCP_NAGLE_CORK instead of the literal number 1 and 2 in the current decnet codes. Signed-off-by: Gao Feng Signed-off-by: David S. Miller --- net/decnet/af_decnet.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index e6e79eda9763..0ec8cb4363e9 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -132,6 +132,7 @@ Version 0.0.6 2.1.110 07-aug-98 Eduardo Marcelo Serrat #include #include #include +#include #include #include #include @@ -1468,18 +1469,18 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us case DSO_NODELAY: if (optlen != sizeof(int)) return -EINVAL; - if (scp->nonagle == 2) + if (scp->nonagle == TCP_NAGLE_CORK) return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 1; + scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_OFF; /* if (scp->nonagle == 1) { Push pending frames } */ break; case DSO_CORK: if (optlen != sizeof(int)) return -EINVAL; - if (scp->nonagle == 1) + if (scp->nonagle == TCP_NAGLE_OFF) return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 2; + scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_CORK; /* if (scp->nonagle == 0) { Push pending frames } */ break; @@ -1607,14 +1608,14 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us case DSO_NODELAY: if (r_len > sizeof(int)) r_len = sizeof(int); - val = (scp->nonagle == 1); + val = (scp->nonagle == TCP_NAGLE_OFF); r_data = &val; break; case DSO_CORK: if (r_len > sizeof(int)) r_len = sizeof(int); - val = (scp->nonagle == 2); + val = (scp->nonagle == TCP_NAGLE_CORK); r_data = &val; break; From efc9b8e33b8b5ef890288758454ce62a1319c94a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 7 Mar 2017 12:45:04 +0100 Subject: [PATCH 031/399] netfilter: bridge: remove unneeded rcu_read_lock as comment says, the function is always called with rcu read lock held. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/br_netfilter_hooks.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 95087e6e8258..52739e6c610e 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -1016,13 +1016,10 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net, if (!elem) return okfn(net, sk, skb); - /* We may already have this, but read-locks nest anyway */ - rcu_read_lock(); nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev, sk, net, okfn); ret = nf_hook_slow(skb, &state, elem); - rcu_read_unlock(); if (ret == 1) ret = okfn(net, sk, skb); From c1183db8853d14df390748aa6baa69734db151aa Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Tue, 7 Mar 2017 22:02:50 +0900 Subject: [PATCH 032/399] netfilter: nf_reject: remove unused variable variable oiph is not used. Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_reject_ipv4.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 146d86105183..7cd8d0d918f8 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -104,7 +104,6 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put); void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) { struct sk_buff *nskb; - const struct iphdr *oiph; struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _oth; @@ -116,8 +115,6 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return; - oiph = ip_hdr(oldskb); - nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) From 9e0b516af24eb72502bb61d383c22cfbe0407c2c Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Tue, 28 Feb 2017 23:49:38 +0100 Subject: [PATCH 033/399] net: smsc: smc911x: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/smsc/smc911x.c | 49 +++++++++++++++-------------- 1 file changed, 26 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index 4f19c6166182..36307d34f641 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1446,40 +1446,40 @@ static int smc911x_close(struct net_device *dev) * Ethtool support */ static int -smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc911x_ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct smc911x_local *lp = netdev_priv(dev); int ret, status; unsigned long flags; + u32 supported; DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - cmd->maxtxpkt = 1; - cmd->maxrxpkt = 1; if (lp->phy_type != 0) { spin_lock_irqsave(&lp->lock, flags); - ret = mii_ethtool_gset(&lp->mii, cmd); + ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd); spin_unlock_irqrestore(&lp->lock, flags); } else { - cmd->supported = SUPPORTED_10baseT_Half | + supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_TP | SUPPORTED_AUI; if (lp->ctl_rspeed == 10) - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; else if (lp->ctl_rspeed == 100) - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; - cmd->autoneg = AUTONEG_DISABLE; - if (lp->mii.phy_id==1) - cmd->transceiver = XCVR_INTERNAL; - else - cmd->transceiver = XCVR_EXTERNAL; - cmd->port = 0; + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = 0; SMC_GET_PHY_SPECIAL(lp, lp->mii.phy_id, status); - cmd->duplex = + cmd->base.duplex = (status & (PHY_SPECIAL_SPD_10FULL_ | PHY_SPECIAL_SPD_100FULL_)) ? DUPLEX_FULL : DUPLEX_HALF; + + ethtool_convert_legacy_u32_to_link_mode( + cmd->link_modes.supported, supported); + ret = 0; } @@ -1487,7 +1487,8 @@ smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) } static int -smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc911x_ethtool_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct smc911x_local *lp = netdev_priv(dev); int ret; @@ -1495,16 +1496,18 @@ smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd) if (lp->phy_type != 0) { spin_lock_irqsave(&lp->lock, flags); - ret = mii_ethtool_sset(&lp->mii, cmd); + ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd); spin_unlock_irqrestore(&lp->lock, flags); } else { - if (cmd->autoneg != AUTONEG_DISABLE || - cmd->speed != SPEED_10 || - (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) || - (cmd->port != PORT_TP && cmd->port != PORT_AUI)) + if (cmd->base.autoneg != AUTONEG_DISABLE || + cmd->base.speed != SPEED_10 || + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL) || + (cmd->base.port != PORT_TP && + cmd->base.port != PORT_AUI)) return -EINVAL; - lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL; + lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL; ret = 0; } @@ -1686,8 +1689,6 @@ static int smc911x_ethtool_geteeprom_len(struct net_device *dev) } static const struct ethtool_ops smc911x_ethtool_ops = { - .get_settings = smc911x_ethtool_getsettings, - .set_settings = smc911x_ethtool_setsettings, .get_drvinfo = smc911x_ethtool_getdrvinfo, .get_msglevel = smc911x_ethtool_getmsglevel, .set_msglevel = smc911x_ethtool_setmsglevel, @@ -1698,6 +1699,8 @@ static const struct ethtool_ops smc911x_ethtool_ops = { .get_eeprom_len = smc911x_ethtool_geteeprom_len, .get_eeprom = smc911x_ethtool_geteeprom, .set_eeprom = smc911x_ethtool_seteeprom, + .get_link_ksettings = smc911x_ethtool_get_link_ksettings, + .set_link_ksettings = smc911x_ethtool_set_link_ksettings, }; /* From c4df19a66617a4818769468975019c736a84e0c9 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sat, 4 Mar 2017 12:42:39 +0100 Subject: [PATCH 034/399] net: smsc: smc91x: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Tested-by: Robert Jarzmik Signed-off-by: David S. Miller --- drivers/net/ethernet/smsc/smc91x.c | 47 ++++++++++++++++-------------- 1 file changed, 25 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 65077c77082a..91e9bd7159ab 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -1535,32 +1535,33 @@ static int smc_close(struct net_device *dev) * Ethtool support */ static int -smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc_ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct smc_local *lp = netdev_priv(dev); int ret; - cmd->maxtxpkt = 1; - cmd->maxrxpkt = 1; - if (lp->phy_type != 0) { spin_lock_irq(&lp->lock); - ret = mii_ethtool_gset(&lp->mii, cmd); + ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd); spin_unlock_irq(&lp->lock); } else { - cmd->supported = SUPPORTED_10baseT_Half | + u32 supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_TP | SUPPORTED_AUI; if (lp->ctl_rspeed == 10) - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; else if (lp->ctl_rspeed == 100) - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; - cmd->autoneg = AUTONEG_DISABLE; - cmd->transceiver = XCVR_INTERNAL; - cmd->port = 0; - cmd->duplex = lp->tcr_cur_mode & TCR_SWFDUP ? DUPLEX_FULL : DUPLEX_HALF; + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = 0; + cmd->base.duplex = lp->tcr_cur_mode & TCR_SWFDUP ? + DUPLEX_FULL : DUPLEX_HALF; + + ethtool_convert_legacy_u32_to_link_mode( + cmd->link_modes.supported, supported); ret = 0; } @@ -1569,24 +1570,26 @@ smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) } static int -smc_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd) +smc_ethtool_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct smc_local *lp = netdev_priv(dev); int ret; if (lp->phy_type != 0) { spin_lock_irq(&lp->lock); - ret = mii_ethtool_sset(&lp->mii, cmd); + ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd); spin_unlock_irq(&lp->lock); } else { - if (cmd->autoneg != AUTONEG_DISABLE || - cmd->speed != SPEED_10 || - (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) || - (cmd->port != PORT_TP && cmd->port != PORT_AUI)) + if (cmd->base.autoneg != AUTONEG_DISABLE || + cmd->base.speed != SPEED_10 || + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL) || + (cmd->base.port != PORT_TP && cmd->base.port != PORT_AUI)) return -EINVAL; -// lp->port = cmd->port; - lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL; +// lp->port = cmd->base.port; + lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL; // if (netif_running(dev)) // smc_set_port(dev); @@ -1744,8 +1747,6 @@ static int smc_ethtool_seteeprom(struct net_device *dev, static const struct ethtool_ops smc_ethtool_ops = { - .get_settings = smc_ethtool_getsettings, - .set_settings = smc_ethtool_setsettings, .get_drvinfo = smc_ethtool_getdrvinfo, .get_msglevel = smc_ethtool_getmsglevel, @@ -1755,6 +1756,8 @@ static const struct ethtool_ops smc_ethtool_ops = { .get_eeprom_len = smc_ethtool_geteeprom_len, .get_eeprom = smc_ethtool_geteeprom, .set_eeprom = smc_ethtool_seteeprom, + .get_link_ksettings = smc_ethtool_get_link_ksettings, + .set_link_ksettings = smc_ethtool_set_link_ksettings, }; static const struct net_device_ops smc_netdev_ops = { From 2c784b0087d8b03b97bfcdbad8b162539dc614c6 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sat, 4 Mar 2017 16:16:12 +0100 Subject: [PATCH 035/399] net: sun: cassini: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/cassini.c | 98 ++++++++++++++++-------------- 1 file changed, 52 insertions(+), 46 deletions(-) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 0e8e89f17dbb..382993c1561c 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -691,7 +691,8 @@ static void cas_mif_poll(struct cas *cp, const int enable) } /* Must be invoked under cp->lock */ -static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep) +static void cas_begin_auto_negotiation(struct cas *cp, + const struct ethtool_link_ksettings *ep) { u16 ctl; #if 1 @@ -704,16 +705,16 @@ static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep) if (!ep) goto start_aneg; lcntl = cp->link_cntl; - if (ep->autoneg == AUTONEG_ENABLE) + if (ep->base.autoneg == AUTONEG_ENABLE) { cp->link_cntl = BMCR_ANENABLE; - else { - u32 speed = ethtool_cmd_speed(ep); + } else { + u32 speed = ep->base.speed; cp->link_cntl = 0; if (speed == SPEED_100) cp->link_cntl |= BMCR_SPEED100; else if (speed == SPEED_1000) cp->link_cntl |= CAS_BMCR_SPEED1000; - if (ep->duplex == DUPLEX_FULL) + if (ep->base.duplex == DUPLEX_FULL) cp->link_cntl |= BMCR_FULLDPLX; } #if 1 @@ -4528,19 +4529,21 @@ static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info)); } -static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cas_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct cas *cp = netdev_priv(dev); u16 bmcr; int full_duplex, speed, pause; unsigned long flags; enum link_state linkstate = link_up; + u32 supported, advertising; - cmd->advertising = 0; - cmd->supported = SUPPORTED_Autoneg; + advertising = 0; + supported = SUPPORTED_Autoneg; if (cp->cas_flags & CAS_FLAG_1000MB_CAP) { - cmd->supported |= SUPPORTED_1000baseT_Full; - cmd->advertising |= ADVERTISED_1000baseT_Full; + supported |= SUPPORTED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; } /* Record PHY settings if HW is on. */ @@ -4548,17 +4551,15 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) bmcr = 0; linkstate = cp->lstate; if (CAS_PHY_MII(cp->phy_type)) { - cmd->port = PORT_MII; - cmd->transceiver = (cp->cas_flags & CAS_FLAG_SATURN) ? - XCVR_INTERNAL : XCVR_EXTERNAL; - cmd->phy_address = cp->phy_addr; - cmd->advertising |= ADVERTISED_TP | ADVERTISED_MII | + cmd->base.port = PORT_MII; + cmd->base.phy_address = cp->phy_addr; + advertising |= ADVERTISED_TP | ADVERTISED_MII | ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full | ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full; - cmd->supported |= + supported |= (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | @@ -4574,11 +4575,10 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) } } else { - cmd->port = PORT_FIBRE; - cmd->transceiver = XCVR_INTERNAL; - cmd->phy_address = 0; - cmd->supported |= SUPPORTED_FIBRE; - cmd->advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; + cmd->base.phy_address = 0; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; if (cp->hw_running) { /* pcs uses the same bits as mii */ @@ -4590,21 +4590,20 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) spin_unlock_irqrestore(&cp->lock, flags); if (bmcr & BMCR_ANENABLE) { - cmd->advertising |= ADVERTISED_Autoneg; - cmd->autoneg = AUTONEG_ENABLE; - ethtool_cmd_speed_set(cmd, ((speed == 10) ? + advertising |= ADVERTISED_Autoneg; + cmd->base.autoneg = AUTONEG_ENABLE; + cmd->base.speed = ((speed == 10) ? SPEED_10 : ((speed == 1000) ? - SPEED_1000 : SPEED_100))); - cmd->duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF; + SPEED_1000 : SPEED_100)); + cmd->base.duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF; } else { - cmd->autoneg = AUTONEG_DISABLE; - ethtool_cmd_speed_set(cmd, ((bmcr & CAS_BMCR_SPEED1000) ? + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.speed = ((bmcr & CAS_BMCR_SPEED1000) ? SPEED_1000 : ((bmcr & BMCR_SPEED100) ? - SPEED_100 : SPEED_10))); - cmd->duplex = - (bmcr & BMCR_FULLDPLX) ? + SPEED_100 : SPEED_10)); + cmd->base.duplex = (bmcr & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } if (linkstate != link_up) { @@ -4619,39 +4618,46 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) * settings that we configured. */ if (cp->link_cntl & BMCR_ANENABLE) { - ethtool_cmd_speed_set(cmd, 0); - cmd->duplex = 0xff; + cmd->base.speed = 0; + cmd->base.duplex = 0xff; } else { - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; if (cp->link_cntl & BMCR_SPEED100) { - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; } else if (cp->link_cntl & CAS_BMCR_SPEED1000) { - ethtool_cmd_speed_set(cmd, SPEED_1000); + cmd->base.speed = SPEED_1000; } - cmd->duplex = (cp->link_cntl & BMCR_FULLDPLX)? + cmd->base.duplex = (cp->link_cntl & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } } + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + return 0; } -static int cas_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int cas_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct cas *cp = netdev_priv(dev); unsigned long flags; - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; /* Verify the settings we care about. */ - if (cmd->autoneg != AUTONEG_ENABLE && - cmd->autoneg != AUTONEG_DISABLE) + if (cmd->base.autoneg != AUTONEG_ENABLE && + cmd->base.autoneg != AUTONEG_DISABLE) return -EINVAL; - if (cmd->autoneg == AUTONEG_DISABLE && + if (cmd->base.autoneg == AUTONEG_DISABLE && ((speed != SPEED_1000 && speed != SPEED_100 && speed != SPEED_10) || - (cmd->duplex != DUPLEX_HALF && - cmd->duplex != DUPLEX_FULL))) + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL))) return -EINVAL; /* Apply settings and restart link process. */ @@ -4753,8 +4759,6 @@ static void cas_get_ethtool_stats(struct net_device *dev, static const struct ethtool_ops cas_ethtool_ops = { .get_drvinfo = cas_get_drvinfo, - .get_settings = cas_get_settings, - .set_settings = cas_set_settings, .nway_reset = cas_nway_reset, .get_link = cas_get_link, .get_msglevel = cas_get_msglevel, @@ -4764,6 +4768,8 @@ static const struct ethtool_ops cas_ethtool_ops = { .get_sset_count = cas_get_sset_count, .get_strings = cas_get_strings, .get_ethtool_stats = cas_get_ethtool_stats, + .get_link_ksettings = cas_get_link_ksettings, + .set_link_ksettings = cas_set_link_ksettings, }; static int cas_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) From d972253146867b65ecff0bcc0e551a970b3efa1b Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sat, 4 Mar 2017 17:50:06 +0100 Subject: [PATCH 036/399] net: sun: niu: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/niu.c | 37 ++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 57978056b336..2dcca249eb9c 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6813,7 +6813,8 @@ static void niu_get_drvinfo(struct net_device *dev, sizeof(info->bus_info)); } -static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int niu_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct niu *np = netdev_priv(dev); struct niu_link_config *lp; @@ -6821,28 +6822,30 @@ static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) lp = &np->link_config; memset(cmd, 0, sizeof(*cmd)); - cmd->phy_address = np->phy_addr; - cmd->supported = lp->supported; - cmd->advertising = lp->active_advertising; - cmd->autoneg = lp->active_autoneg; - ethtool_cmd_speed_set(cmd, lp->active_speed); - cmd->duplex = lp->active_duplex; - cmd->port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP; - cmd->transceiver = (np->flags & NIU_FLAGS_XCVR_SERDES) ? - XCVR_EXTERNAL : XCVR_INTERNAL; + cmd->base.phy_address = np->phy_addr; + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + lp->supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + lp->active_advertising); + cmd->base.autoneg = lp->active_autoneg; + cmd->base.speed = lp->active_speed; + cmd->base.duplex = lp->active_duplex; + cmd->base.port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP; return 0; } -static int niu_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int niu_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct niu *np = netdev_priv(dev); struct niu_link_config *lp = &np->link_config; - lp->advertising = cmd->advertising; - lp->speed = ethtool_cmd_speed(cmd); - lp->duplex = cmd->duplex; - lp->autoneg = cmd->autoneg; + ethtool_convert_link_mode_to_legacy_u32(&lp->advertising, + cmd->link_modes.advertising); + lp->speed = cmd->base.speed; + lp->duplex = cmd->base.duplex; + lp->autoneg = cmd->base.autoneg; return niu_init_link(np); } @@ -7902,14 +7905,14 @@ static const struct ethtool_ops niu_ethtool_ops = { .nway_reset = niu_nway_reset, .get_eeprom_len = niu_get_eeprom_len, .get_eeprom = niu_get_eeprom, - .get_settings = niu_get_settings, - .set_settings = niu_set_settings, .get_strings = niu_get_strings, .get_sset_count = niu_get_sset_count, .get_ethtool_stats = niu_get_ethtool_stats, .set_phys_id = niu_set_phys_id, .get_rxnfc = niu_get_nfc, .set_rxnfc = niu_set_nfc, + .get_link_ksettings = niu_get_link_ksettings, + .set_link_ksettings = niu_set_link_ksettings, }; static int niu_ldg_assign_ldn(struct niu *np, struct niu_parent *parent, From 92552fdda557d1a9d7a819a79d0e356d439e8cfc Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 5 Mar 2017 00:04:18 +0100 Subject: [PATCH 037/399] net: sun: sungem: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sungem.c | 98 ++++++++++++++++++------------- 1 file changed, 57 insertions(+), 41 deletions(-) diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 5c5952e782cd..dbfca0466760 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1250,12 +1250,17 @@ static void gem_stop_dma(struct gem *gp) // XXX dbl check what that function should do when called on PCS PHY -static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep) +static void gem_begin_auto_negotiation(struct gem *gp, + const struct ethtool_link_ksettings *ep) { u32 advertise, features; int autoneg; int speed; int duplex; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + ep->link_modes.advertising); if (gp->phy_type != phy_mii_mdio0 && gp->phy_type != phy_mii_mdio1) @@ -1278,13 +1283,13 @@ static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep) /* Setup link parameters */ if (!ep) goto start_aneg; - if (ep->autoneg == AUTONEG_ENABLE) { - advertise = ep->advertising; + if (ep->base.autoneg == AUTONEG_ENABLE) { + advertise = advertising; autoneg = 1; } else { autoneg = 0; - speed = ethtool_cmd_speed(ep); - duplex = ep->duplex; + speed = ep->base.speed; + duplex = ep->base.duplex; } start_aneg: @@ -2515,85 +2520,96 @@ static void gem_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info strlcpy(info->bus_info, pci_name(gp->pdev), sizeof(info->bus_info)); } -static int gem_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int gem_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct gem *gp = netdev_priv(dev); + u32 supported, advertising; if (gp->phy_type == phy_mii_mdio0 || gp->phy_type == phy_mii_mdio1) { if (gp->phy_mii.def) - cmd->supported = gp->phy_mii.def->features; + supported = gp->phy_mii.def->features; else - cmd->supported = (SUPPORTED_10baseT_Half | + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full); /* XXX hardcoded stuff for now */ - cmd->port = PORT_MII; - cmd->transceiver = XCVR_EXTERNAL; - cmd->phy_address = 0; /* XXX fixed PHYAD */ + cmd->base.port = PORT_MII; + cmd->base.phy_address = 0; /* XXX fixed PHYAD */ /* Return current PHY settings */ - cmd->autoneg = gp->want_autoneg; - ethtool_cmd_speed_set(cmd, gp->phy_mii.speed); - cmd->duplex = gp->phy_mii.duplex; - cmd->advertising = gp->phy_mii.advertising; + cmd->base.autoneg = gp->want_autoneg; + cmd->base.speed = gp->phy_mii.speed; + cmd->base.duplex = gp->phy_mii.duplex; + advertising = gp->phy_mii.advertising; /* If we started with a forced mode, we don't have a default * advertise set, we need to return something sensible so * userland can re-enable autoneg properly. */ - if (cmd->advertising == 0) - cmd->advertising = cmd->supported; + if (advertising == 0) + advertising = supported; } else { // XXX PCS ? - cmd->supported = + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg); - cmd->advertising = cmd->supported; - ethtool_cmd_speed_set(cmd, 0); - cmd->duplex = cmd->port = cmd->phy_address = - cmd->transceiver = cmd->autoneg = 0; + advertising = supported; + cmd->base.speed = 0; + cmd->base.duplex = 0; + cmd->base.port = 0; + cmd->base.phy_address = 0; + cmd->base.autoneg = 0; /* serdes means usually a Fibre connector, with most fixed */ if (gp->phy_type == phy_serdes) { - cmd->port = PORT_FIBRE; - cmd->supported = (SUPPORTED_1000baseT_Half | + cmd->base.port = PORT_FIBRE; + supported = (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full | SUPPORTED_FIBRE | SUPPORTED_Autoneg | SUPPORTED_Pause | SUPPORTED_Asym_Pause); - cmd->advertising = cmd->supported; - cmd->transceiver = XCVR_INTERNAL; + advertising = supported; if (gp->lstate == link_up) - ethtool_cmd_speed_set(cmd, SPEED_1000); - cmd->duplex = DUPLEX_FULL; - cmd->autoneg = 1; + cmd->base.speed = SPEED_1000; + cmd->base.duplex = DUPLEX_FULL; + cmd->base.autoneg = 1; } } - cmd->maxtxpkt = cmd->maxrxpkt = 0; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int gem_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int gem_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct gem *gp = netdev_priv(dev); - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); /* Verify the settings we care about. */ - if (cmd->autoneg != AUTONEG_ENABLE && - cmd->autoneg != AUTONEG_DISABLE) + if (cmd->base.autoneg != AUTONEG_ENABLE && + cmd->base.autoneg != AUTONEG_DISABLE) return -EINVAL; - if (cmd->autoneg == AUTONEG_ENABLE && - cmd->advertising == 0) + if (cmd->base.autoneg == AUTONEG_ENABLE && + advertising == 0) return -EINVAL; - if (cmd->autoneg == AUTONEG_DISABLE && + if (cmd->base.autoneg == AUTONEG_DISABLE && ((speed != SPEED_1000 && speed != SPEED_100 && speed != SPEED_10) || - (cmd->duplex != DUPLEX_HALF && - cmd->duplex != DUPLEX_FULL))) + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL))) return -EINVAL; /* Apply settings and restart link process. */ @@ -2666,13 +2682,13 @@ static int gem_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static const struct ethtool_ops gem_ethtool_ops = { .get_drvinfo = gem_get_drvinfo, .get_link = ethtool_op_get_link, - .get_settings = gem_get_settings, - .set_settings = gem_set_settings, .nway_reset = gem_nway_reset, .get_msglevel = gem_get_msglevel, .set_msglevel = gem_set_msglevel, .get_wol = gem_get_wol, .set_wol = gem_set_wol, + .get_link_ksettings = gem_get_link_ksettings, + .set_link_ksettings = gem_set_link_ksettings, }; static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) From e016cc64423d2b6476e5c99d8a278f9093d53407 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 5 Mar 2017 22:25:39 +0100 Subject: [PATCH 038/399] net: sun: sunhme: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunhme.c | 62 +++++++++++++++++-------------- 1 file changed, 34 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 72ff05cd3ed8..53ff66ef53ac 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1294,9 +1294,10 @@ static void happy_meal_init_rings(struct happy_meal *hp) } /* hp->happy_lock must be held */ -static void happy_meal_begin_auto_negotiation(struct happy_meal *hp, - void __iomem *tregs, - struct ethtool_cmd *ep) +static void +happy_meal_begin_auto_negotiation(struct happy_meal *hp, + void __iomem *tregs, + const struct ethtool_link_ksettings *ep) { int timeout; @@ -1309,7 +1310,7 @@ static void happy_meal_begin_auto_negotiation(struct happy_meal *hp, /* XXX Check BMSR_ANEGCAPABLE, should not be necessary though. */ hp->sw_advertise = happy_meal_tcvr_read(hp, tregs, MII_ADVERTISE); - if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) { + if (!ep || ep->base.autoneg == AUTONEG_ENABLE) { /* Advertise everything we can support. */ if (hp->sw_bmsr & BMSR_10HALF) hp->sw_advertise |= (ADVERTISE_10HALF); @@ -1384,14 +1385,14 @@ static void happy_meal_begin_auto_negotiation(struct happy_meal *hp, /* Disable auto-negotiation in BMCR, enable the duplex and * speed setting, init the timer state machine, and fire it off. */ - if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) { + if (!ep || ep->base.autoneg == AUTONEG_ENABLE) { hp->sw_bmcr = BMCR_SPEED100; } else { - if (ethtool_cmd_speed(ep) == SPEED_100) + if (ep->base.speed == SPEED_100) hp->sw_bmcr = BMCR_SPEED100; else hp->sw_bmcr = 0; - if (ep->duplex == DUPLEX_FULL) + if (ep->base.duplex == DUPLEX_FULL) hp->sw_bmcr |= BMCR_FULLDPLX; } happy_meal_tcvr_write(hp, tregs, MII_BMCR, hp->sw_bmcr); @@ -2434,20 +2435,21 @@ static void happy_meal_set_multicast(struct net_device *dev) } /* Ethtool support... */ -static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int hme_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct happy_meal *hp = netdev_priv(dev); u32 speed; + u32 supported; - cmd->supported = + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII); /* XXX hardcoded stuff for now */ - cmd->port = PORT_TP; /* XXX no MII support */ - cmd->transceiver = XCVR_INTERNAL; /* XXX no external xcvr support */ - cmd->phy_address = 0; /* XXX fixed PHYAD */ + cmd->base.port = PORT_TP; /* XXX no MII support */ + cmd->base.phy_address = 0; /* XXX fixed PHYAD */ /* Record PHY settings. */ spin_lock_irq(&hp->happy_lock); @@ -2456,41 +2458,45 @@ static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) spin_unlock_irq(&hp->happy_lock); if (hp->sw_bmcr & BMCR_ANENABLE) { - cmd->autoneg = AUTONEG_ENABLE; + cmd->base.autoneg = AUTONEG_ENABLE; speed = ((hp->sw_lpa & (LPA_100HALF | LPA_100FULL)) ? SPEED_100 : SPEED_10); if (speed == SPEED_100) - cmd->duplex = + cmd->base.duplex = (hp->sw_lpa & (LPA_100FULL)) ? DUPLEX_FULL : DUPLEX_HALF; else - cmd->duplex = + cmd->base.duplex = (hp->sw_lpa & (LPA_10FULL)) ? DUPLEX_FULL : DUPLEX_HALF; } else { - cmd->autoneg = AUTONEG_DISABLE; + cmd->base.autoneg = AUTONEG_DISABLE; speed = (hp->sw_bmcr & BMCR_SPEED100) ? SPEED_100 : SPEED_10; - cmd->duplex = + cmd->base.duplex = (hp->sw_bmcr & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } - ethtool_cmd_speed_set(cmd, speed); + cmd->base.speed = speed; + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + return 0; } -static int hme_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int hme_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct happy_meal *hp = netdev_priv(dev); /* Verify the settings we care about. */ - if (cmd->autoneg != AUTONEG_ENABLE && - cmd->autoneg != AUTONEG_DISABLE) + if (cmd->base.autoneg != AUTONEG_ENABLE && + cmd->base.autoneg != AUTONEG_DISABLE) return -EINVAL; - if (cmd->autoneg == AUTONEG_DISABLE && - ((ethtool_cmd_speed(cmd) != SPEED_100 && - ethtool_cmd_speed(cmd) != SPEED_10) || - (cmd->duplex != DUPLEX_HALF && - cmd->duplex != DUPLEX_FULL))) + if (cmd->base.autoneg == AUTONEG_DISABLE && + ((cmd->base.speed != SPEED_100 && + cmd->base.speed != SPEED_10) || + (cmd->base.duplex != DUPLEX_HALF && + cmd->base.duplex != DUPLEX_FULL))) return -EINVAL; /* Ok, do it to it. */ @@ -2537,10 +2543,10 @@ static u32 hme_get_link(struct net_device *dev) } static const struct ethtool_ops hme_ethtool_ops = { - .get_settings = hme_get_settings, - .set_settings = hme_set_settings, .get_drvinfo = hme_get_drvinfo, .get_link = hme_get_link, + .get_link_ksettings = hme_get_link_ksettings, + .set_link_ksettings = hme_set_link_ksettings, }; static int hme_version_printed; From 60f285129905c33203f66111363c5503ccbc5c41 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 5 Mar 2017 23:21:06 +0100 Subject: [PATCH 039/399] net: toshiba: ps3_genic_net: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Tested-by: Geoff Levand Signed-off-by: David S. Miller --- drivers/net/ethernet/toshiba/ps3_gelic_net.c | 51 +++++++++++--------- 1 file changed, 29 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index 72013314bba8..fa6a06571187 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -1206,61 +1206,68 @@ void gelic_net_get_drvinfo(struct net_device *netdev, strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } -static int gelic_ether_get_settings(struct net_device *netdev, - struct ethtool_cmd *cmd) +static int gelic_ether_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct gelic_card *card = netdev_card(netdev); + u32 supported, advertising; gelic_card_get_ether_port_status(card, 0); if (card->ether_port_status & GELIC_LV1_ETHER_FULL_DUPLEX) - cmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - cmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; switch (card->ether_port_status & GELIC_LV1_ETHER_SPEED_MASK) { case GELIC_LV1_ETHER_SPEED_10: - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; break; case GELIC_LV1_ETHER_SPEED_100: - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; break; case GELIC_LV1_ETHER_SPEED_1000: - ethtool_cmd_speed_set(cmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; default: pr_info("%s: speed unknown\n", __func__); - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; break; } - cmd->supported = SUPPORTED_TP | SUPPORTED_Autoneg | + supported = SUPPORTED_TP | SUPPORTED_Autoneg | SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_1000baseT_Full; - cmd->advertising = cmd->supported; + advertising = supported; if (card->link_mode & GELIC_LV1_ETHER_AUTO_NEG) { - cmd->autoneg = AUTONEG_ENABLE; + cmd->base.autoneg = AUTONEG_ENABLE; } else { - cmd->autoneg = AUTONEG_DISABLE; - cmd->advertising &= ~ADVERTISED_Autoneg; + cmd->base.autoneg = AUTONEG_DISABLE; + advertising &= ~ADVERTISED_Autoneg; } - cmd->port = PORT_TP; + cmd->base.port = PORT_TP; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int gelic_ether_set_settings(struct net_device *netdev, - struct ethtool_cmd *cmd) +static int +gelic_ether_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct gelic_card *card = netdev_card(netdev); u64 mode; int ret; - if (cmd->autoneg == AUTONEG_ENABLE) { + if (cmd->base.autoneg == AUTONEG_ENABLE) { mode = GELIC_LV1_ETHER_AUTO_NEG; } else { - switch (cmd->speed) { + switch (cmd->base.speed) { case SPEED_10: mode = GELIC_LV1_ETHER_SPEED_10; break; @@ -1273,9 +1280,9 @@ static int gelic_ether_set_settings(struct net_device *netdev, default: return -EINVAL; } - if (cmd->duplex == DUPLEX_FULL) + if (cmd->base.duplex == DUPLEX_FULL) { mode |= GELIC_LV1_ETHER_FULL_DUPLEX; - else if (cmd->speed == SPEED_1000) { + } else if (cmd->base.speed == SPEED_1000) { pr_info("1000 half duplex is not supported.\n"); return -EINVAL; } @@ -1370,11 +1377,11 @@ static int gelic_net_set_wol(struct net_device *netdev, static const struct ethtool_ops gelic_ether_ethtool_ops = { .get_drvinfo = gelic_net_get_drvinfo, - .get_settings = gelic_ether_get_settings, - .set_settings = gelic_ether_set_settings, .get_link = ethtool_op_get_link, .get_wol = gelic_net_get_wol, .set_wol = gelic_net_set_wol, + .get_link_ksettings = gelic_ether_get_link_ksettings, + .set_link_ksettings = gelic_ether_set_link_ksettings, }; /** From fa383d663e3804ef76382c32524802b419b43770 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 5 Mar 2017 23:46:00 +0100 Subject: [PATCH 040/399] net: toshiba: spider_net: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- .../net/ethernet/toshiba/spider_net_ethtool.c | 24 +++++++++++-------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c index ffe519382e11..16bd036d0682 100644 --- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c +++ b/drivers/net/ethernet/toshiba/spider_net_ethtool.c @@ -47,19 +47,23 @@ static struct { }; static int -spider_net_ethtool_get_settings(struct net_device *netdev, - struct ethtool_cmd *cmd) +spider_net_ethtool_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct spider_net_card *card; card = netdev_priv(netdev); - cmd->supported = (SUPPORTED_1000baseT_Full | - SUPPORTED_FIBRE); - cmd->advertising = (ADVERTISED_1000baseT_Full | - ADVERTISED_FIBRE); - cmd->port = PORT_FIBRE; - ethtool_cmd_speed_set(cmd, card->phy.speed); - cmd->duplex = DUPLEX_FULL; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); + + cmd->base.port = PORT_FIBRE; + cmd->base.speed = card->phy.speed; + cmd->base.duplex = DUPLEX_FULL; return 0; } @@ -166,7 +170,6 @@ static void spider_net_get_strings(struct net_device *netdev, u32 stringset, } const struct ethtool_ops spider_net_ethtool_ops = { - .get_settings = spider_net_ethtool_get_settings, .get_drvinfo = spider_net_ethtool_get_drvinfo, .get_wol = spider_net_ethtool_get_wol, .get_msglevel = spider_net_ethtool_get_msglevel, @@ -177,5 +180,6 @@ const struct ethtool_ops spider_net_ethtool_ops = { .get_strings = spider_net_get_strings, .get_sset_count = spider_net_get_sset_count, .get_ethtool_stats = spider_net_get_ethtool_stats, + .get_link_ksettings = spider_net_ethtool_get_link_ksettings, }; From 3907e490d358aa82bf7446fc9d340f688c97c6de Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Thu, 12 Jan 2017 10:00:17 +0200 Subject: [PATCH 041/399] fsl/fman: parse result data is big endian Signed-off-by: Madalin Bucur --- drivers/net/ethernet/freescale/fman/fman.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h index 57aae8d17d77..f53e1473dbcc 100644 --- a/drivers/net/ethernet/freescale/fman/fman.h +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -134,14 +134,14 @@ enum fman_exceptions { struct fman_prs_result { u8 lpid; /* Logical port id */ u8 shimr; /* Shim header result */ - u16 l2r; /* Layer 2 result */ - u16 l3r; /* Layer 3 result */ + __be16 l2r; /* Layer 2 result */ + __be16 l3r; /* Layer 3 result */ u8 l4r; /* Layer 4 result */ u8 cplan; /* Classification plan id */ - u16 nxthdr; /* Next Header */ - u16 cksum; /* Running-sum */ + __be16 nxthdr; /* Next Header */ + __be16 cksum; /* Running-sum */ /* Flags&fragment-offset field of the last IP-header */ - u16 flags_frag_off; + __be16 flags_frag_off; /* Routing type field of a IPV6 routing extension header */ u8 route_type; /* Routing Extension Header Present; last bit is IP valid */ From 1df653cfea251386e8ecd8c9f983caacd965c78e Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Wed, 25 Jan 2017 13:41:28 +0200 Subject: [PATCH 042/399] fsl/fman: set HW parser as BMI next engine Enable the HW parser for all DPAA interfaces. Signed-off-by: Madalin Bucur --- drivers/net/ethernet/freescale/fman/fman.c | 21 ++++++ .../net/ethernet/freescale/fman/fman_port.c | 72 ++++++++++++++++++- 2 files changed, 90 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index f60845f0c6ca..d7559306226d 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -59,6 +59,7 @@ #define DMA_OFFSET 0x000C2000 #define FPM_OFFSET 0x000C3000 #define IMEM_OFFSET 0x000C4000 +#define HWP_OFFSET 0x000C7000 #define CGP_OFFSET 0x000DB000 /* Exceptions bit map */ @@ -218,6 +219,9 @@ #define QMI_GS_HALT_NOT_BUSY 0x00000002 +/* HWP defines */ +#define HWP_RPIMAC_PEN 0x00000001 + /* IRAM defines */ #define IRAM_IADD_AIE 0x80000000 #define IRAM_READY 0x80000000 @@ -475,6 +479,12 @@ struct fman_dma_regs { u32 res00e0[0x400 - 56]; }; +struct fman_hwp_regs { + u32 res0000[0x844 / 4]; /* 0x000..0x843 */ + u32 fmprrpimac; /* FM Parser Internal memory access control */ + u32 res[(0x1000 - 0x848) / 4]; /* 0x848..0xFFF */ +}; + /* Structure that holds current FMan state. * Used for saving run time information. */ @@ -606,6 +616,7 @@ struct fman { struct fman_bmi_regs __iomem *bmi_regs; struct fman_qmi_regs __iomem *qmi_regs; struct fman_dma_regs __iomem *dma_regs; + struct fman_hwp_regs __iomem *hwp_regs; fman_exceptions_cb *exception_cb; fman_bus_error_cb *bus_error_cb; /* Spinlock for FMan use */ @@ -999,6 +1010,12 @@ static void qmi_init(struct fman_qmi_regs __iomem *qmi_rg, iowrite32be(tmp_reg, &qmi_rg->fmqm_ien); } +static void hwp_init(struct fman_hwp_regs __iomem *hwp_rg) +{ + /* enable HW Parser */ + iowrite32be(HWP_RPIMAC_PEN, &hwp_rg->fmprrpimac); +} + static int enable(struct fman *fman, struct fman_cfg *cfg) { u32 cfg_reg = 0; @@ -1793,6 +1810,7 @@ static int fman_config(struct fman *fman) fman->bmi_regs = base_addr + BMI_OFFSET; fman->qmi_regs = base_addr + QMI_OFFSET; fman->dma_regs = base_addr + DMA_OFFSET; + fman->hwp_regs = base_addr + HWP_OFFSET; fman->base_addr = base_addr; spin_lock_init(&fman->spinlock); @@ -2062,6 +2080,9 @@ static int fman_init(struct fman *fman) /* Init QMI Registers */ qmi_init(fman->qmi_regs, fman->cfg); + /* Init HW Parser */ + hwp_init(fman->hwp_regs); + err = enable(fman, cfg); if (err != 0) return err; diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 9f3bb50a2365..f314348b3387 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -62,6 +62,7 @@ #define BMI_PORT_REGS_OFFSET 0 #define QMI_PORT_REGS_OFFSET 0x400 +#define HWP_PORT_REGS_OFFSET 0x800 /* Default values */ #define DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN \ @@ -182,7 +183,7 @@ #define NIA_ENG_BMI 0x00500000 #define NIA_ENG_QMI_ENQ 0x00540000 #define NIA_ENG_QMI_DEQ 0x00580000 - +#define NIA_ENG_HWP 0x00440000 #define NIA_BMI_AC_ENQ_FRAME 0x00000002 #define NIA_BMI_AC_TX_RELEASE 0x000002C0 #define NIA_BMI_AC_RELEASE 0x000000C0 @@ -317,6 +318,19 @@ struct fman_port_qmi_regs { u32 fmqm_pndcc; /* PortID n Dequeue Confirm Counter */ }; +#define HWP_HXS_COUNT 16 +#define HWP_HXS_PHE_REPORT 0x00000800 +#define HWP_HXS_PCAC_PSTAT 0x00000100 +#define HWP_HXS_PCAC_PSTOP 0x00000001 +struct fman_port_hwp_regs { + struct { + u32 ssa; /* Soft Sequence Attachment */ + u32 lcv; /* Line-up Enable Confirmation Mask */ + } pmda[HWP_HXS_COUNT]; /* Parse Memory Direct Access Registers */ + u32 reserved080[(0x3f8 - 0x080) / 4]; /* (0x080-0x3f7) */ + u32 fmpr_pcac; /* Configuration Access Control */ +}; + /* QMI dequeue prefetch modes */ enum fman_port_deq_prefetch { FMAN_PORT_DEQ_NO_PREFETCH, /* No prefetch mode */ @@ -436,6 +450,7 @@ struct fman_port { union fman_port_bmi_regs __iomem *bmi_regs; struct fman_port_qmi_regs __iomem *qmi_regs; + struct fman_port_hwp_regs __iomem *hwp_regs; struct fman_sp_buffer_offsets buffer_offsets; @@ -521,9 +536,12 @@ static int init_bmi_rx(struct fman_port *port) /* NIA */ tmp = (u32)cfg->rx_fd_bits << BMI_NEXT_ENG_FD_BITS_SHIFT; - tmp |= NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME; + tmp |= NIA_ENG_HWP; iowrite32be(tmp, ®s->fmbm_rfne); + /* Parser Next Engine NIA */ + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME, ®s->fmbm_rfpne); + /* Enqueue NIA */ iowrite32be(NIA_ENG_QMI_ENQ | NIA_ORDER_RESTOR, ®s->fmbm_rfene); @@ -665,6 +683,50 @@ static int init_qmi(struct fman_port *port) return 0; } +static void stop_port_hwp(struct fman_port *port) +{ + struct fman_port_hwp_regs __iomem *regs = port->hwp_regs; + int cnt = 100; + + iowrite32be(HWP_HXS_PCAC_PSTOP, ®s->fmpr_pcac); + + while (cnt-- > 0 && + (ioread32be(®s->fmpr_pcac) & HWP_HXS_PCAC_PSTAT)) + udelay(10); + if (!cnt) + pr_err("Timeout stopping HW Parser\n"); +} + +static void start_port_hwp(struct fman_port *port) +{ + struct fman_port_hwp_regs __iomem *regs = port->hwp_regs; + int cnt = 100; + + iowrite32be(0, ®s->fmpr_pcac); + + while (cnt-- > 0 && + !(ioread32be(®s->fmpr_pcac) & HWP_HXS_PCAC_PSTAT)) + udelay(10); + if (!cnt) + pr_err("Timeout starting HW Parser\n"); +} + +static void init_hwp(struct fman_port *port) +{ + struct fman_port_hwp_regs __iomem *regs = port->hwp_regs; + int i; + + stop_port_hwp(port); + + for (i = 0; i < HWP_HXS_COUNT; i++) { + /* enable HXS error reporting into FD[STATUS] PHE */ + iowrite32be(0x00000000, ®s->pmda[i].ssa); + iowrite32be(0xffffffff, ®s->pmda[i].lcv); + } + + start_port_hwp(port); +} + static int init(struct fman_port *port) { int err; @@ -673,6 +735,8 @@ static int init(struct fman_port *port) switch (port->port_type) { case FMAN_PORT_TYPE_RX: err = init_bmi_rx(port); + if (!err) + init_hwp(port); break; case FMAN_PORT_TYPE_TX: err = init_bmi_tx(port); @@ -686,7 +750,8 @@ static int init(struct fman_port *port) /* Init QMI registers */ err = init_qmi(port); - return err; + if (err) + return err; return 0; } @@ -1276,6 +1341,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) /* set memory map pointers */ port->bmi_regs = base_addr + BMI_PORT_REGS_OFFSET; port->qmi_regs = base_addr + QMI_PORT_REGS_OFFSET; + port->hwp_regs = base_addr + HWP_PORT_REGS_OFFSET; port->max_frame_length = DFLT_PORT_MAX_FRAME_LENGTH; /* resource distribution. */ From 226327b236c97c860fe644a409fc536da53d5a98 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 13 Feb 2017 17:10:46 +0200 Subject: [PATCH 043/399] fsl/fman: remove wrong free Reported-by: Dan Carpenter Signed-off-by: Madalin Bucur --- drivers/net/ethernet/freescale/fman/fman_port.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index f314348b3387..57bf44fa16a1 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1312,7 +1312,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) /* Allocate the FM driver's parameters structure */ port->cfg = kzalloc(sizeof(*port->cfg), GFP_KERNEL); if (!port->cfg) - goto err_params; + return -EINVAL; /* Initialize FM port parameters which will be kept by the driver */ port->port_type = port->dts_params.type; @@ -1393,8 +1393,6 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) err_port_cfg: kfree(port->cfg); -err_params: - kfree(port); return -EINVAL; } EXPORT_SYMBOL(fman_port_config); From de8b1e41a251577bdd6eb44a7702473fb22ae497 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Tue, 14 Feb 2017 15:09:07 +0200 Subject: [PATCH 044/399] fsl/fman: enlarge FIFO to allow for the 5th port Signed-off-by: Madalin Bucur --- drivers/net/ethernet/freescale/fman/fman.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index d7559306226d..4aefe2438969 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -1212,7 +1212,7 @@ static int fill_soc_specific_params(struct fman_state_struct *state) state->max_num_of_open_dmas = 32; state->fm_port_num_of_cg = 256; state->num_of_rx_ports = 6; - state->total_fifo_size = 122 * 1024; + state->total_fifo_size = 136 * 1024; break; case 2: From 4529da5b7feab8f9bef585b5a56c7e33bef66e19 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Thu, 12 Jan 2017 09:54:28 +0200 Subject: [PATCH 045/399] dpaa_eth: remove redundant initialization Signed-off-by: Madalin Bucur --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index e2ca107f9d94..e19181f096bc 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2093,7 +2093,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, dma_addr_t addr = qm_fd_addr(fd); enum qm_fd_format fd_format; struct net_device *net_dev; - u32 fd_status = fd->status; + u32 fd_status; struct dpaa_bp *dpaa_bp; struct dpaa_priv *priv; unsigned int skb_len; From 5accb28241e027c9d816b348a870ee3f27c499ff Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Thu, 26 Jan 2017 14:34:02 +0200 Subject: [PATCH 046/399] dpaa_eth: enable Rx checksum offload Use the FMan HW parser L4CV flag to offload Rx checksumming. Signed-off-by: Madalin Bucur --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 29 +++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index e19181f096bc..a7a595c1c07d 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -137,6 +137,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); /* L4 Type field: TCP */ #define FM_L4_PARSE_RESULT_TCP 0x20 +/* FD status field indicating whether the FM Parser has attempted to validate + * the L4 csum of the frame. + * Note that having this bit set doesn't necessarily imply that the checksum + * is valid. One would have to check the parse results to find that out. + */ +#define FM_FD_STAT_L4CV 0x00000004 + #define DPAA_SGT_MAX_ENTRIES 16 /* maximum number of entries in SG Table */ #define DPAA_BUFF_RELEASE_MAX 8 /* maximum number of buffers released at once */ @@ -235,6 +242,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, * For conformity, we'll still declare GSO explicitly. */ net_dev->features |= NETIF_F_GSO; + net_dev->features |= NETIF_F_RXCSUM; net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* we do not want shared skbs on TX */ @@ -1526,6 +1534,23 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, return skb; } +static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd) +{ + /* The parser has run and performed L4 checksum validation. + * We know there were no parser errors (and implicitly no + * L4 csum error), otherwise we wouldn't be here. + */ + if ((priv->net_dev->features & NETIF_F_RXCSUM) && + (be32_to_cpu(fd->status) & FM_FD_STAT_L4CV)) + return CHECKSUM_UNNECESSARY; + + /* We're here because either the parser didn't run or the L4 checksum + * was not verified. This may include the case of a UDP frame with + * checksum zero or an L4 proto other than TCP/UDP + */ + return CHECKSUM_NONE; +} + /* Build a linear skb around the received buffer. * We are guaranteed there is enough room at the end of the data buffer to * accommodate the shared info area of the skb. @@ -1556,7 +1581,7 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv, skb_reserve(skb, fd_off); skb_put(skb, qm_fd_get_length(fd)); - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = rx_csum_offload(priv, fd); return skb; @@ -1616,7 +1641,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, if (WARN_ON(unlikely(!skb))) goto free_buffers; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = rx_csum_offload(priv, fd); /* Make sure forwarded skbs will have enough space * on Tx, if extra headers are added. From 7f8a6a1b8fa4915548e2e426e9780e7c217c3e0e Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 13 Feb 2017 17:20:01 +0200 Subject: [PATCH 047/399] dpaa_eth: do not ignore port api return value Reported-by: Dan Carpenter Signed-off-by: Madalin Bucur --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 65 ++++++++++++------- 1 file changed, 43 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index a7a595c1c07d..ae64cdb7a28c 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1063,9 +1063,9 @@ static int dpaa_fq_free(struct device *dev, struct list_head *list) return err; } -static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, - struct dpaa_fq *defq, - struct dpaa_buffer_layout *buf_layout) +static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, + struct dpaa_fq *defq, + struct dpaa_buffer_layout *buf_layout) { struct fman_buffer_prefix_content buf_prefix_content; struct fman_port_params params; @@ -1084,23 +1084,29 @@ static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, params.specific_params.non_rx_params.dflt_fqid = defq->fqid; err = fman_port_config(port, ¶ms); - if (err) + if (err) { pr_err("%s: fman_port_config failed\n", __func__); + return err; + } err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content); - if (err) + if (err) { pr_err("%s: fman_port_cfg_buf_prefix_content failed\n", __func__); + return err; + } err = fman_port_init(port); if (err) pr_err("%s: fm_port_init failed\n", __func__); + + return err; } -static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, - size_t count, struct dpaa_fq *errq, - struct dpaa_fq *defq, - struct dpaa_buffer_layout *buf_layout) +static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, + size_t count, struct dpaa_fq *errq, + struct dpaa_fq *defq, + struct dpaa_buffer_layout *buf_layout) { struct fman_buffer_prefix_content buf_prefix_content; struct fman_port_rx_params *rx_p; @@ -1128,32 +1134,44 @@ static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, } err = fman_port_config(port, ¶ms); - if (err) + if (err) { pr_err("%s: fman_port_config failed\n", __func__); + return err; + } err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content); - if (err) + if (err) { pr_err("%s: fman_port_cfg_buf_prefix_content failed\n", __func__); + return err; + } err = fman_port_init(port); if (err) pr_err("%s: fm_port_init failed\n", __func__); + + return err; } -static void dpaa_eth_init_ports(struct mac_device *mac_dev, - struct dpaa_bp **bps, size_t count, - struct fm_port_fqs *port_fqs, - struct dpaa_buffer_layout *buf_layout, - struct device *dev) +static int dpaa_eth_init_ports(struct mac_device *mac_dev, + struct dpaa_bp **bps, size_t count, + struct fm_port_fqs *port_fqs, + struct dpaa_buffer_layout *buf_layout, + struct device *dev) { struct fman_port *rxport = mac_dev->port[RX]; struct fman_port *txport = mac_dev->port[TX]; + int err; - dpaa_eth_init_tx_port(txport, port_fqs->tx_errq, - port_fqs->tx_defq, &buf_layout[TX]); - dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq, - port_fqs->rx_defq, &buf_layout[RX]); + err = dpaa_eth_init_tx_port(txport, port_fqs->tx_errq, + port_fqs->tx_defq, &buf_layout[TX]); + if (err) + return err; + + err = dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq, + port_fqs->rx_defq, &buf_layout[RX]); + + return err; } static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp, @@ -2649,8 +2667,10 @@ static int dpaa_eth_probe(struct platform_device *pdev) priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]); /* All real interfaces need their ports initialized */ - dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs, - &priv->buf_layout[0], dev); + err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs, + &priv->buf_layout[0], dev); + if (err) + goto init_ports_failed; priv->percpu_priv = devm_alloc_percpu(dev, *priv->percpu_priv); if (!priv->percpu_priv) { @@ -2683,6 +2703,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) napi_add_failed: dpaa_napi_del(net_dev); alloc_percpu_failed: +init_ports_failed: dpaa_fq_free(dev, &priv->dpaa_fq_list); fq_alloc_failed: qman_delete_cgr_safe(&priv->ingress_cgr); From c44efa1d75e4c0a720fd39d7095a0bd6b306576e Mon Sep 17 00:00:00 2001 From: Camelia Groza Date: Mon, 25 Jul 2016 16:38:21 +0300 Subject: [PATCH 048/399] dpaa_eth: add four prioritised Tx traffic classes Each traffic class corresponds to a WQ priority level. The number of Tx netdev queues and frame queues is increased to NR_CPUS queues for each traffic class. In addition, the priority of the Rx, Error and Conf queues is lowered but their order is maintained. By default, only one traffic class is enabled, only the low priority Tx queues are used and only the corresponding netdev queues are advertised. Signed-off-by: Camelia Groza Signed-off-by: Madalin Bucur --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 43 +++++++++++++++---- .../net/ethernet/freescale/dpaa/dpaa_eth.h | 8 +++- 2 files changed, 42 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ae64cdb7a28c..ac75d09c643e 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -565,16 +565,18 @@ static void dpaa_bps_free(struct dpaa_priv *priv) /* Use multiple WQs for FQ assignment: * - Tx Confirmation queues go to WQ1. - * - Rx Error and Tx Error queues go to WQ2 (giving them a better chance - * to be scheduled, in case there are many more FQs in WQ3). - * - Rx Default and Tx queues go to WQ3 (no differentiation between - * Rx and Tx traffic). + * - Rx Error and Tx Error queues go to WQ5 (giving them a better chance + * to be scheduled, in case there are many more FQs in WQ6). + * - Rx Default goes to WQ6. + * - Tx queues go to different WQs depending on their priority. Equal + * chunks of NR_CPUS queues go to WQ6 (lowest priority), WQ2, WQ1 and + * WQ0 (highest priority). * This ensures that Tx-confirmed buffers are timely released. In particular, * it avoids congestion on the Tx Confirm FQs, which can pile up PFDRs if they * are greatly outnumbered by other FQs in the system, while * dequeue scheduling is round-robin. */ -static inline void dpaa_assign_wq(struct dpaa_fq *fq) +static inline void dpaa_assign_wq(struct dpaa_fq *fq, int idx) { switch (fq->fq_type) { case FQ_TYPE_TX_CONFIRM: @@ -583,11 +585,33 @@ static inline void dpaa_assign_wq(struct dpaa_fq *fq) break; case FQ_TYPE_RX_ERROR: case FQ_TYPE_TX_ERROR: - fq->wq = 2; + fq->wq = 5; break; case FQ_TYPE_RX_DEFAULT: + fq->wq = 6; + break; case FQ_TYPE_TX: - fq->wq = 3; + switch (idx / DPAA_TC_TXQ_NUM) { + case 0: + /* Low priority (best effort) */ + fq->wq = 6; + break; + case 1: + /* Medium priority */ + fq->wq = 2; + break; + case 2: + /* High priority */ + fq->wq = 1; + break; + case 3: + /* Very high priority */ + fq->wq = 0; + break; + default: + WARN(1, "Too many TX FQs: more than %d!\n", + DPAA_ETH_TXQ_NUM); + } break; default: WARN(1, "Invalid FQ type %d for FQID %d!\n", @@ -615,7 +639,7 @@ static struct dpaa_fq *dpaa_fq_alloc(struct device *dev, } for (i = 0; i < count; i++) - dpaa_assign_wq(dpaa_fq + i); + dpaa_assign_wq(dpaa_fq + i, i); return dpaa_fq; } @@ -2683,6 +2707,9 @@ static int dpaa_eth_probe(struct platform_device *pdev) memset(percpu_priv, 0, sizeof(*percpu_priv)); } + priv->num_tc = 1; + netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM); + /* Initialize NAPI */ err = dpaa_napi_add(net_dev); if (err < 0) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h index 1f9aebf3f3c5..9941a7866ebe 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h @@ -39,7 +39,12 @@ #include "mac.h" #include "dpaa_eth_trace.h" -#define DPAA_ETH_TXQ_NUM NR_CPUS +/* Number of prioritised traffic classes */ +#define DPAA_TC_NUM 4 +/* Number of Tx queues per traffic class */ +#define DPAA_TC_TXQ_NUM NR_CPUS +/* Total number of Tx queues */ +#define DPAA_ETH_TXQ_NUM (DPAA_TC_NUM * DPAA_TC_TXQ_NUM) #define DPAA_BPS_NUM 3 /* number of bpools per interface */ @@ -152,6 +157,7 @@ struct dpaa_priv { u16 channel; struct list_head dpaa_fq_list; + u8 num_tc; u32 msg_enable; /* net_device message level */ struct { From 2ea08f8261b1469c728204aaacfca1d046eb0bff Mon Sep 17 00:00:00 2001 From: Camelia Groza Date: Mon, 25 Jul 2016 16:54:56 +0300 Subject: [PATCH 049/399] dpaa_eth: enable multiple Tx traffic classes Implement the setup_tc ndo to configure prioritised Tx traffic classes. Priorities range from 0 (lowest) to 3 (highest). The driver assigns NR_CPUS queues to each traffic class. Signed-off-by: Camelia Groza Signed-off-by: Madalin Bucur --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ac75d09c643e..1b3ea38d014f 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -342,6 +342,41 @@ static void dpaa_get_stats64(struct net_device *net_dev, } } +static int dpaa_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + int i; + + if (tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + + if (tc->tc == priv->num_tc) + return 0; + + if (!tc->tc) { + netdev_reset_tc(net_dev); + goto out; + } + + if (tc->tc > DPAA_TC_NUM) { + netdev_err(net_dev, "Too many traffic classes: max %d supported.\n", + DPAA_TC_NUM); + return -EINVAL; + } + + netdev_set_num_tc(net_dev, tc->tc); + + for (i = 0; i < tc->tc; i++) + netdev_set_tc_queue(net_dev, i, DPAA_TC_TXQ_NUM, + i * DPAA_TC_TXQ_NUM); + +out: + priv->num_tc = tc->tc ? tc->tc : 1; + netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM); + return 0; +} + static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev) { struct platform_device *of_dev; @@ -2417,6 +2452,7 @@ static const struct net_device_ops dpaa_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = dpaa_set_rx_mode, .ndo_do_ioctl = dpaa_ioctl, + .ndo_setup_tc = dpaa_setup_tc, }; static int dpaa_napi_add(struct net_device *net_dev) From 7fe1e290bfca75061d77ad2a67b12c23d6d35e7b Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Tue, 14 Feb 2017 17:17:28 +0200 Subject: [PATCH 050/399] dpaa_eth: enable context-A stashing Signed-off-by: Madalin Bucur --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 1b3ea38d014f..aa769cbc7425 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1052,7 +1052,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) /* Initialization common to all ingress queues */ if (dpaa_fq->flags & QMAN_FQ_FLAG_NO_ENQUEUE) { initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CONTEXTA); - initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE); + initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE | + QM_FQCTRL_CTXASTASHING); initfq.fqd.context_a.stashing.exclusive = QM_STASHING_EXCL_DATA | QM_STASHING_EXCL_CTX | QM_STASHING_EXCL_ANNOTATION; From 9bf881ffc5c0e65343fb51eef10dd989b36d1c1f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 6 Mar 2017 16:39:51 +0100 Subject: [PATCH 051/399] flow_dissector: Move ARP dissection into a separate function Make the main flow_dissect function a bit smaller and move the ARP dissection into a separate function. Along with that, do the ARP header processing only in case the flow dissection user requires it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 120 +++++++++++++++++++++----------------- 1 file changed, 67 insertions(+), 53 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index c35aae13c8d2..d79fb8f8f033 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -113,6 +113,66 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, } EXPORT_SYMBOL(__skb_flow_get_ports); +enum flow_dissect_ret { + FLOW_DISSECT_RET_OUT_GOOD, + FLOW_DISSECT_RET_OUT_BAD, +}; + +static enum flow_dissect_ret +__skb_flow_dissect_arp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, int hlen) +{ + struct flow_dissector_key_arp *key_arp; + struct { + unsigned char ar_sha[ETH_ALEN]; + unsigned char ar_sip[4]; + unsigned char ar_tha[ETH_ALEN]; + unsigned char ar_tip[4]; + } *arp_eth, _arp_eth; + const struct arphdr *arp; + struct arphdr *_arp; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) + return FLOW_DISSECT_RET_OUT_GOOD; + + arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, + hlen, &_arp); + if (!arp) + return FLOW_DISSECT_RET_OUT_BAD; + + if (arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_hln != ETH_ALEN || + arp->ar_pln != 4 || + (arp->ar_op != htons(ARPOP_REPLY) && + arp->ar_op != htons(ARPOP_REQUEST))) + return FLOW_DISSECT_RET_OUT_BAD; + + arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), + sizeof(_arp_eth), data, + hlen, &_arp_eth); + if (!arp_eth) + return FLOW_DISSECT_RET_OUT_BAD; + + key_arp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ARP, + target_container); + + memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); + memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); + + /* Only store the lower byte of the opcode; + * this covers ARPOP_REPLY and ARPOP_REQUEST. + */ + key_arp->op = ntohs(arp->ar_op) & 0xff; + + ether_addr_copy(key_arp->sha, arp_eth->ar_sha); + ether_addr_copy(key_arp->tha, arp_eth->ar_tha); + + return FLOW_DISSECT_RET_OUT_GOOD; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -138,7 +198,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; - struct flow_dissector_key_arp *key_arp; struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; @@ -382,60 +441,15 @@ bool __skb_flow_dissect(const struct sk_buff *skb, goto out_good; case htons(ETH_P_ARP): - case htons(ETH_P_RARP): { - struct { - unsigned char ar_sha[ETH_ALEN]; - unsigned char ar_sip[4]; - unsigned char ar_tha[ETH_ALEN]; - unsigned char ar_tip[4]; - } *arp_eth, _arp_eth; - const struct arphdr *arp; - struct arphdr *_arp; - - arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, - hlen, &_arp); - if (!arp) + case htons(ETH_P_RARP): + switch (__skb_flow_dissect_arp(skb, flow_dissector, + target_container, data, + nhoff, hlen)) { + case FLOW_DISSECT_RET_OUT_GOOD: + goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: goto out_bad; - - if (arp->ar_hrd != htons(ARPHRD_ETHER) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_hln != ETH_ALEN || - arp->ar_pln != 4 || - (arp->ar_op != htons(ARPOP_REPLY) && - arp->ar_op != htons(ARPOP_REQUEST))) - goto out_bad; - - arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), - sizeof(_arp_eth), data, - hlen, - &_arp_eth); - if (!arp_eth) - goto out_bad; - - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_ARP)) { - - key_arp = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_ARP, - target_container); - - memcpy(&key_arp->sip, arp_eth->ar_sip, - sizeof(key_arp->sip)); - memcpy(&key_arp->tip, arp_eth->ar_tip, - sizeof(key_arp->tip)); - - /* Only store the lower byte of the opcode; - * this covers ARPOP_REPLY and ARPOP_REQUEST. - */ - key_arp->op = ntohs(arp->ar_op) & 0xff; - - ether_addr_copy(key_arp->sha, arp_eth->ar_sha); - ether_addr_copy(key_arp->tha, arp_eth->ar_tha); } - - goto out_good; - } - default: goto out_bad; } From 4a5d6c8b14b81e3704607a354434321e390d228a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 6 Mar 2017 16:39:52 +0100 Subject: [PATCH 052/399] flow_dissector: Move MPLS dissection into a separate function Make the main flow_dissect function a bit smaller and move the MPLS dissection into a separate function. Along with that, do the MPLS header processing only in case the flow dissection user requires it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 56 ++++++++++++++++++++++++--------------- 1 file changed, 34 insertions(+), 22 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d79fb8f8f033..8d012987e3c3 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -118,6 +118,33 @@ enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_BAD, }; +static enum flow_dissect_ret +__skb_flow_dissect_mpls(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, int hlen) +{ + struct flow_dissector_key_keyid *key_keyid; + struct mpls_label *hdr, _hdr[2]; + + if (!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) + return FLOW_DISSECT_RET_OUT_GOOD; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, + hlen, &_hdr); + if (!hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >> + MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY, + target_container); + key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK); + } + return FLOW_DISSECT_RET_OUT_GOOD; +} + static enum flow_dissect_ret __skb_flow_dissect_arp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, @@ -408,31 +435,16 @@ bool __skb_flow_dissect(const struct sk_buff *skb, } case htons(ETH_P_MPLS_UC): - case htons(ETH_P_MPLS_MC): { - struct mpls_label *hdr, _hdr[2]; + case htons(ETH_P_MPLS_MC): mpls: - hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, - hlen, &_hdr); - if (!hdr) - goto out_bad; - - if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >> - MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) { - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { - key_keyid = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_MPLS_ENTROPY, - target_container); - key_keyid->keyid = hdr[1].entry & - htonl(MPLS_LS_LABEL_MASK); - } - + switch (__skb_flow_dissect_mpls(skb, flow_dissector, + target_container, data, + nhoff, hlen)) { + case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: + goto out_bad; } - - goto out_good; - } - case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) goto out_bad; From d5774b93f04252b81bd2c2cc84ec663c6aa798d1 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 6 Mar 2017 16:39:53 +0100 Subject: [PATCH 053/399] flow_dissector: Fix GRE header error path Now, when an unexpected element in the GRE header appears, we break so the l4 ports are processed. But since the ports are processed unconditionally, there will be certainly random values dissected. Fix this by just bailing out in such situations. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 8d012987e3c3..cefaf2368a3f 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -479,18 +479,18 @@ bool __skb_flow_dissect(const struct sk_buff *skb, /* Only look inside GRE without routing */ if (hdr->flags & GRE_ROUTING) - break; + goto out_good; /* Only look inside GRE for version 0 and 1 */ gre_ver = ntohs(hdr->flags & GRE_VERSION); if (gre_ver > 1) - break; + goto out_good; proto = hdr->protocol; if (gre_ver) { /* Version1 must be PPTP, and check the flags */ if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) - break; + goto out_good; } offset += sizeof(struct gre_base_hdr); From c5ef188e9318694a073ceacb26011f62d7ed9b3f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 6 Mar 2017 16:39:54 +0100 Subject: [PATCH 054/399] flow_dissector: rename "proto again" goto label Align with "ip_proto_again" label used in the same function and rename vague "again" to "proto_again". Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index cefaf2368a3f..912083576594 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -267,7 +267,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs)); } -again: +proto_again: switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; @@ -370,7 +370,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); if (skip_vlan) - goto again; + goto proto_again; } skip_vlan = true; @@ -393,7 +393,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, } } - goto again; + goto proto_again; } case htons(ETH_P_PPP_SES): { struct { @@ -577,7 +577,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) goto out_good; - goto again; + goto proto_again; } case NEXTHDR_HOP: case NEXTHDR_ROUTING: From 7c92de8eaabfff42f6f57466c12f255cbd718f58 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 6 Mar 2017 16:39:55 +0100 Subject: [PATCH 055/399] flow_dissector: Move GRE dissection into a separate function Make the main flow_dissect function a bit smaller and move the GRE dissection into a separate function. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 244 +++++++++++++++++++++----------------- 1 file changed, 134 insertions(+), 110 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 912083576594..5f3ae922fcd1 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -116,6 +116,7 @@ EXPORT_SYMBOL(__skb_flow_get_ports); enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_GOOD, FLOW_DISSECT_RET_OUT_BAD, + FLOW_DISSECT_RET_OUT_PROTO_AGAIN, }; static enum flow_dissect_ret @@ -200,6 +201,128 @@ __skb_flow_dissect_arp(const struct sk_buff *skb, return FLOW_DISSECT_RET_OUT_GOOD; } +static enum flow_dissect_ret +__skb_flow_dissect_gre(const struct sk_buff *skb, + struct flow_dissector_key_control *key_control, + struct flow_dissector *flow_dissector, + void *target_container, void *data, + __be16 *p_proto, int *p_nhoff, int *p_hlen, + unsigned int flags) +{ + struct flow_dissector_key_keyid *key_keyid; + struct gre_base_hdr *hdr, _hdr; + int offset = 0; + u16 gre_ver; + + hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), + data, *p_hlen, &_hdr); + if (!hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + /* Only look inside GRE without routing */ + if (hdr->flags & GRE_ROUTING) + return FLOW_DISSECT_RET_OUT_GOOD; + + /* Only look inside GRE for version 0 and 1 */ + gre_ver = ntohs(hdr->flags & GRE_VERSION); + if (gre_ver > 1) + return FLOW_DISSECT_RET_OUT_GOOD; + + *p_proto = hdr->protocol; + if (gre_ver) { + /* Version1 must be PPTP, and check the flags */ + if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) + return FLOW_DISSECT_RET_OUT_GOOD; + } + + offset += sizeof(struct gre_base_hdr); + + if (hdr->flags & GRE_CSUM) + offset += sizeof(((struct gre_full_hdr *) 0)->csum) + + sizeof(((struct gre_full_hdr *) 0)->reserved1); + + if (hdr->flags & GRE_KEY) { + const __be32 *keyid; + __be32 _keyid; + + keyid = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_keyid), + data, *p_hlen, &_keyid); + if (!keyid) + return FLOW_DISSECT_RET_OUT_BAD; + + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID)) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID, + target_container); + if (gre_ver == 0) + key_keyid->keyid = *keyid; + else + key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; + } + offset += sizeof(((struct gre_full_hdr *) 0)->key); + } + + if (hdr->flags & GRE_SEQ) + offset += sizeof(((struct pptp_gre_header *) 0)->seq); + + if (gre_ver == 0) { + if (*p_proto == htons(ETH_P_TEB)) { + const struct ethhdr *eth; + struct ethhdr _eth; + + eth = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_eth), + data, *p_hlen, &_eth); + if (!eth) + return FLOW_DISSECT_RET_OUT_BAD; + *p_proto = eth->h_proto; + offset += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + *p_hlen = *p_nhoff + offset; + } + } else { /* version 1, must be PPTP */ + u8 _ppp_hdr[PPP_HDRLEN]; + u8 *ppp_hdr; + + if (hdr->flags & GRE_ACK) + offset += sizeof(((struct pptp_gre_header *) 0)->ack); + + ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_ppp_hdr), + data, *p_hlen, _ppp_hdr); + if (!ppp_hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + switch (PPP_PROTOCOL(ppp_hdr)) { + case PPP_IP: + *p_proto = htons(ETH_P_IP); + break; + case PPP_IPV6: + *p_proto = htons(ETH_P_IPV6); + break; + default: + /* Could probably catch some more like MPLS */ + break; + } + + offset += PPP_HDRLEN; + } + + *p_nhoff += offset; + key_control->flags |= FLOW_DIS_ENCAPSULATION; + if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return FLOW_DISSECT_RET_OUT_GOOD; + + return FLOW_DISSECT_RET_OUT_PROTO_AGAIN; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -229,7 +352,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; - struct flow_dissector_key_keyid *key_keyid; bool skip_vlan = false; u8 ip_proto = 0; bool ret; @@ -443,6 +565,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; case FLOW_DISSECT_RET_OUT_BAD: + default: goto out_bad; } case htons(ETH_P_FCOE): @@ -460,6 +583,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; case FLOW_DISSECT_RET_OUT_BAD: + default: goto out_bad; } default: @@ -468,117 +592,17 @@ bool __skb_flow_dissect(const struct sk_buff *skb, ip_proto_again: switch (ip_proto) { - case IPPROTO_GRE: { - struct gre_base_hdr *hdr, _hdr; - u16 gre_ver; - int offset = 0; - - hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); - if (!hdr) + case IPPROTO_GRE: + switch (__skb_flow_dissect_gre(skb, key_control, flow_dissector, + target_container, data, + &proto, &nhoff, &hlen, flags)) { + case FLOW_DISSECT_RET_OUT_GOOD: + goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: goto out_bad; - - /* Only look inside GRE without routing */ - if (hdr->flags & GRE_ROUTING) - goto out_good; - - /* Only look inside GRE for version 0 and 1 */ - gre_ver = ntohs(hdr->flags & GRE_VERSION); - if (gre_ver > 1) - goto out_good; - - proto = hdr->protocol; - if (gre_ver) { - /* Version1 must be PPTP, and check the flags */ - if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) - goto out_good; + case FLOW_DISSECT_RET_OUT_PROTO_AGAIN: + goto proto_again; } - - offset += sizeof(struct gre_base_hdr); - - if (hdr->flags & GRE_CSUM) - offset += sizeof(((struct gre_full_hdr *)0)->csum) + - sizeof(((struct gre_full_hdr *)0)->reserved1); - - if (hdr->flags & GRE_KEY) { - const __be32 *keyid; - __be32 _keyid; - - keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid), - data, hlen, &_keyid); - if (!keyid) - goto out_bad; - - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_GRE_KEYID)) { - key_keyid = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_GRE_KEYID, - target_container); - if (gre_ver == 0) - key_keyid->keyid = *keyid; - else - key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; - } - offset += sizeof(((struct gre_full_hdr *)0)->key); - } - - if (hdr->flags & GRE_SEQ) - offset += sizeof(((struct pptp_gre_header *)0)->seq); - - if (gre_ver == 0) { - if (proto == htons(ETH_P_TEB)) { - const struct ethhdr *eth; - struct ethhdr _eth; - - eth = __skb_header_pointer(skb, nhoff + offset, - sizeof(_eth), - data, hlen, &_eth); - if (!eth) - goto out_bad; - proto = eth->h_proto; - offset += sizeof(*eth); - - /* Cap headers that we access via pointers at the - * end of the Ethernet header as our maximum alignment - * at that point is only 2 bytes. - */ - if (NET_IP_ALIGN) - hlen = (nhoff + offset); - } - } else { /* version 1, must be PPTP */ - u8 _ppp_hdr[PPP_HDRLEN]; - u8 *ppp_hdr; - - if (hdr->flags & GRE_ACK) - offset += sizeof(((struct pptp_gre_header *)0)->ack); - - ppp_hdr = __skb_header_pointer(skb, nhoff + offset, - sizeof(_ppp_hdr), - data, hlen, _ppp_hdr); - if (!ppp_hdr) - goto out_bad; - - switch (PPP_PROTOCOL(ppp_hdr)) { - case PPP_IP: - proto = htons(ETH_P_IP); - break; - case PPP_IPV6: - proto = htons(ETH_P_IPV6); - break; - default: - /* Could probably catch some more like MPLS */ - break; - } - - offset += PPP_HDRLEN; - } - - nhoff += offset; - key_control->flags |= FLOW_DIS_ENCAPSULATION; - if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) - goto out_good; - - goto proto_again; - } case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { From 95964c6de787eb21468a29b94e9d25e1a24d6a37 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Mar 2017 11:23:55 -0800 Subject: [PATCH 056/399] net: use proper lockdep annotation in __sk_dst_set() __sk_dst_set() must be called while we own the socket. We can get proper lockdep coverage using lockdep_sock_is_held() and rcu_dereference_protected() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 5e5997654db6..6db7693b9e61 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1780,11 +1780,8 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) sk_tx_queue_clear(sk); sk->sk_dst_pending_confirm = 0; - /* - * This can be called while sk is owned by the caller only, - * with no state that can be checked in a rcu_dereference_check() cond - */ - old_dst = rcu_dereference_raw(sk->sk_dst_cache); + old_dst = rcu_dereference_protected(sk->sk_dst_cache, + lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } From 1182e53639518698e3bc5a6cc9a09659623e7cac Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 6 Mar 2017 21:25:20 +0100 Subject: [PATCH 057/399] mlxsw: spectrum: Fix helper function and port variable names Commit dd82364c3ab9 ("mlxsw: Flip to the new dev walk API") did some small changes in mlxsw code, but it did not respect the naming conventions. So fix this now. Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 23 ++++++++++--------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 16484f24b7db..ae18067198dd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3326,13 +3326,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev) return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; } -static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data) +static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) { - struct mlxsw_sp_port **port = data; + struct mlxsw_sp_port **p_mlxsw_sp_port = data; int ret = 0; if (mlxsw_sp_port_dev_check(lower_dev)) { - *port = netdev_priv(lower_dev); + *p_mlxsw_sp_port = netdev_priv(lower_dev); ret = 1; } @@ -3341,15 +3341,15 @@ static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data) static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev) { - struct mlxsw_sp_port *port; + struct mlxsw_sp_port *mlxsw_sp_port; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - port = NULL; - netdev_walk_all_lower_dev(dev, mlxsw_lower_dev_walk, &port); + mlxsw_sp_port = NULL; + netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port); - return port; + return mlxsw_sp_port; } static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) @@ -3362,15 +3362,16 @@ static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev) { - struct mlxsw_sp_port *port; + struct mlxsw_sp_port *mlxsw_sp_port; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - port = NULL; - netdev_walk_all_lower_dev_rcu(dev, mlxsw_lower_dev_walk, &port); + mlxsw_sp_port = NULL; + netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk, + &mlxsw_sp_port); - return port; + return mlxsw_sp_port; } struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev) From 61793af6ab8b4455cdfd7a41b45991f8e3900dc8 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 6 Mar 2017 21:25:21 +0100 Subject: [PATCH 058/399] mlxsw: pci: Remove unused bit The overrun ignore bit isn't supported by the device's firmware and was recently removed from the programmer's reference manual (PRM). Remove it from the driver as well. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/cmd.h | 12 ------------ drivers/net/ethernet/mellanox/mlxsw/pci.c | 2 -- 2 files changed, 14 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index a1b48421648a..479511cf79bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -1043,13 +1043,6 @@ MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4); */ MLXSW_ITEM32(cmd_mbox, sw2hw_cq, c_eqn, 0x00, 24, 1); -/* cmd_mbox_sw2hw_cq_oi - * When set, overrun ignore is enabled. When set, updates of - * CQ consumer counter (poll for completion) or Request completion - * notifications (Arm CQ) DoorBells should not be rung on that CQ. - */ -MLXSW_ITEM32(cmd_mbox, sw2hw_cq, oi, 0x00, 12, 1); - /* cmd_mbox_sw2hw_cq_st * Event delivery state machine * 0x0 - FIRED @@ -1132,11 +1125,6 @@ static inline int mlxsw_cmd_sw2hw_eq(struct mlxsw_core *mlxsw_core, */ MLXSW_ITEM32(cmd_mbox, sw2hw_eq, int_msix, 0x00, 24, 1); -/* cmd_mbox_sw2hw_eq_oi - * When set, overrun ignore is enabled. - */ -MLXSW_ITEM32(cmd_mbox, sw2hw_eq, oi, 0x00, 12, 1); - /* cmd_mbox_sw2hw_eq_st * Event delivery state machine * 0x0 - FIRED diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index a223c85dfde0..ffeb746fe2f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -580,7 +580,6 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */ mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM); - mlxsw_cmd_mbox_sw2hw_cq_oi_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count)); for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) { @@ -755,7 +754,6 @@ static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, } mlxsw_cmd_mbox_sw2hw_eq_int_msix_set(mbox, 1); /* MSI-X used */ - mlxsw_cmd_mbox_sw2hw_eq_oi_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_eq_st_set(mbox, 1); /* armed */ mlxsw_cmd_mbox_sw2hw_eq_log_eq_size_set(mbox, ilog2(q->count)); for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) { From 69ba943151b2e40e201700cf5b3a94e433c6fd83 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:06 -0800 Subject: [PATCH 059/399] mlx4: dma_dir is a mlx4_en_priv attribute No need to duplicate it for all queues and frags. num_frags & log_rx_info become u8 to save space. u8 accesses are a bit faster than u16 anyway. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 16 ++++++++-------- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 +- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 6 +++--- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 867292880c07..6183128b2d3d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -72,7 +72,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, return -ENOMEM; } dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order, - frag_info->dma_dir); + priv->dma_dir); if (unlikely(dma_mapping_error(priv->ddev, dma))) { put_page(page); return -ENOMEM; @@ -128,7 +128,7 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, if (page_alloc[i].page != ring_alloc[i].page) { dma_unmap_page(priv->ddev, page_alloc[i].dma, page_alloc[i].page_size, - priv->frag_info[i].dma_dir); + priv->dma_dir); page = page_alloc[i].page; /* Revert changes done by mlx4_alloc_pages */ page_ref_sub(page, page_alloc[i].page_size / @@ -149,7 +149,7 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv, if (next_frag_end > frags[i].page_size) dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size, - frag_info->dma_dir); + priv->dma_dir); if (frags[i].page) put_page(frags[i].page); @@ -181,7 +181,7 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv, page_alloc = &ring->page_alloc[i]; dma_unmap_page(priv->ddev, page_alloc->dma, page_alloc->page_size, - priv->frag_info[i].dma_dir); + priv->dma_dir); page = page_alloc->page; /* Revert changes done by mlx4_alloc_pages */ page_ref_sub(page, page_alloc->page_size / @@ -206,7 +206,7 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, i, page_count(page_alloc->page)); dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, frag_info->dma_dir); + page_alloc->page_size, priv->dma_dir); while (page_alloc->page_offset + frag_info->frag_stride < page_alloc->page_size) { put_page(page_alloc->page); @@ -570,7 +570,7 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i]; dma_unmap_page(priv->ddev, frame->dma, frame->page_size, - priv->frag_info[0].dma_dir); + priv->dma_dir); put_page(frame->page); } ring->page_cache.index = 0; @@ -1202,7 +1202,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) * expense of more costly truesize accounting */ priv->frag_info[0].frag_stride = PAGE_SIZE; - priv->frag_info[0].dma_dir = PCI_DMA_BIDIRECTIONAL; + priv->dma_dir = PCI_DMA_BIDIRECTIONAL; priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM; i = 1; } else { @@ -1217,11 +1217,11 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) priv->frag_info[i].frag_stride = ALIGN(priv->frag_info[i].frag_size, SMP_CACHE_BYTES); - priv->frag_info[i].dma_dir = PCI_DMA_FROMDEVICE; priv->frag_info[i].rx_headroom = 0; buf_size += priv->frag_info[i].frag_size; i++; } + priv->dma_dir = PCI_DMA_FROMDEVICE; } priv->num_frags = i; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 3ed42199d3f1..98bc67a7249b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -360,7 +360,7 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) { dma_unmap_page(priv->ddev, tx_info->map0_dma, - PAGE_SIZE, priv->frag_info[0].dma_dir); + PAGE_SIZE, priv->dma_dir); put_page(tx_info->page); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 3629ce11a68b..a4c7d94d52c6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -474,7 +474,6 @@ struct mlx4_en_frag_info { u16 frag_size; u16 frag_prefix_size; u32 frag_stride; - enum dma_data_direction dma_dir; u16 order; u16 rx_headroom; }; @@ -584,8 +583,9 @@ struct mlx4_en_priv { u32 rx_ring_num; u32 rx_skb_size; struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS]; - u16 num_frags; - u16 log_rx_info; + u8 num_frags; + u8 log_rx_info; + u8 dma_dir; struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES]; struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS]; From 159ddfd2ca30a2361324111ef64fdedf43e7dc32 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:07 -0800 Subject: [PATCH 060/399] mlx4: remove order field from mlx4_en_frag_info This is really a port attribute, no need to duplicate it per RX queue and per frag. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 6183128b2d3d..b78d6762e03f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -59,7 +59,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, struct page *page; dma_addr_t dma; - for (order = frag_info->order; ;) { + for (order = priv->rx_page_order; ;) { gfp_t gfp = _gfp; if (order) @@ -1195,7 +1195,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) * This only works when num_frags == 1. */ if (priv->tx_ring_num[TX_XDP]) { - priv->frag_info[0].order = 0; + priv->rx_page_order = 0; priv->frag_info[0].frag_size = eff_mtu; priv->frag_info[0].frag_prefix_size = 0; /* This will gain efficient xdp frame recycling at the @@ -1209,7 +1209,6 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) int buf_size = 0; while (buf_size < eff_mtu) { - priv->frag_info[i].order = MLX4_EN_ALLOC_PREFER_ORDER; priv->frag_info[i].frag_size = (eff_mtu > buf_size + frag_sizes[i]) ? frag_sizes[i] : eff_mtu - buf_size; @@ -1221,6 +1220,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) buf_size += priv->frag_info[i].frag_size; i++; } + priv->rx_page_order = MLX4_EN_ALLOC_PREFER_ORDER; priv->dma_dir = PCI_DMA_FROMDEVICE; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index a4c7d94d52c6..9d2c53ddb15c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -474,7 +474,6 @@ struct mlx4_en_frag_info { u16 frag_size; u16 frag_prefix_size; u32 frag_stride; - u16 order; u16 rx_headroom; }; @@ -586,6 +585,7 @@ struct mlx4_en_priv { u8 num_frags; u8 log_rx_info; u8 dma_dir; + u8 rx_page_order; struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES]; struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS]; From aaca121dd6cfedc9afb9d0ee23ded9d84e217e20 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:08 -0800 Subject: [PATCH 061/399] mlx4: get rid of frag_prefix_size Using per frag storage for frag_prefix_size is really silly. mlx4_en_complete_rx_desc() has all needed info already. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 27 +++++++++----------- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 +-- 2 files changed, 13 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b78d6762e03f..118ea83cff08 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -588,15 +588,14 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, int length) { struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags; - struct mlx4_en_frag_info *frag_info; - int nr; + struct mlx4_en_frag_info *frag_info = priv->frag_info; + int nr, frag_size; dma_addr_t dma; /* Collect used fragments while replacing them in the HW descriptors */ - for (nr = 0; nr < priv->num_frags; nr++) { - frag_info = &priv->frag_info[nr]; - if (length <= frag_info->frag_prefix_size) - break; + for (nr = 0;;) { + frag_size = min_t(int, length, frag_info->frag_size); + if (unlikely(!frags[nr].page)) goto fail; @@ -606,15 +605,16 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, __skb_fill_page_desc(skb, nr, frags[nr].page, frags[nr].page_offset, - frag_info->frag_size); + frag_size); skb->truesize += frag_info->frag_stride; frags[nr].page = NULL; + nr++; + length -= frag_size; + if (!length) + break; + frag_info++; } - /* Adjust size of last fragment to match actual length */ - if (nr > 0) - skb_frag_size_set(&skb_frags_rx[nr - 1], - length - priv->frag_info[nr - 1].frag_prefix_size); return nr; fail: @@ -1197,7 +1197,6 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) if (priv->tx_ring_num[TX_XDP]) { priv->rx_page_order = 0; priv->frag_info[0].frag_size = eff_mtu; - priv->frag_info[0].frag_prefix_size = 0; /* This will gain efficient xdp frame recycling at the * expense of more costly truesize accounting */ @@ -1212,7 +1211,6 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) priv->frag_info[i].frag_size = (eff_mtu > buf_size + frag_sizes[i]) ? frag_sizes[i] : eff_mtu - buf_size; - priv->frag_info[i].frag_prefix_size = buf_size; priv->frag_info[i].frag_stride = ALIGN(priv->frag_info[i].frag_size, SMP_CACHE_BYTES); @@ -1232,10 +1230,9 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) eff_mtu, priv->num_frags); for (i = 0; i < priv->num_frags; i++) { en_err(priv, - " frag:%d - size:%d prefix:%d stride:%d\n", + " frag:%d - size:%d stride:%d\n", i, priv->frag_info[i].frag_size, - priv->frag_info[i].frag_prefix_size, priv->frag_info[i].frag_stride); } } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 9d2c53ddb15c..849aa8af4dd7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -472,9 +472,8 @@ struct mlx4_en_mc_list { struct mlx4_en_frag_info { u16 frag_size; - u16 frag_prefix_size; - u32 frag_stride; u16 rx_headroom; + u32 frag_stride; }; #ifdef CONFIG_MLX4_EN_DCB From d85f6c14e967b0bddfa9712daa17d79e297d18b8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:09 -0800 Subject: [PATCH 062/399] mlx4: rx_headroom is a per port attribute No need to duplicate it per RX queue / frags. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 118ea83cff08..bb33032a280f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -115,7 +115,7 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, for (i = 0; i < priv->num_frags; i++) { frags[i] = ring_alloc[i]; - frags[i].page_offset += priv->frag_info[i].rx_headroom; + frags[i].page_offset += priv->rx_headroom; rx_desc->data[i].addr = cpu_to_be64(frags[i].dma + frags[i].page_offset); ring_alloc[i] = page_alloc[i]; @@ -1202,7 +1202,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) */ priv->frag_info[0].frag_stride = PAGE_SIZE; priv->dma_dir = PCI_DMA_BIDIRECTIONAL; - priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM; + priv->rx_headroom = XDP_PACKET_HEADROOM; i = 1; } else { int buf_size = 0; @@ -1214,12 +1214,12 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) priv->frag_info[i].frag_stride = ALIGN(priv->frag_info[i].frag_size, SMP_CACHE_BYTES); - priv->frag_info[i].rx_headroom = 0; buf_size += priv->frag_info[i].frag_size; i++; } priv->rx_page_order = MLX4_EN_ALLOC_PREFER_ORDER; priv->dma_dir = PCI_DMA_FROMDEVICE; + priv->rx_headroom = 0; } priv->num_frags = i; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 849aa8af4dd7..fc7b4da5d8c3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -472,7 +472,6 @@ struct mlx4_en_mc_list { struct mlx4_en_frag_info { u16 frag_size; - u16 rx_headroom; u32 frag_stride; }; @@ -585,6 +584,7 @@ struct mlx4_en_priv { u8 log_rx_info; u8 dma_dir; u8 rx_page_order; + u16 rx_headroom; struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES]; struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS]; From acd7628de05c73118aab7ae4847a5b5b2c6999c9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:10 -0800 Subject: [PATCH 063/399] mlx4: reduce rx ring page_cache size We only need to store the page and dma address. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 17 ++++++++++------- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 -- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 6 +++++- 3 files changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index bb33032a280f..453313d404e3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -250,7 +250,10 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, (index << priv->log_rx_info); if (ring->page_cache.index > 0) { - frags[0] = ring->page_cache.buf[--ring->page_cache.index]; + ring->page_cache.index--; + frags[0].page = ring->page_cache.buf[ring->page_cache.index].page; + frags[0].dma = ring->page_cache.buf[ring->page_cache.index].dma; + frags[0].page_offset = XDP_PACKET_HEADROOM; rx_desc->data[0].addr = cpu_to_be64(frags[0].dma + frags[0].page_offset); return 0; @@ -537,7 +540,9 @@ bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, if (cache->index >= MLX4_EN_CACHE_SIZE) return false; - cache->buf[cache->index++] = *frame; + cache->buf[cache->index].page = frame->page; + cache->buf[cache->index].dma = frame->dma; + cache->index++; return true; } @@ -567,11 +572,9 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv, int i; for (i = 0; i < ring->page_cache.index; i++) { - struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i]; - - dma_unmap_page(priv->ddev, frame->dma, frame->page_size, - priv->dma_dir); - put_page(frame->page); + dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma, + PAGE_SIZE, priv->dma_dir); + put_page(ring->page_cache.buf[i].page); } ring->page_cache.index = 0; mlx4_en_free_rx_buf(priv, ring); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 98bc67a7249b..e0c5ffb3e3a6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -354,8 +354,6 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_rx_alloc frame = { .page = tx_info->page, .dma = tx_info->map0_dma, - .page_offset = XDP_PACKET_HEADROOM, - .page_size = PAGE_SIZE, }; if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index fc7b4da5d8c3..c98940c6acd0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -268,9 +268,13 @@ struct mlx4_en_rx_alloc { }; #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT) + struct mlx4_en_page_cache { u32 index; - struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE]; + struct { + struct page *page; + dma_addr_t dma; + } buf[MLX4_EN_CACHE_SIZE]; }; struct mlx4_en_priv; From 60c7f5ae5416a8491216bcccf6b3b3d842d69fa4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:11 -0800 Subject: [PATCH 064/399] mlx4: removal of frag_sizes[] We will soon use order-0 pages, and frag truesize will more precisely match real sizes. In the new model, we prefer to use <= 2048 bytes fragments, so that we can use page-recycle technique on PAGE_SIZE=4096 arches. We will still pack as much frames as possible on arches with big pages, like PowerPC. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 24 ++++++++------------ drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 8 ------- 2 files changed, 10 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 453313d404e3..0c61c1200f2a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -1181,13 +1181,6 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget) return done; } -static const int frag_sizes[] = { - FRAG_SZ0, - FRAG_SZ1, - FRAG_SZ2, - FRAG_SZ3 -}; - void mlx4_en_calc_rx_buf(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -1211,13 +1204,16 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) int buf_size = 0; while (buf_size < eff_mtu) { - priv->frag_info[i].frag_size = - (eff_mtu > buf_size + frag_sizes[i]) ? - frag_sizes[i] : eff_mtu - buf_size; - priv->frag_info[i].frag_stride = - ALIGN(priv->frag_info[i].frag_size, - SMP_CACHE_BYTES); - buf_size += priv->frag_info[i].frag_size; + int frag_size = eff_mtu - buf_size; + + if (i < MLX4_EN_MAX_RX_FRAGS - 1) + frag_size = min(frag_size, 2048); + + priv->frag_info[i].frag_size = frag_size; + + priv->frag_info[i].frag_stride = ALIGN(frag_size, + SMP_CACHE_BYTES); + buf_size += frag_size; i++; } priv->rx_page_order = MLX4_EN_ALLOC_PREFER_ORDER; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index c98940c6acd0..608396dc6d95 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -105,14 +105,6 @@ #define MLX4_EN_ALLOC_PREFER_ORDER min_t(int, get_order(32768), \ PAGE_ALLOC_COSTLY_ORDER) -/* Receive fragment sizes; we use at most 3 fragments (for 9600 byte MTU - * and 4K allocations) */ -enum { - FRAG_SZ0 = 1536 - NET_IP_ALIGN, - FRAG_SZ1 = 4096, - FRAG_SZ2 = 4096, - FRAG_SZ3 = MLX4_EN_ALLOC_SIZE -}; #define MLX4_EN_MAX_RX_FRAGS 4 /* Maximum ring sizes */ From b5a54d9a313645ec9607dc557b67d9325c28884c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:12 -0800 Subject: [PATCH 065/399] mlx4: use order-0 pages for RX Use of order-3 pages is problematic in some cases. This patch might add three kinds of regression : 1) a CPU performance regression, but we will add later page recycling and performance should be back. 2) TCP receiver could grow its receive window slightly slower, because skb->len/skb->truesize ratio will decrease. This is mostly ok, we prefer being conservative to not risk OOM, and eventually tune TCP better in the future. This is consistent with other drivers using 2048 per ethernet frame. 3) Because we allocate one page per RX slot, we consume more memory for the ring buffers. XDP already had this constraint anyway. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 72 +++++++++----------- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 5 -- 2 files changed, 33 insertions(+), 44 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 0c61c1200f2a..069ea09185fb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -53,38 +53,26 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, struct mlx4_en_rx_alloc *page_alloc, const struct mlx4_en_frag_info *frag_info, - gfp_t _gfp) + gfp_t gfp) { - int order; struct page *page; dma_addr_t dma; - for (order = priv->rx_page_order; ;) { - gfp_t gfp = _gfp; - - if (order) - gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NOMEMALLOC; - page = alloc_pages(gfp, order); - if (likely(page)) - break; - if (--order < 0 || - ((PAGE_SIZE << order) < frag_info->frag_size)) - return -ENOMEM; - } - dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order, - priv->dma_dir); + page = alloc_page(gfp); + if (unlikely(!page)) + return -ENOMEM; + dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir); if (unlikely(dma_mapping_error(priv->ddev, dma))) { put_page(page); return -ENOMEM; } - page_alloc->page_size = PAGE_SIZE << order; page_alloc->page = page; page_alloc->dma = dma; page_alloc->page_offset = 0; /* Not doing get_page() for each frag is a big win * on asymetric workloads. Note we can not use atomic_set(). */ - page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1); + page_ref_add(page, PAGE_SIZE / frag_info->frag_stride - 1); return 0; } @@ -105,7 +93,7 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, page_alloc[i].page_offset += frag_info->frag_stride; if (page_alloc[i].page_offset + frag_info->frag_stride <= - ring_alloc[i].page_size) + PAGE_SIZE) continue; if (unlikely(mlx4_alloc_pages(priv, &page_alloc[i], @@ -127,11 +115,10 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, while (i--) { if (page_alloc[i].page != ring_alloc[i].page) { dma_unmap_page(priv->ddev, page_alloc[i].dma, - page_alloc[i].page_size, - priv->dma_dir); + PAGE_SIZE, priv->dma_dir); page = page_alloc[i].page; /* Revert changes done by mlx4_alloc_pages */ - page_ref_sub(page, page_alloc[i].page_size / + page_ref_sub(page, PAGE_SIZE / priv->frag_info[i].frag_stride - 1); put_page(page); } @@ -147,8 +134,8 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv, u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride; - if (next_frag_end > frags[i].page_size) - dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size, + if (next_frag_end > PAGE_SIZE) + dma_unmap_page(priv->ddev, frags[i].dma, PAGE_SIZE, priv->dma_dir); if (frags[i].page) @@ -168,9 +155,8 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv, frag_info, GFP_KERNEL | __GFP_COLD)) goto out; - en_dbg(DRV, priv, " frag %d allocator: - size:%d frags:%d\n", - i, ring->page_alloc[i].page_size, - page_ref_count(ring->page_alloc[i].page)); + en_dbg(DRV, priv, " frag %d allocator: - frags:%d\n", + i, page_ref_count(ring->page_alloc[i].page)); } return 0; @@ -180,11 +166,10 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv, page_alloc = &ring->page_alloc[i]; dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, - priv->dma_dir); + PAGE_SIZE, priv->dma_dir); page = page_alloc->page; /* Revert changes done by mlx4_alloc_pages */ - page_ref_sub(page, page_alloc->page_size / + page_ref_sub(page, PAGE_SIZE / priv->frag_info[i].frag_stride - 1); put_page(page); page_alloc->page = NULL; @@ -206,9 +191,9 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, i, page_count(page_alloc->page)); dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->page_size, priv->dma_dir); + PAGE_SIZE, priv->dma_dir); while (page_alloc->page_offset + frag_info->frag_stride < - page_alloc->page_size) { + PAGE_SIZE) { put_page(page_alloc->page); page_alloc->page_offset += frag_info->frag_stride; } @@ -1191,7 +1176,6 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) * This only works when num_frags == 1. */ if (priv->tx_ring_num[TX_XDP]) { - priv->rx_page_order = 0; priv->frag_info[0].frag_size = eff_mtu; /* This will gain efficient xdp frame recycling at the * expense of more costly truesize accounting @@ -1201,22 +1185,32 @@ void mlx4_en_calc_rx_buf(struct net_device *dev) priv->rx_headroom = XDP_PACKET_HEADROOM; i = 1; } else { - int buf_size = 0; + int frag_size_max = 2048, buf_size = 0; + + /* should not happen, right ? */ + if (eff_mtu > PAGE_SIZE + (MLX4_EN_MAX_RX_FRAGS - 1) * 2048) + frag_size_max = PAGE_SIZE; while (buf_size < eff_mtu) { - int frag_size = eff_mtu - buf_size; + int frag_stride, frag_size = eff_mtu - buf_size; + int pad, nb; if (i < MLX4_EN_MAX_RX_FRAGS - 1) - frag_size = min(frag_size, 2048); + frag_size = min(frag_size, frag_size_max); priv->frag_info[i].frag_size = frag_size; + frag_stride = ALIGN(frag_size, SMP_CACHE_BYTES); + /* We can only pack 2 1536-bytes frames in on 4K page + * Therefore, each frame would consume more bytes (truesize) + */ + nb = PAGE_SIZE / frag_stride; + pad = (PAGE_SIZE - nb * frag_stride) / nb; + pad &= ~(SMP_CACHE_BYTES - 1); + priv->frag_info[i].frag_stride = frag_stride + pad; - priv->frag_info[i].frag_stride = ALIGN(frag_size, - SMP_CACHE_BYTES); buf_size += frag_size; i++; } - priv->rx_page_order = MLX4_EN_ALLOC_PREFER_ORDER; priv->dma_dir = PCI_DMA_FROMDEVICE; priv->rx_headroom = 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 608396dc6d95..6c80117006ed 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -102,9 +102,6 @@ /* Use the maximum between 16384 and a single page */ #define MLX4_EN_ALLOC_SIZE PAGE_ALIGN(16384) -#define MLX4_EN_ALLOC_PREFER_ORDER min_t(int, get_order(32768), \ - PAGE_ALLOC_COSTLY_ORDER) - #define MLX4_EN_MAX_RX_FRAGS 4 /* Maximum ring sizes */ @@ -256,7 +253,6 @@ struct mlx4_en_rx_alloc { struct page *page; dma_addr_t dma; u32 page_offset; - u32 page_size; }; #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT) @@ -579,7 +575,6 @@ struct mlx4_en_priv { u8 num_frags; u8 log_rx_info; u8 dma_dir; - u8 rx_page_order; u16 rx_headroom; struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES]; From 34db548bfb9580f33d9a7faecafe4da61a4428a3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:13 -0800 Subject: [PATCH 066/399] mlx4: add page recycling in receive path Same technique than some Intel drivers, for arches where PAGE_SIZE = 4096 In most cases, pages are reused because they were consumed before we could loop around the RX ring. This brings back performance, and is even better, a single TCP flow reaches 30Gbit on my hosts. v2: added full memset() in mlx4_en_free_frag(), as Tariq found it was needed if we switch to large MTU, as priv->log_rx_info can dynamically be changed. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 258 ++++++------------- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 1 - 2 files changed, 82 insertions(+), 177 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 069ea09185fb..5edd0cf2999c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -50,10 +50,9 @@ #include "mlx4_en.h" -static int mlx4_alloc_pages(struct mlx4_en_priv *priv, - struct mlx4_en_rx_alloc *page_alloc, - const struct mlx4_en_frag_info *frag_info, - gfp_t gfp) +static int mlx4_alloc_page(struct mlx4_en_priv *priv, + struct mlx4_en_rx_alloc *frag, + gfp_t gfp) { struct page *page; dma_addr_t dma; @@ -63,145 +62,46 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, return -ENOMEM; dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir); if (unlikely(dma_mapping_error(priv->ddev, dma))) { - put_page(page); + __free_page(page); return -ENOMEM; } - page_alloc->page = page; - page_alloc->dma = dma; - page_alloc->page_offset = 0; - /* Not doing get_page() for each frag is a big win - * on asymetric workloads. Note we can not use atomic_set(). - */ - page_ref_add(page, PAGE_SIZE / frag_info->frag_stride - 1); + frag->page = page; + frag->dma = dma; + frag->page_offset = priv->rx_headroom; return 0; } static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, struct mlx4_en_rx_desc *rx_desc, struct mlx4_en_rx_alloc *frags, - struct mlx4_en_rx_alloc *ring_alloc, gfp_t gfp) { - struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS]; - const struct mlx4_en_frag_info *frag_info; - struct page *page; int i; - for (i = 0; i < priv->num_frags; i++) { - frag_info = &priv->frag_info[i]; - page_alloc[i] = ring_alloc[i]; - page_alloc[i].page_offset += frag_info->frag_stride; - - if (page_alloc[i].page_offset + frag_info->frag_stride <= - PAGE_SIZE) - continue; - - if (unlikely(mlx4_alloc_pages(priv, &page_alloc[i], - frag_info, gfp))) - goto out; - } - - for (i = 0; i < priv->num_frags; i++) { - frags[i] = ring_alloc[i]; - frags[i].page_offset += priv->rx_headroom; - rx_desc->data[i].addr = cpu_to_be64(frags[i].dma + - frags[i].page_offset); - ring_alloc[i] = page_alloc[i]; - } - - return 0; - -out: - while (i--) { - if (page_alloc[i].page != ring_alloc[i].page) { - dma_unmap_page(priv->ddev, page_alloc[i].dma, - PAGE_SIZE, priv->dma_dir); - page = page_alloc[i].page; - /* Revert changes done by mlx4_alloc_pages */ - page_ref_sub(page, PAGE_SIZE / - priv->frag_info[i].frag_stride - 1); - put_page(page); - } - } - return -ENOMEM; -} - -static void mlx4_en_free_frag(struct mlx4_en_priv *priv, - struct mlx4_en_rx_alloc *frags, - int i) -{ - const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; - u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride; - - - if (next_frag_end > PAGE_SIZE) - dma_unmap_page(priv->ddev, frags[i].dma, PAGE_SIZE, - priv->dma_dir); - - if (frags[i].page) - put_page(frags[i].page); -} - -static int mlx4_en_init_allocator(struct mlx4_en_priv *priv, - struct mlx4_en_rx_ring *ring) -{ - int i; - struct mlx4_en_rx_alloc *page_alloc; - - for (i = 0; i < priv->num_frags; i++) { - const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; - - if (mlx4_alloc_pages(priv, &ring->page_alloc[i], - frag_info, GFP_KERNEL | __GFP_COLD)) - goto out; - - en_dbg(DRV, priv, " frag %d allocator: - frags:%d\n", - i, page_ref_count(ring->page_alloc[i].page)); + for (i = 0; i < priv->num_frags; i++, frags++) { + if (!frags->page && mlx4_alloc_page(priv, frags, gfp)) + return -ENOMEM; + rx_desc->data[i].addr = cpu_to_be64(frags->dma + + frags->page_offset); } return 0; - -out: - while (i--) { - struct page *page; - - page_alloc = &ring->page_alloc[i]; - dma_unmap_page(priv->ddev, page_alloc->dma, - PAGE_SIZE, priv->dma_dir); - page = page_alloc->page; - /* Revert changes done by mlx4_alloc_pages */ - page_ref_sub(page, PAGE_SIZE / - priv->frag_info[i].frag_stride - 1); - put_page(page); - page_alloc->page = NULL; - } - return -ENOMEM; } -static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, - struct mlx4_en_rx_ring *ring) +static void mlx4_en_free_frag(const struct mlx4_en_priv *priv, + struct mlx4_en_rx_alloc *frag) { - struct mlx4_en_rx_alloc *page_alloc; - int i; - - for (i = 0; i < priv->num_frags; i++) { - const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; - - page_alloc = &ring->page_alloc[i]; - en_dbg(DRV, priv, "Freeing allocator:%d count:%d\n", - i, page_count(page_alloc->page)); - - dma_unmap_page(priv->ddev, page_alloc->dma, + if (frag->page) { + dma_unmap_page(priv->ddev, frag->dma, PAGE_SIZE, priv->dma_dir); - while (page_alloc->page_offset + frag_info->frag_stride < - PAGE_SIZE) { - put_page(page_alloc->page); - page_alloc->page_offset += frag_info->frag_stride; - } - page_alloc->page = NULL; + __free_page(frag->page); } + /* We need to clear all fields, otherwise a change of priv->log_rx_info + * could lead to see garbage later in frag->page. + */ + memset(frag, 0, sizeof(*frag)); } -static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv, +static void mlx4_en_init_rx_desc(const struct mlx4_en_priv *priv, struct mlx4_en_rx_ring *ring, int index) { struct mlx4_en_rx_desc *rx_desc = ring->buf + ring->stride * index; @@ -235,19 +135,22 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, (index << priv->log_rx_info); if (ring->page_cache.index > 0) { - ring->page_cache.index--; - frags[0].page = ring->page_cache.buf[ring->page_cache.index].page; - frags[0].dma = ring->page_cache.buf[ring->page_cache.index].dma; - frags[0].page_offset = XDP_PACKET_HEADROOM; - rx_desc->data[0].addr = cpu_to_be64(frags[0].dma + - frags[0].page_offset); + /* XDP uses a single page per frame */ + if (!frags->page) { + ring->page_cache.index--; + frags->page = ring->page_cache.buf[ring->page_cache.index].page; + frags->dma = ring->page_cache.buf[ring->page_cache.index].dma; + } + frags->page_offset = XDP_PACKET_HEADROOM; + rx_desc->data[0].addr = cpu_to_be64(frags->dma + + XDP_PACKET_HEADROOM); return 0; } - return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp); + return mlx4_en_alloc_frags(priv, rx_desc, frags, gfp); } -static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring) +static bool mlx4_en_is_ring_empty(const struct mlx4_en_rx_ring *ring) { return ring->prod == ring->cons; } @@ -257,7 +160,8 @@ static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring) *ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff); } -static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv, +/* slow path */ +static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv, struct mlx4_en_rx_ring *ring, int index) { @@ -267,7 +171,7 @@ static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv, frags = ring->rx_info + (index << priv->log_rx_info); for (nr = 0; nr < priv->num_frags; nr++) { en_dbg(DRV, priv, "Freeing fragment:%d\n", nr); - mlx4_en_free_frag(priv, frags, nr); + mlx4_en_free_frag(priv, frags + nr); } } @@ -323,12 +227,12 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv, ring->cons, ring->prod); /* Unmap and free Rx buffers */ - while (!mlx4_en_is_ring_empty(ring)) { - index = ring->cons & ring->size_mask; + for (index = 0; index < ring->size; index++) { en_dbg(DRV, priv, "Processing descriptor:%d\n", index); mlx4_en_free_rx_desc(priv, ring, index); - ++ring->cons; } + ring->cons = 0; + ring->prod = 0; } void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev) @@ -380,9 +284,9 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS * sizeof(struct mlx4_en_rx_alloc)); - ring->rx_info = vmalloc_node(tmp, node); + ring->rx_info = vzalloc_node(tmp, node); if (!ring->rx_info) { - ring->rx_info = vmalloc(tmp); + ring->rx_info = vzalloc(tmp); if (!ring->rx_info) { err = -ENOMEM; goto err_ring; @@ -452,16 +356,6 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv) /* Initialize all descriptors */ for (i = 0; i < ring->size; i++) mlx4_en_init_rx_desc(priv, ring, i); - - /* Initialize page allocators */ - err = mlx4_en_init_allocator(priv, ring); - if (err) { - en_err(priv, "Failed initializing ring allocator\n"); - if (ring->stride <= TXBB_SIZE) - ring->buf -= TXBB_SIZE; - ring_ind--; - goto err_allocator; - } } err = mlx4_en_fill_rx_buffers(priv); if (err) @@ -481,11 +375,9 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv) mlx4_en_free_rx_buf(priv, priv->rx_ring[ring_ind]); ring_ind = priv->rx_ring_num - 1; -err_allocator: while (ring_ind >= 0) { if (priv->rx_ring[ring_ind]->stride <= TXBB_SIZE) priv->rx_ring[ring_ind]->buf -= TXBB_SIZE; - mlx4_en_destroy_allocator(priv, priv->rx_ring[ring_ind]); ring_ind--; } return err; @@ -565,50 +457,68 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv, mlx4_en_free_rx_buf(priv, ring); if (ring->stride <= TXBB_SIZE) ring->buf -= TXBB_SIZE; - mlx4_en_destroy_allocator(priv, ring); } static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, - struct mlx4_en_rx_desc *rx_desc, struct mlx4_en_rx_alloc *frags, struct sk_buff *skb, int length) { - struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags; - struct mlx4_en_frag_info *frag_info = priv->frag_info; + const struct mlx4_en_frag_info *frag_info = priv->frag_info; + unsigned int truesize = 0; int nr, frag_size; + struct page *page; dma_addr_t dma; + bool release; /* Collect used fragments while replacing them in the HW descriptors */ - for (nr = 0;;) { + for (nr = 0;; frags++) { frag_size = min_t(int, length, frag_info->frag_size); - if (unlikely(!frags[nr].page)) + page = frags->page; + if (unlikely(!page)) goto fail; - dma = be64_to_cpu(rx_desc->data[nr].addr); - dma_sync_single_for_cpu(priv->ddev, dma, frag_info->frag_size, - DMA_FROM_DEVICE); + dma = frags->dma; + dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset, + frag_size, priv->dma_dir); - __skb_fill_page_desc(skb, nr, frags[nr].page, - frags[nr].page_offset, + __skb_fill_page_desc(skb, nr, page, frags->page_offset, frag_size); - skb->truesize += frag_info->frag_stride; - frags[nr].page = NULL; + truesize += frag_info->frag_stride; + if (frag_info->frag_stride == PAGE_SIZE / 2) { + frags->page_offset ^= PAGE_SIZE / 2; + release = page_count(page) != 1 || + page_is_pfmemalloc(page) || + page_to_nid(page) != numa_mem_id(); + } else { + u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES); + + frags->page_offset += sz_align; + release = frags->page_offset + frag_info->frag_size > PAGE_SIZE; + } + if (release) { + dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir); + frags->page = NULL; + } else { + page_ref_inc(page); + } + nr++; length -= frag_size; if (!length) break; frag_info++; } + skb->truesize += truesize; return nr; fail: while (nr > 0) { nr--; - __skb_frag_unref(&skb_frags_rx[nr]); + __skb_frag_unref(skb_shinfo(skb)->frags + nr); } return 0; } @@ -639,7 +549,8 @@ static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, if (length <= SMALL_PACKET_SIZE) { /* We are copying all relevant data to the skb - temporarily * sync buffers for the copy */ - dma = be64_to_cpu(rx_desc->data[0].addr); + + dma = frags[0].dma + frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, length, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, va, length); @@ -648,7 +559,7 @@ static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, unsigned int pull_len; /* Move relevant fragments to skb */ - used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, frags, + used_frags = mlx4_en_complete_rx_desc(priv, frags, skb, length); if (unlikely(!used_frags)) { kfree_skb(skb); @@ -916,8 +827,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud case XDP_TX: if (likely(!mlx4_en_xmit_frame(ring, frags, dev, length, cq->ring, - &doorbell_pending))) - goto consumed; + &doorbell_pending))) { + frags[0].page = NULL; + goto next; + } trace_xdp_exception(dev, xdp_prog, act); goto xdp_drop_no_cnt; /* Drop on xmit failure */ default: @@ -927,8 +840,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud case XDP_DROP: ring->xdp_drop++; xdp_drop_no_cnt: - if (likely(mlx4_en_rx_recycle(ring, frags))) - goto consumed; goto next; } } @@ -974,9 +885,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud if (!gro_skb) goto next; - nr = mlx4_en_complete_rx_desc(priv, - rx_desc, frags, gro_skb, - length); + nr = mlx4_en_complete_rx_desc(priv, frags, gro_skb, + length); if (!nr) goto next; @@ -1084,10 +994,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud napi_gro_receive(&cq->napi, skb); next: - for (nr = 0; nr < priv->num_frags; nr++) - mlx4_en_free_frag(priv, frags, nr); - -consumed: ++cq->mcq.cons_index; index = (cq->mcq.cons_index) & ring->size_mask; cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 6c80117006ed..5f6080266981 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -327,7 +327,6 @@ struct mlx4_en_rx_desc { struct mlx4_en_rx_ring { struct mlx4_hwq_resources wqres; - struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS]; u32 size ; /* number of Rx descs*/ u32 actual_size; u32 size_mask; From 7d7bfc6a3f69d2debe104656fadd8d568fda0e5b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:14 -0800 Subject: [PATCH 067/399] mlx4: add rx_alloc_pages counter in ethtool -S This new counter tracks number of pages that we allocated for one port. lpaa24:~# ethtool -S eth0 | egrep 'rx_alloc_pages|rx_packets' rx_packets: 306755183 rx_alloc_pages: 932897 Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_port.c | 2 ++ drivers/net/ethernet/mellanox/mlx4/en_rx.c | 11 +++++++---- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 1 + drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h | 2 +- 5 files changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index c4d714fcc7da..ffbcb27c05e5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -117,7 +117,7 @@ static const char main_strings[][ETH_GSTRING_LEN] = { /* port statistics */ "tso_packets", "xmit_more", - "queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed", + "queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_pages", "rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload", /* pf statistics */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 9166d90e7328..e0eb695318e6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -213,6 +213,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.rx_chksum_good = 0; priv->port_stats.rx_chksum_none = 0; priv->port_stats.rx_chksum_complete = 0; + priv->port_stats.rx_alloc_pages = 0; priv->xdp_stats.rx_xdp_drop = 0; priv->xdp_stats.rx_xdp_tx = 0; priv->xdp_stats.rx_xdp_tx_full = 0; @@ -223,6 +224,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.rx_chksum_good += READ_ONCE(ring->csum_ok); priv->port_stats.rx_chksum_none += READ_ONCE(ring->csum_none); priv->port_stats.rx_chksum_complete += READ_ONCE(ring->csum_complete); + priv->port_stats.rx_alloc_pages += READ_ONCE(ring->rx_alloc_pages); priv->xdp_stats.rx_xdp_drop += READ_ONCE(ring->xdp_drop); priv->xdp_stats.rx_xdp_tx += READ_ONCE(ring->xdp_tx); priv->xdp_stats.rx_xdp_tx_full += READ_ONCE(ring->xdp_tx_full); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 5edd0cf2999c..d3a425fa46b3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -72,6 +72,7 @@ static int mlx4_alloc_page(struct mlx4_en_priv *priv, } static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, + struct mlx4_en_rx_ring *ring, struct mlx4_en_rx_desc *rx_desc, struct mlx4_en_rx_alloc *frags, gfp_t gfp) @@ -79,8 +80,11 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, int i; for (i = 0; i < priv->num_frags; i++, frags++) { - if (!frags->page && mlx4_alloc_page(priv, frags, gfp)) - return -ENOMEM; + if (!frags->page) { + if (mlx4_alloc_page(priv, frags, gfp)) + return -ENOMEM; + ring->rx_alloc_pages++; + } rx_desc->data[i].addr = cpu_to_be64(frags->dma + frags->page_offset); } @@ -133,7 +137,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride); struct mlx4_en_rx_alloc *frags = ring->rx_info + (index << priv->log_rx_info); - if (ring->page_cache.index > 0) { /* XDP uses a single page per frame */ if (!frags->page) { @@ -147,7 +150,7 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, return 0; } - return mlx4_en_alloc_frags(priv, rx_desc, frags, gfp); + return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp); } static bool mlx4_en_is_ring_empty(const struct mlx4_en_rx_ring *ring) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 5f6080266981..39f401aa3047 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -346,6 +346,7 @@ struct mlx4_en_rx_ring { unsigned long csum_ok; unsigned long csum_none; unsigned long csum_complete; + unsigned long rx_alloc_pages; unsigned long xdp_drop; unsigned long xdp_tx; unsigned long xdp_tx_full; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h index 48641cb0367f..926f3c3f3665 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h @@ -37,7 +37,7 @@ struct mlx4_en_port_stats { unsigned long queue_stopped; unsigned long wake_queue; unsigned long tx_timeout; - unsigned long rx_alloc_failed; + unsigned long rx_alloc_pages; unsigned long rx_chksum_good; unsigned long rx_chksum_none; unsigned long rx_chksum_complete; From 9e8c0395a7e87a8f0eb008297df25ffdf3e0e5b3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:15 -0800 Subject: [PATCH 068/399] mlx4: do not access rx_desc from mlx4_en_process_rx_cq() Instead of fetching dma address from rx_desc->data[0].addr, prefer using frags[0].dma + frags[0].page_offset to avoid a potential cache line miss. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index d3a425fa46b3..b62fa265890e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -528,7 +528,6 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, - struct mlx4_en_rx_desc *rx_desc, struct mlx4_en_rx_alloc *frags, unsigned int length) { @@ -703,7 +702,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud struct mlx4_cqe *cqe; struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring]; struct mlx4_en_rx_alloc *frags; - struct mlx4_en_rx_desc *rx_desc; struct bpf_prog *xdp_prog; int doorbell_pending; struct sk_buff *skb; @@ -738,7 +736,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud cq->mcq.cons_index & cq->size)) { frags = ring->rx_info + (index << priv->log_rx_info); - rx_desc = ring->buf + (index << ring->log_stride); /* * make sure we read the CQE after we read the ownership bit @@ -767,7 +764,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud /* Get pointer to first fragment since we haven't * skb yet and cast it to ethhdr struct */ - dma = be64_to_cpu(rx_desc->data[0].addr); + dma = frags[0].dma + frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh), DMA_FROM_DEVICE); ethh = (struct ethhdr *)(page_address(frags[0].page) + @@ -806,7 +803,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud void *orig_data; u32 act; - dma = be64_to_cpu(rx_desc->data[0].addr); + dma = frags[0].dma + frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, priv->frag_info[0].frag_size, DMA_FROM_DEVICE); @@ -946,7 +943,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud } /* GRO not possible, complete processing here */ - skb = mlx4_en_rx_skb(priv, rx_desc, frags, length); + skb = mlx4_en_rx_skb(priv, frags, length); if (unlikely(!skb)) { ring->dropped++; goto next; From 02e6fd3e5598bace683e05ee783f134722cb21b4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:16 -0800 Subject: [PATCH 069/399] mlx4: factorize page_address() calls We need to compute the frame virtual address at different points. Do it once. Following patch will use the new va address for validate_loopback() Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b62fa265890e..b5aa3f986508 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -734,9 +734,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud /* Process all completed CQEs */ while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK, cq->mcq.cons_index & cq->size)) { + void *va; frags = ring->rx_info + (index << priv->log_rx_info); - + va = page_address(frags[0].page) + frags[0].page_offset; /* * make sure we read the CQE after we read the ownership bit */ @@ -759,7 +760,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud * and not performing the selftest or flb disabled */ if (priv->flags & MLX4_EN_FLAG_RX_FILTER_NEEDED) { - struct ethhdr *ethh; + const struct ethhdr *ethh = va; dma_addr_t dma; /* Get pointer to first fragment since we haven't * skb yet and cast it to ethhdr struct @@ -767,8 +768,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud dma = frags[0].dma + frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh), DMA_FROM_DEVICE); - ethh = (struct ethhdr *)(page_address(frags[0].page) + - frags[0].page_offset); if (is_multicast_ether_addr(ethh->h_dest)) { struct mlx4_mac_entry *entry; @@ -808,8 +807,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud priv->frag_info[0].frag_size, DMA_FROM_DEVICE); - xdp.data_hard_start = page_address(frags[0].page); - xdp.data = xdp.data_hard_start + frags[0].page_offset; + xdp.data_hard_start = va - frags[0].page_offset; + xdp.data = va; xdp.data_end = xdp.data + length; orig_data = xdp.data; @@ -819,6 +818,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud length = xdp.data_end - xdp.data; frags[0].page_offset = xdp.data - xdp.data_hard_start; + va = xdp.data; } switch (act) { @@ -891,7 +891,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud goto next; if (ip_summed == CHECKSUM_COMPLETE) { - void *va = skb_frag_address(skb_shinfo(gro_skb)->frags); if (check_csum(cqe, gro_skb, va, dev->features)) { ip_summed = CHECKSUM_NONE; @@ -955,7 +954,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud } if (ip_summed == CHECKSUM_COMPLETE) { - if (check_csum(cqe, skb, skb->data, dev->features)) { + if (check_csum(cqe, skb, va, dev->features)) { ip_summed = CHECKSUM_NONE; ring->csum_complete--; ring->csum_none++; From 6969cf0fdbe9e67ed14cdf7ec95977abcf4a14af Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:17 -0800 Subject: [PATCH 070/399] mlx4: make validate_loopback() more generic Testing a boolean in fast path is not worth duplicating the code allocating packets, when GRO is on or off. If this proves to be a problem, we might later use a jump label. Next patch will remove this duplicated code and ease code review. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 23 ++++++++----------- .../net/ethernet/mellanox/mlx4/en_selftest.c | 6 ----- 2 files changed, 10 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b5aa3f986508..33b28278c827 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -584,20 +584,17 @@ static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, return skb; } -static void validate_loopback(struct mlx4_en_priv *priv, struct sk_buff *skb) +static void validate_loopback(struct mlx4_en_priv *priv, void *va) { + const unsigned char *data = va + ETH_HLEN; int i; - int offset = ETH_HLEN; - for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++, offset++) { - if (*(skb->data + offset) != (unsigned char) (i & 0xff)) - goto out_loopback; + for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++) { + if (data[i] != (unsigned char)i) + return; } /* Loopback found */ priv->loopback_ok = 1; - -out_loopback: - dev_kfree_skb_any(skb); } static bool mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv, @@ -785,6 +782,11 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud } } + if (unlikely(priv->validate_loopback)) { + validate_loopback(priv, va); + goto next; + } + /* * Packet is OK - process it. */ @@ -948,11 +950,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud goto next; } - if (unlikely(priv->validate_loopback)) { - validate_loopback(priv, skb); - goto next; - } - if (ip_summed == CHECKSUM_COMPLETE) { if (check_csum(cqe, skb, va, dev->features)) { ip_summed = CHECKSUM_NONE; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c index 95290e1fc9fe..17112faafbcc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c @@ -81,14 +81,11 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv) { u32 loopback_ok = 0; int i; - bool gro_enabled; priv->loopback_ok = 0; priv->validate_loopback = 1; - gro_enabled = priv->dev->features & NETIF_F_GRO; mlx4_en_update_loopback_state(priv->dev, priv->dev->features); - priv->dev->features &= ~NETIF_F_GRO; /* xmit */ if (mlx4_en_test_loopback_xmit(priv)) { @@ -111,9 +108,6 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv) priv->validate_loopback = 0; - if (gro_enabled) - priv->dev->features |= NETIF_F_GRO; - mlx4_en_update_loopback_state(priv->dev, priv->dev->features); return !loopback_ok; } From 68b8df464406e39925a54955294d5994df46bcf4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Mar 2017 08:17:18 -0800 Subject: [PATCH 071/399] mlx4: remove duplicate code in mlx4_en_process_rx_cq() We should keep one way to build skbs, regardless of GRO being on or off. Note that I made sure to defer as much as possible the point we need to pull data from the frame, so that future prefetch() we might add are more effective. These skb attributes derive from the CQE or ring : ip_summed, csum hash vlan offload hwtstamps queue_mapping As a bonus, this patch removes mlx4 dependency on eth_get_headlen() which is very often broken enough to give us headaches. Signed-off-by: Eric Dumazet Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 209 ++++----------------- 1 file changed, 41 insertions(+), 168 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 33b28278c827..aa074e57ce06 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -526,64 +526,6 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, return 0; } - -static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, - struct mlx4_en_rx_alloc *frags, - unsigned int length) -{ - struct sk_buff *skb; - void *va; - int used_frags; - dma_addr_t dma; - - skb = netdev_alloc_skb(priv->dev, SMALL_PACKET_SIZE + NET_IP_ALIGN); - if (unlikely(!skb)) { - en_dbg(RX_ERR, priv, "Failed allocating skb\n"); - return NULL; - } - skb_reserve(skb, NET_IP_ALIGN); - skb->len = length; - - /* Get pointer to first fragment so we could copy the headers into the - * (linear part of the) skb */ - va = page_address(frags[0].page) + frags[0].page_offset; - - if (length <= SMALL_PACKET_SIZE) { - /* We are copying all relevant data to the skb - temporarily - * sync buffers for the copy */ - - dma = frags[0].dma + frags[0].page_offset; - dma_sync_single_for_cpu(priv->ddev, dma, length, - DMA_FROM_DEVICE); - skb_copy_to_linear_data(skb, va, length); - skb->tail += length; - } else { - unsigned int pull_len; - - /* Move relevant fragments to skb */ - used_frags = mlx4_en_complete_rx_desc(priv, frags, - skb, length); - if (unlikely(!used_frags)) { - kfree_skb(skb); - return NULL; - } - skb_shinfo(skb)->nr_frags = used_frags; - - pull_len = eth_get_headlen(va, SMALL_PACKET_SIZE); - /* Copy headers into the skb linear buffer */ - memcpy(skb->data, va, pull_len); - skb->tail += pull_len; - - /* Skip headers in first fragment */ - skb_shinfo(skb)->frags[0].page_offset += pull_len; - - /* Adjust size of first fragment */ - skb_frag_size_sub(&skb_shinfo(skb)->frags[0], pull_len); - skb->data_len = length - pull_len; - } - return skb; -} - static void validate_loopback(struct mlx4_en_priv *priv, void *va) { const unsigned char *data = va + ETH_HLEN; @@ -792,8 +734,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud */ length = be32_to_cpu(cqe->byte_cnt); length -= ring->fcs_del; - l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) && - (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL)); /* A bpf program gets first chance to drop the packet. It may * read bytes but not past the end of the frag. @@ -849,122 +789,51 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud ring->bytes += length; ring->packets++; + skb = napi_get_frags(&cq->napi); + if (!skb) + goto next; + + if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) { + timestamp = mlx4_en_get_cqe_ts(cqe); + mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb), + timestamp); + } + skb_record_rx_queue(skb, cq->ring); + if (likely(dev->features & NETIF_F_RXCSUM)) { if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) { if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && cqe->checksum == cpu_to_be16(0xffff)) { ip_summed = CHECKSUM_UNNECESSARY; + l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) && + (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL)); + if (l2_tunnel) + skb->csum_level = 1; ring->csum_ok++; } else { - ip_summed = CHECKSUM_NONE; - ring->csum_none++; + goto csum_none; } } else { if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP && (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV6))) { - ip_summed = CHECKSUM_COMPLETE; - ring->csum_complete++; + if (check_csum(cqe, skb, va, dev->features)) { + goto csum_none; + } else { + ip_summed = CHECKSUM_COMPLETE; + ring->csum_complete++; + } } else { - ip_summed = CHECKSUM_NONE; - ring->csum_none++; + goto csum_none; } } } else { +csum_none: ip_summed = CHECKSUM_NONE; ring->csum_none++; } - - /* This packet is eligible for GRO if it is: - * - DIX Ethernet (type interpretation) - * - TCP/IP (v4) - * - without IP options - * - not an IP fragment - */ - if (dev->features & NETIF_F_GRO) { - struct sk_buff *gro_skb = napi_get_frags(&cq->napi); - if (!gro_skb) - goto next; - - nr = mlx4_en_complete_rx_desc(priv, frags, gro_skb, - length); - if (!nr) - goto next; - - if (ip_summed == CHECKSUM_COMPLETE) { - if (check_csum(cqe, gro_skb, va, - dev->features)) { - ip_summed = CHECKSUM_NONE; - ring->csum_none++; - ring->csum_complete--; - } - } - - skb_shinfo(gro_skb)->nr_frags = nr; - gro_skb->len = length; - gro_skb->data_len = length; - gro_skb->ip_summed = ip_summed; - - if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY) - gro_skb->csum_level = 1; - - if ((cqe->vlan_my_qpn & - cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) && - (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) { - u16 vid = be16_to_cpu(cqe->sl_vid); - - __vlan_hwaccel_put_tag(gro_skb, htons(ETH_P_8021Q), vid); - } else if ((be32_to_cpu(cqe->vlan_my_qpn) & - MLX4_CQE_SVLAN_PRESENT_MASK) && - (dev->features & NETIF_F_HW_VLAN_STAG_RX)) { - __vlan_hwaccel_put_tag(gro_skb, - htons(ETH_P_8021AD), - be16_to_cpu(cqe->sl_vid)); - } - - if (dev->features & NETIF_F_RXHASH) - skb_set_hash(gro_skb, - be32_to_cpu(cqe->immed_rss_invalid), - (ip_summed == CHECKSUM_UNNECESSARY) ? - PKT_HASH_TYPE_L4 : - PKT_HASH_TYPE_L3); - - skb_record_rx_queue(gro_skb, cq->ring); - - if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) { - timestamp = mlx4_en_get_cqe_ts(cqe); - mlx4_en_fill_hwtstamps(mdev, - skb_hwtstamps(gro_skb), - timestamp); - } - - napi_gro_frags(&cq->napi); - goto next; - } - - /* GRO not possible, complete processing here */ - skb = mlx4_en_rx_skb(priv, frags, length); - if (unlikely(!skb)) { - ring->dropped++; - goto next; - } - - if (ip_summed == CHECKSUM_COMPLETE) { - if (check_csum(cqe, skb, va, dev->features)) { - ip_summed = CHECKSUM_NONE; - ring->csum_complete--; - ring->csum_none++; - } - } - skb->ip_summed = ip_summed; - skb->protocol = eth_type_trans(skb, dev); - skb_record_rx_queue(skb, cq->ring); - - if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY) - skb->csum_level = 1; - if (dev->features & NETIF_F_RXHASH) skb_set_hash(skb, be32_to_cpu(cqe->immed_rss_invalid), @@ -972,32 +841,36 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); - if ((be32_to_cpu(cqe->vlan_my_qpn) & - MLX4_CQE_CVLAN_PRESENT_MASK) && + + if ((cqe->vlan_my_qpn & + cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) && (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->sl_vid)); - else if ((be32_to_cpu(cqe->vlan_my_qpn) & - MLX4_CQE_SVLAN_PRESENT_MASK) && + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + be16_to_cpu(cqe->sl_vid)); + else if ((cqe->vlan_my_qpn & + cpu_to_be32(MLX4_CQE_SVLAN_PRESENT_MASK)) && (dev->features & NETIF_F_HW_VLAN_STAG_RX)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), be16_to_cpu(cqe->sl_vid)); - if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) { - timestamp = mlx4_en_get_cqe_ts(cqe); - mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb), - timestamp); + nr = mlx4_en_complete_rx_desc(priv, frags, skb, length); + if (likely(nr)) { + skb_shinfo(skb)->nr_frags = nr; + skb->len = length; + skb->data_len = length; + napi_gro_frags(&cq->napi); + } else { + skb->vlan_tci = 0; + skb_clear_hash(skb); } - - napi_gro_receive(&cq->napi, skb); next: ++cq->mcq.cons_index; index = (cq->mcq.cons_index) & ring->size_mask; cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor; if (++polled == budget) - goto out; + break; } -out: rcu_read_unlock(); if (polled) { From aee441193ee2609070418af5843bff55907c713c Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:52:59 +0100 Subject: [PATCH 072/399] dt-bindings: net: update Marvell PPv2 binding for PPv2.2 support The Marvell PPv2 Device Tree binding was so far only used to describe the PPv2.1 network controller, used in the Marvell Armada 375. A new version of this IP block, PPv2.2 is used in the Marvell Armada 7K/8K processor. This commit extends the existing binding so that it can also be used to describe PPv2.2 hardware. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- .../devicetree/bindings/net/marvell-pp2.txt | 62 +++++++++++++++---- 1 file changed, 51 insertions(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt index 4754364df4c6..6b4956beff8c 100644 --- a/Documentation/devicetree/bindings/net/marvell-pp2.txt +++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt @@ -1,17 +1,28 @@ -* Marvell Armada 375 Ethernet Controller (PPv2) +* Marvell Armada 375 Ethernet Controller (PPv2.1) + Marvell Armada 7K/8K Ethernet Controller (PPv2.2) Required properties: -- compatible: should be "marvell,armada-375-pp2" +- compatible: should be one of: + "marvell,armada-375-pp2" + "marvell,armada-7k-pp2" - reg: addresses and length of the register sets for the device. - Must contain the following register sets: + For "marvell,armada-375-pp2", must contain the following register + sets: - common controller registers - LMS registers - In addition, at least one port register set is required. -- clocks: a pointer to the reference clocks for this device, consequently: - - main controller clock - - GOP clock -- clock-names: names of used clocks, must be "pp_clk" and "gop_clk". + - one register area per Ethernet port + For "marvell,armada-7k-pp2", must contain the following register + sets: + - packet processor registers + - networking interfaces registers + +- clocks: pointers to the reference clocks for this device, consequently: + - main controller clock (for both armada-375-pp2 and armada-7k-pp2) + - GOP clock (for both armada-375-pp2 and armada-7k-pp2) + - MG clock (only for armada-7k-pp2) +- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and + "mg_clk" (the latter only for armada-7k-pp2). The ethernet ports are represented by subnodes. At least one port is required. @@ -19,8 +30,10 @@ required. Required properties (port): - interrupts: interrupt for the port -- port-id: should be '0' or '1' for ethernet ports, and '2' for the - loopback port +- port-id: ID of the port from the MAC point of view +- gop-port-id: only for marvell,armada-7k-pp2, ID of the port from the + GOP (Group Of Ports) point of view. This ID is used to index the + per-port registers in the second register area. - phy-mode: See ethernet.txt file in the same directory Optional properties (port): @@ -29,7 +42,7 @@ Optional properties (port): - phy: a phandle to a phy node defining the PHY address (as the reg property, a single integer). -Example: +Example for marvell,armada-375-pp2: ethernet@f0000 { compatible = "marvell,armada-375-pp2"; @@ -57,3 +70,30 @@ ethernet@f0000 { phy-mode = "gmii"; }; }; + +Example for marvell,armada-7k-pp2: + +cpm_ethernet: ethernet@0 { + compatible = "marvell,armada-7k-pp22"; + reg = <0x0 0x100000>, <0x129000 0xb000>; + clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>; + clock-names = "pp_clk", "gop_clk", "gp_clk"; + + eth0: eth0 { + interrupts = ; + port-id = <0>; + gop-port-id = <0>; + }; + + eth1: eth1 { + interrupts = ; + port-id = <1>; + gop-port-id = <2>; + }; + + eth2: eth2 { + interrupts = ; + port-id = <2>; + gop-port-id = <3>; + }; +}; From 20396136fbe563feac927151966a5931c1bac7a9 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:00 +0100 Subject: [PATCH 073/399] net: mvpp2: use "dma" instead of "phys" where appropriate As indicated by Russell King, the mvpp2 driver currently uses a lot "phys" or "phys_addr" to store what really is a DMA address. This commit clarifies this by using "dma" or "dma_addr" where appropriate. This is especially important as we are going to introduce more changes where the distinction between physical address and DMA address will be key. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 148 +++++++++++++-------------- 1 file changed, 74 insertions(+), 74 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index d00421b9ffea..6a4d1266d1e4 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -746,7 +746,7 @@ struct mvpp2_tx_desc { u8 packet_offset; /* the offset from the buffer beginning */ u8 phys_txq; /* destination queue ID */ u16 data_size; /* data size of transmitted packet in bytes */ - u32 buf_phys_addr; /* physical addr of transmitted buffer */ + u32 buf_dma_addr; /* physical addr of transmitted buffer */ u32 buf_cookie; /* cookie for access to TX buffer in tx path */ u32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */ u32 reserved2; /* reserved (for future use) */ @@ -756,7 +756,7 @@ struct mvpp2_rx_desc { u32 status; /* info about received packet */ u16 reserved1; /* parser_info (for future use, PnC) */ u16 data_size; /* size of received packet in bytes */ - u32 buf_phys_addr; /* physical address of the buffer */ + u32 buf_dma_addr; /* physical address of the buffer */ u32 buf_cookie; /* cookie for access to RX buffer in rx path */ u16 reserved2; /* gem_port_id (for future use, PON) */ u16 reserved3; /* csum_l4 (for future use, PnC) */ @@ -772,7 +772,7 @@ struct mvpp2_txq_pcpu_buf { struct sk_buff *skb; /* Physical address of transmitted buffer */ - dma_addr_t phys; + dma_addr_t dma; /* Size transmitted */ size_t size; @@ -825,7 +825,7 @@ struct mvpp2_tx_queue { struct mvpp2_tx_desc *descs; /* DMA address of the Tx DMA descriptors array */ - dma_addr_t descs_phys; + dma_addr_t descs_dma; /* Index of the last Tx DMA descriptor */ int last_desc; @@ -848,7 +848,7 @@ struct mvpp2_rx_queue { struct mvpp2_rx_desc *descs; /* DMA address of the RX DMA descriptors array */ - dma_addr_t descs_phys; + dma_addr_t descs_dma; /* Index of the last RX DMA descriptor */ int last_desc; @@ -922,15 +922,15 @@ struct mvpp2_bm_pool { /* BPPE virtual base address */ u32 *virt_addr; - /* BPPE physical base address */ - dma_addr_t phys_addr; + /* BPPE DMA base address */ + dma_addr_t dma_addr; /* Ports using BM pool */ u32 port_map; }; struct mvpp2_buff_hdr { - u32 next_buff_phys_addr; + u32 next_buff_dma_addr; u32 next_buff_virt_addr; u16 byte_count; u16 info; @@ -982,7 +982,7 @@ static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu, txq_pcpu->buffs + txq_pcpu->txq_put_index; tx_buf->skb = skb; tx_buf->size = tx_desc->data_size; - tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset; + tx_buf->dma = tx_desc->buf_dma_addr + tx_desc->packet_offset; txq_pcpu->txq_put_index++; if (txq_pcpu->txq_put_index == txq_pcpu->size) txq_pcpu->txq_put_index = 0; @@ -3383,7 +3383,7 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, size_bytes = sizeof(u32) * size; bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes, - &bm_pool->phys_addr, + &bm_pool->dma_addr, GFP_KERNEL); if (!bm_pool->virt_addr) return -ENOMEM; @@ -3391,14 +3391,14 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, if (!IS_ALIGNED((unsigned long)bm_pool->virt_addr, MVPP2_BM_POOL_PTR_ALIGN)) { dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr, - bm_pool->phys_addr); + bm_pool->dma_addr); dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n", bm_pool->id, MVPP2_BM_POOL_PTR_ALIGN); return -ENOMEM; } mvpp2_write(priv, MVPP2_BM_POOL_BASE_REG(bm_pool->id), - bm_pool->phys_addr); + bm_pool->dma_addr); mvpp2_write(priv, MVPP2_BM_POOL_SIZE_REG(bm_pool->id), size); val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id)); @@ -3433,15 +3433,15 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, int i; for (i = 0; i < bm_pool->buf_num; i++) { - dma_addr_t buf_phys_addr; + dma_addr_t buf_dma_addr; unsigned long vaddr; /* Get buffer virtual address (indirect access) */ - buf_phys_addr = mvpp2_read(priv, - MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); + buf_dma_addr = mvpp2_read(priv, + MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); - dma_unmap_single(dev, buf_phys_addr, + dma_unmap_single(dev, buf_dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE); if (!vaddr) @@ -3473,7 +3473,7 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev, dma_free_coherent(&pdev->dev, sizeof(u32) * bm_pool->size, bm_pool->virt_addr, - bm_pool->phys_addr); + bm_pool->dma_addr); return 0; } @@ -3563,24 +3563,24 @@ static void mvpp2_rxq_short_pool_set(struct mvpp2_port *port, static void *mvpp2_buf_alloc(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, - dma_addr_t *buf_phys_addr, + dma_addr_t *buf_dma_addr, gfp_t gfp_mask) { - dma_addr_t phys_addr; + dma_addr_t dma_addr; void *data; data = mvpp2_frag_alloc(bm_pool); if (!data) return NULL; - phys_addr = dma_map_single(port->dev->dev.parent, data, - MVPP2_RX_BUF_SIZE(bm_pool->pkt_size), - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(port->dev->dev.parent, phys_addr))) { + dma_addr = dma_map_single(port->dev->dev.parent, data, + MVPP2_RX_BUF_SIZE(bm_pool->pkt_size), + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(port->dev->dev.parent, dma_addr))) { mvpp2_frag_free(bm_pool, data); return NULL; } - *buf_phys_addr = phys_addr; + *buf_dma_addr = dma_addr; return data; } @@ -3604,16 +3604,16 @@ static inline int mvpp2_bm_cookie_pool_get(unsigned long cookie) /* Release buffer to BM */ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, - dma_addr_t buf_phys_addr, + dma_addr_t buf_dma_addr, unsigned long buf_virt_addr) { mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_virt_addr); - mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_phys_addr); + mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); } /* Release multicast buffer */ static void mvpp2_bm_pool_mc_put(struct mvpp2_port *port, int pool, - dma_addr_t buf_phys_addr, + dma_addr_t buf_dma_addr, unsigned long buf_virt_addr, int mc_id) { @@ -3623,18 +3623,18 @@ static void mvpp2_bm_pool_mc_put(struct mvpp2_port *port, int pool, mvpp2_write(port->priv, MVPP2_BM_MC_RLS_REG, val); mvpp2_bm_pool_put(port, pool, - buf_phys_addr | MVPP2_BM_PHY_RLS_MC_BUFF_MASK, + buf_dma_addr | MVPP2_BM_PHY_RLS_MC_BUFF_MASK, buf_virt_addr); } /* Refill BM pool */ static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm, - dma_addr_t phys_addr, + dma_addr_t dma_addr, unsigned long cookie) { int pool = mvpp2_bm_cookie_pool_get(bm); - mvpp2_bm_pool_put(port, pool, phys_addr, cookie); + mvpp2_bm_pool_put(port, pool, dma_addr, cookie); } /* Allocate buffers for the pool */ @@ -3642,7 +3642,7 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, int buf_num) { int i, buf_size, total_size; - dma_addr_t phys_addr; + dma_addr_t dma_addr; void *buf; buf_size = MVPP2_RX_BUF_SIZE(bm_pool->pkt_size); @@ -3657,11 +3657,11 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, } for (i = 0; i < buf_num; i++) { - buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_KERNEL); + buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, GFP_KERNEL); if (!buf) break; - mvpp2_bm_pool_put(port, bm_pool->id, phys_addr, + mvpp2_bm_pool_put(port, bm_pool->id, dma_addr, (unsigned long)buf); } @@ -4449,7 +4449,7 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, struct mvpp2_txq_pcpu_buf *tx_buf = txq_pcpu->buffs + txq_pcpu->txq_get_index; - dma_unmap_single(port->dev->dev.parent, tx_buf->phys, + dma_unmap_single(port->dev->dev.parent, tx_buf->dma, tx_buf->size, DMA_TO_DEVICE); if (tx_buf->skb) dev_kfree_skb_any(tx_buf->skb); @@ -4530,7 +4530,7 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, /* Allocate memory for TX descriptors */ aggr_txq->descs = dma_alloc_coherent(&pdev->dev, desc_num * MVPP2_DESC_ALIGNED_SIZE, - &aggr_txq->descs_phys, GFP_KERNEL); + &aggr_txq->descs_dma, GFP_KERNEL); if (!aggr_txq->descs) return -ENOMEM; @@ -4543,7 +4543,7 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, /* Set Tx descriptors queue starting address */ /* indirect access */ mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), - aggr_txq->descs_phys); + aggr_txq->descs_dma); mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), desc_num); return 0; @@ -4559,7 +4559,7 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, /* Allocate memory for RX descriptors */ rxq->descs = dma_alloc_coherent(port->dev->dev.parent, rxq->size * MVPP2_DESC_ALIGNED_SIZE, - &rxq->descs_phys, GFP_KERNEL); + &rxq->descs_dma, GFP_KERNEL); if (!rxq->descs) return -ENOMEM; @@ -4570,7 +4570,7 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, /* Set Rx descriptors queue starting address - indirect access */ mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq->descs_phys); + mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq->descs_dma); mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); mvpp2_write(port->priv, MVPP2_RXQ_INDEX_REG, 0); @@ -4601,7 +4601,7 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq); u32 bm = mvpp2_bm_cookie_build(rx_desc); - mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr, + mvpp2_pool_refill(port, bm, rx_desc->buf_dma_addr, rx_desc->buf_cookie); } mvpp2_rxq_status_update(port, rxq->id, rx_received, rx_received); @@ -4617,12 +4617,12 @@ static void mvpp2_rxq_deinit(struct mvpp2_port *port, dma_free_coherent(port->dev->dev.parent, rxq->size * MVPP2_DESC_ALIGNED_SIZE, rxq->descs, - rxq->descs_phys); + rxq->descs_dma); rxq->descs = NULL; rxq->last_desc = 0; rxq->next_desc_to_proc = 0; - rxq->descs_phys = 0; + rxq->descs_dma = 0; /* Clear Rx descriptors queue starting address and size; * free descriptor number @@ -4646,7 +4646,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, /* Allocate memory for Tx descriptors */ txq->descs = dma_alloc_coherent(port->dev->dev.parent, txq->size * MVPP2_DESC_ALIGNED_SIZE, - &txq->descs_phys, GFP_KERNEL); + &txq->descs_dma, GFP_KERNEL); if (!txq->descs) return -ENOMEM; @@ -4654,7 +4654,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, /* Set Tx descriptors queue starting address - indirect access */ mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_phys); + mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_dma); mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, txq->size & MVPP2_TXQ_DESC_SIZE_MASK); mvpp2_write(port->priv, MVPP2_TXQ_INDEX_REG, 0); @@ -4716,7 +4716,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port, dma_free_coherent(port->dev->dev.parent, txq->size * MVPP2_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + txq->descs, txq->descs_dma); return -ENOMEM; } @@ -4736,12 +4736,12 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, if (txq->descs) dma_free_coherent(port->dev->dev.parent, txq->size * MVPP2_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + txq->descs, txq->descs_dma); txq->descs = NULL; txq->last_desc = 0; txq->next_desc_to_proc = 0; - txq->descs_phys = 0; + txq->descs_dma = 0; /* Set minimum bandwidth for disabled TXQs */ mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0); @@ -5031,15 +5031,15 @@ static void mvpp2_rx_csum(struct mvpp2_port *port, u32 status, static int mvpp2_rx_refill(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, u32 bm) { - dma_addr_t phys_addr; + dma_addr_t dma_addr; void *buf; /* No recycle or too many buffers are in use, so allocate a new skb */ - buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_ATOMIC); + buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, GFP_ATOMIC); if (!buf) return -ENOMEM; - mvpp2_pool_refill(port, bm, phys_addr, (unsigned long)buf); + mvpp2_pool_refill(port, bm, dma_addr, (unsigned long)buf); return 0; } @@ -5081,16 +5081,16 @@ static void mvpp2_buff_hdr_rx(struct mvpp2_port *port, struct mvpp2_buff_hdr *buff_hdr; struct sk_buff *skb; u32 rx_status = rx_desc->status; - dma_addr_t buff_phys_addr; + dma_addr_t buff_dma_addr; unsigned long buff_virt_addr; - dma_addr_t buff_phys_addr_next; + dma_addr_t buff_dma_addr_next; unsigned long buff_virt_addr_next; int mc_id; int pool_id; pool_id = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >> MVPP2_RXD_BM_POOL_ID_OFFS; - buff_phys_addr = rx_desc->buf_phys_addr; + buff_dma_addr = rx_desc->buf_dma_addr; buff_virt_addr = rx_desc->buf_cookie; do { @@ -5099,14 +5099,14 @@ static void mvpp2_buff_hdr_rx(struct mvpp2_port *port, mc_id = MVPP2_B_HDR_INFO_MC_ID(buff_hdr->info); - buff_phys_addr_next = buff_hdr->next_buff_phys_addr; + buff_dma_addr_next = buff_hdr->next_buff_dma_addr; buff_virt_addr_next = buff_hdr->next_buff_virt_addr; /* Release buffer */ - mvpp2_bm_pool_mc_put(port, pool_id, buff_phys_addr, + mvpp2_bm_pool_mc_put(port, pool_id, buff_dma_addr, buff_virt_addr, mc_id); - buff_phys_addr = buff_phys_addr_next; + buff_dma_addr = buff_dma_addr_next; buff_virt_addr = buff_virt_addr_next; } while (!MVPP2_B_HDR_INFO_IS_LAST(buff_hdr->info)); @@ -5132,7 +5132,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, struct mvpp2_bm_pool *bm_pool; struct sk_buff *skb; unsigned int frag_size; - dma_addr_t phys_addr; + dma_addr_t dma_addr; u32 bm, rx_status; int pool, rx_bytes, err; void *data; @@ -5140,7 +5140,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, rx_done++; rx_status = rx_desc->status; rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE; - phys_addr = rx_desc->buf_phys_addr; + dma_addr = rx_desc->buf_dma_addr; data = (void *)(uintptr_t)rx_desc->buf_cookie; bm = mvpp2_bm_cookie_build(rx_desc); @@ -5163,7 +5163,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ - mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr, + mvpp2_pool_refill(port, bm, rx_desc->buf_dma_addr, rx_desc->buf_cookie); continue; } @@ -5185,7 +5185,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, goto err_drop_frame; } - dma_unmap_single(dev->dev.parent, phys_addr, + dma_unmap_single(dev->dev.parent, dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE); rcvd_pkts++; @@ -5219,7 +5219,7 @@ static inline void tx_desc_unmap_put(struct device *dev, struct mvpp2_tx_queue *txq, struct mvpp2_tx_desc *desc) { - dma_unmap_single(dev, desc->buf_phys_addr, + dma_unmap_single(dev, desc->buf_dma_addr, desc->data_size, DMA_TO_DEVICE); mvpp2_txq_desc_put(txq); } @@ -5232,7 +5232,7 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu); struct mvpp2_tx_desc *tx_desc; int i; - dma_addr_t buf_phys_addr; + dma_addr_t buf_dma_addr; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -5242,16 +5242,16 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, tx_desc->phys_txq = txq->id; tx_desc->data_size = frag->size; - buf_phys_addr = dma_map_single(port->dev->dev.parent, addr, - tx_desc->data_size, - DMA_TO_DEVICE); - if (dma_mapping_error(port->dev->dev.parent, buf_phys_addr)) { + buf_dma_addr = dma_map_single(port->dev->dev.parent, addr, + tx_desc->data_size, + DMA_TO_DEVICE); + if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) { mvpp2_txq_desc_put(txq); goto error; } - tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN; - tx_desc->buf_phys_addr = buf_phys_addr & (~MVPP2_TX_DESC_ALIGN); + tx_desc->packet_offset = buf_dma_addr & MVPP2_TX_DESC_ALIGN; + tx_desc->buf_dma_addr = buf_dma_addr & (~MVPP2_TX_DESC_ALIGN); if (i == (skb_shinfo(skb)->nr_frags - 1)) { /* Last descriptor */ @@ -5285,7 +5285,7 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) struct mvpp2_tx_queue *txq, *aggr_txq; struct mvpp2_txq_pcpu *txq_pcpu; struct mvpp2_tx_desc *tx_desc; - dma_addr_t buf_phys_addr; + dma_addr_t buf_dma_addr; int frags = 0; u16 txq_id; u32 tx_cmd; @@ -5310,15 +5310,15 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) tx_desc->phys_txq = txq->id; tx_desc->data_size = skb_headlen(skb); - buf_phys_addr = dma_map_single(dev->dev.parent, skb->data, - tx_desc->data_size, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev->dev.parent, buf_phys_addr))) { + buf_dma_addr = dma_map_single(dev->dev.parent, skb->data, + tx_desc->data_size, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev->dev.parent, buf_dma_addr))) { mvpp2_txq_desc_put(txq); frags = 0; goto out; } - tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN; - tx_desc->buf_phys_addr = buf_phys_addr & ~MVPP2_TX_DESC_ALIGN; + tx_desc->packet_offset = buf_dma_addr & MVPP2_TX_DESC_ALIGN; + tx_desc->buf_dma_addr = buf_dma_addr & ~MVPP2_TX_DESC_ALIGN; tx_cmd = mvpp2_skb_tx_csum(port, skb); @@ -6506,7 +6506,7 @@ static int mvpp2_remove(struct platform_device *pdev) dma_free_coherent(&pdev->dev, MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, aggr_txq->descs, - aggr_txq->descs_phys); + aggr_txq->descs_dma); } clk_disable_unprepare(priv->pp_clk); From aeb3d1109afad0f4ebb5c9e27bbb67b755c5f47d Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:01 +0100 Subject: [PATCH 074/399] net: mvpp2: remove support for buffer header The "buffer header" functionality is a functionality used by the hardware to split an incoming packets over multiple BM buffers if they are not large enough. However, the mvpp2 driver guarantees that a pool of BM buffers has buffers with a size large enough to store MTU-sized packets. Therefore, this functionality is completely unused, and the code can be removed, and we should never get a descriptor with bit MVPP2_RXD_BUF_HDR set. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 77 ---------------------------- 1 file changed, 77 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 6a4d1266d1e4..fb8b5e9a92f0 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -215,9 +215,6 @@ #define MVPP2_BM_PHY_RLS_PRIO_EN_MASK BIT(1) #define MVPP2_BM_PHY_RLS_GRNTD_MASK BIT(2) #define MVPP2_BM_VIRT_RLS_REG 0x64c0 -#define MVPP2_BM_MC_RLS_REG 0x64c4 -#define MVPP2_BM_MC_ID_MASK 0xfff -#define MVPP2_BM_FORCE_RELEASE_MASK BIT(12) /* TX Scheduler registers */ #define MVPP2_TXP_SCHED_PORT_INDEX_REG 0x8000 @@ -929,22 +926,6 @@ struct mvpp2_bm_pool { u32 port_map; }; -struct mvpp2_buff_hdr { - u32 next_buff_dma_addr; - u32 next_buff_virt_addr; - u16 byte_count; - u16 info; - u8 reserved1; /* bm_qset (for future use, BM) */ -}; - -/* Buffer header info bits */ -#define MVPP2_B_HDR_INFO_MC_ID_MASK 0xfff -#define MVPP2_B_HDR_INFO_MC_ID(info) ((info) & MVPP2_B_HDR_INFO_MC_ID_MASK) -#define MVPP2_B_HDR_INFO_LAST_OFFS 12 -#define MVPP2_B_HDR_INFO_LAST_MASK BIT(12) -#define MVPP2_B_HDR_INFO_IS_LAST(info) \ - ((info & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS) - /* Static declaractions */ /* Number of RXQs used by single port */ @@ -3611,22 +3592,6 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); } -/* Release multicast buffer */ -static void mvpp2_bm_pool_mc_put(struct mvpp2_port *port, int pool, - dma_addr_t buf_dma_addr, - unsigned long buf_virt_addr, - int mc_id) -{ - u32 val = 0; - - val |= (mc_id & MVPP2_BM_MC_ID_MASK); - mvpp2_write(port->priv, MVPP2_BM_MC_RLS_REG, val); - - mvpp2_bm_pool_put(port, pool, - buf_dma_addr | MVPP2_BM_PHY_RLS_MC_BUFF_MASK, - buf_virt_addr); -} - /* Refill BM pool */ static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm, dma_addr_t dma_addr, @@ -5075,43 +5040,6 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE; } -static void mvpp2_buff_hdr_rx(struct mvpp2_port *port, - struct mvpp2_rx_desc *rx_desc) -{ - struct mvpp2_buff_hdr *buff_hdr; - struct sk_buff *skb; - u32 rx_status = rx_desc->status; - dma_addr_t buff_dma_addr; - unsigned long buff_virt_addr; - dma_addr_t buff_dma_addr_next; - unsigned long buff_virt_addr_next; - int mc_id; - int pool_id; - - pool_id = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >> - MVPP2_RXD_BM_POOL_ID_OFFS; - buff_dma_addr = rx_desc->buf_dma_addr; - buff_virt_addr = rx_desc->buf_cookie; - - do { - skb = (struct sk_buff *)buff_virt_addr; - buff_hdr = (struct mvpp2_buff_hdr *)skb->head; - - mc_id = MVPP2_B_HDR_INFO_MC_ID(buff_hdr->info); - - buff_dma_addr_next = buff_hdr->next_buff_dma_addr; - buff_virt_addr_next = buff_hdr->next_buff_virt_addr; - - /* Release buffer */ - mvpp2_bm_pool_mc_put(port, pool_id, buff_dma_addr, - buff_virt_addr, mc_id); - - buff_dma_addr = buff_dma_addr_next; - buff_virt_addr = buff_virt_addr_next; - - } while (!MVPP2_B_HDR_INFO_IS_LAST(buff_hdr->info)); -} - /* Main rx processing */ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, struct mvpp2_rx_queue *rxq) @@ -5146,11 +5074,6 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, bm = mvpp2_bm_cookie_build(rx_desc); pool = mvpp2_bm_cookie_pool_get(bm); bm_pool = &port->priv->bm_pools[pool]; - /* Check if buffer header is used */ - if (rx_status & MVPP2_RXD_BUF_HDR) { - mvpp2_buff_hdr_rx(port, rx_desc); - continue; - } /* In case of an error, release the requested buffer pointer * to the Buffer Manager. This request process is controlled From df905f2e21b42a948b662d39de82039e02b88de3 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:02 +0100 Subject: [PATCH 075/399] net: mvpp2: remove unused register definition MVPP2_TXQ_THRESH_REG This register is no longer used since commit edc660fa09e2 ("net: mvpp2: replace TX coalescing interrupts with hrtimer"). Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index fb8b5e9a92f0..60cc0206a8f0 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -117,9 +117,6 @@ #define MVPP2_TXQ_DESC_SIZE_REG 0x2088 #define MVPP2_TXQ_DESC_SIZE_MASK 0x3ff0 #define MVPP2_AGGR_TXQ_UPDATE_REG 0x2090 -#define MVPP2_TXQ_THRESH_REG 0x2094 -#define MVPP2_TRANSMITTED_THRESH_OFFSET 16 -#define MVPP2_TRANSMITTED_THRESH_MASK 0x3fff0000 #define MVPP2_TXQ_INDEX_REG 0x2098 #define MVPP2_TXQ_PREF_BUF_REG 0x209c #define MVPP2_PREF_BUF_PTR(desc) ((desc) & 0xfff) From 4d6c2a677fe5a903ed6483865cc14ff00a2054b5 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:03 +0100 Subject: [PATCH 076/399] net: mvpp2: remove mvpp2_txq_pend_desc_num_get() function The mvpp2_txq_pend_desc_num_get() function only selects a TX queue, and reads the number of pending descriptors. It is used in only one place, in mvpp2_txq_clean(), where the TX queue has already been selected by a write to MVPP2_TXQ_NUM_REG. Therefore, this function is useless, and the caller can simply read the value of the MVPP2_TXQ_PENDING_REG register instead. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 60cc0206a8f0..9ddda20b1603 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -4123,18 +4123,6 @@ static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc) /* Tx descriptors helper methods */ -/* Get number of Tx descriptors waiting to be transmitted by HW */ -static int mvpp2_txq_pend_desc_num_get(struct mvpp2_port *port, - struct mvpp2_tx_queue *txq) -{ - u32 val; - - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG); - - return val & MVPP2_TXQ_PENDING_MASK; -} - /* Get pointer to next Tx descriptor to be processed (send) by HW */ static struct mvpp2_tx_desc * mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq) @@ -4740,7 +4728,8 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) mdelay(1); delay++; - pending = mvpp2_txq_pend_desc_num_get(port, txq); + pending = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG) & + MVPP2_TXQ_PENDING_MASK; } while (pending); val &= ~MVPP2_TXQ_DRAIN_EN_MASK; From 4e4a105f1fde326a5d1b0fbcbba8254c54a673e4 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:04 +0100 Subject: [PATCH 077/399] net: mvpp2: store physical address of buffer in rx_desc->buf_cookie The RX descriptors of the PPv2 hardware allow to store several information, amongst which: - the DMA address of the buffer in which the data has been received - a "cookie" field, left to the use of the driver, and not used by the hardware In the current implementation, the "cookie" field is used to store the virtual address of the buffer, so that in the receive completion path, we can easily get the virtual address of the buffer that corresponds to a completed RX descriptors. On PPv2.1, used on 32-bit platforms, those two fields are 32-bit wide, which is enough to store a DMA address in the first field, and a virtual address in the second field. On PPv2.2, used on 64-bit platforms, these two fields have been extended to 40 bits. While 40 bits is enough to store a DMA address (as long as the DMA mask is 40 bits or lower), it is not enough to store a virtual address. Therefore, the "cookie" field can no longer be used to store the virtual address of the buffer. However, as Russell King pointed out, the RX buffers are always allocated in the kernel linear mapping, and therefore using phys_to_virt() on the physical address of the RX buffer is possible and correct. Therefore, this commit changes the driver to use the "cookie" field to store the physical address instead of the virtual address. phys_to_virt() is used in the receive completion path to retrieve the virtual address from the physical address. It is obviously important to realize that the DMA address and physical address are two different things, which is why we store both in the RX descriptors. While those addresses may be identical in some situations, it remains two distinct concepts, and both addresses should be handled separately. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 40 ++++++++++++++++++---------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 9ddda20b1603..35dc07160ac6 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -3412,20 +3412,21 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, for (i = 0; i < bm_pool->buf_num; i++) { dma_addr_t buf_dma_addr; - unsigned long vaddr; + phys_addr_t buf_phys_addr; + void *data; - /* Get buffer virtual address (indirect access) */ buf_dma_addr = mvpp2_read(priv, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); - vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); + buf_phys_addr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); dma_unmap_single(dev, buf_dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE); - if (!vaddr) + data = (void *)phys_to_virt(buf_phys_addr); + if (!data) break; - mvpp2_frag_free(bm_pool, (void *)vaddr); + mvpp2_frag_free(bm_pool, data); } /* Update BM driver with number of buffers removed from pool */ @@ -3542,6 +3543,7 @@ static void mvpp2_rxq_short_pool_set(struct mvpp2_port *port, static void *mvpp2_buf_alloc(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, dma_addr_t *buf_dma_addr, + phys_addr_t *buf_phys_addr, gfp_t gfp_mask) { dma_addr_t dma_addr; @@ -3559,6 +3561,7 @@ static void *mvpp2_buf_alloc(struct mvpp2_port *port, return NULL; } *buf_dma_addr = dma_addr; + *buf_phys_addr = virt_to_phys(data); return data; } @@ -3583,20 +3586,25 @@ static inline int mvpp2_bm_cookie_pool_get(unsigned long cookie) /* Release buffer to BM */ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, dma_addr_t buf_dma_addr, - unsigned long buf_virt_addr) + phys_addr_t buf_phys_addr) { - mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_virt_addr); + /* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply + * returned in the "cookie" field of the RX + * descriptor. Instead of storing the virtual address, we + * store the physical address + */ + mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_phys_addr); mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); } /* Refill BM pool */ static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm, dma_addr_t dma_addr, - unsigned long cookie) + phys_addr_t phys_addr) { int pool = mvpp2_bm_cookie_pool_get(bm); - mvpp2_bm_pool_put(port, pool, dma_addr, cookie); + mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); } /* Allocate buffers for the pool */ @@ -3605,6 +3613,7 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, { int i, buf_size, total_size; dma_addr_t dma_addr; + phys_addr_t phys_addr; void *buf; buf_size = MVPP2_RX_BUF_SIZE(bm_pool->pkt_size); @@ -3619,12 +3628,13 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, } for (i = 0; i < buf_num; i++) { - buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, GFP_KERNEL); + buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, + &phys_addr, GFP_KERNEL); if (!buf) break; mvpp2_bm_pool_put(port, bm_pool->id, dma_addr, - (unsigned long)buf); + phys_addr); } /* Update BM driver with number of buffers added to pool */ @@ -4983,14 +4993,16 @@ static int mvpp2_rx_refill(struct mvpp2_port *port, struct mvpp2_bm_pool *bm_pool, u32 bm) { dma_addr_t dma_addr; + phys_addr_t phys_addr; void *buf; /* No recycle or too many buffers are in use, so allocate a new skb */ - buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, GFP_ATOMIC); + buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, &phys_addr, + GFP_ATOMIC); if (!buf) return -ENOMEM; - mvpp2_pool_refill(port, bm, dma_addr, (unsigned long)buf); + mvpp2_pool_refill(port, bm, dma_addr, phys_addr); return 0; } @@ -5055,7 +5067,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, rx_status = rx_desc->status; rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE; dma_addr = rx_desc->buf_dma_addr; - data = (void *)(uintptr_t)rx_desc->buf_cookie; + data = (void *)phys_to_virt(rx_desc->buf_cookie); bm = mvpp2_bm_cookie_build(rx_desc); pool = mvpp2_bm_cookie_pool_get(bm); From ac3dd277826979f50214894eb2781df4b85ab2a8 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:05 +0100 Subject: [PATCH 078/399] net: mvpp2: add and use accessors for TX/RX descriptors The PPv2.2 IP has a different TX and RX descriptor layout compared to PPv2.1. In order to prepare for the introduction of PPv2.2 support in mvpp2, this commit adds accessors for the different fields of the TX and RX descriptors, and changes the code to use them. For now, the mvpp2_port argument passed to the accessors is not used, but it will be used in follow-up to update the descriptor according to the version of the IP being used. Apart from the mechanical changes to use the newly introduced accessors, a few other changes, needed to use the accessors, are made: - The mvpp2_txq_inc_put() function now takes a mvpp2_port as first argument, as it is needed to use the accessors. - Similarly, the mvpp2_bm_cookie_build() gains a mvpp2_port first argument, for the same reason. - In mvpp2_rx_error(), instead of accessing the RX descriptor in each case of the switch, we introduce a local variable to store the packet size. - In mvpp2_tx_frag_process() and mvpp2_tx() instead of accessing the packet size from the TX descriptor, we use the actual value available in the function, which is used to set the TX descriptor packet size a few lines before. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 192 ++++++++++++++++++++------- 1 file changed, 144 insertions(+), 48 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 35dc07160ac6..2ee066b5c28a 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -945,6 +945,83 @@ static u32 mvpp2_read(struct mvpp2 *priv, u32 offset) return readl(priv->base + offset); } +static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc) +{ + return tx_desc->buf_dma_addr; +} + +static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + dma_addr_t dma_addr) +{ + tx_desc->buf_dma_addr = dma_addr; +} + +static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc) +{ + return tx_desc->data_size; +} + +static void mvpp2_txdesc_size_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + size_t size) +{ + tx_desc->data_size = size; +} + +static void mvpp2_txdesc_txq_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + unsigned int txq) +{ + tx_desc->phys_txq = txq; +} + +static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + unsigned int command) +{ + tx_desc->command = command; +} + +static void mvpp2_txdesc_offset_set(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc, + unsigned int offset) +{ + tx_desc->packet_offset = offset; +} + +static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port, + struct mvpp2_tx_desc *tx_desc) +{ + return tx_desc->packet_offset; +} + +static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + return rx_desc->buf_dma_addr; +} + +static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + return rx_desc->buf_cookie; +} + +static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + return rx_desc->data_size; +} + +static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) +{ + return rx_desc->status; +} + static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) { txq_pcpu->txq_get_index++; @@ -952,15 +1029,17 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) txq_pcpu->txq_get_index = 0; } -static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu, +static void mvpp2_txq_inc_put(struct mvpp2_port *port, + struct mvpp2_txq_pcpu *txq_pcpu, struct sk_buff *skb, struct mvpp2_tx_desc *tx_desc) { struct mvpp2_txq_pcpu_buf *tx_buf = txq_pcpu->buffs + txq_pcpu->txq_put_index; tx_buf->skb = skb; - tx_buf->size = tx_desc->data_size; - tx_buf->dma = tx_desc->buf_dma_addr + tx_desc->packet_offset; + tx_buf->size = mvpp2_txdesc_size_get(port, tx_desc); + tx_buf->dma = mvpp2_txdesc_dma_addr_get(port, tx_desc) + + mvpp2_txdesc_offset_get(port, tx_desc); txq_pcpu->txq_put_index++; if (txq_pcpu->txq_put_index == txq_pcpu->size) txq_pcpu->txq_put_index = 0; @@ -4121,11 +4200,15 @@ static void mvpp2_rxq_offset_set(struct mvpp2_port *port, } /* Obtain BM cookie information from descriptor */ -static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc) +static u32 mvpp2_bm_cookie_build(struct mvpp2_port *port, + struct mvpp2_rx_desc *rx_desc) { - int pool = (rx_desc->status & MVPP2_RXD_BM_POOL_ID_MASK) >> - MVPP2_RXD_BM_POOL_ID_OFFS; int cpu = smp_processor_id(); + int pool; + + pool = (mvpp2_rxdesc_status_get(port, rx_desc) & + MVPP2_RXD_BM_POOL_ID_MASK) >> + MVPP2_RXD_BM_POOL_ID_OFFS; return ((pool & 0xFF) << MVPP2_BM_COOKIE_POOL_OFFS) | ((cpu & 0xFF) << MVPP2_BM_COOKIE_CPU_OFFS); @@ -4559,10 +4642,11 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port, for (i = 0; i < rx_received; i++) { struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq); - u32 bm = mvpp2_bm_cookie_build(rx_desc); + u32 bm = mvpp2_bm_cookie_build(port, rx_desc); - mvpp2_pool_refill(port, bm, rx_desc->buf_dma_addr, - rx_desc->buf_cookie); + mvpp2_pool_refill(port, bm, + mvpp2_rxdesc_dma_addr_get(port, rx_desc), + mvpp2_rxdesc_cookie_get(port, rx_desc)); } mvpp2_rxq_status_update(port, rxq->id, rx_received, rx_received); } @@ -4952,20 +5036,21 @@ static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) static void mvpp2_rx_error(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - u32 status = rx_desc->status; + u32 status = mvpp2_rxdesc_status_get(port, rx_desc); + size_t sz = mvpp2_rxdesc_size_get(port, rx_desc); switch (status & MVPP2_RXD_ERR_CODE_MASK) { case MVPP2_RXD_ERR_CRC: - netdev_err(port->dev, "bad rx status %08x (crc error), size=%d\n", - status, rx_desc->data_size); + netdev_err(port->dev, "bad rx status %08x (crc error), size=%zu\n", + status, sz); break; case MVPP2_RXD_ERR_OVERRUN: - netdev_err(port->dev, "bad rx status %08x (overrun error), size=%d\n", - status, rx_desc->data_size); + netdev_err(port->dev, "bad rx status %08x (overrun error), size=%zu\n", + status, sz); break; case MVPP2_RXD_ERR_RESOURCE: - netdev_err(port->dev, "bad rx status %08x (resource error), size=%d\n", - status, rx_desc->data_size); + netdev_err(port->dev, "bad rx status %08x (resource error), size=%zu\n", + status, sz); break; } } @@ -5059,17 +5144,20 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, struct sk_buff *skb; unsigned int frag_size; dma_addr_t dma_addr; + phys_addr_t phys_addr; u32 bm, rx_status; int pool, rx_bytes, err; void *data; rx_done++; - rx_status = rx_desc->status; - rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE; - dma_addr = rx_desc->buf_dma_addr; - data = (void *)phys_to_virt(rx_desc->buf_cookie); + rx_status = mvpp2_rxdesc_status_get(port, rx_desc); + rx_bytes = mvpp2_rxdesc_size_get(port, rx_desc); + rx_bytes -= MVPP2_MH_SIZE; + dma_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc); + phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); + data = (void *)phys_to_virt(phys_addr); - bm = mvpp2_bm_cookie_build(rx_desc); + bm = mvpp2_bm_cookie_build(port, rx_desc); pool = mvpp2_bm_cookie_pool_get(bm); bm_pool = &port->priv->bm_pools[pool]; @@ -5083,9 +5171,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, dev->stats.rx_errors++; mvpp2_rx_error(port, rx_desc); /* Return the buffer to the pool */ - - mvpp2_pool_refill(port, bm, rx_desc->buf_dma_addr, - rx_desc->buf_cookie); + mvpp2_pool_refill(port, bm, dma_addr, phys_addr); continue; } @@ -5137,11 +5223,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, } static inline void -tx_desc_unmap_put(struct device *dev, struct mvpp2_tx_queue *txq, +tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, struct mvpp2_tx_desc *desc) { - dma_unmap_single(dev, desc->buf_dma_addr, - desc->data_size, DMA_TO_DEVICE); + dma_addr_t buf_dma_addr = + mvpp2_txdesc_dma_addr_get(port, desc); + size_t buf_sz = + mvpp2_txdesc_size_get(port, desc); + dma_unmap_single(port->dev->dev.parent, buf_dma_addr, + buf_sz, DMA_TO_DEVICE); mvpp2_txq_desc_put(txq); } @@ -5160,28 +5250,31 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, void *addr = page_address(frag->page.p) + frag->page_offset; tx_desc = mvpp2_txq_next_desc_get(aggr_txq); - tx_desc->phys_txq = txq->id; - tx_desc->data_size = frag->size; + mvpp2_txdesc_txq_set(port, tx_desc, txq->id); + mvpp2_txdesc_size_set(port, tx_desc, frag->size); buf_dma_addr = dma_map_single(port->dev->dev.parent, addr, - tx_desc->data_size, - DMA_TO_DEVICE); + frag->size, + DMA_TO_DEVICE); if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) { mvpp2_txq_desc_put(txq); goto error; } - tx_desc->packet_offset = buf_dma_addr & MVPP2_TX_DESC_ALIGN; - tx_desc->buf_dma_addr = buf_dma_addr & (~MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_offset_set(port, tx_desc, + buf_dma_addr & MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_dma_addr_set(port, tx_desc, + buf_dma_addr & ~MVPP2_TX_DESC_ALIGN); if (i == (skb_shinfo(skb)->nr_frags - 1)) { /* Last descriptor */ - tx_desc->command = MVPP2_TXD_L_DESC; - mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, + MVPP2_TXD_L_DESC); + mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc); } else { /* Descriptor in the middle: Not First, Not Last */ - tx_desc->command = 0; - mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, 0); + mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc); } } @@ -5193,7 +5286,7 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, */ for (i = i - 1; i >= 0; i--) { tx_desc = txq->descs + i; - tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc); + tx_desc_unmap_put(port, txq, tx_desc); } return -ENOMEM; @@ -5228,35 +5321,38 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) /* Get a descriptor for the first part of the packet */ tx_desc = mvpp2_txq_next_desc_get(aggr_txq); - tx_desc->phys_txq = txq->id; - tx_desc->data_size = skb_headlen(skb); + mvpp2_txdesc_txq_set(port, tx_desc, txq->id); + mvpp2_txdesc_size_set(port, tx_desc, skb_headlen(skb)); buf_dma_addr = dma_map_single(dev->dev.parent, skb->data, - tx_desc->data_size, DMA_TO_DEVICE); + skb_headlen(skb), DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev->dev.parent, buf_dma_addr))) { mvpp2_txq_desc_put(txq); frags = 0; goto out; } - tx_desc->packet_offset = buf_dma_addr & MVPP2_TX_DESC_ALIGN; - tx_desc->buf_dma_addr = buf_dma_addr & ~MVPP2_TX_DESC_ALIGN; + + mvpp2_txdesc_offset_set(port, tx_desc, + buf_dma_addr & MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_dma_addr_set(port, tx_desc, + buf_dma_addr & ~MVPP2_TX_DESC_ALIGN); tx_cmd = mvpp2_skb_tx_csum(port, skb); if (frags == 1) { /* First and Last descriptor */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC; - tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd); + mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc); } else { /* First but not Last */ tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE; - tx_desc->command = tx_cmd; - mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc); + mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd); + mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc); /* Continue with other skb fragments */ if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) { - tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc); + tx_desc_unmap_put(port, txq, tx_desc); frags = 0; goto out; } From faca9247980238f297b04f6701cb0f0f3f18b40c Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:06 +0100 Subject: [PATCH 079/399] net: mvpp2: add hw_version field in "struct mvpp2" In preparation to the introduction for the support of PPv2.2 in the mvpp2 driver, this commit adds a hw_version field to the struct mvpp2, and uses the .data field of the DT match table to fill it in. Having the MVPP21 and MVPP22 definitions available will allow to start adding the necessary conditional code to support PPv2.2. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 2ee066b5c28a..27d88388ec65 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -643,6 +644,9 @@ struct mvpp2 { /* Tclk value */ u32 tclk; + + /* HW version */ + enum { MVPP21, MVPP22 } hw_version; }; struct mvpp2_pcpu_stats { @@ -6429,6 +6433,9 @@ static int mvpp2_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + priv->hw_version = + (unsigned long)of_device_get_match_data(&pdev->dev); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); priv->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(priv->base)) @@ -6533,7 +6540,10 @@ static int mvpp2_remove(struct platform_device *pdev) } static const struct of_device_id mvpp2_match[] = { - { .compatible = "marvell,armada-375-pp2" }, + { + .compatible = "marvell,armada-375-pp2", + .data = (void *)MVPP21, + }, { } }; MODULE_DEVICE_TABLE(of, mvpp2_match); From 054f6372dc9c0a02a1b6491ef182f1edafa0b189 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:07 +0100 Subject: [PATCH 080/399] net: mvpp2: introduce an intermediate union for the TX/RX descriptors Since the format of the HW descriptors is different between PPv2.1 and PPv2.2, this commit introduces an intermediate union, with for now only the PPv2.1 descriptors. The bulk of the driver code only manipulates opaque mvpp2_tx_desc and mvpp2_rx_desc pointers, and the descriptors can only be accessed and modified through the accessor functions. A follow-up commit will add the descriptor definitions for PPv2.2. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 45 +++++++++++++++++++--------- 1 file changed, 31 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 27d88388ec65..e9710e86a072 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -739,7 +739,8 @@ struct mvpp2_port { #define MVPP2_RXD_L3_IP6 BIT(30) #define MVPP2_RXD_BUF_HDR BIT(31) -struct mvpp2_tx_desc { +/* HW TX descriptor for PPv2.1 */ +struct mvpp21_tx_desc { u32 command; /* Options used by HW for packet transmitting.*/ u8 packet_offset; /* the offset from the buffer beginning */ u8 phys_txq; /* destination queue ID */ @@ -750,7 +751,8 @@ struct mvpp2_tx_desc { u32 reserved2; /* reserved (for future use) */ }; -struct mvpp2_rx_desc { +/* HW RX descriptor for PPv2.1 */ +struct mvpp21_rx_desc { u32 status; /* info about received packet */ u16 reserved1; /* parser_info (for future use, PnC) */ u16 data_size; /* size of received packet in bytes */ @@ -765,6 +767,21 @@ struct mvpp2_rx_desc { u32 reserved8; }; +/* Opaque type used by the driver to manipulate the HW TX and RX + * descriptors + */ +struct mvpp2_tx_desc { + union { + struct mvpp21_tx_desc pp21; + }; +}; + +struct mvpp2_rx_desc { + union { + struct mvpp21_rx_desc pp21; + }; +}; + struct mvpp2_txq_pcpu_buf { /* Transmitted SKB */ struct sk_buff *skb; @@ -952,78 +969,78 @@ static u32 mvpp2_read(struct mvpp2 *priv, u32 offset) static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { - return tx_desc->buf_dma_addr; + return tx_desc->pp21.buf_dma_addr; } static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, dma_addr_t dma_addr) { - tx_desc->buf_dma_addr = dma_addr; + tx_desc->pp21.buf_dma_addr = dma_addr; } static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { - return tx_desc->data_size; + return tx_desc->pp21.data_size; } static void mvpp2_txdesc_size_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, size_t size) { - tx_desc->data_size = size; + tx_desc->pp21.data_size = size; } static void mvpp2_txdesc_txq_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, unsigned int txq) { - tx_desc->phys_txq = txq; + tx_desc->pp21.phys_txq = txq; } static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, unsigned int command) { - tx_desc->command = command; + tx_desc->pp21.command = command; } static void mvpp2_txdesc_offset_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, unsigned int offset) { - tx_desc->packet_offset = offset; + tx_desc->pp21.packet_offset = offset; } static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { - return tx_desc->packet_offset; + return tx_desc->pp21.packet_offset; } static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->buf_dma_addr; + return rx_desc->pp21.buf_dma_addr; } static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->buf_cookie; + return rx_desc->pp21.buf_cookie; } static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->data_size; + return rx_desc->pp21.data_size; } static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->status; + return rx_desc->pp21.status; } static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) From e7c5359f2eedf2ad3b1b586552d3b6dfa44c2a79 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:08 +0100 Subject: [PATCH 081/399] net: mvpp2: introduce PPv2.2 HW descriptors and adapt accessors This commit adds the definition of the PPv2.2 HW descriptors, adjusts the mvpp2_tx_desc and mvpp2_rx_desc structures accordingly, and adapts the accessors to work on both PPv2.1 and PPv2.2. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 88 ++++++++++++++++++++++++---- 1 file changed, 76 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index e9710e86a072..746b5bea714a 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -767,18 +767,42 @@ struct mvpp21_rx_desc { u32 reserved8; }; +/* HW TX descriptor for PPv2.2 */ +struct mvpp22_tx_desc { + u32 command; + u8 packet_offset; + u8 phys_txq; + u16 data_size; + u64 reserved1; + u64 buf_dma_addr_ptp; + u64 buf_cookie_misc; +}; + +/* HW RX descriptor for PPv2.2 */ +struct mvpp22_rx_desc { + u32 status; + u16 reserved1; + u16 data_size; + u32 reserved2; + u32 reserved3; + u64 buf_dma_addr_key_hash; + u64 buf_cookie_misc; +}; + /* Opaque type used by the driver to manipulate the HW TX and RX * descriptors */ struct mvpp2_tx_desc { union { struct mvpp21_tx_desc pp21; + struct mvpp22_tx_desc pp22; }; }; struct mvpp2_rx_desc { union { struct mvpp21_rx_desc pp21; + struct mvpp22_rx_desc pp22; }; }; @@ -969,78 +993,118 @@ static u32 mvpp2_read(struct mvpp2 *priv, u32 offset) static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { - return tx_desc->pp21.buf_dma_addr; + if (port->priv->hw_version == MVPP21) + return tx_desc->pp21.buf_dma_addr; + else + return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0); } static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, dma_addr_t dma_addr) { - tx_desc->pp21.buf_dma_addr = dma_addr; + if (port->priv->hw_version == MVPP21) { + tx_desc->pp21.buf_dma_addr = dma_addr; + } else { + u64 val = (u64)dma_addr; + + tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0); + tx_desc->pp22.buf_dma_addr_ptp |= val; + } } static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { - return tx_desc->pp21.data_size; + if (port->priv->hw_version == MVPP21) + return tx_desc->pp21.data_size; + else + return tx_desc->pp22.data_size; } static void mvpp2_txdesc_size_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, size_t size) { - tx_desc->pp21.data_size = size; + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.data_size = size; + else + tx_desc->pp22.data_size = size; } static void mvpp2_txdesc_txq_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, unsigned int txq) { - tx_desc->pp21.phys_txq = txq; + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.phys_txq = txq; + else + tx_desc->pp22.phys_txq = txq; } static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, unsigned int command) { - tx_desc->pp21.command = command; + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.command = command; + else + tx_desc->pp22.command = command; } static void mvpp2_txdesc_offset_set(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc, unsigned int offset) { - tx_desc->pp21.packet_offset = offset; + if (port->priv->hw_version == MVPP21) + tx_desc->pp21.packet_offset = offset; + else + tx_desc->pp22.packet_offset = offset; } static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { - return tx_desc->pp21.packet_offset; + if (port->priv->hw_version == MVPP21) + return tx_desc->pp21.packet_offset; + else + return tx_desc->pp22.packet_offset; } static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->pp21.buf_dma_addr; + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.buf_dma_addr; + else + return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0); } static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->pp21.buf_cookie; + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.buf_cookie; + else + return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0); } static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->pp21.data_size; + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.data_size; + else + return rx_desc->pp22.data_size; } static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { - return rx_desc->pp21.status; + if (port->priv->hw_version == MVPP21) + return rx_desc->pp21.status; + else + return rx_desc->pp22.status; } static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) From d01524d8abab00e3688c7435bcae4aeb461b51f7 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:09 +0100 Subject: [PATCH 082/399] net: mvpp2: adjust the allocation/free of BM pools for PPv2.2 This commit adjusts the allocation and freeing of BM pools to support PPv2.2. This involves: - Checking that the number of buffer pointers is a multiple of 16, as required by the hardware. - Adjusting the size of the DMA coherent area allocated for buffer pointers. Indeed, PPv2.2 needs space for 2 pointers of 64-bits per buffer, as opposed to 2 pointers of 32-bits per buffer in PPv2.1. The size in bytes is now stored in a new field of the mvpp2_bm_pool structure. - On PPv2.2, getting the DMA address and cookie (used for the physical address) of each buffer requires reading the MVPP22_BM_ADDR_HIGH_ALLOC to get the high order bits of those addresses. A new utility function mvpp2_bm_bufs_get_addrs() is introduced to handle this. - On PPv2.2, releasing a buffer requires writing the high order 32 bits of the DMA address and cookie to MVPP22_BM_PHY_VIRT_HIGH_RLS_REG. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 81 ++++++++++++++++++++++++---- 1 file changed, 71 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 746b5bea714a..36aef5cd5446 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -208,11 +208,19 @@ #define MVPP2_BM_PHY_ALLOC_REG(pool) (0x6400 + ((pool) * 4)) #define MVPP2_BM_PHY_ALLOC_GRNTD_MASK BIT(0) #define MVPP2_BM_VIRT_ALLOC_REG 0x6440 +#define MVPP22_BM_ADDR_HIGH_ALLOC 0x6444 +#define MVPP22_BM_ADDR_HIGH_PHYS_MASK 0xff +#define MVPP22_BM_ADDR_HIGH_VIRT_MASK 0xff00 +#define MVPP22_BM_ADDR_HIGH_VIRT_SHIFT 8 #define MVPP2_BM_PHY_RLS_REG(pool) (0x6480 + ((pool) * 4)) #define MVPP2_BM_PHY_RLS_MC_BUFF_MASK BIT(0) #define MVPP2_BM_PHY_RLS_PRIO_EN_MASK BIT(1) #define MVPP2_BM_PHY_RLS_GRNTD_MASK BIT(2) #define MVPP2_BM_VIRT_RLS_REG 0x64c0 +#define MVPP22_BM_ADDR_HIGH_RLS_REG 0x64c4 +#define MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK 0xff +#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK 0xff00 +#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT 8 /* TX Scheduler registers */ #define MVPP2_TXP_SCHED_PORT_INDEX_REG 0x8000 @@ -951,6 +959,8 @@ struct mvpp2_bm_pool { /* Buffer Pointers Pool External (BPPE) size */ int size; + /* BPPE size in bytes */ + int size_bytes; /* Number of buffers for this pool */ int buf_num; /* Pool buffer size */ @@ -3520,11 +3530,23 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool, int size) { - int size_bytes; u32 val; - size_bytes = sizeof(u32) * size; - bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes, + /* Number of buffer pointers must be a multiple of 16, as per + * hardware constraints + */ + if (!IS_ALIGNED(size, 16)) + return -EINVAL; + + /* PPv2.1 needs 8 bytes per buffer pointer, PPv2.2 needs 16 + * bytes per buffer pointer + */ + if (priv->hw_version == MVPP21) + bm_pool->size_bytes = 2 * sizeof(u32) * size; + else + bm_pool->size_bytes = 2 * sizeof(u64) * size; + + bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, bm_pool->size_bytes, &bm_pool->dma_addr, GFP_KERNEL); if (!bm_pool->virt_addr) @@ -3532,15 +3554,15 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, if (!IS_ALIGNED((unsigned long)bm_pool->virt_addr, MVPP2_BM_POOL_PTR_ALIGN)) { - dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr, - bm_pool->dma_addr); + dma_free_coherent(&pdev->dev, bm_pool->size_bytes, + bm_pool->virt_addr, bm_pool->dma_addr); dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n", bm_pool->id, MVPP2_BM_POOL_PTR_ALIGN); return -ENOMEM; } mvpp2_write(priv, MVPP2_BM_POOL_BASE_REG(bm_pool->id), - bm_pool->dma_addr); + lower_32_bits(bm_pool->dma_addr)); mvpp2_write(priv, MVPP2_BM_POOL_SIZE_REG(bm_pool->id), size); val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id)); @@ -3568,6 +3590,31 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv, mvpp2_write(priv, MVPP2_POOL_BUF_SIZE_REG(bm_pool->id), val); } +static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv, + struct mvpp2_bm_pool *bm_pool, + dma_addr_t *dma_addr, + phys_addr_t *phys_addr) +{ + *dma_addr = mvpp2_read(priv, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); + *phys_addr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); + + if (priv->hw_version == MVPP22) { + u32 val; + u32 dma_addr_highbits, phys_addr_highbits; + + val = mvpp2_read(priv, MVPP22_BM_ADDR_HIGH_ALLOC); + dma_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_PHYS_MASK); + phys_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_VIRT_MASK) >> + MVPP22_BM_ADDR_HIGH_VIRT_SHIFT; + + if (sizeof(dma_addr_t) == 8) + *dma_addr |= (u64)dma_addr_highbits << 32; + + if (sizeof(phys_addr_t) == 8) + *phys_addr |= (u64)phys_addr_highbits << 32; + } +} + /* Free all buffers from the pool */ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool) @@ -3579,9 +3626,8 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, phys_addr_t buf_phys_addr; void *data; - buf_dma_addr = mvpp2_read(priv, - MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); - buf_phys_addr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); + mvpp2_bm_bufs_get_addrs(dev, priv, bm_pool, + &buf_dma_addr, &buf_phys_addr); dma_unmap_single(dev, buf_dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE); @@ -3614,7 +3660,7 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev, val |= MVPP2_BM_STOP_MASK; mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id), val); - dma_free_coherent(&pdev->dev, sizeof(u32) * bm_pool->size, + dma_free_coherent(&pdev->dev, bm_pool->size_bytes, bm_pool->virt_addr, bm_pool->dma_addr); return 0; @@ -3752,6 +3798,21 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, dma_addr_t buf_dma_addr, phys_addr_t buf_phys_addr) { + if (port->priv->hw_version == MVPP22) { + u32 val = 0; + + if (sizeof(dma_addr_t) == 8) + val |= upper_32_bits(buf_dma_addr) & + MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK; + + if (sizeof(phys_addr_t) == 8) + val |= (upper_32_bits(buf_phys_addr) + << MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) & + MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK; + + mvpp2_write(port->priv, MVPP22_BM_ADDR_HIGH_RLS_REG, val); + } + /* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply * returned in the "cookie" field of the RX * descriptor. Instead of storing the virtual address, we From 5eac892ac937a9edb490a8ad8755db874c63983e Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:10 +0100 Subject: [PATCH 083/399] net: mvpp2: adapt the mvpp2_rxq_*_pool_set functions to PPv2.2 The MVPP2_RXQ_CONFIG_REG register has a slightly different layout between PPv2.1 and PPv2.2, so this commit adapts the functions modifying this register to accommodate for both the PPv2.1 and PPv2.2 cases. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 32 +++++++++++++++++----------- 1 file changed, 20 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 36aef5cd5446..91dca01b66a8 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -50,9 +50,11 @@ #define MVPP2_SNOOP_PKT_SIZE_MASK 0x1ff #define MVPP2_SNOOP_BUF_HDR_MASK BIT(9) #define MVPP2_RXQ_POOL_SHORT_OFFS 20 -#define MVPP2_RXQ_POOL_SHORT_MASK 0x700000 +#define MVPP21_RXQ_POOL_SHORT_MASK 0x700000 +#define MVPP22_RXQ_POOL_SHORT_MASK 0xf00000 #define MVPP2_RXQ_POOL_LONG_OFFS 24 -#define MVPP2_RXQ_POOL_LONG_MASK 0x7000000 +#define MVPP21_RXQ_POOL_LONG_MASK 0x7000000 +#define MVPP22_RXQ_POOL_LONG_MASK 0xf000000 #define MVPP2_RXQ_PACKET_OFFSET_OFFS 28 #define MVPP2_RXQ_PACKET_OFFSET_MASK 0x70000000 #define MVPP2_RXQ_DISABLE_MASK BIT(31) @@ -3718,17 +3720,20 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv) static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port, int lrxq, int long_pool) { - u32 val; + u32 val, mask; int prxq; /* Get queue physical ID */ prxq = port->rxqs[lrxq]->id; - val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); - val &= ~MVPP2_RXQ_POOL_LONG_MASK; - val |= ((long_pool << MVPP2_RXQ_POOL_LONG_OFFS) & - MVPP2_RXQ_POOL_LONG_MASK); + if (port->priv->hw_version == MVPP21) + mask = MVPP21_RXQ_POOL_LONG_MASK; + else + mask = MVPP22_RXQ_POOL_LONG_MASK; + val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); + val &= ~mask; + val |= (long_pool << MVPP2_RXQ_POOL_LONG_OFFS) & mask; mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val); } @@ -3736,17 +3741,20 @@ static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port, static void mvpp2_rxq_short_pool_set(struct mvpp2_port *port, int lrxq, int short_pool) { - u32 val; + u32 val, mask; int prxq; /* Get queue physical ID */ prxq = port->rxqs[lrxq]->id; - val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); - val &= ~MVPP2_RXQ_POOL_SHORT_MASK; - val |= ((short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) & - MVPP2_RXQ_POOL_SHORT_MASK); + if (port->priv->hw_version == MVPP21) + mask = MVPP21_RXQ_POOL_SHORT_MASK; + else + mask = MVPP22_RXQ_POOL_SHORT_MASK; + val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq)); + val &= ~mask; + val |= (short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) & mask; mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val); } From 3d9017d9449bf8756f881970c970999c9148d306 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:11 +0100 Subject: [PATCH 084/399] net: mvpp2: adapt mvpp2_defaults_set() to PPv2.2 This commit modifies the mvpp2_defaults_set() function to not do the loopback and FIFO threshold initialization, which are not needed for PPv2.2. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 91dca01b66a8..da48d6066e7d 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -4157,16 +4157,18 @@ static void mvpp2_defaults_set(struct mvpp2_port *port) { int tx_port_num, val, queue, ptxq, lrxq; - /* Configure port to loopback if needed */ - if (port->flags & MVPP2_F_LOOPBACK) - mvpp2_port_loopback_set(port); + if (port->priv->hw_version == MVPP21) { + /* Configure port to loopback if needed */ + if (port->flags & MVPP2_F_LOOPBACK) + mvpp2_port_loopback_set(port); - /* Update TX FIFO MIN Threshold */ - val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); - val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK; - /* Min. TX threshold must be less than minimal packet length */ - val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2); - writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); + /* Update TX FIFO MIN Threshold */ + val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); + val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK; + /* Min. TX threshold must be less than minimal packet length */ + val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2); + writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG); + } /* Disable Legacy WRR, Disable EJP, Release from reset */ tx_port_num = mvpp2_egress_port(port); From b02f31fbf92d01ad47a7ea1e071301134be2d332 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:12 +0100 Subject: [PATCH 085/399] net: mvpp2: adjust mvpp2_{rxq, txq}_init for PPv2.2 In PPv2.2, the MVPP2_RXQ_DESC_ADDR_REG and MVPP2_TXQ_DESC_ADDR_REG registers have a slightly different layout, because they need to contain a 64-bit address for the RX and TX descriptor arrays. This commit adjusts those functions accordingly. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index da48d6066e7d..2eec380722c4 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -102,6 +102,7 @@ /* Descriptor Manager Top Registers */ #define MVPP2_RXQ_NUM_REG 0x2040 #define MVPP2_RXQ_DESC_ADDR_REG 0x2044 +#define MVPP22_DESC_ADDR_OFFS 8 #define MVPP2_RXQ_DESC_SIZE_REG 0x2048 #define MVPP2_RXQ_DESC_SIZE_MASK 0x3ff0 #define MVPP2_RXQ_STATUS_UPDATE_REG(rxq) (0x3000 + 4 * (rxq)) @@ -140,6 +141,7 @@ #define MVPP2_TXQ_RSVD_CLR_REG 0x20b8 #define MVPP2_TXQ_RSVD_CLR_OFFSET 16 #define MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu) (0x2100 + 4 * (cpu)) +#define MVPP22_AGGR_TXQ_DESC_ADDR_OFFS 8 #define MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu) (0x2140 + 4 * (cpu)) #define MVPP2_AGGR_TXQ_DESC_SIZE_MASK 0x3ff0 #define MVPP2_AGGR_TXQ_STATUS_REG(cpu) (0x2180 + 4 * (cpu)) @@ -4726,6 +4728,8 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, int desc_num, int cpu, struct mvpp2 *priv) { + u32 txq_dma; + /* Allocate memory for TX descriptors */ aggr_txq->descs = dma_alloc_coherent(&pdev->dev, desc_num * MVPP2_DESC_ALIGNED_SIZE, @@ -4739,10 +4743,16 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, aggr_txq->next_desc_to_proc = mvpp2_read(priv, MVPP2_AGGR_TXQ_INDEX_REG(cpu)); - /* Set Tx descriptors queue starting address */ - /* indirect access */ - mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), - aggr_txq->descs_dma); + /* Set Tx descriptors queue starting address indirect + * access + */ + if (priv->hw_version == MVPP21) + txq_dma = aggr_txq->descs_dma; + else + txq_dma = aggr_txq->descs_dma >> + MVPP22_AGGR_TXQ_DESC_ADDR_OFFS; + + mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), txq_dma); mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), desc_num); return 0; @@ -4753,6 +4763,8 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { + u32 rxq_dma; + rxq->size = port->rx_ring_size; /* Allocate memory for RX descriptors */ @@ -4769,7 +4781,11 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, /* Set Rx descriptors queue starting address - indirect access */ mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq->descs_dma); + if (port->priv->hw_version == MVPP21) + rxq_dma = rxq->descs_dma; + else + rxq_dma = rxq->descs_dma >> MVPP22_DESC_ADDR_OFFS; + mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma); mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); mvpp2_write(port->priv, MVPP2_RXQ_INDEX_REG, 0); From a786841df72e37d574b6135b05ebcdb903034224 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:13 +0100 Subject: [PATCH 086/399] net: mvpp2: handle register mapping and access for PPv2.2 This commit adjusts the mvpp2 driver register mapping and access logic to support PPv2.2, to handle a number of differences. Due to how the registers are laid out in memory, the Device Tree binding for the "reg" property is different: - On PPv2.1, we had a first area for the packet processor registers (common to all ports), and then one area per port. - On PPv2.2, we have a first area for the packet processor registers (common to all ports), and a second area for numerous other registers, including a large number of per-port registers In addition, on PPv2.2, the area for the common registers is split into so-called "address spaces" of 64 KB each. They allow to access per-CPU registers, where each CPU has its own copy of some registers. A few other registers, which have a single copy, also need to be accessed from those per-CPU windows if they are related to a per-CPU register. For example: - Writing to MVPP2_TXQ_NUM_REG selects a TX queue. This register is a per-CPU register, it must be accessed from the current CPU register window. - Then a write to MVPP2_TXQ_PENDING_REG, MVPP2_TXQ_DESC_ADDR_REG (and a few others) will affect the TX queue that was selected by the write to MVPP2_TXQ_NUM_REG. It must be accessed from the same CPU window as the write to the TXQ_NUM_REG. Therefore, the ->base member of 'struct mvpp2' is replaced with a ->cpu_base[] array, each entry pointing to a mapping of the per-CPU area. Since PPv2.1 doesn't have this concept of per-CPU windows, all entries in ->cpu_base[] point to the same io-remapped area. The existing mvpp2_read() and mvpp2_write() accessors use cpu_base[0], they are used for registers for which the CPU window doesn't matter. mvpp2_percpu_read() and mvpp2_percpu_write() are new accessors added to access the registers for which the CPU window does matter, which is why they take a "cpu" as argument. The driver is then changed to use mvpp2_percpu_read() and mvpp2_percpu_write() where it matters. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 255 ++++++++++++++++++++------- 1 file changed, 187 insertions(+), 68 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 2eec380722c4..2b4b4f082dce 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -295,6 +295,8 @@ #define MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v) (((v) << 6) & \ MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK) +#define MVPP22_GMAC_BASE(port) (0x7000 + (port) * 0x1000 + 0xe00) + #define MVPP2_CAUSE_TXQ_SENT_DESC_ALL_MASK 0xff /* Descriptor ring Macros */ @@ -622,6 +624,11 @@ enum mvpp2_prs_l3_cast { */ #define MVPP2_BM_SHORT_PKT_SIZE MVPP2_RX_MAX_PKT_SIZE(512) +#define MVPP21_ADDR_SPACE_SZ 0 +#define MVPP22_ADDR_SPACE_SZ SZ_64K + +#define MVPP2_MAX_CPUS 4 + enum mvpp2_bm_type { MVPP2_BM_FREE, MVPP2_BM_SWF_LONG, @@ -633,8 +640,14 @@ enum mvpp2_bm_type { /* Shared Packet Processor resources */ struct mvpp2 { /* Shared registers' base addresses */ - void __iomem *base; void __iomem *lms_base; + void __iomem *iface_base; + + /* On PPv2.2, each CPU can access the base register through a + * separate address space, each 64 KB apart from each + * other. + */ + void __iomem *cpu_base[MVPP2_MAX_CPUS]; /* Common clocks */ struct clk *pp_clk; @@ -680,6 +693,11 @@ struct mvpp2_port_pcpu { struct mvpp2_port { u8 id; + /* Index of the port from the "group of ports" complex point + * of view + */ + int gop_id; + int irq; struct mvpp2 *priv; @@ -996,12 +1014,60 @@ static int txq_number = MVPP2_MAX_TXQ; static void mvpp2_write(struct mvpp2 *priv, u32 offset, u32 data) { - writel(data, priv->base + offset); + writel(data, priv->cpu_base[0] + offset); } static u32 mvpp2_read(struct mvpp2 *priv, u32 offset) { - return readl(priv->base + offset); + return readl(priv->cpu_base[0] + offset); +} + +/* These accessors should be used to access: + * + * - per-CPU registers, where each CPU has its own copy of the + * register. + * + * MVPP2_BM_VIRT_ALLOC_REG + * MVPP2_BM_ADDR_HIGH_ALLOC + * MVPP22_BM_ADDR_HIGH_RLS_REG + * MVPP2_BM_VIRT_RLS_REG + * MVPP2_ISR_RX_TX_CAUSE_REG + * MVPP2_ISR_RX_TX_MASK_REG + * MVPP2_TXQ_NUM_REG + * MVPP2_AGGR_TXQ_UPDATE_REG + * MVPP2_TXQ_RSVD_REQ_REG + * MVPP2_TXQ_RSVD_RSLT_REG + * MVPP2_TXQ_SENT_REG + * MVPP2_RXQ_NUM_REG + * + * - global registers that must be accessed through a specific CPU + * window, because they are related to an access to a per-CPU + * register + * + * MVPP2_BM_PHY_ALLOC_REG (related to MVPP2_BM_VIRT_ALLOC_REG) + * MVPP2_BM_PHY_RLS_REG (related to MVPP2_BM_VIRT_RLS_REG) + * MVPP2_RXQ_THRESH_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_RXQ_DESC_ADDR_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_RXQ_DESC_SIZE_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_RXQ_INDEX_REG (related to MVPP2_RXQ_NUM_REG) + * MVPP2_TXQ_PENDING_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_DESC_ADDR_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_DESC_SIZE_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_INDEX_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_PENDING_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG) + * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG) + */ +static void mvpp2_percpu_write(struct mvpp2 *priv, int cpu, + u32 offset, u32 data) +{ + writel(data, priv->cpu_base[cpu] + offset); +} + +static u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu, + u32 offset) +{ + return readl(priv->cpu_base[cpu] + offset); } static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, @@ -3599,14 +3665,17 @@ static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv, dma_addr_t *dma_addr, phys_addr_t *phys_addr) { - *dma_addr = mvpp2_read(priv, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); - *phys_addr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG); + int cpu = smp_processor_id(); + + *dma_addr = mvpp2_percpu_read(priv, cpu, + MVPP2_BM_PHY_ALLOC_REG(bm_pool->id)); + *phys_addr = mvpp2_percpu_read(priv, cpu, MVPP2_BM_VIRT_ALLOC_REG); if (priv->hw_version == MVPP22) { u32 val; u32 dma_addr_highbits, phys_addr_highbits; - val = mvpp2_read(priv, MVPP22_BM_ADDR_HIGH_ALLOC); + val = mvpp2_percpu_read(priv, cpu, MVPP22_BM_ADDR_HIGH_ALLOC); dma_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_PHYS_MASK); phys_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_VIRT_MASK) >> MVPP22_BM_ADDR_HIGH_VIRT_SHIFT; @@ -3808,6 +3877,8 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, dma_addr_t buf_dma_addr, phys_addr_t buf_phys_addr) { + int cpu = smp_processor_id(); + if (port->priv->hw_version == MVPP22) { u32 val = 0; @@ -3820,7 +3891,8 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, << MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) & MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK; - mvpp2_write(port->priv, MVPP22_BM_ADDR_HIGH_RLS_REG, val); + mvpp2_percpu_write(port->priv, cpu, + MVPP22_BM_ADDR_HIGH_RLS_REG, val); } /* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply @@ -3828,8 +3900,10 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool, * descriptor. Instead of storing the virtual address, we * store the physical address */ - mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_phys_addr); - mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); + mvpp2_percpu_write(port->priv, cpu, + MVPP2_BM_VIRT_RLS_REG, buf_phys_addr); + mvpp2_percpu_write(port->priv, cpu, + MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr); } /* Refill BM pool */ @@ -4037,7 +4111,8 @@ static void mvpp2_interrupts_mask(void *arg) { struct mvpp2_port *port = arg; - mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), 0); + mvpp2_percpu_write(port->priv, smp_processor_id(), + MVPP2_ISR_RX_TX_MASK_REG(port->id), 0); } /* Unmask the current CPU's Rx/Tx interrupts */ @@ -4045,9 +4120,10 @@ static void mvpp2_interrupts_unmask(void *arg) { struct mvpp2_port *port = arg; - mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), - (MVPP2_CAUSE_MISC_SUM_MASK | - MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK)); + mvpp2_percpu_write(port->priv, smp_processor_id(), + MVPP2_ISR_RX_TX_MASK_REG(port->id), + (MVPP2_CAUSE_MISC_SUM_MASK | + MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK)); } /* Port configuration routines */ @@ -4388,7 +4464,8 @@ mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq) static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending) { /* aggregated access - relevant TXQ number is written in TX desc */ - mvpp2_write(port->priv, MVPP2_AGGR_TXQ_UPDATE_REG, pending); + mvpp2_percpu_write(port->priv, smp_processor_id(), + MVPP2_AGGR_TXQ_UPDATE_REG, pending); } @@ -4417,11 +4494,12 @@ static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv, struct mvpp2_tx_queue *txq, int num) { u32 val; + int cpu = smp_processor_id(); val = (txq->id << MVPP2_TXQ_RSVD_REQ_Q_OFFSET) | num; - mvpp2_write(priv, MVPP2_TXQ_RSVD_REQ_REG, val); + mvpp2_percpu_write(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val); - val = mvpp2_read(priv, MVPP2_TXQ_RSVD_RSLT_REG); + val = mvpp2_percpu_read(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG); return val & MVPP2_TXQ_RSVD_RSLT_MASK; } @@ -4522,7 +4600,8 @@ static inline int mvpp2_txq_sent_desc_proc(struct mvpp2_port *port, u32 val; /* Reading status reg resets transmitted descriptor counter */ - val = mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(txq->id)); + val = mvpp2_percpu_read(port->priv, smp_processor_id(), + MVPP2_TXQ_SENT_REG(txq->id)); return (val & MVPP2_TRANSMITTED_COUNT_MASK) >> MVPP2_TRANSMITTED_COUNT_OFFSET; @@ -4536,7 +4615,8 @@ static void mvpp2_txq_sent_counter_clear(void *arg) for (queue = 0; queue < txq_number; queue++) { int id = port->txqs[queue]->id; - mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(id)); + mvpp2_percpu_read(port->priv, smp_processor_id(), + MVPP2_TXQ_SENT_REG(id)); } } @@ -4595,12 +4675,14 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port) static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { + int cpu = smp_processor_id(); + if (rxq->pkts_coal > MVPP2_OCCUPIED_THRESH_MASK) rxq->pkts_coal = MVPP2_OCCUPIED_THRESH_MASK; - mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_write(port->priv, MVPP2_RXQ_THRESH_REG, - rxq->pkts_coal); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_THRESH_REG, + rxq->pkts_coal); } static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz) @@ -4764,6 +4846,7 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, { u32 rxq_dma; + int cpu; rxq->size = port->rx_ring_size; @@ -4780,14 +4863,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); /* Set Rx descriptors queue starting address - indirect access */ - mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); if (port->priv->hw_version == MVPP21) rxq_dma = rxq->descs_dma; else rxq_dma = rxq->descs_dma >> MVPP22_DESC_ADDR_OFFS; - mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); - mvpp2_write(port->priv, MVPP2_RXQ_INDEX_REG, 0); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, rxq->size); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_INDEX_REG, 0); /* Set Offset */ mvpp2_rxq_offset_set(port, rxq->id, NET_SKB_PAD); @@ -4827,6 +4911,8 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port, static void mvpp2_rxq_deinit(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq) { + int cpu; + mvpp2_rxq_drop_pkts(port, rxq); if (rxq->descs) @@ -4844,9 +4930,10 @@ static void mvpp2_rxq_deinit(struct mvpp2_port *port, * free descriptor number */ mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0); - mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, 0); - mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, 0); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, 0); + mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, 0); } /* Create and initialize a Tx queue */ @@ -4869,16 +4956,18 @@ static int mvpp2_txq_init(struct mvpp2_port *port, txq->last_desc = txq->size - 1; /* Set Tx descriptors queue starting address - indirect access */ - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_dma); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, txq->size & - MVPP2_TXQ_DESC_SIZE_MASK); - mvpp2_write(port->priv, MVPP2_TXQ_INDEX_REG, 0); - mvpp2_write(port->priv, MVPP2_TXQ_RSVD_CLR_REG, - txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET); - val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, + txq->descs_dma); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, + txq->size & MVPP2_TXQ_DESC_SIZE_MASK); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_INDEX_REG, 0); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_RSVD_CLR_REG, + txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET); + val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PENDING_REG); val &= ~MVPP2_TXQ_PENDING_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_PENDING_REG, val); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PENDING_REG, val); /* Calculate base address in prefetch buffer. We reserve 16 descriptors * for each existing TXQ. @@ -4889,9 +4978,9 @@ static int mvpp2_txq_init(struct mvpp2_port *port, desc = (port->id * MVPP2_MAX_TXQ * desc_per_txq) + (txq->log_id * desc_per_txq); - mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, - MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 | - MVPP2_PREF_BUF_THRESH(desc_per_txq/2)); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, + MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 | + MVPP2_PREF_BUF_THRESH(desc_per_txq / 2)); /* WRR / EJP configuration - indirect access */ tx_port_num = mvpp2_egress_port(port); @@ -4963,9 +5052,10 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0); /* Set Tx descriptors queue starting address and size */ - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, 0); - mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, 0); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, 0); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, 0); } /* Cleanup Tx ports */ @@ -4975,10 +5065,11 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) int delay, pending, cpu; u32 val; - mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id); - val = mvpp2_read(port->priv, MVPP2_TXQ_PREF_BUF_REG); + cpu = smp_processor_id(); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); + val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG); val |= MVPP2_TXQ_DRAIN_EN_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val); /* The napi queue has been stopped so wait for all packets * to be transmitted. @@ -4994,12 +5085,13 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) mdelay(1); delay++; - pending = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG) & - MVPP2_TXQ_PENDING_MASK; + pending = mvpp2_percpu_read(port->priv, cpu, + MVPP2_TXQ_PENDING_REG); + pending &= MVPP2_TXQ_PENDING_MASK; } while (pending); val &= ~MVPP2_TXQ_DRAIN_EN_MASK; - mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val); for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); @@ -5585,6 +5677,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) u32 cause_rx_tx, cause_rx, cause_misc; int rx_done = 0; struct mvpp2_port *port = netdev_priv(napi->dev); + int cpu = smp_processor_id(); /* Rx/Tx cause register * @@ -5596,8 +5689,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) * * Each CPU has its own Rx/Tx cause register */ - cause_rx_tx = mvpp2_read(port->priv, - MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); + cause_rx_tx = mvpp2_percpu_read(port->priv, cpu, + MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK; @@ -5606,8 +5699,9 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) /* Clear the cause register */ mvpp2_write(port->priv, MVPP2_ISR_MISC_CAUSE_REG, 0); - mvpp2_write(port->priv, MVPP2_ISR_RX_TX_CAUSE_REG(port->id), - cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); + mvpp2_percpu_write(port->priv, cpu, + MVPP2_ISR_RX_TX_CAUSE_REG(port->id), + cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); } cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; @@ -6306,7 +6400,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, u32 id; int features; int phy_mode; - int priv_common_regs_num = 2; int err, i, cpu; dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number, @@ -6356,12 +6449,22 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->phy_node = phy_node; port->phy_interface = phy_mode; - res = platform_get_resource(pdev, IORESOURCE_MEM, - priv_common_regs_num + id); - port->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(port->base)) { - err = PTR_ERR(port->base); - goto err_free_irq; + if (priv->hw_version == MVPP21) { + res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id); + port->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(port->base)) { + err = PTR_ERR(port->base); + goto err_free_irq; + } + } else { + if (of_property_read_u32(port_node, "gop-port-id", + &port->gop_id)) { + err = -EINVAL; + dev_err(&pdev->dev, "missing gop-port-id value\n"); + goto err_free_irq; + } + + port->base = priv->iface_base + MVPP22_GMAC_BASE(port->gop_id); } /* Alloc per-cpu stats */ @@ -6594,7 +6697,8 @@ static int mvpp2_probe(struct platform_device *pdev) struct device_node *port_node; struct mvpp2 *priv; struct resource *res; - int port_count, first_rxq; + void __iomem *base; + int port_count, first_rxq, cpu; int err; priv = devm_kzalloc(&pdev->dev, sizeof(struct mvpp2), GFP_KERNEL); @@ -6605,14 +6709,29 @@ static int mvpp2_probe(struct platform_device *pdev) (unsigned long)of_device_get_match_data(&pdev->dev); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(priv->base)) - return PTR_ERR(priv->base); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - priv->lms_base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(priv->lms_base)) - return PTR_ERR(priv->lms_base); + if (priv->hw_version == MVPP21) { + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->lms_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->lms_base)) + return PTR_ERR(priv->lms_base); + } else { + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->iface_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->iface_base)) + return PTR_ERR(priv->iface_base); + } + + for_each_present_cpu(cpu) { + u32 addr_space_sz; + + addr_space_sz = (priv->hw_version == MVPP21 ? + MVPP21_ADDR_SPACE_SZ : MVPP22_ADDR_SPACE_SZ); + priv->cpu_base[cpu] = base + cpu * addr_space_sz; + } priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk"); if (IS_ERR(priv->pp_clk)) From 2697582144dd813b0e071ac18e4e59b4f53192de Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:14 +0100 Subject: [PATCH 087/399] net: mvpp2: handle misc PPv2.1/PPv2.2 differences This commit handles a few miscellaneous differences between PPv2.1 and PPv2.2 in different areas, where code done for PPv2.1 doesn't apply for PPv2.2 or needs to be adjusted (getting the MAC address, disabling PHY polling, etc.). Thanks to Russell King for providing the initial implementation of mvpp22_port_mii_set(). Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 85 ++++++++++++++++++++++------ 1 file changed, 67 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 2b4b4f082dce..bd7dc4b6eb2d 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -294,6 +294,22 @@ #define MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK 0x1fc0 #define MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v) (((v) << 6) & \ MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK) +#define MVPP22_GMAC_CTRL_4_REG 0x90 +#define MVPP22_CTRL4_EXT_PIN_GMII_SEL BIT(0) +#define MVPP22_CTRL4_DP_CLK_SEL BIT(5) +#define MVPP22_CTRL4_SYNC_BYPASS BIT(6) +#define MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE BIT(7) + +/* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0, + * relative to port->base. + */ +#define MVPP22_XLG_CTRL3_REG 0x11c +#define MVPP22_XLG_CTRL3_MACMODESELECT_MASK (7 << 13) +#define MVPP22_XLG_CTRL3_MACMODESELECT_GMAC (0 << 13) + +/* SMI registers. PPv2.2 only, relative to priv->iface_base. */ +#define MVPP22_SMI_MISC_CFG_REG 0x1204 +#define MVPP22_SMI_POLLING_EN BIT(10) #define MVPP22_GMAC_BASE(port) (0x7000 + (port) * 0x1000 + 0xe00) @@ -4128,10 +4144,38 @@ static void mvpp2_interrupts_unmask(void *arg) /* Port configuration routines */ +static void mvpp22_port_mii_set(struct mvpp2_port *port) +{ + u32 val; + + return; + + /* Only GOP port 0 has an XLG MAC */ + if (port->gop_id == 0) { + val = readl(port->base + MVPP22_XLG_CTRL3_REG); + val &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK; + val |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC; + writel(val, port->base + MVPP22_XLG_CTRL3_REG); + } + + val = readl(port->base + MVPP22_GMAC_CTRL_4_REG); + if (port->phy_interface == PHY_INTERFACE_MODE_RGMII) + val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL; + else + val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; + val &= ~MVPP22_CTRL4_DP_CLK_SEL; + val |= MVPP22_CTRL4_SYNC_BYPASS; + val |= MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + writel(val, port->base + MVPP22_GMAC_CTRL_4_REG); +} + static void mvpp2_port_mii_set(struct mvpp2_port *port) { u32 val; + if (port->priv->hw_version == MVPP22) + mvpp22_port_mii_set(port); + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); switch (port->phy_interface) { @@ -5813,7 +5857,7 @@ static int mvpp2_check_ringparam_valid(struct net_device *dev, return 0; } -static void mvpp2_get_mac_address(struct mvpp2_port *port, unsigned char *addr) +static void mvpp21_get_mac_address(struct mvpp2_port *port, unsigned char *addr) { u32 mac_addr_l, mac_addr_m, mac_addr_h; @@ -6258,16 +6302,6 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, }; -/* Driver initialization */ - -static void mvpp2_port_power_up(struct mvpp2_port *port) -{ - mvpp2_port_mii_set(port); - mvpp2_port_periodic_xon_disable(port); - mvpp2_port_fc_adv_enable(port); - mvpp2_port_reset(port); -} - /* Initialize port HW */ static int mvpp2_port_init(struct mvpp2_port *port) { @@ -6479,7 +6513,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, mac_from = "device tree"; ether_addr_copy(dev->dev_addr, dt_mac_addr); } else { - mvpp2_get_mac_address(port, hw_mac_addr); + if (priv->hw_version == MVPP21) + mvpp21_get_mac_address(port, hw_mac_addr); if (is_valid_ether_addr(hw_mac_addr)) { mac_from = "hardware"; ether_addr_copy(dev->dev_addr, hw_mac_addr); @@ -6499,7 +6534,14 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev_err(&pdev->dev, "failed to init port %d\n", id); goto err_free_stats; } - mvpp2_port_power_up(port); + + mvpp2_port_mii_set(port); + mvpp2_port_periodic_xon_disable(port); + + if (priv->hw_version == MVPP21) + mvpp2_port_fc_adv_enable(port); + + mvpp2_port_reset(port); port->pcpu = alloc_percpu(struct mvpp2_port_pcpu); if (!port->pcpu) { @@ -6642,9 +6684,15 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_conf_mbus_windows(dram_target_info, priv); /* Disable HW PHY polling */ - val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG); - val |= MVPP2_PHY_AN_STOP_SMI0_MASK; - writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG); + if (priv->hw_version == MVPP21) { + val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG); + val |= MVPP2_PHY_AN_STOP_SMI0_MASK; + writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG); + } else { + val = readl(priv->iface_base + MVPP22_SMI_MISC_CFG_REG); + val &= ~MVPP22_SMI_POLLING_EN; + writel(val, priv->iface_base + MVPP22_SMI_MISC_CFG_REG); + } /* Allocate and initialize aggregated TXQs */ priv->aggr_txqs = devm_kcalloc(&pdev->dev, num_present_cpus(), @@ -6669,8 +6717,9 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) for (i = 0; i < MVPP2_MAX_PORTS; i++) mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(i), rxq_number); - writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT, - priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG); + if (priv->hw_version == MVPP21) + writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT, + priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG); /* Allow cache snoop when transmiting packets */ mvpp2_write(priv, MVPP2_TX_SNOOP_REG, 0x1); From 6763ce3127ed6f346fe60975deea12e290dca719 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:15 +0100 Subject: [PATCH 088/399] net: mvpp2: add AXI bridge initialization for PPv2.2 The PPv2.2 unit is connected to an AXI bus on Armada 7K/8K, so this commit adds the necessary initialization of the AXI bridge. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 85 ++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index bd7dc4b6eb2d..0e103032d16c 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -154,6 +154,34 @@ #define MVPP2_WIN_REMAP(w) (0x4040 + ((w) << 2)) #define MVPP2_BASE_ADDR_ENABLE 0x4060 +/* AXI Bridge Registers */ +#define MVPP22_AXI_BM_WR_ATTR_REG 0x4100 +#define MVPP22_AXI_BM_RD_ATTR_REG 0x4104 +#define MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG 0x4110 +#define MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG 0x4114 +#define MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG 0x4118 +#define MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG 0x411c +#define MVPP22_AXI_RX_DATA_WR_ATTR_REG 0x4120 +#define MVPP22_AXI_TX_DATA_RD_ATTR_REG 0x4130 +#define MVPP22_AXI_RD_NORMAL_CODE_REG 0x4150 +#define MVPP22_AXI_RD_SNOOP_CODE_REG 0x4154 +#define MVPP22_AXI_WR_NORMAL_CODE_REG 0x4160 +#define MVPP22_AXI_WR_SNOOP_CODE_REG 0x4164 + +/* Values for AXI Bridge registers */ +#define MVPP22_AXI_ATTR_CACHE_OFFS 0 +#define MVPP22_AXI_ATTR_DOMAIN_OFFS 12 + +#define MVPP22_AXI_CODE_CACHE_OFFS 0 +#define MVPP22_AXI_CODE_DOMAIN_OFFS 4 + +#define MVPP22_AXI_CODE_CACHE_NON_CACHE 0x3 +#define MVPP22_AXI_CODE_CACHE_WR_CACHE 0x7 +#define MVPP22_AXI_CODE_CACHE_RD_CACHE 0xb + +#define MVPP22_AXI_CODE_DOMAIN_OUTER_DOM 2 +#define MVPP22_AXI_CODE_DOMAIN_SYSTEM 3 + /* Interrupt Cause and Mask registers */ #define MVPP2_ISR_RX_THRESHOLD_REG(rxq) (0x5200 + 4 * (rxq)) #define MVPP2_MAX_ISR_RX_THRESHOLD 0xfffff0 @@ -6664,6 +6692,60 @@ static void mvpp2_rx_fifo_init(struct mvpp2 *priv) mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1); } +static void mvpp2_axi_init(struct mvpp2 *priv) +{ + u32 val, rdval, wrval; + + mvpp2_write(priv, MVPP22_BM_ADDR_HIGH_RLS_REG, 0x0); + + /* AXI Bridge Configuration */ + + rdval = MVPP22_AXI_CODE_CACHE_RD_CACHE + << MVPP22_AXI_ATTR_CACHE_OFFS; + rdval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_ATTR_DOMAIN_OFFS; + + wrval = MVPP22_AXI_CODE_CACHE_WR_CACHE + << MVPP22_AXI_ATTR_CACHE_OFFS; + wrval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_ATTR_DOMAIN_OFFS; + + /* BM */ + mvpp2_write(priv, MVPP22_AXI_BM_WR_ATTR_REG, wrval); + mvpp2_write(priv, MVPP22_AXI_BM_RD_ATTR_REG, rdval); + + /* Descriptors */ + mvpp2_write(priv, MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG, rdval); + mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG, wrval); + mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG, rdval); + mvpp2_write(priv, MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG, wrval); + + /* Buffer Data */ + mvpp2_write(priv, MVPP22_AXI_TX_DATA_RD_ATTR_REG, rdval); + mvpp2_write(priv, MVPP22_AXI_RX_DATA_WR_ATTR_REG, wrval); + + val = MVPP22_AXI_CODE_CACHE_NON_CACHE + << MVPP22_AXI_CODE_CACHE_OFFS; + val |= MVPP22_AXI_CODE_DOMAIN_SYSTEM + << MVPP22_AXI_CODE_DOMAIN_OFFS; + mvpp2_write(priv, MVPP22_AXI_RD_NORMAL_CODE_REG, val); + mvpp2_write(priv, MVPP22_AXI_WR_NORMAL_CODE_REG, val); + + val = MVPP22_AXI_CODE_CACHE_RD_CACHE + << MVPP22_AXI_CODE_CACHE_OFFS; + val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_CODE_DOMAIN_OFFS; + + mvpp2_write(priv, MVPP22_AXI_RD_SNOOP_CODE_REG, val); + + val = MVPP22_AXI_CODE_CACHE_WR_CACHE + << MVPP22_AXI_CODE_CACHE_OFFS; + val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM + << MVPP22_AXI_CODE_DOMAIN_OFFS; + + mvpp2_write(priv, MVPP22_AXI_WR_SNOOP_CODE_REG, val); +} + /* Initialize network controller common part HW */ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) { @@ -6683,6 +6765,9 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) if (dram_target_info) mvpp2_conf_mbus_windows(dram_target_info, priv); + if (priv->hw_version == MVPP22) + mvpp2_axi_init(priv); + /* Disable HW PHY polling */ if (priv->hw_version == MVPP21) { val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG); From a73fef100275d5228cad5041b3e55af859f30d1e Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:16 +0100 Subject: [PATCH 089/399] net: mvpp2: rework RXQ interrupt group initialization for PPv2.2 This commit adjusts how the MVPP2_ISR_RXQ_GROUP_REG register is configured, since it changed between PPv2.1 and PPv2.2. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 46 +++++++++++++++++++++++++--- 1 file changed, 42 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 0e103032d16c..21f47d280995 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -185,7 +185,21 @@ /* Interrupt Cause and Mask registers */ #define MVPP2_ISR_RX_THRESHOLD_REG(rxq) (0x5200 + 4 * (rxq)) #define MVPP2_MAX_ISR_RX_THRESHOLD 0xfffff0 -#define MVPP2_ISR_RXQ_GROUP_REG(rxq) (0x5400 + 4 * (rxq)) +#define MVPP21_ISR_RXQ_GROUP_REG(rxq) (0x5400 + 4 * (rxq)) + +#define MVPP22_ISR_RXQ_GROUP_INDEX_REG 0x5400 +#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET 7 + +#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 + +#define MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG 0x5404 +#define MVPP22_ISR_RXQ_SUB_GROUP_STARTQ_MASK 0x1f +#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_MASK 0xf00 +#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET 8 + #define MVPP2_ISR_ENABLE_REG(port) (0x5420 + 4 * (port)) #define MVPP2_ISR_ENABLE_INTERRUPT(mask) ((mask) & 0xffff) #define MVPP2_ISR_DISABLE_INTERRUPT(mask) (((mask) << 16) & 0xffff0000) @@ -6406,7 +6420,18 @@ static int mvpp2_port_init(struct mvpp2_port *port) } /* Configure Rx queue group interrupt for this port */ - mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(port->id), rxq_number); + if (priv->hw_version == MVPP21) { + mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(port->id), + rxq_number); + } else { + u32 val; + + val = (port->id << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val); + + val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val); + } /* Create Rx descriptor rings */ for (queue = 0; queue < rxq_number; queue++) { @@ -6799,8 +6824,21 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_rx_fifo_init(priv); /* Reset Rx queue group interrupt configuration */ - for (i = 0; i < MVPP2_MAX_PORTS; i++) - mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(i), rxq_number); + for (i = 0; i < MVPP2_MAX_PORTS; i++) { + if (priv->hw_version == MVPP21) { + mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(i), + rxq_number); + continue; + } else { + u32 val; + + val = (i << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val); + + val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET); + mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val); + } + } if (priv->hw_version == MVPP21) writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT, From 59b9a31ede18ef54dcac466052706bb47a394ab5 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:17 +0100 Subject: [PATCH 090/399] net: mvpp2: adapt rxq distribution to PPv2.2 In PPv2.1, we have a maximum of 8 RXQs per port, with a default of 4 RXQs per port, and we were assigning RXQs 0->3 to the first port, 4->7 to the second port, 8->11 to the third port, etc. In PPv2.2, we have a maximum of 32 RXQs per port, and we must allocate RXQs from the range of 32 RXQs available for each port. So port 0 must use RXQs in the range 0->31, port 1 in the range 32->63, etc. This commit adapts the mvpp2 to this difference between PPv2.1 and PPv2.2: - The constant definition MVPP2_MAX_RXQ is replaced by a new field 'max_port_rxqs' in 'struct mvpp2', which stores the maximum number of RXQs per port. This field is initialized during ->probe() depending on the IP version. - MVPP2_RXQ_TOTAL_NUM is removed, and instead we calculate the total number of RXQs by multiplying the number of ports by the maximum of RXQs per port. This was anyway used in only one place. - In mvpp2_port_probe(), the calculation of port->first_rxq is adjusted to cope with the different allocation strategy between PPv2.1 and PPv2.2. Due to this change, the 'next_first_rxq' argument of this function is no longer needed and is removed. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 35 +++++++++++++++------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 21f47d280995..1bb1aa52618d 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -402,15 +402,9 @@ /* Maximum number of TXQs used by single port */ #define MVPP2_MAX_TXQ 8 -/* Maximum number of RXQs used by single port */ -#define MVPP2_MAX_RXQ 8 - /* Dfault number of RXQs in use */ #define MVPP2_DEFAULT_RXQ 4 -/* Total number of RXQs available to all ports */ -#define MVPP2_RXQ_TOTAL_NUM (MVPP2_MAX_PORTS * MVPP2_MAX_RXQ) - /* Max number of Rx descriptors */ #define MVPP2_MAX_RXD 128 @@ -730,6 +724,9 @@ struct mvpp2 { /* HW version */ enum { MVPP21, MVPP22 } hw_version; + + /* Maximum number of RXQs per port */ + unsigned int max_port_rxqs; }; struct mvpp2_pcpu_stats { @@ -6352,7 +6349,8 @@ static int mvpp2_port_init(struct mvpp2_port *port) struct mvpp2_txq_pcpu *txq_pcpu; int queue, cpu, err; - if (port->first_rxq + rxq_number > MVPP2_RXQ_TOTAL_NUM) + if (port->first_rxq + rxq_number > + MVPP2_MAX_PORTS * priv->max_port_rxqs) return -EINVAL; /* Disable port */ @@ -6473,8 +6471,7 @@ static int mvpp2_port_init(struct mvpp2_port *port) /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, struct device_node *port_node, - struct mvpp2 *priv, - int *next_first_rxq) + struct mvpp2 *priv) { struct device_node *phy_node; struct mvpp2_port *port; @@ -6532,7 +6529,11 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->priv = priv; port->id = id; - port->first_rxq = *next_first_rxq; + if (priv->hw_version == MVPP21) + port->first_rxq = port->id * rxq_number; + else + port->first_rxq = port->id * priv->max_port_rxqs; + port->phy_node = phy_node; port->phy_interface = phy_mode; @@ -6632,8 +6633,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, } netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr); - /* Increment the first Rx queue number to be used by the next port */ - *next_first_rxq += rxq_number; priv->port_list[id] = port; return 0; @@ -6779,7 +6778,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) u32 val; /* Checks for hardware constraints */ - if (rxq_number % 4 || (rxq_number > MVPP2_MAX_RXQ) || + if (rxq_number % 4 || (rxq_number > priv->max_port_rxqs) || (txq_number > MVPP2_MAX_TXQ)) { dev_err(&pdev->dev, "invalid queue size parameter\n"); return -EINVAL; @@ -6870,7 +6869,7 @@ static int mvpp2_probe(struct platform_device *pdev) struct mvpp2 *priv; struct resource *res; void __iomem *base; - int port_count, first_rxq, cpu; + int port_count, cpu; int err; priv = devm_kzalloc(&pdev->dev, sizeof(struct mvpp2), GFP_KERNEL); @@ -6905,6 +6904,11 @@ static int mvpp2_probe(struct platform_device *pdev) priv->cpu_base[cpu] = base + cpu * addr_space_sz; } + if (priv->hw_version == MVPP21) + priv->max_port_rxqs = 8; + else + priv->max_port_rxqs = 32; + priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk"); if (IS_ERR(priv->pp_clk)) return PTR_ERR(priv->pp_clk); @@ -6947,9 +6951,8 @@ static int mvpp2_probe(struct platform_device *pdev) } /* Initialize ports */ - first_rxq = 0; for_each_available_child_of_node(dn, port_node) { - err = mvpp2_port_probe(pdev, port_node, priv, &first_rxq); + err = mvpp2_port_probe(pdev, port_node, priv); if (err < 0) goto err_gop_clk; } From fceb55d41508c01ac05f1c9382d7efddcdf71409 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:18 +0100 Subject: [PATCH 091/399] net: mvpp2: add support for an additional clock needed for PPv2.2 The PPv2.2 variant of the network controller needs an additional clock, the "MG clock" in order for the IP block to operate properly. This commit adds support for this additional clock to the driver, reworking as needed the error handling path. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 1bb1aa52618d..0a3c47017809 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -704,6 +704,7 @@ struct mvpp2 { /* Common clocks */ struct clk *pp_clk; struct clk *gop_clk; + struct clk *mg_clk; /* List of pointers to port structures */ struct mvpp2_port **port_list; @@ -6925,6 +6926,18 @@ static int mvpp2_probe(struct platform_device *pdev) if (err < 0) goto err_pp_clk; + if (priv->hw_version == MVPP22) { + priv->mg_clk = devm_clk_get(&pdev->dev, "mg_clk"); + if (IS_ERR(priv->mg_clk)) { + err = PTR_ERR(priv->mg_clk); + goto err_gop_clk; + } + + err = clk_prepare_enable(priv->mg_clk); + if (err < 0) + goto err_gop_clk; + } + /* Get system's tclk rate */ priv->tclk = clk_get_rate(priv->pp_clk); @@ -6932,14 +6945,14 @@ static int mvpp2_probe(struct platform_device *pdev) err = mvpp2_init(pdev, priv); if (err < 0) { dev_err(&pdev->dev, "failed to initialize controller\n"); - goto err_gop_clk; + goto err_mg_clk; } port_count = of_get_available_child_count(dn); if (port_count == 0) { dev_err(&pdev->dev, "no ports enabled\n"); err = -ENODEV; - goto err_gop_clk; + goto err_mg_clk; } priv->port_list = devm_kcalloc(&pdev->dev, port_count, @@ -6947,19 +6960,22 @@ static int mvpp2_probe(struct platform_device *pdev) GFP_KERNEL); if (!priv->port_list) { err = -ENOMEM; - goto err_gop_clk; + goto err_mg_clk; } /* Initialize ports */ for_each_available_child_of_node(dn, port_node) { err = mvpp2_port_probe(pdev, port_node, priv); if (err < 0) - goto err_gop_clk; + goto err_mg_clk; } platform_set_drvdata(pdev, priv); return 0; +err_mg_clk: + if (priv->hw_version == MVPP22) + clk_disable_unprepare(priv->mg_clk); err_gop_clk: clk_disable_unprepare(priv->gop_clk); err_pp_clk: @@ -6995,6 +7011,7 @@ static int mvpp2_remove(struct platform_device *pdev) aggr_txq->descs_dma); } + clk_disable_unprepare(priv->mg_clk); clk_disable_unprepare(priv->pp_clk); clk_disable_unprepare(priv->gop_clk); From 2067e0a13cfe0b1bdca7b91bc5e4f2740b07d478 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:19 +0100 Subject: [PATCH 092/399] net: mvpp2: set dma mask and coherent dma mask on PPv2.2 On PPv2.2, the streaming mappings can be anywhere in the first 40 bits of the physical address space. However, for the coherent mappings, we still need them to be in the first 32 bits of the address space, because all BM pools share a single register to store the high 32 bits of the BM pool address, which means all BM pools must be allocated in the same 4GB memory area. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 0a3c47017809..92c47f35bbdb 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -6941,6 +6941,20 @@ static int mvpp2_probe(struct platform_device *pdev) /* Get system's tclk rate */ priv->tclk = clk_get_rate(priv->pp_clk); + if (priv->hw_version == MVPP22) { + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40)); + if (err) + goto err_mg_clk; + /* Sadly, the BM pools all share the same register to + * store the high 32 bits of their address. So they + * must all have the same high 32 bits, which forces + * us to restrict coherent memory to DMA_BIT_MASK(32). + */ + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + goto err_mg_clk; + } + /* Initialize network controller */ err = mvpp2_init(pdev, priv); if (err < 0) { From fc5e1550e5c365ecd94497fe6d2f230a5e8a2a22 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 7 Mar 2017 16:53:20 +0100 Subject: [PATCH 093/399] net: mvpp2: finally add the PPv2.2 compatible string Now that the mvpp2 driver has been modified to accommodate the support for PPv2.2, we can finally advertise this support by adding the appropriate compatible string. At the same time, we update the Kconfig description of the MVPP2 driver. Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/Kconfig | 4 ++-- drivers/net/ethernet/marvell/mvpp2.c | 4 ++++ 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index d2555e8b947e..da6fb825afea 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -82,13 +82,13 @@ config MVNETA_BM that all dependencies are met. config MVPP2 - tristate "Marvell Armada 375 network interface support" + tristate "Marvell Armada 375/7K/8K network interface support" depends on ARCH_MVEBU || COMPILE_TEST depends on HAS_DMA select MVMDIO ---help--- This driver supports the network interface units in the - Marvell ARMADA 375 SoC. + Marvell ARMADA 375, 7K and 8K SoCs. config PXA168_ETH tristate "Marvell pxa168 ethernet support" diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 92c47f35bbdb..af5bfa13d976 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -7037,6 +7037,10 @@ static const struct of_device_id mvpp2_match[] = { .compatible = "marvell,armada-375-pp2", .data = (void *)MVPP21, }, + { + .compatible = "marvell,armada-7k-pp22", + .data = (void *)MVPP22, + }, { } }; MODULE_DEVICE_TABLE(of, mvpp2_match); From 038e893d78037b5876771f84722b459b3916bfaf Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 6 Mar 2017 12:56:02 -0800 Subject: [PATCH 094/399] tg3: Add the ability to conditionally build w/ HWMON Introduce a Kconfig option: CONFIG_TIGON3_HWMON which allows to build in/out support for thermal sensors reported by Tigon3 NICs. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/Kconfig | 8 +++++++- drivers/net/ethernet/broadcom/tg3.c | 7 +++++++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 940fb24bba21..96413808c726 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -109,7 +109,6 @@ config TIGON3 tristate "Broadcom Tigon3 support" depends on PCI select PHYLIB - select HWMON imply PTP_1588_CLOCK ---help--- This driver supports Broadcom Tigon3 based gigabit Ethernet cards. @@ -117,6 +116,13 @@ config TIGON3 To compile this driver as a module, choose M here: the module will be called tg3. This is recommended. +config TIGON3_HWMON + bool "Broadcom Tigon3 HWMON support" + default y + depends on TIGON3 && HWMON && !(TIGON3=y && HWMON=m) + ---help--- + Say Y if you want to expose the thermal sensor on Tigon3 devices. + config BNX2X tristate "Broadcom NetXtremeII 10Gb support" depends on PCI diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 30d1eb9ebec9..f395b951f5e7 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -825,6 +825,7 @@ static int tg3_ape_event_lock(struct tg3 *tp, u32 timeout_us) return timeout_us ? 0 : -EBUSY; } +#ifdef CONFIG_TIGON3_HWMON static int tg3_ape_wait_for_event(struct tg3 *tp, u32 timeout_us) { u32 i, apedata; @@ -904,6 +905,7 @@ static int tg3_ape_scratchpad_read(struct tg3 *tp, u32 *data, u32 base_off, return 0; } +#endif static int tg3_ape_send_event(struct tg3 *tp, u32 event) { @@ -10744,6 +10746,7 @@ static int tg3_init_hw(struct tg3 *tp, bool reset_phy) return tg3_reset_hw(tp, reset_phy); } +#ifdef CONFIG_TIGON3_HWMON static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir) { int i; @@ -10826,6 +10829,10 @@ static void tg3_hwmon_open(struct tg3 *tp) dev_err(&pdev->dev, "Cannot register hwmon device, aborting\n"); } } +#else +static inline void tg3_hwmon_close(struct tg3 *tp) { } +static inline void tg3_hwmon_open(struct tg3 *tp) { } +#endif /* CONFIG_TIGON3_HWMON */ #define TG3_STAT_ADD32(PSTAT, REG) \ From e3c36e483b4806a6bf28db411f79ea9aad61ec78 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 7 Mar 2017 16:27:10 +0100 Subject: [PATCH 095/399] net: mediatek: Use eth_hw_addr_random() Use eth_hw_addr_random() to set a random dev_addr and update addr_assign_type instead of open-coding it. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 9e757684816d..bf6317eca2f6 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1908,10 +1908,9 @@ static int __init mtk_init(struct net_device *dev) /* If the mac address is invalid, use random mac address */ if (!is_valid_ether_addr(dev->dev_addr)) { - random_ether_addr(dev->dev_addr); + eth_hw_addr_random(dev); dev_err(eth->dev, "generated random MAC address %pM\n", dev->dev_addr); - dev->addr_assign_type = NET_ADDR_RANDOM; } return mtk_phy_connect(dev); From 64f48e593a54a8bee8bee4bf8391d5a4e9057d34 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Tue, 7 Mar 2017 15:27:36 +0000 Subject: [PATCH 096/399] net: stmicro: replace kzalloc with devm_kzalloc The axi variable was not being freed upon device removal. With devm_kzalloc it ensures that it is properly freed. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 433a84239a68..0ba1caf18619 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -108,7 +108,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) if (!np) return NULL; - axi = kzalloc(sizeof(*axi), GFP_KERNEL); + axi = devm_kzalloc(&pdev->dev, sizeof(*axi), GFP_KERNEL); if (!axi) { of_node_put(np); return ERR_PTR(-ENOMEM); From 35ae57eae9135f891640f3076fd0a3c990632af0 Mon Sep 17 00:00:00 2001 From: Rick Farrington Date: Tue, 7 Mar 2017 11:40:41 -0800 Subject: [PATCH 097/399] liquidio: add support for XPS Add support for XPS. Signed-off-by: Rick Farrington Signed-off-by: Felix Manlunas Signed-off-by: Derek Chickles Signed-off-by: Satanand Burla Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_main.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index be9c0e3f5ade..dffed432d58e 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2553,6 +2553,15 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev, __func__); return 1; } + + if (octeon_dev->ioq_vector) { + struct octeon_ioq_vector *ioq_vector; + + ioq_vector = &octeon_dev->ioq_vector[q]; + netif_set_xps_queue(netdev, + &ioq_vector->affinity_mask, + ioq_vector->iq_index); + } } return 0; From 384fe7a4d732c3812542142ce5bb353973b34638 Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Tue, 7 Mar 2017 17:08:40 -0800 Subject: [PATCH 098/399] drivers: net: xgene-v2: Add DMA descriptor This patch adds DMA descriptor setup and interrupt enable/disable functions. Signed-off-by: Iyappan Subramanian Signed-off-by: Keyur Chudgar Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene-v2/main.h | 74 ++++++++++++++ drivers/net/ethernet/apm/xgene-v2/ring.c | 81 +++++++++++++++ drivers/net/ethernet/apm/xgene-v2/ring.h | 119 +++++++++++++++++++++++ 3 files changed, 274 insertions(+) create mode 100644 drivers/net/ethernet/apm/xgene-v2/main.h create mode 100644 drivers/net/ethernet/apm/xgene-v2/ring.c create mode 100644 drivers/net/ethernet/apm/xgene-v2/ring.h diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h new file mode 100644 index 000000000000..a2f87126dce0 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/main.h @@ -0,0 +1,74 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __XGENE_ENET_V2_MAIN_H__ +#define __XGENE_ENET_V2_MAIN_H__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "mac.h" +#include "enet.h" +#include "ring.h" + +#define XGENE_ENET_V2_VERSION "v1.0" +#define XGENE_ENET_STD_MTU 1536 +#define XGENE_ENET_MIN_FRAME 60 +#define IRQ_ID_SIZE 16 + +struct xge_resource { + void __iomem *base_addr; + int phy_mode; + u32 irq; +}; + +struct xge_stats { + u64 tx_packets; + u64 tx_bytes; + u64 rx_packets; + u64 rx_bytes; +}; + +/* ethernet private data */ +struct xge_pdata { + struct xge_resource resources; + struct xge_desc_ring *tx_ring; + struct xge_desc_ring *rx_ring; + struct platform_device *pdev; + char irq_name[IRQ_ID_SIZE]; + struct net_device *ndev; + struct napi_struct napi; + struct xge_stats stats; + int phy_speed; + u8 nbufs; +}; + +#endif /* __XGENE_ENET_V2_MAIN_H__ */ diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.c b/drivers/net/ethernet/apm/xgene-v2/ring.c new file mode 100644 index 000000000000..38810828f8f0 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/ring.c @@ -0,0 +1,81 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include "main.h" + +/* create circular linked list of descriptors */ +void xge_setup_desc(struct xge_desc_ring *ring) +{ + struct xge_raw_desc *raw_desc; + dma_addr_t dma_h, next_dma; + u16 offset; + int i; + + for (i = 0; i < XGENE_ENET_NUM_DESC; i++) { + raw_desc = &ring->raw_desc[i]; + + offset = (i + 1) & (XGENE_ENET_NUM_DESC - 1); + next_dma = ring->dma_addr + (offset * XGENE_ENET_DESC_SIZE); + + raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) | + SET_BITS(PKT_SIZE, SLOT_EMPTY)); + dma_h = upper_32_bits(next_dma); + raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, next_dma) | + SET_BITS(NEXT_DESC_ADDRH, dma_h)); + } +} + +void xge_update_tx_desc_addr(struct xge_pdata *pdata) +{ + struct xge_desc_ring *ring = pdata->tx_ring; + dma_addr_t dma_addr = ring->dma_addr; + + xge_wr_csr(pdata, DMATXDESCL, dma_addr); + xge_wr_csr(pdata, DMATXDESCH, upper_32_bits(dma_addr)); + + ring->head = 0; + ring->tail = 0; +} + +void xge_update_rx_desc_addr(struct xge_pdata *pdata) +{ + struct xge_desc_ring *ring = pdata->rx_ring; + dma_addr_t dma_addr = ring->dma_addr; + + xge_wr_csr(pdata, DMARXDESCL, dma_addr); + xge_wr_csr(pdata, DMARXDESCH, upper_32_bits(dma_addr)); + + ring->head = 0; + ring->tail = 0; +} + +void xge_intr_enable(struct xge_pdata *pdata) +{ + u32 data; + + data = RX_PKT_RCVD | TX_PKT_SENT; + xge_wr_csr(pdata, DMAINTRMASK, data); +} + +void xge_intr_disable(struct xge_pdata *pdata) +{ + xge_wr_csr(pdata, DMAINTRMASK, 0); +} diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.h b/drivers/net/ethernet/apm/xgene-v2/ring.h new file mode 100644 index 000000000000..abc8c9a84954 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/ring.h @@ -0,0 +1,119 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __XGENE_ENET_V2_RING_H__ +#define __XGENE_ENET_V2_RING_H__ + +#define XGENE_ENET_DESC_SIZE 64 +#define XGENE_ENET_NUM_DESC 256 +#define NUM_BUFS 8 +#define SLOT_EMPTY 0xfff + +#define DMATXCTRL 0xa180 +#define DMATXDESCL 0xa184 +#define DMATXDESCH 0xa1a0 +#define DMATXSTATUS 0xa188 +#define DMARXCTRL 0xa18c +#define DMARXDESCL 0xa190 +#define DMARXDESCH 0xa1a4 +#define DMARXSTATUS 0xa194 +#define DMAINTRMASK 0xa198 +#define DMAINTERRUPT 0xa19c + +#define D_POS 62 +#define D_LEN 2 +#define E_POS 63 +#define E_LEN 1 +#define PKT_ADDRL_POS 0 +#define PKT_ADDRL_LEN 32 +#define PKT_ADDRH_POS 32 +#define PKT_ADDRH_LEN 10 +#define PKT_SIZE_POS 32 +#define PKT_SIZE_LEN 12 +#define NEXT_DESC_ADDRL_POS 0 +#define NEXT_DESC_ADDRL_LEN 32 +#define NEXT_DESC_ADDRH_POS 48 +#define NEXT_DESC_ADDRH_LEN 10 + +#define TXPKTCOUNT_POS 16 +#define TXPKTCOUNT_LEN 8 +#define RXPKTCOUNT_POS 16 +#define RXPKTCOUNT_LEN 8 + +#define TX_PKT_SENT BIT(0) +#define TX_BUS_ERROR BIT(3) +#define RX_PKT_RCVD BIT(4) +#define RX_BUS_ERROR BIT(7) +#define RXSTATUS_RXPKTRCVD BIT(0) + +struct xge_raw_desc { + __le64 m0; + __le64 m1; + __le64 m2; + __le64 m3; + __le64 m4; + __le64 m5; + __le64 m6; + __le64 m7; +}; + +struct pkt_info { + struct sk_buff *skb; + dma_addr_t dma_addr; + void *pkt_buf; +}; + +/* software context of a descriptor ring */ +struct xge_desc_ring { + struct net_device *ndev; + dma_addr_t dma_addr; + u8 head; + u8 tail; + union { + void *desc_addr; + struct xge_raw_desc *raw_desc; + }; + struct pkt_info (*pkt_info); +}; + +static inline u64 xge_set_desc_bits(int pos, int len, u64 val) +{ + return (val & ((1ULL << len) - 1)) << pos; +} + +static inline u64 xge_get_desc_bits(int pos, int len, u64 src) +{ + return (src >> pos) & ((1ULL << len) - 1); +} + +#define SET_BITS(field, val) \ + xge_set_desc_bits(field ## _POS, field ## _LEN, val) + +#define GET_BITS(field, src) \ + xge_get_desc_bits(field ## _POS, field ## _LEN, src) + +void xge_setup_desc(struct xge_desc_ring *ring); +void xge_update_tx_desc_addr(struct xge_pdata *pdata); +void xge_update_rx_desc_addr(struct xge_pdata *pdata); +void xge_intr_enable(struct xge_pdata *pdata); +void xge_intr_disable(struct xge_pdata *pdata); + +#endif /* __XGENE_ENET_V2_RING_H__ */ From 81ccd0cab29b682a0f5337fd2076a77aa8e4472e Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Tue, 7 Mar 2017 17:08:41 -0800 Subject: [PATCH 099/399] drivers: net: xgene-v2: Add mac configuration This patch adds functions to configure and control mac. This patch also adds helper functions to get/set registers. Signed-off-by: Iyappan Subramanian Signed-off-by: Keyur Chudgar Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene-v2/mac.c | 116 ++++++++++++++++++++++++ drivers/net/ethernet/apm/xgene-v2/mac.h | 110 ++++++++++++++++++++++ 2 files changed, 226 insertions(+) create mode 100644 drivers/net/ethernet/apm/xgene-v2/mac.c create mode 100644 drivers/net/ethernet/apm/xgene-v2/mac.h diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c new file mode 100644 index 000000000000..9c3d32d3b7dd --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/mac.c @@ -0,0 +1,116 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include "main.h" + +void xge_mac_reset(struct xge_pdata *pdata) +{ + xge_wr_csr(pdata, MAC_CONFIG_1, SOFT_RESET); + xge_wr_csr(pdata, MAC_CONFIG_1, 0); +} + +static void xge_mac_set_speed(struct xge_pdata *pdata) +{ + u32 icm0, icm2, ecm0, mc2; + u32 intf_ctrl, rgmii; + + icm0 = xge_rd_csr(pdata, ICM_CONFIG0_REG_0); + icm2 = xge_rd_csr(pdata, ICM_CONFIG2_REG_0); + ecm0 = xge_rd_csr(pdata, ECM_CONFIG0_REG_0); + rgmii = xge_rd_csr(pdata, RGMII_REG_0); + mc2 = xge_rd_csr(pdata, MAC_CONFIG_2); + intf_ctrl = xge_rd_csr(pdata, INTERFACE_CONTROL); + icm2 |= CFG_WAITASYNCRD_EN; + + switch (pdata->phy_speed) { + case SPEED_10: + SET_REG_BITS(&mc2, INTF_MODE, 1); + SET_REG_BITS(&intf_ctrl, HD_MODE, 0); + SET_REG_BITS(&icm0, CFG_MACMODE, 0); + SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 500); + SET_REG_BIT(&rgmii, CFG_SPEED_125, 0); + break; + case SPEED_100: + SET_REG_BITS(&mc2, INTF_MODE, 1); + SET_REG_BITS(&intf_ctrl, HD_MODE, 1); + SET_REG_BITS(&icm0, CFG_MACMODE, 1); + SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 80); + SET_REG_BIT(&rgmii, CFG_SPEED_125, 0); + break; + default: + SET_REG_BITS(&mc2, INTF_MODE, 2); + SET_REG_BITS(&intf_ctrl, HD_MODE, 2); + SET_REG_BITS(&icm0, CFG_MACMODE, 2); + SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 16); + SET_REG_BIT(&rgmii, CFG_SPEED_125, 1); + break; + } + + mc2 |= FULL_DUPLEX | CRC_EN | PAD_CRC; + SET_REG_BITS(&ecm0, CFG_WFIFOFULLTHR, 0x32); + + xge_wr_csr(pdata, MAC_CONFIG_2, mc2); + xge_wr_csr(pdata, INTERFACE_CONTROL, intf_ctrl); + xge_wr_csr(pdata, RGMII_REG_0, rgmii); + xge_wr_csr(pdata, ICM_CONFIG0_REG_0, icm0); + xge_wr_csr(pdata, ICM_CONFIG2_REG_0, icm2); + xge_wr_csr(pdata, ECM_CONFIG0_REG_0, ecm0); +} + +void xge_mac_set_station_addr(struct xge_pdata *pdata) +{ + u32 addr0, addr1; + u8 *dev_addr = pdata->ndev->dev_addr; + + addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | + (dev_addr[1] << 8) | dev_addr[0]; + addr1 = (dev_addr[5] << 24) | (dev_addr[4] << 16); + + xge_wr_csr(pdata, STATION_ADDR0, addr0); + xge_wr_csr(pdata, STATION_ADDR1, addr1); +} + +void xge_mac_init(struct xge_pdata *pdata) +{ + xge_mac_reset(pdata); + xge_mac_set_speed(pdata); + xge_mac_set_station_addr(pdata); +} + +void xge_mac_enable(struct xge_pdata *pdata) +{ + u32 data; + + data = xge_rd_csr(pdata, MAC_CONFIG_1); + data |= TX_EN | RX_EN; + xge_wr_csr(pdata, MAC_CONFIG_1, data); + + data = xge_rd_csr(pdata, MAC_CONFIG_1); +} + +void xge_mac_disable(struct xge_pdata *pdata) +{ + u32 data; + + data = xge_rd_csr(pdata, MAC_CONFIG_1); + data &= ~(TX_EN | RX_EN); + xge_wr_csr(pdata, MAC_CONFIG_1, data); +} diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.h b/drivers/net/ethernet/apm/xgene-v2/mac.h new file mode 100644 index 000000000000..0fce6ae15ce0 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/mac.h @@ -0,0 +1,110 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __XGENE_ENET_V2_MAC_H__ +#define __XGENE_ENET_V2_MAC_H__ + +/* Register offsets */ +#define MAC_CONFIG_1 0xa000 +#define MAC_CONFIG_2 0xa004 +#define MII_MGMT_CONFIG 0xa020 +#define MII_MGMT_COMMAND 0xa024 +#define MII_MGMT_ADDRESS 0xa028 +#define MII_MGMT_CONTROL 0xa02c +#define MII_MGMT_STATUS 0xa030 +#define MII_MGMT_INDICATORS 0xa034 +#define INTERFACE_CONTROL 0xa038 +#define STATION_ADDR0 0xa040 +#define STATION_ADDR1 0xa044 +#define RBYT 0xa09c +#define RPKT 0xa0a0 +#define RFCS 0xa0a4 + +#define RGMII_REG_0 0x27e0 +#define ICM_CONFIG0_REG_0 0x2c00 +#define ICM_CONFIG2_REG_0 0x2c08 +#define ECM_CONFIG0_REG_0 0x2d00 + +/* Register fields */ +#define SOFT_RESET BIT(31) +#define TX_EN BIT(0) +#define RX_EN BIT(2) +#define PAD_CRC BIT(2) +#define CRC_EN BIT(1) +#define FULL_DUPLEX BIT(0) + +#define INTF_MODE_POS 8 +#define INTF_MODE_LEN 2 +#define HD_MODE_POS 25 +#define HD_MODE_LEN 2 +#define CFG_MACMODE_POS 18 +#define CFG_MACMODE_LEN 2 +#define CFG_WAITASYNCRD_POS 0 +#define CFG_WAITASYNCRD_LEN 16 +#define CFG_SPEED_125_POS 24 +#define CFG_WFIFOFULLTHR_POS 0 +#define CFG_WFIFOFULLTHR_LEN 7 +#define MGMT_CLOCK_SEL_POS 0 +#define MGMT_CLOCK_SEL_LEN 3 +#define PHY_ADDR_POS 8 +#define PHY_ADDR_LEN 5 +#define REG_ADDR_POS 0 +#define REG_ADDR_LEN 5 +#define MII_MGMT_BUSY BIT(0) +#define MII_READ_CYCLE BIT(0) +#define CFG_WAITASYNCRD_EN BIT(16) + +static inline void xgene_set_reg_bits(u32 *var, int pos, int len, u32 val) +{ + u32 mask = GENMASK(pos + len, pos); + + *var &= ~mask; + *var |= ((val << pos) & mask); +} + +static inline u32 xgene_get_reg_bits(u32 var, int pos, int len) +{ + u32 mask = GENMASK(pos + len, pos); + + return (var & mask) >> pos; +} + +#define SET_REG_BITS(var, field, val) \ + xgene_set_reg_bits(var, field ## _POS, field ## _LEN, val) + +#define SET_REG_BIT(var, field, val) \ + xgene_set_reg_bits(var, field ## _POS, 1, val) + +#define GET_REG_BITS(var, field) \ + xgene_get_reg_bits(var, field ## _POS, field ## _LEN) + +#define GET_REG_BIT(var, field) ((var) & (field)) + +struct xge_pdata; + +void xge_mac_reset(struct xge_pdata *pdata); +void xge_mac_enable(struct xge_pdata *pdata); +void xge_mac_disable(struct xge_pdata *pdata); +void xge_mac_init(struct xge_pdata *pdata); +int xge_port_init(struct net_device *ndev); +void xge_mac_set_station_addr(struct xge_pdata *pdata); + +#endif /* __XGENE_ENET_V2_MAC_H__ */ From 272d6dc1fcab6307c10bd411c614933bf10877e5 Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Tue, 7 Mar 2017 17:08:42 -0800 Subject: [PATCH 100/399] drivers: net: xgene-v2: Add ethernet hardware configuration This patch adds functions to configure ethernet hardware. Signed-off-by: Iyappan Subramanian Signed-off-by: Keyur Chudgar Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene-v2/enet.c | 71 ++++++++++++++++++++++++ drivers/net/ethernet/apm/xgene-v2/enet.h | 43 ++++++++++++++ 2 files changed, 114 insertions(+) create mode 100644 drivers/net/ethernet/apm/xgene-v2/enet.c create mode 100644 drivers/net/ethernet/apm/xgene-v2/enet.h diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.c b/drivers/net/ethernet/apm/xgene-v2/enet.c new file mode 100644 index 000000000000..b49edeeb6275 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/enet.c @@ -0,0 +1,71 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include "main.h" + +void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val) +{ + void __iomem *addr = pdata->resources.base_addr + offset; + + iowrite32(val, addr); +} + +u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset) +{ + void __iomem *addr = pdata->resources.base_addr + offset; + + return ioread32(addr); +} + +int xge_port_reset(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + xge_wr_csr(pdata, ENET_SRST, 0x3); + xge_wr_csr(pdata, ENET_SRST, 0x2); + xge_wr_csr(pdata, ENET_SRST, 0x0); + + xge_wr_csr(pdata, ENET_SHIM, DEVM_ARAUX_COH | DEVM_AWAUX_COH); + + return 0; +} + +static void xge_traffic_resume(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + xge_wr_csr(pdata, CFG_FORCE_LINK_STATUS_EN, 1); + xge_wr_csr(pdata, FORCE_LINK_STATUS, 1); + + xge_wr_csr(pdata, CFG_LINK_AGGR_RESUME, 1); + xge_wr_csr(pdata, RX_DV_GATE_REG, 1); +} + +int xge_port_init(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + pdata->phy_speed = SPEED_1000; + xge_mac_init(pdata); + xge_traffic_resume(ndev); + + return 0; +} diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.h b/drivers/net/ethernet/apm/xgene-v2/enet.h new file mode 100644 index 000000000000..40371cfcfce4 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/enet.h @@ -0,0 +1,43 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __XGENE_ENET_V2_ENET_H__ +#define __XGENE_ENET_V2_ENET_H__ + +#define ENET_CLKEN 0xc008 +#define ENET_SRST 0xc000 +#define ENET_SHIM 0xc010 +#define CFG_MEM_RAM_SHUTDOWN 0xd070 +#define BLOCK_MEM_RDY 0xd074 + +#define DEVM_ARAUX_COH BIT(19) +#define DEVM_AWAUX_COH BIT(3) + +#define CFG_FORCE_LINK_STATUS_EN 0x229c +#define FORCE_LINK_STATUS 0x22a0 +#define CFG_LINK_AGGR_RESUME 0x27c8 +#define RX_DV_GATE_REG 0x2dfc + +void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val); +u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset); +int xge_port_reset(struct net_device *ndev); + +#endif /* __XGENE_ENET_V2_ENET__H__ */ From 3b3f9a75d93186613bb5ee19484454928af469c3 Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Tue, 7 Mar 2017 17:08:43 -0800 Subject: [PATCH 101/399] drivers: net: xgene-v2: Add base driver This patch adds, - probe, remove, shutdown - open, close and stats - create and delete ring - request and delete irq Signed-off-by: Iyappan Subramanian Signed-off-by: Keyur Chudgar Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene-v2/main.c | 510 +++++++++++++++++++++++ 1 file changed, 510 insertions(+) create mode 100644 drivers/net/ethernet/apm/xgene-v2/main.c diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c new file mode 100644 index 000000000000..c96b4ccdcfbf --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -0,0 +1,510 @@ +/* + * Applied Micro X-Gene SoC Ethernet v2 Driver + * + * Copyright (c) 2017, Applied Micro Circuits Corporation + * Author(s): Iyappan Subramanian + * Keyur Chudgar + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include "main.h" + +static const struct acpi_device_id xge_acpi_match[]; + +static int xge_get_resources(struct xge_pdata *pdata) +{ + struct platform_device *pdev; + struct net_device *ndev; + struct device *dev; + struct resource *res; + int phy_mode, ret = 0; + + pdev = pdata->pdev; + dev = &pdev->dev; + ndev = pdata->ndev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "Resource enet_csr not defined\n"); + return -ENODEV; + } + + pdata->resources.base_addr = devm_ioremap(dev, res->start, + resource_size(res)); + if (!pdata->resources.base_addr) { + dev_err(dev, "Unable to retrieve ENET Port CSR region\n"); + return -ENOMEM; + } + + if (!device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) + eth_hw_addr_random(ndev); + + memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len); + + phy_mode = device_get_phy_mode(dev); + if (phy_mode < 0) { + dev_err(dev, "Unable to get phy-connection-type\n"); + return phy_mode; + } + pdata->resources.phy_mode = phy_mode; + + if (pdata->resources.phy_mode != PHY_INTERFACE_MODE_RGMII) { + dev_err(dev, "Incorrect phy-connection-type specified\n"); + return -ENODEV; + } + + ret = platform_get_irq(pdev, 0); + if (ret <= 0) { + dev_err(dev, "Unable to get ENET IRQ\n"); + ret = ret ? : -ENXIO; + return ret; + } + pdata->resources.irq = ret; + + return 0; +} + +static int xge_refill_buffers(struct net_device *ndev, u32 nbuf) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_desc_ring *ring = pdata->rx_ring; + const u8 slots = XGENE_ENET_NUM_DESC - 1; + struct device *dev = &pdata->pdev->dev; + struct xge_raw_desc *raw_desc; + u64 addr_lo, addr_hi; + u8 tail = ring->tail; + struct sk_buff *skb; + dma_addr_t dma_addr; + u16 len; + int i; + + for (i = 0; i < nbuf; i++) { + raw_desc = &ring->raw_desc[tail]; + + len = XGENE_ENET_STD_MTU; + skb = netdev_alloc_skb(ndev, len); + if (unlikely(!skb)) + return -ENOMEM; + + dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + netdev_err(ndev, "DMA mapping error\n"); + dev_kfree_skb_any(skb); + return -EINVAL; + } + + ring->pkt_info[tail].skb = skb; + ring->pkt_info[tail].dma_addr = dma_addr; + + addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1)); + addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1)); + raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) | + SET_BITS(NEXT_DESC_ADDRH, addr_hi) | + SET_BITS(PKT_ADDRH, + dma_addr >> PKT_ADDRL_LEN)); + + dma_wmb(); + raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) | + SET_BITS(E, 1)); + tail = (tail + 1) & slots; + } + + ring->tail = tail; + + return 0; +} + +static int xge_init_hw(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + int ret; + + ret = xge_port_reset(ndev); + if (ret) + return ret; + + xge_port_init(ndev); + pdata->nbufs = NUM_BUFS; + + return 0; +} + +static irqreturn_t xge_irq(const int irq, void *data) +{ + struct xge_pdata *pdata = data; + + if (napi_schedule_prep(&pdata->napi)) { + xge_intr_disable(pdata); + __napi_schedule(&pdata->napi); + } + + return IRQ_HANDLED; +} + +static int xge_request_irq(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + int ret; + + snprintf(pdata->irq_name, IRQ_ID_SIZE, "%s", ndev->name); + + ret = devm_request_irq(dev, pdata->resources.irq, xge_irq, + 0, pdata->irq_name, pdata); + if (ret) + netdev_err(ndev, "Failed to request irq %s\n", pdata->irq_name); + + return ret; +} + +static void xge_free_irq(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + + devm_free_irq(dev, pdata->resources.irq, pdata); +} + +static void xge_delete_desc_ring(struct net_device *ndev, + struct xge_desc_ring *ring) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + u16 size; + + if (!ring) + return; + + size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC; + if (ring->desc_addr) + dma_free_coherent(dev, size, ring->desc_addr, ring->dma_addr); + + kfree(ring->pkt_info); + kfree(ring); +} + +static void xge_free_buffers(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_desc_ring *ring = pdata->rx_ring; + struct device *dev = &pdata->pdev->dev; + struct sk_buff *skb; + dma_addr_t dma_addr; + int i; + + for (i = 0; i < XGENE_ENET_NUM_DESC; i++) { + skb = ring->pkt_info[i].skb; + dma_addr = ring->pkt_info[i].dma_addr; + + if (!skb) + continue; + + dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU, + DMA_FROM_DEVICE); + dev_kfree_skb_any(skb); + } +} + +static void xge_delete_desc_rings(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + xge_delete_desc_ring(ndev, pdata->tx_ring); + + xge_free_buffers(ndev); + xge_delete_desc_ring(ndev, pdata->rx_ring); +} + +static struct xge_desc_ring *xge_create_desc_ring(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *ring; + u16 size; + + ring = kzalloc(sizeof(struct xge_desc_ring), GFP_KERNEL); + if (!ring) + return NULL; + + ring->ndev = ndev; + + size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC; + ring->desc_addr = dma_zalloc_coherent(dev, size, &ring->dma_addr, + GFP_KERNEL); + if (!ring->desc_addr) + goto err; + + ring->pkt_info = kcalloc(XGENE_ENET_NUM_DESC, sizeof(struct pkt_info), + GFP_KERNEL); + if (!ring->pkt_info) + goto err; + + xge_setup_desc(ring); + + return ring; + +err: + xge_delete_desc_ring(ndev, ring); + + return NULL; +} + +static int xge_create_desc_rings(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_desc_ring *ring; + int ret; + + /* create tx ring */ + ring = xge_create_desc_ring(ndev); + if (!ring) + goto err; + + pdata->tx_ring = ring; + xge_update_tx_desc_addr(pdata); + + /* create rx ring */ + ring = xge_create_desc_ring(ndev); + if (!ring) + goto err; + + pdata->rx_ring = ring; + xge_update_rx_desc_addr(pdata); + + ret = xge_refill_buffers(ndev, XGENE_ENET_NUM_DESC); + if (ret) + goto err; + + return 0; +err: + xge_delete_desc_rings(ndev); + + return -ENOMEM; +} + +static int xge_open(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + int ret; + + ret = xge_create_desc_rings(ndev); + if (ret) + return ret; + + napi_enable(&pdata->napi); + ret = xge_request_irq(ndev); + if (ret) + return ret; + + xge_intr_enable(pdata); + xge_wr_csr(pdata, DMARXCTRL, 1); + xge_mac_enable(pdata); + netif_start_queue(ndev); + netif_carrier_on(ndev); + + return 0; +} + +static int xge_close(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + netif_carrier_off(ndev); + netif_stop_queue(ndev); + xge_mac_disable(pdata); + + xge_intr_disable(pdata); + xge_free_irq(ndev); + napi_disable(&pdata->napi); + xge_delete_desc_rings(ndev); + + return 0; +} + +static int xge_set_mac_addr(struct net_device *ndev, void *addr) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + int ret; + + ret = eth_mac_addr(ndev, addr); + if (ret) + return ret; + + xge_mac_set_station_addr(pdata); + + return 0; +} + +static void xge_timeout(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + + rtnl_lock(); + + if (netif_running(ndev)) { + netif_carrier_off(ndev); + netif_stop_queue(ndev); + xge_intr_disable(pdata); + napi_disable(&pdata->napi); + + xge_wr_csr(pdata, DMATXCTRL, 0); + xge_txc_poll(ndev); + xge_free_pending_skb(ndev); + xge_wr_csr(pdata, DMATXSTATUS, ~0U); + + xge_setup_desc(pdata->tx_ring); + xge_update_tx_desc_addr(pdata); + xge_mac_init(pdata); + + napi_enable(&pdata->napi); + xge_intr_enable(pdata); + xge_mac_enable(pdata); + netif_start_queue(ndev); + netif_carrier_on(ndev); + } + + rtnl_unlock(); +} + +static void xge_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *storage) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_stats *stats = &pdata->stats; + + storage->tx_packets += stats->tx_packets; + storage->tx_bytes += stats->tx_bytes; + + storage->rx_packets += stats->rx_packets; + storage->rx_bytes += stats->rx_bytes; +} + +static const struct net_device_ops xgene_ndev_ops = { + .ndo_open = xge_open, + .ndo_stop = xge_close, + .ndo_set_mac_address = xge_set_mac_addr, + .ndo_tx_timeout = xge_timeout, + .ndo_get_stats64 = xge_get_stats64, +}; + +static int xge_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct net_device *ndev; + struct xge_pdata *pdata; + int ret; + + ndev = alloc_etherdev(sizeof(struct xge_pdata)); + if (!ndev) + return -ENOMEM; + + pdata = netdev_priv(ndev); + + pdata->pdev = pdev; + pdata->ndev = ndev; + SET_NETDEV_DEV(ndev, dev); + platform_set_drvdata(pdev, pdata); + ndev->netdev_ops = &xgene_ndev_ops; + + ndev->features |= NETIF_F_GSO | + NETIF_F_GRO; + + ret = xge_get_resources(pdata); + if (ret) + goto err; + + ndev->hw_features = ndev->features; + + ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (ret) { + netdev_err(ndev, "No usable DMA configuration\n"); + goto err; + } + + ret = xge_init_hw(ndev); + if (ret) + goto err; + + netif_napi_add(ndev, &pdata->napi, xge_napi, NAPI_POLL_WEIGHT); + + netif_carrier_off(ndev); + ret = register_netdev(ndev); + if (ret) { + netdev_err(ndev, "Failed to register netdev\n"); + goto err; + } + + return 0; + +err: + free_netdev(ndev); + + return ret; +} + +static int xge_remove(struct platform_device *pdev) +{ + struct xge_pdata *pdata; + struct net_device *ndev; + + pdata = platform_get_drvdata(pdev); + ndev = pdata->ndev; + + rtnl_lock(); + if (netif_running(ndev)) + dev_close(ndev); + rtnl_unlock(); + + unregister_netdev(ndev); + free_netdev(ndev); + + return 0; +} + +static void xge_shutdown(struct platform_device *pdev) +{ + struct xge_pdata *pdata; + + pdata = platform_get_drvdata(pdev); + if (!pdata) + return; + + if (!pdata->ndev) + return; + + xge_remove(pdev); +} + +static const struct acpi_device_id xge_acpi_match[] = { + { "APMC0D80" }, + { } +}; +MODULE_DEVICE_TABLE(acpi, xge_acpi_match); + +static struct platform_driver xge_driver = { + .driver = { + .name = "xgene-enet-v2", + .acpi_match_table = ACPI_PTR(xge_acpi_match), + }, + .probe = xge_probe, + .remove = xge_remove, + .shutdown = xge_shutdown, +}; +module_platform_driver(xge_driver); + +MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver"); +MODULE_AUTHOR("Iyappan Subramanian "); +MODULE_VERSION(XGENE_ENET_V2_VERSION); +MODULE_LICENSE("GPL"); From b105bcdaaa0efac4512d108495f1cc19abe7b7a4 Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Tue, 7 Mar 2017 17:08:44 -0800 Subject: [PATCH 102/399] drivers: net: xgene-v2: Add transmit and receive This patch adds, - Transmit - Transmit completion poll - Receive poll - NAPI handler and enables the driver. Signed-off-by: Iyappan Subramanian Signed-off-by: Keyur Chudgar Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/Kconfig | 1 + drivers/net/ethernet/apm/Makefile | 1 + drivers/net/ethernet/apm/xgene-v2/Kconfig | 11 + drivers/net/ethernet/apm/xgene-v2/Makefile | 6 + drivers/net/ethernet/apm/xgene-v2/main.c | 248 ++++++++++++++++++++- drivers/net/ethernet/apm/xgene-v2/main.h | 1 + 6 files changed, 267 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/apm/xgene-v2/Kconfig create mode 100644 drivers/net/ethernet/apm/xgene-v2/Makefile diff --git a/drivers/net/ethernet/apm/Kconfig b/drivers/net/ethernet/apm/Kconfig index ec63d706d464..59efe5b145dd 100644 --- a/drivers/net/ethernet/apm/Kconfig +++ b/drivers/net/ethernet/apm/Kconfig @@ -1 +1,2 @@ source "drivers/net/ethernet/apm/xgene/Kconfig" +source "drivers/net/ethernet/apm/xgene-v2/Kconfig" diff --git a/drivers/net/ethernet/apm/Makefile b/drivers/net/ethernet/apm/Makefile index 65ce32ad1b2c..946b2a4c882d 100644 --- a/drivers/net/ethernet/apm/Makefile +++ b/drivers/net/ethernet/apm/Makefile @@ -3,3 +3,4 @@ # obj-$(CONFIG_NET_XGENE) += xgene/ +obj-$(CONFIG_NET_XGENE_V2) += xgene-v2/ diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig new file mode 100644 index 000000000000..1205861b6318 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig @@ -0,0 +1,11 @@ +config NET_XGENE_V2 + tristate "APM X-Gene SoC Ethernet-v2 Driver" + depends on HAS_DMA + depends on ARCH_XGENE || COMPILE_TEST + help + This is the Ethernet driver for the on-chip ethernet interface + which uses a linked list of DMA descriptor architecture (v2) for + APM X-Gene SoCs. + + To compile this driver as a module, choose M here. This module will + be called xgene-enet-v2. diff --git a/drivers/net/ethernet/apm/xgene-v2/Makefile b/drivers/net/ethernet/apm/xgene-v2/Makefile new file mode 100644 index 000000000000..735309c0b8b1 --- /dev/null +++ b/drivers/net/ethernet/apm/xgene-v2/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for APM X-Gene Ethernet v2 driver +# + +xgene-enet-v2-objs := main.o mac.o enet.o ring.o +obj-$(CONFIG_NET_XGENE_V2) += xgene-enet-v2.o diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index c96b4ccdcfbf..b16ef43bc83c 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -113,7 +113,7 @@ static int xge_refill_buffers(struct net_device *ndev, u32 nbuf) raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) | SET_BITS(NEXT_DESC_ADDRH, addr_hi) | SET_BITS(PKT_ADDRH, - dma_addr >> PKT_ADDRL_LEN)); + upper_32_bits(dma_addr))); dma_wmb(); raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) | @@ -177,6 +177,194 @@ static void xge_free_irq(struct net_device *ndev) devm_free_irq(dev, pdata->resources.irq, pdata); } +static bool is_tx_slot_available(struct xge_raw_desc *raw_desc) +{ + if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) && + (GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)) == SLOT_EMPTY)) + return true; + + return false; +} + +static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + static dma_addr_t dma_addr; + struct xge_desc_ring *tx_ring; + struct xge_raw_desc *raw_desc; + u64 addr_lo, addr_hi; + void *pkt_buf; + u8 tail; + u16 len; + + tx_ring = pdata->tx_ring; + tail = tx_ring->tail; + len = skb_headlen(skb); + raw_desc = &tx_ring->raw_desc[tail]; + + if (!is_tx_slot_available(raw_desc)) { + netif_stop_queue(ndev); + return NETDEV_TX_BUSY; + } + + /* Packet buffers should be 64B aligned */ + pkt_buf = dma_zalloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr, + GFP_ATOMIC); + if (unlikely(!pkt_buf)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + memcpy(pkt_buf, skb->data, len); + + addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1)); + addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1)); + raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) | + SET_BITS(NEXT_DESC_ADDRH, addr_hi) | + SET_BITS(PKT_ADDRH, + upper_32_bits(dma_addr))); + + tx_ring->pkt_info[tail].skb = skb; + tx_ring->pkt_info[tail].dma_addr = dma_addr; + tx_ring->pkt_info[tail].pkt_buf = pkt_buf; + + dma_wmb(); + + raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) | + SET_BITS(PKT_SIZE, len) | + SET_BITS(E, 0)); + skb_tx_timestamp(skb); + xge_wr_csr(pdata, DMATXCTRL, 1); + + tx_ring->tail = (tail + 1) & (XGENE_ENET_NUM_DESC - 1); + + return NETDEV_TX_OK; +} + +static bool is_tx_hw_done(struct xge_raw_desc *raw_desc) +{ + if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) && + !GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0))) + return true; + + return false; +} + +static void xge_txc_poll(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *tx_ring; + struct xge_raw_desc *raw_desc; + dma_addr_t dma_addr; + struct sk_buff *skb; + void *pkt_buf; + u32 data; + u8 head; + + tx_ring = pdata->tx_ring; + head = tx_ring->head; + + data = xge_rd_csr(pdata, DMATXSTATUS); + if (!GET_BITS(TXPKTCOUNT, data)) + return; + + while (1) { + raw_desc = &tx_ring->raw_desc[head]; + + if (!is_tx_hw_done(raw_desc)) + break; + + dma_rmb(); + + skb = tx_ring->pkt_info[head].skb; + dma_addr = tx_ring->pkt_info[head].dma_addr; + pkt_buf = tx_ring->pkt_info[head].pkt_buf; + pdata->stats.tx_packets++; + pdata->stats.tx_bytes += skb->len; + dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr); + dev_kfree_skb_any(skb); + + /* clear pktstart address and pktsize */ + raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) | + SET_BITS(PKT_SIZE, SLOT_EMPTY)); + xge_wr_csr(pdata, DMATXSTATUS, 1); + + head = (head + 1) & (XGENE_ENET_NUM_DESC - 1); + } + + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); + + tx_ring->head = head; +} + +static int xge_rx_poll(struct net_device *ndev, unsigned int budget) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *rx_ring; + struct xge_raw_desc *raw_desc; + struct sk_buff *skb; + dma_addr_t dma_addr; + int processed = 0; + u8 head, rx_error; + int i, ret; + u32 data; + u16 len; + + rx_ring = pdata->rx_ring; + head = rx_ring->head; + + data = xge_rd_csr(pdata, DMARXSTATUS); + if (!GET_BITS(RXPKTCOUNT, data)) + return 0; + + for (i = 0; i < budget; i++) { + raw_desc = &rx_ring->raw_desc[head]; + + if (GET_BITS(E, le64_to_cpu(raw_desc->m0))) + break; + + dma_rmb(); + + skb = rx_ring->pkt_info[head].skb; + rx_ring->pkt_info[head].skb = NULL; + dma_addr = rx_ring->pkt_info[head].dma_addr; + len = GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)); + dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU, + DMA_FROM_DEVICE); + + rx_error = GET_BITS(D, le64_to_cpu(raw_desc->m2)); + if (unlikely(rx_error)) { + pdata->stats.rx_errors++; + dev_kfree_skb_any(skb); + goto out; + } + + skb_put(skb, len); + skb->protocol = eth_type_trans(skb, ndev); + + pdata->stats.rx_packets++; + pdata->stats.rx_bytes += len; + napi_gro_receive(&pdata->napi, skb); +out: + ret = xge_refill_buffers(ndev, 1); + xge_wr_csr(pdata, DMARXSTATUS, 1); + xge_wr_csr(pdata, DMARXCTRL, 1); + + if (ret) + break; + + head = (head + 1) & (XGENE_ENET_NUM_DESC - 1); + processed++; + } + + rx_ring->head = head; + + return processed; +} + static void xge_delete_desc_ring(struct net_device *ndev, struct xge_desc_ring *ring) { @@ -221,8 +409,10 @@ static void xge_delete_desc_rings(struct net_device *ndev) { struct xge_pdata *pdata = netdev_priv(ndev); + xge_txc_poll(ndev); xge_delete_desc_ring(ndev, pdata->tx_ring); + xge_rx_poll(ndev, 64); xge_free_buffers(ndev); xge_delete_desc_ring(ndev, pdata->rx_ring); } @@ -333,6 +523,25 @@ static int xge_close(struct net_device *ndev) return 0; } +static int xge_napi(struct napi_struct *napi, const int budget) +{ + struct net_device *ndev = napi->dev; + struct xge_pdata *pdata = netdev_priv(ndev); + int processed; + + pdata = netdev_priv(ndev); + + xge_txc_poll(ndev); + processed = xge_rx_poll(ndev, budget); + + if (processed < budget) { + napi_complete_done(napi, processed); + xge_intr_enable(pdata); + } + + return processed; +} + static int xge_set_mac_addr(struct net_device *ndev, void *addr) { struct xge_pdata *pdata = netdev_priv(ndev); @@ -347,6 +556,41 @@ static int xge_set_mac_addr(struct net_device *ndev, void *addr) return 0; } +static bool is_tx_pending(struct xge_raw_desc *raw_desc) +{ + if (!GET_BITS(E, le64_to_cpu(raw_desc->m0))) + return true; + + return false; +} + +static void xge_free_pending_skb(struct net_device *ndev) +{ + struct xge_pdata *pdata = netdev_priv(ndev); + struct device *dev = &pdata->pdev->dev; + struct xge_desc_ring *tx_ring; + struct xge_raw_desc *raw_desc; + dma_addr_t dma_addr; + struct sk_buff *skb; + void *pkt_buf; + int i; + + tx_ring = pdata->tx_ring; + + for (i = 0; i < XGENE_ENET_NUM_DESC; i++) { + raw_desc = &tx_ring->raw_desc[i]; + + if (!is_tx_pending(raw_desc)) + continue; + + skb = tx_ring->pkt_info[i].skb; + dma_addr = tx_ring->pkt_info[i].dma_addr; + pkt_buf = tx_ring->pkt_info[i].pkt_buf; + dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr); + dev_kfree_skb_any(skb); + } +} + static void xge_timeout(struct net_device *ndev) { struct xge_pdata *pdata = netdev_priv(ndev); @@ -389,11 +633,13 @@ static void xge_get_stats64(struct net_device *ndev, storage->rx_packets += stats->rx_packets; storage->rx_bytes += stats->rx_bytes; + storage->rx_errors += stats->rx_errors; } static const struct net_device_ops xgene_ndev_ops = { .ndo_open = xge_open, .ndo_stop = xge_close, + .ndo_start_xmit = xge_start_xmit, .ndo_set_mac_address = xge_set_mac_addr, .ndo_tx_timeout = xge_timeout, .ndo_get_stats64 = xge_get_stats64, diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h index a2f87126dce0..ada7b0e82586 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.h +++ b/drivers/net/ethernet/apm/xgene-v2/main.h @@ -55,6 +55,7 @@ struct xge_stats { u64 tx_bytes; u64 rx_packets; u64 rx_bytes; + u64 rx_errors; }; /* ethernet private data */ From 70dbd9b258d5a6a21d9a41ae798f5476dcdb086c Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Tue, 7 Mar 2017 17:08:45 -0800 Subject: [PATCH 103/399] MAINTAINERS: Add entry for APM X-Gene SoC Ethernet (v2) driver This patch adds a MAINTAINERS entry for the ethernet driver for the on-chip ethernet interface which uses a linked list of DMA descriptor architecture (v2) for APM X-Gene SoCs. Signed-off-by: Iyappan Subramanian Signed-off-by: Keyur Chudgar Signed-off-by: David S. Miller --- MAINTAINERS | 6 ++++++ drivers/net/ethernet/apm/xgene-v2/mac.c | 2 +- drivers/net/ethernet/apm/xgene-v2/main.c | 8 ++++---- 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index c265a5fe4848..e04d3a6725fc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -902,6 +902,12 @@ F: drivers/net/phy/mdio-xgene.c F: Documentation/devicetree/bindings/net/apm-xgene-enet.txt F: Documentation/devicetree/bindings/net/apm-xgene-mdio.txt +APPLIED MICRO (APM) X-GENE SOC ETHERNET (V2) DRIVER +M: Iyappan Subramanian +M: Keyur Chudgar +S: Supported +F: drivers/net/ethernet/apm/xgene-v2/ + APPLIED MICRO (APM) X-GENE SOC PMU M: Tai Nguyen S: Supported diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c index 9c3d32d3b7dd..c3189de3df55 100644 --- a/drivers/net/ethernet/apm/xgene-v2/mac.c +++ b/drivers/net/ethernet/apm/xgene-v2/mac.c @@ -77,8 +77,8 @@ static void xge_mac_set_speed(struct xge_pdata *pdata) void xge_mac_set_station_addr(struct xge_pdata *pdata) { - u32 addr0, addr1; u8 *dev_addr = pdata->ndev->dev_addr; + u32 addr0, addr1; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index b16ef43bc83c..ae76977d10b4 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -27,9 +27,9 @@ static int xge_get_resources(struct xge_pdata *pdata) { struct platform_device *pdev; struct net_device *ndev; - struct device *dev; - struct resource *res; int phy_mode, ret = 0; + struct resource *res; + struct device *dev; pdev = pdata->pdev; dev = &pdev->dev; @@ -190,9 +190,9 @@ static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct xge_pdata *pdata = netdev_priv(ndev); struct device *dev = &pdata->pdev->dev; - static dma_addr_t dma_addr; struct xge_desc_ring *tx_ring; struct xge_raw_desc *raw_desc; + static dma_addr_t dma_addr; u64 addr_lo, addr_hi; void *pkt_buf; u8 tail; @@ -526,7 +526,7 @@ static int xge_close(struct net_device *ndev) static int xge_napi(struct napi_struct *napi, const int budget) { struct net_device *ndev = napi->dev; - struct xge_pdata *pdata = netdev_priv(ndev); + struct xge_pdata *pdata; int processed; pdata = netdev_priv(ndev); From 65e0ace2c5cdd7aa898fea17d6e7bdc909394bf9 Mon Sep 17 00:00:00 2001 From: Jie Deng Date: Wed, 8 Mar 2017 14:06:18 +0800 Subject: [PATCH 104/399] net: dwc-xlgmac: Initial driver for DesignWare Enterprise Ethernet Synopsys provides a new DesignWare Core Enterprise Ethernet MAC IP (DWC-XLGMAC) for Ethernet designs. It is compliant with the IEEE 802.3-2012 specifications, including IEEE 802.3ba and consortium specifications. This patch provides the initial 25G/40G/50G/100G Ethernet driver for Synopsys XLGMAC IP Prototyping Kit. Signed-off-by: Jie Deng Signed-off-by: David S. Miller --- MAINTAINERS | 6 + drivers/net/ethernet/Kconfig | 1 + drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/synopsys/Kconfig | 41 + drivers/net/ethernet/synopsys/Makefile | 9 + .../net/ethernet/synopsys/dwc-xlgmac-common.c | 736 ++++ .../net/ethernet/synopsys/dwc-xlgmac-desc.c | 648 ++++ drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c | 3146 +++++++++++++++++ .../net/ethernet/synopsys/dwc-xlgmac-net.c | 1334 +++++++ .../net/ethernet/synopsys/dwc-xlgmac-pci.c | 80 + .../net/ethernet/synopsys/dwc-xlgmac-reg.h | 746 ++++ drivers/net/ethernet/synopsys/dwc-xlgmac.h | 651 ++++ 12 files changed, 7399 insertions(+) create mode 100644 drivers/net/ethernet/synopsys/Kconfig create mode 100644 drivers/net/ethernet/synopsys/Makefile create mode 100644 drivers/net/ethernet/synopsys/dwc-xlgmac-common.c create mode 100644 drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c create mode 100644 drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c create mode 100644 drivers/net/ethernet/synopsys/dwc-xlgmac-net.c create mode 100644 drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c create mode 100644 drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h create mode 100644 drivers/net/ethernet/synopsys/dwc-xlgmac.h diff --git a/MAINTAINERS b/MAINTAINERS index e04d3a6725fc..a375d855f539 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11068,6 +11068,12 @@ F: include/linux/dma/dw.h F: include/linux/platform_data/dma-dw.h F: drivers/dma/dw/ +SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER +M: Jie Deng +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/synopsys/ + SYNOPSYS DESIGNWARE I2C DRIVER M: Jarkko Nikula R: Andy Shevchenko diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 8c08f9deef92..edae15ac0e98 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -180,5 +180,6 @@ source "drivers/net/ethernet/via/Kconfig" source "drivers/net/ethernet/wiznet/Kconfig" source "drivers/net/ethernet/xilinx/Kconfig" source "drivers/net/ethernet/xircom/Kconfig" +source "drivers/net/ethernet/synopsys/Kconfig" endif # ETHERNET diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 26dce5bf2c18..bf7f4502cabc 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -91,3 +91,4 @@ obj-$(CONFIG_NET_VENDOR_VIA) += via/ obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/ obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/ obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/ +obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/ diff --git a/drivers/net/ethernet/synopsys/Kconfig b/drivers/net/ethernet/synopsys/Kconfig new file mode 100644 index 000000000000..a9503884e1c2 --- /dev/null +++ b/drivers/net/ethernet/synopsys/Kconfig @@ -0,0 +1,41 @@ +# +# Synopsys network device configuration +# + +config NET_VENDOR_SYNOPSYS + bool "Synopsys devices" + default y + ---help--- + If you have a network (Ethernet) device belonging to this class, say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Synopsys devices. If you say Y, you will be asked + for your specific device in the following questions. + +if NET_VENDOR_SYNOPSYS + +config DWC_XLGMAC + tristate "Synopsys DWC Enterprise Ethernet (XLGMAC) driver support" + depends on HAS_IOMEM && HAS_DMA + select BITREVERSE + select CRC32 + ---help--- + This driver supports the Synopsys DesignWare Cores Enterprise + Ethernet (dwc-xlgmac). + +if DWC_XLGMAC + +config DWC_XLGMAC_PCI + tristate "XLGMAC PCI bus support" + depends on DWC_XLGMAC && PCI + ---help--- + This selects the pci bus support for the dwc-xlgmac driver. + This driver was tested on Synopsys XLGMAC IP Prototyping Kit. + + If you have a controller with this interface, say Y or M here. + If unsure, say N. + +endif # DWC_XLGMAC + +endif # NET_VENDOR_SYNOPSYS diff --git a/drivers/net/ethernet/synopsys/Makefile b/drivers/net/ethernet/synopsys/Makefile new file mode 100644 index 000000000000..c06e2eb3be90 --- /dev/null +++ b/drivers/net/ethernet/synopsys/Makefile @@ -0,0 +1,9 @@ +# +# Makefile for the Synopsys network device drivers. +# + +obj-$(CONFIG_DWC_XLGMAC) += dwc-xlgmac.o +dwc-xlgmac-objs := dwc-xlgmac-net.o dwc-xlgmac-desc.o \ + dwc-xlgmac-hw.o dwc-xlgmac-common.o + +dwc-xlgmac-$(CONFIG_DWC_XLGMAC_PCI) += dwc-xlgmac-pci.o diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c new file mode 100644 index 000000000000..726d78ac4907 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c @@ -0,0 +1,736 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include +#include + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int debug = -1; +module_param(debug, int, 0644); +MODULE_PARM_DESC(debug, "DWC ethernet debug level (0=none,...,16=all)"); +static const u32 default_msg_level = (NETIF_MSG_LINK | NETIF_MSG_IFDOWN | + NETIF_MSG_IFUP); + +static unsigned char dev_addr[6] = {0, 0x55, 0x7b, 0xb5, 0x7d, 0xf7}; + +static void xlgmac_read_mac_addr(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + + /* Currently it uses a static mac address for test */ + memcpy(pdata->mac_addr, dev_addr, netdev->addr_len); +} + +static void xlgmac_default_config(struct xlgmac_pdata *pdata) +{ + pdata->tx_osp_mode = DMA_OSP_ENABLE; + pdata->tx_sf_mode = MTL_TSF_ENABLE; + pdata->rx_sf_mode = MTL_RSF_DISABLE; + pdata->pblx8 = DMA_PBL_X8_ENABLE; + pdata->tx_pbl = DMA_PBL_32; + pdata->rx_pbl = DMA_PBL_32; + pdata->tx_threshold = MTL_TX_THRESHOLD_128; + pdata->rx_threshold = MTL_RX_THRESHOLD_128; + pdata->tx_pause = 1; + pdata->rx_pause = 1; + pdata->phy_speed = SPEED_25000; + pdata->sysclk_rate = XLGMAC_SYSCLOCK; + + strlcpy(pdata->drv_name, XLGMAC_DRV_NAME, sizeof(pdata->drv_name)); + strlcpy(pdata->drv_ver, XLGMAC_DRV_VERSION, sizeof(pdata->drv_ver)); +} + +static void xlgmac_init_all_ops(struct xlgmac_pdata *pdata) +{ + xlgmac_init_desc_ops(&pdata->desc_ops); + xlgmac_init_hw_ops(&pdata->hw_ops); +} + +static int xlgmac_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct net_device *netdev = pdata->netdev; + unsigned int i; + int ret; + + /* Set default configuration data */ + xlgmac_default_config(pdata); + + /* Set irq, base_addr, MAC address, */ + netdev->irq = pdata->dev_irq; + netdev->base_addr = (unsigned long)pdata->mac_regs; + xlgmac_read_mac_addr(pdata); + memcpy(netdev->dev_addr, pdata->mac_addr, netdev->addr_len); + + /* Set all the function pointers */ + xlgmac_init_all_ops(pdata); + + /* Issue software reset to device */ + hw_ops->exit(pdata); + + /* Populate the hardware features */ + xlgmac_get_all_hw_features(pdata); + xlgmac_print_all_hw_features(pdata); + + /* TODO: Set the PHY mode to XLGMII */ + + /* Set the DMA mask */ + ret = dma_set_mask_and_coherent(pdata->dev, + DMA_BIT_MASK(pdata->hw_feat.dma_width)); + if (ret) { + dev_err(pdata->dev, "dma_set_mask_and_coherent failed\n"); + return ret; + } + + /* Channel and ring params initializtion + * pdata->channel_count; + * pdata->tx_ring_count; + * pdata->rx_ring_count; + * pdata->tx_desc_count; + * pdata->rx_desc_count; + */ + BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_TX_DESC_CNT); + pdata->tx_desc_count = XLGMAC_TX_DESC_CNT; + if (pdata->tx_desc_count & (pdata->tx_desc_count - 1)) { + dev_err(pdata->dev, "tx descriptor count (%d) is not valid\n", + pdata->tx_desc_count); + ret = -EINVAL; + return ret; + } + BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_RX_DESC_CNT); + pdata->rx_desc_count = XLGMAC_RX_DESC_CNT; + if (pdata->rx_desc_count & (pdata->rx_desc_count - 1)) { + dev_err(pdata->dev, "rx descriptor count (%d) is not valid\n", + pdata->rx_desc_count); + ret = -EINVAL; + return ret; + } + + pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(), + pdata->hw_feat.tx_ch_cnt); + pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count, + pdata->hw_feat.tx_q_cnt); + pdata->tx_q_count = pdata->tx_ring_count; + ret = netif_set_real_num_tx_queues(netdev, pdata->tx_q_count); + if (ret) { + dev_err(pdata->dev, "error setting real tx queue count\n"); + return ret; + } + + pdata->rx_ring_count = min_t(unsigned int, + netif_get_num_default_rss_queues(), + pdata->hw_feat.rx_ch_cnt); + pdata->rx_ring_count = min_t(unsigned int, pdata->rx_ring_count, + pdata->hw_feat.rx_q_cnt); + pdata->rx_q_count = pdata->rx_ring_count; + ret = netif_set_real_num_rx_queues(netdev, pdata->rx_q_count); + if (ret) { + dev_err(pdata->dev, "error setting real rx queue count\n"); + return ret; + } + + pdata->channel_count = + max_t(unsigned int, pdata->tx_ring_count, pdata->rx_ring_count); + + /* Initialize RSS hash key and lookup table */ + netdev_rss_key_fill(pdata->rss_key, sizeof(pdata->rss_key)); + + for (i = 0; i < XLGMAC_RSS_MAX_TABLE_SIZE; i++) + pdata->rss_table[i] = XLGMAC_SET_REG_BITS( + pdata->rss_table[i], + MAC_RSSDR_DMCH_POS, + MAC_RSSDR_DMCH_LEN, + i % pdata->rx_ring_count); + + pdata->rss_options = XLGMAC_SET_REG_BITS( + pdata->rss_options, + MAC_RSSCR_IP2TE_POS, + MAC_RSSCR_IP2TE_LEN, 1); + pdata->rss_options = XLGMAC_SET_REG_BITS( + pdata->rss_options, + MAC_RSSCR_TCP4TE_POS, + MAC_RSSCR_TCP4TE_LEN, 1); + pdata->rss_options = XLGMAC_SET_REG_BITS( + pdata->rss_options, + MAC_RSSCR_UDP4TE_POS, + MAC_RSSCR_UDP4TE_LEN, 1); + + /* Set device operations */ + netdev->netdev_ops = xlgmac_get_netdev_ops(); + + /* Set device features */ + if (pdata->hw_feat.tso) { + netdev->hw_features = NETIF_F_TSO; + netdev->hw_features |= NETIF_F_TSO6; + netdev->hw_features |= NETIF_F_SG; + netdev->hw_features |= NETIF_F_IP_CSUM; + netdev->hw_features |= NETIF_F_IPV6_CSUM; + } else if (pdata->hw_feat.tx_coe) { + netdev->hw_features = NETIF_F_IP_CSUM; + netdev->hw_features |= NETIF_F_IPV6_CSUM; + } + + if (pdata->hw_feat.rx_coe) { + netdev->hw_features |= NETIF_F_RXCSUM; + netdev->hw_features |= NETIF_F_GRO; + } + + if (pdata->hw_feat.rss) + netdev->hw_features |= NETIF_F_RXHASH; + + netdev->vlan_features |= netdev->hw_features; + + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; + if (pdata->hw_feat.sa_vlan_ins) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + if (pdata->hw_feat.vlhash) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + netdev->features |= netdev->hw_features; + pdata->netdev_features = netdev->features; + + netdev->priv_flags |= IFF_UNICAST_FLT; + + /* Use default watchdog timeout */ + netdev->watchdog_timeo = 0; + + /* Tx coalesce parameters initialization */ + pdata->tx_usecs = XLGMAC_INIT_DMA_TX_USECS; + pdata->tx_frames = XLGMAC_INIT_DMA_TX_FRAMES; + + /* Rx coalesce parameters initialization */ + pdata->rx_riwt = hw_ops->usec_to_riwt(pdata, XLGMAC_INIT_DMA_RX_USECS); + pdata->rx_usecs = XLGMAC_INIT_DMA_RX_USECS; + pdata->rx_frames = XLGMAC_INIT_DMA_RX_FRAMES; + + return 0; +} + +int xlgmac_drv_probe(struct device *dev, struct xlgmac_resources *res) +{ + struct xlgmac_pdata *pdata; + struct net_device *netdev; + int ret; + + netdev = alloc_etherdev_mq(sizeof(struct xlgmac_pdata), + XLGMAC_MAX_DMA_CHANNELS); + + if (!netdev) { + dev_err(dev, "alloc_etherdev failed\n"); + return -ENOMEM; + } + + SET_NETDEV_DEV(netdev, dev); + dev_set_drvdata(dev, netdev); + pdata = netdev_priv(netdev); + pdata->dev = dev; + pdata->netdev = netdev; + + pdata->dev_irq = res->irq; + pdata->mac_regs = res->addr; + + mutex_init(&pdata->rss_mutex); + pdata->msg_enable = netif_msg_init(debug, default_msg_level); + + ret = xlgmac_init(pdata); + if (ret) { + dev_err(dev, "xlgmac init failed\n"); + goto err_free_netdev; + } + + ret = register_netdev(netdev); + if (ret) { + dev_err(dev, "net device registration failed\n"); + goto err_free_netdev; + } + + return 0; + +err_free_netdev: + free_netdev(netdev); + + return ret; +} + +int xlgmac_drv_remove(struct device *dev) +{ + struct net_device *netdev = dev_get_drvdata(dev); + + unregister_netdev(netdev); + free_netdev(netdev); + + return 0; +} + +void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx, + unsigned int count, + unsigned int flag) +{ + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + + while (count--) { + desc_data = XLGMAC_GET_DESC_DATA(ring, idx); + dma_desc = desc_data->dma_desc; + + netdev_dbg(pdata->netdev, "TX: dma_desc=%p, dma_desc_addr=%pad\n", + desc_data->dma_desc, &desc_data->dma_desc_addr); + netdev_dbg(pdata->netdev, + "TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx, + (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE", + le32_to_cpu(dma_desc->desc0), + le32_to_cpu(dma_desc->desc1), + le32_to_cpu(dma_desc->desc2), + le32_to_cpu(dma_desc->desc3)); + + idx++; + } +} + +void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx) +{ + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + + desc_data = XLGMAC_GET_DESC_DATA(ring, idx); + dma_desc = desc_data->dma_desc; + + netdev_dbg(pdata->netdev, "RX: dma_desc=%p, dma_desc_addr=%pad\n", + desc_data->dma_desc, &desc_data->dma_desc_addr); + netdev_dbg(pdata->netdev, + "RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n", + idx, + le32_to_cpu(dma_desc->desc0), + le32_to_cpu(dma_desc->desc1), + le32_to_cpu(dma_desc->desc2), + le32_to_cpu(dma_desc->desc3)); +} + +void xlgmac_print_pkt(struct net_device *netdev, + struct sk_buff *skb, bool tx_rx) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + unsigned char *buf = skb->data; + unsigned char buffer[128]; + unsigned int i, j; + + netdev_dbg(netdev, "\n************** SKB dump ****************\n"); + + netdev_dbg(netdev, "%s packet of %d bytes\n", + (tx_rx ? "TX" : "RX"), skb->len); + + netdev_dbg(netdev, "Dst MAC addr: %pM\n", eth->h_dest); + netdev_dbg(netdev, "Src MAC addr: %pM\n", eth->h_source); + netdev_dbg(netdev, "Protocol: %#06hx\n", ntohs(eth->h_proto)); + + for (i = 0, j = 0; i < skb->len;) { + j += snprintf(buffer + j, sizeof(buffer) - j, "%02hhx", + buf[i++]); + + if ((i % 32) == 0) { + netdev_dbg(netdev, " %#06x: %s\n", i - 32, buffer); + j = 0; + } else if ((i % 16) == 0) { + buffer[j++] = ' '; + buffer[j++] = ' '; + } else if ((i % 4) == 0) { + buffer[j++] = ' '; + } + } + if (i % 32) + netdev_dbg(netdev, " %#06x: %s\n", i - (i % 32), buffer); + + netdev_dbg(netdev, "\n************** SKB dump ****************\n"); +} + +void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_features *hw_feat = &pdata->hw_feat; + unsigned int mac_hfr0, mac_hfr1, mac_hfr2; + + mac_hfr0 = readl(pdata->mac_regs + MAC_HWF0R); + mac_hfr1 = readl(pdata->mac_regs + MAC_HWF1R); + mac_hfr2 = readl(pdata->mac_regs + MAC_HWF2R); + + memset(hw_feat, 0, sizeof(*hw_feat)); + + hw_feat->version = readl(pdata->mac_regs + MAC_VR); + + /* Hardware feature register 0 */ + hw_feat->phyifsel = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_PHYIFSEL_POS, + MAC_HWF0R_PHYIFSEL_LEN); + hw_feat->vlhash = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_VLHASH_POS, + MAC_HWF0R_VLHASH_LEN); + hw_feat->sma = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_SMASEL_POS, + MAC_HWF0R_SMASEL_LEN); + hw_feat->rwk = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_RWKSEL_POS, + MAC_HWF0R_RWKSEL_LEN); + hw_feat->mgk = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_MGKSEL_POS, + MAC_HWF0R_MGKSEL_LEN); + hw_feat->mmc = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_MMCSEL_POS, + MAC_HWF0R_MMCSEL_LEN); + hw_feat->aoe = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_ARPOFFSEL_POS, + MAC_HWF0R_ARPOFFSEL_LEN); + hw_feat->ts = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_TSSEL_POS, + MAC_HWF0R_TSSEL_LEN); + hw_feat->eee = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_EEESEL_POS, + MAC_HWF0R_EEESEL_LEN); + hw_feat->tx_coe = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_TXCOESEL_POS, + MAC_HWF0R_TXCOESEL_LEN); + hw_feat->rx_coe = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_RXCOESEL_POS, + MAC_HWF0R_RXCOESEL_LEN); + hw_feat->addn_mac = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_ADDMACADRSEL_POS, + MAC_HWF0R_ADDMACADRSEL_LEN); + hw_feat->ts_src = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_TSSTSSEL_POS, + MAC_HWF0R_TSSTSSEL_LEN); + hw_feat->sa_vlan_ins = XLGMAC_GET_REG_BITS(mac_hfr0, + MAC_HWF0R_SAVLANINS_POS, + MAC_HWF0R_SAVLANINS_LEN); + + /* Hardware feature register 1 */ + hw_feat->rx_fifo_size = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_RXFIFOSIZE_POS, + MAC_HWF1R_RXFIFOSIZE_LEN); + hw_feat->tx_fifo_size = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_TXFIFOSIZE_POS, + MAC_HWF1R_TXFIFOSIZE_LEN); + hw_feat->adv_ts_hi = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_ADVTHWORD_POS, + MAC_HWF1R_ADVTHWORD_LEN); + hw_feat->dma_width = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_ADDR64_POS, + MAC_HWF1R_ADDR64_LEN); + hw_feat->dcb = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_DCBEN_POS, + MAC_HWF1R_DCBEN_LEN); + hw_feat->sph = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_SPHEN_POS, + MAC_HWF1R_SPHEN_LEN); + hw_feat->tso = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_TSOEN_POS, + MAC_HWF1R_TSOEN_LEN); + hw_feat->dma_debug = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_DBGMEMA_POS, + MAC_HWF1R_DBGMEMA_LEN); + hw_feat->rss = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_RSSEN_POS, + MAC_HWF1R_RSSEN_LEN); + hw_feat->tc_cnt = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_NUMTC_POS, + MAC_HWF1R_NUMTC_LEN); + hw_feat->hash_table_size = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_HASHTBLSZ_POS, + MAC_HWF1R_HASHTBLSZ_LEN); + hw_feat->l3l4_filter_num = XLGMAC_GET_REG_BITS(mac_hfr1, + MAC_HWF1R_L3L4FNUM_POS, + MAC_HWF1R_L3L4FNUM_LEN); + + /* Hardware feature register 2 */ + hw_feat->rx_q_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_RXQCNT_POS, + MAC_HWF2R_RXQCNT_LEN); + hw_feat->tx_q_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_TXQCNT_POS, + MAC_HWF2R_TXQCNT_LEN); + hw_feat->rx_ch_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_RXCHCNT_POS, + MAC_HWF2R_RXCHCNT_LEN); + hw_feat->tx_ch_cnt = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_TXCHCNT_POS, + MAC_HWF2R_TXCHCNT_LEN); + hw_feat->pps_out_num = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_PPSOUTNUM_POS, + MAC_HWF2R_PPSOUTNUM_LEN); + hw_feat->aux_snap_num = XLGMAC_GET_REG_BITS(mac_hfr2, + MAC_HWF2R_AUXSNAPNUM_POS, + MAC_HWF2R_AUXSNAPNUM_LEN); + + /* Translate the Hash Table size into actual number */ + switch (hw_feat->hash_table_size) { + case 0: + break; + case 1: + hw_feat->hash_table_size = 64; + break; + case 2: + hw_feat->hash_table_size = 128; + break; + case 3: + hw_feat->hash_table_size = 256; + break; + } + + /* Translate the address width setting into actual number */ + switch (hw_feat->dma_width) { + case 0: + hw_feat->dma_width = 32; + break; + case 1: + hw_feat->dma_width = 40; + break; + case 2: + hw_feat->dma_width = 48; + break; + default: + hw_feat->dma_width = 32; + } + + /* The Queue, Channel and TC counts are zero based so increment them + * to get the actual number + */ + hw_feat->rx_q_cnt++; + hw_feat->tx_q_cnt++; + hw_feat->rx_ch_cnt++; + hw_feat->tx_ch_cnt++; + hw_feat->tc_cnt++; +} + +void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata) +{ + char *str = NULL; + + XLGMAC_PR("\n"); + XLGMAC_PR("=====================================================\n"); + XLGMAC_PR("\n"); + XLGMAC_PR("HW support following features\n"); + XLGMAC_PR("\n"); + /* HW Feature Register0 */ + XLGMAC_PR("VLAN Hash Filter Selected : %s\n", + pdata->hw_feat.vlhash ? "YES" : "NO"); + XLGMAC_PR("SMA (MDIO) Interface : %s\n", + pdata->hw_feat.sma ? "YES" : "NO"); + XLGMAC_PR("PMT Remote Wake-up Packet Enable : %s\n", + pdata->hw_feat.rwk ? "YES" : "NO"); + XLGMAC_PR("PMT Magic Packet Enable : %s\n", + pdata->hw_feat.mgk ? "YES" : "NO"); + XLGMAC_PR("RMON/MMC Module Enable : %s\n", + pdata->hw_feat.mmc ? "YES" : "NO"); + XLGMAC_PR("ARP Offload Enabled : %s\n", + pdata->hw_feat.aoe ? "YES" : "NO"); + XLGMAC_PR("IEEE 1588-2008 Timestamp Enabled : %s\n", + pdata->hw_feat.ts ? "YES" : "NO"); + XLGMAC_PR("Energy Efficient Ethernet Enabled : %s\n", + pdata->hw_feat.eee ? "YES" : "NO"); + XLGMAC_PR("Transmit Checksum Offload Enabled : %s\n", + pdata->hw_feat.tx_coe ? "YES" : "NO"); + XLGMAC_PR("Receive Checksum Offload Enabled : %s\n", + pdata->hw_feat.rx_coe ? "YES" : "NO"); + XLGMAC_PR("Additional MAC Addresses 1-31 Selected : %s\n", + pdata->hw_feat.addn_mac ? "YES" : "NO"); + + switch (pdata->hw_feat.ts_src) { + case 0: + str = "RESERVED"; + break; + case 1: + str = "INTERNAL"; + break; + case 2: + str = "EXTERNAL"; + break; + case 3: + str = "BOTH"; + break; + } + XLGMAC_PR("Timestamp System Time Source : %s\n", str); + + XLGMAC_PR("Source Address or VLAN Insertion Enable : %s\n", + pdata->hw_feat.sa_vlan_ins ? "YES" : "NO"); + + /* HW Feature Register1 */ + switch (pdata->hw_feat.rx_fifo_size) { + case 0: + str = "128 bytes"; + break; + case 1: + str = "256 bytes"; + break; + case 2: + str = "512 bytes"; + break; + case 3: + str = "1 KBytes"; + break; + case 4: + str = "2 KBytes"; + break; + case 5: + str = "4 KBytes"; + break; + case 6: + str = "8 KBytes"; + break; + case 7: + str = "16 KBytes"; + break; + case 8: + str = "32 kBytes"; + break; + case 9: + str = "64 KBytes"; + break; + case 10: + str = "128 KBytes"; + break; + case 11: + str = "256 KBytes"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("MTL Receive FIFO Size : %s\n", str); + + switch (pdata->hw_feat.tx_fifo_size) { + case 0: + str = "128 bytes"; + break; + case 1: + str = "256 bytes"; + break; + case 2: + str = "512 bytes"; + break; + case 3: + str = "1 KBytes"; + break; + case 4: + str = "2 KBytes"; + break; + case 5: + str = "4 KBytes"; + break; + case 6: + str = "8 KBytes"; + break; + case 7: + str = "16 KBytes"; + break; + case 8: + str = "32 kBytes"; + break; + case 9: + str = "64 KBytes"; + break; + case 10: + str = "128 KBytes"; + break; + case 11: + str = "256 KBytes"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("MTL Transmit FIFO Size : %s\n", str); + + XLGMAC_PR("IEEE 1588 High Word Register Enable : %s\n", + pdata->hw_feat.adv_ts_hi ? "YES" : "NO"); + XLGMAC_PR("Address width : %u\n", + pdata->hw_feat.dma_width); + XLGMAC_PR("DCB Feature Enable : %s\n", + pdata->hw_feat.dcb ? "YES" : "NO"); + XLGMAC_PR("Split Header Feature Enable : %s\n", + pdata->hw_feat.sph ? "YES" : "NO"); + XLGMAC_PR("TCP Segmentation Offload Enable : %s\n", + pdata->hw_feat.tso ? "YES" : "NO"); + XLGMAC_PR("DMA Debug Registers Enabled : %s\n", + pdata->hw_feat.dma_debug ? "YES" : "NO"); + XLGMAC_PR("RSS Feature Enabled : %s\n", + pdata->hw_feat.rss ? "YES" : "NO"); + XLGMAC_PR("Number of Traffic classes : %u\n", + (pdata->hw_feat.tc_cnt)); + XLGMAC_PR("Hash Table Size : %u\n", + pdata->hw_feat.hash_table_size); + XLGMAC_PR("Total number of L3 or L4 Filters : %u\n", + pdata->hw_feat.l3l4_filter_num); + + /* HW Feature Register2 */ + XLGMAC_PR("Number of MTL Receive Queues : %u\n", + pdata->hw_feat.rx_q_cnt); + XLGMAC_PR("Number of MTL Transmit Queues : %u\n", + pdata->hw_feat.tx_q_cnt); + XLGMAC_PR("Number of DMA Receive Channels : %u\n", + pdata->hw_feat.rx_ch_cnt); + XLGMAC_PR("Number of DMA Transmit Channels : %u\n", + pdata->hw_feat.tx_ch_cnt); + + switch (pdata->hw_feat.pps_out_num) { + case 0: + str = "No PPS output"; + break; + case 1: + str = "1 PPS output"; + break; + case 2: + str = "2 PPS output"; + break; + case 3: + str = "3 PPS output"; + break; + case 4: + str = "4 PPS output"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("Number of PPS Outputs : %s\n", str); + + switch (pdata->hw_feat.aux_snap_num) { + case 0: + str = "No auxiliary input"; + break; + case 1: + str = "1 auxiliary input"; + break; + case 2: + str = "2 auxiliary input"; + break; + case 3: + str = "3 auxiliary input"; + break; + case 4: + str = "4 auxiliary input"; + break; + default: + str = "RESERVED"; + } + XLGMAC_PR("Number of Auxiliary Snapshot Inputs : %s", str); + + XLGMAC_PR("\n"); + XLGMAC_PR("=====================================================\n"); + XLGMAC_PR("\n"); +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c new file mode 100644 index 000000000000..55c796ed7d26 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c @@ -0,0 +1,648 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static void xlgmac_unmap_desc_data(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data) +{ + if (desc_data->skb_dma) { + if (desc_data->mapped_as_page) { + dma_unmap_page(pdata->dev, desc_data->skb_dma, + desc_data->skb_dma_len, DMA_TO_DEVICE); + } else { + dma_unmap_single(pdata->dev, desc_data->skb_dma, + desc_data->skb_dma_len, DMA_TO_DEVICE); + } + desc_data->skb_dma = 0; + desc_data->skb_dma_len = 0; + } + + if (desc_data->skb) { + dev_kfree_skb_any(desc_data->skb); + desc_data->skb = NULL; + } + + if (desc_data->rx.hdr.pa.pages) + put_page(desc_data->rx.hdr.pa.pages); + + if (desc_data->rx.hdr.pa_unmap.pages) { + dma_unmap_page(pdata->dev, desc_data->rx.hdr.pa_unmap.pages_dma, + desc_data->rx.hdr.pa_unmap.pages_len, + DMA_FROM_DEVICE); + put_page(desc_data->rx.hdr.pa_unmap.pages); + } + + if (desc_data->rx.buf.pa.pages) + put_page(desc_data->rx.buf.pa.pages); + + if (desc_data->rx.buf.pa_unmap.pages) { + dma_unmap_page(pdata->dev, desc_data->rx.buf.pa_unmap.pages_dma, + desc_data->rx.buf.pa_unmap.pages_len, + DMA_FROM_DEVICE); + put_page(desc_data->rx.buf.pa_unmap.pages); + } + + memset(&desc_data->tx, 0, sizeof(desc_data->tx)); + memset(&desc_data->rx, 0, sizeof(desc_data->rx)); + + desc_data->mapped_as_page = 0; + + if (desc_data->state_saved) { + desc_data->state_saved = 0; + desc_data->state.skb = NULL; + desc_data->state.len = 0; + desc_data->state.error = 0; + } +} + +static void xlgmac_free_ring(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring) +{ + struct xlgmac_desc_data *desc_data; + unsigned int i; + + if (!ring) + return; + + if (ring->desc_data_head) { + for (i = 0; i < ring->dma_desc_count; i++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, i); + xlgmac_unmap_desc_data(pdata, desc_data); + } + + kfree(ring->desc_data_head); + ring->desc_data_head = NULL; + } + + if (ring->rx_hdr_pa.pages) { + dma_unmap_page(pdata->dev, ring->rx_hdr_pa.pages_dma, + ring->rx_hdr_pa.pages_len, DMA_FROM_DEVICE); + put_page(ring->rx_hdr_pa.pages); + + ring->rx_hdr_pa.pages = NULL; + ring->rx_hdr_pa.pages_len = 0; + ring->rx_hdr_pa.pages_offset = 0; + ring->rx_hdr_pa.pages_dma = 0; + } + + if (ring->rx_buf_pa.pages) { + dma_unmap_page(pdata->dev, ring->rx_buf_pa.pages_dma, + ring->rx_buf_pa.pages_len, DMA_FROM_DEVICE); + put_page(ring->rx_buf_pa.pages); + + ring->rx_buf_pa.pages = NULL; + ring->rx_buf_pa.pages_len = 0; + ring->rx_buf_pa.pages_offset = 0; + ring->rx_buf_pa.pages_dma = 0; + } + + if (ring->dma_desc_head) { + dma_free_coherent(pdata->dev, + (sizeof(struct xlgmac_dma_desc) * + ring->dma_desc_count), + ring->dma_desc_head, + ring->dma_desc_head_addr); + ring->dma_desc_head = NULL; + } +} + +static int xlgmac_init_ring(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int dma_desc_count) +{ + if (!ring) + return 0; + + /* Descriptors */ + ring->dma_desc_count = dma_desc_count; + ring->dma_desc_head = dma_alloc_coherent(pdata->dev, + (sizeof(struct xlgmac_dma_desc) * + dma_desc_count), + &ring->dma_desc_head_addr, + GFP_KERNEL); + if (!ring->dma_desc_head) + return -ENOMEM; + + /* Array of descriptor data */ + ring->desc_data_head = kcalloc(dma_desc_count, + sizeof(struct xlgmac_desc_data), + GFP_KERNEL); + if (!ring->desc_data_head) + return -ENOMEM; + + netif_dbg(pdata, drv, pdata->netdev, + "dma_desc_head=%p, dma_desc_head_addr=%pad, desc_data_head=%p\n", + ring->dma_desc_head, + &ring->dma_desc_head_addr, + ring->desc_data_head); + + return 0; +} + +static void xlgmac_free_rings(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + if (!pdata->channel_head) + return; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + xlgmac_free_ring(pdata, channel->tx_ring); + xlgmac_free_ring(pdata, channel->rx_ring); + } +} + +static int xlgmac_alloc_rings(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + int ret; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + netif_dbg(pdata, drv, pdata->netdev, "%s - Tx ring:\n", + channel->name); + + ret = xlgmac_init_ring(pdata, channel->tx_ring, + pdata->tx_desc_count); + + if (ret) { + netdev_alert(pdata->netdev, + "error initializing Tx ring"); + goto err_init_ring; + } + + netif_dbg(pdata, drv, pdata->netdev, "%s - Rx ring:\n", + channel->name); + + ret = xlgmac_init_ring(pdata, channel->rx_ring, + pdata->rx_desc_count); + if (ret) { + netdev_alert(pdata->netdev, + "error initializing Rx ring\n"); + goto err_init_ring; + } + } + + return 0; + +err_init_ring: + xlgmac_free_rings(pdata); + + return ret; +} + +static void xlgmac_free_channels(struct xlgmac_pdata *pdata) +{ + if (!pdata->channel_head) + return; + + kfree(pdata->channel_head->tx_ring); + pdata->channel_head->tx_ring = NULL; + + kfree(pdata->channel_head->rx_ring); + pdata->channel_head->rx_ring = NULL; + + kfree(pdata->channel_head); + + pdata->channel_head = NULL; + pdata->channel_count = 0; +} + +static int xlgmac_alloc_channels(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel_head, *channel; + struct xlgmac_ring *tx_ring, *rx_ring; + int ret = -ENOMEM; + unsigned int i; + + channel_head = kcalloc(pdata->channel_count, + sizeof(struct xlgmac_channel), GFP_KERNEL); + if (!channel_head) + return ret; + + netif_dbg(pdata, drv, pdata->netdev, + "channel_head=%p\n", channel_head); + + tx_ring = kcalloc(pdata->tx_ring_count, sizeof(struct xlgmac_ring), + GFP_KERNEL); + if (!tx_ring) + goto err_tx_ring; + + rx_ring = kcalloc(pdata->rx_ring_count, sizeof(struct xlgmac_ring), + GFP_KERNEL); + if (!rx_ring) + goto err_rx_ring; + + for (i = 0, channel = channel_head; i < pdata->channel_count; + i++, channel++) { + snprintf(channel->name, sizeof(channel->name), "channel-%u", i); + channel->pdata = pdata; + channel->queue_index = i; + channel->dma_regs = pdata->mac_regs + DMA_CH_BASE + + (DMA_CH_INC * i); + + if (pdata->per_channel_irq) { + /* Get the per DMA interrupt */ + ret = pdata->channel_irq[i]; + if (ret < 0) { + netdev_err(pdata->netdev, + "get_irq %u failed\n", + i + 1); + goto err_irq; + } + channel->dma_irq = ret; + } + + if (i < pdata->tx_ring_count) + channel->tx_ring = tx_ring++; + + if (i < pdata->rx_ring_count) + channel->rx_ring = rx_ring++; + + netif_dbg(pdata, drv, pdata->netdev, + "%s: dma_regs=%p, tx_ring=%p, rx_ring=%p\n", + channel->name, channel->dma_regs, + channel->tx_ring, channel->rx_ring); + } + + pdata->channel_head = channel_head; + + return 0; + +err_irq: + kfree(rx_ring); + +err_rx_ring: + kfree(tx_ring); + +err_tx_ring: + kfree(channel_head); + + return ret; +} + +static void xlgmac_free_channels_and_rings(struct xlgmac_pdata *pdata) +{ + xlgmac_free_rings(pdata); + + xlgmac_free_channels(pdata); +} + +static int xlgmac_alloc_channels_and_rings(struct xlgmac_pdata *pdata) +{ + int ret; + + ret = xlgmac_alloc_channels(pdata); + if (ret) + goto err_alloc; + + ret = xlgmac_alloc_rings(pdata); + if (ret) + goto err_alloc; + + return 0; + +err_alloc: + xlgmac_free_channels_and_rings(pdata); + + return ret; +} + +static int xlgmac_alloc_pages(struct xlgmac_pdata *pdata, + struct xlgmac_page_alloc *pa, + gfp_t gfp, int order) +{ + struct page *pages = NULL; + dma_addr_t pages_dma; + int ret; + + /* Try to obtain pages, decreasing order if necessary */ + gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN; + while (order >= 0) { + pages = alloc_pages(gfp, order); + if (pages) + break; + + order--; + } + if (!pages) + return -ENOMEM; + + /* Map the pages */ + pages_dma = dma_map_page(pdata->dev, pages, 0, + PAGE_SIZE << order, DMA_FROM_DEVICE); + ret = dma_mapping_error(pdata->dev, pages_dma); + if (ret) { + put_page(pages); + return ret; + } + + pa->pages = pages; + pa->pages_len = PAGE_SIZE << order; + pa->pages_offset = 0; + pa->pages_dma = pages_dma; + + return 0; +} + +static void xlgmac_set_buffer_data(struct xlgmac_buffer_data *bd, + struct xlgmac_page_alloc *pa, + unsigned int len) +{ + get_page(pa->pages); + bd->pa = *pa; + + bd->dma_base = pa->pages_dma; + bd->dma_off = pa->pages_offset; + bd->dma_len = len; + + pa->pages_offset += len; + if ((pa->pages_offset + len) > pa->pages_len) { + /* This data descriptor is responsible for unmapping page(s) */ + bd->pa_unmap = *pa; + + /* Get a new allocation next time */ + pa->pages = NULL; + pa->pages_len = 0; + pa->pages_offset = 0; + pa->pages_dma = 0; + } +} + +static int xlgmac_map_rx_buffer(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + struct xlgmac_desc_data *desc_data) +{ + int order, ret; + + if (!ring->rx_hdr_pa.pages) { + ret = xlgmac_alloc_pages(pdata, &ring->rx_hdr_pa, + GFP_ATOMIC, 0); + if (ret) + return ret; + } + + if (!ring->rx_buf_pa.pages) { + order = max_t(int, PAGE_ALLOC_COSTLY_ORDER - 1, 0); + ret = xlgmac_alloc_pages(pdata, &ring->rx_buf_pa, + GFP_ATOMIC, order); + if (ret) + return ret; + } + + /* Set up the header page info */ + xlgmac_set_buffer_data(&desc_data->rx.hdr, &ring->rx_hdr_pa, + XLGMAC_SKB_ALLOC_SIZE); + + /* Set up the buffer page info */ + xlgmac_set_buffer_data(&desc_data->rx.buf, &ring->rx_buf_pa, + pdata->rx_buf_size); + + return 0; +} + +static void xlgmac_tx_desc_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + dma_addr_t dma_desc_addr; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->tx_ring; + if (!ring) + break; + + dma_desc = ring->dma_desc_head; + dma_desc_addr = ring->dma_desc_head_addr; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + + desc_data->dma_desc = dma_desc; + desc_data->dma_desc_addr = dma_desc_addr; + + dma_desc++; + dma_desc_addr += sizeof(struct xlgmac_dma_desc); + } + + ring->cur = 0; + ring->dirty = 0; + memset(&ring->tx, 0, sizeof(ring->tx)); + + hw_ops->tx_desc_init(channel); + } +} + +static void xlgmac_rx_desc_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + dma_addr_t dma_desc_addr; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->rx_ring; + if (!ring) + break; + + dma_desc = ring->dma_desc_head; + dma_desc_addr = ring->dma_desc_head_addr; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + + desc_data->dma_desc = dma_desc; + desc_data->dma_desc_addr = dma_desc_addr; + + if (xlgmac_map_rx_buffer(pdata, ring, desc_data)) + break; + + dma_desc++; + dma_desc_addr += sizeof(struct xlgmac_dma_desc); + } + + ring->cur = 0; + ring->dirty = 0; + + hw_ops->rx_desc_init(channel); + } +} + +static int xlgmac_map_tx_skb(struct xlgmac_channel *channel, + struct sk_buff *skb) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->tx_ring; + unsigned int start_index, cur_index; + struct xlgmac_desc_data *desc_data; + unsigned int offset, datalen, len; + struct xlgmac_pkt_info *pkt_info; + struct skb_frag_struct *frag; + unsigned int tso, vlan; + dma_addr_t skb_dma; + unsigned int i; + + offset = 0; + start_index = ring->cur; + cur_index = ring->cur; + + pkt_info = &ring->pkt_info; + pkt_info->desc_count = 0; + pkt_info->length = 0; + + tso = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN); + vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN); + + /* Save space for a context descriptor if needed */ + if ((tso && (pkt_info->mss != ring->tx.cur_mss)) || + (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag))) + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + + if (tso) { + /* Map the TSO header */ + skb_dma = dma_map_single(pdata->dev, skb->data, + pkt_info->header_len, DMA_TO_DEVICE); + if (dma_mapping_error(pdata->dev, skb_dma)) { + netdev_alert(pdata->netdev, "dma_map_single failed\n"); + goto err_out; + } + desc_data->skb_dma = skb_dma; + desc_data->skb_dma_len = pkt_info->header_len; + netif_dbg(pdata, tx_queued, pdata->netdev, + "skb header: index=%u, dma=%pad, len=%u\n", + cur_index, &skb_dma, pkt_info->header_len); + + offset = pkt_info->header_len; + + pkt_info->length += pkt_info->header_len; + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + } + + /* Map the (remainder of the) packet */ + for (datalen = skb_headlen(skb) - offset; datalen; ) { + len = min_t(unsigned int, datalen, XLGMAC_TX_MAX_BUF_SIZE); + + skb_dma = dma_map_single(pdata->dev, skb->data + offset, len, + DMA_TO_DEVICE); + if (dma_mapping_error(pdata->dev, skb_dma)) { + netdev_alert(pdata->netdev, "dma_map_single failed\n"); + goto err_out; + } + desc_data->skb_dma = skb_dma; + desc_data->skb_dma_len = len; + netif_dbg(pdata, tx_queued, pdata->netdev, + "skb data: index=%u, dma=%pad, len=%u\n", + cur_index, &skb_dma, len); + + datalen -= len; + offset += len; + + pkt_info->length += len; + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + netif_dbg(pdata, tx_queued, pdata->netdev, + "mapping frag %u\n", i); + + frag = &skb_shinfo(skb)->frags[i]; + offset = 0; + + for (datalen = skb_frag_size(frag); datalen; ) { + len = min_t(unsigned int, datalen, + XLGMAC_TX_MAX_BUF_SIZE); + + skb_dma = skb_frag_dma_map(pdata->dev, frag, offset, + len, DMA_TO_DEVICE); + if (dma_mapping_error(pdata->dev, skb_dma)) { + netdev_alert(pdata->netdev, + "skb_frag_dma_map failed\n"); + goto err_out; + } + desc_data->skb_dma = skb_dma; + desc_data->skb_dma_len = len; + desc_data->mapped_as_page = 1; + netif_dbg(pdata, tx_queued, pdata->netdev, + "skb frag: index=%u, dma=%pad, len=%u\n", + cur_index, &skb_dma, len); + + datalen -= len; + offset += len; + + pkt_info->length += len; + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + } + } + + /* Save the skb address in the last entry. We always have some data + * that has been mapped so desc_data is always advanced past the last + * piece of mapped data - use the entry pointed to by cur_index - 1. + */ + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index - 1); + desc_data->skb = skb; + + /* Save the number of descriptor entries used */ + pkt_info->desc_count = cur_index - start_index; + + return pkt_info->desc_count; + +err_out: + while (start_index < cur_index) { + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index++); + xlgmac_unmap_desc_data(pdata, desc_data); + } + + return 0; +} + +void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops) +{ + desc_ops->alloc_channles_and_rings = xlgmac_alloc_channels_and_rings; + desc_ops->free_channels_and_rings = xlgmac_free_channels_and_rings; + desc_ops->map_tx_skb = xlgmac_map_tx_skb; + desc_ops->map_rx_buffer = xlgmac_map_rx_buffer; + desc_ops->unmap_desc_data = xlgmac_unmap_desc_data; + desc_ops->tx_desc_init = xlgmac_tx_desc_init; + desc_ops->rx_desc_init = xlgmac_rx_desc_init; +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c new file mode 100644 index 000000000000..5cf3e90d4834 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c @@ -0,0 +1,3146 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include +#include +#include +#include +#include + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int xlgmac_tx_complete(struct xlgmac_dma_desc *dma_desc) +{ + return !XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN); +} + +static int xlgmac_disable_rx_csum(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS, + MAC_RCR_IPC_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RCR); + + return 0; +} + +static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS, + MAC_RCR_IPC_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RCR); + + return 0; +} + +static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr) +{ + unsigned int mac_addr_hi, mac_addr_lo; + + mac_addr_hi = (addr[5] << 8) | (addr[4] << 0); + mac_addr_lo = (addr[3] << 24) | (addr[2] << 16) | + (addr[1] << 8) | (addr[0] << 0); + + writel(mac_addr_hi, pdata->mac_regs + MAC_MACA0HR); + writel(mac_addr_lo, pdata->mac_regs + MAC_MACA0LR); + + return 0; +} + +static void xlgmac_set_mac_reg(struct xlgmac_pdata *pdata, + struct netdev_hw_addr *ha, + unsigned int *mac_reg) +{ + unsigned int mac_addr_hi, mac_addr_lo; + u8 *mac_addr; + + mac_addr_lo = 0; + mac_addr_hi = 0; + + if (ha) { + mac_addr = (u8 *)&mac_addr_lo; + mac_addr[0] = ha->addr[0]; + mac_addr[1] = ha->addr[1]; + mac_addr[2] = ha->addr[2]; + mac_addr[3] = ha->addr[3]; + mac_addr = (u8 *)&mac_addr_hi; + mac_addr[0] = ha->addr[4]; + mac_addr[1] = ha->addr[5]; + + netif_dbg(pdata, drv, pdata->netdev, + "adding mac address %pM at %#x\n", + ha->addr, *mac_reg); + + mac_addr_hi = XLGMAC_SET_REG_BITS(mac_addr_hi, + MAC_MACA1HR_AE_POS, + MAC_MACA1HR_AE_LEN, + 1); + } + + writel(mac_addr_hi, pdata->mac_regs + *mac_reg); + *mac_reg += MAC_MACA_INC; + writel(mac_addr_lo, pdata->mac_regs + *mac_reg); + *mac_reg += MAC_MACA_INC; +} + +static int xlgmac_enable_rx_vlan_stripping(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_VLANTR); + /* Put the VLAN tag in the Rx descriptor */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLRXS_POS, + MAC_VLANTR_EVLRXS_LEN, 1); + /* Don't check the VLAN type */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_DOVLTC_POS, + MAC_VLANTR_DOVLTC_LEN, 1); + /* Check only C-TAG (0x8100) packets */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ERSVLM_POS, + MAC_VLANTR_ERSVLM_LEN, 0); + /* Don't consider an S-TAG (0x88A8) packet as a VLAN packet */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ESVL_POS, + MAC_VLANTR_ESVL_LEN, 0); + /* Enable VLAN tag stripping */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS, + MAC_VLANTR_EVLS_LEN, 0x3); + writel(regval, pdata->mac_regs + MAC_VLANTR); + + return 0; +} + +static int xlgmac_disable_rx_vlan_stripping(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_VLANTR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS, + MAC_VLANTR_EVLS_LEN, 0); + writel(regval, pdata->mac_regs + MAC_VLANTR); + + return 0; +} + +static int xlgmac_enable_rx_vlan_filtering(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_PFR); + /* Enable VLAN filtering */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS, + MAC_PFR_VTFE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_PFR); + + regval = readl(pdata->mac_regs + MAC_VLANTR); + /* Enable VLAN Hash Table filtering */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTHM_POS, + MAC_VLANTR_VTHM_LEN, 1); + /* Disable VLAN tag inverse matching */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTIM_POS, + MAC_VLANTR_VTIM_LEN, 0); + /* Only filter on the lower 12-bits of the VLAN tag */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ETV_POS, + MAC_VLANTR_ETV_LEN, 1); + /* In order for the VLAN Hash Table filtering to be effective, + * the VLAN tag identifier in the VLAN Tag Register must not + * be zero. Set the VLAN tag identifier to "1" to enable the + * VLAN Hash Table filtering. This implies that a VLAN tag of + * 1 will always pass filtering. + */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VL_POS, + MAC_VLANTR_VL_LEN, 1); + writel(regval, pdata->mac_regs + MAC_VLANTR); + + return 0; +} + +static int xlgmac_disable_rx_vlan_filtering(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_PFR); + /* Disable VLAN filtering */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS, + MAC_PFR_VTFE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_PFR); + + return 0; +} + +static u32 xlgmac_vid_crc32_le(__le16 vid_le) +{ + unsigned char *data = (unsigned char *)&vid_le; + unsigned char data_byte = 0; + u32 poly = 0xedb88320; + u32 crc = ~0; + u32 temp = 0; + int i, bits; + + bits = get_bitmask_order(VLAN_VID_MASK); + for (i = 0; i < bits; i++) { + if ((i % 8) == 0) + data_byte = data[i / 8]; + + temp = ((crc & 1) ^ data_byte) & 1; + crc >>= 1; + data_byte >>= 1; + + if (temp) + crc ^= poly; + } + + return crc; +} + +static int xlgmac_update_vlan_hash_table(struct xlgmac_pdata *pdata) +{ + u16 vlan_hash_table = 0; + __le16 vid_le; + u32 regval; + u32 crc; + u16 vid; + + /* Generate the VLAN Hash Table value */ + for_each_set_bit(vid, pdata->active_vlans, VLAN_N_VID) { + /* Get the CRC32 value of the VLAN ID */ + vid_le = cpu_to_le16(vid); + crc = bitrev32(~xlgmac_vid_crc32_le(vid_le)) >> 28; + + vlan_hash_table |= (1 << crc); + } + + regval = readl(pdata->mac_regs + MAC_VLANHTR); + /* Set the VLAN Hash Table filtering register */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANHTR_VLHT_POS, + MAC_VLANHTR_VLHT_LEN, vlan_hash_table); + writel(regval, pdata->mac_regs + MAC_VLANHTR); + + return 0; +} + +static int xlgmac_set_promiscuous_mode(struct xlgmac_pdata *pdata, + unsigned int enable) +{ + unsigned int val = enable ? 1 : 0; + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR), + MAC_PFR_PR_POS, MAC_PFR_PR_LEN); + if (regval == val) + return 0; + + netif_dbg(pdata, drv, pdata->netdev, "%s promiscuous mode\n", + enable ? "entering" : "leaving"); + + regval = readl(pdata->mac_regs + MAC_PFR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PR_POS, + MAC_PFR_PR_LEN, val); + writel(regval, pdata->mac_regs + MAC_PFR); + + /* Hardware will still perform VLAN filtering in promiscuous mode */ + if (enable) { + xlgmac_disable_rx_vlan_filtering(pdata); + } else { + if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + xlgmac_enable_rx_vlan_filtering(pdata); + } + + return 0; +} + +static int xlgmac_set_all_multicast_mode(struct xlgmac_pdata *pdata, + unsigned int enable) +{ + unsigned int val = enable ? 1 : 0; + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR), + MAC_PFR_PM_POS, MAC_PFR_PM_LEN); + if (regval == val) + return 0; + + netif_dbg(pdata, drv, pdata->netdev, "%s allmulti mode\n", + enable ? "entering" : "leaving"); + + regval = readl(pdata->mac_regs + MAC_PFR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PM_POS, + MAC_PFR_PM_LEN, val); + writel(regval, pdata->mac_regs + MAC_PFR); + + return 0; +} + +static void xlgmac_set_mac_addn_addrs(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + struct netdev_hw_addr *ha; + unsigned int addn_macs; + unsigned int mac_reg; + + mac_reg = MAC_MACA1HR; + addn_macs = pdata->hw_feat.addn_mac; + + if (netdev_uc_count(netdev) > addn_macs) { + xlgmac_set_promiscuous_mode(pdata, 1); + } else { + netdev_for_each_uc_addr(ha, netdev) { + xlgmac_set_mac_reg(pdata, ha, &mac_reg); + addn_macs--; + } + + if (netdev_mc_count(netdev) > addn_macs) { + xlgmac_set_all_multicast_mode(pdata, 1); + } else { + netdev_for_each_mc_addr(ha, netdev) { + xlgmac_set_mac_reg(pdata, ha, &mac_reg); + addn_macs--; + } + } + } + + /* Clear remaining additional MAC address entries */ + while (addn_macs--) + xlgmac_set_mac_reg(pdata, NULL, &mac_reg); +} + +static void xlgmac_set_mac_hash_table(struct xlgmac_pdata *pdata) +{ + unsigned int hash_table_shift, hash_table_count; + u32 hash_table[XLGMAC_MAC_HASH_TABLE_SIZE]; + struct net_device *netdev = pdata->netdev; + struct netdev_hw_addr *ha; + unsigned int hash_reg; + unsigned int i; + u32 crc; + + hash_table_shift = 26 - (pdata->hw_feat.hash_table_size >> 7); + hash_table_count = pdata->hw_feat.hash_table_size / 32; + memset(hash_table, 0, sizeof(hash_table)); + + /* Build the MAC Hash Table register values */ + netdev_for_each_uc_addr(ha, netdev) { + crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)); + crc >>= hash_table_shift; + hash_table[crc >> 5] |= (1 << (crc & 0x1f)); + } + + netdev_for_each_mc_addr(ha, netdev) { + crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)); + crc >>= hash_table_shift; + hash_table[crc >> 5] |= (1 << (crc & 0x1f)); + } + + /* Set the MAC Hash Table registers */ + hash_reg = MAC_HTR0; + for (i = 0; i < hash_table_count; i++) { + writel(hash_table[i], pdata->mac_regs + hash_reg); + hash_reg += MAC_HTR_INC; + } +} + +static int xlgmac_add_mac_addresses(struct xlgmac_pdata *pdata) +{ + if (pdata->hw_feat.hash_table_size) + xlgmac_set_mac_hash_table(pdata); + else + xlgmac_set_mac_addn_addrs(pdata); + + return 0; +} + +static void xlgmac_config_mac_address(struct xlgmac_pdata *pdata) +{ + u32 regval; + + xlgmac_set_mac_address(pdata, pdata->netdev->dev_addr); + + /* Filtering is done using perfect filtering and hash filtering */ + if (pdata->hw_feat.hash_table_size) { + regval = readl(pdata->mac_regs + MAC_PFR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HPF_POS, + MAC_PFR_HPF_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HUC_POS, + MAC_PFR_HUC_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HMC_POS, + MAC_PFR_HMC_LEN, 1); + writel(regval, pdata->mac_regs + MAC_PFR); + } +} + +static void xlgmac_config_jumbo_enable(struct xlgmac_pdata *pdata) +{ + unsigned int val; + u32 regval; + + val = (pdata->netdev->mtu > XLGMAC_STD_PACKET_MTU) ? 1 : 0; + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_JE_POS, + MAC_RCR_JE_LEN, val); + writel(regval, pdata->mac_regs + MAC_RCR); +} + +static void xlgmac_config_checksum_offload(struct xlgmac_pdata *pdata) +{ + if (pdata->netdev->features & NETIF_F_RXCSUM) + xlgmac_enable_rx_csum(pdata); + else + xlgmac_disable_rx_csum(pdata); +} + +static void xlgmac_config_vlan_support(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_VLANIR); + /* Indicate that VLAN Tx CTAGs come from context descriptors */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_CSVL_POS, + MAC_VLANIR_CSVL_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_VLTI_POS, + MAC_VLANIR_VLTI_LEN, 1); + writel(regval, pdata->mac_regs + MAC_VLANIR); + + /* Set the current VLAN Hash Table register value */ + xlgmac_update_vlan_hash_table(pdata); + + if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + xlgmac_enable_rx_vlan_filtering(pdata); + else + xlgmac_disable_rx_vlan_filtering(pdata); + + if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) + xlgmac_enable_rx_vlan_stripping(pdata); + else + xlgmac_disable_rx_vlan_stripping(pdata); +} + +static int xlgmac_config_rx_mode(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + unsigned int pr_mode, am_mode; + + pr_mode = ((netdev->flags & IFF_PROMISC) != 0); + am_mode = ((netdev->flags & IFF_ALLMULTI) != 0); + + xlgmac_set_promiscuous_mode(pdata, pr_mode); + xlgmac_set_all_multicast_mode(pdata, am_mode); + + xlgmac_add_mac_addresses(pdata); + + return 0; +} + +static void xlgmac_prepare_tx_stop(struct xlgmac_pdata *pdata, + struct xlgmac_channel *channel) +{ + unsigned int tx_dsr, tx_pos, tx_qidx; + unsigned long tx_timeout; + unsigned int tx_status; + + /* Calculate the status register to read and the position within */ + if (channel->queue_index < DMA_DSRX_FIRST_QUEUE) { + tx_dsr = DMA_DSR0; + tx_pos = (channel->queue_index * DMA_DSR_Q_LEN) + + DMA_DSR0_TPS_START; + } else { + tx_qidx = channel->queue_index - DMA_DSRX_FIRST_QUEUE; + + tx_dsr = DMA_DSR1 + ((tx_qidx / DMA_DSRX_QPR) * DMA_DSRX_INC); + tx_pos = ((tx_qidx % DMA_DSRX_QPR) * DMA_DSR_Q_LEN) + + DMA_DSRX_TPS_START; + } + + /* The Tx engine cannot be stopped if it is actively processing + * descriptors. Wait for the Tx engine to enter the stopped or + * suspended state. Don't wait forever though... + */ + tx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ); + while (time_before(jiffies, tx_timeout)) { + tx_status = readl(pdata->mac_regs + tx_dsr); + tx_status = XLGMAC_GET_REG_BITS(tx_status, tx_pos, + DMA_DSR_TPS_LEN); + if ((tx_status == DMA_TPS_STOPPED) || + (tx_status == DMA_TPS_SUSPENDED)) + break; + + usleep_range(500, 1000); + } + + if (!time_before(jiffies, tx_timeout)) + netdev_info(pdata->netdev, + "timed out waiting for Tx DMA channel %u to stop\n", + channel->queue_index); +} + +static void xlgmac_enable_tx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + /* Enable each Tx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS, + DMA_CH_TCR_ST_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + + /* Enable each Tx queue */ + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS, + MTL_Q_TQOMR_TXQEN_LEN, + MTL_Q_ENABLED); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + /* Enable MAC Tx */ + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS, + MAC_TCR_TE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_TCR); +} + +static void xlgmac_disable_tx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + /* Prepare for Tx DMA channel stop */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + xlgmac_prepare_tx_stop(pdata, channel); + } + + /* Disable MAC Tx */ + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS, + MAC_TCR_TE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_TCR); + + /* Disable each Tx queue */ + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS, + MTL_Q_TQOMR_TXQEN_LEN, 0); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + /* Disable each Tx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS, + DMA_CH_TCR_ST_LEN, 0); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } +} + +static void xlgmac_prepare_rx_stop(struct xlgmac_pdata *pdata, + unsigned int queue) +{ + unsigned int rx_status, prxq, rxqsts; + unsigned long rx_timeout; + + /* The Rx engine cannot be stopped if it is actively processing + * packets. Wait for the Rx queue to empty the Rx fifo. Don't + * wait forever though... + */ + rx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ); + while (time_before(jiffies, rx_timeout)) { + rx_status = readl(XLGMAC_MTL_REG(pdata, queue, MTL_Q_RQDR)); + prxq = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_PRXQ_POS, + MTL_Q_RQDR_PRXQ_LEN); + rxqsts = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_RXQSTS_POS, + MTL_Q_RQDR_RXQSTS_LEN); + if ((prxq == 0) && (rxqsts == 0)) + break; + + usleep_range(500, 1000); + } + + if (!time_before(jiffies, rx_timeout)) + netdev_info(pdata->netdev, + "timed out waiting for Rx queue %u to empty\n", + queue); +} + +static void xlgmac_enable_rx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int regval, i; + + /* Enable each Rx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS, + DMA_CH_RCR_SR_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } + + /* Enable each Rx queue */ + regval = 0; + for (i = 0; i < pdata->rx_q_count; i++) + regval |= (0x02 << (i << 1)); + writel(regval, pdata->mac_regs + MAC_RQC0R); + + /* Enable MAC Rx */ + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS, + MAC_RCR_DCRCC_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS, + MAC_RCR_CST_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS, + MAC_RCR_ACS_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS, + MAC_RCR_RE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RCR); +} + +static void xlgmac_disable_rx(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + /* Disable MAC Rx */ + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS, + MAC_RCR_DCRCC_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS, + MAC_RCR_CST_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS, + MAC_RCR_ACS_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS, + MAC_RCR_RE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RCR); + + /* Prepare for Rx DMA channel stop */ + for (i = 0; i < pdata->rx_q_count; i++) + xlgmac_prepare_rx_stop(pdata, i); + + /* Disable each Rx queue */ + writel(0, pdata->mac_regs + MAC_RQC0R); + + /* Disable each Rx DMA channel */ + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS, + DMA_CH_RCR_SR_LEN, 0); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } +} + +static void xlgmac_tx_start_xmit(struct xlgmac_channel *channel, + struct xlgmac_ring *ring) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_desc_data *desc_data; + + /* Make sure everything is written before the register write */ + wmb(); + + /* Issue a poll command to Tx DMA by writing address + * of next immediate free descriptor + */ + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_TDTR_LO)); + + /* Start the Tx timer */ + if (pdata->tx_usecs && !channel->tx_timer_active) { + channel->tx_timer_active = 1; + mod_timer(&channel->tx_timer, + jiffies + usecs_to_jiffies(pdata->tx_usecs)); + } + + ring->tx.xmit_more = 0; +} + +static void xlgmac_dev_xmit(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->tx_ring; + unsigned int tso_context, vlan_context; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_pkt_info *pkt_info; + unsigned int csum, tso, vlan; + int start_index = ring->cur; + int cur_index = ring->cur; + unsigned int tx_set_ic; + int i; + + pkt_info = &ring->pkt_info; + csum = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN); + tso = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN); + vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN); + + if (tso && (pkt_info->mss != ring->tx.cur_mss)) + tso_context = 1; + else + tso_context = 0; + + if (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag)) + vlan_context = 1; + else + vlan_context = 0; + + /* Determine if an interrupt should be generated for this Tx: + * Interrupt: + * - Tx frame count exceeds the frame count setting + * - Addition of Tx frame count to the frame count since the + * last interrupt was set exceeds the frame count setting + * No interrupt: + * - No frame count setting specified (ethtool -C ethX tx-frames 0) + * - Addition of Tx frame count to the frame count since the + * last interrupt was set does not exceed the frame count setting + */ + ring->coalesce_count += pkt_info->tx_packets; + if (!pdata->tx_frames) + tx_set_ic = 0; + else if (pkt_info->tx_packets > pdata->tx_frames) + tx_set_ic = 1; + else if ((ring->coalesce_count % pdata->tx_frames) < + pkt_info->tx_packets) + tx_set_ic = 1; + else + tx_set_ic = 0; + + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + dma_desc = desc_data->dma_desc; + + /* Create a context descriptor if this is a TSO pkt_info */ + if (tso_context || vlan_context) { + if (tso_context) { + netif_dbg(pdata, tx_queued, pdata->netdev, + "TSO context descriptor, mss=%u\n", + pkt_info->mss); + + /* Set the MSS size */ + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_CONTEXT_DESC2_MSS_POS, + TX_CONTEXT_DESC2_MSS_LEN, + pkt_info->mss); + + /* Mark it as a CONTEXT descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_CTXT_POS, + TX_CONTEXT_DESC3_CTXT_LEN, + 1); + + /* Indicate this descriptor contains the MSS */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_TCMSSV_POS, + TX_CONTEXT_DESC3_TCMSSV_LEN, + 1); + + ring->tx.cur_mss = pkt_info->mss; + } + + if (vlan_context) { + netif_dbg(pdata, tx_queued, pdata->netdev, + "VLAN context descriptor, ctag=%u\n", + pkt_info->vlan_ctag); + + /* Mark it as a CONTEXT descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_CTXT_POS, + TX_CONTEXT_DESC3_CTXT_LEN, + 1); + + /* Set the VLAN tag */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_VT_POS, + TX_CONTEXT_DESC3_VT_LEN, + pkt_info->vlan_ctag); + + /* Indicate this descriptor contains the VLAN tag */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_CONTEXT_DESC3_VLTV_POS, + TX_CONTEXT_DESC3_VLTV_LEN, + 1); + + ring->tx.cur_vlan_ctag = pkt_info->vlan_ctag; + } + + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + dma_desc = desc_data->dma_desc; + } + + /* Update buffer address (for TSO this is the header) */ + dma_desc->desc0 = cpu_to_le32(lower_32_bits(desc_data->skb_dma)); + dma_desc->desc1 = cpu_to_le32(upper_32_bits(desc_data->skb_dma)); + + /* Update the buffer length */ + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_HL_B1L_POS, + TX_NORMAL_DESC2_HL_B1L_LEN, + desc_data->skb_dma_len); + + /* VLAN tag insertion check */ + if (vlan) + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_VTIR_POS, + TX_NORMAL_DESC2_VTIR_LEN, + TX_NORMAL_DESC2_VLAN_INSERT); + + /* Timestamp enablement check */ + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_PTP_POS, + TX_PACKET_ATTRIBUTES_PTP_LEN)) + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_TTSE_POS, + TX_NORMAL_DESC2_TTSE_LEN, + 1); + + /* Mark it as First Descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_FD_POS, + TX_NORMAL_DESC3_FD_LEN, + 1); + + /* Mark it as a NORMAL descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CTXT_POS, + TX_NORMAL_DESC3_CTXT_LEN, + 0); + + /* Set OWN bit if not the first descriptor */ + if (cur_index != start_index) + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN, + 1); + + if (tso) { + /* Enable TSO */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_TSE_POS, + TX_NORMAL_DESC3_TSE_LEN, 1); + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_TCPPL_POS, + TX_NORMAL_DESC3_TCPPL_LEN, + pkt_info->tcp_payload_len); + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_TCPHDRLEN_POS, + TX_NORMAL_DESC3_TCPHDRLEN_LEN, + pkt_info->tcp_header_len / 4); + + pdata->stats.tx_tso_packets++; + } else { + /* Enable CRC and Pad Insertion */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CPC_POS, + TX_NORMAL_DESC3_CPC_LEN, 0); + + /* Enable HW CSUM */ + if (csum) + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CIC_POS, + TX_NORMAL_DESC3_CIC_LEN, + 0x3); + + /* Set the total length to be transmitted */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_FL_POS, + TX_NORMAL_DESC3_FL_LEN, + pkt_info->length); + } + + for (i = cur_index - start_index + 1; i < pkt_info->desc_count; i++) { + cur_index++; + desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index); + dma_desc = desc_data->dma_desc; + + /* Update buffer address */ + dma_desc->desc0 = + cpu_to_le32(lower_32_bits(desc_data->skb_dma)); + dma_desc->desc1 = + cpu_to_le32(upper_32_bits(desc_data->skb_dma)); + + /* Update the buffer length */ + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_HL_B1L_POS, + TX_NORMAL_DESC2_HL_B1L_LEN, + desc_data->skb_dma_len); + + /* Set OWN bit */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN, 1); + + /* Mark it as NORMAL descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CTXT_POS, + TX_NORMAL_DESC3_CTXT_LEN, 0); + + /* Enable HW CSUM */ + if (csum) + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_CIC_POS, + TX_NORMAL_DESC3_CIC_LEN, + 0x3); + } + + /* Set LAST bit for the last descriptor */ + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_LD_POS, + TX_NORMAL_DESC3_LD_LEN, 1); + + /* Set IC bit based on Tx coalescing settings */ + if (tx_set_ic) + dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc2, + TX_NORMAL_DESC2_IC_POS, + TX_NORMAL_DESC2_IC_LEN, 1); + + /* Save the Tx info to report back during cleanup */ + desc_data->tx.packets = pkt_info->tx_packets; + desc_data->tx.bytes = pkt_info->tx_bytes; + + /* In case the Tx DMA engine is running, make sure everything + * is written to the descriptor(s) before setting the OWN bit + * for the first descriptor + */ + dma_wmb(); + + /* Set OWN bit for the first descriptor */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index); + dma_desc = desc_data->dma_desc; + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + TX_NORMAL_DESC3_OWN_POS, + TX_NORMAL_DESC3_OWN_LEN, 1); + + if (netif_msg_tx_queued(pdata)) + xlgmac_dump_tx_desc(pdata, ring, start_index, + pkt_info->desc_count, 1); + + /* Make sure ownership is written to the descriptor */ + smp_wmb(); + + ring->cur = cur_index + 1; + if (!pkt_info->skb->xmit_more || + netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev, + channel->queue_index))) + xlgmac_tx_start_xmit(channel, ring); + else + ring->tx.xmit_more = 1; + + XLGMAC_PR("%s: descriptors %u to %u written\n", + channel->name, start_index & (ring->dma_desc_count - 1), + (ring->cur - 1) & (ring->dma_desc_count - 1)); +} + +static void xlgmac_get_rx_tstamp(struct xlgmac_pkt_info *pkt_info, + struct xlgmac_dma_desc *dma_desc) +{ + u32 tsa, tsd; + u64 nsec; + + tsa = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_CONTEXT_DESC3_TSA_POS, + RX_CONTEXT_DESC3_TSA_LEN); + tsd = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_CONTEXT_DESC3_TSD_POS, + RX_CONTEXT_DESC3_TSD_LEN); + if (tsa && !tsd) { + nsec = le32_to_cpu(dma_desc->desc1); + nsec <<= 32; + nsec |= le32_to_cpu(dma_desc->desc0); + if (nsec != 0xffffffffffffffffULL) { + pkt_info->rx_tstamp = nsec; + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS, + RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN, + 1); + } + } +} + +static void xlgmac_tx_desc_reset(struct xlgmac_desc_data *desc_data) +{ + struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc; + + /* Reset the Tx descriptor + * Set buffer 1 (lo) address to zero + * Set buffer 1 (hi) address to zero + * Reset all other control bits (IC, TTSE, B2L & B1L) + * Reset all other control bits (OWN, CTXT, FD, LD, CPC, CIC, etc) + */ + dma_desc->desc0 = 0; + dma_desc->desc1 = 0; + dma_desc->desc2 = 0; + dma_desc->desc3 = 0; + + /* Make sure ownership is written to the descriptor */ + dma_wmb(); +} + +static void xlgmac_tx_desc_init(struct xlgmac_channel *channel) +{ + struct xlgmac_ring *ring = channel->tx_ring; + struct xlgmac_desc_data *desc_data; + int start_index = ring->cur; + int i; + + /* Initialze all descriptors */ + for (i = 0; i < ring->dma_desc_count; i++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, i); + + /* Initialize Tx descriptor */ + xlgmac_tx_desc_reset(desc_data); + } + + /* Update the total number of Tx descriptors */ + writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_TDRLR)); + + /* Update the starting address of descriptor ring */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index); + writel(upper_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_TDLR_HI)); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_TDLR_LO)); +} + +static void xlgmac_rx_desc_reset(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data, + unsigned int index) +{ + struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc; + unsigned int rx_frames = pdata->rx_frames; + unsigned int rx_usecs = pdata->rx_usecs; + dma_addr_t hdr_dma, buf_dma; + unsigned int inte; + + if (!rx_usecs && !rx_frames) { + /* No coalescing, interrupt for every descriptor */ + inte = 1; + } else { + /* Set interrupt based on Rx frame coalescing setting */ + if (rx_frames && !((index + 1) % rx_frames)) + inte = 1; + else + inte = 0; + } + + /* Reset the Rx descriptor + * Set buffer 1 (lo) address to header dma address (lo) + * Set buffer 1 (hi) address to header dma address (hi) + * Set buffer 2 (lo) address to buffer dma address (lo) + * Set buffer 2 (hi) address to buffer dma address (hi) and + * set control bits OWN and INTE + */ + hdr_dma = desc_data->rx.hdr.dma_base + desc_data->rx.hdr.dma_off; + buf_dma = desc_data->rx.buf.dma_base + desc_data->rx.buf.dma_off; + dma_desc->desc0 = cpu_to_le32(lower_32_bits(hdr_dma)); + dma_desc->desc1 = cpu_to_le32(upper_32_bits(hdr_dma)); + dma_desc->desc2 = cpu_to_le32(lower_32_bits(buf_dma)); + dma_desc->desc3 = cpu_to_le32(upper_32_bits(buf_dma)); + + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + RX_NORMAL_DESC3_INTE_POS, + RX_NORMAL_DESC3_INTE_LEN, + inte); + + /* Since the Rx DMA engine is likely running, make sure everything + * is written to the descriptor(s) before setting the OWN bit + * for the descriptor + */ + dma_wmb(); + + dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE( + dma_desc->desc3, + RX_NORMAL_DESC3_OWN_POS, + RX_NORMAL_DESC3_OWN_LEN, + 1); + + /* Make sure ownership is written to the descriptor */ + dma_wmb(); +} + +static void xlgmac_rx_desc_init(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + unsigned int start_index = ring->cur; + struct xlgmac_desc_data *desc_data; + unsigned int i; + + /* Initialize all descriptors */ + for (i = 0; i < ring->dma_desc_count; i++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, i); + + /* Initialize Rx descriptor */ + xlgmac_rx_desc_reset(pdata, desc_data, i); + } + + /* Update the total number of Rx descriptors */ + writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_RDRLR)); + + /* Update the starting address of descriptor ring */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index); + writel(upper_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDLR_HI)); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDLR_LO)); + + /* Update the Rx Descriptor Tail Pointer */ + desc_data = XLGMAC_GET_DESC_DATA(ring, start_index + + ring->dma_desc_count - 1); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO)); +} + +static int xlgmac_is_context_desc(struct xlgmac_dma_desc *dma_desc) +{ + /* Rx and Tx share CTXT bit, so check TDES3.CTXT bit */ + return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + TX_NORMAL_DESC3_CTXT_POS, + TX_NORMAL_DESC3_CTXT_LEN); +} + +static int xlgmac_is_last_desc(struct xlgmac_dma_desc *dma_desc) +{ + /* Rx and Tx share LD bit, so check TDES3.LD bit */ + return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + TX_NORMAL_DESC3_LD_POS, + TX_NORMAL_DESC3_LD_LEN); +} + +static int xlgmac_disable_tx_flow_control(struct xlgmac_pdata *pdata) +{ + unsigned int max_q_count, q_count; + unsigned int reg, regval; + unsigned int i; + + /* Clear MTL flow control */ + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS, + MTL_Q_RQOMR_EHFC_LEN, 0); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + /* Clear MAC flow control */ + max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES; + q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + reg = MAC_Q0TFCR; + for (i = 0; i < q_count; i++) { + regval = readl(pdata->mac_regs + reg); + regval = XLGMAC_SET_REG_BITS(regval, + MAC_Q0TFCR_TFE_POS, + MAC_Q0TFCR_TFE_LEN, + 0); + writel(regval, pdata->mac_regs + reg); + + reg += MAC_QTFCR_INC; + } + + return 0; +} + +static int xlgmac_enable_tx_flow_control(struct xlgmac_pdata *pdata) +{ + unsigned int max_q_count, q_count; + unsigned int reg, regval; + unsigned int i; + + /* Set MTL flow control */ + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS, + MTL_Q_RQOMR_EHFC_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + /* Set MAC flow control */ + max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES; + q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + reg = MAC_Q0TFCR; + for (i = 0; i < q_count; i++) { + regval = readl(pdata->mac_regs + reg); + + /* Enable transmit flow control */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_TFE_POS, + MAC_Q0TFCR_TFE_LEN, 1); + /* Set pause time */ + regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_PT_POS, + MAC_Q0TFCR_PT_LEN, 0xffff); + + writel(regval, pdata->mac_regs + reg); + + reg += MAC_QTFCR_INC; + } + + return 0; +} + +static int xlgmac_disable_rx_flow_control(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RFCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS, + MAC_RFCR_RFE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RFCR); + + return 0; +} + +static int xlgmac_enable_rx_flow_control(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MAC_RFCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS, + MAC_RFCR_RFE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RFCR); + + return 0; +} + +static int xlgmac_config_tx_flow_control(struct xlgmac_pdata *pdata) +{ + if (pdata->tx_pause) + xlgmac_enable_tx_flow_control(pdata); + else + xlgmac_disable_tx_flow_control(pdata); + + return 0; +} + +static int xlgmac_config_rx_flow_control(struct xlgmac_pdata *pdata) +{ + if (pdata->rx_pause) + xlgmac_enable_rx_flow_control(pdata); + else + xlgmac_disable_rx_flow_control(pdata); + + return 0; +} + +static int xlgmac_config_rx_coalesce(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RIWT)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RIWT_RWT_POS, + DMA_CH_RIWT_RWT_LEN, + pdata->rx_riwt); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RIWT)); + } + + return 0; +} + +static void xlgmac_config_flow_control(struct xlgmac_pdata *pdata) +{ + xlgmac_config_tx_flow_control(pdata); + xlgmac_config_rx_flow_control(pdata); +} + +static void xlgmac_config_rx_fep_enable(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FEP_POS, + MTL_Q_RQOMR_FEP_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } +} + +static void xlgmac_config_rx_fup_enable(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FUP_POS, + MTL_Q_RQOMR_FUP_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } +} + +static int xlgmac_config_tx_coalesce(struct xlgmac_pdata *pdata) +{ + return 0; +} + +static void xlgmac_config_rx_buffer_size(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_RBSZ_POS, + DMA_CH_RCR_RBSZ_LEN, + pdata->rx_buf_size); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } +} + +static void xlgmac_config_tso_mode(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + if (pdata->hw_feat.tso) { + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_TSE_POS, + DMA_CH_TCR_TSE_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + } +} + +static void xlgmac_config_sph_mode(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_SPH_POS, + DMA_CH_CR_SPH_LEN, 1); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR)); + } + + regval = readl(pdata->mac_regs + MAC_RCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_HDSMS_POS, + MAC_RCR_HDSMS_LEN, + XLGMAC_SPH_HDSMS_SIZE); + writel(regval, pdata->mac_regs + MAC_RCR); +} + +static unsigned int xlgmac_usec_to_riwt(struct xlgmac_pdata *pdata, + unsigned int usec) +{ + unsigned long rate; + unsigned int ret; + + rate = pdata->sysclk_rate; + + /* Convert the input usec value to the watchdog timer value. Each + * watchdog timer value is equivalent to 256 clock cycles. + * Calculate the required value as: + * ( usec * ( system_clock_mhz / 10^6 ) / 256 + */ + ret = (usec * (rate / 1000000)) / 256; + + return ret; +} + +static unsigned int xlgmac_riwt_to_usec(struct xlgmac_pdata *pdata, + unsigned int riwt) +{ + unsigned long rate; + unsigned int ret; + + rate = pdata->sysclk_rate; + + /* Convert the input watchdog timer value to the usec value. Each + * watchdog timer value is equivalent to 256 clock cycles. + * Calculate the required value as: + * ( riwt * 256 ) / ( system_clock_mhz / 10^6 ) + */ + ret = (riwt * 256) / (rate / 1000000); + + return ret; +} + +static int xlgmac_config_rx_threshold(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RTC_POS, + MTL_Q_RQOMR_RTC_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + return 0; +} + +static void xlgmac_config_mtl_mode(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + /* Set Tx to weighted round robin scheduling algorithm */ + regval = readl(pdata->mac_regs + MTL_OMR); + regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_ETSALG_POS, + MTL_OMR_ETSALG_LEN, MTL_ETSALG_WRR); + writel(regval, pdata->mac_regs + MTL_OMR); + + /* Set Tx traffic classes to use WRR algorithm with equal weights */ + for (i = 0; i < pdata->hw_feat.tc_cnt; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_ETSCR_TSA_POS, + MTL_TC_ETSCR_TSA_LEN, MTL_TSA_ETS); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR)); + + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_QWR_QW_POS, + MTL_TC_QWR_QW_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR)); + } + + /* Set Rx to strict priority algorithm */ + regval = readl(pdata->mac_regs + MTL_OMR); + regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_RAA_POS, + MTL_OMR_RAA_LEN, MTL_RAA_SP); + writel(regval, pdata->mac_regs + MTL_OMR); +} + +static void xlgmac_config_queue_mapping(struct xlgmac_pdata *pdata) +{ + unsigned int ppq, ppq_extra, prio, prio_queues; + unsigned int qptc, qptc_extra, queue; + unsigned int reg, regval; + unsigned int mask; + unsigned int i, j; + + /* Map the MTL Tx Queues to Traffic Classes + * Note: Tx Queues >= Traffic Classes + */ + qptc = pdata->tx_q_count / pdata->hw_feat.tc_cnt; + qptc_extra = pdata->tx_q_count % pdata->hw_feat.tc_cnt; + + for (i = 0, queue = 0; i < pdata->hw_feat.tc_cnt; i++) { + for (j = 0; j < qptc; j++) { + netif_dbg(pdata, drv, pdata->netdev, + "TXq%u mapped to TC%u\n", queue, i); + regval = readl(XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, + MTL_Q_TQOMR_Q2TCMAP_POS, + MTL_Q_TQOMR_Q2TCMAP_LEN, + i); + writel(regval, XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + queue++; + } + + if (i < qptc_extra) { + netif_dbg(pdata, drv, pdata->netdev, + "TXq%u mapped to TC%u\n", queue, i); + regval = readl(XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, + MTL_Q_TQOMR_Q2TCMAP_POS, + MTL_Q_TQOMR_Q2TCMAP_LEN, + i); + writel(regval, XLGMAC_MTL_REG(pdata, queue, + MTL_Q_TQOMR)); + queue++; + } + } + + /* Map the 8 VLAN priority values to available MTL Rx queues */ + prio_queues = min_t(unsigned int, IEEE_8021QAZ_MAX_TCS, + pdata->rx_q_count); + ppq = IEEE_8021QAZ_MAX_TCS / prio_queues; + ppq_extra = IEEE_8021QAZ_MAX_TCS % prio_queues; + + reg = MAC_RQC2R; + regval = 0; + for (i = 0, prio = 0; i < prio_queues;) { + mask = 0; + for (j = 0; j < ppq; j++) { + netif_dbg(pdata, drv, pdata->netdev, + "PRIO%u mapped to RXq%u\n", prio, i); + mask |= (1 << prio); + prio++; + } + + if (i < ppq_extra) { + netif_dbg(pdata, drv, pdata->netdev, + "PRIO%u mapped to RXq%u\n", prio, i); + mask |= (1 << prio); + prio++; + } + + regval |= (mask << ((i++ % MAC_RQC2_Q_PER_REG) << 3)); + + if ((i % MAC_RQC2_Q_PER_REG) && (i != prio_queues)) + continue; + + writel(regval, pdata->mac_regs + reg); + reg += MAC_RQC2_INC; + regval = 0; + } + + /* Configure one to one, MTL Rx queue to DMA Rx channel mapping + * ie Q0 <--> CH0, Q1 <--> CH1 ... Q11 <--> CH11 + */ + reg = MTL_RQDCM0R; + regval = readl(pdata->mac_regs + reg); + regval |= (MTL_RQDCM0R_Q0MDMACH | MTL_RQDCM0R_Q1MDMACH | + MTL_RQDCM0R_Q2MDMACH | MTL_RQDCM0R_Q3MDMACH); + writel(regval, pdata->mac_regs + reg); + + reg += MTL_RQDCM_INC; + regval = readl(pdata->mac_regs + reg); + regval |= (MTL_RQDCM1R_Q4MDMACH | MTL_RQDCM1R_Q5MDMACH | + MTL_RQDCM1R_Q6MDMACH | MTL_RQDCM1R_Q7MDMACH); + writel(regval, pdata->mac_regs + reg); + + reg += MTL_RQDCM_INC; + regval = readl(pdata->mac_regs + reg); + regval |= (MTL_RQDCM2R_Q8MDMACH | MTL_RQDCM2R_Q9MDMACH | + MTL_RQDCM2R_Q10MDMACH | MTL_RQDCM2R_Q11MDMACH); + writel(regval, pdata->mac_regs + reg); +} + +static unsigned int xlgmac_calculate_per_queue_fifo( + unsigned int fifo_size, + unsigned int queue_count) +{ + unsigned int q_fifo_size; + unsigned int p_fifo; + + /* Calculate the configured fifo size */ + q_fifo_size = 1 << (fifo_size + 7); + + /* The configured value may not be the actual amount of fifo RAM */ + q_fifo_size = min_t(unsigned int, XLGMAC_MAX_FIFO, q_fifo_size); + + q_fifo_size = q_fifo_size / queue_count; + + /* Each increment in the queue fifo size represents 256 bytes of + * fifo, with 0 representing 256 bytes. Distribute the fifo equally + * between the queues. + */ + p_fifo = q_fifo_size / 256; + if (p_fifo) + p_fifo--; + + return p_fifo; +} + +static void xlgmac_config_tx_fifo_size(struct xlgmac_pdata *pdata) +{ + unsigned int fifo_size; + unsigned int i; + u32 regval; + + fifo_size = xlgmac_calculate_per_queue_fifo( + pdata->hw_feat.tx_fifo_size, + pdata->tx_q_count); + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TQS_POS, + MTL_Q_TQOMR_TQS_LEN, fifo_size); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + netif_info(pdata, drv, pdata->netdev, + "%d Tx hardware queues, %d byte fifo per queue\n", + pdata->tx_q_count, ((fifo_size + 1) * 256)); +} + +static void xlgmac_config_rx_fifo_size(struct xlgmac_pdata *pdata) +{ + unsigned int fifo_size; + unsigned int i; + u32 regval; + + fifo_size = xlgmac_calculate_per_queue_fifo( + pdata->hw_feat.rx_fifo_size, + pdata->rx_q_count); + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RQS_POS, + MTL_Q_RQOMR_RQS_LEN, fifo_size); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + netif_info(pdata, drv, pdata->netdev, + "%d Rx hardware queues, %d byte fifo per queue\n", + pdata->rx_q_count, ((fifo_size + 1) * 256)); +} + +static void xlgmac_config_flow_control_threshold(struct xlgmac_pdata *pdata) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR)); + /* Activate flow control when less than 4k left in fifo */ + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFA_POS, + MTL_Q_RQFCR_RFA_LEN, 2); + /* De-activate flow control when more than 6k left in fifo */ + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFD_POS, + MTL_Q_RQFCR_RFD_LEN, 4); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR)); + } +} + +static int xlgmac_config_tx_threshold(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TTC_POS, + MTL_Q_TQOMR_TTC_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + return 0; +} + +static int xlgmac_config_rsf_mode(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->rx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RSF_POS, + MTL_Q_RQOMR_RSF_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR)); + } + + return 0; +} + +static int xlgmac_config_tsf_mode(struct xlgmac_pdata *pdata, + unsigned int val) +{ + unsigned int i; + u32 regval; + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TSF_POS, + MTL_Q_TQOMR_TSF_LEN, val); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + return 0; +} + +static int xlgmac_config_osp_mode(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_OSP_POS, + DMA_CH_TCR_OSP_LEN, + pdata->tx_osp_mode); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + + return 0; +} + +static int xlgmac_config_pblx8(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_PBLX8_POS, + DMA_CH_CR_PBLX8_LEN, + pdata->pblx8); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR)); + } + + return 0; +} + +static int xlgmac_get_tx_pbl_val(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_TCR)); + regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_TCR_PBL_POS, + DMA_CH_TCR_PBL_LEN); + return regval; +} + +static int xlgmac_config_tx_pbl_val(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_PBL_POS, + DMA_CH_TCR_PBL_LEN, + pdata->tx_pbl); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR)); + } + + return 0; +} + +static int xlgmac_get_rx_pbl_val(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_RCR)); + regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_RCR_PBL_POS, + DMA_CH_RCR_PBL_LEN); + return regval; +} + +static int xlgmac_config_rx_pbl_val(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + u32 regval; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->rx_ring) + break; + + regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_PBL_POS, + DMA_CH_RCR_PBL_LEN, + pdata->rx_pbl); + writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR)); + } + + return 0; +} + +static u64 xlgmac_mmc_read(struct xlgmac_pdata *pdata, unsigned int reg_lo) +{ + bool read_hi; + u64 val; + + switch (reg_lo) { + /* These registers are always 64 bit */ + case MMC_TXOCTETCOUNT_GB_LO: + case MMC_TXOCTETCOUNT_G_LO: + case MMC_RXOCTETCOUNT_GB_LO: + case MMC_RXOCTETCOUNT_G_LO: + read_hi = true; + break; + + default: + read_hi = false; + } + + val = (u64)readl(pdata->mac_regs + reg_lo); + + if (read_hi) + val |= ((u64)readl(pdata->mac_regs + reg_lo + 4) << 32); + + return val; +} + +static void xlgmac_tx_mmc_int(struct xlgmac_pdata *pdata) +{ + unsigned int mmc_isr = readl(pdata->mac_regs + MMC_TISR); + struct xlgmac_stats *stats = &pdata->stats; + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXOCTETCOUNT_GB_POS, + MMC_TISR_TXOCTETCOUNT_GB_LEN)) + stats->txoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXFRAMECOUNT_GB_POS, + MMC_TISR_TXFRAMECOUNT_GB_LEN)) + stats->txframecount_gb += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXBROADCASTFRAMES_G_POS, + MMC_TISR_TXBROADCASTFRAMES_G_LEN)) + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXMULTICASTFRAMES_G_POS, + MMC_TISR_TXMULTICASTFRAMES_G_LEN)) + stats->txmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX64OCTETS_GB_POS, + MMC_TISR_TX64OCTETS_GB_LEN)) + stats->tx64octets_gb += + xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX65TO127OCTETS_GB_POS, + MMC_TISR_TX65TO127OCTETS_GB_LEN)) + stats->tx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX128TO255OCTETS_GB_POS, + MMC_TISR_TX128TO255OCTETS_GB_LEN)) + stats->tx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX256TO511OCTETS_GB_POS, + MMC_TISR_TX256TO511OCTETS_GB_LEN)) + stats->tx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX512TO1023OCTETS_GB_POS, + MMC_TISR_TX512TO1023OCTETS_GB_LEN)) + stats->tx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TX1024TOMAXOCTETS_GB_POS, + MMC_TISR_TX1024TOMAXOCTETS_GB_LEN)) + stats->tx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXUNICASTFRAMES_GB_POS, + MMC_TISR_TXUNICASTFRAMES_GB_LEN)) + stats->txunicastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXMULTICASTFRAMES_GB_POS, + MMC_TISR_TXMULTICASTFRAMES_GB_LEN)) + stats->txmulticastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXBROADCASTFRAMES_GB_POS, + MMC_TISR_TXBROADCASTFRAMES_GB_LEN)) + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXUNDERFLOWERROR_POS, + MMC_TISR_TXUNDERFLOWERROR_LEN)) + stats->txunderflowerror += + xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXOCTETCOUNT_G_POS, + MMC_TISR_TXOCTETCOUNT_G_LEN)) + stats->txoctetcount_g += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXFRAMECOUNT_G_POS, + MMC_TISR_TXFRAMECOUNT_G_LEN)) + stats->txframecount_g += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXPAUSEFRAMES_POS, + MMC_TISR_TXPAUSEFRAMES_LEN)) + stats->txpauseframes += + xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_TISR_TXVLANFRAMES_G_POS, + MMC_TISR_TXVLANFRAMES_G_LEN)) + stats->txvlanframes_g += + xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO); +} + +static void xlgmac_rx_mmc_int(struct xlgmac_pdata *pdata) +{ + unsigned int mmc_isr = readl(pdata->mac_regs + MMC_RISR); + struct xlgmac_stats *stats = &pdata->stats; + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXFRAMECOUNT_GB_POS, + MMC_RISR_RXFRAMECOUNT_GB_LEN)) + stats->rxframecount_gb += + xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOCTETCOUNT_GB_POS, + MMC_RISR_RXOCTETCOUNT_GB_LEN)) + stats->rxoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOCTETCOUNT_G_POS, + MMC_RISR_RXOCTETCOUNT_G_LEN)) + stats->rxoctetcount_g += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXBROADCASTFRAMES_G_POS, + MMC_RISR_RXBROADCASTFRAMES_G_LEN)) + stats->rxbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXMULTICASTFRAMES_G_POS, + MMC_RISR_RXMULTICASTFRAMES_G_LEN)) + stats->rxmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXCRCERROR_POS, + MMC_RISR_RXCRCERROR_LEN)) + stats->rxcrcerror += + xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXRUNTERROR_POS, + MMC_RISR_RXRUNTERROR_LEN)) + stats->rxrunterror += + xlgmac_mmc_read(pdata, MMC_RXRUNTERROR); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXJABBERERROR_POS, + MMC_RISR_RXJABBERERROR_LEN)) + stats->rxjabbererror += + xlgmac_mmc_read(pdata, MMC_RXJABBERERROR); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXUNDERSIZE_G_POS, + MMC_RISR_RXUNDERSIZE_G_LEN)) + stats->rxundersize_g += + xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOVERSIZE_G_POS, + MMC_RISR_RXOVERSIZE_G_LEN)) + stats->rxoversize_g += + xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX64OCTETS_GB_POS, + MMC_RISR_RX64OCTETS_GB_LEN)) + stats->rx64octets_gb += + xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX65TO127OCTETS_GB_POS, + MMC_RISR_RX65TO127OCTETS_GB_LEN)) + stats->rx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX128TO255OCTETS_GB_POS, + MMC_RISR_RX128TO255OCTETS_GB_LEN)) + stats->rx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX256TO511OCTETS_GB_POS, + MMC_RISR_RX256TO511OCTETS_GB_LEN)) + stats->rx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX512TO1023OCTETS_GB_POS, + MMC_RISR_RX512TO1023OCTETS_GB_LEN)) + stats->rx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RX1024TOMAXOCTETS_GB_POS, + MMC_RISR_RX1024TOMAXOCTETS_GB_LEN)) + stats->rx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXUNICASTFRAMES_G_POS, + MMC_RISR_RXUNICASTFRAMES_G_LEN)) + stats->rxunicastframes_g += + xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXLENGTHERROR_POS, + MMC_RISR_RXLENGTHERROR_LEN)) + stats->rxlengtherror += + xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXOUTOFRANGETYPE_POS, + MMC_RISR_RXOUTOFRANGETYPE_LEN)) + stats->rxoutofrangetype += + xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXPAUSEFRAMES_POS, + MMC_RISR_RXPAUSEFRAMES_LEN)) + stats->rxpauseframes += + xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXFIFOOVERFLOW_POS, + MMC_RISR_RXFIFOOVERFLOW_LEN)) + stats->rxfifooverflow += + xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXVLANFRAMES_GB_POS, + MMC_RISR_RXVLANFRAMES_GB_LEN)) + stats->rxvlanframes_gb += + xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO); + + if (XLGMAC_GET_REG_BITS(mmc_isr, + MMC_RISR_RXWATCHDOGERROR_POS, + MMC_RISR_RXWATCHDOGERROR_LEN)) + stats->rxwatchdogerror += + xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR); +} + +static void xlgmac_read_mmc_stats(struct xlgmac_pdata *pdata) +{ + struct xlgmac_stats *stats = &pdata->stats; + u32 regval; + + /* Freeze counters */ + regval = readl(pdata->mac_regs + MMC_CR); + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS, + MMC_CR_MCF_LEN, 1); + writel(regval, pdata->mac_regs + MMC_CR); + + stats->txoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO); + + stats->txframecount_gb += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO); + + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO); + + stats->txmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO); + + stats->tx64octets_gb += + xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO); + + stats->tx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO); + + stats->tx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO); + + stats->tx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO); + + stats->tx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO); + + stats->tx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); + + stats->txunicastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO); + + stats->txmulticastframes_gb += + xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO); + + stats->txbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO); + + stats->txunderflowerror += + xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO); + + stats->txoctetcount_g += + xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO); + + stats->txframecount_g += + xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO); + + stats->txpauseframes += + xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO); + + stats->txvlanframes_g += + xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO); + + stats->rxframecount_gb += + xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO); + + stats->rxoctetcount_gb += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO); + + stats->rxoctetcount_g += + xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO); + + stats->rxbroadcastframes_g += + xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO); + + stats->rxmulticastframes_g += + xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO); + + stats->rxcrcerror += + xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO); + + stats->rxrunterror += + xlgmac_mmc_read(pdata, MMC_RXRUNTERROR); + + stats->rxjabbererror += + xlgmac_mmc_read(pdata, MMC_RXJABBERERROR); + + stats->rxundersize_g += + xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G); + + stats->rxoversize_g += + xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G); + + stats->rx64octets_gb += + xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO); + + stats->rx65to127octets_gb += + xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO); + + stats->rx128to255octets_gb += + xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO); + + stats->rx256to511octets_gb += + xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO); + + stats->rx512to1023octets_gb += + xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO); + + stats->rx1024tomaxoctets_gb += + xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); + + stats->rxunicastframes_g += + xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO); + + stats->rxlengtherror += + xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO); + + stats->rxoutofrangetype += + xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO); + + stats->rxpauseframes += + xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO); + + stats->rxfifooverflow += + xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO); + + stats->rxvlanframes_gb += + xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO); + + stats->rxwatchdogerror += + xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR); + + /* Un-freeze counters */ + regval = readl(pdata->mac_regs + MMC_CR); + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS, + MMC_CR_MCF_LEN, 0); + writel(regval, pdata->mac_regs + MMC_CR); +} + +static void xlgmac_config_mmc(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + MMC_CR); + /* Set counters to reset on read */ + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_ROR_POS, + MMC_CR_ROR_LEN, 1); + /* Reset the counters */ + regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_CR_POS, + MMC_CR_CR_LEN, 1); + writel(regval, pdata->mac_regs + MMC_CR); +} + +static int xlgmac_write_rss_reg(struct xlgmac_pdata *pdata, unsigned int type, + unsigned int index, unsigned int val) +{ + unsigned int wait; + int ret = 0; + u32 regval; + + mutex_lock(&pdata->rss_mutex); + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR), + MAC_RSSAR_OB_POS, MAC_RSSAR_OB_LEN); + if (regval) { + ret = -EBUSY; + goto unlock; + } + + writel(val, pdata->mac_regs + MAC_RSSDR); + + regval = readl(pdata->mac_regs + MAC_RSSAR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_RSSIA_POS, + MAC_RSSAR_RSSIA_LEN, index); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_ADDRT_POS, + MAC_RSSAR_ADDRT_LEN, type); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_CT_POS, + MAC_RSSAR_CT_LEN, 0); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_OB_POS, + MAC_RSSAR_OB_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RSSAR); + + wait = 1000; + while (wait--) { + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR), + MAC_RSSAR_OB_POS, + MAC_RSSAR_OB_LEN); + if (!regval) + goto unlock; + + usleep_range(1000, 1500); + } + + ret = -EBUSY; + +unlock: + mutex_unlock(&pdata->rss_mutex); + + return ret; +} + +static int xlgmac_write_rss_hash_key(struct xlgmac_pdata *pdata) +{ + unsigned int key_regs = sizeof(pdata->rss_key) / sizeof(u32); + unsigned int *key = (unsigned int *)&pdata->rss_key; + int ret; + + while (key_regs--) { + ret = xlgmac_write_rss_reg(pdata, XLGMAC_RSS_HASH_KEY_TYPE, + key_regs, *key++); + if (ret) + return ret; + } + + return 0; +} + +static int xlgmac_write_rss_lookup_table(struct xlgmac_pdata *pdata) +{ + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) { + ret = xlgmac_write_rss_reg(pdata, + XLGMAC_RSS_LOOKUP_TABLE_TYPE, i, + pdata->rss_table[i]); + if (ret) + return ret; + } + + return 0; +} + +static int xlgmac_set_rss_hash_key(struct xlgmac_pdata *pdata, const u8 *key) +{ + memcpy(pdata->rss_key, key, sizeof(pdata->rss_key)); + + return xlgmac_write_rss_hash_key(pdata); +} + +static int xlgmac_set_rss_lookup_table(struct xlgmac_pdata *pdata, + const u32 *table) +{ + unsigned int i; + u32 tval; + + for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) { + tval = table[i]; + pdata->rss_table[i] = XLGMAC_SET_REG_BITS( + pdata->rss_table[i], + MAC_RSSDR_DMCH_POS, + MAC_RSSDR_DMCH_LEN, + tval); + } + + return xlgmac_write_rss_lookup_table(pdata); +} + +static int xlgmac_enable_rss(struct xlgmac_pdata *pdata) +{ + u32 regval; + int ret; + + if (!pdata->hw_feat.rss) + return -EOPNOTSUPP; + + /* Program the hash key */ + ret = xlgmac_write_rss_hash_key(pdata); + if (ret) + return ret; + + /* Program the lookup table */ + ret = xlgmac_write_rss_lookup_table(pdata); + if (ret) + return ret; + + /* Set the RSS options */ + writel(pdata->rss_options, pdata->mac_regs + MAC_RSSCR); + + /* Enable RSS */ + regval = readl(pdata->mac_regs + MAC_RSSCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS, + MAC_RSSCR_RSSE_LEN, 1); + writel(regval, pdata->mac_regs + MAC_RSSCR); + + return 0; +} + +static int xlgmac_disable_rss(struct xlgmac_pdata *pdata) +{ + u32 regval; + + if (!pdata->hw_feat.rss) + return -EOPNOTSUPP; + + regval = readl(pdata->mac_regs + MAC_RSSCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS, + MAC_RSSCR_RSSE_LEN, 0); + writel(regval, pdata->mac_regs + MAC_RSSCR); + + return 0; +} + +static void xlgmac_config_rss(struct xlgmac_pdata *pdata) +{ + int ret; + + if (!pdata->hw_feat.rss) + return; + + if (pdata->netdev->features & NETIF_F_RXHASH) + ret = xlgmac_enable_rss(pdata); + else + ret = xlgmac_disable_rss(pdata); + + if (ret) + netdev_err(pdata->netdev, + "error configuring RSS, RSS disabled\n"); +} + +static void xlgmac_enable_dma_interrupts(struct xlgmac_pdata *pdata) +{ + unsigned int dma_ch_isr, dma_ch_ier; + struct xlgmac_channel *channel; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + /* Clear all the interrupts which are set */ + dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR)); + writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR)); + + /* Clear all interrupt enable bits */ + dma_ch_ier = 0; + + /* Enable following interrupts + * NIE - Normal Interrupt Summary Enable + * AIE - Abnormal Interrupt Summary Enable + * FBEE - Fatal Bus Error Enable + */ + dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier, + DMA_CH_IER_NIE_POS, + DMA_CH_IER_NIE_LEN, 1); + dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier, + DMA_CH_IER_AIE_POS, + DMA_CH_IER_AIE_LEN, 1); + dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier, + DMA_CH_IER_FBEE_POS, + DMA_CH_IER_FBEE_LEN, 1); + + if (channel->tx_ring) { + /* Enable the following Tx interrupts + * TIE - Transmit Interrupt Enable (unless using + * per channel interrupts) + */ + if (!pdata->per_channel_irq) + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, + DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, + 1); + } + if (channel->rx_ring) { + /* Enable following Rx interrupts + * RBUE - Receive Buffer Unavailable Enable + * RIE - Receive Interrupt Enable (unless using + * per channel interrupts) + */ + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, + DMA_CH_IER_RBUE_POS, + DMA_CH_IER_RBUE_LEN, + 1); + if (!pdata->per_channel_irq) + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, + DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, + 1); + } + + writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_IER)); + } +} + +static void xlgmac_enable_mtl_interrupts(struct xlgmac_pdata *pdata) +{ + unsigned int q_count, i; + unsigned int mtl_q_isr; + + q_count = max(pdata->hw_feat.tx_q_cnt, pdata->hw_feat.rx_q_cnt); + for (i = 0; i < q_count; i++) { + /* Clear all the interrupts which are set */ + mtl_q_isr = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR)); + writel(mtl_q_isr, XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR)); + + /* No MTL interrupts to be enabled */ + writel(0, XLGMAC_MTL_REG(pdata, i, MTL_Q_IER)); + } +} + +static void xlgmac_enable_mac_interrupts(struct xlgmac_pdata *pdata) +{ + unsigned int mac_ier = 0; + u32 regval; + + /* Enable Timestamp interrupt */ + mac_ier = XLGMAC_SET_REG_BITS(mac_ier, MAC_IER_TSIE_POS, + MAC_IER_TSIE_LEN, 1); + + writel(mac_ier, pdata->mac_regs + MAC_IER); + + /* Enable all counter interrupts */ + regval = readl(pdata->mac_regs + MMC_RIER); + regval = XLGMAC_SET_REG_BITS(regval, MMC_RIER_ALL_INTERRUPTS_POS, + MMC_RIER_ALL_INTERRUPTS_LEN, 0xffffffff); + writel(regval, pdata->mac_regs + MMC_RIER); + regval = readl(pdata->mac_regs + MMC_TIER); + regval = XLGMAC_SET_REG_BITS(regval, MMC_TIER_ALL_INTERRUPTS_POS, + MMC_TIER_ALL_INTERRUPTS_LEN, 0xffffffff); + writel(regval, pdata->mac_regs + MMC_TIER); +} + +static int xlgmac_set_xlgmii_25000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0x1) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0x1); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static int xlgmac_set_xlgmii_40000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static int xlgmac_set_xlgmii_50000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0x2) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0x2); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static int xlgmac_set_xlgmii_100000_speed(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR), + MAC_TCR_SS_POS, MAC_TCR_SS_LEN); + if (regval == 0x3) + return 0; + + regval = readl(pdata->mac_regs + MAC_TCR); + regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS, + MAC_TCR_SS_LEN, 0x3); + writel(regval, pdata->mac_regs + MAC_TCR); + + return 0; +} + +static void xlgmac_config_mac_speed(struct xlgmac_pdata *pdata) +{ + switch (pdata->phy_speed) { + case SPEED_100000: + xlgmac_set_xlgmii_100000_speed(pdata); + break; + + case SPEED_50000: + xlgmac_set_xlgmii_50000_speed(pdata); + break; + + case SPEED_40000: + xlgmac_set_xlgmii_40000_speed(pdata); + break; + + case SPEED_25000: + xlgmac_set_xlgmii_25000_speed(pdata); + break; + } +} + +static int xlgmac_dev_read(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + struct net_device *netdev = pdata->netdev; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_pkt_info *pkt_info; + unsigned int err, etlt, l34t; + + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + dma_desc = desc_data->dma_desc; + pkt_info = &ring->pkt_info; + + /* Check for data availability */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_OWN_POS, + RX_NORMAL_DESC3_OWN_LEN)) + return 1; + + /* Make sure descriptor fields are read after reading the OWN bit */ + dma_rmb(); + + if (netif_msg_rx_status(pdata)) + xlgmac_dump_rx_desc(pdata, ring, ring->cur); + + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_CTXT_POS, + RX_NORMAL_DESC3_CTXT_LEN)) { + /* Timestamp Context Descriptor */ + xlgmac_get_rx_tstamp(pkt_info, dma_desc); + + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_LEN, + 1); + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN, + 0); + return 0; + } + + /* Normal Descriptor, be sure Context Descriptor bit is off */ + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_LEN, + 0); + + /* Indicate if a Context Descriptor is next */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_CDA_POS, + RX_NORMAL_DESC3_CDA_LEN)) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN, + 1); + + /* Get the header length */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_FD_POS, + RX_NORMAL_DESC3_FD_LEN)) { + desc_data->rx.hdr_len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc2, + RX_NORMAL_DESC2_HL_POS, + RX_NORMAL_DESC2_HL_LEN); + if (desc_data->rx.hdr_len) + pdata->stats.rx_split_header_packets++; + } + + /* Get the RSS hash */ + if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_RSV_POS, + RX_NORMAL_DESC3_RSV_LEN)) { + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_RSS_HASH_POS, + RX_PACKET_ATTRIBUTES_RSS_HASH_LEN, + 1); + + pkt_info->rss_hash = le32_to_cpu(dma_desc->desc1); + + l34t = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_L34T_POS, + RX_NORMAL_DESC3_L34T_LEN); + switch (l34t) { + case RX_DESC3_L34T_IPV4_TCP: + case RX_DESC3_L34T_IPV4_UDP: + case RX_DESC3_L34T_IPV6_TCP: + case RX_DESC3_L34T_IPV6_UDP: + pkt_info->rss_hash_type = PKT_HASH_TYPE_L4; + break; + default: + pkt_info->rss_hash_type = PKT_HASH_TYPE_L3; + } + } + + /* Get the pkt_info length */ + desc_data->rx.len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_PL_POS, + RX_NORMAL_DESC3_PL_LEN); + + if (!XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_LD_POS, + RX_NORMAL_DESC3_LD_LEN)) { + /* Not all the data has been transferred for this pkt_info */ + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_INCOMPLETE_POS, + RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN, + 1); + return 0; + } + + /* This is the last of the data for this pkt_info */ + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_INCOMPLETE_POS, + RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN, + 0); + + /* Set checksum done indicator as appropriate */ + if (netdev->features & NETIF_F_RXCSUM) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CSUM_DONE_POS, + RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN, + 1); + + /* Check for errors (only valid in last descriptor) */ + err = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_ES_POS, + RX_NORMAL_DESC3_ES_LEN); + etlt = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3, + RX_NORMAL_DESC3_ETLT_POS, + RX_NORMAL_DESC3_ETLT_LEN); + netif_dbg(pdata, rx_status, netdev, "err=%u, etlt=%#x\n", err, etlt); + + if (!err || !etlt) { + /* No error if err is 0 or etlt is 0 */ + if ((etlt == 0x09) && + (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) { + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN, + 1); + pkt_info->vlan_ctag = + XLGMAC_GET_REG_BITS_LE(dma_desc->desc0, + RX_NORMAL_DESC0_OVT_POS, + RX_NORMAL_DESC0_OVT_LEN); + netif_dbg(pdata, rx_status, netdev, "vlan-ctag=%#06x\n", + pkt_info->vlan_ctag); + } + } else { + if ((etlt == 0x05) || (etlt == 0x06)) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CSUM_DONE_POS, + RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN, + 0); + else + pkt_info->errors = XLGMAC_SET_REG_BITS( + pkt_info->errors, + RX_PACKET_ERRORS_FRAME_POS, + RX_PACKET_ERRORS_FRAME_LEN, + 1); + } + + XLGMAC_PR("%s - descriptor=%u (cur=%d)\n", channel->name, + ring->cur & (ring->dma_desc_count - 1), ring->cur); + + return 0; +} + +static int xlgmac_enable_int(struct xlgmac_channel *channel, + enum xlgmac_int int_id) +{ + unsigned int dma_ch_ier; + + dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + switch (int_id) { + case XLGMAC_INT_DMA_CH_SR_TI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_TPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TXSE_POS, + DMA_CH_IER_TXSE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_TBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TBUE_POS, + DMA_CH_IER_TBUE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_RBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RBUE_POS, + DMA_CH_IER_RBUE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_RPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RSE_POS, + DMA_CH_IER_RSE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_TI_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 1); + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 1); + break; + case XLGMAC_INT_DMA_CH_SR_FBE: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_FBEE_POS, + DMA_CH_IER_FBEE_LEN, 1); + break; + case XLGMAC_INT_DMA_ALL: + dma_ch_ier |= channel->saved_ier; + break; + default: + return -1; + } + + writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + return 0; +} + +static int xlgmac_disable_int(struct xlgmac_channel *channel, + enum xlgmac_int int_id) +{ + unsigned int dma_ch_ier; + + dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + switch (int_id) { + case XLGMAC_INT_DMA_CH_SR_TI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_TPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TXSE_POS, + DMA_CH_IER_TXSE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_TBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TBUE_POS, + DMA_CH_IER_TBUE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_RBU: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RBUE_POS, + DMA_CH_IER_RBUE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_RPS: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RSE_POS, + DMA_CH_IER_RSE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_TI_RI: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_TIE_POS, + DMA_CH_IER_TIE_LEN, 0); + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_RIE_POS, + DMA_CH_IER_RIE_LEN, 0); + break; + case XLGMAC_INT_DMA_CH_SR_FBE: + dma_ch_ier = XLGMAC_SET_REG_BITS( + dma_ch_ier, DMA_CH_IER_FBEE_POS, + DMA_CH_IER_FBEE_LEN, 0); + break; + case XLGMAC_INT_DMA_ALL: + channel->saved_ier = dma_ch_ier & XLGMAC_DMA_INTERRUPT_MASK; + dma_ch_ier &= ~XLGMAC_DMA_INTERRUPT_MASK; + break; + default: + return -1; + } + + writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER)); + + return 0; +} + +static int xlgmac_flush_tx_queues(struct xlgmac_pdata *pdata) +{ + unsigned int i, count; + u32 regval; + + for (i = 0; i < pdata->tx_q_count; i++) { + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS, + MTL_Q_TQOMR_FTQ_LEN, 1); + writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + } + + /* Poll Until Poll Condition */ + for (i = 0; i < pdata->tx_q_count; i++) { + count = 2000; + regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR)); + regval = XLGMAC_GET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS, + MTL_Q_TQOMR_FTQ_LEN); + while (--count && regval) + usleep_range(500, 600); + + if (!count) + return -EBUSY; + } + + return 0; +} + +static void xlgmac_config_dma_bus(struct xlgmac_pdata *pdata) +{ + u32 regval; + + regval = readl(pdata->mac_regs + DMA_SBMR); + /* Set enhanced addressing mode */ + regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_EAME_POS, + DMA_SBMR_EAME_LEN, 1); + /* Set the System Bus mode */ + regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_UNDEF_POS, + DMA_SBMR_UNDEF_LEN, 1); + regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_BLEN_256_POS, + DMA_SBMR_BLEN_256_LEN, 1); + writel(regval, pdata->mac_regs + DMA_SBMR); +} + +static int xlgmac_hw_init(struct xlgmac_pdata *pdata) +{ + struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops; + int ret; + + /* Flush Tx queues */ + ret = xlgmac_flush_tx_queues(pdata); + if (ret) + return ret; + + /* Initialize DMA related features */ + xlgmac_config_dma_bus(pdata); + xlgmac_config_osp_mode(pdata); + xlgmac_config_pblx8(pdata); + xlgmac_config_tx_pbl_val(pdata); + xlgmac_config_rx_pbl_val(pdata); + xlgmac_config_rx_coalesce(pdata); + xlgmac_config_tx_coalesce(pdata); + xlgmac_config_rx_buffer_size(pdata); + xlgmac_config_tso_mode(pdata); + xlgmac_config_sph_mode(pdata); + xlgmac_config_rss(pdata); + desc_ops->tx_desc_init(pdata); + desc_ops->rx_desc_init(pdata); + xlgmac_enable_dma_interrupts(pdata); + + /* Initialize MTL related features */ + xlgmac_config_mtl_mode(pdata); + xlgmac_config_queue_mapping(pdata); + xlgmac_config_tsf_mode(pdata, pdata->tx_sf_mode); + xlgmac_config_rsf_mode(pdata, pdata->rx_sf_mode); + xlgmac_config_tx_threshold(pdata, pdata->tx_threshold); + xlgmac_config_rx_threshold(pdata, pdata->rx_threshold); + xlgmac_config_tx_fifo_size(pdata); + xlgmac_config_rx_fifo_size(pdata); + xlgmac_config_flow_control_threshold(pdata); + xlgmac_config_rx_fep_enable(pdata); + xlgmac_config_rx_fup_enable(pdata); + xlgmac_enable_mtl_interrupts(pdata); + + /* Initialize MAC related features */ + xlgmac_config_mac_address(pdata); + xlgmac_config_rx_mode(pdata); + xlgmac_config_jumbo_enable(pdata); + xlgmac_config_flow_control(pdata); + xlgmac_config_mac_speed(pdata); + xlgmac_config_checksum_offload(pdata); + xlgmac_config_vlan_support(pdata); + xlgmac_config_mmc(pdata); + xlgmac_enable_mac_interrupts(pdata); + + return 0; +} + +static int xlgmac_hw_exit(struct xlgmac_pdata *pdata) +{ + unsigned int count = 2000; + u32 regval; + + /* Issue a software reset */ + regval = readl(pdata->mac_regs + DMA_MR); + regval = XLGMAC_SET_REG_BITS(regval, DMA_MR_SWR_POS, + DMA_MR_SWR_LEN, 1); + writel(regval, pdata->mac_regs + DMA_MR); + usleep_range(10, 15); + + /* Poll Until Poll Condition */ + while (--count && + XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + DMA_MR), + DMA_MR_SWR_POS, DMA_MR_SWR_LEN)) + usleep_range(500, 600); + + if (!count) + return -EBUSY; + + return 0; +} + +void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops) +{ + hw_ops->init = xlgmac_hw_init; + hw_ops->exit = xlgmac_hw_exit; + + hw_ops->tx_complete = xlgmac_tx_complete; + + hw_ops->enable_tx = xlgmac_enable_tx; + hw_ops->disable_tx = xlgmac_disable_tx; + hw_ops->enable_rx = xlgmac_enable_rx; + hw_ops->disable_rx = xlgmac_disable_rx; + + hw_ops->dev_xmit = xlgmac_dev_xmit; + hw_ops->dev_read = xlgmac_dev_read; + hw_ops->enable_int = xlgmac_enable_int; + hw_ops->disable_int = xlgmac_disable_int; + + hw_ops->set_mac_address = xlgmac_set_mac_address; + hw_ops->config_rx_mode = xlgmac_config_rx_mode; + hw_ops->enable_rx_csum = xlgmac_enable_rx_csum; + hw_ops->disable_rx_csum = xlgmac_disable_rx_csum; + + /* For MII speed configuration */ + hw_ops->set_xlgmii_25000_speed = xlgmac_set_xlgmii_25000_speed; + hw_ops->set_xlgmii_40000_speed = xlgmac_set_xlgmii_40000_speed; + hw_ops->set_xlgmii_50000_speed = xlgmac_set_xlgmii_50000_speed; + hw_ops->set_xlgmii_100000_speed = xlgmac_set_xlgmii_100000_speed; + + /* For descriptor related operation */ + hw_ops->tx_desc_init = xlgmac_tx_desc_init; + hw_ops->rx_desc_init = xlgmac_rx_desc_init; + hw_ops->tx_desc_reset = xlgmac_tx_desc_reset; + hw_ops->rx_desc_reset = xlgmac_rx_desc_reset; + hw_ops->is_last_desc = xlgmac_is_last_desc; + hw_ops->is_context_desc = xlgmac_is_context_desc; + hw_ops->tx_start_xmit = xlgmac_tx_start_xmit; + + /* For Flow Control */ + hw_ops->config_tx_flow_control = xlgmac_config_tx_flow_control; + hw_ops->config_rx_flow_control = xlgmac_config_rx_flow_control; + + /* For Vlan related config */ + hw_ops->enable_rx_vlan_stripping = xlgmac_enable_rx_vlan_stripping; + hw_ops->disable_rx_vlan_stripping = xlgmac_disable_rx_vlan_stripping; + hw_ops->enable_rx_vlan_filtering = xlgmac_enable_rx_vlan_filtering; + hw_ops->disable_rx_vlan_filtering = xlgmac_disable_rx_vlan_filtering; + hw_ops->update_vlan_hash_table = xlgmac_update_vlan_hash_table; + + /* For RX coalescing */ + hw_ops->config_rx_coalesce = xlgmac_config_rx_coalesce; + hw_ops->config_tx_coalesce = xlgmac_config_tx_coalesce; + hw_ops->usec_to_riwt = xlgmac_usec_to_riwt; + hw_ops->riwt_to_usec = xlgmac_riwt_to_usec; + + /* For RX and TX threshold config */ + hw_ops->config_rx_threshold = xlgmac_config_rx_threshold; + hw_ops->config_tx_threshold = xlgmac_config_tx_threshold; + + /* For RX and TX Store and Forward Mode config */ + hw_ops->config_rsf_mode = xlgmac_config_rsf_mode; + hw_ops->config_tsf_mode = xlgmac_config_tsf_mode; + + /* For TX DMA Operating on Second Frame config */ + hw_ops->config_osp_mode = xlgmac_config_osp_mode; + + /* For RX and TX PBL config */ + hw_ops->config_rx_pbl_val = xlgmac_config_rx_pbl_val; + hw_ops->get_rx_pbl_val = xlgmac_get_rx_pbl_val; + hw_ops->config_tx_pbl_val = xlgmac_config_tx_pbl_val; + hw_ops->get_tx_pbl_val = xlgmac_get_tx_pbl_val; + hw_ops->config_pblx8 = xlgmac_config_pblx8; + + /* For MMC statistics support */ + hw_ops->tx_mmc_int = xlgmac_tx_mmc_int; + hw_ops->rx_mmc_int = xlgmac_rx_mmc_int; + hw_ops->read_mmc_stats = xlgmac_read_mmc_stats; + + /* For Receive Side Scaling */ + hw_ops->enable_rss = xlgmac_enable_rss; + hw_ops->disable_rss = xlgmac_disable_rss; + hw_ops->set_rss_hash_key = xlgmac_set_rss_hash_key; + hw_ops->set_rss_lookup_table = xlgmac_set_rss_lookup_table; +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c new file mode 100644 index 000000000000..5e8428be3d66 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c @@ -0,0 +1,1334 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include +#include + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int xlgmac_one_poll(struct napi_struct *, int); +static int xlgmac_all_poll(struct napi_struct *, int); + +static inline unsigned int xlgmac_tx_avail_desc(struct xlgmac_ring *ring) +{ + return (ring->dma_desc_count - (ring->cur - ring->dirty)); +} + +static inline unsigned int xlgmac_rx_dirty_desc(struct xlgmac_ring *ring) +{ + return (ring->cur - ring->dirty); +} + +static int xlgmac_maybe_stop_tx_queue( + struct xlgmac_channel *channel, + struct xlgmac_ring *ring, + unsigned int count) +{ + struct xlgmac_pdata *pdata = channel->pdata; + + if (count > xlgmac_tx_avail_desc(ring)) { + netif_info(pdata, drv, pdata->netdev, + "Tx queue stopped, not enough descriptors available\n"); + netif_stop_subqueue(pdata->netdev, channel->queue_index); + ring->tx.queue_stopped = 1; + + /* If we haven't notified the hardware because of xmit_more + * support, tell it now + */ + if (ring->tx.xmit_more) + pdata->hw_ops.tx_start_xmit(channel, ring); + + return NETDEV_TX_BUSY; + } + + return 0; +} + +static void xlgmac_prep_vlan(struct sk_buff *skb, + struct xlgmac_pkt_info *pkt_info) +{ + if (skb_vlan_tag_present(skb)) + pkt_info->vlan_ctag = skb_vlan_tag_get(skb); +} + +static int xlgmac_prep_tso(struct sk_buff *skb, + struct xlgmac_pkt_info *pkt_info) +{ + int ret; + + if (!XLGMAC_GET_REG_BITS(pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN)) + return 0; + + ret = skb_cow_head(skb, 0); + if (ret) + return ret; + + pkt_info->header_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + pkt_info->tcp_header_len = tcp_hdrlen(skb); + pkt_info->tcp_payload_len = skb->len - pkt_info->header_len; + pkt_info->mss = skb_shinfo(skb)->gso_size; + + XLGMAC_PR("header_len=%u\n", pkt_info->header_len); + XLGMAC_PR("tcp_header_len=%u, tcp_payload_len=%u\n", + pkt_info->tcp_header_len, pkt_info->tcp_payload_len); + XLGMAC_PR("mss=%u\n", pkt_info->mss); + + /* Update the number of packets that will ultimately be transmitted + * along with the extra bytes for each extra packet + */ + pkt_info->tx_packets = skb_shinfo(skb)->gso_segs; + pkt_info->tx_bytes += (pkt_info->tx_packets - 1) * pkt_info->header_len; + + return 0; +} + +static int xlgmac_is_tso(struct sk_buff *skb) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + if (!skb_is_gso(skb)) + return 0; + + return 1; +} + +static void xlgmac_prep_tx_pkt(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + struct sk_buff *skb, + struct xlgmac_pkt_info *pkt_info) +{ + struct skb_frag_struct *frag; + unsigned int context_desc; + unsigned int len; + unsigned int i; + + pkt_info->skb = skb; + + context_desc = 0; + pkt_info->desc_count = 0; + + pkt_info->tx_packets = 1; + pkt_info->tx_bytes = skb->len; + + if (xlgmac_is_tso(skb)) { + /* TSO requires an extra descriptor if mss is different */ + if (skb_shinfo(skb)->gso_size != ring->tx.cur_mss) { + context_desc = 1; + pkt_info->desc_count++; + } + + /* TSO requires an extra descriptor for TSO header */ + pkt_info->desc_count++; + + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS, + TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN, + 1); + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN, + 1); + } else if (skb->ip_summed == CHECKSUM_PARTIAL) + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS, + TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN, + 1); + + if (skb_vlan_tag_present(skb)) { + /* VLAN requires an extra descriptor if tag is different */ + if (skb_vlan_tag_get(skb) != ring->tx.cur_vlan_ctag) + /* We can share with the TSO context descriptor */ + if (!context_desc) { + context_desc = 1; + pkt_info->desc_count++; + } + + pkt_info->attributes = XLGMAC_SET_REG_BITS( + pkt_info->attributes, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN, + 1); + } + + for (len = skb_headlen(skb); len;) { + pkt_info->desc_count++; + len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE); + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + frag = &skb_shinfo(skb)->frags[i]; + for (len = skb_frag_size(frag); len; ) { + pkt_info->desc_count++; + len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE); + } + } +} + +static int xlgmac_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu) +{ + unsigned int rx_buf_size; + + if (mtu > XLGMAC_JUMBO_PACKET_MTU) { + netdev_alert(netdev, "MTU exceeds maximum supported value\n"); + return -EINVAL; + } + + rx_buf_size = mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + rx_buf_size = clamp_val(rx_buf_size, XLGMAC_RX_MIN_BUF_SIZE, PAGE_SIZE); + + rx_buf_size = (rx_buf_size + XLGMAC_RX_BUF_ALIGN - 1) & + ~(XLGMAC_RX_BUF_ALIGN - 1); + + return rx_buf_size; +} + +static void xlgmac_enable_rx_tx_ints(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_channel *channel; + enum xlgmac_int int_id; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (channel->tx_ring && channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI_RI; + else if (channel->tx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI; + else if (channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_RI; + else + continue; + + hw_ops->enable_int(channel, int_id); + } +} + +static void xlgmac_disable_rx_tx_ints(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct xlgmac_channel *channel; + enum xlgmac_int int_id; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (channel->tx_ring && channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI_RI; + else if (channel->tx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_TI; + else if (channel->rx_ring) + int_id = XLGMAC_INT_DMA_CH_SR_RI; + else + continue; + + hw_ops->disable_int(channel, int_id); + } +} + +static irqreturn_t xlgmac_isr(int irq, void *data) +{ + unsigned int dma_isr, dma_ch_isr, mac_isr; + struct xlgmac_pdata *pdata = data; + struct xlgmac_channel *channel; + struct xlgmac_hw_ops *hw_ops; + unsigned int i, ti, ri; + + hw_ops = &pdata->hw_ops; + + /* The DMA interrupt status register also reports MAC and MTL + * interrupts. So for polling mode, we just need to check for + * this register to be non-zero + */ + dma_isr = readl(pdata->mac_regs + DMA_ISR); + if (!dma_isr) + return IRQ_HANDLED; + + netif_dbg(pdata, intr, pdata->netdev, "DMA_ISR=%#010x\n", dma_isr); + + for (i = 0; i < pdata->channel_count; i++) { + if (!(dma_isr & (1 << i))) + continue; + + channel = pdata->channel_head + i; + + dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR)); + netif_dbg(pdata, intr, pdata->netdev, "DMA_CH%u_ISR=%#010x\n", + i, dma_ch_isr); + + /* The TI or RI interrupt bits may still be set even if using + * per channel DMA interrupts. Check to be sure those are not + * enabled before using the private data napi structure. + */ + ti = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TI_POS, + DMA_CH_SR_TI_LEN); + ri = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RI_POS, + DMA_CH_SR_RI_LEN); + if (!pdata->per_channel_irq && (ti || ri)) { + if (napi_schedule_prep(&pdata->napi)) { + /* Disable Tx and Rx interrupts */ + xlgmac_disable_rx_tx_ints(pdata); + + /* Turn on polling */ + __napi_schedule_irqoff(&pdata->napi); + } + } + + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RBU_POS, + DMA_CH_SR_RBU_LEN)) + pdata->stats.rx_buffer_unavailable++; + + /* Restart the device on a Fatal Bus Error */ + if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_FBE_POS, + DMA_CH_SR_FBE_LEN)) + schedule_work(&pdata->restart_work); + + /* Clear all interrupt signals */ + writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR)); + } + + if (XLGMAC_GET_REG_BITS(dma_isr, DMA_ISR_MACIS_POS, + DMA_ISR_MACIS_LEN)) { + mac_isr = readl(pdata->mac_regs + MAC_ISR); + + if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCTXIS_POS, + MAC_ISR_MMCTXIS_LEN)) + hw_ops->tx_mmc_int(pdata); + + if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCRXIS_POS, + MAC_ISR_MMCRXIS_LEN)) + hw_ops->rx_mmc_int(pdata); + } + + return IRQ_HANDLED; +} + +static irqreturn_t xlgmac_dma_isr(int irq, void *data) +{ + struct xlgmac_channel *channel = data; + + /* Per channel DMA interrupts are enabled, so we use the per + * channel napi structure and not the private data napi structure + */ + if (napi_schedule_prep(&channel->napi)) { + /* Disable Tx and Rx interrupts */ + disable_irq_nosync(channel->dma_irq); + + /* Turn on polling */ + __napi_schedule_irqoff(&channel->napi); + } + + return IRQ_HANDLED; +} + +static void xlgmac_tx_timer(unsigned long data) +{ + struct xlgmac_channel *channel = (struct xlgmac_channel *)data; + struct xlgmac_pdata *pdata = channel->pdata; + struct napi_struct *napi; + + napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi; + + if (napi_schedule_prep(napi)) { + /* Disable Tx and Rx interrupts */ + if (pdata->per_channel_irq) + disable_irq_nosync(channel->dma_irq); + else + xlgmac_disable_rx_tx_ints(pdata); + + /* Turn on polling */ + __napi_schedule(napi); + } + + channel->tx_timer_active = 0; +} + +static void xlgmac_init_timers(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + setup_timer(&channel->tx_timer, xlgmac_tx_timer, + (unsigned long)channel); + } +} + +static void xlgmac_stop_timers(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + break; + + del_timer_sync(&channel->tx_timer); + } +} + +static void xlgmac_napi_enable(struct xlgmac_pdata *pdata, unsigned int add) +{ + struct xlgmac_channel *channel; + unsigned int i; + + if (pdata->per_channel_irq) { + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (add) + netif_napi_add(pdata->netdev, &channel->napi, + xlgmac_one_poll, + NAPI_POLL_WEIGHT); + + napi_enable(&channel->napi); + } + } else { + if (add) + netif_napi_add(pdata->netdev, &pdata->napi, + xlgmac_all_poll, NAPI_POLL_WEIGHT); + + napi_enable(&pdata->napi); + } +} + +static void xlgmac_napi_disable(struct xlgmac_pdata *pdata, unsigned int del) +{ + struct xlgmac_channel *channel; + unsigned int i; + + if (pdata->per_channel_irq) { + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + napi_disable(&channel->napi); + + if (del) + netif_napi_del(&channel->napi); + } + } else { + napi_disable(&pdata->napi); + + if (del) + netif_napi_del(&pdata->napi); + } +} + +static int xlgmac_request_irqs(struct xlgmac_pdata *pdata) +{ + struct net_device *netdev = pdata->netdev; + struct xlgmac_channel *channel; + unsigned int i; + int ret; + + ret = devm_request_irq(pdata->dev, pdata->dev_irq, xlgmac_isr, + IRQF_SHARED, netdev->name, pdata); + if (ret) { + netdev_alert(netdev, "error requesting irq %d\n", + pdata->dev_irq); + return ret; + } + + if (!pdata->per_channel_irq) + return 0; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + snprintf(channel->dma_irq_name, + sizeof(channel->dma_irq_name) - 1, + "%s-TxRx-%u", netdev_name(netdev), + channel->queue_index); + + ret = devm_request_irq(pdata->dev, channel->dma_irq, + xlgmac_dma_isr, 0, + channel->dma_irq_name, channel); + if (ret) { + netdev_alert(netdev, "error requesting irq %d\n", + channel->dma_irq); + goto err_irq; + } + } + + return 0; + +err_irq: + /* Using an unsigned int, 'i' will go to UINT_MAX and exit */ + for (i--, channel--; i < pdata->channel_count; i--, channel--) + devm_free_irq(pdata->dev, channel->dma_irq, channel); + + devm_free_irq(pdata->dev, pdata->dev_irq, pdata); + + return ret; +} + +static void xlgmac_free_irqs(struct xlgmac_pdata *pdata) +{ + struct xlgmac_channel *channel; + unsigned int i; + + devm_free_irq(pdata->dev, pdata->dev_irq, pdata); + + if (!pdata->per_channel_irq) + return; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) + devm_free_irq(pdata->dev, channel->dma_irq, channel); +} + +static void xlgmac_free_tx_data(struct xlgmac_pdata *pdata) +{ + struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->tx_ring; + if (!ring) + break; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + desc_ops->unmap_desc_data(pdata, desc_data); + } + } +} + +static void xlgmac_free_rx_data(struct xlgmac_pdata *pdata) +{ + struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops; + struct xlgmac_desc_data *desc_data; + struct xlgmac_channel *channel; + struct xlgmac_ring *ring; + unsigned int i, j; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + ring = channel->rx_ring; + if (!ring) + break; + + for (j = 0; j < ring->dma_desc_count; j++) { + desc_data = XLGMAC_GET_DESC_DATA(ring, j); + desc_ops->unmap_desc_data(pdata, desc_data); + } + } +} + +static int xlgmac_start(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct net_device *netdev = pdata->netdev; + int ret; + + hw_ops->init(pdata); + xlgmac_napi_enable(pdata, 1); + + ret = xlgmac_request_irqs(pdata); + if (ret) + goto err_napi; + + hw_ops->enable_tx(pdata); + hw_ops->enable_rx(pdata); + netif_tx_start_all_queues(netdev); + + return 0; + +err_napi: + xlgmac_napi_disable(pdata, 1); + hw_ops->exit(pdata); + + return ret; +} + +static void xlgmac_stop(struct xlgmac_pdata *pdata) +{ + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct net_device *netdev = pdata->netdev; + struct xlgmac_channel *channel; + struct netdev_queue *txq; + unsigned int i; + + netif_tx_stop_all_queues(netdev); + xlgmac_stop_timers(pdata); + hw_ops->disable_tx(pdata); + hw_ops->disable_rx(pdata); + xlgmac_free_irqs(pdata); + xlgmac_napi_disable(pdata, 1); + hw_ops->exit(pdata); + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + if (!channel->tx_ring) + continue; + + txq = netdev_get_tx_queue(netdev, channel->queue_index); + netdev_tx_reset_queue(txq); + } +} + +static void xlgmac_restart_dev(struct xlgmac_pdata *pdata) +{ + /* If not running, "restart" will happen on open */ + if (!netif_running(pdata->netdev)) + return; + + xlgmac_stop(pdata); + + xlgmac_free_tx_data(pdata); + xlgmac_free_rx_data(pdata); + + xlgmac_start(pdata); +} + +static void xlgmac_restart(struct work_struct *work) +{ + struct xlgmac_pdata *pdata = container_of(work, + struct xlgmac_pdata, + restart_work); + + rtnl_lock(); + + xlgmac_restart_dev(pdata); + + rtnl_unlock(); +} + +static int xlgmac_open(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_desc_ops *desc_ops; + int ret; + + desc_ops = &pdata->desc_ops; + + /* TODO: Initialize the phy */ + + /* Calculate the Rx buffer size before allocating rings */ + ret = xlgmac_calc_rx_buf_size(netdev, netdev->mtu); + if (ret < 0) + return ret; + pdata->rx_buf_size = ret; + + /* Allocate the channels and rings */ + ret = desc_ops->alloc_channles_and_rings(pdata); + if (ret) + return ret; + + INIT_WORK(&pdata->restart_work, xlgmac_restart); + xlgmac_init_timers(pdata); + + ret = xlgmac_start(pdata); + if (ret) + goto err_channels_and_rings; + + return 0; + +err_channels_and_rings: + desc_ops->free_channels_and_rings(pdata); + + return ret; +} + +static int xlgmac_close(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_desc_ops *desc_ops; + + desc_ops = &pdata->desc_ops; + + /* Stop the device */ + xlgmac_stop(pdata); + + /* Free the channels and rings */ + desc_ops->free_channels_and_rings(pdata); + + return 0; +} + +static void xlgmac_tx_timeout(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + + netdev_warn(netdev, "tx timeout, device restarting\n"); + schedule_work(&pdata->restart_work); +} + +static int xlgmac_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_pkt_info *tx_pkt_info; + struct xlgmac_desc_ops *desc_ops; + struct xlgmac_channel *channel; + struct xlgmac_hw_ops *hw_ops; + struct netdev_queue *txq; + struct xlgmac_ring *ring; + int ret; + + desc_ops = &pdata->desc_ops; + hw_ops = &pdata->hw_ops; + + XLGMAC_PR("skb->len = %d\n", skb->len); + + channel = pdata->channel_head + skb->queue_mapping; + txq = netdev_get_tx_queue(netdev, channel->queue_index); + ring = channel->tx_ring; + tx_pkt_info = &ring->pkt_info; + + if (skb->len == 0) { + netif_err(pdata, tx_err, netdev, + "empty skb received from stack\n"); + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* Prepare preliminary packet info for TX */ + memset(tx_pkt_info, 0, sizeof(*tx_pkt_info)); + xlgmac_prep_tx_pkt(pdata, ring, skb, tx_pkt_info); + + /* Check that there are enough descriptors available */ + ret = xlgmac_maybe_stop_tx_queue(channel, ring, + tx_pkt_info->desc_count); + if (ret) + return ret; + + ret = xlgmac_prep_tso(skb, tx_pkt_info); + if (ret) { + netif_err(pdata, tx_err, netdev, + "error processing TSO packet\n"); + dev_kfree_skb_any(skb); + return ret; + } + xlgmac_prep_vlan(skb, tx_pkt_info); + + if (!desc_ops->map_tx_skb(channel, skb)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* Report on the actual number of bytes (to be) sent */ + netdev_tx_sent_queue(txq, tx_pkt_info->tx_bytes); + + /* Configure required descriptor fields for transmission */ + hw_ops->dev_xmit(channel); + + if (netif_msg_pktdata(pdata)) + xlgmac_print_pkt(netdev, skb, true); + + /* Stop the queue in advance if there may not be enough descriptors */ + xlgmac_maybe_stop_tx_queue(channel, ring, XLGMAC_TX_MAX_DESC_NR); + + return NETDEV_TX_OK; +} + +static void xlgmac_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *s) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_stats *pstats = &pdata->stats; + + pdata->hw_ops.read_mmc_stats(pdata); + + s->rx_packets = pstats->rxframecount_gb; + s->rx_bytes = pstats->rxoctetcount_gb; + s->rx_errors = pstats->rxframecount_gb - + pstats->rxbroadcastframes_g - + pstats->rxmulticastframes_g - + pstats->rxunicastframes_g; + s->multicast = pstats->rxmulticastframes_g; + s->rx_length_errors = pstats->rxlengtherror; + s->rx_crc_errors = pstats->rxcrcerror; + s->rx_fifo_errors = pstats->rxfifooverflow; + + s->tx_packets = pstats->txframecount_gb; + s->tx_bytes = pstats->txoctetcount_gb; + s->tx_errors = pstats->txframecount_gb - pstats->txframecount_g; + s->tx_dropped = netdev->stats.tx_dropped; +} + +static int xlgmac_set_mac_address(struct net_device *netdev, void *addr) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + struct sockaddr *saddr = addr; + + if (!is_valid_ether_addr(saddr->sa_data)) + return -EADDRNOTAVAIL; + + memcpy(netdev->dev_addr, saddr->sa_data, netdev->addr_len); + + hw_ops->set_mac_address(pdata, netdev->dev_addr); + + return 0; +} + +static int xlgmac_ioctl(struct net_device *netdev, + struct ifreq *ifreq, int cmd) +{ + if (!netif_running(netdev)) + return -ENODEV; + + return 0; +} + +static int xlgmac_change_mtu(struct net_device *netdev, int mtu) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + int ret; + + ret = xlgmac_calc_rx_buf_size(netdev, mtu); + if (ret < 0) + return ret; + + pdata->rx_buf_size = ret; + netdev->mtu = mtu; + + xlgmac_restart_dev(pdata); + + return 0; +} + +static int xlgmac_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, + u16 vid) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + + set_bit(vid, pdata->active_vlans); + hw_ops->update_vlan_hash_table(pdata); + + return 0; +} + +static int xlgmac_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, + u16 vid) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + + clear_bit(vid, pdata->active_vlans); + hw_ops->update_vlan_hash_table(pdata); + + return 0; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void xlgmac_poll_controller(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_channel *channel; + unsigned int i; + + if (pdata->per_channel_irq) { + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) + xlgmac_dma_isr(channel->dma_irq, channel); + } else { + disable_irq(pdata->dev_irq); + xlgmac_isr(pdata->dev_irq, pdata); + enable_irq(pdata->dev_irq); + } +} +#endif /* CONFIG_NET_POLL_CONTROLLER */ + +static int xlgmac_set_features(struct net_device *netdev, + netdev_features_t features) +{ + netdev_features_t rxhash, rxcsum, rxvlan, rxvlan_filter; + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + int ret = 0; + + rxhash = pdata->netdev_features & NETIF_F_RXHASH; + rxcsum = pdata->netdev_features & NETIF_F_RXCSUM; + rxvlan = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX; + rxvlan_filter = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_FILTER; + + if ((features & NETIF_F_RXHASH) && !rxhash) + ret = hw_ops->enable_rss(pdata); + else if (!(features & NETIF_F_RXHASH) && rxhash) + ret = hw_ops->disable_rss(pdata); + if (ret) + return ret; + + if ((features & NETIF_F_RXCSUM) && !rxcsum) + hw_ops->enable_rx_csum(pdata); + else if (!(features & NETIF_F_RXCSUM) && rxcsum) + hw_ops->disable_rx_csum(pdata); + + if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan) + hw_ops->enable_rx_vlan_stripping(pdata); + else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && rxvlan) + hw_ops->disable_rx_vlan_stripping(pdata); + + if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && !rxvlan_filter) + hw_ops->enable_rx_vlan_filtering(pdata); + else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && rxvlan_filter) + hw_ops->disable_rx_vlan_filtering(pdata); + + pdata->netdev_features = features; + + return 0; +} + +static void xlgmac_set_rx_mode(struct net_device *netdev) +{ + struct xlgmac_pdata *pdata = netdev_priv(netdev); + struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; + + hw_ops->config_rx_mode(pdata); +} + +static const struct net_device_ops xlgmac_netdev_ops = { + .ndo_open = xlgmac_open, + .ndo_stop = xlgmac_close, + .ndo_start_xmit = xlgmac_xmit, + .ndo_tx_timeout = xlgmac_tx_timeout, + .ndo_get_stats64 = xlgmac_get_stats64, + .ndo_change_mtu = xlgmac_change_mtu, + .ndo_set_mac_address = xlgmac_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_do_ioctl = xlgmac_ioctl, + .ndo_vlan_rx_add_vid = xlgmac_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = xlgmac_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = xlgmac_poll_controller, +#endif + .ndo_set_features = xlgmac_set_features, + .ndo_set_rx_mode = xlgmac_set_rx_mode, +}; + +const struct net_device_ops *xlgmac_get_netdev_ops(void) +{ + return &xlgmac_netdev_ops; +} + +static void xlgmac_rx_refresh(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + struct xlgmac_desc_data *desc_data; + struct xlgmac_desc_ops *desc_ops; + struct xlgmac_hw_ops *hw_ops; + + desc_ops = &pdata->desc_ops; + hw_ops = &pdata->hw_ops; + + while (ring->dirty != ring->cur) { + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty); + + /* Reset desc_data values */ + desc_ops->unmap_desc_data(pdata, desc_data); + + if (desc_ops->map_rx_buffer(pdata, ring, desc_data)) + break; + + hw_ops->rx_desc_reset(pdata, desc_data, ring->dirty); + + ring->dirty++; + } + + /* Make sure everything is written before the register write */ + wmb(); + + /* Update the Rx Tail Pointer Register with address of + * the last cleaned entry + */ + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty - 1); + writel(lower_32_bits(desc_data->dma_desc_addr), + XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO)); +} + +static struct sk_buff *xlgmac_create_skb(struct xlgmac_pdata *pdata, + struct napi_struct *napi, + struct xlgmac_desc_data *desc_data, + unsigned int len) +{ + unsigned int copy_len; + struct sk_buff *skb; + u8 *packet; + + skb = napi_alloc_skb(napi, desc_data->rx.hdr.dma_len); + if (!skb) + return NULL; + + /* Start with the header buffer which may contain just the header + * or the header plus data + */ + dma_sync_single_range_for_cpu(pdata->dev, desc_data->rx.hdr.dma_base, + desc_data->rx.hdr.dma_off, + desc_data->rx.hdr.dma_len, + DMA_FROM_DEVICE); + + packet = page_address(desc_data->rx.hdr.pa.pages) + + desc_data->rx.hdr.pa.pages_offset; + copy_len = (desc_data->rx.hdr_len) ? desc_data->rx.hdr_len : len; + copy_len = min(desc_data->rx.hdr.dma_len, copy_len); + skb_copy_to_linear_data(skb, packet, copy_len); + skb_put(skb, copy_len); + + len -= copy_len; + if (len) { + /* Add the remaining data as a frag */ + dma_sync_single_range_for_cpu(pdata->dev, + desc_data->rx.buf.dma_base, + desc_data->rx.buf.dma_off, + desc_data->rx.buf.dma_len, + DMA_FROM_DEVICE); + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + desc_data->rx.buf.pa.pages, + desc_data->rx.buf.pa.pages_offset, + len, desc_data->rx.buf.dma_len); + desc_data->rx.buf.pa.pages = NULL; + } + + return skb; +} + +static int xlgmac_tx_poll(struct xlgmac_channel *channel) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->tx_ring; + struct net_device *netdev = pdata->netdev; + unsigned int tx_packets = 0, tx_bytes = 0; + struct xlgmac_desc_data *desc_data; + struct xlgmac_dma_desc *dma_desc; + struct xlgmac_desc_ops *desc_ops; + struct xlgmac_hw_ops *hw_ops; + struct netdev_queue *txq; + int processed = 0; + unsigned int cur; + + desc_ops = &pdata->desc_ops; + hw_ops = &pdata->hw_ops; + + /* Nothing to do if there isn't a Tx ring for this channel */ + if (!ring) + return 0; + + cur = ring->cur; + + /* Be sure we get ring->cur before accessing descriptor data */ + smp_rmb(); + + txq = netdev_get_tx_queue(netdev, channel->queue_index); + + while ((processed < XLGMAC_TX_DESC_MAX_PROC) && + (ring->dirty != cur)) { + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty); + dma_desc = desc_data->dma_desc; + + if (!hw_ops->tx_complete(dma_desc)) + break; + + /* Make sure descriptor fields are read after reading + * the OWN bit + */ + dma_rmb(); + + if (netif_msg_tx_done(pdata)) + xlgmac_dump_tx_desc(pdata, ring, ring->dirty, 1, 0); + + if (hw_ops->is_last_desc(dma_desc)) { + tx_packets += desc_data->tx.packets; + tx_bytes += desc_data->tx.bytes; + } + + /* Free the SKB and reset the descriptor for re-use */ + desc_ops->unmap_desc_data(pdata, desc_data); + hw_ops->tx_desc_reset(desc_data); + + processed++; + ring->dirty++; + } + + if (!processed) + return 0; + + netdev_tx_completed_queue(txq, tx_packets, tx_bytes); + + if ((ring->tx.queue_stopped == 1) && + (xlgmac_tx_avail_desc(ring) > XLGMAC_TX_DESC_MIN_FREE)) { + ring->tx.queue_stopped = 0; + netif_tx_wake_queue(txq); + } + + XLGMAC_PR("processed=%d\n", processed); + + return processed; +} + +static int xlgmac_rx_poll(struct xlgmac_channel *channel, int budget) +{ + struct xlgmac_pdata *pdata = channel->pdata; + struct xlgmac_ring *ring = channel->rx_ring; + struct net_device *netdev = pdata->netdev; + unsigned int len, dma_desc_len, max_len; + unsigned int context_next, context; + struct xlgmac_desc_data *desc_data; + struct xlgmac_pkt_info *pkt_info; + unsigned int incomplete, error; + struct xlgmac_hw_ops *hw_ops; + unsigned int received = 0; + struct napi_struct *napi; + struct sk_buff *skb; + int packet_count = 0; + + hw_ops = &pdata->hw_ops; + + /* Nothing to do if there isn't a Rx ring for this channel */ + if (!ring) + return 0; + + incomplete = 0; + context_next = 0; + + napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi; + + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + pkt_info = &ring->pkt_info; + while (packet_count < budget) { + /* First time in loop see if we need to restore state */ + if (!received && desc_data->state_saved) { + skb = desc_data->state.skb; + error = desc_data->state.error; + len = desc_data->state.len; + } else { + memset(pkt_info, 0, sizeof(*pkt_info)); + skb = NULL; + error = 0; + len = 0; + } + +read_again: + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + + if (xlgmac_rx_dirty_desc(ring) > XLGMAC_RX_DESC_MAX_DIRTY) + xlgmac_rx_refresh(channel); + + if (hw_ops->dev_read(channel)) + break; + + received++; + ring->cur++; + + incomplete = XLGMAC_GET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_INCOMPLETE_POS, + RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN); + context_next = XLGMAC_GET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN); + context = XLGMAC_GET_REG_BITS( + pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CONTEXT_POS, + RX_PACKET_ATTRIBUTES_CONTEXT_LEN); + + /* Earlier error, just drain the remaining data */ + if ((incomplete || context_next) && error) + goto read_again; + + if (error || pkt_info->errors) { + if (pkt_info->errors) + netif_err(pdata, rx_err, netdev, + "error in received packet\n"); + dev_kfree_skb(skb); + goto next_packet; + } + + if (!context) { + /* Length is cumulative, get this descriptor's length */ + dma_desc_len = desc_data->rx.len - len; + len += dma_desc_len; + + if (dma_desc_len && !skb) { + skb = xlgmac_create_skb(pdata, napi, desc_data, + dma_desc_len); + if (!skb) + error = 1; + } else if (dma_desc_len) { + dma_sync_single_range_for_cpu( + pdata->dev, + desc_data->rx.buf.dma_base, + desc_data->rx.buf.dma_off, + desc_data->rx.buf.dma_len, + DMA_FROM_DEVICE); + + skb_add_rx_frag( + skb, skb_shinfo(skb)->nr_frags, + desc_data->rx.buf.pa.pages, + desc_data->rx.buf.pa.pages_offset, + dma_desc_len, + desc_data->rx.buf.dma_len); + desc_data->rx.buf.pa.pages = NULL; + } + } + + if (incomplete || context_next) + goto read_again; + + if (!skb) + goto next_packet; + + /* Be sure we don't exceed the configured MTU */ + max_len = netdev->mtu + ETH_HLEN; + if (!(netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && + (skb->protocol == htons(ETH_P_8021Q))) + max_len += VLAN_HLEN; + + if (skb->len > max_len) { + netif_err(pdata, rx_err, netdev, + "packet length exceeds configured MTU\n"); + dev_kfree_skb(skb); + goto next_packet; + } + + if (netif_msg_pktdata(pdata)) + xlgmac_print_pkt(netdev, skb, false); + + skb_checksum_none_assert(skb); + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + RX_PACKET_ATTRIBUTES_CSUM_DONE_POS, + RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS, + RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + pkt_info->vlan_ctag); + + if (XLGMAC_GET_REG_BITS(pkt_info->attributes, + RX_PACKET_ATTRIBUTES_RSS_HASH_POS, + RX_PACKET_ATTRIBUTES_RSS_HASH_LEN)) + skb_set_hash(skb, pkt_info->rss_hash, + pkt_info->rss_hash_type); + + skb->dev = netdev; + skb->protocol = eth_type_trans(skb, netdev); + skb_record_rx_queue(skb, channel->queue_index); + + napi_gro_receive(napi, skb); + +next_packet: + packet_count++; + } + + /* Check if we need to save state before leaving */ + if (received && (incomplete || context_next)) { + desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur); + desc_data->state_saved = 1; + desc_data->state.skb = skb; + desc_data->state.len = len; + desc_data->state.error = error; + } + + XLGMAC_PR("packet_count = %d\n", packet_count); + + return packet_count; +} + +static int xlgmac_one_poll(struct napi_struct *napi, int budget) +{ + struct xlgmac_channel *channel = container_of(napi, + struct xlgmac_channel, + napi); + int processed = 0; + + XLGMAC_PR("budget=%d\n", budget); + + /* Cleanup Tx ring first */ + xlgmac_tx_poll(channel); + + /* Process Rx ring next */ + processed = xlgmac_rx_poll(channel, budget); + + /* If we processed everything, we are done */ + if (processed < budget) { + /* Turn off polling */ + napi_complete_done(napi, processed); + + /* Enable Tx and Rx interrupts */ + enable_irq(channel->dma_irq); + } + + XLGMAC_PR("received = %d\n", processed); + + return processed; +} + +static int xlgmac_all_poll(struct napi_struct *napi, int budget) +{ + struct xlgmac_pdata *pdata = container_of(napi, + struct xlgmac_pdata, + napi); + struct xlgmac_channel *channel; + int processed, last_processed; + int ring_budget; + unsigned int i; + + XLGMAC_PR("budget=%d\n", budget); + + processed = 0; + ring_budget = budget / pdata->rx_ring_count; + do { + last_processed = processed; + + channel = pdata->channel_head; + for (i = 0; i < pdata->channel_count; i++, channel++) { + /* Cleanup Tx ring first */ + xlgmac_tx_poll(channel); + + /* Process Rx ring next */ + if (ring_budget > (budget - processed)) + ring_budget = budget - processed; + processed += xlgmac_rx_poll(channel, ring_budget); + } + } while ((processed < budget) && (processed != last_processed)); + + /* If we processed everything, we are done */ + if (processed < budget) { + /* Turn off polling */ + napi_complete_done(napi, processed); + + /* Enable Tx and Rx interrupts */ + xlgmac_enable_rx_tx_ints(pdata); + } + + XLGMAC_PR("received = %d\n", processed); + + return processed; +} diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c new file mode 100644 index 000000000000..504e80de7bba --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c @@ -0,0 +1,80 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#include +#include +#include + +#include "dwc-xlgmac.h" +#include "dwc-xlgmac-reg.h" + +static int xlgmac_probe(struct pci_dev *pcidev, const struct pci_device_id *id) +{ + struct device *dev = &pcidev->dev; + struct xlgmac_resources res; + int i, ret; + + ret = pcim_enable_device(pcidev); + if (ret) { + dev_err(dev, "ERROR: failed to enable device\n"); + return ret; + } + + for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + if (pci_resource_len(pcidev, i) == 0) + continue; + ret = pcim_iomap_regions(pcidev, BIT(i), XLGMAC_DRV_NAME); + if (ret) + return ret; + break; + } + + pci_set_master(pcidev); + + memset(&res, 0, sizeof(res)); + res.irq = pcidev->irq; + res.addr = pcim_iomap_table(pcidev)[i]; + + return xlgmac_drv_probe(&pcidev->dev, &res); +} + +static void xlgmac_remove(struct pci_dev *pcidev) +{ + xlgmac_drv_remove(&pcidev->dev); +} + +static const struct pci_device_id xlgmac_pci_tbl[] = { + { PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS, 0x7302) }, + { 0 } +}; +MODULE_DEVICE_TABLE(pci, xlgmac_pci_tbl); + +static struct pci_driver xlgmac_pci_driver = { + .name = XLGMAC_DRV_NAME, + .id_table = xlgmac_pci_tbl, + .probe = xlgmac_probe, + .remove = xlgmac_remove, +}; + +module_pci_driver(xlgmac_pci_driver); + +MODULE_DESCRIPTION(XLGMAC_DRV_DESC); +MODULE_VERSION(XLGMAC_DRV_VERSION); +MODULE_AUTHOR("Jie Deng "); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h new file mode 100644 index 000000000000..782448128a89 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h @@ -0,0 +1,746 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#ifndef __DWC_XLGMAC_REG_H__ +#define __DWC_XLGMAC_REG_H__ + +/* MAC register offsets */ +#define MAC_TCR 0x0000 +#define MAC_RCR 0x0004 +#define MAC_PFR 0x0008 +#define MAC_HTR0 0x0010 +#define MAC_VLANTR 0x0050 +#define MAC_VLANHTR 0x0058 +#define MAC_VLANIR 0x0060 +#define MAC_Q0TFCR 0x0070 +#define MAC_RFCR 0x0090 +#define MAC_RQC0R 0x00a0 +#define MAC_RQC1R 0x00a4 +#define MAC_RQC2R 0x00a8 +#define MAC_RQC3R 0x00ac +#define MAC_ISR 0x00b0 +#define MAC_IER 0x00b4 +#define MAC_VR 0x0110 +#define MAC_HWF0R 0x011c +#define MAC_HWF1R 0x0120 +#define MAC_HWF2R 0x0124 +#define MAC_MACA0HR 0x0300 +#define MAC_MACA0LR 0x0304 +#define MAC_MACA1HR 0x0308 +#define MAC_MACA1LR 0x030c +#define MAC_RSSCR 0x0c80 +#define MAC_RSSAR 0x0c88 +#define MAC_RSSDR 0x0c8c + +#define MAC_QTFCR_INC 4 +#define MAC_MACA_INC 4 +#define MAC_HTR_INC 4 +#define MAC_RQC2_INC 4 +#define MAC_RQC2_Q_PER_REG 4 + +/* MAC register entry bit positions and sizes */ +#define MAC_HWF0R_ADDMACADRSEL_POS 18 +#define MAC_HWF0R_ADDMACADRSEL_LEN 5 +#define MAC_HWF0R_ARPOFFSEL_POS 9 +#define MAC_HWF0R_ARPOFFSEL_LEN 1 +#define MAC_HWF0R_EEESEL_POS 13 +#define MAC_HWF0R_EEESEL_LEN 1 +#define MAC_HWF0R_PHYIFSEL_POS 1 +#define MAC_HWF0R_PHYIFSEL_LEN 2 +#define MAC_HWF0R_MGKSEL_POS 7 +#define MAC_HWF0R_MGKSEL_LEN 1 +#define MAC_HWF0R_MMCSEL_POS 8 +#define MAC_HWF0R_MMCSEL_LEN 1 +#define MAC_HWF0R_RWKSEL_POS 6 +#define MAC_HWF0R_RWKSEL_LEN 1 +#define MAC_HWF0R_RXCOESEL_POS 16 +#define MAC_HWF0R_RXCOESEL_LEN 1 +#define MAC_HWF0R_SAVLANINS_POS 27 +#define MAC_HWF0R_SAVLANINS_LEN 1 +#define MAC_HWF0R_SMASEL_POS 5 +#define MAC_HWF0R_SMASEL_LEN 1 +#define MAC_HWF0R_TSSEL_POS 12 +#define MAC_HWF0R_TSSEL_LEN 1 +#define MAC_HWF0R_TSSTSSEL_POS 25 +#define MAC_HWF0R_TSSTSSEL_LEN 2 +#define MAC_HWF0R_TXCOESEL_POS 14 +#define MAC_HWF0R_TXCOESEL_LEN 1 +#define MAC_HWF0R_VLHASH_POS 4 +#define MAC_HWF0R_VLHASH_LEN 1 +#define MAC_HWF1R_ADDR64_POS 14 +#define MAC_HWF1R_ADDR64_LEN 2 +#define MAC_HWF1R_ADVTHWORD_POS 13 +#define MAC_HWF1R_ADVTHWORD_LEN 1 +#define MAC_HWF1R_DBGMEMA_POS 19 +#define MAC_HWF1R_DBGMEMA_LEN 1 +#define MAC_HWF1R_DCBEN_POS 16 +#define MAC_HWF1R_DCBEN_LEN 1 +#define MAC_HWF1R_HASHTBLSZ_POS 24 +#define MAC_HWF1R_HASHTBLSZ_LEN 3 +#define MAC_HWF1R_L3L4FNUM_POS 27 +#define MAC_HWF1R_L3L4FNUM_LEN 4 +#define MAC_HWF1R_NUMTC_POS 21 +#define MAC_HWF1R_NUMTC_LEN 3 +#define MAC_HWF1R_RSSEN_POS 20 +#define MAC_HWF1R_RSSEN_LEN 1 +#define MAC_HWF1R_RXFIFOSIZE_POS 0 +#define MAC_HWF1R_RXFIFOSIZE_LEN 5 +#define MAC_HWF1R_SPHEN_POS 17 +#define MAC_HWF1R_SPHEN_LEN 1 +#define MAC_HWF1R_TSOEN_POS 18 +#define MAC_HWF1R_TSOEN_LEN 1 +#define MAC_HWF1R_TXFIFOSIZE_POS 6 +#define MAC_HWF1R_TXFIFOSIZE_LEN 5 +#define MAC_HWF2R_AUXSNAPNUM_POS 28 +#define MAC_HWF2R_AUXSNAPNUM_LEN 3 +#define MAC_HWF2R_PPSOUTNUM_POS 24 +#define MAC_HWF2R_PPSOUTNUM_LEN 3 +#define MAC_HWF2R_RXCHCNT_POS 12 +#define MAC_HWF2R_RXCHCNT_LEN 4 +#define MAC_HWF2R_RXQCNT_POS 0 +#define MAC_HWF2R_RXQCNT_LEN 4 +#define MAC_HWF2R_TXCHCNT_POS 18 +#define MAC_HWF2R_TXCHCNT_LEN 4 +#define MAC_HWF2R_TXQCNT_POS 6 +#define MAC_HWF2R_TXQCNT_LEN 4 +#define MAC_IER_TSIE_POS 12 +#define MAC_IER_TSIE_LEN 1 +#define MAC_ISR_MMCRXIS_POS 9 +#define MAC_ISR_MMCRXIS_LEN 1 +#define MAC_ISR_MMCTXIS_POS 10 +#define MAC_ISR_MMCTXIS_LEN 1 +#define MAC_ISR_PMTIS_POS 4 +#define MAC_ISR_PMTIS_LEN 1 +#define MAC_ISR_TSIS_POS 12 +#define MAC_ISR_TSIS_LEN 1 +#define MAC_MACA1HR_AE_POS 31 +#define MAC_MACA1HR_AE_LEN 1 +#define MAC_PFR_HMC_POS 2 +#define MAC_PFR_HMC_LEN 1 +#define MAC_PFR_HPF_POS 10 +#define MAC_PFR_HPF_LEN 1 +#define MAC_PFR_HUC_POS 1 +#define MAC_PFR_HUC_LEN 1 +#define MAC_PFR_PM_POS 4 +#define MAC_PFR_PM_LEN 1 +#define MAC_PFR_PR_POS 0 +#define MAC_PFR_PR_LEN 1 +#define MAC_PFR_VTFE_POS 16 +#define MAC_PFR_VTFE_LEN 1 +#define MAC_Q0TFCR_PT_POS 16 +#define MAC_Q0TFCR_PT_LEN 16 +#define MAC_Q0TFCR_TFE_POS 1 +#define MAC_Q0TFCR_TFE_LEN 1 +#define MAC_RCR_ACS_POS 1 +#define MAC_RCR_ACS_LEN 1 +#define MAC_RCR_CST_POS 2 +#define MAC_RCR_CST_LEN 1 +#define MAC_RCR_DCRCC_POS 3 +#define MAC_RCR_DCRCC_LEN 1 +#define MAC_RCR_HDSMS_POS 12 +#define MAC_RCR_HDSMS_LEN 3 +#define MAC_RCR_IPC_POS 9 +#define MAC_RCR_IPC_LEN 1 +#define MAC_RCR_JE_POS 8 +#define MAC_RCR_JE_LEN 1 +#define MAC_RCR_LM_POS 10 +#define MAC_RCR_LM_LEN 1 +#define MAC_RCR_RE_POS 0 +#define MAC_RCR_RE_LEN 1 +#define MAC_RFCR_PFCE_POS 8 +#define MAC_RFCR_PFCE_LEN 1 +#define MAC_RFCR_RFE_POS 0 +#define MAC_RFCR_RFE_LEN 1 +#define MAC_RFCR_UP_POS 1 +#define MAC_RFCR_UP_LEN 1 +#define MAC_RQC0R_RXQ0EN_POS 0 +#define MAC_RQC0R_RXQ0EN_LEN 2 +#define MAC_RSSAR_ADDRT_POS 2 +#define MAC_RSSAR_ADDRT_LEN 1 +#define MAC_RSSAR_CT_POS 1 +#define MAC_RSSAR_CT_LEN 1 +#define MAC_RSSAR_OB_POS 0 +#define MAC_RSSAR_OB_LEN 1 +#define MAC_RSSAR_RSSIA_POS 8 +#define MAC_RSSAR_RSSIA_LEN 8 +#define MAC_RSSCR_IP2TE_POS 1 +#define MAC_RSSCR_IP2TE_LEN 1 +#define MAC_RSSCR_RSSE_POS 0 +#define MAC_RSSCR_RSSE_LEN 1 +#define MAC_RSSCR_TCP4TE_POS 2 +#define MAC_RSSCR_TCP4TE_LEN 1 +#define MAC_RSSCR_UDP4TE_POS 3 +#define MAC_RSSCR_UDP4TE_LEN 1 +#define MAC_RSSDR_DMCH_POS 0 +#define MAC_RSSDR_DMCH_LEN 4 +#define MAC_TCR_SS_POS 28 +#define MAC_TCR_SS_LEN 3 +#define MAC_TCR_TE_POS 0 +#define MAC_TCR_TE_LEN 1 +#define MAC_VLANHTR_VLHT_POS 0 +#define MAC_VLANHTR_VLHT_LEN 16 +#define MAC_VLANIR_VLTI_POS 20 +#define MAC_VLANIR_VLTI_LEN 1 +#define MAC_VLANIR_CSVL_POS 19 +#define MAC_VLANIR_CSVL_LEN 1 +#define MAC_VLANTR_DOVLTC_POS 20 +#define MAC_VLANTR_DOVLTC_LEN 1 +#define MAC_VLANTR_ERSVLM_POS 19 +#define MAC_VLANTR_ERSVLM_LEN 1 +#define MAC_VLANTR_ESVL_POS 18 +#define MAC_VLANTR_ESVL_LEN 1 +#define MAC_VLANTR_ETV_POS 16 +#define MAC_VLANTR_ETV_LEN 1 +#define MAC_VLANTR_EVLS_POS 21 +#define MAC_VLANTR_EVLS_LEN 2 +#define MAC_VLANTR_EVLRXS_POS 24 +#define MAC_VLANTR_EVLRXS_LEN 1 +#define MAC_VLANTR_VL_POS 0 +#define MAC_VLANTR_VL_LEN 16 +#define MAC_VLANTR_VTHM_POS 25 +#define MAC_VLANTR_VTHM_LEN 1 +#define MAC_VLANTR_VTIM_POS 17 +#define MAC_VLANTR_VTIM_LEN 1 +#define MAC_VR_DEVID_POS 8 +#define MAC_VR_DEVID_LEN 8 +#define MAC_VR_SNPSVER_POS 0 +#define MAC_VR_SNPSVER_LEN 8 +#define MAC_VR_USERVER_POS 16 +#define MAC_VR_USERVER_LEN 8 + +/* MMC register offsets */ +#define MMC_CR 0x0800 +#define MMC_RISR 0x0804 +#define MMC_TISR 0x0808 +#define MMC_RIER 0x080c +#define MMC_TIER 0x0810 +#define MMC_TXOCTETCOUNT_GB_LO 0x0814 +#define MMC_TXFRAMECOUNT_GB_LO 0x081c +#define MMC_TXBROADCASTFRAMES_G_LO 0x0824 +#define MMC_TXMULTICASTFRAMES_G_LO 0x082c +#define MMC_TX64OCTETS_GB_LO 0x0834 +#define MMC_TX65TO127OCTETS_GB_LO 0x083c +#define MMC_TX128TO255OCTETS_GB_LO 0x0844 +#define MMC_TX256TO511OCTETS_GB_LO 0x084c +#define MMC_TX512TO1023OCTETS_GB_LO 0x0854 +#define MMC_TX1024TOMAXOCTETS_GB_LO 0x085c +#define MMC_TXUNICASTFRAMES_GB_LO 0x0864 +#define MMC_TXMULTICASTFRAMES_GB_LO 0x086c +#define MMC_TXBROADCASTFRAMES_GB_LO 0x0874 +#define MMC_TXUNDERFLOWERROR_LO 0x087c +#define MMC_TXOCTETCOUNT_G_LO 0x0884 +#define MMC_TXFRAMECOUNT_G_LO 0x088c +#define MMC_TXPAUSEFRAMES_LO 0x0894 +#define MMC_TXVLANFRAMES_G_LO 0x089c +#define MMC_RXFRAMECOUNT_GB_LO 0x0900 +#define MMC_RXOCTETCOUNT_GB_LO 0x0908 +#define MMC_RXOCTETCOUNT_G_LO 0x0910 +#define MMC_RXBROADCASTFRAMES_G_LO 0x0918 +#define MMC_RXMULTICASTFRAMES_G_LO 0x0920 +#define MMC_RXCRCERROR_LO 0x0928 +#define MMC_RXRUNTERROR 0x0930 +#define MMC_RXJABBERERROR 0x0934 +#define MMC_RXUNDERSIZE_G 0x0938 +#define MMC_RXOVERSIZE_G 0x093c +#define MMC_RX64OCTETS_GB_LO 0x0940 +#define MMC_RX65TO127OCTETS_GB_LO 0x0948 +#define MMC_RX128TO255OCTETS_GB_LO 0x0950 +#define MMC_RX256TO511OCTETS_GB_LO 0x0958 +#define MMC_RX512TO1023OCTETS_GB_LO 0x0960 +#define MMC_RX1024TOMAXOCTETS_GB_LO 0x0968 +#define MMC_RXUNICASTFRAMES_G_LO 0x0970 +#define MMC_RXLENGTHERROR_LO 0x0978 +#define MMC_RXOUTOFRANGETYPE_LO 0x0980 +#define MMC_RXPAUSEFRAMES_LO 0x0988 +#define MMC_RXFIFOOVERFLOW_LO 0x0990 +#define MMC_RXVLANFRAMES_GB_LO 0x0998 +#define MMC_RXWATCHDOGERROR 0x09a0 + +/* MMC register entry bit positions and sizes */ +#define MMC_CR_CR_POS 0 +#define MMC_CR_CR_LEN 1 +#define MMC_CR_CSR_POS 1 +#define MMC_CR_CSR_LEN 1 +#define MMC_CR_ROR_POS 2 +#define MMC_CR_ROR_LEN 1 +#define MMC_CR_MCF_POS 3 +#define MMC_CR_MCF_LEN 1 +#define MMC_CR_MCT_POS 4 +#define MMC_CR_MCT_LEN 2 +#define MMC_RIER_ALL_INTERRUPTS_POS 0 +#define MMC_RIER_ALL_INTERRUPTS_LEN 23 +#define MMC_RISR_RXFRAMECOUNT_GB_POS 0 +#define MMC_RISR_RXFRAMECOUNT_GB_LEN 1 +#define MMC_RISR_RXOCTETCOUNT_GB_POS 1 +#define MMC_RISR_RXOCTETCOUNT_GB_LEN 1 +#define MMC_RISR_RXOCTETCOUNT_G_POS 2 +#define MMC_RISR_RXOCTETCOUNT_G_LEN 1 +#define MMC_RISR_RXBROADCASTFRAMES_G_POS 3 +#define MMC_RISR_RXBROADCASTFRAMES_G_LEN 1 +#define MMC_RISR_RXMULTICASTFRAMES_G_POS 4 +#define MMC_RISR_RXMULTICASTFRAMES_G_LEN 1 +#define MMC_RISR_RXCRCERROR_POS 5 +#define MMC_RISR_RXCRCERROR_LEN 1 +#define MMC_RISR_RXRUNTERROR_POS 6 +#define MMC_RISR_RXRUNTERROR_LEN 1 +#define MMC_RISR_RXJABBERERROR_POS 7 +#define MMC_RISR_RXJABBERERROR_LEN 1 +#define MMC_RISR_RXUNDERSIZE_G_POS 8 +#define MMC_RISR_RXUNDERSIZE_G_LEN 1 +#define MMC_RISR_RXOVERSIZE_G_POS 9 +#define MMC_RISR_RXOVERSIZE_G_LEN 1 +#define MMC_RISR_RX64OCTETS_GB_POS 10 +#define MMC_RISR_RX64OCTETS_GB_LEN 1 +#define MMC_RISR_RX65TO127OCTETS_GB_POS 11 +#define MMC_RISR_RX65TO127OCTETS_GB_LEN 1 +#define MMC_RISR_RX128TO255OCTETS_GB_POS 12 +#define MMC_RISR_RX128TO255OCTETS_GB_LEN 1 +#define MMC_RISR_RX256TO511OCTETS_GB_POS 13 +#define MMC_RISR_RX256TO511OCTETS_GB_LEN 1 +#define MMC_RISR_RX512TO1023OCTETS_GB_POS 14 +#define MMC_RISR_RX512TO1023OCTETS_GB_LEN 1 +#define MMC_RISR_RX1024TOMAXOCTETS_GB_POS 15 +#define MMC_RISR_RX1024TOMAXOCTETS_GB_LEN 1 +#define MMC_RISR_RXUNICASTFRAMES_G_POS 16 +#define MMC_RISR_RXUNICASTFRAMES_G_LEN 1 +#define MMC_RISR_RXLENGTHERROR_POS 17 +#define MMC_RISR_RXLENGTHERROR_LEN 1 +#define MMC_RISR_RXOUTOFRANGETYPE_POS 18 +#define MMC_RISR_RXOUTOFRANGETYPE_LEN 1 +#define MMC_RISR_RXPAUSEFRAMES_POS 19 +#define MMC_RISR_RXPAUSEFRAMES_LEN 1 +#define MMC_RISR_RXFIFOOVERFLOW_POS 20 +#define MMC_RISR_RXFIFOOVERFLOW_LEN 1 +#define MMC_RISR_RXVLANFRAMES_GB_POS 21 +#define MMC_RISR_RXVLANFRAMES_GB_LEN 1 +#define MMC_RISR_RXWATCHDOGERROR_POS 22 +#define MMC_RISR_RXWATCHDOGERROR_LEN 1 +#define MMC_TIER_ALL_INTERRUPTS_POS 0 +#define MMC_TIER_ALL_INTERRUPTS_LEN 18 +#define MMC_TISR_TXOCTETCOUNT_GB_POS 0 +#define MMC_TISR_TXOCTETCOUNT_GB_LEN 1 +#define MMC_TISR_TXFRAMECOUNT_GB_POS 1 +#define MMC_TISR_TXFRAMECOUNT_GB_LEN 1 +#define MMC_TISR_TXBROADCASTFRAMES_G_POS 2 +#define MMC_TISR_TXBROADCASTFRAMES_G_LEN 1 +#define MMC_TISR_TXMULTICASTFRAMES_G_POS 3 +#define MMC_TISR_TXMULTICASTFRAMES_G_LEN 1 +#define MMC_TISR_TX64OCTETS_GB_POS 4 +#define MMC_TISR_TX64OCTETS_GB_LEN 1 +#define MMC_TISR_TX65TO127OCTETS_GB_POS 5 +#define MMC_TISR_TX65TO127OCTETS_GB_LEN 1 +#define MMC_TISR_TX128TO255OCTETS_GB_POS 6 +#define MMC_TISR_TX128TO255OCTETS_GB_LEN 1 +#define MMC_TISR_TX256TO511OCTETS_GB_POS 7 +#define MMC_TISR_TX256TO511OCTETS_GB_LEN 1 +#define MMC_TISR_TX512TO1023OCTETS_GB_POS 8 +#define MMC_TISR_TX512TO1023OCTETS_GB_LEN 1 +#define MMC_TISR_TX1024TOMAXOCTETS_GB_POS 9 +#define MMC_TISR_TX1024TOMAXOCTETS_GB_LEN 1 +#define MMC_TISR_TXUNICASTFRAMES_GB_POS 10 +#define MMC_TISR_TXUNICASTFRAMES_GB_LEN 1 +#define MMC_TISR_TXMULTICASTFRAMES_GB_POS 11 +#define MMC_TISR_TXMULTICASTFRAMES_GB_LEN 1 +#define MMC_TISR_TXBROADCASTFRAMES_GB_POS 12 +#define MMC_TISR_TXBROADCASTFRAMES_GB_LEN 1 +#define MMC_TISR_TXUNDERFLOWERROR_POS 13 +#define MMC_TISR_TXUNDERFLOWERROR_LEN 1 +#define MMC_TISR_TXOCTETCOUNT_G_POS 14 +#define MMC_TISR_TXOCTETCOUNT_G_LEN 1 +#define MMC_TISR_TXFRAMECOUNT_G_POS 15 +#define MMC_TISR_TXFRAMECOUNT_G_LEN 1 +#define MMC_TISR_TXPAUSEFRAMES_POS 16 +#define MMC_TISR_TXPAUSEFRAMES_LEN 1 +#define MMC_TISR_TXVLANFRAMES_G_POS 17 +#define MMC_TISR_TXVLANFRAMES_G_LEN 1 + +/* MTL register offsets */ +#define MTL_OMR 0x1000 +#define MTL_FDDR 0x1010 +#define MTL_RQDCM0R 0x1030 + +#define MTL_RQDCM_INC 4 +#define MTL_RQDCM_Q_PER_REG 4 + +/* MTL register entry bit positions and sizes */ +#define MTL_OMR_ETSALG_POS 5 +#define MTL_OMR_ETSALG_LEN 2 +#define MTL_OMR_RAA_POS 2 +#define MTL_OMR_RAA_LEN 1 + +/* MTL queue register offsets + * Multiple queues can be active. The first queue has registers + * that begin at 0x1100. Each subsequent queue has registers that + * are accessed using an offset of 0x80 from the previous queue. + */ +#define MTL_Q_BASE 0x1100 +#define MTL_Q_INC 0x80 + +#define MTL_Q_TQOMR 0x00 +#define MTL_Q_RQOMR 0x40 +#define MTL_Q_RQDR 0x48 +#define MTL_Q_RQFCR 0x50 +#define MTL_Q_IER 0x70 +#define MTL_Q_ISR 0x74 + +/* MTL queue register entry bit positions and sizes */ +#define MTL_Q_RQDR_PRXQ_POS 16 +#define MTL_Q_RQDR_PRXQ_LEN 14 +#define MTL_Q_RQDR_RXQSTS_POS 4 +#define MTL_Q_RQDR_RXQSTS_LEN 2 +#define MTL_Q_RQFCR_RFA_POS 1 +#define MTL_Q_RQFCR_RFA_LEN 6 +#define MTL_Q_RQFCR_RFD_POS 17 +#define MTL_Q_RQFCR_RFD_LEN 6 +#define MTL_Q_RQOMR_EHFC_POS 7 +#define MTL_Q_RQOMR_EHFC_LEN 1 +#define MTL_Q_RQOMR_RQS_POS 16 +#define MTL_Q_RQOMR_RQS_LEN 9 +#define MTL_Q_RQOMR_RSF_POS 5 +#define MTL_Q_RQOMR_RSF_LEN 1 +#define MTL_Q_RQOMR_FEP_POS 4 +#define MTL_Q_RQOMR_FEP_LEN 1 +#define MTL_Q_RQOMR_FUP_POS 3 +#define MTL_Q_RQOMR_FUP_LEN 1 +#define MTL_Q_RQOMR_RTC_POS 0 +#define MTL_Q_RQOMR_RTC_LEN 2 +#define MTL_Q_TQOMR_FTQ_POS 0 +#define MTL_Q_TQOMR_FTQ_LEN 1 +#define MTL_Q_TQOMR_Q2TCMAP_POS 8 +#define MTL_Q_TQOMR_Q2TCMAP_LEN 3 +#define MTL_Q_TQOMR_TQS_POS 16 +#define MTL_Q_TQOMR_TQS_LEN 10 +#define MTL_Q_TQOMR_TSF_POS 1 +#define MTL_Q_TQOMR_TSF_LEN 1 +#define MTL_Q_TQOMR_TTC_POS 4 +#define MTL_Q_TQOMR_TTC_LEN 3 +#define MTL_Q_TQOMR_TXQEN_POS 2 +#define MTL_Q_TQOMR_TXQEN_LEN 2 + +/* MTL queue register value */ +#define MTL_RSF_DISABLE 0x00 +#define MTL_RSF_ENABLE 0x01 +#define MTL_TSF_DISABLE 0x00 +#define MTL_TSF_ENABLE 0x01 + +#define MTL_RX_THRESHOLD_64 0x00 +#define MTL_RX_THRESHOLD_96 0x02 +#define MTL_RX_THRESHOLD_128 0x03 +#define MTL_TX_THRESHOLD_64 0x00 +#define MTL_TX_THRESHOLD_96 0x02 +#define MTL_TX_THRESHOLD_128 0x03 +#define MTL_TX_THRESHOLD_192 0x04 +#define MTL_TX_THRESHOLD_256 0x05 +#define MTL_TX_THRESHOLD_384 0x06 +#define MTL_TX_THRESHOLD_512 0x07 + +#define MTL_ETSALG_WRR 0x00 +#define MTL_ETSALG_WFQ 0x01 +#define MTL_ETSALG_DWRR 0x02 +#define MTL_RAA_SP 0x00 +#define MTL_RAA_WSP 0x01 + +#define MTL_Q_DISABLED 0x00 +#define MTL_Q_ENABLED 0x02 + +#define MTL_RQDCM0R_Q0MDMACH 0x0 +#define MTL_RQDCM0R_Q1MDMACH 0x00000100 +#define MTL_RQDCM0R_Q2MDMACH 0x00020000 +#define MTL_RQDCM0R_Q3MDMACH 0x03000000 +#define MTL_RQDCM1R_Q4MDMACH 0x00000004 +#define MTL_RQDCM1R_Q5MDMACH 0x00000500 +#define MTL_RQDCM1R_Q6MDMACH 0x00060000 +#define MTL_RQDCM1R_Q7MDMACH 0x07000000 +#define MTL_RQDCM2R_Q8MDMACH 0x00000008 +#define MTL_RQDCM2R_Q9MDMACH 0x00000900 +#define MTL_RQDCM2R_Q10MDMACH 0x000A0000 +#define MTL_RQDCM2R_Q11MDMACH 0x0B000000 + +/* MTL traffic class register offsets + * Multiple traffic classes can be active. The first class has registers + * that begin at 0x1100. Each subsequent queue has registers that + * are accessed using an offset of 0x80 from the previous queue. + */ +#define MTL_TC_BASE MTL_Q_BASE +#define MTL_TC_INC MTL_Q_INC + +#define MTL_TC_ETSCR 0x10 +#define MTL_TC_ETSSR 0x14 +#define MTL_TC_QWR 0x18 + +/* MTL traffic class register entry bit positions and sizes */ +#define MTL_TC_ETSCR_TSA_POS 0 +#define MTL_TC_ETSCR_TSA_LEN 2 +#define MTL_TC_QWR_QW_POS 0 +#define MTL_TC_QWR_QW_LEN 21 + +/* MTL traffic class register value */ +#define MTL_TSA_SP 0x00 +#define MTL_TSA_ETS 0x02 + +/* DMA register offsets */ +#define DMA_MR 0x3000 +#define DMA_SBMR 0x3004 +#define DMA_ISR 0x3008 +#define DMA_DSR0 0x3020 +#define DMA_DSR1 0x3024 + +/* DMA register entry bit positions and sizes */ +#define DMA_ISR_MACIS_POS 17 +#define DMA_ISR_MACIS_LEN 1 +#define DMA_ISR_MTLIS_POS 16 +#define DMA_ISR_MTLIS_LEN 1 +#define DMA_MR_SWR_POS 0 +#define DMA_MR_SWR_LEN 1 +#define DMA_SBMR_EAME_POS 11 +#define DMA_SBMR_EAME_LEN 1 +#define DMA_SBMR_BLEN_64_POS 5 +#define DMA_SBMR_BLEN_64_LEN 1 +#define DMA_SBMR_BLEN_128_POS 6 +#define DMA_SBMR_BLEN_128_LEN 1 +#define DMA_SBMR_BLEN_256_POS 7 +#define DMA_SBMR_BLEN_256_LEN 1 +#define DMA_SBMR_UNDEF_POS 0 +#define DMA_SBMR_UNDEF_LEN 1 + +/* DMA register values */ +#define DMA_DSR_RPS_LEN 4 +#define DMA_DSR_TPS_LEN 4 +#define DMA_DSR_Q_LEN (DMA_DSR_RPS_LEN + DMA_DSR_TPS_LEN) +#define DMA_DSR0_TPS_START 12 +#define DMA_DSRX_FIRST_QUEUE 3 +#define DMA_DSRX_INC 4 +#define DMA_DSRX_QPR 4 +#define DMA_DSRX_TPS_START 4 +#define DMA_TPS_STOPPED 0x00 +#define DMA_TPS_SUSPENDED 0x06 + +/* DMA channel register offsets + * Multiple channels can be active. The first channel has registers + * that begin at 0x3100. Each subsequent channel has registers that + * are accessed using an offset of 0x80 from the previous channel. + */ +#define DMA_CH_BASE 0x3100 +#define DMA_CH_INC 0x80 + +#define DMA_CH_CR 0x00 +#define DMA_CH_TCR 0x04 +#define DMA_CH_RCR 0x08 +#define DMA_CH_TDLR_HI 0x10 +#define DMA_CH_TDLR_LO 0x14 +#define DMA_CH_RDLR_HI 0x18 +#define DMA_CH_RDLR_LO 0x1c +#define DMA_CH_TDTR_LO 0x24 +#define DMA_CH_RDTR_LO 0x2c +#define DMA_CH_TDRLR 0x30 +#define DMA_CH_RDRLR 0x34 +#define DMA_CH_IER 0x38 +#define DMA_CH_RIWT 0x3c +#define DMA_CH_SR 0x60 + +/* DMA channel register entry bit positions and sizes */ +#define DMA_CH_CR_PBLX8_POS 16 +#define DMA_CH_CR_PBLX8_LEN 1 +#define DMA_CH_CR_SPH_POS 24 +#define DMA_CH_CR_SPH_LEN 1 +#define DMA_CH_IER_AIE_POS 15 +#define DMA_CH_IER_AIE_LEN 1 +#define DMA_CH_IER_FBEE_POS 12 +#define DMA_CH_IER_FBEE_LEN 1 +#define DMA_CH_IER_NIE_POS 16 +#define DMA_CH_IER_NIE_LEN 1 +#define DMA_CH_IER_RBUE_POS 7 +#define DMA_CH_IER_RBUE_LEN 1 +#define DMA_CH_IER_RIE_POS 6 +#define DMA_CH_IER_RIE_LEN 1 +#define DMA_CH_IER_RSE_POS 8 +#define DMA_CH_IER_RSE_LEN 1 +#define DMA_CH_IER_TBUE_POS 2 +#define DMA_CH_IER_TBUE_LEN 1 +#define DMA_CH_IER_TIE_POS 0 +#define DMA_CH_IER_TIE_LEN 1 +#define DMA_CH_IER_TXSE_POS 1 +#define DMA_CH_IER_TXSE_LEN 1 +#define DMA_CH_RCR_PBL_POS 16 +#define DMA_CH_RCR_PBL_LEN 6 +#define DMA_CH_RCR_RBSZ_POS 1 +#define DMA_CH_RCR_RBSZ_LEN 14 +#define DMA_CH_RCR_SR_POS 0 +#define DMA_CH_RCR_SR_LEN 1 +#define DMA_CH_RIWT_RWT_POS 0 +#define DMA_CH_RIWT_RWT_LEN 8 +#define DMA_CH_SR_FBE_POS 12 +#define DMA_CH_SR_FBE_LEN 1 +#define DMA_CH_SR_RBU_POS 7 +#define DMA_CH_SR_RBU_LEN 1 +#define DMA_CH_SR_RI_POS 6 +#define DMA_CH_SR_RI_LEN 1 +#define DMA_CH_SR_RPS_POS 8 +#define DMA_CH_SR_RPS_LEN 1 +#define DMA_CH_SR_TBU_POS 2 +#define DMA_CH_SR_TBU_LEN 1 +#define DMA_CH_SR_TI_POS 0 +#define DMA_CH_SR_TI_LEN 1 +#define DMA_CH_SR_TPS_POS 1 +#define DMA_CH_SR_TPS_LEN 1 +#define DMA_CH_TCR_OSP_POS 4 +#define DMA_CH_TCR_OSP_LEN 1 +#define DMA_CH_TCR_PBL_POS 16 +#define DMA_CH_TCR_PBL_LEN 6 +#define DMA_CH_TCR_ST_POS 0 +#define DMA_CH_TCR_ST_LEN 1 +#define DMA_CH_TCR_TSE_POS 12 +#define DMA_CH_TCR_TSE_LEN 1 + +/* DMA channel register values */ +#define DMA_OSP_DISABLE 0x00 +#define DMA_OSP_ENABLE 0x01 +#define DMA_PBL_1 1 +#define DMA_PBL_2 2 +#define DMA_PBL_4 4 +#define DMA_PBL_8 8 +#define DMA_PBL_16 16 +#define DMA_PBL_32 32 +#define DMA_PBL_64 64 +#define DMA_PBL_128 128 +#define DMA_PBL_256 256 +#define DMA_PBL_X8_DISABLE 0x00 +#define DMA_PBL_X8_ENABLE 0x01 + +/* Descriptor/Packet entry bit positions and sizes */ +#define RX_PACKET_ERRORS_CRC_POS 2 +#define RX_PACKET_ERRORS_CRC_LEN 1 +#define RX_PACKET_ERRORS_FRAME_POS 3 +#define RX_PACKET_ERRORS_FRAME_LEN 1 +#define RX_PACKET_ERRORS_LENGTH_POS 0 +#define RX_PACKET_ERRORS_LENGTH_LEN 1 +#define RX_PACKET_ERRORS_OVERRUN_POS 1 +#define RX_PACKET_ERRORS_OVERRUN_LEN 1 + +#define RX_PACKET_ATTRIBUTES_CSUM_DONE_POS 0 +#define RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN 1 +#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS 1 +#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN 1 +#define RX_PACKET_ATTRIBUTES_INCOMPLETE_POS 2 +#define RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN 1 +#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS 3 +#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN 1 +#define RX_PACKET_ATTRIBUTES_CONTEXT_POS 4 +#define RX_PACKET_ATTRIBUTES_CONTEXT_LEN 1 +#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS 5 +#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN 1 +#define RX_PACKET_ATTRIBUTES_RSS_HASH_POS 6 +#define RX_PACKET_ATTRIBUTES_RSS_HASH_LEN 1 + +#define RX_NORMAL_DESC0_OVT_POS 0 +#define RX_NORMAL_DESC0_OVT_LEN 16 +#define RX_NORMAL_DESC2_HL_POS 0 +#define RX_NORMAL_DESC2_HL_LEN 10 +#define RX_NORMAL_DESC3_CDA_POS 27 +#define RX_NORMAL_DESC3_CDA_LEN 1 +#define RX_NORMAL_DESC3_CTXT_POS 30 +#define RX_NORMAL_DESC3_CTXT_LEN 1 +#define RX_NORMAL_DESC3_ES_POS 15 +#define RX_NORMAL_DESC3_ES_LEN 1 +#define RX_NORMAL_DESC3_ETLT_POS 16 +#define RX_NORMAL_DESC3_ETLT_LEN 4 +#define RX_NORMAL_DESC3_FD_POS 29 +#define RX_NORMAL_DESC3_FD_LEN 1 +#define RX_NORMAL_DESC3_INTE_POS 30 +#define RX_NORMAL_DESC3_INTE_LEN 1 +#define RX_NORMAL_DESC3_L34T_POS 20 +#define RX_NORMAL_DESC3_L34T_LEN 4 +#define RX_NORMAL_DESC3_LD_POS 28 +#define RX_NORMAL_DESC3_LD_LEN 1 +#define RX_NORMAL_DESC3_OWN_POS 31 +#define RX_NORMAL_DESC3_OWN_LEN 1 +#define RX_NORMAL_DESC3_PL_POS 0 +#define RX_NORMAL_DESC3_PL_LEN 14 +#define RX_NORMAL_DESC3_RSV_POS 26 +#define RX_NORMAL_DESC3_RSV_LEN 1 + +#define RX_DESC3_L34T_IPV4_TCP 1 +#define RX_DESC3_L34T_IPV4_UDP 2 +#define RX_DESC3_L34T_IPV4_ICMP 3 +#define RX_DESC3_L34T_IPV6_TCP 9 +#define RX_DESC3_L34T_IPV6_UDP 10 +#define RX_DESC3_L34T_IPV6_ICMP 11 + +#define RX_CONTEXT_DESC3_TSA_POS 4 +#define RX_CONTEXT_DESC3_TSA_LEN 1 +#define RX_CONTEXT_DESC3_TSD_POS 6 +#define RX_CONTEXT_DESC3_TSD_LEN 1 + +#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS 0 +#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN 1 +#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS 1 +#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN 1 +#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS 2 +#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN 1 +#define TX_PACKET_ATTRIBUTES_PTP_POS 3 +#define TX_PACKET_ATTRIBUTES_PTP_LEN 1 + +#define TX_CONTEXT_DESC2_MSS_POS 0 +#define TX_CONTEXT_DESC2_MSS_LEN 15 +#define TX_CONTEXT_DESC3_CTXT_POS 30 +#define TX_CONTEXT_DESC3_CTXT_LEN 1 +#define TX_CONTEXT_DESC3_TCMSSV_POS 26 +#define TX_CONTEXT_DESC3_TCMSSV_LEN 1 +#define TX_CONTEXT_DESC3_VLTV_POS 16 +#define TX_CONTEXT_DESC3_VLTV_LEN 1 +#define TX_CONTEXT_DESC3_VT_POS 0 +#define TX_CONTEXT_DESC3_VT_LEN 16 + +#define TX_NORMAL_DESC2_HL_B1L_POS 0 +#define TX_NORMAL_DESC2_HL_B1L_LEN 14 +#define TX_NORMAL_DESC2_IC_POS 31 +#define TX_NORMAL_DESC2_IC_LEN 1 +#define TX_NORMAL_DESC2_TTSE_POS 30 +#define TX_NORMAL_DESC2_TTSE_LEN 1 +#define TX_NORMAL_DESC2_VTIR_POS 14 +#define TX_NORMAL_DESC2_VTIR_LEN 2 +#define TX_NORMAL_DESC3_CIC_POS 16 +#define TX_NORMAL_DESC3_CIC_LEN 2 +#define TX_NORMAL_DESC3_CPC_POS 26 +#define TX_NORMAL_DESC3_CPC_LEN 2 +#define TX_NORMAL_DESC3_CTXT_POS 30 +#define TX_NORMAL_DESC3_CTXT_LEN 1 +#define TX_NORMAL_DESC3_FD_POS 29 +#define TX_NORMAL_DESC3_FD_LEN 1 +#define TX_NORMAL_DESC3_FL_POS 0 +#define TX_NORMAL_DESC3_FL_LEN 15 +#define TX_NORMAL_DESC3_LD_POS 28 +#define TX_NORMAL_DESC3_LD_LEN 1 +#define TX_NORMAL_DESC3_OWN_POS 31 +#define TX_NORMAL_DESC3_OWN_LEN 1 +#define TX_NORMAL_DESC3_TCPHDRLEN_POS 19 +#define TX_NORMAL_DESC3_TCPHDRLEN_LEN 4 +#define TX_NORMAL_DESC3_TCPPL_POS 0 +#define TX_NORMAL_DESC3_TCPPL_LEN 18 +#define TX_NORMAL_DESC3_TSE_POS 18 +#define TX_NORMAL_DESC3_TSE_LEN 1 + +#define TX_NORMAL_DESC2_VLAN_INSERT 0x2 + +#define XLGMAC_MTL_REG(pdata, n, reg) \ + ((pdata)->mac_regs + MTL_Q_BASE + ((n) * MTL_Q_INC) + (reg)) + +#define XLGMAC_DMA_REG(channel, reg) ((channel)->dma_regs + (reg)) + +#endif /* __DWC_XLGMAC_REG_H__ */ diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h new file mode 100644 index 000000000000..7a4dc643b2b9 --- /dev/null +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h @@ -0,0 +1,651 @@ +/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver + * + * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This Synopsys DWC XLGMAC software driver and associated documentation + * (hereinafter the "Software") is an unsupported proprietary work of + * Synopsys, Inc. unless otherwise expressly agreed to in writing between + * Synopsys and you. The Software IS NOT an item of Licensed Software or a + * Licensed Product under any End User Software License Agreement or + * Agreement for Licensed Products with Synopsys or any supplement thereto. + * Synopsys is a registered trademark of Synopsys, Inc. Other names included + * in the SOFTWARE may be the trademarks of their respective owners. + */ + +#ifndef __DWC_XLGMAC_H__ +#define __DWC_XLGMAC_H__ + +#include +#include +#include +#include +#include +#include +#include + +#define XLGMAC_DRV_NAME "dwc-xlgmac" +#define XLGMAC_DRV_VERSION "1.0.0" +#define XLGMAC_DRV_DESC "Synopsys DWC XLGMAC Driver" + +/* Descriptor related parameters */ +#define XLGMAC_TX_DESC_CNT 1024 +#define XLGMAC_TX_DESC_MIN_FREE (XLGMAC_TX_DESC_CNT >> 3) +#define XLGMAC_TX_DESC_MAX_PROC (XLGMAC_TX_DESC_CNT >> 1) +#define XLGMAC_RX_DESC_CNT 1024 +#define XLGMAC_RX_DESC_MAX_DIRTY (XLGMAC_RX_DESC_CNT >> 3) + +/* Descriptors required for maximum contiguous TSO/GSO packet */ +#define XLGMAC_TX_MAX_SPLIT ((GSO_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1) + +/* Maximum possible descriptors needed for a SKB */ +#define XLGMAC_TX_MAX_DESC_NR (MAX_SKB_FRAGS + XLGMAC_TX_MAX_SPLIT + 2) + +#define XLGMAC_TX_MAX_BUF_SIZE (0x3fff & ~(64 - 1)) +#define XLGMAC_RX_MIN_BUF_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN) +#define XLGMAC_RX_BUF_ALIGN 64 + +/* Maximum Size for Splitting the Header Data + * Keep in sync with SKB_ALLOC_SIZE + * 3'b000: 64 bytes, 3'b001: 128 bytes + * 3'b010: 256 bytes, 3'b011: 512 bytes + * 3'b100: 1023 bytes , 3'b101'3'b111: Reserved + */ +#define XLGMAC_SPH_HDSMS_SIZE 3 +#define XLGMAC_SKB_ALLOC_SIZE 512 + +#define XLGMAC_MAX_FIFO 81920 + +#define XLGMAC_MAX_DMA_CHANNELS 16 +#define XLGMAC_DMA_STOP_TIMEOUT 5 +#define XLGMAC_DMA_INTERRUPT_MASK 0x31c7 + +/* Default coalescing parameters */ +#define XLGMAC_INIT_DMA_TX_USECS 1000 +#define XLGMAC_INIT_DMA_TX_FRAMES 25 +#define XLGMAC_INIT_DMA_RX_USECS 30 +#define XLGMAC_INIT_DMA_RX_FRAMES 25 + +/* Flow control queue count */ +#define XLGMAC_MAX_FLOW_CONTROL_QUEUES 8 + +/* System clock is 125 MHz */ +#define XLGMAC_SYSCLOCK 125000000 + +/* Maximum MAC address hash table size (256 bits = 8 bytes) */ +#define XLGMAC_MAC_HASH_TABLE_SIZE 8 + +/* Receive Side Scaling */ +#define XLGMAC_RSS_HASH_KEY_SIZE 40 +#define XLGMAC_RSS_MAX_TABLE_SIZE 256 +#define XLGMAC_RSS_LOOKUP_TABLE_TYPE 0 +#define XLGMAC_RSS_HASH_KEY_TYPE 1 + +#define XLGMAC_STD_PACKET_MTU 1500 +#define XLGMAC_JUMBO_PACKET_MTU 9000 + +/* Helper macro for descriptor handling + * Always use XLGMAC_GET_DESC_DATA to access the descriptor data + */ +#define XLGMAC_GET_DESC_DATA(ring, idx) ({ \ + typeof(ring) _ring = (ring); \ + ((_ring)->desc_data_head + \ + ((idx) & ((_ring)->dma_desc_count - 1))); \ +}) + +#define XLGMAC_GET_REG_BITS(var, pos, len) ({ \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + ((var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos); \ +}) + +#define XLGMAC_GET_REG_BITS_LE(var, pos, len) ({ \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + typeof(var) _var = le32_to_cpu((var)); \ + ((_var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos); \ +}) + +#define XLGMAC_SET_REG_BITS(var, pos, len, val) ({ \ + typeof(var) _var = (var); \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + typeof(val) _val = (val); \ + _val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos); \ + _var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val; \ +}) + +#define XLGMAC_SET_REG_BITS_LE(var, pos, len, val) ({ \ + typeof(var) _var = (var); \ + typeof(pos) _pos = (pos); \ + typeof(len) _len = (len); \ + typeof(val) _val = (val); \ + _val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos); \ + _var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val; \ + cpu_to_le32(_var); \ +}) + +struct xlgmac_pdata; + +enum xlgmac_int { + XLGMAC_INT_DMA_CH_SR_TI, + XLGMAC_INT_DMA_CH_SR_TPS, + XLGMAC_INT_DMA_CH_SR_TBU, + XLGMAC_INT_DMA_CH_SR_RI, + XLGMAC_INT_DMA_CH_SR_RBU, + XLGMAC_INT_DMA_CH_SR_RPS, + XLGMAC_INT_DMA_CH_SR_TI_RI, + XLGMAC_INT_DMA_CH_SR_FBE, + XLGMAC_INT_DMA_ALL, +}; + +struct xlgmac_stats { + /* MMC TX counters */ + u64 txoctetcount_gb; + u64 txframecount_gb; + u64 txbroadcastframes_g; + u64 txmulticastframes_g; + u64 tx64octets_gb; + u64 tx65to127octets_gb; + u64 tx128to255octets_gb; + u64 tx256to511octets_gb; + u64 tx512to1023octets_gb; + u64 tx1024tomaxoctets_gb; + u64 txunicastframes_gb; + u64 txmulticastframes_gb; + u64 txbroadcastframes_gb; + u64 txunderflowerror; + u64 txoctetcount_g; + u64 txframecount_g; + u64 txpauseframes; + u64 txvlanframes_g; + + /* MMC RX counters */ + u64 rxframecount_gb; + u64 rxoctetcount_gb; + u64 rxoctetcount_g; + u64 rxbroadcastframes_g; + u64 rxmulticastframes_g; + u64 rxcrcerror; + u64 rxrunterror; + u64 rxjabbererror; + u64 rxundersize_g; + u64 rxoversize_g; + u64 rx64octets_gb; + u64 rx65to127octets_gb; + u64 rx128to255octets_gb; + u64 rx256to511octets_gb; + u64 rx512to1023octets_gb; + u64 rx1024tomaxoctets_gb; + u64 rxunicastframes_g; + u64 rxlengtherror; + u64 rxoutofrangetype; + u64 rxpauseframes; + u64 rxfifooverflow; + u64 rxvlanframes_gb; + u64 rxwatchdogerror; + + /* Extra counters */ + u64 tx_tso_packets; + u64 rx_split_header_packets; + u64 rx_buffer_unavailable; +}; + +struct xlgmac_ring_buf { + struct sk_buff *skb; + dma_addr_t skb_dma; + unsigned int skb_len; +}; + +/* Common Tx and Rx DMA hardware descriptor */ +struct xlgmac_dma_desc { + __le32 desc0; + __le32 desc1; + __le32 desc2; + __le32 desc3; +}; + +/* Page allocation related values */ +struct xlgmac_page_alloc { + struct page *pages; + unsigned int pages_len; + unsigned int pages_offset; + + dma_addr_t pages_dma; +}; + +/* Ring entry buffer data */ +struct xlgmac_buffer_data { + struct xlgmac_page_alloc pa; + struct xlgmac_page_alloc pa_unmap; + + dma_addr_t dma_base; + unsigned long dma_off; + unsigned int dma_len; +}; + +/* Tx-related desc data */ +struct xlgmac_tx_desc_data { + unsigned int packets; /* BQL packet count */ + unsigned int bytes; /* BQL byte count */ +}; + +/* Rx-related desc data */ +struct xlgmac_rx_desc_data { + struct xlgmac_buffer_data hdr; /* Header locations */ + struct xlgmac_buffer_data buf; /* Payload locations */ + + unsigned short hdr_len; /* Length of received header */ + unsigned short len; /* Length of received packet */ +}; + +struct xlgmac_pkt_info { + struct sk_buff *skb; + + unsigned int attributes; + + unsigned int errors; + + /* descriptors needed for this packet */ + unsigned int desc_count; + unsigned int length; + + unsigned int tx_packets; + unsigned int tx_bytes; + + unsigned int header_len; + unsigned int tcp_header_len; + unsigned int tcp_payload_len; + unsigned short mss; + + unsigned short vlan_ctag; + + u64 rx_tstamp; + + u32 rss_hash; + enum pkt_hash_types rss_hash_type; +}; + +struct xlgmac_desc_data { + /* dma_desc: Virtual address of descriptor + * dma_desc_addr: DMA address of descriptor + */ + struct xlgmac_dma_desc *dma_desc; + dma_addr_t dma_desc_addr; + + /* skb: Virtual address of SKB + * skb_dma: DMA address of SKB data + * skb_dma_len: Length of SKB DMA area + */ + struct sk_buff *skb; + dma_addr_t skb_dma; + unsigned int skb_dma_len; + + /* Tx/Rx -related data */ + struct xlgmac_tx_desc_data tx; + struct xlgmac_rx_desc_data rx; + + unsigned int mapped_as_page; + + /* Incomplete receive save location. If the budget is exhausted + * or the last descriptor (last normal descriptor or a following + * context descriptor) has not been DMA'd yet the current state + * of the receive processing needs to be saved. + */ + unsigned int state_saved; + struct { + struct sk_buff *skb; + unsigned int len; + unsigned int error; + } state; +}; + +struct xlgmac_ring { + /* Per packet related information */ + struct xlgmac_pkt_info pkt_info; + + /* Virtual/DMA addresses of DMA descriptor list and the total count */ + struct xlgmac_dma_desc *dma_desc_head; + dma_addr_t dma_desc_head_addr; + unsigned int dma_desc_count; + + /* Array of descriptor data corresponding the DMA descriptor + * (always use the XLGMAC_GET_DESC_DATA macro to access this data) + */ + struct xlgmac_desc_data *desc_data_head; + + /* Page allocation for RX buffers */ + struct xlgmac_page_alloc rx_hdr_pa; + struct xlgmac_page_alloc rx_buf_pa; + + /* Ring index values + * cur - Tx: index of descriptor to be used for current transfer + * Rx: index of descriptor to check for packet availability + * dirty - Tx: index of descriptor to check for transfer complete + * Rx: index of descriptor to check for buffer reallocation + */ + unsigned int cur; + unsigned int dirty; + + /* Coalesce frame count used for interrupt bit setting */ + unsigned int coalesce_count; + + union { + struct { + unsigned int xmit_more; + unsigned int queue_stopped; + unsigned short cur_mss; + unsigned short cur_vlan_ctag; + } tx; + }; +} ____cacheline_aligned; + +struct xlgmac_channel { + char name[16]; + + /* Address of private data area for device */ + struct xlgmac_pdata *pdata; + + /* Queue index and base address of queue's DMA registers */ + unsigned int queue_index; + void __iomem *dma_regs; + + /* Per channel interrupt irq number */ + int dma_irq; + char dma_irq_name[IFNAMSIZ + 32]; + + /* Netdev related settings */ + struct napi_struct napi; + + unsigned int saved_ier; + + unsigned int tx_timer_active; + struct timer_list tx_timer; + + struct xlgmac_ring *tx_ring; + struct xlgmac_ring *rx_ring; +} ____cacheline_aligned; + +struct xlgmac_desc_ops { + int (*alloc_channles_and_rings)(struct xlgmac_pdata *pdata); + void (*free_channels_and_rings)(struct xlgmac_pdata *pdata); + int (*map_tx_skb)(struct xlgmac_channel *channel, + struct sk_buff *skb); + int (*map_rx_buffer)(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + struct xlgmac_desc_data *desc_data); + void (*unmap_desc_data)(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data); + void (*tx_desc_init)(struct xlgmac_pdata *pdata); + void (*rx_desc_init)(struct xlgmac_pdata *pdata); +}; + +struct xlgmac_hw_ops { + int (*init)(struct xlgmac_pdata *pdata); + int (*exit)(struct xlgmac_pdata *pdata); + + int (*tx_complete)(struct xlgmac_dma_desc *dma_desc); + + void (*enable_tx)(struct xlgmac_pdata *pdata); + void (*disable_tx)(struct xlgmac_pdata *pdata); + void (*enable_rx)(struct xlgmac_pdata *pdata); + void (*disable_rx)(struct xlgmac_pdata *pdata); + + int (*enable_int)(struct xlgmac_channel *channel, + enum xlgmac_int int_id); + int (*disable_int)(struct xlgmac_channel *channel, + enum xlgmac_int int_id); + void (*dev_xmit)(struct xlgmac_channel *channel); + int (*dev_read)(struct xlgmac_channel *channel); + + int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr); + int (*config_rx_mode)(struct xlgmac_pdata *pdata); + int (*enable_rx_csum)(struct xlgmac_pdata *pdata); + int (*disable_rx_csum)(struct xlgmac_pdata *pdata); + + /* For MII speed configuration */ + int (*set_xlgmii_25000_speed)(struct xlgmac_pdata *pdata); + int (*set_xlgmii_40000_speed)(struct xlgmac_pdata *pdata); + int (*set_xlgmii_50000_speed)(struct xlgmac_pdata *pdata); + int (*set_xlgmii_100000_speed)(struct xlgmac_pdata *pdata); + + /* For descriptor related operation */ + void (*tx_desc_init)(struct xlgmac_channel *channel); + void (*rx_desc_init)(struct xlgmac_channel *channel); + void (*tx_desc_reset)(struct xlgmac_desc_data *desc_data); + void (*rx_desc_reset)(struct xlgmac_pdata *pdata, + struct xlgmac_desc_data *desc_data, + unsigned int index); + int (*is_last_desc)(struct xlgmac_dma_desc *dma_desc); + int (*is_context_desc)(struct xlgmac_dma_desc *dma_desc); + void (*tx_start_xmit)(struct xlgmac_channel *channel, + struct xlgmac_ring *ring); + + /* For Flow Control */ + int (*config_tx_flow_control)(struct xlgmac_pdata *pdata); + int (*config_rx_flow_control)(struct xlgmac_pdata *pdata); + + /* For Vlan related config */ + int (*enable_rx_vlan_stripping)(struct xlgmac_pdata *pdata); + int (*disable_rx_vlan_stripping)(struct xlgmac_pdata *pdata); + int (*enable_rx_vlan_filtering)(struct xlgmac_pdata *pdata); + int (*disable_rx_vlan_filtering)(struct xlgmac_pdata *pdata); + int (*update_vlan_hash_table)(struct xlgmac_pdata *pdata); + + /* For RX coalescing */ + int (*config_rx_coalesce)(struct xlgmac_pdata *pdata); + int (*config_tx_coalesce)(struct xlgmac_pdata *pdata); + unsigned int (*usec_to_riwt)(struct xlgmac_pdata *pdata, + unsigned int usec); + unsigned int (*riwt_to_usec)(struct xlgmac_pdata *pdata, + unsigned int riwt); + + /* For RX and TX threshold config */ + int (*config_rx_threshold)(struct xlgmac_pdata *pdata, + unsigned int val); + int (*config_tx_threshold)(struct xlgmac_pdata *pdata, + unsigned int val); + + /* For RX and TX Store and Forward Mode config */ + int (*config_rsf_mode)(struct xlgmac_pdata *pdata, + unsigned int val); + int (*config_tsf_mode)(struct xlgmac_pdata *pdata, + unsigned int val); + + /* For TX DMA Operate on Second Frame config */ + int (*config_osp_mode)(struct xlgmac_pdata *pdata); + + /* For RX and TX PBL config */ + int (*config_rx_pbl_val)(struct xlgmac_pdata *pdata); + int (*get_rx_pbl_val)(struct xlgmac_pdata *pdata); + int (*config_tx_pbl_val)(struct xlgmac_pdata *pdata); + int (*get_tx_pbl_val)(struct xlgmac_pdata *pdata); + int (*config_pblx8)(struct xlgmac_pdata *pdata); + + /* For MMC statistics */ + void (*rx_mmc_int)(struct xlgmac_pdata *pdata); + void (*tx_mmc_int)(struct xlgmac_pdata *pdata); + void (*read_mmc_stats)(struct xlgmac_pdata *pdata); + + /* For Receive Side Scaling */ + int (*enable_rss)(struct xlgmac_pdata *pdata); + int (*disable_rss)(struct xlgmac_pdata *pdata); + int (*set_rss_hash_key)(struct xlgmac_pdata *pdata, + const u8 *key); + int (*set_rss_lookup_table)(struct xlgmac_pdata *pdata, + const u32 *table); +}; + +/* This structure contains flags that indicate what hardware features + * or configurations are present in the device. + */ +struct xlgmac_hw_features { + /* HW Version */ + unsigned int version; + + /* HW Feature Register0 */ + unsigned int phyifsel; /* PHY interface support */ + unsigned int vlhash; /* VLAN Hash Filter */ + unsigned int sma; /* SMA(MDIO) Interface */ + unsigned int rwk; /* PMT remote wake-up packet */ + unsigned int mgk; /* PMT magic packet */ + unsigned int mmc; /* RMON module */ + unsigned int aoe; /* ARP Offload */ + unsigned int ts; /* IEEE 1588-2008 Advanced Timestamp */ + unsigned int eee; /* Energy Efficient Ethernet */ + unsigned int tx_coe; /* Tx Checksum Offload */ + unsigned int rx_coe; /* Rx Checksum Offload */ + unsigned int addn_mac; /* Additional MAC Addresses */ + unsigned int ts_src; /* Timestamp Source */ + unsigned int sa_vlan_ins; /* Source Address or VLAN Insertion */ + + /* HW Feature Register1 */ + unsigned int rx_fifo_size; /* MTL Receive FIFO Size */ + unsigned int tx_fifo_size; /* MTL Transmit FIFO Size */ + unsigned int adv_ts_hi; /* Advance Timestamping High Word */ + unsigned int dma_width; /* DMA width */ + unsigned int dcb; /* DCB Feature */ + unsigned int sph; /* Split Header Feature */ + unsigned int tso; /* TCP Segmentation Offload */ + unsigned int dma_debug; /* DMA Debug Registers */ + unsigned int rss; /* Receive Side Scaling */ + unsigned int tc_cnt; /* Number of Traffic Classes */ + unsigned int hash_table_size; /* Hash Table Size */ + unsigned int l3l4_filter_num; /* Number of L3-L4 Filters */ + + /* HW Feature Register2 */ + unsigned int rx_q_cnt; /* Number of MTL Receive Queues */ + unsigned int tx_q_cnt; /* Number of MTL Transmit Queues */ + unsigned int rx_ch_cnt; /* Number of DMA Receive Channels */ + unsigned int tx_ch_cnt; /* Number of DMA Transmit Channels */ + unsigned int pps_out_num; /* Number of PPS outputs */ + unsigned int aux_snap_num; /* Number of Aux snapshot inputs */ +}; + +struct xlgmac_resources { + void __iomem *addr; + int irq; +}; + +struct xlgmac_pdata { + struct net_device *netdev; + struct device *dev; + + struct xlgmac_hw_ops hw_ops; + struct xlgmac_desc_ops desc_ops; + + /* Device statistics */ + struct xlgmac_stats stats; + + u32 msg_enable; + + /* MAC registers base */ + void __iomem *mac_regs; + + /* Hardware features of the device */ + struct xlgmac_hw_features hw_feat; + + struct work_struct restart_work; + + /* Rings for Tx/Rx on a DMA channel */ + struct xlgmac_channel *channel_head; + unsigned int channel_count; + unsigned int tx_ring_count; + unsigned int rx_ring_count; + unsigned int tx_desc_count; + unsigned int rx_desc_count; + unsigned int tx_q_count; + unsigned int rx_q_count; + + /* Tx/Rx common settings */ + unsigned int pblx8; + + /* Tx settings */ + unsigned int tx_sf_mode; + unsigned int tx_threshold; + unsigned int tx_pbl; + unsigned int tx_osp_mode; + + /* Rx settings */ + unsigned int rx_sf_mode; + unsigned int rx_threshold; + unsigned int rx_pbl; + + /* Tx coalescing settings */ + unsigned int tx_usecs; + unsigned int tx_frames; + + /* Rx coalescing settings */ + unsigned int rx_riwt; + unsigned int rx_usecs; + unsigned int rx_frames; + + /* Current Rx buffer size */ + unsigned int rx_buf_size; + + /* Flow control settings */ + unsigned int tx_pause; + unsigned int rx_pause; + + /* Device interrupt number */ + int dev_irq; + unsigned int per_channel_irq; + int channel_irq[XLGMAC_MAX_DMA_CHANNELS]; + + /* Netdev related settings */ + unsigned char mac_addr[ETH_ALEN]; + netdev_features_t netdev_features; + struct napi_struct napi; + + /* Filtering support */ + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + + /* Device clocks */ + unsigned long sysclk_rate; + + /* RSS addressing mutex */ + struct mutex rss_mutex; + + /* Receive Side Scaling settings */ + u8 rss_key[XLGMAC_RSS_HASH_KEY_SIZE]; + u32 rss_table[XLGMAC_RSS_MAX_TABLE_SIZE]; + u32 rss_options; + + int phy_speed; + + char drv_name[32]; + char drv_ver[32]; +}; + +void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops); +void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops); +const struct net_device_ops *xlgmac_get_netdev_ops(void); +void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx, + unsigned int count, + unsigned int flag); +void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata, + struct xlgmac_ring *ring, + unsigned int idx); +void xlgmac_print_pkt(struct net_device *netdev, + struct sk_buff *skb, bool tx_rx); +void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata); +void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata); +int xlgmac_drv_probe(struct device *dev, + struct xlgmac_resources *res); +int xlgmac_drv_remove(struct device *dev); + +/* For debug prints */ +#ifdef XLGMAC_DEBUG +#define XLGMAC_PR(fmt, args...) \ + pr_alert("[%s,%d]:" fmt, __func__, __LINE__, ## args) +#else +#define XLGMAC_PR(x...) do { } while (0) +#endif + +#endif /* __DWC_XLGMAC_H__ */ From 581319c58600b54612c417aff32ae9bbd79f4cdb Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Mar 2017 13:54:08 +0100 Subject: [PATCH 105/399] net/socket: use per af lockdep classes for sk queues Currently the sock queue's spin locks get their lockdep classes by the default init_spin_lock() initializer: all socket families get - usually, see below - a single class for rx, another specific class for tx, etc. This can lead to false positive lockdep splat, as reported by Andrey. Moreover there are two separate initialization points for the sock queues, one in sk_clone_lock() and one in sock_init_data(), so that e.g. the rx queue lock can get one of two possible, different classes, depending on the socket being cloned or not. This change tries to address the above, setting explicitly a per address family lockdep class for each queue's spinlock. Also, move the duplicated initialization code to a single location. v1 -> v2: - renamed the init helper rfc -> v1: - no changes, tested with several different workload Suggested-by: Cong Wang Signed-off-by: Paolo Abeni Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 96 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 78 insertions(+), 18 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index f6fd79f33097..768aedf238f5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -258,12 +258,66 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX" }; +static const char *const af_family_rlock_key_strings[AF_MAX+1] = { + "rlock-AF_UNSPEC", "rlock-AF_UNIX" , "rlock-AF_INET" , + "rlock-AF_AX25" , "rlock-AF_IPX" , "rlock-AF_APPLETALK", + "rlock-AF_NETROM", "rlock-AF_BRIDGE" , "rlock-AF_ATMPVC" , + "rlock-AF_X25" , "rlock-AF_INET6" , "rlock-AF_ROSE" , + "rlock-AF_DECnet", "rlock-AF_NETBEUI" , "rlock-AF_SECURITY" , + "rlock-AF_KEY" , "rlock-AF_NETLINK" , "rlock-AF_PACKET" , + "rlock-AF_ASH" , "rlock-AF_ECONET" , "rlock-AF_ATMSVC" , + "rlock-AF_RDS" , "rlock-AF_SNA" , "rlock-AF_IRDA" , + "rlock-AF_PPPOX" , "rlock-AF_WANPIPE" , "rlock-AF_LLC" , + "rlock-27" , "rlock-28" , "rlock-AF_CAN" , + "rlock-AF_TIPC" , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV" , + "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" , + "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" , + "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" , + "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX" +}; +static const char *const af_family_wlock_key_strings[AF_MAX+1] = { + "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" , + "wlock-AF_AX25" , "wlock-AF_IPX" , "wlock-AF_APPLETALK", + "wlock-AF_NETROM", "wlock-AF_BRIDGE" , "wlock-AF_ATMPVC" , + "wlock-AF_X25" , "wlock-AF_INET6" , "wlock-AF_ROSE" , + "wlock-AF_DECnet", "wlock-AF_NETBEUI" , "wlock-AF_SECURITY" , + "wlock-AF_KEY" , "wlock-AF_NETLINK" , "wlock-AF_PACKET" , + "wlock-AF_ASH" , "wlock-AF_ECONET" , "wlock-AF_ATMSVC" , + "wlock-AF_RDS" , "wlock-AF_SNA" , "wlock-AF_IRDA" , + "wlock-AF_PPPOX" , "wlock-AF_WANPIPE" , "wlock-AF_LLC" , + "wlock-27" , "wlock-28" , "wlock-AF_CAN" , + "wlock-AF_TIPC" , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV" , + "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" , + "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" , + "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" , + "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX" +}; +static const char *const af_family_elock_key_strings[AF_MAX+1] = { + "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" , + "elock-AF_AX25" , "elock-AF_IPX" , "elock-AF_APPLETALK", + "elock-AF_NETROM", "elock-AF_BRIDGE" , "elock-AF_ATMPVC" , + "elock-AF_X25" , "elock-AF_INET6" , "elock-AF_ROSE" , + "elock-AF_DECnet", "elock-AF_NETBEUI" , "elock-AF_SECURITY" , + "elock-AF_KEY" , "elock-AF_NETLINK" , "elock-AF_PACKET" , + "elock-AF_ASH" , "elock-AF_ECONET" , "elock-AF_ATMSVC" , + "elock-AF_RDS" , "elock-AF_SNA" , "elock-AF_IRDA" , + "elock-AF_PPPOX" , "elock-AF_WANPIPE" , "elock-AF_LLC" , + "elock-27" , "elock-28" , "elock-AF_CAN" , + "elock-AF_TIPC" , "elock-AF_BLUETOOTH", "elock-AF_IUCV" , + "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" , + "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" , + "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" , + "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX" +}; /* - * sk_callback_lock locking rules are per-address-family, + * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; +static struct lock_class_key af_rlock_keys[AF_MAX]; +static struct lock_class_key af_wlock_keys[AF_MAX]; +static struct lock_class_key af_elock_keys[AF_MAX]; /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across @@ -1478,6 +1532,27 @@ void sk_free(struct sock *sk) } EXPORT_SYMBOL(sk_free); +static void sk_init_common(struct sock *sk) +{ + skb_queue_head_init(&sk->sk_receive_queue); + skb_queue_head_init(&sk->sk_write_queue); + skb_queue_head_init(&sk->sk_error_queue); + + rwlock_init(&sk->sk_callback_lock); + lockdep_set_class_and_name(&sk->sk_receive_queue.lock, + af_rlock_keys + sk->sk_family, + af_family_rlock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_write_queue.lock, + af_wlock_keys + sk->sk_family, + af_family_wlock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_error_queue.lock, + af_elock_keys + sk->sk_family, + af_family_elock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_callback_lock, + af_callback_keys + sk->sk_family, + af_family_clock_key_strings[sk->sk_family]); +} + /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone @@ -1511,13 +1586,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ atomic_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); - skb_queue_head_init(&newsk->sk_receive_queue); - skb_queue_head_init(&newsk->sk_write_queue); - - rwlock_init(&newsk->sk_callback_lock); - lockdep_set_class_and_name(&newsk->sk_callback_lock, - af_callback_keys + newsk->sk_family, - af_family_clock_key_strings[newsk->sk_family]); + sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; @@ -1528,7 +1597,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; sock_reset_flag(newsk, SOCK_DONE); - skb_queue_head_init(&newsk->sk_error_queue); filter = rcu_dereference_protected(newsk->sk_filter, 1); if (filter != NULL) @@ -2454,10 +2522,7 @@ EXPORT_SYMBOL(sk_stop_timer); void sock_init_data(struct socket *sock, struct sock *sk) { - skb_queue_head_init(&sk->sk_receive_queue); - skb_queue_head_init(&sk->sk_write_queue); - skb_queue_head_init(&sk->sk_error_queue); - + sk_init_common(sk); sk->sk_send_head = NULL; init_timer(&sk->sk_timer); @@ -2480,11 +2545,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0); } - rwlock_init(&sk->sk_callback_lock); - lockdep_set_class_and_name(&sk->sk_callback_lock, - af_callback_keys + sk->sk_family, - af_family_clock_key_strings[sk->sk_family]); - sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; From abb521e36b9286c262971974ebaeda2d67dadd86 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:00 -0800 Subject: [PATCH 106/399] ethtool: add CRC32 as an RSS hash function CRC32 engines are usually easily available in hardware and generate OK spread for RSS hash. Add CRC32 RSS hash function to ethtool API. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/ethtool.h | 2 ++ net/core/ethtool.c | 1 + 2 files changed, 3 insertions(+) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9ded8c6d8176..83cc9863444b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -60,6 +60,7 @@ enum ethtool_phys_id_state { enum { ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */ ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */ + ETH_RSS_HASH_CRC32_BIT, /* Configurable RSS hash function - Crc32 */ /* * Add your fresh new hash function bits above and remember to update @@ -73,6 +74,7 @@ enum { #define ETH_RSS_HASH_TOP __ETH_RSS_HASH(TOP) #define ETH_RSS_HASH_XOR __ETH_RSS_HASH(XOR) +#define ETH_RSS_HASH_CRC32 __ETH_RSS_HASH(CRC32) #define ETH_RSS_HASH_UNKNOWN 0 #define ETH_RSS_HASH_NO_CHANGE 0 diff --git a/net/core/ethtool.c b/net/core/ethtool.c index aecb2c7241b6..905a88ad28e0 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -109,6 +109,7 @@ static const char rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { [ETH_RSS_HASH_TOP_BIT] = "toeplitz", [ETH_RSS_HASH_XOR_BIT] = "xor", + [ETH_RSS_HASH_CRC32_BIT] = "crc32", }; static const char From 9ff304bfaf58c119ef8ba3e20326edeed9983aef Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:01 -0800 Subject: [PATCH 107/399] nfp: add support for reporting CRC32 hash function Some firmware images may reuse CRC32 hardware to compute RXHASH. Make sure we report the correct hash function. Note that we don't support changing functions at runtime. That would also require a few more additions to the way the key is set because different functions have different key sizes. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 3 ++ .../ethernet/netronome/nfp/nfp_net_common.c | 46 +++++++++++++++++-- .../net/ethernet/netronome/nfp/nfp_net_ctrl.h | 14 +++++- .../ethernet/netronome/nfp/nfp_net_ethtool.c | 23 +++++++--- 4 files changed, 75 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index e614a376b595..9843e953bbed 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -446,6 +446,7 @@ struct nfp_stat_pair { * @fw_ver: Firmware version * @cap: Capabilities advertised by the Firmware * @max_mtu: Maximum support MTU advertised by the Firmware + * @rss_hfunc: RSS selected hash function * @rss_cfg: RSS configuration * @rss_key: RSS secret key * @rss_itbl: RSS indirection table @@ -518,6 +519,7 @@ struct nfp_net { u32 cap; u32 max_mtu; + u8 rss_hfunc; u32 rss_cfg; u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ]; u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ]; @@ -776,6 +778,7 @@ void nfp_net_netdev_clean(struct net_device *netdev); void nfp_net_set_ethtool_ops(struct net_device *netdev); void nfp_net_info(struct nfp_net *nn); int nfp_net_reconfig(struct nfp_net *nn, u32 update); +unsigned int nfp_net_rss_key_sz(struct nfp_net *nn); void nfp_net_rss_write_itbl(struct nfp_net *nn); void nfp_net_rss_write_key(struct nfp_net *nn); void nfp_net_coalesce_write_cfg(struct nfp_net *nn); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 9179a99563af..e72468d65c28 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -41,6 +41,7 @@ * Chris Telfer */ +#include #include #include #include @@ -2045,7 +2046,7 @@ void nfp_net_rss_write_key(struct nfp_net *nn) { int i; - for (i = 0; i < NFP_NET_CFG_RSS_KEY_SZ; i += 4) + for (i = 0; i < nfp_net_rss_key_sz(nn); i += 4) nn_writel(nn, NFP_NET_CFG_RSS_KEY + i, get_unaligned_le32(nn->rss_key + i)); } @@ -3111,20 +3112,59 @@ void nfp_net_netdev_free(struct nfp_net *nn) free_netdev(nn->netdev); } +/** + * nfp_net_rss_key_sz() - Get current size of the RSS key + * @nn: NFP Net device instance + * + * Return: size of the RSS key for currently selected hash function. + */ +unsigned int nfp_net_rss_key_sz(struct nfp_net *nn) +{ + switch (nn->rss_hfunc) { + case ETH_RSS_HASH_TOP: + return NFP_NET_CFG_RSS_KEY_SZ; + case ETH_RSS_HASH_XOR: + return 0; + case ETH_RSS_HASH_CRC32: + return 4; + } + + nn_warn(nn, "Unknown hash function: %u\n", nn->rss_hfunc); + return 0; +} + /** * nfp_net_rss_init() - Set the initial RSS parameters * @nn: NFP Net device to reconfigure */ static void nfp_net_rss_init(struct nfp_net *nn) { - netdev_rss_key_fill(nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ); + unsigned long func_bit, rss_cap_hfunc; + u32 reg; + + /* Read the RSS function capability and select first supported func */ + reg = nn_readl(nn, NFP_NET_CFG_RSS_CAP); + rss_cap_hfunc = FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC, reg); + if (!rss_cap_hfunc) + rss_cap_hfunc = FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC, + NFP_NET_CFG_RSS_TOEPLITZ); + + func_bit = find_first_bit(&rss_cap_hfunc, NFP_NET_CFG_RSS_HFUNCS); + if (func_bit == NFP_NET_CFG_RSS_HFUNCS) { + dev_warn(&nn->pdev->dev, + "Bad RSS config, defaulting to Toeplitz hash\n"); + func_bit = ETH_RSS_HASH_TOP_BIT; + } + nn->rss_hfunc = 1 << func_bit; + + netdev_rss_key_fill(nn->rss_key, nfp_net_rss_key_sz(nn)); nfp_net_rss_init_itbl(nn); /* Enable IPv4/IPv6 TCP by default */ nn->rss_cfg = NFP_NET_CFG_RSS_IPV4_TCP | NFP_NET_CFG_RSS_IPV6_TCP | - NFP_NET_CFG_RSS_TOEPLITZ | + FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc) | NFP_NET_CFG_RSS_MASK; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 385ba355c965..71d86171b4ee 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Netronome Systems, Inc. + * Copyright (C) 2015-2017 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -191,6 +191,14 @@ #define NFP_NET_CFG_RX_OFFSET 0x0050 #define NFP_NET_CFG_RX_OFFSET_DYNAMIC 0 /* Prepend mode */ +/** + * RSS capabilities + * @NFP_NET_CFG_RSS_CAP_HFUNC: supported hash functions (same bits as + * @NFP_NET_CFG_RSS_HFUNC) + */ +#define NFP_NET_CFG_RSS_CAP 0x0054 +#define NFP_NET_CFG_RSS_CAP_HFUNC 0xff000000 + /** * VXLAN/UDP encap configuration * @NFP_NET_CFG_VXLAN_PORT: Base address of table of tunnels' UDP dst ports @@ -249,7 +257,11 @@ #define NFP_NET_CFG_RSS_IPV4_UDP (1 << 11) /* RSS for IPv4/UDP */ #define NFP_NET_CFG_RSS_IPV6_TCP (1 << 12) /* RSS for IPv6/TCP */ #define NFP_NET_CFG_RSS_IPV6_UDP (1 << 13) /* RSS for IPv6/UDP */ +#define NFP_NET_CFG_RSS_HFUNC 0xff000000 #define NFP_NET_CFG_RSS_TOEPLITZ (1 << 24) /* Use Toeplitz hash */ +#define NFP_NET_CFG_RSS_XOR (1 << 25) /* Use XOR as hash */ +#define NFP_NET_CFG_RSS_CRC32 (1 << 26) /* Use CRC32 as hash */ +#define NFP_NET_CFG_RSS_HFUNCS 3 #define NFP_NET_CFG_RSS_KEY (NFP_NET_CFG_RSS_BASE + 0x4) #define NFP_NET_CFG_RSS_KEY_SZ 0x28 #define NFP_NET_CFG_RSS_ITBL (NFP_NET_CFG_RSS_BASE + 0x4 + \ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 2649f7523c81..a1bca2dca0a5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -40,6 +40,7 @@ * Brad Petrus */ +#include #include #include #include @@ -454,7 +455,7 @@ static int nfp_net_set_rss_hash_opt(struct nfp_net *nn, return -EINVAL; } - new_rss_cfg |= NFP_NET_CFG_RSS_TOEPLITZ; + new_rss_cfg |= FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc); new_rss_cfg |= NFP_NET_CFG_RSS_MASK; if (new_rss_cfg == nn->rss_cfg) @@ -496,7 +497,12 @@ static u32 nfp_net_get_rxfh_indir_size(struct net_device *netdev) static u32 nfp_net_get_rxfh_key_size(struct net_device *netdev) { - return NFP_NET_CFG_RSS_KEY_SZ; + struct nfp_net *nn = netdev_priv(netdev); + + if (!(nn->cap & NFP_NET_CFG_CTRL_RSS)) + return -EOPNOTSUPP; + + return nfp_net_rss_key_sz(nn); } static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, @@ -512,9 +518,12 @@ static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++) indir[i] = nn->rss_itbl[i]; if (key) - memcpy(key, nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ); - if (hfunc) - *hfunc = ETH_RSS_HASH_TOP; + memcpy(key, nn->rss_key, nfp_net_rss_key_sz(nn)); + if (hfunc) { + *hfunc = nn->rss_hfunc; + if (*hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT) + *hfunc = ETH_RSS_HASH_UNKNOWN; + } return 0; } @@ -527,14 +536,14 @@ static int nfp_net_set_rxfh(struct net_device *netdev, int i; if (!(nn->cap & NFP_NET_CFG_CTRL_RSS) || - !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == ETH_RSS_HASH_TOP)) + !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == nn->rss_hfunc)) return -EOPNOTSUPP; if (!key && !indir) return 0; if (key) { - memcpy(nn->rss_key, key, NFP_NET_CFG_RSS_KEY_SZ); + memcpy(nn->rss_key, key, nfp_net_rss_key_sz(nn)); nfp_net_rss_write_key(nn); } if (indir) { From 47465aed3220c3b95646bd53d3a6fd11cbf1ebfe Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:02 -0800 Subject: [PATCH 108/399] nfp: implement .ndo_get_phys_port_name() NSP reports to us port labels. First id is the id of the physical port, the other one tells us which logical interface is it within a split port. Instead of printing them as string keep them in integer format. Compute which interfaces are part of port split. On netdev side use port labels and split information to provide a .ndo_get_phys_port_name() implementation. We follow the name format of mlxsw which is also suggested in "Port Netdev Naming" section of Documentation/networking/switchdev.txt. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 4 +++ .../ethernet/netronome/nfp/nfp_net_common.c | 22 +++++++++++++ .../net/ethernet/netronome/nfp/nfp_net_main.c | 2 ++ .../netronome/nfp/nfpcore/nfp_nsp_eth.c | 31 +++++++++++++++++-- .../netronome/nfp/nfpcore/nfp_nsp_eth.h | 15 +++++++-- 5 files changed, 69 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 9843e953bbed..50413eea9540 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -112,6 +112,7 @@ /* Forward declarations */ struct nfp_cpp; +struct nfp_eth_table_port; struct nfp_net; struct nfp_net_r_vector; @@ -496,6 +497,7 @@ struct nfp_stat_pair { * @ethtool_dump_flag: Ethtool dump flag * @port_list: Entry on device port list * @cpp: CPP device handle if available + * @eth_port: Translated ETH Table port entry */ struct nfp_net { struct pci_dev *pdev; @@ -587,6 +589,8 @@ struct nfp_net { struct list_head port_list; struct nfp_cpp *cpp; + + struct nfp_eth_table_port *eth_port; }; struct nfp_net_ring_set { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index e72468d65c28..5c34f79053f7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -67,6 +67,7 @@ #include #include +#include "nfpcore/nfp_nsp_eth.h" #include "nfp_net_ctrl.h" #include "nfp_net.h" @@ -2831,6 +2832,26 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev, return features; } +static int +nfp_net_get_phys_port_name(struct net_device *netdev, char *name, size_t len) +{ + struct nfp_net *nn = netdev_priv(netdev); + int err; + + if (!nn->eth_port) + return -EOPNOTSUPP; + + if (!nn->eth_port->is_split) + err = snprintf(name, len, "p%d", nn->eth_port->label_port); + else + err = snprintf(name, len, "p%ds%d", nn->eth_port->label_port, + nn->eth_port->label_subport); + if (err >= len) + return -EINVAL; + + return 0; +} + /** * nfp_net_set_vxlan_port() - set vxlan port in SW and reconfigure HW * @nn: NFP Net device to reconfigure @@ -3009,6 +3030,7 @@ static const struct net_device_ops nfp_net_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_set_features = nfp_net_set_features, .ndo_features_check = nfp_net_features_check, + .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_udp_tunnel_add = nfp_net_add_vxlan_port, .ndo_udp_tunnel_del = nfp_net_del_vxlan_port, .ndo_xdp = nfp_net_xdp, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 3afcdc11480c..f04d0b8e84ad 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -178,6 +178,8 @@ nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_pf *pf, unsigned int id) if (pf->eth_tbl->ports[i].eth_index == id) { const u8 *mac_addr = pf->eth_tbl->ports[i].mac_addr; + nn->eth_port = &pf->eth_tbl->ports[i]; + ether_addr_copy(nn->netdev->dev_addr, mac_addr); ether_addr_copy(nn->netdev->perm_addr, mac_addr); return; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c index 1ece1f8ae4b3..10a0c8392d2b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c @@ -134,9 +134,32 @@ nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index, nfp_eth_copy_mac_reverse(dst->mac_addr, src->mac_addr); - snprintf(dst->label, sizeof(dst->label) - 1, "%llu.%llu", - FIELD_GET(NSP_ETH_PORT_PHYLABEL, port), - FIELD_GET(NSP_ETH_PORT_LABEL, port)); + dst->label_port = FIELD_GET(NSP_ETH_PORT_PHYLABEL, port); + dst->label_subport = FIELD_GET(NSP_ETH_PORT_LABEL, port); +} + +static void +nfp_eth_mark_split_ports(struct nfp_cpp *cpp, struct nfp_eth_table *table) +{ + unsigned int i, j; + + for (i = 0; i < table->count; i++) + for (j = 0; j < table->count; j++) { + if (i == j) + continue; + if (table->ports[i].label_port != + table->ports[j].label_port) + continue; + if (table->ports[i].label_subport == + table->ports[j].label_subport) + nfp_warn(cpp, + "Port %d subport %d is a duplicate\n", + table->ports[i].label_port, + table->ports[i].label_subport); + + table->ports[i].is_split = true; + break; + } } /** @@ -203,6 +226,8 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) nfp_eth_port_translate(&entries[i], i, &table->ports[j++]); + nfp_eth_mark_split_ports(cpp, table); + kfree(entries); return table; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h index edf703d319c8..325e841ca90a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h @@ -49,10 +49,13 @@ * @lanes: number of channels * @speed: interface speed (in Mbps) * @mac_addr: interface MAC address - * @label: interface id string + * @label_port: port id + * @label_subport: id of interface within port (for split ports) * @enabled: is enabled? * @tx_enabled: is TX enabled? * @rx_enabled: is RX enabled? + * + * @is_split: is interface part of a split port */ struct nfp_eth_table { unsigned int count; @@ -65,14 +68,22 @@ struct nfp_eth_table { unsigned int speed; u8 mac_addr[ETH_ALEN]; - char label[8]; + + u8 label_port; + u8 label_subport; bool enabled; bool tx_enabled; bool rx_enabled; + + /* Computed fields */ + bool is_split; } ports[0]; }; +struct nfp_cpp; +struct nfp_nsp; + struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp); struct nfp_eth_table * __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp); From 43860c1211650ef4f2e03413cacb3420fdb69cde Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:03 -0800 Subject: [PATCH 109/399] nfp: move more ring debug info to debugfs We already print most of ring configuration including descriptors in debugfs, add the few missing pieces and remove debug prints. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 9 --------- .../net/ethernet/netronome/nfp/nfp_net_debugfs.c | 13 +++++++++---- 2 files changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 5c34f79053f7..0be47188fd36 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1776,11 +1776,6 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask, tx_ring->idx); - nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p %s\n", - tx_ring->idx, tx_ring->qcidx, - tx_ring->cnt, (unsigned long long)tx_ring->dma, tx_ring->txds, - is_xdp ? "XDP" : ""); - return 0; err_alloc: @@ -1900,10 +1895,6 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz, if (!rx_ring->rxbufs) goto err_alloc; - nn_dbg(nn, "RxQ%02d: FlQCidx=%02d RxQCidx=%02d cnt=%d dma=%#llx host=%p\n", - rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx, - rx_ring->cnt, (unsigned long long)rx_ring->dma, rx_ring->rxds); - return 0; err_alloc: diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c index 6e9372a18375..edfa59e51fdd 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c @@ -64,8 +64,10 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data) rx_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_rx); rx_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_rx); - seq_printf(file, "RX[%02d]: H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d RX_RD=%d RX_WR=%d\n", - rx_ring->idx, rx_ring->rd_p, rx_ring->wr_p, + seq_printf(file, "RX[%02d,%02d,%02d]: cnt=%d dma=%pad host=%p H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d RX_RD=%d RX_WR=%d\n", + rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx, + rx_ring->cnt, &rx_ring->dma, rx_ring->rxds, + rx_ring->rd_p, rx_ring->wr_p, fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p); for (i = 0; i < rxd_cnt; i++) { @@ -151,8 +153,11 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data) d_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q); d_wr_p = nfp_qcp_wr_ptr_read(tx_ring->qcp_q); - seq_printf(file, "TX[%02d]: H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n", - tx_ring->idx, tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p); + seq_printf(file, "TX[%02d,%02d%s]: cnt=%d dma=%pad host=%p H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n", + tx_ring->idx, tx_ring->qcidx, + tx_ring == r_vec->tx_ring ? "" : "xdp", + tx_ring->cnt, &tx_ring->dma, tx_ring->txds, + tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p); for (i = 0; i < txd_cnt; i++) { txd = &tx_ring->txds[i]; From bef6b1b7a6ffaa9afc8776c5e09e4ea11ac1727e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:04 -0800 Subject: [PATCH 110/399] nfp: reorder variables in nfp_net_tx() Reorder variables longest to shortest to comply with netdev coding style. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 0be47188fd36..8b5fa6fe8807 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -739,10 +739,10 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); const struct skb_frag_struct *frag; - struct nfp_net_r_vector *r_vec; struct nfp_net_tx_desc *txd, txdg; - struct nfp_net_tx_buf *txbuf; struct nfp_net_tx_ring *tx_ring; + struct nfp_net_r_vector *r_vec; + struct nfp_net_tx_buf *txbuf; struct netdev_queue *nd_q; dma_addr_t dma_addr; unsigned int fsize; From fa43d2a895e61defdd32f6ed825740bd2f08106c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:05 -0800 Subject: [PATCH 111/399] nfp: store device pointer for the fastpath We really only need the device pointer on the fast path, stash it at the beginning of the adapter structure and move pci_dev pointer down. This saves up a few lines of code. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 6 ++- .../ethernet/netronome/nfp/nfp_net_common.c | 51 ++++++++----------- .../net/ethernet/netronome/nfp/nfp_net_main.c | 5 +- .../ethernet/netronome/nfp/nfp_net_offload.c | 7 ++- 4 files changed, 31 insertions(+), 38 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 50413eea9540..4ad27570b6c4 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -435,7 +435,7 @@ struct nfp_stat_pair { /** * struct nfp_net - NFP network device structure - * @pdev: Backpointer to PCI device + * @dev: Backpointer to struct device * @netdev: Backpointer to net_device structure * @is_vf: Is the driver attached to a VF? * @bpf_offload_skip_sw: Offloaded BPF program will not be rerun by cls_bpf @@ -496,11 +496,12 @@ struct nfp_stat_pair { * @debugfs_dir: Device directory in debugfs * @ethtool_dump_flag: Ethtool dump flag * @port_list: Entry on device port list + * @pdev: Backpointer to PCI device * @cpp: CPP device handle if available * @eth_port: Translated ETH Table port entry */ struct nfp_net { - struct pci_dev *pdev; + struct device *dev; struct net_device *netdev; unsigned is_vf:1; @@ -588,6 +589,7 @@ struct nfp_net { struct list_head port_list; + struct pci_dev *pdev; struct nfp_cpp *cpp; struct nfp_eth_table_port *eth_port; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 8b5fa6fe8807..397d9e82ed0e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -89,7 +89,7 @@ static dma_addr_t nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz, int direction) { - return dma_map_single(&nn->pdev->dev, frag + NFP_NET_RX_BUF_HEADROOM, + return dma_map_single(nn->dev, frag + NFP_NET_RX_BUF_HEADROOM, bufsz - NFP_NET_RX_BUF_NON_DATA, direction); } @@ -97,7 +97,7 @@ static void nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr, unsigned int bufsz, int direction) { - dma_unmap_single(&nn->pdev->dev, dma_addr, + dma_unmap_single(nn->dev, dma_addr, bufsz - NFP_NET_RX_BUF_NON_DATA, direction); } @@ -768,9 +768,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) } /* Start with the head skbuf */ - dma_addr = dma_map_single(&nn->pdev->dev, skb->data, skb_headlen(skb), + dma_addr = dma_map_single(nn->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); - if (dma_mapping_error(&nn->pdev->dev, dma_addr)) + if (dma_mapping_error(nn->dev, dma_addr)) goto err_free; wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1); @@ -812,9 +812,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[f]; fsize = skb_frag_size(frag); - dma_addr = skb_frag_dma_map(&nn->pdev->dev, frag, 0, + dma_addr = skb_frag_dma_map(nn->dev, frag, 0, fsize, DMA_TO_DEVICE); - if (dma_mapping_error(&nn->pdev->dev, dma_addr)) + if (dma_mapping_error(nn->dev, dma_addr)) goto err_unmap; wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1); @@ -853,8 +853,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) --f; while (f >= 0) { frag = &skb_shinfo(skb)->frags[f]; - dma_unmap_page(&nn->pdev->dev, - tx_ring->txbufs[wr_idx].dma_addr, + dma_unmap_page(nn->dev, tx_ring->txbufs[wr_idx].dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); tx_ring->txbufs[wr_idx].skb = NULL; tx_ring->txbufs[wr_idx].dma_addr = 0; @@ -863,7 +862,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) if (wr_idx < 0) wr_idx += tx_ring->cnt; } - dma_unmap_single(&nn->pdev->dev, tx_ring->txbufs[wr_idx].dma_addr, + dma_unmap_single(nn->dev, tx_ring->txbufs[wr_idx].dma_addr, skb_headlen(skb), DMA_TO_DEVICE); tx_ring->txbufs[wr_idx].skb = NULL; tx_ring->txbufs[wr_idx].dma_addr = 0; @@ -920,8 +919,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) if (fidx == -1) { /* unmap head */ - dma_unmap_single(&nn->pdev->dev, - tx_ring->txbufs[idx].dma_addr, + dma_unmap_single(nn->dev, tx_ring->txbufs[idx].dma_addr, skb_headlen(skb), DMA_TO_DEVICE); done_pkts += tx_ring->txbufs[idx].pkt_cnt; @@ -929,8 +927,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) } else { /* unmap fragment */ frag = &skb_shinfo(skb)->frags[fidx]; - dma_unmap_page(&nn->pdev->dev, - tx_ring->txbufs[idx].dma_addr, + dma_unmap_page(nn->dev, tx_ring->txbufs[idx].dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); } @@ -1027,7 +1024,6 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; const struct skb_frag_struct *frag; - struct pci_dev *pdev = nn->pdev; struct netdev_queue *nd_q; while (tx_ring->rd_p != tx_ring->wr_p) { @@ -1047,13 +1043,13 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) if (tx_buf->fidx == -1) { /* unmap head */ - dma_unmap_single(&pdev->dev, tx_buf->dma_addr, + dma_unmap_single(nn->dev, tx_buf->dma_addr, skb_headlen(skb), DMA_TO_DEVICE); } else { /* unmap fragment */ frag = &skb_shinfo(skb)->frags[tx_buf->fidx]; - dma_unmap_page(&pdev->dev, tx_buf->dma_addr, + dma_unmap_page(nn->dev, tx_buf->dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); } @@ -1157,7 +1153,7 @@ nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; *dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction); - if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) { + if (dma_mapping_error(nn->dev, *dma_addr)) { nfp_net_free_frag(frag, xdp); nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n"); return NULL; @@ -1181,7 +1177,7 @@ nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr) } *dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction); - if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) { + if (dma_mapping_error(nn->dev, *dma_addr)) { nfp_net_free_frag(frag, nn->xdp_prog); nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n"); return NULL; @@ -1499,7 +1495,7 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, txbuf->pkt_cnt = 1; txbuf->real_len = pkt_len; - dma_sync_single_for_device(&nn->pdev->dev, rxbuf->dma_addr + pkt_off, + dma_sync_single_for_device(nn->dev, rxbuf->dma_addr + pkt_off, pkt_len, DMA_BIDIRECTIONAL); /* Build TX descriptor */ @@ -1611,7 +1607,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) nn->bpf_offload_xdp)) { int act; - dma_sync_single_for_cpu(&nn->pdev->dev, + dma_sync_single_for_cpu(nn->dev, rxbuf->dma_addr + pkt_off, pkt_len, DMA_BIDIRECTIONAL); act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off, @@ -1728,12 +1724,11 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; kfree(tx_ring->txbufs); if (tx_ring->txds) - dma_free_coherent(&pdev->dev, tx_ring->size, + dma_free_coherent(nn->dev, tx_ring->size, tx_ring->txds, tx_ring->dma); tx_ring->cnt = 0; @@ -1756,13 +1751,12 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; int sz; tx_ring->cnt = cnt; tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt; - tx_ring->txds = dma_zalloc_coherent(&pdev->dev, tx_ring->size, + tx_ring->txds = dma_zalloc_coherent(nn->dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); if (!tx_ring->txds) goto err_alloc; @@ -1849,12 +1843,11 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) { struct nfp_net_r_vector *r_vec = rx_ring->r_vec; struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; kfree(rx_ring->rxbufs); if (rx_ring->rxds) - dma_free_coherent(&pdev->dev, rx_ring->size, + dma_free_coherent(nn->dev, rx_ring->size, rx_ring->rxds, rx_ring->dma); rx_ring->cnt = 0; @@ -1878,14 +1871,13 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz, { struct nfp_net_r_vector *r_vec = rx_ring->r_vec; struct nfp_net *nn = r_vec->nfp_net; - struct pci_dev *pdev = nn->pdev; int sz; rx_ring->cnt = cnt; rx_ring->bufsz = fl_bufsz; rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt; - rx_ring->rxds = dma_zalloc_coherent(&pdev->dev, rx_ring->size, + rx_ring->rxds = dma_zalloc_coherent(nn->dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->rxds) goto err_alloc; @@ -3089,6 +3081,7 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev, nn = netdev_priv(netdev); nn->netdev = netdev; + nn->dev = &pdev->dev; nn->pdev = pdev; nn->max_tx_rings = max_tx_rings; @@ -3164,7 +3157,7 @@ static void nfp_net_rss_init(struct nfp_net *nn) func_bit = find_first_bit(&rss_cap_hfunc, NFP_NET_CFG_RSS_HFUNCS); if (func_bit == NFP_NET_CFG_RSS_HFUNCS) { - dev_warn(&nn->pdev->dev, + dev_warn(nn->dev, "Bad RSS config, defaulting to Toeplitz hash\n"); func_bit = ETH_RSS_HASH_TOP_BIT; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index f04d0b8e84ad..8a9b3f3b95a8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -141,8 +141,7 @@ nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp, mac_str = nfp_hwinfo_lookup(cpp, name); if (!mac_str) { - dev_warn(&nn->pdev->dev, - "Can't lookup MAC address. Generate\n"); + dev_warn(nn->dev, "Can't lookup MAC address. Generate\n"); eth_hw_addr_random(nn->netdev); return; } @@ -150,7 +149,7 @@ nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp, if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx", &mac_addr[0], &mac_addr[1], &mac_addr[2], &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) { - dev_warn(&nn->pdev->dev, + dev_warn(nn->dev, "Can't parse MAC address (%s). Generate.\n", mac_str); eth_hw_addr_random(nn->netdev); return; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c index 18a851eb3508..f6ed1aa9d94b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c @@ -168,8 +168,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, start_off = nn_readw(nn, NFP_NET_CFG_BPF_START); done_off = nn_readw(nn, NFP_NET_CFG_BPF_DONE); - *code = dma_zalloc_coherent(&nn->pdev->dev, code_sz, dma_addr, - GFP_KERNEL); + *code = dma_zalloc_coherent(nn->dev, code_sz, dma_addr, GFP_KERNEL); if (!*code) return -ENOMEM; @@ -181,7 +180,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, return 0; out: - dma_free_coherent(&nn->pdev->dev, code_sz, *code, *dma_addr); + dma_free_coherent(nn->dev, code_sz, *code, *dma_addr); return ret; } @@ -214,7 +213,7 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags, if (err) nn_err(nn, "FW command error while enabling BPF: %d\n", err); - dma_free_coherent(&nn->pdev->dev, code_sz, code, dma_addr); + dma_free_coherent(nn->dev, code_sz, code, dma_addr); nfp_net_bpf_stats_reset(nn); mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL); From 7de5f115e1fd8a6df7aa89078cb70700e725173d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:06 -0800 Subject: [PATCH 112/399] nfp: avoid rearming the interrupts when in busy poll Make use of return code from napi_complete_done() to avoid rearming interrupts when busy polling is on. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 397d9e82ed0e..119775d4097e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1705,10 +1705,9 @@ static int nfp_net_poll(struct napi_struct *napi, int budget) nfp_net_xdp_complete(r_vec->xdp_ring); } - if (pkts_polled < budget) { - napi_complete_done(napi, pkts_polled); - nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); - } + if (pkts_polled < budget) + if (napi_complete_done(napi, pkts_polled)) + nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); return pkts_polled; } From b9dcf88a47ebab2743a0c627a95126c4cb3e9883 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Mar 2017 08:57:07 -0800 Subject: [PATCH 113/399] nfp: add metadata format bit We only need FW version in the first cache line of adapter struct because we need to know the metadata format. To save space add a metadata format bit. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 2 ++ drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 4ad27570b6c4..34f8c439f42f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -440,6 +440,7 @@ struct nfp_stat_pair { * @is_vf: Is the driver attached to a VF? * @bpf_offload_skip_sw: Offloaded BPF program will not be rerun by cls_bpf * @bpf_offload_xdp: Offloaded BPF program is XDP + * @chained_metadata_format: Firemware will use new metadata format * @ctrl: Local copy of the control register/word. * @fl_bufsz: Currently configured size of the freelist buffers * @rx_offset: Offset in the RX buffers where packet data starts @@ -507,6 +508,7 @@ struct nfp_net { unsigned is_vf:1; unsigned bpf_offload_skip_sw:1; unsigned bpf_offload_xdp:1; + unsigned chained_metadata_format:1; u32 ctrl; u32 fl_bufsz; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 119775d4097e..2d964d030dbe 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1652,7 +1652,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) skb_reserve(skb, data_off); skb_put(skb, pkt_len); - if (nn->fw_ver.major <= 3) { + if (!nn->chained_metadata_format) { nfp_net_set_hash_desc(nn->netdev, skb, rxd); } else if (meta_len) { void *end; @@ -3196,6 +3196,8 @@ int nfp_net_netdev_init(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); int err; + nn->chained_metadata_format = nn->fw_ver.major > 3; + /* Get some of the read-only fields from the BAR */ nn->cap = nn_readl(nn, NFP_NET_CFG_CAP); nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU); From 5692dbb56e6012c0755614ee64fe4c221f357e7a Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 8 Mar 2017 08:57:08 -0800 Subject: [PATCH 114/399] nfp: prevent theoretical buffer overrun in nfp_eth_read_ports Prevent theoretical buffer overrun by returning an error if the number of entries returned by the firmware does not match those present. Also use a common handling error path. Found by inspection. Signed-off-by: Simon Horman Tested-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../netronome/nfp/nfpcore/nfp_nsp_eth.c | 34 +++++++++++-------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c index 10a0c8392d2b..38bd80077e33 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c @@ -191,8 +191,7 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) { struct eth_table_entry *entries; struct nfp_eth_table *table; - unsigned int cnt; - int i, j, ret; + int i, j, ret, cnt = 0; entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL); if (!entries) @@ -201,24 +200,27 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE); if (ret < 0) { nfp_err(cpp, "reading port table failed %d\n", ret); - kfree(entries); - return NULL; + goto err; } - /* Some versions of flash will give us 0 instead of port count */ - cnt = ret; - if (!cnt) { - for (i = 0; i < NSP_ETH_MAX_COUNT; i++) - if (entries[i].port & NSP_ETH_PORT_LANES_MASK) - cnt++; + for (i = 0; i < NSP_ETH_MAX_COUNT; i++) + if (entries[i].port & NSP_ETH_PORT_LANES_MASK) + cnt++; + + /* Some versions of flash will give us 0 instead of port count. + * For those that give a port count, verify it against the value + * calculated above. + */ + if (ret && ret != cnt) { + nfp_err(cpp, "table entry count reported (%d) does not match entries present (%d)\n", + ret, cnt); + goto err; } table = kzalloc(sizeof(*table) + sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL); - if (!table) { - kfree(entries); - return NULL; - } + if (!table) + goto err; table->count = cnt; for (i = 0, j = 0; i < NSP_ETH_MAX_COUNT; i++) @@ -231,6 +233,10 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) kfree(entries); return table; + +err: + kfree(entries); + return NULL; } /** From d5e73f7be850323ae3adbbe84ed37a38b0c31476 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 8 Mar 2017 10:55:51 -0800 Subject: [PATCH 115/399] bonding: restructure arp-monitor In preparation to move the work-queue initialization to port creation from current port_open phase. Work-queue initialization does not make sense every time we do 'ifup/ifdown'. So moving to port creation phase. Arp monitoring work depends on the bonding mode and that is not tied to the port creation and can change anytime during the life after port creation. So this restructuring allows us to move the initialization at creation without losing the ability to arm the correct work for the mode user has selected. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8a4ba8b88e52..619f0c65f18a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2575,10 +2575,8 @@ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, * arp is transmitted to generate traffic. see activebackup_arp_monitor for * arp monitoring in active backup mode. */ -static void bond_loadbalance_arp_mon(struct work_struct *work) +static void bond_loadbalance_arp_mon(struct bonding *bond) { - struct bonding *bond = container_of(work, struct bonding, - arp_work.work); struct slave *slave, *oldcurrent; struct list_head *iter; int do_failover = 0, slave_state_changed = 0; @@ -2916,10 +2914,8 @@ static bool bond_ab_arp_probe(struct bonding *bond) return should_notify_rtnl; } -static void bond_activebackup_arp_mon(struct work_struct *work) +static void bond_activebackup_arp_mon(struct bonding *bond) { - struct bonding *bond = container_of(work, struct bonding, - arp_work.work); bool should_notify_peers = false; bool should_notify_rtnl = false; int delta_in_ticks; @@ -2972,6 +2968,17 @@ static void bond_activebackup_arp_mon(struct work_struct *work) } } +static void bond_arp_monitor(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + arp_work.work); + + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) + bond_activebackup_arp_mon(bond); + else + bond_loadbalance_arp_mon(bond); +} + /*-------------------------- netdev event handling --------------------------*/ /* Change device name */ @@ -3228,10 +3235,7 @@ static void bond_work_init_all(struct bonding *bond) bond_resend_igmp_join_requests_delayed); INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); - if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) - INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon); - else - INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon); + INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor); INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler); } From 4493b81bea24269df898339dee638d7c5cb2b2df Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 8 Mar 2017 10:55:54 -0800 Subject: [PATCH 116/399] bonding: initialize work-queues during creation of bond Initializing work-queues every time ifup operation performed is unnecessary and can be performed only once when the port is created. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 619f0c65f18a..1329110ed85f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3270,8 +3270,6 @@ static int bond_open(struct net_device *bond_dev) } } - bond_work_init_all(bond); - if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. @@ -4691,6 +4689,8 @@ int bond_create(struct net *net, const char *name) netif_carrier_off(bond_dev); + bond_work_init_all(bond); + rtnl_unlock(); if (res < 0) bond_destructor(bond_dev); From 8b426dc54cf4056984bab7dfa48c92ee79a46434 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 8 Mar 2017 10:55:56 -0800 Subject: [PATCH 117/399] bonding: remove hardcoded value Eliminate hard-coded value and use the default that is set. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1329110ed85f..0f9f5ceae80e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4254,6 +4254,7 @@ static int bond_check_params(struct bond_params *params) int arp_all_targets_value; u16 ad_actor_sys_prio = 0; u16 ad_user_port_key = 0; + int tlb_dynamic_lb = 0; /* Convert string parameters. */ if (mode) { @@ -4566,6 +4567,17 @@ static int bond_check_params(struct bond_params *params) } ad_user_port_key = valptr->value; + if (bond_mode == BOND_MODE_TLB) { + bond_opt_initstr(&newval, "default"); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), + &newval); + if (!valptr) { + pr_err("Error: No tlb_dynamic_lb default value"); + return -EINVAL; + } + tlb_dynamic_lb = valptr->value; + } + if (lp_interval == 0) { pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); @@ -4593,7 +4605,7 @@ static int bond_check_params(struct bond_params *params) params->min_links = min_links; params->lp_interval = lp_interval; params->packets_per_slave = packets_per_slave; - params->tlb_dynamic_lb = 1; /* Default value */ + params->tlb_dynamic_lb = tlb_dynamic_lb; params->ad_actor_sys_prio = ad_actor_sys_prio; eth_zero_addr(params->ad_actor_system); params->ad_user_port_key = ad_user_port_key; From ec891c8b8da2c3862a5f76ba72f6d140c418d812 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 8 Mar 2017 10:55:59 -0800 Subject: [PATCH 118/399] bonding: remove "port-moved" state that was never implemented LACP state-machine defines "port-moved" state when the same ActorSystemID and Port are seen in a LACPDU received on different port. The state is never set since it's not implemented. However the state-machine attempts to clear that state occasionally. LACP state machine is already complicated and since this state is not implemented, removing it's checks makes the state-machine little simpler. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index edc70ffad660..431926bba9f4 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1052,8 +1052,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) port->sm_rx_state = AD_RX_INITIALIZE; port->sm_vars |= AD_PORT_CHURNED; /* check if port is not enabled */ - } else if (!(port->sm_vars & AD_PORT_BEGIN) - && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED)) + } else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled) port->sm_rx_state = AD_RX_PORT_DISABLED; /* check if new lacpdu arrived */ else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) || @@ -1081,11 +1080,8 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) /* if no lacpdu arrived and no timer is on */ switch (port->sm_rx_state) { case AD_RX_PORT_DISABLED: - if (port->sm_vars & AD_PORT_MOVED) - port->sm_rx_state = AD_RX_INITIALIZE; - else if (port->is_enabled - && (port->sm_vars - & AD_PORT_LACP_ENABLED)) + if (port->is_enabled && + (port->sm_vars & AD_PORT_LACP_ENABLED)) port->sm_rx_state = AD_RX_EXPIRED; else if (port->is_enabled && ((port->sm_vars @@ -1115,7 +1111,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) port->sm_vars &= ~AD_PORT_SELECTED; __record_default(port); port->actor_oper_port_state &= ~AD_STATE_EXPIRED; - port->sm_vars &= ~AD_PORT_MOVED; port->sm_rx_state = AD_RX_PORT_DISABLED; /* Fall Through */ From dc9c4d0fe023b508f1b41dbe2a3f3133f81b4d29 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 8 Mar 2017 10:56:02 -0800 Subject: [PATCH 119/399] bonding: reduce scope of some global variables Many of the bond param variables are declared global while it's not really necessary for these variables to be global. So moving them to the location these are used. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0f9f5ceae80e..ba934020dfaa 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -201,12 +201,6 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0); unsigned int bond_net_id __read_mostly; -static __be32 arp_target[BOND_MAX_ARP_TARGETS]; -static int arp_ip_count; -static int bond_mode = BOND_MODE_ROUNDROBIN; -static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; -static int lacp_fast; - /*-------------------------- Forward declarations ---------------------------*/ static int bond_init(struct net_device *bond_dev); @@ -4254,6 +4248,11 @@ static int bond_check_params(struct bond_params *params) int arp_all_targets_value; u16 ad_actor_sys_prio = 0; u16 ad_user_port_key = 0; + __be32 arp_target[BOND_MAX_ARP_TARGETS]; + int arp_ip_count; + int bond_mode = BOND_MODE_ROUNDROBIN; + int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; + int lacp_fast = 0; int tlb_dynamic_lb = 0; /* Convert string parameters. */ From 9efd3831d5ae3babb45a37ae7d6b18642a0745de Mon Sep 17 00:00:00 2001 From: Sergey Shcherbakov Date: Thu, 9 Mar 2017 02:58:14 +0200 Subject: [PATCH 120/399] net: ks8851: Added support for half-duplex SPI In original driver was implemented support for half- and full-duplex modes, but it was not enabled. Instead of it ks8851_rx_1msg method always returns "true" that means "full-duplex" mode. This patch replaces hard-coded functionality with flexible solution that supports both SPI modes. Signed-off-by: Sergey Shcherbakov Signed-off-by: David S. Miller --- drivers/net/ethernet/micrel/ks8851.c | 41 ++++++++-------------------- 1 file changed, 11 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c index 279ee4612981..20358f87de57 100644 --- a/drivers/net/ethernet/micrel/ks8851.c +++ b/drivers/net/ethernet/micrel/ks8851.c @@ -211,25 +211,6 @@ static void ks8851_wrreg8(struct ks8851_net *ks, unsigned reg, unsigned val) netdev_err(ks->netdev, "spi_sync() failed\n"); } -/** - * ks8851_rx_1msg - select whether to use one or two messages for spi read - * @ks: The device structure - * - * Return whether to generate a single message with a tx and rx buffer - * supplied to spi_sync(), or alternatively send the tx and rx buffers - * as separate messages. - * - * Depending on the hardware in use, a single message may be more efficient - * on interrupts or work done by the driver. - * - * This currently always returns true until we add some per-device data passed - * from the platform code to specify which mode is better. - */ -static inline bool ks8851_rx_1msg(struct ks8851_net *ks) -{ - return true; -} - /** * ks8851_rdreg - issue read register command and return the data * @ks: The device state @@ -251,14 +232,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op, txb[0] = cpu_to_le16(op | KS_SPIOP_RD); - if (ks8851_rx_1msg(ks)) { - msg = &ks->spi_msg1; - xfer = &ks->spi_xfer1; - - xfer->tx_buf = txb; - xfer->rx_buf = trx; - xfer->len = rxl + 2; - } else { + if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) { msg = &ks->spi_msg2; xfer = ks->spi_xfer2; @@ -270,15 +244,22 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op, xfer->tx_buf = NULL; xfer->rx_buf = trx; xfer->len = rxl; + } else { + msg = &ks->spi_msg1; + xfer = &ks->spi_xfer1; + + xfer->tx_buf = txb; + xfer->rx_buf = trx; + xfer->len = rxl + 2; } ret = spi_sync(ks->spidev, msg); if (ret < 0) netdev_err(ks->netdev, "read: spi_sync() failed\n"); - else if (ks8851_rx_1msg(ks)) - memcpy(rxb, trx + 2, rxl); - else + else if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) memcpy(rxb, trx, rxl); + else + memcpy(rxb, trx + 2, rxl); } /** From a30aad50c26cac63026e5dfcc2e055ae63fe6ef7 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Thu, 9 Mar 2017 13:53:55 +0300 Subject: [PATCH 121/399] tcp: rename *_sequence_number() to *_seq_and_tsoff() The functions that are returning tcp sequence number also setup TS offset value, so rename them to better describe their purpose. No functional changes in this patch. Suggested-by: Eric Dumazet Signed-off-by: Alexey Kodanev Signed-off-by: David S. Miller --- include/net/secure_seq.h | 6 +++--- include/net/tcp.h | 2 +- net/core/secure_seq.c | 13 ++++++------- net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_ipv4.c | 22 +++++++++++----------- net/ipv6/tcp_ipv6.c | 22 +++++++++++----------- 6 files changed, 34 insertions(+), 35 deletions(-) diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index 0caee631a836..fe236b3429f0 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -6,10 +6,10 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, +u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, u32 *tsoff); +u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport, u32 *tsoff); -u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport, u32 *tsoff); u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ec4ea652f3f..bede8f7fa742 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1816,7 +1816,7 @@ struct tcp_request_sock_ops { struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req, bool *strict); - __u32 (*init_seq)(const struct sk_buff *skb, u32 *tsoff); + __u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 758f140b6bed..fb87e78a2cc7 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -45,8 +45,8 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport, u32 *tsoff) { const struct { struct in6_addr saddr; @@ -66,7 +66,7 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0; return seq_scale(hash); } -EXPORT_SYMBOL(secure_tcpv6_sequence_number); +EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -89,14 +89,13 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #ifdef CONFIG_INET -/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), +/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ - -u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, u32 *tsoff) { u64 hash; net_secret_init(); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 39c393cc0fd3..96b67a8b18c3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6324,7 +6324,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; if (isn && tmp_opt.tstamp_ok) - af_ops->init_seq(skb, &tcp_rsk(req)->ts_off); + af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); if (!want_cookie && !isn) { /* VJ's idea. We save last timestamp seen @@ -6366,7 +6366,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq(skb, &tcp_rsk(req)->ts_off); + isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); } if (!dst) { dst = af_ops->route_req(sk, &fl, req, NULL); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9a89b8deafae..7b332ed66488 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -94,12 +94,12 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) { - return secure_tcp_sequence_number(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source, tsoff); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -236,11 +236,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = NULL; if (likely(!tp->repair)) { - seq = secure_tcp_sequence_number(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port, - &tp->tsoffset); + seq = secure_tcp_seq_and_tsoff(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port, + &tp->tsoffset); if (!tp->write_seq) tp->write_seq = seq; } @@ -1249,7 +1249,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq = tcp_v4_init_sequence, + .init_seq_tsoff = tcp_v4_init_seq_and_tsoff, .send_synack = tcp_v4_send_synack, }; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 60a5295a7de6..56f742fff967 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -101,12 +101,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) { - return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source, tsoff); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, @@ -287,11 +287,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { - seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport, - &tp->tsoffset); + seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport, + &tp->tsoffset); if (!tp->write_seq) tp->write_seq = seq; } @@ -755,7 +755,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq = tcp_v6_init_sequence, + .init_seq_tsoff = tcp_v6_init_seq_and_tsoff, .send_synack = tcp_v6_send_synack, }; From a150201a70da3bcbe76c85c255c6ab2d342c3278 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 9 Mar 2017 09:25:19 +0100 Subject: [PATCH 122/399] mlxsw: spectrum: Add support for vlan modify TC action Add VLAN action offloading. Invoke it from Spectrum flower handler for "vlan modify" actions. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../mellanox/mlxsw/core_acl_flex_actions.c | 83 +++++++++++++++++++ .../mellanox/mlxsw/core_acl_flex_actions.h | 2 + .../net/ethernet/mellanox/mlxsw/spectrum.h | 3 + .../ethernet/mellanox/mlxsw/spectrum_acl.c | 29 +++++++ .../ethernet/mellanox/mlxsw/spectrum_flower.c | 10 +++ include/net/tc_act/tc_vlan.h | 5 ++ 6 files changed, 132 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index 5f337715a4da..fe3c6ea16a99 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -567,6 +567,89 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, return oneact + MLXSW_AFA_PAYLOAD_OFFSET; } +/* VLAN Action + * ----------- + * VLAN action is used for manipulating VLANs. It can be used to implement QinQ, + * VLAN translation, change of PCP bits of the VLAN tag, push, pop as swap VLANs + * and more. + */ + +#define MLXSW_AFA_VLAN_CODE 0x02 +#define MLXSW_AFA_VLAN_SIZE 1 + +enum mlxsw_afa_vlan_vlan_tag_cmd { + MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP, + MLXSW_AFA_VLAN_VLAN_TAG_CMD_PUSH_TAG, + MLXSW_AFA_VLAN_VLAN_TAG_CMD_POP_TAG, +}; + +enum mlxsw_afa_vlan_cmd { + MLXSW_AFA_VLAN_CMD_NOP, + MLXSW_AFA_VLAN_CMD_SET_OUTER, + MLXSW_AFA_VLAN_CMD_SET_INNER, + MLXSW_AFA_VLAN_CMD_COPY_OUTER_TO_INNER, + MLXSW_AFA_VLAN_CMD_COPY_INNER_TO_OUTER, + MLXSW_AFA_VLAN_CMD_SWAP, +}; + +/* afa_vlan_vlan_tag_cmd + * Tag command: push, pop, nop VLAN header. + */ +MLXSW_ITEM32(afa, vlan, vlan_tag_cmd, 0x00, 29, 3); + +/* afa_vlan_vid_cmd */ +MLXSW_ITEM32(afa, vlan, vid_cmd, 0x04, 29, 3); + +/* afa_vlan_vid */ +MLXSW_ITEM32(afa, vlan, vid, 0x04, 0, 12); + +/* afa_vlan_ethertype_cmd */ +MLXSW_ITEM32(afa, vlan, ethertype_cmd, 0x08, 29, 3); + +/* afa_vlan_ethertype + * Index to EtherTypes in Switch VLAN EtherType Register (SVER). + */ +MLXSW_ITEM32(afa, vlan, ethertype, 0x08, 24, 3); + +/* afa_vlan_pcp_cmd */ +MLXSW_ITEM32(afa, vlan, pcp_cmd, 0x08, 13, 3); + +/* afa_vlan_pcp */ +MLXSW_ITEM32(afa, vlan, pcp, 0x08, 8, 3); + +static inline void +mlxsw_afa_vlan_pack(char *payload, + enum mlxsw_afa_vlan_vlan_tag_cmd vlan_tag_cmd, + enum mlxsw_afa_vlan_cmd vid_cmd, u16 vid, + enum mlxsw_afa_vlan_cmd pcp_cmd, u8 pcp, + enum mlxsw_afa_vlan_cmd ethertype_cmd, u8 ethertype) +{ + mlxsw_afa_vlan_vlan_tag_cmd_set(payload, vlan_tag_cmd); + mlxsw_afa_vlan_vid_cmd_set(payload, vid_cmd); + mlxsw_afa_vlan_vid_set(payload, vid); + mlxsw_afa_vlan_pcp_cmd_set(payload, pcp_cmd); + mlxsw_afa_vlan_pcp_set(payload, pcp); + mlxsw_afa_vlan_ethertype_cmd_set(payload, ethertype_cmd); + mlxsw_afa_vlan_ethertype_set(payload, ethertype); +} + +int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, + u16 vid, u8 pcp, u8 et) +{ + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_VLAN_CODE, + MLXSW_AFA_VLAN_SIZE); + + if (!act) + return -ENOBUFS; + mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP, + MLXSW_AFA_VLAN_CMD_SET_OUTER, vid, + MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp, + MLXSW_AFA_VLAN_CMD_SET_OUTER, et); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_vlan_modify); + /* Trap / Discard Action * --------------------- * The Trap / Discard action enables trapping / mirroring packets to the CPU diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 43f78dcfe394..6e103ac41d99 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -62,5 +62,7 @@ void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, u8 local_port, bool in_port); +int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, + u16 vid, u8 pcp, u8 et); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 13ec85e7c392..ac445d810eb3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -679,6 +679,9 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct net_device *out_dev); +int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + u32 action, u16 vid, u16 proto, u8 prio); struct mlxsw_sp_acl_rule; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 8a18b3aa70dc..3c5ea7e41db0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "reg.h" #include "core.h" @@ -335,6 +336,34 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp, local_port, in_port); } +int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + u32 action, u16 vid, u16 proto, u8 prio) +{ + u8 ethertype; + + if (action == TCA_VLAN_ACT_MODIFY) { + switch (proto) { + case ETH_P_8021Q: + ethertype = 0; + break; + case ETH_P_8021AD: + ethertype = 1; + break; + default: + dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN protocol %#04x\n", + proto); + return -EINVAL; + } + + return mlxsw_afa_block_append_vlan_modify(rulei->act_block, + vid, prio, ethertype); + } else { + dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n"); + return -EINVAL; + } +} + struct mlxsw_sp_acl_rule * mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 22ab42925377..d8984074f358 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "spectrum.h" #include "core_acl_flex_keys.h" @@ -73,6 +74,15 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, out_dev); if (err) return err; + } else if (is_tcf_vlan(a)) { + u16 proto = be16_to_cpu(tcf_vlan_push_proto(a)); + u32 action = tcf_vlan_action(a); + u8 prio = tcf_vlan_push_prio(a); + u16 vid = tcf_vlan_push_vid(a); + + return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei, + action, vid, + proto, prio); } else { dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n"); return -EOPNOTSUPP; diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index 48cca321ee6c..9690c047b6cf 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -49,4 +49,9 @@ static inline __be16 tcf_vlan_push_proto(const struct tc_action *a) return to_vlan(a)->tcfv_push_proto; } +static inline u8 tcf_vlan_push_prio(const struct tc_action *a) +{ + return to_vlan(a)->tcfv_push_prio; +} + #endif /* __NET_TC_VLAN_H */ From 9caab08a7685c874e7f20ef16f8191daf85609ae Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 9 Mar 2017 09:25:20 +0100 Subject: [PATCH 123/399] mlxsw: spectrum: Add support for flower matches on VLAN ID, PCP Introduce MLXSW_AFK_ELEMENT_VID, PCP and declare them in afk_element infos that contain them. Use the elements when VLAD ID or priority are used in the flow. Also add MLXSW_AFK_ELEMENT_VID, PCP to mlxsw_sp_acl_tcam_pattern_ipv4. Both items are included in mlxsw_sp_afk_element_info_l2_dmac, resp. _smac, and both MLXSW_AFK_ELEMENT_SMAC and _DMAC are already in the pattern. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../mellanox/mlxsw/core_acl_flex_keys.h | 6 ++++- .../mellanox/mlxsw/spectrum_acl_flex_keys.h | 6 +++++ .../mellanox/mlxsw/spectrum_acl_tcam.c | 2 ++ .../ethernet/mellanox/mlxsw/spectrum_flower.c | 24 ++++++++++++++++++- 4 files changed, 36 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index e4fcba7c2af2..c75e9141e3ec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -54,6 +54,8 @@ enum mlxsw_afk_element { MLXSW_AFK_ELEMENT_DST_IP6_LO, MLXSW_AFK_ELEMENT_DST_L4_PORT, MLXSW_AFK_ELEMENT_SRC_L4_PORT, + MLXSW_AFK_ELEMENT_VID, + MLXSW_AFK_ELEMENT_PCP, MLXSW_AFK_ELEMENT_MAX, }; @@ -88,7 +90,7 @@ struct mlxsw_afk_element_info { MLXSW_AFK_ELEMENT_INFO(MLXSW_AFK_ELEMENT_TYPE_BUF, \ _element, _offset, 0, _size) -/* For the purpose of the driver, define a internal storage scratchpad +/* For the purpose of the driver, define an internal storage scratchpad * that will be used to store key/mask values. For each defined element type * define an internal storage geometry. */ @@ -98,6 +100,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6), MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16), MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8), + MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12), + MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3), MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32), MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h index 82b81cf7f4a7..af7b7bad48df 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h @@ -39,11 +39,15 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = { MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6), + MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3), + MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12), MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = { MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6), + MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3), + MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12), MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16), }; @@ -65,6 +69,8 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = { }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = { + MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12), + MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3), MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16), MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16), }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 7382832215fa..6858439a1319 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -950,6 +950,8 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_DST_IP4, MLXSW_AFK_ELEMENT_DST_L4_PORT, MLXSW_AFK_ELEMENT_SRC_L4_PORT, + MLXSW_AFK_ELEMENT_VID, + MLXSW_AFK_ELEMENT_PCP, }; static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index d8984074f358..f2ed0b3d5718 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -183,7 +183,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS))) { + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_VLAN))) { dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n"); return -EOPNOTSUPP; } @@ -244,6 +245,27 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, sizeof(key->src)); } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + struct flow_dissector_key_vlan *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + if (mask->vlan_id != 0) + mlxsw_sp_acl_rulei_keymask_u32(rulei, + MLXSW_AFK_ELEMENT_VID, + key->vlan_id, + mask->vlan_id); + if (mask->vlan_priority != 0) + mlxsw_sp_acl_rulei_keymask_u32(rulei, + MLXSW_AFK_ELEMENT_PCP, + key->vlan_priority, + mask->vlan_priority); + } + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) mlxsw_sp_flower_parse_ipv4(rulei, f); From b414970e210d39d81cc70b46f7d9aa8e07b9297f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:34 +0100 Subject: [PATCH 124/399] mlxsw: spectrum: Sanitize bridge's upper devices We're going to allow bridges stacked on top of port netdevs to be enslaved to a VRF, but for now, only VLAN uppers of the VLAN-aware bridge are supported. Sanitize any other bridge upper. This is consistent with the way we sanitize port netdevs' uppers. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 31 ++++++++++++------- 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ae18067198dd..c27c8f83f7ac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4565,33 +4565,40 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, struct netdev_notifier_changeupper_info *info; struct net_device *upper_dev; struct mlxsw_sp *mlxsw_sp; - int err; + int err = 0; mlxsw_sp = mlxsw_sp_lower_get(br_dev); if (!mlxsw_sp) return 0; - if (br_dev != mlxsw_sp->master_bridge.dev) - return 0; info = ptr; switch (event) { - case NETDEV_CHANGEUPPER: + case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; if (!is_vlan_dev(upper_dev)) - break; - if (info->linking) { - err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp, - upper_dev); - if (err) - return err; + return -EINVAL; + if (is_vlan_dev(upper_dev) && + br_dev != mlxsw_sp->master_bridge.dev) + return -EINVAL; + break; + case NETDEV_CHANGEUPPER: + upper_dev = info->upper_dev; + if (is_vlan_dev(upper_dev)) { + if (info->linking) + err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp, + upper_dev); + else + mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, + upper_dev); } else { - mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev); + err = -EINVAL; + WARN_ON(1); } break; } - return 0; + return err; } static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp) From 1f88061ee409f5ec3d3451fc3235965aa3789af1 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:35 +0100 Subject: [PATCH 125/399] mlxsw: spectrum: Don't assume upper device's type When an upper device is configured on top of a vPort we make sure it's a bridge master during PRECHANGEUPPER and fail otherwise. Therefore, when CHANGEUPPER is later received we don't bother checking the upper's type. Make the code more extendable in preparation for VRF uppers, by checking the upper's type. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c27c8f83f7ac..b8238ed9ae73 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4818,6 +4818,8 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, int err = 0; mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (!mlxsw_sp_vport) + return 0; switch (event) { case NETDEV_PRECHANGEUPPER: @@ -4835,16 +4837,17 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; - if (info->linking) { - if (WARN_ON(!mlxsw_sp_vport)) - return -EINVAL; - err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport, - upper_dev); + if (netif_is_bridge_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport, + upper_dev); + else + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport); } else { - if (!mlxsw_sp_vport) - return 0; - mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport); + err = -EINVAL; + WARN_ON(1); } + break; } return err; From 186962ebb7ecd74d305cf167e99bf1885b89ea8c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:36 +0100 Subject: [PATCH 126/399] mlxsw: spectrum: Associate PVID vPort with appropriate netdev When a VLAN device is configured on top of a LAG device (f.e., bond0.10), a vPort is created on top of each of the LAG's slaves and its 'dev' pointer is set to the VLAN device. This is in contrast to the implicit PVID vPort (representing 'bond0'), whose 'dev' pointer keeps pointing to the port netdev itself (f.e., 'sw1p1'). Make both cases consistent by setting their 'dev' pointer to the actual netdev they represent. Either the LAG device itself (in the case of the PVID vPort) or the VLAN device on top of it. This will later allow us to more easily understand for which netdev we should create the router interface (RIF) upon enslavement to a VRF master. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b8238ed9ae73..fd6c40ead96a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4221,7 +4221,7 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, - u16 lag_id) + struct net_device *lag_dev, u16 lag_id) { struct mlxsw_sp_port *mlxsw_sp_vport; struct mlxsw_sp_fid *f; @@ -4239,6 +4239,7 @@ mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_vport->lag_id = lag_id; mlxsw_sp_vport->lagged = 1; + mlxsw_sp_vport->dev = lag_dev; } static void @@ -4255,6 +4256,7 @@ mlxsw_sp_port_pvid_vport_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port) if (f) f->leave(mlxsw_sp_vport); + mlxsw_sp_vport->dev = mlxsw_sp_port->dev; mlxsw_sp_vport->lagged = 0; } @@ -4294,7 +4296,7 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port->lagged = 1; lag->ref_count++; - mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_id); + mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_dev, lag_id); return 0; From f4a761d2030289229e5e7837a8afd35e48af464c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:37 +0100 Subject: [PATCH 127/399] mlxsw: spectrum: Destroy RIFs based on last removed address We only use the RIF reference count to determine when the last IP address was removed, but instead we can just test 'in_dev->ifa_list'. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 7 +++---- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 1 - 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index fd6c40ead96a..cb0e77ad4c0a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3392,16 +3392,16 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port) } static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, + const struct in_device *in_dev, unsigned long event) { switch (event) { case NETDEV_UP: if (!r) return true; - r->ref_count++; return false; case NETDEV_DOWN: - if (r && --r->ref_count == 0) + if (r && !in_dev->ifa_list) return true; /* It is possible we already removed the RIF ourselves * if it was assigned to a netdev that is now a bridge @@ -3484,7 +3484,6 @@ mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f) INIT_LIST_HEAD(&r->neigh_list); ether_addr_copy(r->addr, l3_dev->dev_addr); r->mtu = l3_dev->mtu; - r->ref_count = 1; r->dev = l3_dev; r->rif = rif; r->f = f; @@ -3858,7 +3857,7 @@ static int mlxsw_sp_inetaddr_event(struct notifier_block *unused, goto out; r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!mlxsw_sp_rif_should_config(r, event)) + if (!mlxsw_sp_rif_should_config(r, ifa->ifa_dev, event)) goto out; if (mlxsw_sp_port_dev_check(dev)) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index ac445d810eb3..7805430e5d4f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -111,7 +111,6 @@ struct mlxsw_sp_rif { struct list_head nexthop_list; struct list_head neigh_list; struct net_device *dev; - unsigned int ref_count; struct mlxsw_sp_fid *f; unsigned char addr[ETH_ALEN]; int mtu; From 97989ee0f5e855f4f5ec473b292c17f39cbaac58 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:38 +0100 Subject: [PATCH 128/399] mlxsw: spectrum_router: Allow more route types to be programmed Allow 'unreachable', 'blackhole' and 'prohibit' route types to be programmed into the device by sending any packet hitting them to the CPU. This is needed so that users will be able to program a default route into the VRF's table, thereby preventing lookup from leaking to other tables. Audit the code paths to make sure we don't rely on the presence of a nexthop netdev, as it doesn't exist for above mentioned route types. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 31 ++++++++++++++----- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index bd8de6b9be71..2fc4a9751469 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1514,6 +1514,9 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; + if (!dev) + return 0; + in_dev = __in_dev_get_rtnl(dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) @@ -1877,17 +1880,29 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, { struct fib_info *fi = fen_info->fi; - if (fen_info->type == RTN_LOCAL || fen_info->type == RTN_BROADCAST) { + switch (fen_info->type) { + case RTN_BROADCAST: /* fall through */ + case RTN_LOCAL: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; return 0; - } - if (fen_info->type != RTN_UNICAST) - return -EINVAL; - if (fi->fib_nh->nh_scope != RT_SCOPE_LINK) + case RTN_UNREACHABLE: /* fall through */ + case RTN_BLACKHOLE: /* fall through */ + case RTN_PROHIBIT: + /* Packets hitting these routes need to be trapped, but + * can do so with a lower priority than packets directed + * at the host, so use action type local instead of trap. + */ fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; - else - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; - return 0; + return 0; + case RTN_UNICAST: + if (fi->fib_nh->nh_scope != RT_SCOPE_LINK) + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + else + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; + return 0; + default: + return -EINVAL; + } } static struct mlxsw_sp_fib_entry * From 4724ba561a1ae0fcad2f2f2d3a5b1d4fd0840a9d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:39 +0100 Subject: [PATCH 129/399] mlxsw: spectrum_router: Place RIF related code with router code The inetaddr notification block is currently implemented in the main driver file, but this isn't really appropriate, as it mainly creates and destroys router interfaces (RIFs) which belong with the rest of the router code. This will become even more apparent later on when we'll need to bind these RIFs to virtual routers according to the VRF's table. Structure the driver better and prevent unnecessary function exports by moving the RIF related code with the rest of the router code. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 541 +------------- .../net/ethernet/mellanox/mlxsw/spectrum.h | 45 +- .../ethernet/mellanox/mlxsw/spectrum_router.c | 700 ++++++++++++++++-- 3 files changed, 644 insertions(+), 642 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index cb0e77ad4c0a..2104ee47e965 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3352,7 +3352,7 @@ static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev return mlxsw_sp_port; } -static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) +struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) { struct mlxsw_sp_port *mlxsw_sp_port; @@ -3391,545 +3391,6 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port) dev_put(mlxsw_sp_port->dev); } -static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, - const struct in_device *in_dev, - unsigned long event) -{ - switch (event) { - case NETDEV_UP: - if (!r) - return true; - return false; - case NETDEV_DOWN: - if (r && !in_dev->ifa_list) - return true; - /* It is possible we already removed the RIF ourselves - * if it was assigned to a netdev that is now a bridge - * or LAG slave. - */ - return false; - } - - return false; -} - -static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) -{ - int i; - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) - if (!mlxsw_sp->rifs[i]) - return i; - - return MLXSW_SP_INVALID_RIF; -} - -static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, - bool *p_lagged, u16 *p_system_port) -{ - u8 local_port = mlxsw_sp_vport->local_port; - - *p_lagged = mlxsw_sp_vport->lagged; - *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port; -} - -static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *l3_dev, u16 rif, - bool create) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - bool lagged = mlxsw_sp_vport->lagged; - char ritr_pl[MLXSW_REG_RITR_LEN]; - u16 system_port; - - mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, - l3_dev->mtu, l3_dev->dev_addr); - - mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); - mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port, - mlxsw_sp_vport_vid_get(mlxsw_sp_vport)); - - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport); - -static struct mlxsw_sp_fid * -mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) -{ - struct mlxsw_sp_fid *f; - - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (!f) - return NULL; - - f->leave = mlxsw_sp_vport_rif_sp_leave; - f->ref_count = 0; - f->dev = l3_dev; - f->fid = fid; - - return f; -} - -static struct mlxsw_sp_rif * -mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f) -{ - struct mlxsw_sp_rif *r; - - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return NULL; - - INIT_LIST_HEAD(&r->nexthop_list); - INIT_LIST_HEAD(&r->neigh_list); - ether_addr_copy(r->addr, l3_dev->dev_addr); - r->mtu = l3_dev->mtu; - r->dev = l3_dev; - r->rif = rif; - r->f = f; - - return r; -} - -static struct mlxsw_sp_rif * -mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *l3_dev) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct mlxsw_sp_fid *f; - struct mlxsw_sp_rif *r; - u16 fid, rif; - int err; - - rif = mlxsw_sp_avail_rif_get(mlxsw_sp); - if (rif == MLXSW_SP_INVALID_RIF) - return ERR_PTR(-ERANGE); - - err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true); - if (err) - return ERR_PTR(err); - - fid = mlxsw_sp_rif_sp_to_fid(rif); - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); - if (err) - goto err_rif_fdb_op; - - f = mlxsw_sp_rfid_alloc(fid, l3_dev); - if (!f) { - err = -ENOMEM; - goto err_rfid_alloc; - } - - r = mlxsw_sp_rif_alloc(rif, l3_dev, f); - if (!r) { - err = -ENOMEM; - goto err_rif_alloc; - } - - f->r = r; - mlxsw_sp->rifs[rif] = r; - - return r; - -err_rif_alloc: - kfree(f); -err_rfid_alloc: - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); -err_rif_fdb_op: - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); - return ERR_PTR(err); -} - -static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, - struct mlxsw_sp_rif *r) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct net_device *l3_dev = r->dev; - struct mlxsw_sp_fid *f = r->f; - u16 fid = f->fid; - u16 rif = r->rif; - - mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); - - mlxsw_sp->rifs[rif] = NULL; - f->r = NULL; - - kfree(r); - - kfree(f); - - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); - - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); -} - -static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *l3_dev) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct mlxsw_sp_rif *r; - - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); - if (!r) { - r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); - if (IS_ERR(r)) - return PTR_ERR(r); - } - - mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f); - r->f->ref_count++; - - netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid); - - return 0; -} - -static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport) -{ - struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); - - netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid); - - mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); - if (--f->ref_count == 0) - mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r); -} - -static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, - struct net_device *port_dev, - unsigned long event, u16 vid) -{ - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev); - struct mlxsw_sp_port *mlxsw_sp_vport; - - mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); - if (WARN_ON(!mlxsw_sp_vport)) - return -EINVAL; - - switch (event) { - case NETDEV_UP: - return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev); - case NETDEV_DOWN: - mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); - break; - } - - return 0; -} - -static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, - unsigned long event) -{ - if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev)) - return 0; - - return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1); -} - -static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, - struct net_device *lag_dev, - unsigned long event, u16 vid) -{ - struct net_device *port_dev; - struct list_head *iter; - int err; - - netdev_for_each_lower_dev(lag_dev, port_dev, iter) { - if (mlxsw_sp_port_dev_check(port_dev)) { - err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev, - event, vid); - if (err) - return err; - } - } - - return 0; -} - -static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev, - unsigned long event) -{ - if (netif_is_bridge_port(lag_dev)) - return 0; - - return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1); -} - -static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, - struct net_device *l3_dev) -{ - u16 fid; - - if (is_vlan_dev(l3_dev)) - fid = vlan_dev_vlan_id(l3_dev); - else if (mlxsw_sp->master_bridge.dev == l3_dev) - fid = 1; - else - return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev); - - return mlxsw_sp_fid_find(mlxsw_sp, fid); -} - -static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid) -{ - return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID : - MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; -} - -static u16 mlxsw_sp_flood_table_index_get(u16 fid) -{ - return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid; -} - -static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid, - bool set) -{ - enum mlxsw_flood_table_type table_type; - char *sftr_pl; - u16 index; - int err; - - sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); - if (!sftr_pl) - return -ENOMEM; - - table_type = mlxsw_sp_flood_table_type_get(fid); - index = mlxsw_sp_flood_table_index_get(fid); - mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type, - 1, MLXSW_PORT_ROUTER_PORT, set); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); - - kfree(sftr_pl); - return err; -} - -static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) -{ - if (mlxsw_sp_fid_is_vfid(fid)) - return MLXSW_REG_RITR_FID_IF; - else - return MLXSW_REG_RITR_VLAN_IF; -} - -static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, - struct net_device *l3_dev, - u16 fid, u16 rif, - bool create) -{ - enum mlxsw_reg_ritr_if_type rif_type; - char ritr_pl[MLXSW_REG_RITR_LEN]; - - rif_type = mlxsw_sp_rif_type_get(fid); - mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu, - l3_dev->dev_addr); - mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid); - - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, - struct net_device *l3_dev, - struct mlxsw_sp_fid *f) -{ - struct mlxsw_sp_rif *r; - u16 rif; - int err; - - rif = mlxsw_sp_avail_rif_get(mlxsw_sp); - if (rif == MLXSW_SP_INVALID_RIF) - return -ERANGE; - - err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); - if (err) - return err; - - err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); - if (err) - goto err_rif_bridge_op; - - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); - if (err) - goto err_rif_fdb_op; - - r = mlxsw_sp_rif_alloc(rif, l3_dev, f); - if (!r) { - err = -ENOMEM; - goto err_rif_alloc; - } - - f->r = r; - mlxsw_sp->rifs[rif] = r; - - netdev_dbg(l3_dev, "RIF=%d created\n", rif); - - return 0; - -err_rif_alloc: - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); -err_rif_fdb_op: - mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); -err_rif_bridge_op: - mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); - return err; -} - -void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) -{ - struct net_device *l3_dev = r->dev; - struct mlxsw_sp_fid *f = r->f; - u16 rif = r->rif; - - mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); - - mlxsw_sp->rifs[rif] = NULL; - f->r = NULL; - - kfree(r); - - mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); - - mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); - - mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); - - netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); -} - -static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, - struct net_device *br_dev, - unsigned long event) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); - struct mlxsw_sp_fid *f; - - /* FID can either be an actual FID if the L3 device is the - * VLAN-aware bridge or a VLAN device on top. Otherwise, the - * L3 device is a VLAN-unaware bridge and we get a vFID. - */ - f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); - if (WARN_ON(!f)) - return -EINVAL; - - switch (event) { - case NETDEV_UP: - return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); - case NETDEV_DOWN: - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); - break; - } - - return 0; -} - -static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, - unsigned long event) -{ - struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); - u16 vid = vlan_dev_vlan_id(vlan_dev); - - if (mlxsw_sp_port_dev_check(real_dev)) - return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event, - vid); - else if (netif_is_lag_master(real_dev)) - return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event, - vid); - else if (netif_is_bridge_master(real_dev) && - mlxsw_sp->master_bridge.dev == real_dev) - return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev, - event); - - return 0; -} - -static int mlxsw_sp_inetaddr_event(struct notifier_block *unused, - unsigned long event, void *ptr) -{ - struct in_ifaddr *ifa = (struct in_ifaddr *) ptr; - struct net_device *dev = ifa->ifa_dev->dev; - struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif *r; - int err = 0; - - mlxsw_sp = mlxsw_sp_lower_get(dev); - if (!mlxsw_sp) - goto out; - - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!mlxsw_sp_rif_should_config(r, ifa->ifa_dev, event)) - goto out; - - if (mlxsw_sp_port_dev_check(dev)) - err = mlxsw_sp_inetaddr_port_event(dev, event); - else if (netif_is_lag_master(dev)) - err = mlxsw_sp_inetaddr_lag_event(dev, event); - else if (netif_is_bridge_master(dev)) - err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event); - else if (is_vlan_dev(dev)) - err = mlxsw_sp_inetaddr_vlan_event(dev, event); - -out: - return notifier_from_errno(err); -} - -static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif, - const char *mac, int mtu) -{ - char ritr_pl[MLXSW_REG_RITR_LEN]; - int err; - - mlxsw_reg_ritr_rif_pack(ritr_pl, rif); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); - if (err) - return err; - - mlxsw_reg_ritr_mtu_set(ritr_pl, mtu); - mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac); - mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -static int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) -{ - struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif *r; - int err; - - mlxsw_sp = mlxsw_sp_lower_get(dev); - if (!mlxsw_sp) - return 0; - - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!r) - return 0; - - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false); - if (err) - return err; - - err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu); - if (err) - goto err_rif_edit; - - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true); - if (err) - goto err_rif_fdb_op; - - ether_addr_copy(r->addr, dev->dev_addr); - r->mtu = dev->mtu; - - netdev_dbg(dev, "Updated RIF=%d\n", r->rif); - - return 0; - -err_rif_fdb_op: - mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu); -err_rif_edit: - mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true); - return err; -} - static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port, u16 fid) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 7805430e5d4f..5bc60421a860 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -58,7 +58,6 @@ #define MLXSW_SP_VFID_MAX 1024 /* Bridged VLAN interfaces */ #define MLXSW_SP_RFID_BASE 15360 -#define MLXSW_SP_INVALID_RIF 0xffff #define MLXSW_SP_MID_MAX 7000 @@ -92,6 +91,7 @@ static inline u16 mlxsw_sp_pfc_delay_get(int mtu, u16 delay) } struct mlxsw_sp_port; +struct mlxsw_sp_rif; struct mlxsw_sp_upper { struct net_device *dev; @@ -107,16 +107,6 @@ struct mlxsw_sp_fid { u16 fid; }; -struct mlxsw_sp_rif { - struct list_head nexthop_list; - struct list_head neigh_list; - struct net_device *dev; - struct mlxsw_sp_fid *f; - unsigned char addr[ETH_ALEN]; - int mtu; - u16 rif; -}; - struct mlxsw_sp_mid { struct list_head list; unsigned char addr[ETH_ALEN]; @@ -140,16 +130,6 @@ static inline bool mlxsw_sp_fid_is_vfid(u16 fid) return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE; } -static inline bool mlxsw_sp_fid_is_rfid(u16 fid) -{ - return fid >= MLXSW_SP_RFID_BASE; -} - -static inline u16 mlxsw_sp_rif_sp_to_fid(u16 rif) -{ - return MLXSW_SP_RFID_BASE + rif; -} - struct mlxsw_sp_sb_pr { enum mlxsw_reg_sbpr_mode mode; u32 size; @@ -385,6 +365,7 @@ struct mlxsw_sp_port { }; bool mlxsw_sp_port_dev_check(const struct net_device *dev); +struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev); void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port); @@ -496,19 +477,6 @@ mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp, return NULL; } -static inline struct mlxsw_sp_rif * -mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *dev) -{ - int i; - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) - if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev) - return mlxsw_sp->rifs[i]; - - return NULL; -} - enum mlxsw_sp_flood_table { MLXSW_SP_FLOOD_TABLE_UC, MLXSW_SP_FLOOD_TABLE_BC, @@ -569,8 +537,6 @@ int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid, bool adding); struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid); void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f); -void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r); int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index, bool dwrr, u8 dwrr_weight); @@ -607,8 +573,11 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_router_netevent_event(struct notifier_block *unused, unsigned long event, void *ptr); -void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r); +int mlxsw_sp_netdevice_router_port_event(struct net_device *dev); +int mlxsw_sp_inetaddr_event(struct notifier_block *unused, + unsigned long event, void *ptr); +void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r); int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count); void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 2fc4a9751469..1839ba05f4dd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -50,6 +50,20 @@ #include "core.h" #include "reg.h" +struct mlxsw_sp_rif { + struct list_head nexthop_list; + struct list_head neigh_list; + struct net_device *dev; + struct mlxsw_sp_fid *f; + unsigned char addr[ETH_ALEN]; + int mtu; + u16 rif; +}; + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); + #define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \ for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT) @@ -2452,70 +2466,6 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n"); } -static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) -{ - char ritr_pl[MLXSW_REG_RITR_LEN]; - int err; - - mlxsw_reg_ritr_rif_pack(ritr_pl, rif); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); - if (WARN_ON_ONCE(err)) - return err; - - mlxsw_reg_ritr_enable_set(ritr_pl, false); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) -{ - mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif); - mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r); - mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r); -} - -static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) -{ - char rgcr_pl[MLXSW_REG_RGCR_LEN]; - u64 max_rifs; - int err; - - if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) - return -EIO; - - max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); - mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *), - GFP_KERNEL); - if (!mlxsw_sp->rifs) - return -ENOMEM; - - mlxsw_reg_rgcr_pack(rgcr_pl, true); - mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); - if (err) - goto err_rgcr_fail; - - return 0; - -err_rgcr_fail: - kfree(mlxsw_sp->rifs); - return err; -} - -static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) -{ - char rgcr_pl[MLXSW_REG_RGCR_LEN]; - int i; - - mlxsw_reg_rgcr_pack(rgcr_pl, false); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) - WARN_ON_ONCE(mlxsw_sp->rifs[i]); - - kfree(mlxsw_sp->rifs); -} - struct mlxsw_sp_fib_event_work { struct work_struct work; union { @@ -2609,6 +2559,586 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, return NOTIFY_DONE; } +static struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev) +{ + int i; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev) + return mlxsw_sp->rifs[i]; + + return NULL; +} + +static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + int err; + + mlxsw_reg_ritr_rif_pack(ritr_pl, rif); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (WARN_ON_ONCE(err)) + return err; + + mlxsw_reg_ritr_enable_set(ritr_pl, false); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r) +{ + mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif); + mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r); + mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r); +} + +static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, + const struct in_device *in_dev, + unsigned long event) +{ + switch (event) { + case NETDEV_UP: + if (!r) + return true; + return false; + case NETDEV_DOWN: + if (r && !in_dev->ifa_list) + return true; + /* It is possible we already removed the RIF ourselves + * if it was assigned to a netdev that is now a bridge + * or LAG slave. + */ + return false; + } + + return false; +} + +#define MLXSW_SP_INVALID_RIF 0xffff +static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + if (!mlxsw_sp->rifs[i]) + return i; + + return MLXSW_SP_INVALID_RIF; +} + +static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, + bool *p_lagged, u16 *p_system_port) +{ + u8 local_port = mlxsw_sp_vport->local_port; + + *p_lagged = mlxsw_sp_vport->lagged; + *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port; +} + +static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev, u16 rif, + bool create) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + bool lagged = mlxsw_sp_vport->lagged; + char ritr_pl[MLXSW_REG_RITR_LEN]; + u16 system_port; + + mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, + l3_dev->mtu, l3_dev->dev_addr); + + mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); + mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port, + mlxsw_sp_vport_vid_get(mlxsw_sp_vport)); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport); + +static u16 mlxsw_sp_rif_sp_to_fid(u16 rif) +{ + return MLXSW_SP_RFID_BASE + rif; +} + +static struct mlxsw_sp_fid * +mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + f->leave = mlxsw_sp_vport_rif_sp_leave; + f->ref_count = 0; + f->dev = l3_dev; + f->fid = fid; + + return f; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f) +{ + struct mlxsw_sp_rif *r; + + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return NULL; + + INIT_LIST_HEAD(&r->nexthop_list); + INIT_LIST_HEAD(&r->neigh_list); + ether_addr_copy(r->addr, l3_dev->dev_addr); + r->mtu = l3_dev->mtu; + r->dev = l3_dev; + r->rif = rif; + r->f = f; + + return r; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_fid *f; + struct mlxsw_sp_rif *r; + u16 fid, rif; + int err; + + rif = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif == MLXSW_SP_INVALID_RIF) + return ERR_PTR(-ERANGE); + + err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true); + if (err) + return ERR_PTR(err); + + fid = mlxsw_sp_rif_sp_to_fid(rif); + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); + if (err) + goto err_rif_fdb_op; + + f = mlxsw_sp_rfid_alloc(fid, l3_dev); + if (!f) { + err = -ENOMEM; + goto err_rfid_alloc; + } + + r = mlxsw_sp_rif_alloc(rif, l3_dev, f); + if (!r) { + err = -ENOMEM; + goto err_rif_alloc; + } + + f->r = r; + mlxsw_sp->rifs[rif] = r; + + return r; + +err_rif_alloc: + kfree(f); +err_rfid_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); +err_rif_fdb_op: + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); + return ERR_PTR(err); +} + +static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, + struct mlxsw_sp_rif *r) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct net_device *l3_dev = r->dev; + struct mlxsw_sp_fid *f = r->f; + u16 fid = f->fid; + u16 rif = r->rif; + + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + + mlxsw_sp->rifs[rif] = NULL; + f->r = NULL; + + kfree(r); + + kfree(f); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); + + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); +} + +static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_rif *r; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); + if (!r) { + r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); + if (IS_ERR(r)) + return PTR_ERR(r); + } + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f); + r->f->ref_count++; + + netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid); + + return 0; +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + + netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid); + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); + if (--f->ref_count == 0) + mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r); +} + +static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, + struct net_device *port_dev, + unsigned long event, u16 vid) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev); + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (WARN_ON(!mlxsw_sp_vport)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev); + case NETDEV_DOWN: + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, + unsigned long event) +{ + if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev)) + return 0; + + return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1); +} + +static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, + struct net_device *lag_dev, + unsigned long event, u16 vid) +{ + struct net_device *port_dev; + struct list_head *iter; + int err; + + netdev_for_each_lower_dev(lag_dev, port_dev, iter) { + if (mlxsw_sp_port_dev_check(port_dev)) { + err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev, + event, vid); + if (err) + return err; + } + } + + return 0; +} + +static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev, + unsigned long event) +{ + if (netif_is_bridge_port(lag_dev)) + return 0; + + return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1); +} + +static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + u16 fid; + + if (is_vlan_dev(l3_dev)) + fid = vlan_dev_vlan_id(l3_dev); + else if (mlxsw_sp->master_bridge.dev == l3_dev) + fid = 1; + else + return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev); + + return mlxsw_sp_fid_find(mlxsw_sp, fid); +} + +static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID : + MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; +} + +static u16 mlxsw_sp_flood_table_index_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid; +} + +static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid, + bool set) +{ + enum mlxsw_flood_table_type table_type; + char *sftr_pl; + u16 index; + int err; + + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); + if (!sftr_pl) + return -ENOMEM; + + table_type = mlxsw_sp_flood_table_type_get(fid); + index = mlxsw_sp_flood_table_index_get(fid); + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type, + 1, MLXSW_PORT_ROUTER_PORT, set); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + + kfree(sftr_pl); + return err; +} + +static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) +{ + if (mlxsw_sp_fid_is_vfid(fid)) + return MLXSW_REG_RITR_FID_IF; + else + return MLXSW_REG_RITR_VLAN_IF; +} + +static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + u16 fid, u16 rif, + bool create) +{ + enum mlxsw_reg_ritr_if_type rif_type; + char ritr_pl[MLXSW_REG_RITR_LEN]; + + rif_type = mlxsw_sp_rif_type_get(fid); + mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu, + l3_dev->dev_addr); + mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + struct mlxsw_sp_fid *f) +{ + struct mlxsw_sp_rif *r; + u16 rif; + int err; + + rif = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif == MLXSW_SP_INVALID_RIF) + return -ERANGE; + + err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); + if (err) + return err; + + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); + if (err) + goto err_rif_bridge_op; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); + if (err) + goto err_rif_fdb_op; + + r = mlxsw_sp_rif_alloc(rif, l3_dev, f); + if (!r) { + err = -ENOMEM; + goto err_rif_alloc; + } + + f->r = r; + mlxsw_sp->rifs[rif] = r; + + netdev_dbg(l3_dev, "RIF=%d created\n", rif); + + return 0; + +err_rif_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); +err_rif_fdb_op: + mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); +err_rif_bridge_op: + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); + return err; +} + +void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *r) +{ + struct net_device *l3_dev = r->dev; + struct mlxsw_sp_fid *f = r->f; + u16 rif = r->rif; + + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + + mlxsw_sp->rifs[rif] = NULL; + f->r = NULL; + + kfree(r); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); + + mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); + + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); + + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); +} + +static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, + struct net_device *br_dev, + unsigned long event) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); + struct mlxsw_sp_fid *f; + + /* FID can either be an actual FID if the L3 device is the + * VLAN-aware bridge or a VLAN device on top. Otherwise, the + * L3 device is a VLAN-unaware bridge and we get a vFID. + */ + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); + case NETDEV_DOWN: + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, + unsigned long event) +{ + struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); + u16 vid = vlan_dev_vlan_id(vlan_dev); + + if (mlxsw_sp_port_dev_check(real_dev)) + return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_lag_master(real_dev)) + return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_bridge_master(real_dev) && + mlxsw_sp->master_bridge.dev == real_dev) + return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev, + event); + + return 0; +} + +int mlxsw_sp_inetaddr_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in_ifaddr *ifa = (struct in_ifaddr *) ptr; + struct net_device *dev = ifa->ifa_dev->dev; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *r; + int err = 0; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + goto out; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(r, ifa->ifa_dev, event)) + goto out; + + if (mlxsw_sp_port_dev_check(dev)) + err = mlxsw_sp_inetaddr_port_event(dev, event); + else if (netif_is_lag_master(dev)) + err = mlxsw_sp_inetaddr_lag_event(dev, event); + else if (netif_is_bridge_master(dev)) + err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event); + else if (is_vlan_dev(dev)) + err = mlxsw_sp_inetaddr_vlan_event(dev, event); + +out: + return notifier_from_errno(err); +} + +static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif, + const char *mac, int mtu) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + int err; + + mlxsw_reg_ritr_rif_pack(ritr_pl, rif); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (err) + return err; + + mlxsw_reg_ritr_mtu_set(ritr_pl, mtu); + mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac); + mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) +{ + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *r; + int err; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + return 0; + + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!r) + return 0; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false); + if (err) + return err; + + err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu); + if (err) + goto err_rif_edit; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true); + if (err) + goto err_rif_fdb_op; + + ether_addr_copy(r->addr, dev->dev_addr); + r->mtu = dev->mtu; + + netdev_dbg(dev, "Updated RIF=%d\n", r->rif); + + return 0; + +err_rif_fdb_op: + mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu); +err_rif_edit: + mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true); + return err; +} + static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) { struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb); @@ -2621,6 +3151,48 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) mlxsw_sp_router_fib_flush(mlxsw_sp); } +static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + u64 max_rifs; + int err; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) + return -EIO; + + max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); + mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *), + GFP_KERNEL); + if (!mlxsw_sp->rifs) + return -ENOMEM; + + mlxsw_reg_rgcr_pack(rgcr_pl, true); + mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); + if (err) + goto err_rgcr_fail; + + return 0; + +err_rgcr_fail: + kfree(mlxsw_sp->rifs); + return err; +} + +static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + int i; + + mlxsw_reg_rgcr_pack(rgcr_pl, false); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + WARN_ON_ONCE(mlxsw_sp->rifs[i]); + + kfree(mlxsw_sp->rifs); +} + int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { int err; From 382dbb40145076f3a023992117ddaaae1ced5af8 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:40 +0100 Subject: [PATCH 130/399] mlxsw: spectrum_router: Simplify LPM tree allocation When looking for a new LPM tree we should always consider all the unused trees. It doesn't matter if the new tree is required due to changes in currently used prefixes inside an existing routing table or because a route was inserted into an empty table. Both cases are functionally identical and therefore should be treated the same. When looking for a new LPM tree, consider all unused trees and don't reserve trees for specific cases. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 22 ++++++++----------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 1839ba05f4dd..c11a5baca539 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -196,19 +196,15 @@ static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib) } static struct mlxsw_sp_lpm_tree * -mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved) +mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp) { static struct mlxsw_sp_lpm_tree *lpm_tree; int i; for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { lpm_tree = &mlxsw_sp->router.lpm_trees[i]; - if (lpm_tree->ref_count == 0) { - if (one_reserved) - one_reserved = false; - else - return lpm_tree; - } + if (lpm_tree->ref_count == 0) + return lpm_tree; } return NULL; } @@ -262,12 +258,12 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, - enum mlxsw_sp_l3proto proto, bool one_reserved) + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_lpm_tree *lpm_tree; int err; - lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved); + lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp); if (!lpm_tree) return ERR_PTR(-EBUSY); lpm_tree->proto = proto; @@ -297,7 +293,7 @@ static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, - enum mlxsw_sp_l3proto proto, bool one_reserved) + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_lpm_tree *lpm_tree; int i; @@ -311,7 +307,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, goto inc_ref_count; } lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, - proto, one_reserved); + proto); if (IS_ERR(lpm_tree)) return lpm_tree; @@ -421,7 +417,7 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_prefix_usage_zero(&req_prefix_usage); mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - proto, true); + proto); if (IS_ERR(lpm_tree)) { err = PTR_ERR(lpm_tree); goto err_tree_get; @@ -463,7 +459,7 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return 0; new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, - vr->proto, false); + vr->proto); if (IS_ERR(new_tree)) { /* We failed to get a tree according to the required * prefix usage. However, the current tree might be still good From 76610ebbde1883527cf5afa8708a5b0599439a28 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:41 +0100 Subject: [PATCH 131/399] mlxsw: spectrum_router: Refactor virtual router handling A virtual router (VR) is an entity within the device to which routing tables and interfaces can be bound to. It can be used to implement VRFs. In the initial implementation we associated the VR with a specific protocol (e.g., IPv4) and an LPM tree. However, this isn't really accurate, as the same VR can be used for both IPv4 and IPv6 traffic, by binding a different LPM tree to a {VR, Proto} pair. This patch aims to restructure the VR code according to the above logic, so that VRs are more accurately represented by the driver's data structures. The main motivation behind this change is to prepare the driver for VRF offload. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.h | 5 +- .../ethernet/mellanox/mlxsw/spectrum_router.c | 328 ++++++++++-------- 2 files changed, 181 insertions(+), 152 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 5bc60421a860..5a7ffa1cadf9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -186,11 +186,8 @@ struct mlxsw_sp_fib; struct mlxsw_sp_vr { u16 id; /* virtual router ID */ - bool used; - enum mlxsw_sp_l3proto proto; u32 tb_id; /* kernel fib table id */ - struct mlxsw_sp_lpm_tree *lpm_tree; - struct mlxsw_sp_fib *fib; + struct mlxsw_sp_fib *fib4; }; enum mlxsw_sp_span_type { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c11a5baca539..0a79fc7afd63 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -102,12 +102,6 @@ mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1, memcpy(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1)); } -static void -mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage) -{ - memset(prefix_usage, 0, sizeof(*prefix_usage)); -} - static void mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage, unsigned char prefix_len) @@ -139,7 +133,7 @@ struct mlxsw_sp_fib_node { struct list_head entry_list; struct list_head list; struct rhash_head ht_node; - struct mlxsw_sp_vr *vr; + struct mlxsw_sp_fib *fib; struct mlxsw_sp_fib_key key; }; @@ -163,13 +157,17 @@ struct mlxsw_sp_fib_entry { struct mlxsw_sp_fib { struct rhashtable ht; struct list_head node_list; + struct mlxsw_sp_vr *vr; + struct mlxsw_sp_lpm_tree *lpm_tree; unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT]; struct mlxsw_sp_prefix_usage prefix_usage; + enum mlxsw_sp_l3proto proto; }; static const struct rhashtable_params mlxsw_sp_fib_ht_params; -static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) +static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_fib *fib; int err; @@ -181,6 +179,8 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) if (err) goto err_rhashtable_init; INIT_LIST_HEAD(&fib->node_list); + fib->proto = proto; + fib->vr = vr; return fib; err_rhashtable_init: @@ -191,6 +191,7 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib) { WARN_ON(!list_empty(&fib->node_list)); + WARN_ON(fib->lpm_tree); rhashtable_destroy(&fib->ht); kfree(fib); } @@ -335,6 +336,11 @@ static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp) } } +static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr) +{ + return !!vr->fib4; +} + static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_vr *vr; @@ -342,31 +348,31 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { vr = &mlxsw_sp->router.vrs[i]; - if (!vr->used) + if (!mlxsw_sp_vr_is_used(vr)) return vr; } return NULL; } static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) + const struct mlxsw_sp_fib *fib) { char raltb_pl[MLXSW_REG_RALTB_LEN]; - mlxsw_reg_raltb_pack(raltb_pl, vr->id, - (enum mlxsw_reg_ralxx_protocol) vr->proto, - vr->lpm_tree->id); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + fib->lpm_tree->id); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) + const struct mlxsw_sp_fib *fib) { char raltb_pl[MLXSW_REG_RALTB_LEN]; /* Bind to tree 0 which is default */ - mlxsw_reg_raltb_pack(raltb_pl, vr->id, - (enum mlxsw_reg_ralxx_protocol) vr->proto, 0); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } @@ -379,8 +385,7 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id) } static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, - u32 tb_id, - enum mlxsw_sp_l3proto proto) + u32 tb_id) { struct mlxsw_sp_vr *vr; int i; @@ -389,69 +394,50 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { vr = &mlxsw_sp->router.vrs[i]; - if (vr->used && vr->proto == proto && vr->tb_id == tb_id) + if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id) return vr; } return NULL; } -static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, - unsigned char prefix_len, - u32 tb_id, - enum mlxsw_sp_l3proto proto) +static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) +{ + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return vr->fib4; + case MLXSW_SP_L3_PROTO_IPV6: + BUG_ON(1); + } + return NULL; +} + +static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, + u32 tb_id) { - struct mlxsw_sp_prefix_usage req_prefix_usage; - struct mlxsw_sp_lpm_tree *lpm_tree; struct mlxsw_sp_vr *vr; - int err; vr = mlxsw_sp_vr_find_unused(mlxsw_sp); if (!vr) return ERR_PTR(-EBUSY); - vr->fib = mlxsw_sp_fib_create(); - if (IS_ERR(vr->fib)) - return ERR_CAST(vr->fib); - - vr->proto = proto; + vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(vr->fib4)) + return ERR_CAST(vr->fib4); vr->tb_id = tb_id; - mlxsw_sp_prefix_usage_zero(&req_prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - proto); - if (IS_ERR(lpm_tree)) { - err = PTR_ERR(lpm_tree); - goto err_tree_get; - } - vr->lpm_tree = lpm_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); - if (err) - goto err_tree_bind; - - vr->used = true; return vr; - -err_tree_bind: - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); -err_tree_get: - mlxsw_sp_fib_destroy(vr->fib); - - return ERR_PTR(err); } -static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) { - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); - mlxsw_sp_fib_destroy(vr->fib); - vr->used = false; + mlxsw_sp_fib_destroy(vr->fib4); + vr->fib4 = NULL; } static int -mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, +mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib, struct mlxsw_sp_prefix_usage *req_prefix_usage) { - struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree; + struct mlxsw_sp_lpm_tree *lpm_tree = fib->lpm_tree; struct mlxsw_sp_lpm_tree *new_tree; int err; @@ -459,7 +445,7 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return 0; new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, - vr->proto); + fib->proto); if (IS_ERR(new_tree)) { /* We failed to get a tree according to the required * prefix usage. However, the current tree might be still good @@ -473,8 +459,8 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, } /* Prevent packet loss by overwriting existing binding */ - vr->lpm_tree = new_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + fib->lpm_tree = new_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); if (err) goto err_tree_bind; mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); @@ -482,53 +468,26 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return 0; err_tree_bind: - vr->lpm_tree = lpm_tree; + fib->lpm_tree = lpm_tree; mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); return err; } -static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, - unsigned char prefix_len, - u32 tb_id, - enum mlxsw_sp_l3proto proto) +static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) { struct mlxsw_sp_vr *vr; - int err; tb_id = mlxsw_sp_fix_tb_id(tb_id); - vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto); - if (!vr) { - vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto); - if (IS_ERR(vr)) - return vr; - } else { - struct mlxsw_sp_prefix_usage req_prefix_usage; - - mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, - &vr->fib->prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); - /* Need to replace LPM tree in case new prefix is required. */ - err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, - &req_prefix_usage); - if (err) - return ERR_PTR(err); - } + vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id); + if (!vr) + vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id); return vr; } -static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr) { - /* Destroy virtual router entity in case the associated FIB is empty - * and allow it to be used for other tables in future. Otherwise, - * check if some prefix usage did not disappear and change tree if - * that is the case. Note that in case new, smaller tree cannot be - * allocated, the original one will be kept being used. - */ - if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage)) - mlxsw_sp_vr_destroy(mlxsw_sp, vr); - else - mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, - &vr->fib->prefix_usage); + if (list_empty(&vr->fib4->node_list)) + mlxsw_sp_vr_destroy(vr); } static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) @@ -1181,7 +1140,7 @@ mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr, + const struct mlxsw_sp_fib *fib, u32 adj_index, u16 ecmp_size, u32 new_adj_index, u16 new_ecmp_size) @@ -1189,8 +1148,8 @@ static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, char raleu_pl[MLXSW_REG_RALEU_LEN]; mlxsw_reg_raleu_pack(raleu_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, vr->id, - adj_index, ecmp_size, new_adj_index, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + fib->vr->id, adj_index, ecmp_size, new_adj_index, new_ecmp_size); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl); } @@ -1200,14 +1159,14 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp, u32 old_adj_index, u16 old_ecmp_size) { struct mlxsw_sp_fib_entry *fib_entry; - struct mlxsw_sp_vr *vr = NULL; + struct mlxsw_sp_fib *fib = NULL; int err; list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) { - if (vr == fib_entry->fib_node->vr) + if (fib == fib_entry->fib_node->fib) continue; - vr = fib_entry->fib_node->vr; - err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr, + fib = fib_entry->fib_node->fib; + err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib, old_adj_index, old_ecmp_size, nh_grp->adj_index, @@ -1712,7 +1671,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) { fib_entry->offloaded = true; - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: fib_info_offload_inc(fib_entry->nh_group->key.fi); break; @@ -1724,7 +1683,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) static void mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) { - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: fib_info_offload_dec(fib_entry->nh_group->key.fi); break; @@ -1764,8 +1723,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, enum mlxsw_reg_ralue_op op) { char ralue_pl[MLXSW_REG_RALUE_LEN]; + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; @@ -1785,8 +1744,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, } mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id, adjacency_index, ecmp_size); @@ -1798,10 +1757,10 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, enum mlxsw_reg_ralue_op op) { struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif; + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; enum mlxsw_reg_ralue_trap_action trap_action; char ralue_pl[MLXSW_REG_RALUE_LEN]; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; u16 trap_id = 0; u16 rif = 0; @@ -1814,8 +1773,8 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, } mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); @@ -1825,13 +1784,13 @@ static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; char ralue_pl[MLXSW_REG_RALUE_LEN]; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); @@ -1858,7 +1817,7 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, { int err = -EINVAL; - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op); break; @@ -2021,7 +1980,7 @@ mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr, } static struct mlxsw_sp_fib_node * -mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr, +mlxsw_sp_fib_node_create(struct mlxsw_sp_fib *fib, const void *addr, size_t addr_len, unsigned char prefix_len) { struct mlxsw_sp_fib_node *fib_node; @@ -2031,18 +1990,15 @@ mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr, return NULL; INIT_LIST_HEAD(&fib_node->entry_list); - list_add(&fib_node->list, &vr->fib->node_list); + list_add(&fib_node->list, &fib->node_list); memcpy(fib_node->key.addr, addr, addr_len); fib_node->key.prefix_len = prefix_len; - mlxsw_sp_fib_node_insert(vr->fib, fib_node); - fib_node->vr = vr; return fib_node; } static void mlxsw_sp_fib_node_destroy(struct mlxsw_sp_fib_node *fib_node) { - mlxsw_sp_fib_node_remove(fib_node->vr->fib, fib_node); list_del(&fib_node->list); WARN_ON(!list_empty(&fib_node->entry_list)); kfree(fib_node); @@ -2059,7 +2015,7 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node, static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) { unsigned char prefix_len = fib_node->key.prefix_len; - struct mlxsw_sp_fib *fib = fib_node->vr->fib; + struct mlxsw_sp_fib *fib = fib_node->fib; if (fib->prefix_ref_count[prefix_len]++ == 0) mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len); @@ -2068,32 +2024,98 @@ static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node) { unsigned char prefix_len = fib_node->key.prefix_len; - struct mlxsw_sp_fib *fib = fib_node->vr->fib; + struct mlxsw_sp_fib *fib = fib_node->fib; if (--fib->prefix_ref_count[prefix_len] == 0) mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len); } +static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node, + struct mlxsw_sp_fib *fib) +{ + struct mlxsw_sp_prefix_usage req_prefix_usage; + struct mlxsw_sp_lpm_tree *lpm_tree; + int err; + + err = mlxsw_sp_fib_node_insert(fib, fib_node); + if (err) + return err; + fib_node->fib = fib; + + mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &fib->prefix_usage); + mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len); + + if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { + err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, + &req_prefix_usage); + if (err) + goto err_tree_check; + } else { + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + fib->proto); + if (IS_ERR(lpm_tree)) + return PTR_ERR(lpm_tree); + fib->lpm_tree = lpm_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); + if (err) + goto err_tree_bind; + } + + mlxsw_sp_fib_node_prefix_inc(fib_node); + + return 0; + +err_tree_bind: + fib->lpm_tree = NULL; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); +err_tree_check: + fib_node->fib = NULL; + mlxsw_sp_fib_node_remove(fib, fib_node); + return err; +} + +static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node) +{ + struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree; + struct mlxsw_sp_fib *fib = fib_node->fib; + + mlxsw_sp_fib_node_prefix_dec(fib_node); + + if (mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { + mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); + fib->lpm_tree = NULL; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + } else { + mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, &fib->prefix_usage); + } + + fib_node->fib = NULL; + mlxsw_sp_fib_node_remove(fib, fib_node); +} + static struct mlxsw_sp_fib_node * mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib_node *fib_node; + struct mlxsw_sp_fib *fib; struct mlxsw_sp_vr *vr; int err; - vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->dst_len, fen_info->tb_id, - MLXSW_SP_L3_PROTO_IPV4); + vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->tb_id); if (IS_ERR(vr)) return ERR_CAST(vr); + fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4); - fib_node = mlxsw_sp_fib_node_lookup(vr->fib, &fen_info->dst, + fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst, sizeof(fen_info->dst), fen_info->dst_len); if (fib_node) return fib_node; - fib_node = mlxsw_sp_fib_node_create(vr, &fen_info->dst, + fib_node = mlxsw_sp_fib_node_create(fib, &fen_info->dst, sizeof(fen_info->dst), fen_info->dst_len); if (!fib_node) { @@ -2101,22 +2123,29 @@ mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, goto err_fib_node_create; } + err = mlxsw_sp_fib_node_init(mlxsw_sp, fib_node, fib); + if (err) + goto err_fib_node_init; + return fib_node; +err_fib_node_init: + mlxsw_sp_fib_node_destroy(fib_node); err_fib_node_create: - mlxsw_sp_vr_put(mlxsw_sp, vr); + mlxsw_sp_vr_put(vr); return ERR_PTR(err); } static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - struct mlxsw_sp_vr *vr = fib_node->vr; + struct mlxsw_sp_vr *vr = fib_node->fib->vr; if (!list_empty(&fib_node->entry_list)) return; + mlxsw_sp_fib_node_fini(mlxsw_sp, fib_node); mlxsw_sp_fib_node_destroy(fib_node); - mlxsw_sp_vr_put(mlxsw_sp, vr); + mlxsw_sp_vr_put(vr); } static struct mlxsw_sp_fib_entry * @@ -2261,8 +2290,6 @@ static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp, if (err) goto err_fib4_node_entry_add; - mlxsw_sp_fib_node_prefix_inc(fib_node); - return 0; err_fib4_node_entry_add: @@ -2276,7 +2303,6 @@ mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; - mlxsw_sp_fib_node_prefix_dec(fib_node); mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry); mlxsw_sp_fib4_node_list_remove(fib_entry); } @@ -2415,7 +2441,7 @@ static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - switch (fib_node->vr->proto) { + switch (fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node); break; @@ -2425,26 +2451,32 @@ static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, } } +static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) +{ + struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto); + struct mlxsw_sp_fib_node *fib_node, *tmp; + + list_for_each_entry_safe(fib_node, tmp, &fib->node_list, list) { + bool do_break = &tmp->list == &fib->node_list; + + mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node); + if (do_break) + break; + } +} + static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) { - struct mlxsw_sp_fib_node *fib_node, *tmp; - struct mlxsw_sp_vr *vr; int i; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { - vr = &mlxsw_sp->router.vrs[i]; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i]; - if (!vr->used) + if (!mlxsw_sp_vr_is_used(vr)) continue; - - list_for_each_entry_safe(fib_node, tmp, &vr->fib->node_list, - list) { - bool do_break = &tmp->list == &vr->fib->node_list; - - mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node); - if (do_break) - break; - } + mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); } } From 6913229eea27e63df086f55372e52021727fd0a7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:42 +0100 Subject: [PATCH 132/399] mlxsw: spectrum_router: Explicitly Associate RIFs with VRs Up until now we implicitly associated all the router interfaces (RIFs) with the first virtual router (VR). This must be changed in order to enable VRF offload. Otherwise, a packet received via a VRF slave would do a FIB lookup in the same table used by other VRFs. Instead, bind the RIF to a VR according to the table where FIB lookup should be performed for packets received via the RIF. Currently, we only care about the MAIN and LOCAL tables (which we squash together). Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 4 +- .../net/ethernet/mellanox/mlxsw/spectrum.h | 1 + .../ethernet/mellanox/mlxsw/spectrum_router.c | 63 ++++++++++++++----- 3 files changed, 50 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0899e2d310e2..eb94a5a4625d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4141,7 +4141,8 @@ static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag, static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, enum mlxsw_reg_ritr_if_type type, - u16 rif, u16 mtu, const char *mac) + u16 rif, u16 vr_id, u16 mtu, + const char *mac) { bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL; @@ -4153,6 +4154,7 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, mlxsw_reg_ritr_rif_set(payload, rif); mlxsw_reg_ritr_ipv4_fe_set(payload, 1); mlxsw_reg_ritr_lb_en_set(payload, 1); + mlxsw_reg_ritr_virtual_router_set(payload, vr_id); mlxsw_reg_ritr_mtu_set(payload, mtu); mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 5a7ffa1cadf9..3bc1b0998654 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -187,6 +187,7 @@ struct mlxsw_sp_fib; struct mlxsw_sp_vr { u16 id; /* virtual router ID */ u32 tb_id; /* kernel fib table id */ + unsigned int rif_count; struct mlxsw_sp_fib *fib4; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 0a79fc7afd63..22a4d689ea13 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -58,6 +58,7 @@ struct mlxsw_sp_rif { unsigned char addr[ETH_ALEN]; int mtu; u16 rif; + u16 vr_id; }; static struct mlxsw_sp_rif * @@ -486,7 +487,7 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr) { - if (list_empty(&vr->fib4->node_list)) + if (!vr->rif_count && list_empty(&vr->fib4->node_list)) mlxsw_sp_vr_destroy(vr); } @@ -2666,15 +2667,15 @@ static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, } static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *l3_dev, u16 rif, - bool create) + u16 vr_id, struct net_device *l3_dev, + u16 rif, bool create) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; bool lagged = mlxsw_sp_vport->lagged; char ritr_pl[MLXSW_REG_RITR_LEN]; u16 system_port; - mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, + mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, vr_id, l3_dev->mtu, l3_dev->dev_addr); mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); @@ -2709,7 +2710,8 @@ mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) } static struct mlxsw_sp_rif * -mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f) +mlxsw_sp_rif_alloc(u16 rif, u16 vr_id, struct net_device *l3_dev, + struct mlxsw_sp_fid *f) { struct mlxsw_sp_rif *r; @@ -2721,6 +2723,7 @@ mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f) INIT_LIST_HEAD(&r->neigh_list); ether_addr_copy(r->addr, l3_dev->dev_addr); r->mtu = l3_dev->mtu; + r->vr_id = vr_id; r->dev = l3_dev; r->rif = rif; r->f = f; @@ -2733,6 +2736,7 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, struct net_device *l3_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_vr *vr; struct mlxsw_sp_fid *f; struct mlxsw_sp_rif *r; u16 fid, rif; @@ -2742,9 +2746,14 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, if (rif == MLXSW_SP_INVALID_RIF) return ERR_PTR(-ERANGE); - err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true); + vr = mlxsw_sp_vr_get(mlxsw_sp, RT_TABLE_MAIN); + if (IS_ERR(vr)) + return ERR_CAST(vr); + + err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, + true); if (err) - return ERR_PTR(err); + goto err_vport_rif_sp_op; fid = mlxsw_sp_rif_sp_to_fid(rif); err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); @@ -2757,7 +2766,7 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, goto err_rfid_alloc; } - r = mlxsw_sp_rif_alloc(rif, l3_dev, f); + r = mlxsw_sp_rif_alloc(rif, vr->id, l3_dev, f); if (!r) { err = -ENOMEM; goto err_rif_alloc; @@ -2765,6 +2774,7 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, f->r = r; mlxsw_sp->rifs[rif] = r; + vr->rif_count++; return r; @@ -2773,7 +2783,9 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, err_rfid_alloc: mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); err_rif_fdb_op: - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, false); +err_vport_rif_sp_op: + mlxsw_sp_vr_put(vr); return ERR_PTR(err); } @@ -2781,6 +2793,7 @@ static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, struct mlxsw_sp_rif *r) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[r->vr_id]; struct net_device *l3_dev = r->dev; struct mlxsw_sp_fid *f = r->f; u16 fid = f->fid; @@ -2788,6 +2801,7 @@ static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + vr->rif_count--; mlxsw_sp->rifs[rif] = NULL; f->r = NULL; @@ -2797,7 +2811,9 @@ static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false); + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, false); + + mlxsw_sp_vr_put(vr); } static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, @@ -2948,7 +2964,7 @@ static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) return MLXSW_REG_RITR_VLAN_IF; } -static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, +static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, u16 vr_id, struct net_device *l3_dev, u16 fid, u16 rif, bool create) @@ -2957,7 +2973,7 @@ static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, char ritr_pl[MLXSW_REG_RITR_LEN]; rif_type = mlxsw_sp_rif_type_get(fid); - mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu, + mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, vr_id, l3_dev->mtu, l3_dev->dev_addr); mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid); @@ -2968,6 +2984,7 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, struct net_device *l3_dev, struct mlxsw_sp_fid *f) { + struct mlxsw_sp_vr *vr; struct mlxsw_sp_rif *r; u16 rif; int err; @@ -2976,11 +2993,16 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, if (rif == MLXSW_SP_INVALID_RIF) return -ERANGE; + vr = mlxsw_sp_vr_get(mlxsw_sp, RT_TABLE_MAIN); + if (IS_ERR(vr)) + return PTR_ERR(vr); + err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); if (err) - return err; + goto err_port_flood_set; - err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, + true); if (err) goto err_rif_bridge_op; @@ -2988,7 +3010,7 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rif_fdb_op; - r = mlxsw_sp_rif_alloc(rif, l3_dev, f); + r = mlxsw_sp_rif_alloc(rif, vr->id, l3_dev, f); if (!r) { err = -ENOMEM; goto err_rif_alloc; @@ -2996,6 +3018,7 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, f->r = r; mlxsw_sp->rifs[rif] = r; + vr->rif_count++; netdev_dbg(l3_dev, "RIF=%d created\n", rif); @@ -3004,21 +3027,25 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, err_rif_alloc: mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); err_rif_fdb_op: - mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, false); err_rif_bridge_op: mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); +err_port_flood_set: + mlxsw_sp_vr_put(vr); return err; } void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *r) { + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[r->vr_id]; struct net_device *l3_dev = r->dev; struct mlxsw_sp_fid *f = r->f; u16 rif = r->rif; mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + vr->rif_count--; mlxsw_sp->rifs[rif] = NULL; f->r = NULL; @@ -3026,10 +3053,12 @@ void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); - mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, false); mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); + mlxsw_sp_vr_put(vr); + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); } From b5d90e6d6b19477c49ad699c173bbcfa3e4725bd Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:53:43 +0100 Subject: [PATCH 133/399] mlxsw: spectrum_router: Make abort mechanism VR-aware When the abort mechanism is invoked it binds the first virtual router (VR) to an LPM tree and inserts a default route to direct packets to the CPU. With VRFs, we can have router interfaces (RIFs) bound to multiple VRs, so we need to make sure packets are trapped from all VRs and not just the first one. Upon abort invocation, bind all active VRs to the same LPM tree and insert a default route in each. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 39 +++++++++++++------ 1 file changed, 27 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 22a4d689ea13..80345a1ddf17 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2392,9 +2392,7 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) { char ralta_pl[MLXSW_REG_RALTA_LEN]; char ralst_pl[MLXSW_REG_RALST_LEN]; - char raltb_pl[MLXSW_REG_RALTB_LEN]; - char ralue_pl[MLXSW_REG_RALUE_LEN]; - int err; + int i, err; mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4, MLXSW_SP_LPM_TREE_MIN); @@ -2407,16 +2405,33 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) if (err) return err; - mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4, - MLXSW_SP_LPM_TREE_MIN); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); - if (err) - return err; + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i]; + char raltb_pl[MLXSW_REG_RALTB_LEN]; + char ralue_pl[MLXSW_REG_RALUE_LEN]; - mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4, - MLXSW_REG_RALUE_OP_WRITE_WRITE, 0, 0, 0); - mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + if (!mlxsw_sp_vr_is_used(vr)) + continue; + + mlxsw_reg_raltb_pack(raltb_pl, vr->id, + MLXSW_REG_RALXX_PROTOCOL_IPV4, + MLXSW_SP_LPM_TREE_MIN); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), + raltb_pl); + if (err) + return err; + + mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4, + MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0, + 0); + mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), + ralue_pl); + if (err) + return err; + } + + return 0; } static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, From c0243892cbb0e48873d6132f673c830602808245 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:56:18 +0100 Subject: [PATCH 134/399] ipv4: fib: Move FIB notification code to a separate file Most of the code concerned with the FIB notification chain currently resides in fib_trie.c, but this isn't really appropriate, as the FIB notification chain is also used for FIB rules. Therefore, it makes sense to move the common FIB notification code to a separate file and have it export the relevant functions, which can be invoked by its different users (e.g., fib_trie.c, fib_rules.c). Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 15 +++++++ net/ipv4/Makefile | 2 +- net/ipv4/fib_notifier.c | 86 ++++++++++++++++++++++++++++++++++++ net/ipv4/fib_rules.c | 9 ++++ net/ipv4/fib_trie.c | 97 +---------------------------------------- 5 files changed, 113 insertions(+), 96 deletions(-) create mode 100644 net/ipv4/fib_notifier.c diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 368bb4024b78..3ad87063a475 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -232,9 +232,24 @@ enum fib_event_type { int register_fib_notifier(struct notifier_block *nb, void (*cb)(struct notifier_block *nb)); int unregister_fib_notifier(struct notifier_block *nb); +int call_fib_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); +void fib_notify(struct net *net, struct notifier_block *nb, + enum fib_event_type event_type); +#ifdef CONFIG_IP_MULTIPLE_TABLES +void fib_rules_notify(struct net *net, struct notifier_block *nb, + enum fib_event_type event_type); +#else +static inline void fib_rules_notify(struct net *net, struct notifier_block *nb, + enum fib_event_type event_type) +{ +} +#endif + struct fib_table { struct hlist_node tb_hlist; u32 tb_id; diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index c6d4238ff94a..f83de23a30e7 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -11,7 +11,7 @@ obj-y := route.o inetpeer.o protocol.o \ tcp_rate.o tcp_recovery.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ - fib_frontend.o fib_semantics.o fib_trie.o \ + fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c new file mode 100644 index 000000000000..91f8f181fa03 --- /dev/null +++ b/net/ipv4/fib_notifier.c @@ -0,0 +1,86 @@ +#include +#include +#include +#include +#include +#include +#include + +static ATOMIC_NOTIFIER_HEAD(fib_chain); + +int call_fib_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + info->net = net; + return nb->notifier_call(nb, event_type, info); +} + +int call_fib_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + net->ipv4.fib_seq++; + info->net = net; + return atomic_notifier_call_chain(&fib_chain, event_type, info); +} + +static unsigned int fib_seq_sum(void) +{ + unsigned int fib_seq = 0; + struct net *net; + + rtnl_lock(); + for_each_net(net) + fib_seq += net->ipv4.fib_seq; + rtnl_unlock(); + + return fib_seq; +} + +static bool fib_dump_is_consistent(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb), + unsigned int fib_seq) +{ + atomic_notifier_chain_register(&fib_chain, nb); + if (fib_seq == fib_seq_sum()) + return true; + atomic_notifier_chain_unregister(&fib_chain, nb); + if (cb) + cb(nb); + return false; +} + +#define FIB_DUMP_MAX_RETRIES 5 +int register_fib_notifier(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb)) +{ + int retries = 0; + + do { + unsigned int fib_seq = fib_seq_sum(); + struct net *net; + + /* Mutex semantics guarantee that every change done to + * FIB tries before we read the change sequence counter + * is now visible to us. + */ + rcu_read_lock(); + for_each_net_rcu(net) { + fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD); + fib_notify(net, nb, FIB_EVENT_ENTRY_ADD); + } + rcu_read_unlock(); + + if (fib_dump_is_consistent(nb, cb, fib_seq)) + return 0; + } while (++retries < FIB_DUMP_MAX_RETRIES); + + return -EBUSY; +} +EXPORT_SYMBOL(register_fib_notifier); + +int unregister_fib_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&fib_chain, nb); +} +EXPORT_SYMBOL(unregister_fib_notifier); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 2e50062f642d..bbd57f099183 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -172,6 +172,15 @@ static int call_fib_rule_notifiers(struct net *net, return call_fib_notifiers(net, event_type, &info); } +void fib_rules_notify(struct net *net, struct notifier_block *nb, + enum fib_event_type event_type) +{ + struct fib_notifier_info info; + + if (net->ipv4.fib_has_custom_rules) + call_fib_notifier(nb, net, event_type, &info); +} + static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { FRA_GENERIC_POLICY, [FRA_FLOW] = { .type = NLA_U32 }, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2f0d8233950f..5639e8a42f1b 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -84,43 +84,6 @@ #include #include "fib_lookup.h" -static unsigned int fib_seq_sum(void) -{ - unsigned int fib_seq = 0; - struct net *net; - - rtnl_lock(); - for_each_net(net) - fib_seq += net->ipv4.fib_seq; - rtnl_unlock(); - - return fib_seq; -} - -static ATOMIC_NOTIFIER_HEAD(fib_chain); - -static int call_fib_notifier(struct notifier_block *nb, struct net *net, - enum fib_event_type event_type, - struct fib_notifier_info *info) -{ - info->net = net; - return nb->notifier_call(nb, event_type, info); -} - -static void fib_rules_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) -{ -#ifdef CONFIG_IP_MULTIPLE_TABLES - struct fib_notifier_info info; - - if (net->ipv4.fib_has_custom_rules) - call_fib_notifier(nb, net, event_type, &info); -#endif -} - -static void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type); - static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_info *fi, @@ -137,62 +100,6 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, return call_fib_notifier(nb, net, event_type, &info.info); } -static bool fib_dump_is_consistent(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb), - unsigned int fib_seq) -{ - atomic_notifier_chain_register(&fib_chain, nb); - if (fib_seq == fib_seq_sum()) - return true; - atomic_notifier_chain_unregister(&fib_chain, nb); - if (cb) - cb(nb); - return false; -} - -#define FIB_DUMP_MAX_RETRIES 5 -int register_fib_notifier(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)) -{ - int retries = 0; - - do { - unsigned int fib_seq = fib_seq_sum(); - struct net *net; - - /* Mutex semantics guarantee that every change done to - * FIB tries before we read the change sequence counter - * is now visible to us. - */ - rcu_read_lock(); - for_each_net_rcu(net) { - fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD); - fib_notify(net, nb, FIB_EVENT_ENTRY_ADD); - } - rcu_read_unlock(); - - if (fib_dump_is_consistent(nb, cb, fib_seq)) - return 0; - } while (++retries < FIB_DUMP_MAX_RETRIES); - - return -EBUSY; -} -EXPORT_SYMBOL(register_fib_notifier); - -int unregister_fib_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&fib_chain, nb); -} -EXPORT_SYMBOL(unregister_fib_notifier); - -int call_fib_notifiers(struct net *net, enum fib_event_type event_type, - struct fib_notifier_info *info) -{ - net->ipv4.fib_seq++; - info->net = net; - return atomic_notifier_call_chain(&fib_chain, event_type, info); -} - static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_info *fi, @@ -2036,8 +1943,8 @@ static void fib_table_notify(struct net *net, struct fib_table *tb, } } -static void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) +void fib_notify(struct net *net, struct notifier_block *nb, + enum fib_event_type event_type) { unsigned int h; From d05f7a7dd470f71dc45c2928dbf76afe2b1c2f07 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 10 Mar 2017 08:56:19 +0100 Subject: [PATCH 135/399] ipv4: fib: Remove redundant argument We always pass the same event type to fib_notify() and fib_rules_notify(), so we can safely drop this argument. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 9 +++------ net/ipv4/fib_notifier.c | 4 ++-- net/ipv4/fib_rules.c | 5 ++--- net/ipv4/fib_trie.c | 15 ++++++--------- 4 files changed, 13 insertions(+), 20 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 3ad87063a475..d9cee9659978 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -238,14 +238,11 @@ int call_fib_notifier(struct notifier_block *nb, struct net *net, int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); -void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type); +void fib_notify(struct net *net, struct notifier_block *nb); #ifdef CONFIG_IP_MULTIPLE_TABLES -void fib_rules_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type); +void fib_rules_notify(struct net *net, struct notifier_block *nb); #else -static inline void fib_rules_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) +static inline void fib_rules_notify(struct net *net, struct notifier_block *nb) { } #endif diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index 91f8f181fa03..e0714d975947 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -66,8 +66,8 @@ int register_fib_notifier(struct notifier_block *nb, */ rcu_read_lock(); for_each_net_rcu(net) { - fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD); - fib_notify(net, nb, FIB_EVENT_ENTRY_ADD); + fib_rules_notify(net, nb); + fib_notify(net, nb); } rcu_read_unlock(); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index bbd57f099183..289210903d58 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -172,13 +172,12 @@ static int call_fib_rule_notifiers(struct net *net, return call_fib_notifiers(net, event_type, &info); } -void fib_rules_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) +void fib_rules_notify(struct net *net, struct notifier_block *nb) { struct fib_notifier_info info; if (net->ipv4.fib_has_custom_rules) - call_fib_notifier(nb, net, event_type, &info); + call_fib_notifier(nb, net, FIB_EVENT_RULE_ADD, &info); } static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5639e8a42f1b..1201409ba1dc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1902,8 +1902,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb) } static void fib_leaf_notify(struct net *net, struct key_vector *l, - struct fib_table *tb, struct notifier_block *nb, - enum fib_event_type event_type) + struct fib_table *tb, struct notifier_block *nb) { struct fib_alias *fa; @@ -1919,22 +1918,21 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, if (tb->tb_id != fa->tb_id) continue; - call_fib_entry_notifier(nb, net, event_type, l->key, + call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, KEYLENGTH - fa->fa_slen, fi, fa->fa_tos, fa->fa_type, fa->tb_id); } } static void fib_table_notify(struct net *net, struct fib_table *tb, - struct notifier_block *nb, - enum fib_event_type event_type) + struct notifier_block *nb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - fib_leaf_notify(net, l, tb, nb, event_type); + fib_leaf_notify(net, l, tb, nb); key = l->key + 1; /* stop in case of wrap around */ @@ -1943,8 +1941,7 @@ static void fib_table_notify(struct net *net, struct fib_table *tb, } } -void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) +void fib_notify(struct net *net, struct notifier_block *nb) { unsigned int h; @@ -1953,7 +1950,7 @@ void fib_notify(struct net *net, struct notifier_block *nb, struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) - fib_table_notify(net, tb, nb, event_type); + fib_table_notify(net, tb, nb); } } From 99bdb400f7a5c998e106aeef3954e94b1d3d4ca5 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Mon, 6 Mar 2017 23:26:09 +0100 Subject: [PATCH 136/399] net: tundra: tsi108: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/tundra/tsi108_eth.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index c5583991da4a..5ac6eaa9e785 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1499,27 +1499,29 @@ static void tsi108_init_mac(struct net_device *dev) TSI_WRITE(TSI108_EC_INTMASK, ~0); } -static int tsi108_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int tsi108_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct tsi108_prv_data *data = netdev_priv(dev); unsigned long flags; int rc; spin_lock_irqsave(&data->txlock, flags); - rc = mii_ethtool_gset(&data->mii_if, cmd); + rc = mii_ethtool_get_link_ksettings(&data->mii_if, cmd); spin_unlock_irqrestore(&data->txlock, flags); return rc; } -static int tsi108_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int tsi108_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct tsi108_prv_data *data = netdev_priv(dev); unsigned long flags; int rc; spin_lock_irqsave(&data->txlock, flags); - rc = mii_ethtool_sset(&data->mii_if, cmd); + rc = mii_ethtool_set_link_ksettings(&data->mii_if, cmd); spin_unlock_irqrestore(&data->txlock, flags); return rc; @@ -1535,8 +1537,8 @@ static int tsi108_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static const struct ethtool_ops tsi108_ethtool_ops = { .get_link = ethtool_op_get_link, - .get_settings = tsi108_get_settings, - .set_settings = tsi108_set_settings, + .get_link_ksettings = tsi108_get_link_ksettings, + .set_link_ksettings = tsi108_set_link_ksettings, }; static const struct net_device_ops tsi108_netdev_ops = { From 8704f21c8449d4ee0ea22a16014b6af6e757ec81 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Tue, 7 Mar 2017 23:32:25 +0100 Subject: [PATCH 137/399] net: intel: ixgbe: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- .../net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 168 ++++++++++-------- 1 file changed, 91 insertions(+), 77 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 90fa5bf23d1b..0da0752fedef 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -186,60 +186,62 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw) } } -static int ixgbe_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbe_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; ixgbe_link_speed supported_link; bool autoneg = false; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg); /* set the supported link speeds */ if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->supported |= ixgbe_get_supported_10gtypes(hw); + supported |= ixgbe_get_supported_10gtypes(hw); if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) - ecmd->supported |= (ixgbe_isbackplane(hw->phy.media_type)) ? + supported |= (ixgbe_isbackplane(hw->phy.media_type)) ? SUPPORTED_1000baseKX_Full : SUPPORTED_1000baseT_Full; if (supported_link & IXGBE_LINK_SPEED_100_FULL) - ecmd->supported |= SUPPORTED_100baseT_Full; + supported |= SUPPORTED_100baseT_Full; if (supported_link & IXGBE_LINK_SPEED_10_FULL) - ecmd->supported |= SUPPORTED_10baseT_Full; + supported |= SUPPORTED_10baseT_Full; /* default advertised speed if phy.autoneg_advertised isn't set */ - ecmd->advertising = ecmd->supported; + advertising = supported; /* set the advertised speeds */ if (hw->phy.autoneg_advertised) { - ecmd->advertising = 0; + advertising = 0; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) - ecmd->advertising |= ADVERTISED_10baseT_Full; + advertising |= ADVERTISED_10baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) - ecmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising |= ecmd->supported & ADVRTSD_MSK_10G; + advertising |= supported & ADVRTSD_MSK_10G; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) { - if (ecmd->supported & SUPPORTED_1000baseKX_Full) - ecmd->advertising |= ADVERTISED_1000baseKX_Full; + if (supported & SUPPORTED_1000baseKX_Full) + advertising |= ADVERTISED_1000baseKX_Full; else - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; } } else { if (hw->phy.multispeed_fiber && !autoneg) { if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising = ADVERTISED_10000baseT_Full; + advertising = ADVERTISED_10000baseT_Full; } } if (autoneg) { - ecmd->supported |= SUPPORTED_Autoneg; - ecmd->advertising |= ADVERTISED_Autoneg; - ecmd->autoneg = AUTONEG_ENABLE; + supported |= SUPPORTED_Autoneg; + advertising |= ADVERTISED_Autoneg; + cmd->base.autoneg = AUTONEG_ENABLE; } else - ecmd->autoneg = AUTONEG_DISABLE; - - ecmd->transceiver = XCVR_EXTERNAL; + cmd->base.autoneg = AUTONEG_DISABLE; /* Determine the remaining settings based on the PHY type. */ switch (adapter->hw.phy.type) { @@ -248,14 +250,14 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_phy_x550em_ext_t: case ixgbe_phy_fw: case ixgbe_phy_cu_unknown: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + supported |= SUPPORTED_TP; + advertising |= ADVERTISED_TP; + cmd->base.port = PORT_TP; break; case ixgbe_phy_qt: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_FIBRE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; break; case ixgbe_phy_nl: case ixgbe_phy_sfp_passive_tyco: @@ -273,9 +275,9 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_sfp_type_da_cu: case ixgbe_sfp_type_da_cu_core0: case ixgbe_sfp_type_da_cu_core1: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_DA; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_DA; break; case ixgbe_sfp_type_sr: case ixgbe_sfp_type_lr: @@ -285,102 +287,113 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_sfp_type_1g_sx_core1: case ixgbe_sfp_type_1g_lx_core0: case ixgbe_sfp_type_1g_lx_core1: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_FIBRE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; break; case ixgbe_sfp_type_not_present: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_NONE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_NONE; break; case ixgbe_sfp_type_1g_cu_core0: case ixgbe_sfp_type_1g_cu_core1: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + supported |= SUPPORTED_TP; + advertising |= ADVERTISED_TP; + cmd->base.port = PORT_TP; break; case ixgbe_sfp_type_unknown: default: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_OTHER; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_OTHER; break; } break; case ixgbe_phy_xaui: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_NONE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_NONE; break; case ixgbe_phy_unknown: case ixgbe_phy_generic: case ixgbe_phy_sfp_unsupported: default: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_OTHER; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_OTHER; break; } /* Indicate pause support */ - ecmd->supported |= SUPPORTED_Pause; + supported |= SUPPORTED_Pause; switch (hw->fc.requested_mode) { case ixgbe_fc_full: - ecmd->advertising |= ADVERTISED_Pause; + advertising |= ADVERTISED_Pause; break; case ixgbe_fc_rx_pause: - ecmd->advertising |= ADVERTISED_Pause | + advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; break; case ixgbe_fc_tx_pause: - ecmd->advertising |= ADVERTISED_Asym_Pause; + advertising |= ADVERTISED_Asym_Pause; break; default: - ecmd->advertising &= ~(ADVERTISED_Pause | + advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); } if (netif_carrier_ok(netdev)) { switch (adapter->link_speed) { case IXGBE_LINK_SPEED_10GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_10000); + cmd->base.speed = SPEED_10000; break; case IXGBE_LINK_SPEED_5GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_5000); + cmd->base.speed = SPEED_5000; break; case IXGBE_LINK_SPEED_2_5GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_2500); + cmd->base.speed = SPEED_2500; break; case IXGBE_LINK_SPEED_1GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; case IXGBE_LINK_SPEED_100_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; break; case IXGBE_LINK_SPEED_10_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_10); + cmd->base.speed = SPEED_10; break; default: break; } - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + return 0; } -static int ixgbe_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbe_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 advertised, old; s32 err = 0; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); if ((hw->phy.media_type == ixgbe_media_type_copper) || (hw->phy.multispeed_fiber)) { @@ -388,12 +401,12 @@ static int ixgbe_set_settings(struct net_device *netdev, * this function does not support duplex forcing, but can * limit the advertising of the adapter to the specified speed */ - if (ecmd->advertising & ~ecmd->supported) + if (advertising & ~supported) return -EINVAL; /* only allow one speed at a time if no autoneg */ - if (!ecmd->autoneg && hw->phy.multispeed_fiber) { - if (ecmd->advertising == + if (!cmd->base.autoneg && hw->phy.multispeed_fiber) { + if (advertising == (ADVERTISED_10000baseT_Full | ADVERTISED_1000baseT_Full)) return -EINVAL; @@ -401,16 +414,16 @@ static int ixgbe_set_settings(struct net_device *netdev, old = hw->phy.autoneg_advertised; advertised = 0; - if (ecmd->advertising & ADVERTISED_10000baseT_Full) + if (advertising & ADVERTISED_10000baseT_Full) advertised |= IXGBE_LINK_SPEED_10GB_FULL; - if (ecmd->advertising & ADVERTISED_1000baseT_Full) + if (advertising & ADVERTISED_1000baseT_Full) advertised |= IXGBE_LINK_SPEED_1GB_FULL; - if (ecmd->advertising & ADVERTISED_100baseT_Full) + if (advertising & ADVERTISED_100baseT_Full) advertised |= IXGBE_LINK_SPEED_100_FULL; - if (ecmd->advertising & ADVERTISED_10baseT_Full) + if (advertising & ADVERTISED_10baseT_Full) advertised |= IXGBE_LINK_SPEED_10_FULL; if (old == advertised) @@ -428,10 +441,11 @@ static int ixgbe_set_settings(struct net_device *netdev, clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); } else { /* in this case we currently only support 10Gb/FULL */ - u32 speed = ethtool_cmd_speed(ecmd); - if ((ecmd->autoneg == AUTONEG_ENABLE) || - (ecmd->advertising != ADVERTISED_10000baseT_Full) || - (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL)) + u32 speed = cmd->base.speed; + + if ((cmd->base.autoneg == AUTONEG_ENABLE) || + (advertising != ADVERTISED_10000baseT_Full) || + (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL)) return -EINVAL; } @@ -3402,8 +3416,6 @@ static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags) } static const struct ethtool_ops ixgbe_ethtool_ops = { - .get_settings = ixgbe_get_settings, - .set_settings = ixgbe_set_settings, .get_drvinfo = ixgbe_get_drvinfo, .get_regs_len = ixgbe_get_regs_len, .get_regs = ixgbe_get_regs, @@ -3442,6 +3454,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .get_ts_info = ixgbe_get_ts_info, .get_module_info = ixgbe_get_module_info, .get_module_eeprom = ixgbe_get_module_eeprom, + .get_link_ksettings = ixgbe_get_link_ksettings, + .set_link_ksettings = ixgbe_set_link_ksettings, }; void ixgbe_set_ethtool_ops(struct net_device *netdev) From f918b9861f222bae04747fe0ec804d1825337f8e Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Tue, 7 Mar 2017 23:46:16 +0100 Subject: [PATCH 138/399] net: via: via-rhine: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/via/via-rhine.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index c068c58428f7..4cf41f779d0e 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -2303,25 +2303,27 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info)); } -static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct rhine_private *rp = netdev_priv(dev); int rc; mutex_lock(&rp->task_lock); - rc = mii_ethtool_gset(&rp->mii_if, cmd); + rc = mii_ethtool_get_link_ksettings(&rp->mii_if, cmd); mutex_unlock(&rp->task_lock); return rc; } -static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netdev_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct rhine_private *rp = netdev_priv(dev); int rc; mutex_lock(&rp->task_lock); - rc = mii_ethtool_sset(&rp->mii_if, cmd); + rc = mii_ethtool_set_link_ksettings(&rp->mii_if, cmd); rhine_set_carrier(&rp->mii_if); mutex_unlock(&rp->task_lock); @@ -2391,14 +2393,14 @@ static int rhine_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, - .get_settings = netdev_get_settings, - .set_settings = netdev_set_settings, .nway_reset = netdev_nway_reset, .get_link = netdev_get_link, .get_msglevel = netdev_get_msglevel, .set_msglevel = netdev_set_msglevel, .get_wol = rhine_get_wol, .set_wol = rhine_set_wol, + .get_link_ksettings = netdev_get_link_ksettings, + .set_link_ksettings = netdev_set_link_ksettings, }; static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) From 92f4a13efd8b2ab263e589e8bb814ef49f4fc6f9 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Wed, 8 Mar 2017 22:20:20 +0100 Subject: [PATCH 139/399] net: via: via-velocity: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/via/via-velocity.c | 62 ++++++++++++++----------- 1 file changed, 35 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index d088788b27a7..ef9538ee53d0 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -3291,15 +3291,17 @@ static void velocity_ethtool_down(struct net_device *dev) velocity_set_power_state(vptr, PCI_D3hot); } -static int velocity_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int velocity_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct velocity_info *vptr = netdev_priv(dev); struct mac_regs __iomem *regs = vptr->mac_regs; u32 status; + u32 supported, advertising; + status = check_connection_type(vptr->mac_regs); - cmd->supported = SUPPORTED_TP | + supported = SUPPORTED_TP | SUPPORTED_Autoneg | SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | @@ -3308,9 +3310,9 @@ static int velocity_get_settings(struct net_device *dev, SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full; - cmd->advertising = ADVERTISED_TP | ADVERTISED_Autoneg; + advertising = ADVERTISED_TP | ADVERTISED_Autoneg; if (vptr->options.spd_dpx == SPD_DPX_AUTO) { - cmd->advertising |= + advertising |= ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full | ADVERTISED_100baseT_Half | @@ -3320,19 +3322,19 @@ static int velocity_get_settings(struct net_device *dev, } else { switch (vptr->options.spd_dpx) { case SPD_DPX_1000_FULL: - cmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; break; case SPD_DPX_100_HALF: - cmd->advertising |= ADVERTISED_100baseT_Half; + advertising |= ADVERTISED_100baseT_Half; break; case SPD_DPX_100_FULL: - cmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; break; case SPD_DPX_10_HALF: - cmd->advertising |= ADVERTISED_10baseT_Half; + advertising |= ADVERTISED_10baseT_Half; break; case SPD_DPX_10_FULL: - cmd->advertising |= ADVERTISED_10baseT_Full; + advertising |= ADVERTISED_10baseT_Full; break; default: break; @@ -3340,30 +3342,35 @@ static int velocity_get_settings(struct net_device *dev, } if (status & VELOCITY_SPEED_1000) - ethtool_cmd_speed_set(cmd, SPEED_1000); + cmd->base.speed = SPEED_1000; else if (status & VELOCITY_SPEED_100) - ethtool_cmd_speed_set(cmd, SPEED_100); + cmd->base.speed = SPEED_100; else - ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->base.speed = SPEED_10; - cmd->autoneg = (status & VELOCITY_AUTONEG_ENABLE) ? AUTONEG_ENABLE : AUTONEG_DISABLE; - cmd->port = PORT_TP; - cmd->transceiver = XCVR_INTERNAL; - cmd->phy_address = readb(®s->MIIADR) & 0x1F; + cmd->base.autoneg = (status & VELOCITY_AUTONEG_ENABLE) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; + cmd->base.port = PORT_TP; + cmd->base.phy_address = readb(®s->MIIADR) & 0x1F; if (status & VELOCITY_DUPLEX_FULL) - cmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - cmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int velocity_set_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int velocity_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct velocity_info *vptr = netdev_priv(dev); - u32 speed = ethtool_cmd_speed(cmd); + u32 speed = cmd->base.speed; u32 curr_status; u32 new_status = 0; int ret = 0; @@ -3371,11 +3378,12 @@ static int velocity_set_settings(struct net_device *dev, curr_status = check_connection_type(vptr->mac_regs); curr_status &= (~VELOCITY_LINK_FAIL); - new_status |= ((cmd->autoneg) ? VELOCITY_AUTONEG_ENABLE : 0); + new_status |= ((cmd->base.autoneg) ? VELOCITY_AUTONEG_ENABLE : 0); new_status |= ((speed == SPEED_1000) ? VELOCITY_SPEED_1000 : 0); new_status |= ((speed == SPEED_100) ? VELOCITY_SPEED_100 : 0); new_status |= ((speed == SPEED_10) ? VELOCITY_SPEED_10 : 0); - new_status |= ((cmd->duplex == DUPLEX_FULL) ? VELOCITY_DUPLEX_FULL : 0); + new_status |= ((cmd->base.duplex == DUPLEX_FULL) ? + VELOCITY_DUPLEX_FULL : 0); if ((new_status & VELOCITY_AUTONEG_ENABLE) && (new_status != (curr_status | VELOCITY_AUTONEG_ENABLE))) { @@ -3644,8 +3652,6 @@ static void velocity_get_ethtool_stats(struct net_device *dev, } static const struct ethtool_ops velocity_ethtool_ops = { - .get_settings = velocity_get_settings, - .set_settings = velocity_set_settings, .get_drvinfo = velocity_get_drvinfo, .get_wol = velocity_ethtool_get_wol, .set_wol = velocity_ethtool_set_wol, @@ -3658,7 +3664,9 @@ static const struct ethtool_ops velocity_ethtool_ops = { .get_coalesce = velocity_get_coalesce, .set_coalesce = velocity_set_coalesce, .begin = velocity_ethtool_up, - .complete = velocity_ethtool_down + .complete = velocity_ethtool_down, + .get_link_ksettings = velocity_get_link_ksettings, + .set_link_ksettings = velocity_set_link_ksettings, }; #if defined(CONFIG_PM) && defined(CONFIG_INET) From 031e51445a065d94639faf1581d0377438a33b96 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Wed, 8 Mar 2017 23:16:11 +0100 Subject: [PATCH 140/399] net: fjes: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/fjes/fjes_ethtool.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c index 6575f880f1be..7d101714c2ef 100644 --- a/drivers/net/fjes/fjes_ethtool.c +++ b/drivers/net/fjes/fjes_ethtool.c @@ -175,16 +175,15 @@ static void fjes_get_drvinfo(struct net_device *netdev, "platform:%s", plat_dev->name); } -static int fjes_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int fjes_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ecmd) { - ecmd->supported = 0; - ecmd->advertising = 0; - ecmd->duplex = DUPLEX_FULL; - ecmd->autoneg = AUTONEG_DISABLE; - ecmd->transceiver = XCVR_DUMMY1; - ecmd->port = PORT_NONE; - ethtool_cmd_speed_set(ecmd, 20000); /* 20Gb/s */ + ethtool_link_ksettings_zero_link_mode(ecmd, supported); + ethtool_link_ksettings_zero_link_mode(ecmd, advertising); + ecmd->base.duplex = DUPLEX_FULL; + ecmd->base.autoneg = AUTONEG_DISABLE; + ecmd->base.port = PORT_NONE; + ecmd->base.speed = 20000; /* 20Gb/s */ return 0; } @@ -296,7 +295,6 @@ static int fjes_get_dump_data(struct net_device *netdev, } static const struct ethtool_ops fjes_ethtool_ops = { - .get_settings = fjes_get_settings, .get_drvinfo = fjes_get_drvinfo, .get_ethtool_stats = fjes_get_ethtool_stats, .get_strings = fjes_get_strings, @@ -306,6 +304,7 @@ static const struct ethtool_ops fjes_ethtool_ops = { .set_dump = fjes_set_dump, .get_dump_flag = fjes_get_dump_flag, .get_dump_data = fjes_get_dump_data, + .get_link_ksettings = fjes_get_link_ksettings, }; void fjes_set_ethtool_ops(struct net_device *netdev) From 5e8456fdd23c23bbfa06e0d647c90758102a4410 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Wed, 8 Mar 2017 23:41:04 +0100 Subject: [PATCH 141/399] net: hyperv: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Tested-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc_drv.c | 39 ++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 18 deletions(-) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 617dd90803c9..b12808ab3432 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -789,18 +789,19 @@ static int netvsc_set_channels(struct net_device *net, return ret; } -static bool netvsc_validate_ethtool_ss_cmd(const struct ethtool_cmd *cmd) +static bool +netvsc_validate_ethtool_ss_cmd(const struct ethtool_link_ksettings *cmd) { - struct ethtool_cmd diff1 = *cmd; - struct ethtool_cmd diff2 = {}; + struct ethtool_link_ksettings diff1 = *cmd; + struct ethtool_link_ksettings diff2 = {}; - ethtool_cmd_speed_set(&diff1, 0); - diff1.duplex = 0; + diff1.base.speed = 0; + diff1.base.duplex = 0; /* advertising and cmd are usually set */ - diff1.advertising = 0; - diff1.cmd = 0; + ethtool_link_ksettings_zero_link_mode(&diff1, advertising); + diff1.base.cmd = 0; /* We set port to PORT_OTHER */ - diff2.port = PORT_OTHER; + diff2.base.port = PORT_OTHER; return !memcmp(&diff1, &diff2, sizeof(diff1)); } @@ -813,30 +814,32 @@ static void netvsc_init_settings(struct net_device *dev) ndc->duplex = DUPLEX_UNKNOWN; } -static int netvsc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netvsc_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct net_device_context *ndc = netdev_priv(dev); - ethtool_cmd_speed_set(cmd, ndc->speed); - cmd->duplex = ndc->duplex; - cmd->port = PORT_OTHER; + cmd->base.speed = ndc->speed; + cmd->base.duplex = ndc->duplex; + cmd->base.port = PORT_OTHER; return 0; } -static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int netvsc_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct net_device_context *ndc = netdev_priv(dev); u32 speed; - speed = ethtool_cmd_speed(cmd); + speed = cmd->base.speed; if (!ethtool_validate_speed(speed) || - !ethtool_validate_duplex(cmd->duplex) || + !ethtool_validate_duplex(cmd->base.duplex) || !netvsc_validate_ethtool_ss_cmd(cmd)) return -EINVAL; ndc->speed = speed; - ndc->duplex = cmd->duplex; + ndc->duplex = cmd->base.duplex; return 0; } @@ -1170,13 +1173,13 @@ static const struct ethtool_ops ethtool_ops = { .get_channels = netvsc_get_channels, .set_channels = netvsc_set_channels, .get_ts_info = ethtool_op_get_ts_info, - .get_settings = netvsc_get_settings, - .set_settings = netvsc_set_settings, .get_rxnfc = netvsc_get_rxnfc, .get_rxfh_key_size = netvsc_get_rxfh_key_size, .get_rxfh_indir_size = netvsc_rss_indir_size, .get_rxfh = netvsc_get_rxfh, .set_rxfh = netvsc_set_rxfh, + .get_link_ksettings = netvsc_get_link_ksettings, + .set_link_ksettings = netvsc_set_link_ksettings, }; static const struct net_device_ops device_ops = { From 49b499718fa1b0d639663cfd03085b9bfd23cdc8 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Wed, 8 Mar 2017 16:03:32 +0100 Subject: [PATCH 142/399] net: sched: make default fifo qdiscs appear in the dump The original reason [1] for having hidden qdiscs (potential scalability issues in qdisc_match_from_root() with single linked list in case of large amount of qdiscs) has been invalidated by 59cc1f61f0 ("net: sched: convert qdisc linked list to hashtable"). This allows us for bringing more clarity and determinism into the dump by making default pfifo qdiscs visible. We're not turning this on by default though, at it was deemed [2] too intrusive / unnecessary change of default behavior towards userspace. Instead, TCA_DUMP_INVISIBLE netlink attribute is introduced, which allows applications to request complete qdisc hierarchy dump, including the ones that have always been implicit/invisible. Singleton noop_qdisc stays invisible, as teaching the whole infrastructure about singletons would require quite some surgery with very little gain (seeing no qdisc or seeing noop qdisc in the dump is probably setting the same user expectation). [1] http://lkml.kernel.org/r/1460732328.10638.74.camel@edumazet-glaptop3.roam.corp.google.com [2] http://lkml.kernel.org/r/20161021.105935.1907696543877061916.davem@davemloft.net Signed-off-by: Jiri Kosina Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 +- include/net/sch_generic.h | 1 + include/uapi/linux/rtnetlink.h | 1 + net/sched/sch_api.c | 42 ++++++++++++++++++++++++---------- net/sched/sch_cbq.c | 5 ++++ net/sched/sch_drr.c | 2 ++ net/sched/sch_dsmark.c | 2 ++ net/sched/sch_generic.c | 2 +- net/sched/sch_hfsc.c | 4 ++++ net/sched/sch_htb.c | 2 ++ net/sched/sch_mq.c | 2 +- net/sched/sch_mqprio.c | 2 +- net/sched/sch_multiq.c | 2 ++ net/sched/sch_prio.c | 5 +++- net/sched/sch_qfq.c | 2 ++ net/sched/sch_red.c | 2 ++ net/sched/sch_sfb.c | 2 ++ net/sched/sch_tbf.c | 2 ++ 18 files changed, 65 insertions(+), 17 deletions(-) diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f1b76b8e6d2d..bec46f63f10c 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -92,7 +92,7 @@ int unregister_qdisc(struct Qdisc_ops *qops); void qdisc_get_default(char *id, size_t len); int qdisc_set_default(const char *id); -void qdisc_hash_add(struct Qdisc *q); +void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index aeec4086afb2..65d502610314 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -66,6 +66,7 @@ struct Qdisc { #define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : * qdisc_tree_decrease_qlen() should stop. */ +#define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 6546917d605a..75fcf5eff093 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -545,6 +545,7 @@ enum { TCA_STATS2, TCA_STAB, TCA_PAD, + TCA_DUMP_INVISIBLE, __TCA_MAX }; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bcf49cd22786..62567bfe52c7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -274,7 +274,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) return NULL; } -void qdisc_hash_add(struct Qdisc *q) +void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { struct Qdisc *root = qdisc_dev(q)->qdisc; @@ -282,6 +282,8 @@ void qdisc_hash_add(struct Qdisc *q) WARN_ON_ONCE(root == &noop_qdisc); ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); + if (invisible) + q->flags |= TCQ_F_INVISIBLE; } } EXPORT_SYMBOL(qdisc_hash_add); @@ -1003,7 +1005,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, goto err_out4; } - qdisc_hash_add(sch); + qdisc_hash_add(sch, false); return sch; } @@ -1401,9 +1403,14 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, return -1; } -static bool tc_qdisc_dump_ignore(struct Qdisc *q) +static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) { - return (q->flags & TCQ_F_BUILTIN) ? true : false; + if (q->flags & TCQ_F_BUILTIN) + return true; + if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) + return true; + + return false; } static int qdisc_notify(struct net *net, struct sk_buff *oskb, @@ -1417,12 +1424,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (old && !tc_qdisc_dump_ignore(old)) { + if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) goto err_out; } - if (new && !tc_qdisc_dump_ignore(new)) { + if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; @@ -1439,7 +1446,8 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, struct netlink_callback *cb, - int *q_idx_p, int s_q_idx, bool recur) + int *q_idx_p, int s_q_idx, bool recur, + bool dump_invisible) { int ret = 0, q_idx = *q_idx_p; struct Qdisc *q; @@ -1452,7 +1460,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (q_idx < s_q_idx) { q_idx++; } else { - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) @@ -1474,7 +1482,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, q_idx++; continue; } - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) @@ -1496,12 +1504,21 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int idx, q_idx; int s_idx, s_q_idx; struct net_device *dev; + const struct nlmsghdr *nlh = cb->nlh; + struct tcmsg *tcm = nlmsg_data(nlh); + struct nlattr *tca[TCA_MAX + 1]; + int err; s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; idx = 0; ASSERT_RTNL(); + + err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL); + if (err < 0) + return err; + for_each_netdev(net, dev) { struct netdev_queue *dev_queue; @@ -1512,13 +1529,14 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) q_idx = 0; if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, - true) < 0) + true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx, false) < 0) + &q_idx, s_q_idx, false, + tca[TCA_DUMP_INVISIBLE]) < 0) goto done; cont: @@ -1762,7 +1780,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, { struct qdisc_dump_args arg; - if (tc_qdisc_dump_ignore(q) || + if (tc_qdisc_dump_ignore(q, false) || *t_p < s_t || !q->ops->cl_ops || (tcm->tcm_parent && TC_H_MAJ(tcm->tcm_parent) != q->handle)) { diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index d6ca18dc04c3..cf93e5ff3d63 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1161,6 +1161,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) sch->handle); if (!q->link.q) q->link.q = &noop_qdisc; + else + qdisc_hash_add(q->link.q, true); q->link.priority = TC_CBQ_MAXPRIO - 1; q->link.priority2 = TC_CBQ_MAXPRIO - 1; @@ -1600,6 +1602,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!cl->q) cl->q = &noop_qdisc; + else + qdisc_hash_add(cl->q, true); + cl->common.classid = classid; cl->tparent = parent; cl->qdisc = sch; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index bb4cbdf75004..9fe67e257dfa 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -117,6 +117,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; + else + qdisc_hash_add(cl->qdisc, true); if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 802ac7c2e5e8..1b98cb2160ff 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -368,6 +368,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (p->q == NULL) p->q = &noop_qdisc; + else + qdisc_hash_add(p->q, true); pr_debug("%s: qdisc %p\n", __func__, p->q); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b052b27a984e..3e64d23e098c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -795,7 +795,7 @@ static void attach_default_qdiscs(struct net_device *dev) } #ifdef CONFIG_NET_SCHED if (dev->qdisc) - qdisc_hash_add(dev->qdisc); + qdisc_hash_add(dev->qdisc, false); #endif } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3ffaa6fb0990..0198c6cdda49 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1066,6 +1066,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; + else + qdisc_hash_add(cl->qdisc, true); INIT_LIST_HEAD(&cl->children); cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; @@ -1425,6 +1427,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) sch->handle); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; + else + qdisc_hash_add(q->root.qdisc, true); INIT_LIST_HEAD(&q->root.children); q->root.vt_tree = RB_ROOT; q->root.cf_tree = RB_ROOT; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 4cd5fb134bc9..95867033542e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1460,6 +1460,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; + if (cl->un.leaf.q != &noop_qdisc) + qdisc_hash_add(cl->un.leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 20b7f1646f69..cadfdd4f1e52 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -84,7 +84,7 @@ static void mq_attach(struct Qdisc *sch) qdisc_destroy(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc); + qdisc_hash_add(qdisc, false); #endif } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 922683418e53..b851e209da4d 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -175,7 +175,7 @@ static void mqprio_attach(struct Qdisc *sch) if (old) qdisc_destroy(old); if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc); + qdisc_hash_add(qdisc, false); } kfree(priv->qdiscs); priv->qdiscs = NULL; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e7839a0d0eaa..43a3a10b3c81 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -217,6 +217,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) sch_tree_lock(sch); old = q->queues[i]; q->queues[i] = child; + if (child != &noop_qdisc) + qdisc_hash_add(child, true); if (old != &noop_qdisc) { qdisc_tree_reduce_backlog(old, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index d4d7db267b6e..92c2e6d448d7 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -192,8 +192,11 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) qdisc_destroy(child); } - for (i = oldbands; i < q->bands; i++) + for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; + if (q->queues[i] != &noop_qdisc) + qdisc_hash_add(q->queues[i], true); + } sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f9e712ce2d15..6c85f3e9239b 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -494,6 +494,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, goto destroy_class; } + if (cl->qdisc != &noop_qdisc) + qdisc_hash_add(cl->qdisc, true); sch_tree_lock(sch); qdisc_class_hash_insert(&q->clhash, &cl->common); sch_tree_unlock(sch); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 249b2a18acbd..799ea6dd69b2 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -191,6 +191,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return PTR_ERR(child); } + if (child != &noop_qdisc) + qdisc_hash_add(child, true); sch_tree_lock(sch); q->flags = ctl->flags; q->limit = ctl->limit; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index fe6963d21519..ae862f172c94 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -513,6 +513,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) if (IS_ERR(child)) return PTR_ERR(child); + if (child != &noop_qdisc) + qdisc_hash_add(child, true); sch_tree_lock(sch); qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 303355c449ab..40c29a801391 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -396,6 +396,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; + if (child != &noop_qdisc); + qdisc_hash_add(child, true); } q->limit = qopt->limit; if (tb[TCA_TBF_PBURST]) From 5425077d73e0c8e7e9267ca8397cc0e2293c1fb9 Mon Sep 17 00:00:00 2001 From: "subashab@codeaurora.org" Date: Wed, 8 Mar 2017 16:36:49 -0700 Subject: [PATCH 143/399] net: ipv6: Add early demux handler for UDP unicast While running a single stream UDPv6 test, we observed that amount of CPU spent in NET_RX softirq was much greater than UDPv4 for an equivalent receive rate. The test here was run on an ARM64 based Android system. On further analysis with perf, we found that UDPv6 was spending significant time in the statistics netfilter targets which did socket lookup per packet. These statistics rules perform a lookup when there is no socket associated with the skb. Since there are multiple instances of these rules based on UID, there will be equal number of lookups per skb. By introducing early demux for UDPv6, we avoid the redundant lookups. This also helped to improve the performance (800Mbps -> 870Mbps) on a CPU limited system in a single stream UDPv6 receive test with 1450 byte sized datagrams using iperf. v1->v2: Use IPv6 cookie to validate dst instead of 0 as suggested by Eric Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- net/ipv6/udp.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4e4c401e3bc6..08a188ffe070 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -864,6 +864,64 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, return 0; } +static struct sock *__udp6_lib_demux_lookup(struct net *net, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, + int dif) +{ + struct sock *sk; + + rcu_read_lock(); + sk = __udp6_lib_lookup(net, rmt_addr, rmt_port, loc_addr, loc_port, + dif, &udp_table, NULL); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + rcu_read_unlock(); + + return sk; +} + +static void udp_v6_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + const struct udphdr *uh; + struct sock *sk; + struct dst_entry *dst; + int dif = skb->dev->ifindex; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct udphdr))) + return; + + uh = udp_hdr(skb); + + if (skb->pkt_type == PACKET_HOST) + sk = __udp6_lib_demux_lookup(net, uh->dest, + &ipv6_hdr(skb)->daddr, + uh->source, &ipv6_hdr(skb)->saddr, + dif); + else + return; + + if (!sk) + return; + + skb->sk = sk; + skb->destructor = sock_efree; + dst = READ_ONCE(sk->sk_rx_dst); + + if (dst) + dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); + if (dst) { + if (dst->flags & DST_NOCACHE) { + if (likely(atomic_inc_not_zero(&dst->__refcnt))) + skb_dst_set(skb, dst); + } else { + skb_dst_set_noref(skb, dst); + } + } +} + static __inline__ int udpv6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); @@ -1379,6 +1437,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, #endif static const struct inet6_protocol udpv6_protocol = { + .early_demux = udp_v6_early_demux, .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, From 0d6dd35784e76bc3e052ffa13c6839d5c9bcb449 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 9 Mar 2017 15:04:14 -0800 Subject: [PATCH 144/399] netvsc: need napi scheduled during removal Since rndis_halt_device waits until all outstanding sends and receives are completed. Netvsc device needs to still schedule NAPI to see those completions. Fixes: 2506b1dc4bbe ("netvsc: implement NAPI") Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index b1328cef9d5a..0e0c757c1681 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -91,15 +91,6 @@ static void free_netvsc_device(struct netvsc_device *nvdev) } -static inline bool netvsc_channel_idle(const struct netvsc_device *net_device, - u16 q_idx) -{ - const struct netvsc_channel *nvchan = &net_device->chan_table[q_idx]; - - return atomic_read(&net_device->num_outstanding_recvs) == 0 && - atomic_read(&nvchan->queue_sends) == 0; -} - static struct netvsc_device *get_outbound_net_device(struct hv_device *device) { struct netvsc_device *net_device = hv_device_to_netvsc_device(device); @@ -1273,13 +1264,10 @@ void netvsc_channel_cb(void *context) if (unlikely(!ndev)) return; - net_device = net_device_to_netvsc_device(ndev); - if (unlikely(net_device->destroy) && - netvsc_channel_idle(net_device, q_idx)) - return; - /* disable interupts from host */ hv_begin_read(&channel->inbound); + + net_device = net_device_to_netvsc_device(ndev); napi_schedule(&net_device->chan_table[q_idx].napi); } From 79cd874c96b38694fb2b4ee3850f6fbbc3015439 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 9 Mar 2017 15:04:15 -0800 Subject: [PATCH 145/399] netvsc: fix hang on netvsc module removal The code in netvsc_device_remove was incorrectly calling napi_disable repeatedly on the same element. This would cause attempts to remove netvsc module to hang. Fixes: 2506b1dc4bbe ("netvsc: implement NAPI") Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 0e0c757c1681..8f9aeec2ce0f 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -562,8 +562,8 @@ void netvsc_device_remove(struct hv_device *device) /* Now, we can close the channel safely */ vmbus_close(device->channel); - for (i = 0; i < VRSS_CHANNEL_MAX; i++) - napi_disable(&net_device->chan_table[0].napi); + for (i = 0; i < net_device->num_chn; i++) + napi_disable(&net_device->chan_table[i].napi); /* Release all resources */ free_netvsc_device(net_device); From b3ca9af0fb65098dd2afecca6831c361a585f37f Mon Sep 17 00:00:00 2001 From: VSR Burru Date: Thu, 9 Mar 2017 17:03:24 -0800 Subject: [PATCH 146/399] liquidio: optimize DMA in NUMA systems Optimize DMA in NUMA systems by allocating memory from NUMA node that NIC is plugged in to; DMA will no longer cross NUMA nodes. If NIC IRQs are pinned to a local CPU, that CPU's access to the DMA'd data is also optimized. Signed-off-by: VSR Burru Signed-off-by: Felix Manlunas Signed-off-by: Raghu Vatsavayi Signed-off-by: Satanand Burla Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_main.c | 2 +- .../net/ethernet/cavium/liquidio/octeon_device.c | 4 ++-- drivers/net/ethernet/cavium/liquidio/octeon_droq.c | 10 ++-------- drivers/net/ethernet/cavium/liquidio/octeon_iq.h | 2 +- .../net/ethernet/cavium/liquidio/request_manager.c | 13 +++---------- 5 files changed, 9 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index dffed432d58e..acfd848d5344 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -782,7 +782,7 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs) } for (i = 0; i < num_iqs; i++) { - int numa_node = cpu_to_node(i % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); spin_lock_init(&lio->glist_lock[i]); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index 9675ffbf25e6..e21b477d0159 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -793,7 +793,7 @@ int octeon_setup_instr_queues(struct octeon_device *oct) u32 num_descs = 0; u32 iq_no = 0; union oct_txpciq txpciq; - int numa_node = cpu_to_node(iq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (OCTEON_CN6XXX(oct)) num_descs = @@ -837,7 +837,7 @@ int octeon_setup_output_queues(struct octeon_device *oct) u32 num_descs = 0; u32 desc_size = 0; u32 oq_no = 0; - int numa_node = cpu_to_node(oq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (OCTEON_CN6XXX(oct)) { num_descs = diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index 0be87d119a97..a91835da1acc 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -234,8 +234,7 @@ int octeon_init_droq(struct octeon_device *oct, struct octeon_droq *droq; u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0; u32 c_pkts_per_intr = 0, c_refill_threshold = 0; - int orig_node = dev_to_node(&oct->pci_dev->dev); - int numa_node = cpu_to_node(q_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no); @@ -275,13 +274,8 @@ int octeon_init_droq(struct octeon_device *oct, droq->buffer_size = c_buf_size; desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE; - set_dev_node(&oct->pci_dev->dev, numa_node); droq->desc_ring = lio_dma_alloc(oct, desc_ring_size, (dma_addr_t *)&droq->desc_ring_dma); - set_dev_node(&oct->pci_dev->dev, orig_node); - if (!droq->desc_ring) - droq->desc_ring = lio_dma_alloc(oct, desc_ring_size, - (dma_addr_t *)&droq->desc_ring_dma); if (!droq->desc_ring) { dev_err(&oct->pci_dev->dev, @@ -983,7 +977,7 @@ int octeon_create_droq(struct octeon_device *oct, u32 desc_size, void *app_ctx) { struct octeon_droq *droq; - int numa_node = cpu_to_node(q_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (oct->droq[q_no]) { dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n", diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h index 4608a5af35a3..5063a12613e5 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h @@ -152,7 +152,7 @@ struct octeon_instr_queue { struct oct_iq_stats stats; /** DMA mapped base address of the input descriptor ring. */ - u64 base_addr_dma; + dma_addr_t base_addr_dma; /** Application context */ void *app_ctx; diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index 707bc15adec6..261f448f9de2 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -62,8 +62,7 @@ int octeon_init_instr_queue(struct octeon_device *oct, u32 iq_no = (u32)txpciq.s.q_no; u32 q_size; struct cavium_wq *db_wq; - int orig_node = dev_to_node(&oct->pci_dev->dev); - int numa_node = cpu_to_node(iq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (OCTEON_CN6XXX(oct)) conf = &(CFG_GET_IQ_CFG(CHIP_CONF(oct, cn6xxx))); @@ -91,13 +90,7 @@ int octeon_init_instr_queue(struct octeon_device *oct, iq->oct_dev = oct; - set_dev_node(&oct->pci_dev->dev, numa_node); - iq->base_addr = lio_dma_alloc(oct, q_size, - (dma_addr_t *)&iq->base_addr_dma); - set_dev_node(&oct->pci_dev->dev, orig_node); - if (!iq->base_addr) - iq->base_addr = lio_dma_alloc(oct, q_size, - (dma_addr_t *)&iq->base_addr_dma); + iq->base_addr = lio_dma_alloc(oct, q_size, &iq->base_addr_dma); if (!iq->base_addr) { dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n", iq_no); @@ -211,7 +204,7 @@ int octeon_setup_iq(struct octeon_device *oct, void *app_ctx) { u32 iq_no = (u32)txpciq.s.q_no; - int numa_node = cpu_to_node(iq_no % num_online_cpus()); + int numa_node = dev_to_node(&oct->pci_dev->dev); if (oct->instr_queue[iq_no]) { dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n", From c95129d127c6d3d9fca189c6f94c539a7f086b1a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 10 Mar 2017 12:11:06 +0800 Subject: [PATCH 147/399] sctp: add support for generating assoc reset event notification This patch is to add Association Reset Event described in rfc6525 section 6.1.2. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/ulpevent.h | 4 ++++ include/uapi/linux/sctp.h | 15 +++++++++++++++ net/sctp/ulpevent.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+) diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 324b5965fc4d..2ab7ed44de52 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -132,6 +132,10 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( const struct sctp_association *asoc, __u16 flags, __u16 stream_num, __u16 *stream_list, gfp_t gfp); +struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( + const struct sctp_association *asoc, __u16 flags, + __u32 local_tsn, __u32 remote_tsn, gfp_t gfp); + void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *); void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index d3ae381fcf33..77358297c2f9 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -502,6 +502,17 @@ struct sctp_stream_reset_event { __u16 strreset_stream_list[]; }; +#define SCTP_ASSOC_RESET_DENIED 0x0004 +#define SCTP_ASSOC_RESET_FAILED 0x0008 +struct sctp_assoc_reset_event { + __u16 assocreset_type; + __u16 assocreset_flags; + __u32 assocreset_length; + sctp_assoc_t assocreset_assoc_id; + __u32 assocreset_local_tsn; + __u32 assocreset_remote_tsn; +}; + /* * Described in Section 7.3 * Ancillary Data and Notification Interest Options @@ -518,6 +529,7 @@ struct sctp_event_subscribe { __u8 sctp_authentication_event; __u8 sctp_sender_dry_event; __u8 sctp_stream_reset_event; + __u8 sctp_assoc_reset_event; }; /* @@ -543,6 +555,7 @@ union sctp_notification { struct sctp_authkey_event sn_authkey_event; struct sctp_sender_dry_event sn_sender_dry_event; struct sctp_stream_reset_event sn_strreset_event; + struct sctp_assoc_reset_event sn_assocreset_event; }; /* Section 5.3.1 @@ -572,6 +585,8 @@ enum sctp_sn_type { #define SCTP_SENDER_DRY_EVENT SCTP_SENDER_DRY_EVENT SCTP_STREAM_RESET_EVENT, #define SCTP_STREAM_RESET_EVENT SCTP_STREAM_RESET_EVENT + SCTP_ASSOC_RESET_EVENT, +#define SCTP_ASSOC_RESET_EVENT SCTP_ASSOC_RESET_EVENT }; /* Notification error codes used to fill up the error fields in some diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index c8881bc542a0..420d7f35256a 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -883,6 +883,34 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( return event; } +struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( + const struct sctp_association *asoc, __u16 flags, __u32 local_tsn, + __u32 remote_tsn, gfp_t gfp) +{ + struct sctp_assoc_reset_event *areset; + struct sctp_ulpevent *event; + struct sk_buff *skb; + + event = sctp_ulpevent_new(sizeof(struct sctp_assoc_reset_event), + MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + areset = (struct sctp_assoc_reset_event *) + skb_put(skb, sizeof(struct sctp_assoc_reset_event)); + + areset->assocreset_type = SCTP_ASSOC_RESET_EVENT; + areset->assocreset_flags = flags; + areset->assocreset_length = sizeof(struct sctp_assoc_reset_event); + sctp_ulpevent_set_owner(event, asoc); + areset->assocreset_assoc_id = sctp_assoc2id(asoc); + areset->assocreset_local_tsn = local_tsn; + areset->assocreset_remote_tsn = remote_tsn; + + return event; +} + /* Return the notification type, assuming this is a notification * event. */ From 692787cef6515188f25a5b6cdf008cfe10acf89f Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 10 Mar 2017 12:11:07 +0800 Subject: [PATCH 148/399] sctp: implement receiver-side procedures for the SSN/TSN Reset Request Parameter This patch is to implement Receiver-Side Procedures for the SSN/TSN Reset Request Parameter described in rfc6525 section 6.2.4. The process is kind of complicate, it's wonth having some comments from section 6.2.4 in the codes. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sm.h | 4 +++ net/sctp/sm_statefuns.c | 3 ++ net/sctp/stream.c | 79 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 86 insertions(+) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index b6f682ec184a..2629d6670a27 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -293,6 +293,10 @@ struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_tsnreq( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); /* Prototypes for statetable processing. */ diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index e03bb1aab4d0..6982064957a7 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3872,6 +3872,9 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net, else if (param.p->type == SCTP_PARAM_RESET_IN_REQUEST) reply = sctp_process_strreset_inreq( (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST) + reply = sctp_process_strreset_tsnreq( + (struct sctp_association *)asoc, param, &ev); /* More handles for other types will be added here, by now it * just ignores other types. */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 1c6cc04fa3a4..7e993b0c1412 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -477,3 +477,82 @@ struct sctp_chunk *sctp_process_strreset_inreq( return chunk; } + +struct sctp_chunk *sctp_process_strreset_tsnreq( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + __u32 init_tsn = 0, next_tsn = 0, max_tsn_seen; + struct sctp_strreset_tsnreq *tsnreq = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + __u32 request_seq; + __u16 i; + + request_seq = ntohl(tsnreq->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ)) + goto out; + + if (asoc->strreset_outstanding) { + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + /* G3: The same processing as though a SACK chunk with no gap report + * and a cumulative TSN ACK of the Sender's Next TSN minus 1 were + * received MUST be performed. + */ + max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map); + sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen); + sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + + /* G1: Compute an appropriate value for the Receiver's Next TSN -- the + * TSN that the peer should use to send the next DATA chunk. The + * value SHOULD be the smallest TSN not acknowledged by the + * receiver of the request plus 2^31. + */ + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, + init_tsn, GFP_ATOMIC); + + /* G4: The same processing as though a FWD-TSN chunk (as defined in + * [RFC3758]) with all streams affected and a new cumulative TSN + * ACK of the Receiver's Next TSN minus 1 were received MUST be + * performed. + */ + sctp_outq_free(&asoc->outqueue); + + /* G2: Compute an appropriate value for the local endpoint's next TSN, + * i.e., the next TSN assigned by the receiver of the SSN/TSN reset + * chunk. The value SHOULD be the highest TSN sent by the receiver + * of the request plus 1. + */ + next_tsn = asoc->next_tsn; + asoc->ctsn_ack_point = next_tsn - 1; + asoc->adv_peer_ack_point = asoc->ctsn_ack_point; + + /* G5: The next expected and outgoing SSNs MUST be reset to 0 for all + * incoming and outgoing streams. + */ + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + for (i = 0; i < stream->incnt; i++) + stream->in[i].ssn = 0; + + result = SCTP_STRRESET_PERFORMED; + + *evp = sctp_ulpevent_make_assoc_reset_event(asoc, 0, init_tsn, + next_tsn, GFP_ATOMIC); + +out: + return sctp_make_strreset_tsnresp(asoc, result, request_seq, + next_tsn, init_tsn); +} From b444153fb5a647448c2080ad28656ad183cae4fc Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 10 Mar 2017 12:11:08 +0800 Subject: [PATCH 149/399] sctp: add support for generating add stream change event notification This patch is to add Stream Change Event described in rfc6525 section 6.1.3. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/ulpevent.h | 4 ++++ include/uapi/linux/sctp.h | 15 +++++++++++++++ net/sctp/ulpevent.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+) diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 2ab7ed44de52..1060494ac230 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -136,6 +136,10 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( const struct sctp_association *asoc, __u16 flags, __u32 local_tsn, __u32 remote_tsn, gfp_t gfp); +struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( + const struct sctp_association *asoc, __u16 flags, + __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp); + void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *); void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 77358297c2f9..fd652e6501b4 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -513,6 +513,17 @@ struct sctp_assoc_reset_event { __u32 assocreset_remote_tsn; }; +#define SCTP_ASSOC_CHANGE_DENIED 0x0004 +#define SCTP_ASSOC_CHANGE_FAILED 0x0008 +struct sctp_stream_change_event { + __u16 strchange_type; + __u16 strchange_flags; + __u32 strchange_length; + sctp_assoc_t strchange_assoc_id; + __u16 strchange_instrms; + __u16 strchange_outstrms; +}; + /* * Described in Section 7.3 * Ancillary Data and Notification Interest Options @@ -530,6 +541,7 @@ struct sctp_event_subscribe { __u8 sctp_sender_dry_event; __u8 sctp_stream_reset_event; __u8 sctp_assoc_reset_event; + __u8 sctp_stream_change_event; }; /* @@ -556,6 +568,7 @@ union sctp_notification { struct sctp_sender_dry_event sn_sender_dry_event; struct sctp_stream_reset_event sn_strreset_event; struct sctp_assoc_reset_event sn_assocreset_event; + struct sctp_stream_change_event sn_strchange_event; }; /* Section 5.3.1 @@ -587,6 +600,8 @@ enum sctp_sn_type { #define SCTP_STREAM_RESET_EVENT SCTP_STREAM_RESET_EVENT SCTP_ASSOC_RESET_EVENT, #define SCTP_ASSOC_RESET_EVENT SCTP_ASSOC_RESET_EVENT + SCTP_STREAM_CHANGE_EVENT, +#define SCTP_STREAM_CHANGE_EVENT SCTP_STREAM_CHANGE_EVENT }; /* Notification error codes used to fill up the error fields in some diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 420d7f35256a..ec2b3e013c2f 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -911,6 +911,34 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( return event; } +struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( + const struct sctp_association *asoc, __u16 flags, + __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp) +{ + struct sctp_stream_change_event *schange; + struct sctp_ulpevent *event; + struct sk_buff *skb; + + event = sctp_ulpevent_new(sizeof(struct sctp_stream_change_event), + MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + schange = (struct sctp_stream_change_event *) + skb_put(skb, sizeof(struct sctp_stream_change_event)); + + schange->strchange_type = SCTP_STREAM_CHANGE_EVENT; + schange->strchange_flags = flags; + schange->strchange_length = sizeof(struct sctp_stream_change_event); + sctp_ulpevent_set_owner(event, asoc); + schange->strchange_assoc_id = sctp_assoc2id(asoc); + schange->strchange_instrms = strchange_instrms; + schange->strchange_outstrms = strchange_outstrms; + + return event; +} + /* Return the notification type, assuming this is a notification * event. */ From 50a41591f11022dcf76c23238dce1a1a62470c46 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 10 Mar 2017 12:11:09 +0800 Subject: [PATCH 150/399] sctp: implement receiver-side procedures for the Add Outgoing Streams Request Parameter This patch is to add Receiver-Side Procedures for the Add Outgoing Streams Request Parameter described in section 5.2.5. It is also to improve sctp_chunk_lookup_strreset_param, so that it can be used for processing addstrm_out request. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sm.h | 4 ++ net/sctp/sm_statefuns.c | 3 ++ net/sctp/stream.c | 89 ++++++++++++++++++++++++++++++++++++----- 3 files changed, 86 insertions(+), 10 deletions(-) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 2629d6670a27..93ae50bbfa99 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -297,6 +297,10 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_addstrm_out( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); /* Prototypes for statetable processing. */ diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 6982064957a7..881122b8c370 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3875,6 +3875,9 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net, else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST) reply = sctp_process_strreset_tsnreq( (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) + reply = sctp_process_strreset_addstrm_out( + (struct sctp_association *)asoc, param, &ev); /* More handles for other types will be added here, by now it * just ignores other types. */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 7e993b0c1412..df2794db05d3 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -303,13 +303,14 @@ int sctp_send_add_streams(struct sctp_association *asoc, } static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( - struct sctp_association *asoc, __u32 resp_seq) + struct sctp_association *asoc, __u32 resp_seq, + __be16 type) { struct sctp_chunk *chunk = asoc->strreset_chunk; struct sctp_reconf_chunk *hdr; union sctp_params param; - if (ntohl(resp_seq) != asoc->strreset_outseq || !chunk) + if (!chunk) return NULL; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; @@ -320,7 +321,8 @@ static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( */ struct sctp_strreset_tsnreq *req = param.v; - if (req->request_seq == resp_seq) + if ((!resp_seq || req->request_seq == resp_seq) && + (!type || type == req->param_hdr.type)) return param.v; } @@ -361,13 +363,9 @@ struct sctp_chunk *sctp_process_strreset_outreq( goto out; if (asoc->strreset_chunk) { - sctp_paramhdr_t *param_hdr; - struct sctp_transport *t; - - param_hdr = sctp_chunk_lookup_strreset_param( - asoc, outreq->response_seq); - if (!param_hdr || param_hdr->type != - SCTP_PARAM_RESET_IN_REQUEST) { + if (!sctp_chunk_lookup_strreset_param( + asoc, outreq->response_seq, + SCTP_PARAM_RESET_IN_REQUEST)) { /* same process with outstanding isn't 0 */ result = SCTP_STRRESET_ERR_IN_PROGRESS; goto out; @@ -377,6 +375,8 @@ struct sctp_chunk *sctp_process_strreset_outreq( asoc->strreset_outseq++; if (!asoc->strreset_outstanding) { + struct sctp_transport *t; + t = asoc->strreset_chunk->transport; if (del_timer(&t->reconf_timer)) sctp_transport_put(t); @@ -556,3 +556,72 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( return sctp_make_strreset_tsnresp(asoc, result, request_seq, next_tsn, init_tsn); } + +struct sctp_chunk *sctp_process_strreset_addstrm_out( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_addstrm *addstrm = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + struct sctp_stream_in *streamin; + __u32 request_seq, incnt; + __u16 in; + + request_seq = ntohl(addstrm->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) + goto out; + + if (asoc->strreset_chunk) { + if (!sctp_chunk_lookup_strreset_param( + asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) { + /* same process with outstanding isn't 0 */ + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + asoc->strreset_outstanding--; + asoc->strreset_outseq++; + + if (!asoc->strreset_outstanding) { + struct sctp_transport *t; + + t = asoc->strreset_chunk->transport; + if (del_timer(&t->reconf_timer)) + sctp_transport_put(t); + + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + } + } + + in = ntohs(addstrm->number_of_streams); + incnt = stream->incnt + in; + if (!in || incnt > SCTP_MAX_STREAM) + goto out; + + streamin = krealloc(stream->in, incnt * sizeof(*streamin), + GFP_ATOMIC); + if (!streamin) + goto out; + + memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); + stream->in = streamin; + stream->incnt = incnt; + + result = SCTP_STRRESET_PERFORMED; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, + 0, ntohs(addstrm->number_of_streams), 0, GFP_ATOMIC); + +out: + return sctp_make_strreset_resp(asoc, result, request_seq); +} From c5c4ebb3ab87fd87e44a47ec8289238e6f6084c1 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 10 Mar 2017 12:11:10 +0800 Subject: [PATCH 151/399] sctp: implement receiver-side procedures for the Add Incoming Streams Request Parameter This patch is to implement Receiver-Side Procedures for the Add Incoming Streams Request Parameter described in rfc6525 section 5.2.6. It is also to fix that it shouldn't have add streams when sending addstrm in request, as the process in peer will handle it by sending a addstrm out request back. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sm.h | 4 +++ net/sctp/sm_statefuns.c | 3 ++ net/sctp/stream.c | 74 ++++++++++++++++++++++++++++++++++------- 3 files changed, 69 insertions(+), 12 deletions(-) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 93ae50bbfa99..e0d982588642 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -301,6 +301,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_addstrm_in( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); /* Prototypes for statetable processing. */ diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 881122b8c370..a8687a78ed41 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3878,6 +3878,9 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net, else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) reply = sctp_process_strreset_addstrm_out( (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) + reply = sctp_process_strreset_addstrm_in( + (struct sctp_association *)asoc, param, &ev); /* More handles for other types will be added here, by now it * just ignores other types. */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index df2794db05d3..1c925db2e914 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -267,18 +267,6 @@ int sctp_send_add_streams(struct sctp_association *asoc, stream->out = streamout; } - if (in) { - struct sctp_stream_in *streamin; - - streamin = krealloc(stream->in, incnt * sizeof(*streamin), - GFP_KERNEL); - if (!streamin) - goto out; - - memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); - stream->in = streamin; - } - chunk = sctp_make_strreset_addstrm(asoc, out, in); if (!chunk) goto out; @@ -625,3 +613,65 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( out: return sctp_make_strreset_resp(asoc, result, request_seq); } + +struct sctp_chunk *sctp_process_strreset_addstrm_in( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_addstrm *addstrm = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + struct sctp_stream_out *streamout; + struct sctp_chunk *chunk = NULL; + __u32 request_seq, outcnt; + __u16 out; + + request_seq = ntohl(addstrm->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) + goto out; + + if (asoc->strreset_outstanding) { + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + out = ntohs(addstrm->number_of_streams); + outcnt = stream->outcnt + out; + if (!out || outcnt > SCTP_MAX_STREAM) + goto out; + + streamout = krealloc(stream->out, outcnt * sizeof(*streamout), + GFP_ATOMIC); + if (!streamout) + goto out; + + memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); + stream->out = streamout; + + chunk = sctp_make_strreset_addstrm(asoc, out, 0); + if (!chunk) + goto out; + + asoc->strreset_chunk = chunk; + asoc->strreset_outstanding = 1; + sctp_chunk_hold(asoc->strreset_chunk); + + stream->outcnt = outcnt; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, + 0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC); + +out: + if (!chunk) + chunk = sctp_make_strreset_resp(asoc, result, request_seq); + + return chunk; +} From 11ae76e67a179f25ae8f772d62a7ddf717b1cdf3 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 10 Mar 2017 12:11:11 +0800 Subject: [PATCH 152/399] sctp: implement receiver-side procedures for the Reconf Response Parameter This patch is to implement Receiver-Side Procedures for the Re-configuration Response Parameter in rfc6525 section 5.2.7. sctp_process_strreset_resp would process the response for any kind of reconf request, and the stream reconf is applied only when the response result is success. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sm.h | 4 ++ net/sctp/sm_statefuns.c | 6 +- net/sctp/stream.c | 154 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 161 insertions(+), 3 deletions(-) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index e0d982588642..47113f2c4b0a 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -305,6 +305,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); +struct sctp_chunk *sctp_process_strreset_resp( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp); /* Prototypes for statetable processing. */ diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index a8687a78ed41..ab1374fa5ab0 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3881,9 +3881,9 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net, else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) reply = sctp_process_strreset_addstrm_in( (struct sctp_association *)asoc, param, &ev); - /* More handles for other types will be added here, by now it - * just ignores other types. - */ + else if (param.p->type == SCTP_PARAM_RESET_RESPONSE) + reply = sctp_process_strreset_resp( + (struct sctp_association *)asoc, param, &ev); if (ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 1c925db2e914..961d0a1e99d1 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -675,3 +675,157 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( return chunk; } + +struct sctp_chunk *sctp_process_strreset_resp( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_resp *resp = param.v; + struct sctp_stream *stream = asoc->stream; + struct sctp_transport *t; + __u16 i, nums, flags = 0; + sctp_paramhdr_t *req; + __u32 result; + + req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0); + if (!req) + return NULL; + + result = ntohl(resp->result); + if (result != SCTP_STRRESET_PERFORMED) { + /* if in progress, do nothing but retransmit */ + if (result == SCTP_STRRESET_IN_PROGRESS) + return NULL; + else if (result == SCTP_STRRESET_DENIED) + flags = SCTP_STREAM_RESET_DENIED; + else + flags = SCTP_STREAM_RESET_FAILED; + } + + if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) { + struct sctp_strreset_outreq *outreq; + __u16 *str_p = NULL; + + outreq = (struct sctp_strreset_outreq *)req; + nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) / 2; + + if (result == SCTP_STRRESET_PERFORMED) { + if (nums) { + str_p = outreq->list_of_streams; + for (i = 0; i < nums; i++) + stream->out[ntohs(str_p[i])].ssn = 0; + } else { + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + } + + flags = SCTP_STREAM_RESET_OUTGOING_SSN; + } + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, + nums, str_p, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) { + struct sctp_strreset_inreq *inreq; + __u16 *str_p = NULL; + + /* if the result is performed, it's impossible for inreq */ + if (result == SCTP_STRRESET_PERFORMED) + return NULL; + + inreq = (struct sctp_strreset_inreq *)req; + nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / 2; + + str_p = inreq->list_of_streams; + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, + nums, str_p, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) { + struct sctp_strreset_resptsn *resptsn; + __u32 stsn, rtsn; + + /* check for resptsn, as sctp_verify_reconf didn't do it*/ + if (ntohs(param.p->length) != sizeof(*resptsn)) + return NULL; + + resptsn = (struct sctp_strreset_resptsn *)resp; + stsn = ntohl(resptsn->senders_next_tsn); + rtsn = ntohl(resptsn->receivers_next_tsn); + + if (result == SCTP_STRRESET_PERFORMED) { + __u32 mtsn = sctp_tsnmap_get_max_tsn_seen( + &asoc->peer.tsn_map); + + sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn); + sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + + sctp_tsnmap_init(&asoc->peer.tsn_map, + SCTP_TSN_MAP_INITIAL, + stsn, GFP_ATOMIC); + + sctp_outq_free(&asoc->outqueue); + + asoc->next_tsn = rtsn; + asoc->ctsn_ack_point = asoc->next_tsn - 1; + asoc->adv_peer_ack_point = asoc->ctsn_ack_point; + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + for (i = 0; i < stream->incnt; i++) + stream->in[i].ssn = 0; + } + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + + *evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags, + stsn, rtsn, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) { + struct sctp_strreset_addstrm *addstrm; + __u16 number; + + addstrm = (struct sctp_strreset_addstrm *)req; + nums = ntohs(addstrm->number_of_streams); + number = stream->outcnt - nums; + + if (result == SCTP_STRRESET_PERFORMED) + for (i = number; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + else + stream->outcnt = number; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, + 0, nums, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) { + struct sctp_strreset_addstrm *addstrm; + + /* if the result is performed, it's impossible for addstrm in + * request. + */ + if (result == SCTP_STRRESET_PERFORMED) + return NULL; + + addstrm = (struct sctp_strreset_addstrm *)req; + nums = ntohs(addstrm->number_of_streams); + + *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, + nums, 0, GFP_ATOMIC); + } + + asoc->strreset_outstanding--; + asoc->strreset_outseq++; + + /* remove everything for this reconf request */ + if (!asoc->strreset_outstanding) { + t = asoc->strreset_chunk->transport; + if (del_timer(&t->reconf_timer)) + sctp_transport_put(t); + + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + } + + return NULL; +} From c0d8bab6ae518cedfb5246e99ece43fe51d79b56 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 10 Mar 2017 12:11:12 +0800 Subject: [PATCH 153/399] sctp: add get and set sockopt for reconf_enable This patchset is to add SCTP_RECONFIG_SUPPORTED sockopt, it would set and get asoc reconf_enable value when asoc_id is set, or it would set and get ep reconf_enalbe value if asoc_id is 0. It is also to add sysctl interface for users to set the default value for reconf_enable. After this patch, stream reconf will work. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 1 + net/sctp/socket.c | 81 +++++++++++++++++++++++++++++++++++++++ net/sctp/sysctl.c | 7 ++++ 3 files changed, 89 insertions(+) diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index fd652e6501b4..7212870ef5d7 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -115,6 +115,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_PR_SUPPORTED 113 #define SCTP_DEFAULT_PRINFO 114 #define SCTP_PR_ASSOC_STATUS 115 +#define SCTP_RECONFIG_SUPPORTED 117 #define SCTP_ENABLE_STREAM_RESET 118 #define SCTP_RESET_STREAMS 119 #define SCTP_RESET_ASSOC 120 diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6f0a9be50f50..24e28cfb542b 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3758,6 +3758,39 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk, return retval; } +static int sctp_setsockopt_reconfig_supported(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen != sizeof(params)) + goto out; + + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + asoc->reconf_enable = !!params.assoc_value; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + sp->ep->reconf_enable = !!params.assoc_value; + } else { + goto out; + } + + retval = 0; + +out: + return retval; +} + static int sctp_setsockopt_enable_strreset(struct sock *sk, char __user *optval, unsigned int optlen) @@ -4038,6 +4071,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_DEFAULT_PRINFO: retval = sctp_setsockopt_default_prinfo(sk, optval, optlen); break; + case SCTP_RECONFIG_SUPPORTED: + retval = sctp_setsockopt_reconfig_supported(sk, optval, optlen); + break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_setsockopt_enable_strreset(sk, optval, optlen); break; @@ -6540,6 +6576,47 @@ static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len, return retval; } +static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + params.assoc_value = asoc->reconf_enable; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + params.assoc_value = sp->ep->reconf_enable; + } else { + retval = -EINVAL; + goto out; + } + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -6748,6 +6825,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_pr_assocstatus(sk, len, optval, optlen); break; + case SCTP_RECONFIG_SUPPORTED: + retval = sctp_getsockopt_reconfig_supported(sk, len, optval, + optlen); + break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index daf8554fd42a..0e732f68c2bf 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -274,6 +274,13 @@ static struct ctl_table sctp_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "reconf_enable", + .data = &init_net.sctp.reconf_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "auth_enable", .data = &init_net.sctp.auth_enable, From 8b57fd1ec13e22b3e722891ff7a6e6ccaf286779 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Fri, 10 Mar 2017 12:38:47 +0800 Subject: [PATCH 154/399] net: Eliminate duplicated codes by creating one new function in_dev_select_addr There are two duplicated loops codes which used to select right address in current codes. Now eliminate these codes by creating one new function in_dev_select_addr. Signed-off-by: Gao Feng Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cebedd545e5e..927f1d4b8c80 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1192,6 +1192,18 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len) return done; } +static __be32 in_dev_select_addr(const struct in_device *in_dev, + int scope) +{ + for_primary_ifa(in_dev) { + if (ifa->ifa_scope != RT_SCOPE_LINK && + ifa->ifa_scope <= scope) + return ifa->ifa_local; + } endfor_ifa(in_dev); + + return 0; +} + __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { __be32 addr = 0; @@ -1228,13 +1240,9 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { - for_primary_ifa(in_dev) { - if (ifa->ifa_scope != RT_SCOPE_LINK && - ifa->ifa_scope <= scope) { - addr = ifa->ifa_local; - goto out_unlock; - } - } endfor_ifa(in_dev); + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; } /* Not loopback addresses on loopback should be preferred @@ -1249,13 +1257,9 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) if (!in_dev) continue; - for_primary_ifa(in_dev) { - if (ifa->ifa_scope != RT_SCOPE_LINK && - ifa->ifa_scope <= scope) { - addr = ifa->ifa_local; - goto out_unlock; - } - } endfor_ifa(in_dev); + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; } out_unlock: rcu_read_unlock(); From 8f48ba71ede12231d5d63fdd34bd8ce7908a3377 Mon Sep 17 00:00:00 2001 From: Vincent Bernat Date: Fri, 10 Mar 2017 16:30:24 +0100 Subject: [PATCH 155/399] vxlan: use appropriate family on L3 miss When sending a L3 miss, the family is set to AF_INET even for IPv6. This causes userland (eg "ip monitor") to be confused. Ensure we send the appropriate family in this case. For L2 miss, keep using AF_INET. Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e375560cc74e..168257aa8ace 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -276,9 +276,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, send_eth = send_ip = true; if (type == RTM_GETNEIGH) { - ndm->ndm_family = AF_INET; send_ip = !vxlan_addr_any(&rdst->remote_ip); send_eth = !is_zero_ether_addr(fdb->eth_addr); + ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; From 9fbb9dd8eee459e810560a7d459103d865c48beb Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:34:53 +0100 Subject: [PATCH 156/399] net: stmmac: Rename clk_ptp_ref clock to ptp_ref There aren't currently any users of the "clk_ptp_ref", but there are other references to "ptp_ref", so I'm leaning towards considering that a typo. Fix it. Cc: Mark Rutland Cc: Rob Herring Cc: devicetree@vger.kernel.org Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/stmmac.txt | 6 +++--- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index d3bfc2b30fb5..11b27dfd1627 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -28,9 +28,9 @@ Optional properties: clocks may be specified in derived bindings. - clock-names: One name for each entry in the clocks property, the first one should be "stmmaceth" and the second one should be "pclk". -- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is - available this clock is used for programming the Timestamp Addend Register. - If not passed then the system clock will be used and this is fine on some +- ptp_ref: this is the PTP reference clock; in case of the PTP is available + this clock is used for programming the Timestamp Addend Register. If not + passed then the system clock will be used and this is fine on some platforms. - tx-fifo-depth: See ethernet.txt file in the same directory - rx-fifo-depth: See ethernet.txt file in the same directory diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 0ba1caf18619..f2d94eafeb0a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -359,7 +359,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) clk_prepare_enable(plat->pclk); /* Fall-back to main clock in case of no PTP ref is passed */ - plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "clk_ptp_ref"); + plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "ptp_ref"); if (IS_ERR(plat->clk_ptp_ref)) { plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk); plat->clk_ptp_ref = NULL; From 6c1e5abe0780cecafdc24b64aefc84ce6924dda9 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:34:54 +0100 Subject: [PATCH 157/399] net: stmmac: Stop PHY and remove TX timer on error If an error occurs while opening the device, make sure that both the TX timer and the PHY are properly cleaned up. Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4498a3861aa3..7c38c9baf238 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1821,7 +1821,7 @@ static int stmmac_open(struct net_device *dev) netdev_err(priv->dev, "%s: ERROR: allocating the IRQ %d (error: %d)\n", __func__, dev->irq, ret); - goto init_error; + goto irq_error; } /* Request the Wake IRQ in case of another line is used for WoL */ @@ -1858,7 +1858,11 @@ static int stmmac_open(struct net_device *dev) free_irq(priv->wol_irq, dev); wolirq_error: free_irq(dev->irq, dev); +irq_error: + if (dev->phydev) + phy_stop(dev->phydev); + del_timer_sync(&priv->txtimer); init_error: free_dma_desc_resources(priv); dma_desc_error: From c66f6c3775bed342693feec2925276fd13bb1355 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:34:55 +0100 Subject: [PATCH 158/399] net: stmmac: Disable PTP reference clock on error If an error occurs while opening the device, make sure to disable the PTP reference clock. Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7c38c9baf238..6060410d2b9e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1754,6 +1754,13 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) return 0; } +static void stmmac_hw_teardown(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + clk_disable_unprepare(priv->plat->clk_ptp_ref); +} + /** * stmmac_open - open entry point of the driver * @dev : pointer to the device structure. @@ -1863,6 +1870,7 @@ static int stmmac_open(struct net_device *dev) phy_stop(dev->phydev); del_timer_sync(&priv->txtimer); + stmmac_hw_teardown(dev); init_error: free_dma_desc_resources(priv); dma_desc_error: From 0ad2be79f254965f277fabdd7c64512527208f64 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:34:56 +0100 Subject: [PATCH 159/399] net: stmmac: Balance PTP reference clock enable/disable clk_prepare_enable() and clk_disable_unprepare() for this clock aren't properly balanced, which can trigger a WARN_ON() in the common clock framework. Reviewed-By: Joao Pinto Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++++ drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 1 - 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 6060410d2b9e..ce6d7e791f3f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1711,6 +1711,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_mmc_setup(priv); if (init_ptp) { + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) + netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret); + ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) netdev_warn(priv->dev, "PTP not supported by HW\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index f2d94eafeb0a..fe49c3105755 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -365,7 +365,6 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->clk_ptp_ref = NULL; dev_warn(&pdev->dev, "PTP uses main clock\n"); } else { - clk_prepare_enable(plat->clk_ptp_ref); plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref); dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate); } From 937071c171ff3656e196c965c5179ba3f9f6a2fc Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:34:57 +0100 Subject: [PATCH 160/399] net: stmmac: Check for DMA mapping errors When DMA mapping an SKB fragment, the mapping must be checked for errors, otherwise the DMA debug code will complain upon unmap. Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ce6d7e791f3f..eba9088e1f61 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2079,6 +2079,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) des = skb_frag_dma_map(priv->device, frag, 0, skb_frag_size(frag), DMA_TO_DEVICE); + if (dma_mapping_error(priv->device, des)) + goto dma_map_err; stmmac_tso_allocator(priv, des, skb_frag_size(frag), (i == nfrags - 1)); From 11fbf811c8e8a11529214a494eab25e21ca86739 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:34:58 +0100 Subject: [PATCH 161/399] net: stmmac: Parse FIFO sizes from feature registers New version of this core encode the FIFO sizes in one of the feature registers. Use these sizes as default, but still allow device tree to override them for backwards compatibility. Reviewed-by: Mikko Perttunen Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 3 +++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 2 ++ drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 5 +++++ drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 +++ 4 files changed, 13 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 04d9245b7149..3ca36744007b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -324,6 +324,9 @@ struct dma_features { unsigned int number_tx_queues; /* Alternate (enhanced) DESC mode */ unsigned int enh_desc; + /* TX and RX FIFO sizes */ + unsigned int tx_fifo_size; + unsigned int rx_fifo_size; }; /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index db45134fddf0..83f5e953e291 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -148,6 +148,8 @@ enum power_event { /* MAC HW features1 bitmap */ #define GMAC_HW_FEAT_AVSEL BIT(20) #define GMAC_HW_TSOEN BIT(18) +#define GMAC_HW_TXFIFOSIZE GENMASK(10, 6) +#define GMAC_HW_RXFIFOSIZE GENMASK(4, 0) /* MAC HW features2 bitmap */ #define GMAC_HW_FEAT_TXCHCNT GENMASK(21, 18) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index f97b0d5d9987..55270933bae1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -294,6 +294,11 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr, hw_cap = readl(ioaddr + GMAC_HW_FEATURE1); dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20; dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18; + /* RX and TX FIFO sizes are encoded as log2(n / 128). Undo that by + * shifting and store the sizes in bytes. + */ + dma_cap->tx_fifo_size = 128 << ((hw_cap & GMAC_HW_TXFIFOSIZE) >> 6); + dma_cap->rx_fifo_size = 128 << ((hw_cap & GMAC_HW_RXFIFOSIZE) >> 0); /* MAC HW feature2 */ hw_cap = readl(ioaddr + GMAC_HW_FEATURE2); /* TX and RX number of channels */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index eba9088e1f61..78f6ec2d165b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1281,6 +1281,9 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) { int rxfifosz = priv->plat->rx_fifo_size; + if (rxfifosz == 0) + rxfifosz = priv->dma_cap.rx_fifo_size; + if (priv->plat->force_thresh_dma_mode) priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, rxfifosz); else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) { From 356b7557857e43c52561ac722168ea173f5f6ddc Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:34:59 +0100 Subject: [PATCH 162/399] net: stmmac: Program RX queue size and flow control Program the receive queue size based on the RX FIFO size and enable hardware flow control for large FIFOs. Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 12 +++++ .../net/ethernet/stmicro/stmmac/dwmac4_dma.c | 52 ++++++++++++++++++- 2 files changed, 62 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 83f5e953e291..3b1828b4d294 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -182,6 +182,7 @@ enum power_event { #define MTL_OP_MODE_TSF BIT(1) #define MTL_OP_MODE_TQS_MASK GENMASK(24, 16) +#define MTL_OP_MODE_TQS_SHIFT 16 #define MTL_OP_MODE_TTC_MASK 0x70 #define MTL_OP_MODE_TTC_SHIFT 4 @@ -195,6 +196,17 @@ enum power_event { #define MTL_OP_MODE_TTC_384 (6 << MTL_OP_MODE_TTC_SHIFT) #define MTL_OP_MODE_TTC_512 (7 << MTL_OP_MODE_TTC_SHIFT) +#define MTL_OP_MODE_RQS_MASK GENMASK(29, 20) +#define MTL_OP_MODE_RQS_SHIFT 20 + +#define MTL_OP_MODE_RFD_MASK GENMASK(19, 14) +#define MTL_OP_MODE_RFD_SHIFT 14 + +#define MTL_OP_MODE_RFA_MASK GENMASK(13, 8) +#define MTL_OP_MODE_RFA_SHIFT 8 + +#define MTL_OP_MODE_EHFC BIT(7) + #define MTL_OP_MODE_RTC_MASK 0x18 #define MTL_OP_MODE_RTC_SHIFT 3 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 55270933bae1..6ac6b2600a7c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -183,8 +183,9 @@ static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt) } static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, - int rxmode, u32 channel) + int rxmode, u32 channel, int rxfifosz) { + unsigned int rqs = rxfifosz / 256 - 1; u32 mtl_tx_op, mtl_rx_op, mtl_rx_int; /* Following code only done for channel 0, other channels not yet @@ -250,6 +251,53 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, mtl_rx_op |= MTL_OP_MODE_RTC_128; } + mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK; + mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT; + + /* enable flow control only if each channel gets 4 KiB or more FIFO */ + if (rxfifosz >= 4096) { + unsigned int rfd, rfa; + + mtl_rx_op |= MTL_OP_MODE_EHFC; + + /* Set Threshold for Activating Flow Control to min 2 frames, + * i.e. 1500 * 2 = 3000 bytes. + * + * Set Threshold for Deactivating Flow Control to min 1 frame, + * i.e. 1500 bytes. + */ + switch (rxfifosz) { + case 4096: + /* This violates the above formula because of FIFO size + * limit therefore overflow may occur in spite of this. + */ + rfd = 0x03; /* Full-2.5K */ + rfa = 0x01; /* Full-1.5K */ + break; + + case 8192: + rfd = 0x06; /* Full-4K */ + rfa = 0x0a; /* Full-6K */ + break; + + case 16384: + rfd = 0x06; /* Full-4K */ + rfa = 0x12; /* Full-10K */ + break; + + default: + rfd = 0x06; /* Full-4K */ + rfa = 0x1e; /* Full-16K */ + break; + } + + mtl_rx_op &= ~MTL_OP_MODE_RFD_MASK; + mtl_rx_op |= rfd << MTL_OP_MODE_RFD_SHIFT; + + mtl_rx_op &= ~MTL_OP_MODE_RFA_MASK; + mtl_rx_op |= rfa << MTL_OP_MODE_RFA_SHIFT; + } + writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel)); /* Enable MTL RX overflow */ @@ -262,7 +310,7 @@ static void dwmac4_dma_operation_mode(void __iomem *ioaddr, int txmode, int rxmode, int rxfifosz) { /* Only Channel 0 is actually configured and used */ - dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0); + dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0, rxfifosz); } static void dwmac4_get_hw_feature(void __iomem *ioaddr, From cee45b2edafaa1063bd3a43ba3577490a26fed4c Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:35:00 +0100 Subject: [PATCH 163/399] net: stmmac: dwc-qos: Split out ->probe() and ->remove() Split out the binding specific parts of ->probe() and ->remove() to enable the driver to support variants of the binding. This is useful in order to keep backwards-compatibility while making it easy for a sub- driver to deal only with the updated bindings rather than having to add compatibility quirks all over the place. Reviewed-by: Mikko Perttunen Reviewed-By: Joao Pinto Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- .../stmicro/stmmac/dwmac-dwc-qos-eth.c | 124 ++++++++++++++---- 1 file changed, 98 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 1a3fa3d9f855..319232021bb7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -106,13 +107,80 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, return 0; } +static void *dwc_qos_probe(struct platform_device *pdev, + struct plat_stmmacenet_data *plat_dat, + struct stmmac_resources *stmmac_res) +{ + int err; + + plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk"); + if (IS_ERR(plat_dat->stmmac_clk)) { + dev_err(&pdev->dev, "apb_pclk clock not found.\n"); + return ERR_CAST(plat_dat->stmmac_clk); + } + + err = clk_prepare_enable(plat_dat->stmmac_clk); + if (err < 0) { + dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n", + err); + return ERR_PTR(err); + } + + plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk"); + if (IS_ERR(plat_dat->pclk)) { + dev_err(&pdev->dev, "phy_ref_clk clock not found.\n"); + err = PTR_ERR(plat_dat->pclk); + goto disable; + } + + err = clk_prepare_enable(plat_dat->pclk); + if (err < 0) { + dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n", + err); + goto disable; + } + + return NULL; + +disable: + clk_disable_unprepare(plat_dat->stmmac_clk); + return ERR_PTR(err); +} + +static int dwc_qos_remove(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct stmmac_priv *priv = netdev_priv(ndev); + + clk_disable_unprepare(priv->plat->pclk); + clk_disable_unprepare(priv->plat->stmmac_clk); + + return 0; +} + +struct dwc_eth_dwmac_data { + void *(*probe)(struct platform_device *pdev, + struct plat_stmmacenet_data *data, + struct stmmac_resources *res); + int (*remove)(struct platform_device *pdev); +}; + +static const struct dwc_eth_dwmac_data dwc_qos_data = { + .probe = dwc_qos_probe, + .remove = dwc_qos_remove, +}; + static int dwc_eth_dwmac_probe(struct platform_device *pdev) { + const struct dwc_eth_dwmac_data *data; struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; struct resource *res; + void *priv; int ret; + data = of_device_get_match_data(&pdev->dev); + memset(&stmmac_res, 0, sizeof(struct stmmac_resources)); /** @@ -138,39 +206,26 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk"); - if (IS_ERR(plat_dat->stmmac_clk)) { - dev_err(&pdev->dev, "apb_pclk clock not found.\n"); - ret = PTR_ERR(plat_dat->stmmac_clk); - plat_dat->stmmac_clk = NULL; - goto err_remove_config_dt; + priv = data->probe(pdev, plat_dat, &stmmac_res); + if (IS_ERR(priv)) { + ret = PTR_ERR(priv); + dev_err(&pdev->dev, "failed to probe subdriver: %d\n", ret); + goto remove_config; } - clk_prepare_enable(plat_dat->stmmac_clk); - - plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk"); - if (IS_ERR(plat_dat->pclk)) { - dev_err(&pdev->dev, "phy_ref_clk clock not found.\n"); - ret = PTR_ERR(plat_dat->pclk); - plat_dat->pclk = NULL; - goto err_out_clk_dis_phy; - } - clk_prepare_enable(plat_dat->pclk); ret = dwc_eth_dwmac_config_dt(pdev, plat_dat); if (ret) - goto err_out_clk_dis_aper; + goto remove; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - goto err_out_clk_dis_aper; + goto remove; - return 0; + return ret; -err_out_clk_dis_aper: - clk_disable_unprepare(plat_dat->pclk); -err_out_clk_dis_phy: - clk_disable_unprepare(plat_dat->stmmac_clk); -err_remove_config_dt: +remove: + data->remove(pdev); +remove_config: stmmac_remove_config_dt(pdev, plat_dat); return ret; @@ -178,11 +233,28 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) static int dwc_eth_dwmac_remove(struct platform_device *pdev) { - return stmmac_pltfr_remove(pdev); + struct net_device *ndev = platform_get_drvdata(pdev); + struct stmmac_priv *priv = netdev_priv(ndev); + const struct dwc_eth_dwmac_data *data; + int err; + + data = of_device_get_match_data(&pdev->dev); + + err = stmmac_dvr_remove(&pdev->dev); + if (err < 0) + dev_err(&pdev->dev, "failed to remove platform: %d\n", err); + + err = data->remove(pdev); + if (err < 0) + dev_err(&pdev->dev, "failed to remove subdriver: %d\n", err); + + stmmac_remove_config_dt(pdev, priv->plat); + + return err; } static const struct of_device_id dwc_eth_dwmac_match[] = { - { .compatible = "snps,dwc-qos-ethernet-4.10", }, + { .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data }, { } }; MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match); From e6ea2d16fc615e82bbd9c022c6a4302f22f418bf Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Mar 2017 17:35:01 +0100 Subject: [PATCH 164/399] net: stmmac: dwc-qos: Add Tegra186 support The NVIDIA Tegra186 SoC contains an instance of the Synopsys DWC ethernet QOS IP core. The binding that it uses is slightly different from existing ones because of the integration (clocks, resets, ...). Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- .../stmicro/stmmac/dwmac-dwc-qos-eth.c | 247 ++++++++++++++++++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 1 + 2 files changed, 248 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 319232021bb7..dd6a2f9791cc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -14,17 +14,34 @@ #include #include #include +#include #include #include +#include #include #include #include #include #include #include +#include #include #include "stmmac_platform.h" +#include "dwmac4.h" + +struct tegra_eqos { + struct device *dev; + void __iomem *regs; + + struct reset_control *rst; + struct clk *clk_master; + struct clk *clk_slave; + struct clk *clk_tx; + struct clk *clk_rx; + + struct gpio_desc *reset; +}; static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat) @@ -158,6 +175,230 @@ static int dwc_qos_remove(struct platform_device *pdev) return 0; } +#define SDMEMCOMPPADCTRL 0x8800 +#define SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD BIT(31) + +#define AUTO_CAL_CONFIG 0x8804 +#define AUTO_CAL_CONFIG_START BIT(31) +#define AUTO_CAL_CONFIG_ENABLE BIT(29) + +#define AUTO_CAL_STATUS 0x880c +#define AUTO_CAL_STATUS_ACTIVE BIT(31) + +static void tegra_eqos_fix_speed(void *priv, unsigned int speed) +{ + struct tegra_eqos *eqos = priv; + unsigned long rate = 125000000; + bool needs_calibration = false; + u32 value; + int err; + + switch (speed) { + case SPEED_1000: + needs_calibration = true; + rate = 125000000; + break; + + case SPEED_100: + needs_calibration = true; + rate = 25000000; + break; + + case SPEED_10: + rate = 2500000; + break; + + default: + dev_err(eqos->dev, "invalid speed %u\n", speed); + break; + } + + if (needs_calibration) { + /* calibrate */ + value = readl(eqos->regs + SDMEMCOMPPADCTRL); + value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD; + writel(value, eqos->regs + SDMEMCOMPPADCTRL); + + udelay(1); + + value = readl(eqos->regs + AUTO_CAL_CONFIG); + value |= AUTO_CAL_CONFIG_START | AUTO_CAL_CONFIG_ENABLE; + writel(value, eqos->regs + AUTO_CAL_CONFIG); + + err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS, + value, + value & AUTO_CAL_STATUS_ACTIVE, + 1, 10); + if (err < 0) { + dev_err(eqos->dev, "calibration did not start\n"); + goto failed; + } + + err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS, + value, + (value & AUTO_CAL_STATUS_ACTIVE) == 0, + 20, 200); + if (err < 0) { + dev_err(eqos->dev, "calibration didn't finish\n"); + goto failed; + } + + failed: + value = readl(eqos->regs + SDMEMCOMPPADCTRL); + value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD; + writel(value, eqos->regs + SDMEMCOMPPADCTRL); + } else { + value = readl(eqos->regs + AUTO_CAL_CONFIG); + value &= ~AUTO_CAL_CONFIG_ENABLE; + writel(value, eqos->regs + AUTO_CAL_CONFIG); + } + + err = clk_set_rate(eqos->clk_tx, rate); + if (err < 0) + dev_err(eqos->dev, "failed to set TX rate: %d\n", err); +} + +static int tegra_eqos_init(struct platform_device *pdev, void *priv) +{ + struct tegra_eqos *eqos = priv; + unsigned long rate; + u32 value; + + rate = clk_get_rate(eqos->clk_slave); + + value = (rate / 1000000) - 1; + writel(value, eqos->regs + GMAC_1US_TIC_COUNTER); + + return 0; +} + +static void *tegra_eqos_probe(struct platform_device *pdev, + struct plat_stmmacenet_data *data, + struct stmmac_resources *res) +{ + struct tegra_eqos *eqos; + int err; + + eqos = devm_kzalloc(&pdev->dev, sizeof(*eqos), GFP_KERNEL); + if (!eqos) { + err = -ENOMEM; + goto error; + } + + eqos->dev = &pdev->dev; + eqos->regs = res->addr; + + eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus"); + if (IS_ERR(eqos->clk_master)) { + err = PTR_ERR(eqos->clk_master); + goto error; + } + + err = clk_prepare_enable(eqos->clk_master); + if (err < 0) + goto error; + + eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus"); + if (IS_ERR(eqos->clk_slave)) { + err = PTR_ERR(eqos->clk_slave); + goto disable_master; + } + + data->stmmac_clk = eqos->clk_slave; + + err = clk_prepare_enable(eqos->clk_slave); + if (err < 0) + goto disable_master; + + eqos->clk_rx = devm_clk_get(&pdev->dev, "rx"); + if (IS_ERR(eqos->clk_rx)) { + err = PTR_ERR(eqos->clk_rx); + goto disable_slave; + } + + err = clk_prepare_enable(eqos->clk_rx); + if (err < 0) + goto disable_slave; + + eqos->clk_tx = devm_clk_get(&pdev->dev, "tx"); + if (IS_ERR(eqos->clk_tx)) { + err = PTR_ERR(eqos->clk_tx); + goto disable_rx; + } + + err = clk_prepare_enable(eqos->clk_tx); + if (err < 0) + goto disable_rx; + + eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH); + if (IS_ERR(eqos->reset)) { + err = PTR_ERR(eqos->reset); + goto disable_tx; + } + + usleep_range(2000, 4000); + gpiod_set_value(eqos->reset, 0); + + eqos->rst = devm_reset_control_get(&pdev->dev, "eqos"); + if (IS_ERR(eqos->rst)) { + err = PTR_ERR(eqos->rst); + goto reset_phy; + } + + err = reset_control_assert(eqos->rst); + if (err < 0) + goto reset_phy; + + usleep_range(2000, 4000); + + err = reset_control_deassert(eqos->rst); + if (err < 0) + goto reset_phy; + + usleep_range(2000, 4000); + + data->fix_mac_speed = tegra_eqos_fix_speed; + data->init = tegra_eqos_init; + data->bsp_priv = eqos; + + err = tegra_eqos_init(pdev, eqos); + if (err < 0) + goto reset; + +out: + return eqos; + +reset: + reset_control_assert(eqos->rst); +reset_phy: + gpiod_set_value(eqos->reset, 1); +disable_tx: + clk_disable_unprepare(eqos->clk_tx); +disable_rx: + clk_disable_unprepare(eqos->clk_rx); +disable_slave: + clk_disable_unprepare(eqos->clk_slave); +disable_master: + clk_disable_unprepare(eqos->clk_master); +error: + eqos = ERR_PTR(err); + goto out; +} + +static int tegra_eqos_remove(struct platform_device *pdev) +{ + struct tegra_eqos *eqos = get_stmmac_bsp_priv(&pdev->dev); + + reset_control_assert(eqos->rst); + gpiod_set_value(eqos->reset, 1); + clk_disable_unprepare(eqos->clk_tx); + clk_disable_unprepare(eqos->clk_rx); + clk_disable_unprepare(eqos->clk_slave); + clk_disable_unprepare(eqos->clk_master); + + return 0; +} + struct dwc_eth_dwmac_data { void *(*probe)(struct platform_device *pdev, struct plat_stmmacenet_data *data, @@ -170,6 +411,11 @@ static const struct dwc_eth_dwmac_data dwc_qos_data = { .remove = dwc_qos_remove, }; +static const struct dwc_eth_dwmac_data tegra_eqos_data = { + .probe = tegra_eqos_probe, + .remove = tegra_eqos_remove, +}; + static int dwc_eth_dwmac_probe(struct platform_device *pdev) { const struct dwc_eth_dwmac_data *data; @@ -255,6 +501,7 @@ static int dwc_eth_dwmac_remove(struct platform_device *pdev) static const struct of_device_id dwc_eth_dwmac_match[] = { { .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data }, + { .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data }, { } }; MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 3b1828b4d294..018fc2d447c4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -25,6 +25,7 @@ #define GMAC_RXQ_CTRL0 0x000000a0 #define GMAC_INT_STATUS 0x000000b0 #define GMAC_INT_EN 0x000000b4 +#define GMAC_1US_TIC_COUNTER 0x000000dc #define GMAC_PCS_BASE 0x000000e0 #define GMAC_PHYIF_CONTROL_STATUS 0x000000f8 #define GMAC_PMT 0x000000c0 From d976a525c371276cebd2517349d1d3568a0e48b5 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:51 +0000 Subject: [PATCH 165/399] net: stmmac: multiple queues dt configuration This patch adds the multiple queues configuration in the Device Tree. It was also created a set of structures to keep the RX and TX queues configurations to be used in the driver. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- .../devicetree/bindings/net/stmmac.txt | 40 ++++++++ .../ethernet/stmicro/stmmac/stmmac_platform.c | 91 +++++++++++++++++++ include/linux/stmmac.h | 30 ++++++ 3 files changed, 161 insertions(+) diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index 11b27dfd1627..04a258e2d4e0 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -72,6 +72,27 @@ Optional properties: - snps,mb: mixed-burst - snps,rb: rebuild INCRx Burst - mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus. +- Multiple RX Queues parameters: below the list of all the parameters to + configure the multiple RX queues: + - snps,rx-queues-to-use: number of RX queues to be used in the driver + - Choose one of these RX scheduling algorithms: + - snps,rx-sched-sp: Strict priority + - snps,rx-sched-wsp: Weighted Strict priority + - For each RX queue + - Choose one of these modes: + - snps,dcb-algorithm: Queue to be enabled as DCB + - snps,avb-algorithm: Queue to be enabled as AVB + - snps,map-to-dma-channel: Channel to map +- Multiple TX Queues parameters: below the list of all the parameters to + configure the multiple TX queues: + - snps,tx-queues-to-use: number of TX queues to be used in the driver + - Choose one of these TX scheduling algorithms: + - snps,tx-sched-wrr: Weighted Round Robin + - snps,tx-sched-wfq: Weighted Fair Queuing + - snps,tx-sched-dwrr: Deficit Weighted Round Robin + - snps,tx-sched-sp: Strict priority + - For each TX queue + - snps,weight: TX queue weight (if using a weighted algorithm) Examples: @@ -81,6 +102,23 @@ Examples: snps,blen = <256 128 64 32 0 0 0>; }; + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <1>; + snps,rx-sched-sp; + queue0 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x0>; + }; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <1>; + snps,tx-sched-wrr; + queue0 { + snps,weight = <0x10>; + }; + }; + gmac0: ethernet@e0800000 { compatible = "st,spear600-gmac"; reg = <0xe0800000 0x8000>; @@ -104,4 +142,6 @@ Examples: phy1: ethernet-phy@0 { }; }; + snps,mtl-rx-config = <&mtl_rx_setup>; + snps,mtl-tx-config = <&mtl_tx_setup>; }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index fe49c3105755..0b76e3de502d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -131,6 +131,95 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) return axi; } +/** + * stmmac_mtl_setup - parse DT parameters for multiple queues configuration + * @pdev: platform device + */ +static void stmmac_mtl_setup(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ + struct device_node *q_node; + struct device_node *rx_node; + struct device_node *tx_node; + u8 queue = 0; + + rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0); + if (!rx_node) + return; + + tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0); + if (!tx_node) { + of_node_put(rx_node); + return; + } + + /* Processing RX queues common config */ + if (of_property_read_u8(rx_node, "snps,rx-queues-to-use", + &plat->rx_queues_to_use)) + plat->rx_queues_to_use = 1; + + if (of_property_read_bool(rx_node, "snps,rx-sched-sp")) + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; + else if (of_property_read_bool(rx_node, "snps,rx-sched-wsp")) + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_WSP; + else + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; + + /* Processing individual RX queue config */ + for_each_child_of_node(rx_node, q_node) { + if (queue >= plat->rx_queues_to_use) + break; + + if (of_property_read_bool(q_node, "snps,dcb-algorithm")) + plat->rx_queues_cfg[queue].mode_to_use = MTL_RX_DCB; + else if (of_property_read_bool(q_node, "snps,avb-algorithm")) + plat->rx_queues_cfg[queue].mode_to_use = MTL_RX_AVB; + else + plat->rx_queues_cfg[queue].mode_to_use = MTL_RX_DCB; + + if (of_property_read_u8(q_node, "snps,map-to-dma-channel", + &plat->rx_queues_cfg[queue].chan)) + plat->rx_queues_cfg[queue].chan = queue; + /* TODO: Dynamic mapping to be included in the future */ + + queue++; + } + + /* Processing TX queues common config */ + if (of_property_read_u8(tx_node, "snps,tx-queues-to-use", + &plat->tx_queues_to_use)) + plat->tx_queues_to_use = 1; + + if (of_property_read_bool(tx_node, "snps,tx-sched-wrr")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; + else if (of_property_read_bool(tx_node, "snps,tx-sched-wfq")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WFQ; + else if (of_property_read_bool(tx_node, "snps,tx-sched-dwrr")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_DWRR; + else if (of_property_read_bool(tx_node, "snps,tx-sched-sp")) + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP; + else + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP; + + queue = 0; + + /* Processing individual TX queue config */ + for_each_child_of_node(tx_node, q_node) { + if (queue >= plat->tx_queues_to_use) + break; + + if (of_property_read_u8(q_node, "snps,weight", + &plat->tx_queues_cfg[queue].weight)) + plat->tx_queues_cfg[queue].weight = 0x10 + queue; + + queue++; + } + + of_node_put(rx_node); + of_node_put(tx_node); + of_node_put(q_node); +} + /** * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources * @plat: driver data platform structure @@ -340,6 +429,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->axi = stmmac_axi_setup(pdev); + stmmac_mtl_setup(pdev, plat); + /* clock setup */ plat->stmmac_clk = devm_clk_get(&pdev->dev, STMMAC_RESOURCE_NAME); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index fc273e9d5f67..266ff2af91e5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -28,6 +28,9 @@ #include +#define MTL_MAX_RX_QUEUES 8 +#define MTL_MAX_TX_QUEUES 8 + #define STMMAC_RX_COE_NONE 0 #define STMMAC_RX_COE_TYPE1 1 #define STMMAC_RX_COE_TYPE2 2 @@ -44,6 +47,18 @@ #define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */ #define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/122 */ +/* MTL algorithms identifiers */ +#define MTL_TX_ALGORITHM_WRR 0x0 +#define MTL_TX_ALGORITHM_WFQ 0x1 +#define MTL_TX_ALGORITHM_DWRR 0x2 +#define MTL_TX_ALGORITHM_SP 0x3 +#define MTL_RX_ALGORITHM_SP 0x4 +#define MTL_RX_ALGORITHM_WSP 0x5 + +/* RX Queue Mode */ +#define MTL_RX_DCB 0x0 +#define MTL_RX_AVB 0x1 + /* The MDC clock could be set higher than the IEEE 802.3 * specified frequency limit 0f 2.5 MHz, by programming a clock divider * of value different than the above defined values. The resultant MDIO @@ -109,6 +124,15 @@ struct stmmac_axi { bool axi_rb; }; +struct stmmac_rxq_cfg { + u8 mode_to_use; + u8 chan; +}; + +struct stmmac_txq_cfg { + u8 weight; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -133,6 +157,12 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; + u8 rx_queues_to_use; + u8 tx_queues_to_use; + u8 rx_sched_algorithm; + u8 tx_sched_algorithm; + struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; + struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*fix_mac_speed)(void *priv, unsigned int speed); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); From d0a9c9f9c6d0b1f0773e0aba5ab519b8ddc87a7a Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:52 +0000 Subject: [PATCH 166/399] net: stmmac: configure mtl rx and tx algorithms This patch adds the RX and TX scheduling algorithms programming. It introduces the multiple queues configuration function (stmmac_mtl_configuration) in stmmac_main. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 4 ++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 10 ++++ .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 48 +++++++++++++++++++ .../net/ethernet/stmicro/stmmac/stmmac_main.c | 31 ++++++++++-- 4 files changed, 90 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 3ca36744007b..31d3324df6d4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -458,6 +458,10 @@ struct stmmac_ops { int (*rx_ipc)(struct mac_device_info *hw); /* Enable RX Queues */ void (*rx_queue_enable)(struct mac_device_info *hw, u32 queue); + /* Program RX Algorithms */ + void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); + /* Program TX Algorithms */ + void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg); /* Dump MAC registers */ void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space); /* Handle extra events on specific interrupts hw dependent */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 018fc2d447c4..bc994fe3e6bf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -164,6 +164,16 @@ enum power_event { #define GMAC_HI_REG_AE BIT(31) /* MTL registers */ +#define MTL_OPERATION_MODE 0x00000c00 +#define MTL_OPERATION_SCHALG_MASK GENMASK(6, 5) +#define MTL_OPERATION_SCHALG_WRR (0x0 << 5) +#define MTL_OPERATION_SCHALG_WFQ (0x1 << 5) +#define MTL_OPERATION_SCHALG_DWRR (0x2 << 5) +#define MTL_OPERATION_SCHALG_SP (0x3 << 5) +#define MTL_OPERATION_RAA BIT(2) +#define MTL_OPERATION_RAA_SP (0x0 << 2) +#define MTL_OPERATION_RAA_WSP (0x1 << 2) + #define MTL_INT_STATUS 0x00000c20 #define MTL_INT_Q0 BIT(0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 1e79e6529c4a..f96675567192 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -70,6 +70,52 @@ static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 queue) writel(value, ioaddr + GMAC_RXQ_CTRL0); } +static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw, + u32 rx_alg) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value = readl(ioaddr + MTL_OPERATION_MODE); + + value &= ~MTL_OPERATION_RAA; + switch (rx_alg) { + case MTL_RX_ALGORITHM_SP: + value |= MTL_OPERATION_RAA_SP; + break; + case MTL_RX_ALGORITHM_WSP: + value |= MTL_OPERATION_RAA_WSP; + break; + default: + break; + } + + writel(value, ioaddr + MTL_OPERATION_MODE); +} + +static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw, + u32 tx_alg) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value = readl(ioaddr + MTL_OPERATION_MODE); + + value &= ~MTL_OPERATION_SCHALG_MASK; + switch (tx_alg) { + case MTL_TX_ALGORITHM_WRR: + value |= MTL_OPERATION_SCHALG_WRR; + break; + case MTL_TX_ALGORITHM_WFQ: + value |= MTL_OPERATION_SCHALG_WFQ; + break; + case MTL_TX_ALGORITHM_DWRR: + value |= MTL_OPERATION_SCHALG_DWRR; + break; + case MTL_TX_ALGORITHM_SP: + value |= MTL_OPERATION_SCHALG_SP; + break; + default: + break; + } +} + static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space) { void __iomem *ioaddr = hw->pcsr; @@ -457,6 +503,8 @@ static const struct stmmac_ops dwmac4_ops = { .core_init = dwmac4_core_init, .rx_ipc = dwmac4_rx_ipc_enable, .rx_queue_enable = dwmac4_rx_queue_enable, + .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, + .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .dump_regs = dwmac4_dump_regs, .host_irq_status = dwmac4_irq_status, .flow_ctrl = dwmac4_flow_ctrl, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 78f6ec2d165b..064fa0e6b536 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1647,6 +1647,31 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv) add_timer(&priv->txtimer); } +/** + * stmmac_mtl_configuration - Configure MTL + * @priv: driver private structure + * Description: It is used for configurring MTL + */ +static void stmmac_mtl_configuration(struct stmmac_priv *priv) +{ + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 tx_queues_count = priv->plat->tx_queues_to_use; + + /* Configure MTL RX algorithms */ + if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms) + priv->hw->mac->prog_mtl_rx_algorithms(priv->hw, + priv->plat->rx_sched_algorithm); + + /* Configure MTL TX algorithms */ + if (tx_queues_count > 1 && priv->hw->mac->prog_mtl_tx_algorithms) + priv->hw->mac->prog_mtl_tx_algorithms(priv->hw, + priv->plat->tx_sched_algorithm); + + /* Enable MAC RX Queues */ + if (rx_queues_count > 1 && priv->hw->mac->rx_queue_enable) + stmmac_mac_enable_rx_queues(priv); +} + /** * stmmac_hw_setup - setup mac in a usable state. * @dev : pointer to the device structure. @@ -1691,9 +1716,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) /* Initialize the MAC Core */ priv->hw->mac->core_init(priv->hw, dev->mtu); - /* Initialize MAC RX Queues */ - if (priv->hw->mac->rx_queue_enable) - stmmac_mac_enable_rx_queues(priv); + /* Initialize MTL*/ + if (priv->synopsys_id >= DWMAC_CORE_4_00) + stmmac_mtl_configuration(priv); ret = priv->hw->mac->rx_ipc(priv->hw); if (!ret) { From 6a3a7193b2811537c64eb513e39473050a72f1a4 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:53 +0000 Subject: [PATCH 167/399] net: stmmac: configure tx queue weight This patch adds TX queues weight programming. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 3 +++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 7 +++++++ .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 12 +++++++++++ .../net/ethernet/stmicro/stmmac/stmmac_main.c | 20 +++++++++++++++++++ 4 files changed, 42 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 31d3324df6d4..4eeaa5c905f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -462,6 +462,9 @@ struct stmmac_ops { void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); /* Program TX Algorithms */ void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg); + /* Set MTL TX queues weight */ + void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw, + u32 weight, u32 queue); /* Dump MAC registers */ void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space); /* Handle extra events on specific interrupts hw dependent */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index bc994fe3e6bf..89824fe484f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -226,6 +226,13 @@ enum power_event { #define MTL_OP_MODE_RTC_96 (2 << MTL_OP_MODE_RTC_SHIFT) #define MTL_OP_MODE_RTC_128 (3 << MTL_OP_MODE_RTC_SHIFT) +/* MTL Queue Quantum Weight */ +#define MTL_TXQ_WEIGHT_BASE_ADDR 0x00000d18 +#define MTL_TXQ_WEIGHT_BASE_OFFSET 0x40 +#define MTL_TXQX_WEIGHT_BASE_ADDR(x) (MTL_TXQ_WEIGHT_BASE_ADDR + \ + ((x) * MTL_TXQ_WEIGHT_BASE_OFFSET)) +#define MTL_TXQ_WEIGHT_ISCQW_MASK GENMASK(20, 0) + /* MTL debug */ #define MTL_DEBUG_TXSTSFSTS BIT(5) #define MTL_DEBUG_TXFSTS BIT(4) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f96675567192..fda6cfa7aba4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -116,6 +116,17 @@ static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw, } } +static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw, + u32 weight, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value = readl(ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue)); + + value &= ~MTL_TXQ_WEIGHT_ISCQW_MASK; + value |= weight & MTL_TXQ_WEIGHT_ISCQW_MASK; + writel(value, ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue)); +} + static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space) { void __iomem *ioaddr = hw->pcsr; @@ -505,6 +516,7 @@ static const struct stmmac_ops dwmac4_ops = { .rx_queue_enable = dwmac4_rx_queue_enable, .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, + .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, .dump_regs = dwmac4_dump_regs, .host_irq_status = dwmac4_irq_status, .flow_ctrl = dwmac4_flow_ctrl, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 064fa0e6b536..7b05cd3fce1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1647,6 +1647,23 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv) add_timer(&priv->txtimer); } +/** + * stmmac_set_tx_queue_weight - Set TX queue weight + * @priv: driver private structure + * Description: It is used for setting TX queues weight + */ +static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv) +{ + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 weight; + u32 queue; + + for (queue = 0; queue < tx_queues_count; queue++) { + weight = priv->plat->tx_queues_cfg[queue].weight; + priv->hw->mac->set_mtl_tx_queue_weight(priv->hw, weight, queue); + } +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -1657,6 +1674,9 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) u32 rx_queues_count = priv->plat->rx_queues_to_use; u32 tx_queues_count = priv->plat->tx_queues_to_use; + if (tx_queues_count > 1 && priv->hw->mac->set_mtl_tx_queue_weight) + stmmac_set_tx_queue_weight(priv); + /* Configure MTL RX algorithms */ if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms) priv->hw->mac->prog_mtl_rx_algorithms(priv->hw, From 4f6046f5872c7db6a152b923cee21c37a04d56b8 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:54 +0000 Subject: [PATCH 168/399] net: stmmac: mtl rx queue enabled as dcb or avb This patch introduces the enabling of RX queues as DCB or as AVB based on configuration. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 8 ++++++-- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 19 +++++++------------ 3 files changed, 14 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 4eeaa5c905f2..f61611c8e8b0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -457,7 +457,7 @@ struct stmmac_ops { /* Enable and verify that the IPC module is supported */ int (*rx_ipc)(struct mac_device_info *hw); /* Enable RX Queues */ - void (*rx_queue_enable)(struct mac_device_info *hw, u32 queue); + void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue); /* Program RX Algorithms */ void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); /* Program TX Algorithms */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index fda6cfa7aba4..21a696eda9ce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -59,13 +59,17 @@ static void dwmac4_core_init(struct mac_device_info *hw, int mtu) writel(value, ioaddr + GMAC_INT_EN); } -static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 queue) +static void dwmac4_rx_queue_enable(struct mac_device_info *hw, + u8 mode, u32 queue) { void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_RXQ_CTRL0); value &= GMAC_RX_QUEUE_CLEAR(queue); - value |= GMAC_RX_AV_QUEUE_ENABLE(queue); + if (mode == MTL_RX_AVB) + value |= GMAC_RX_AV_QUEUE_ENABLE(queue); + else if (mode == MTL_RX_DCB) + value |= GMAC_RX_DCB_QUEUE_ENABLE(queue); writel(value, ioaddr + GMAC_RXQ_CTRL0); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7b05cd3fce1c..43036dabb9f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1256,19 +1256,14 @@ static void free_dma_desc_resources(struct stmmac_priv *priv) */ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv) { - int rx_count = priv->dma_cap.number_rx_queues; - int queue = 0; + u32 rx_queues_count = priv->plat->rx_queues_to_use; + int queue; + u8 mode; - /* If GMAC does not have multiple queues, then this is not necessary*/ - if (rx_count == 1) - return; - - /** - * If the core is synthesized with multiple rx queues / multiple - * dma channels, then rx queues will be disabled by default. - * For now only rx queue 0 is enabled. - */ - priv->hw->mac->rx_queue_enable(priv->hw, queue); + for (queue = 0; queue < rx_queues_count; queue++) { + mode = priv->plat->rx_queues_cfg[queue].mode_to_use; + priv->hw->mac->rx_queue_enable(priv->hw, mode, queue); + } } /** From d43042f4da3e1c2e4ccac3b1d9153cb0798533a4 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:55 +0000 Subject: [PATCH 169/399] net: stmmac: mapping mtl rx to dma channel This patch adds the functionality of RX queue to dma channel mapping based on configuration. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 ++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 7 ++++++ .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 25 +++++++++++++++++++ .../net/ethernet/stmicro/stmmac/stmmac_main.c | 21 ++++++++++++++++ 4 files changed, 55 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index f61611c8e8b0..7d23e3dc7797 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -465,6 +465,8 @@ struct stmmac_ops { /* Set MTL TX queues weight */ void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw, u32 weight, u32 queue); + /* RX MTL queue to RX dma mapping */ + void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan); /* Dump MAC registers */ void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space); /* Handle extra events on specific interrupts hw dependent */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 89824fe484f6..773f25b8e403 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -177,6 +177,13 @@ enum power_event { #define MTL_INT_STATUS 0x00000c20 #define MTL_INT_Q0 BIT(0) +#define MTL_RXQ_DMA_MAP0 0x00000c30 /* queue 0 to 3 */ +#define MTL_RXQ_DMA_MAP1 0x00000c34 /* queue 4 to 7 */ +#define MTL_RXQ_DMA_Q04MDMACH_MASK GENMASK(3, 0) +#define MTL_RXQ_DMA_Q04MDMACH(x) ((x) << 0) +#define MTL_RXQ_DMA_QXMDMACH_MASK(x) GENMASK(11 + (8 * ((x) - 1)), 8 * (x)) +#define MTL_RXQ_DMA_QXMDMACH(chan, q) ((chan) << (8 * (q))) + #define MTL_CHAN_BASE_ADDR 0x00000d00 #define MTL_CHAN_BASE_OFFSET 0x40 #define MTL_CHANX_BASE_ADDR(x) (MTL_CHAN_BASE_ADDR + \ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 21a696eda9ce..e9b153f75538 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -131,6 +131,30 @@ static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw, writel(value, ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue)); } +static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + if (queue < 4) + value = readl(ioaddr + MTL_RXQ_DMA_MAP0); + else + value = readl(ioaddr + MTL_RXQ_DMA_MAP1); + + if (queue == 0 || queue == 4) { + value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK; + value |= MTL_RXQ_DMA_Q04MDMACH(chan); + } else { + value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue); + value |= MTL_RXQ_DMA_QXMDMACH(chan, queue); + } + + if (queue < 4) + writel(value, ioaddr + MTL_RXQ_DMA_MAP0); + else + writel(value, ioaddr + MTL_RXQ_DMA_MAP1); +} + static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space) { void __iomem *ioaddr = hw->pcsr; @@ -521,6 +545,7 @@ static const struct stmmac_ops dwmac4_ops = { .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, + .map_mtl_to_dma = dwmac4_map_mtl_dma, .dump_regs = dwmac4_dump_regs, .host_irq_status = dwmac4_irq_status, .flow_ctrl = dwmac4_flow_ctrl, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 43036dabb9f9..e1d5fe7f54a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1659,6 +1659,23 @@ static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv) } } +/** + * stmmac_rx_queue_dma_chan_map - Map RX queue to RX dma channel + * @priv: driver private structure + * Description: It is used for mapping RX queues to RX dma channels + */ +static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv) +{ + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 queue; + u32 chan; + + for (queue = 0; queue < rx_queues_count; queue++) { + chan = priv->plat->rx_queues_cfg[queue].chan; + priv->hw->mac->map_mtl_to_dma(priv->hw, queue, chan); + } +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -1682,6 +1699,10 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) priv->hw->mac->prog_mtl_tx_algorithms(priv->hw, priv->plat->tx_sched_algorithm); + /* Map RX MTL to DMA channels */ + if (rx_queues_count > 1 && priv->hw->mac->map_mtl_to_dma) + stmmac_rx_queue_dma_chan_map(priv); + /* Enable MAC RX Queues */ if (rx_queues_count > 1 && priv->hw->mac->rx_queue_enable) stmmac_mac_enable_rx_queues(priv); From 29feff39000bb57fe6c25f5ec1435489196c8838 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:56 +0000 Subject: [PATCH 170/399] net: stmmac: flow_ctrl functions adapted to mtl This patch adapts flow_ctrl function to prepare it for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- .../ethernet/stmicro/stmmac/dwmac1000_core.c | 3 ++- .../ethernet/stmicro/stmmac/dwmac100_core.c | 3 ++- .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 20 ++++++++++++------- .../ethernet/stmicro/stmmac/stmmac_ethtool.c | 3 ++- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 17 +++++++++++++--- 6 files changed, 34 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 7d23e3dc7797..7a175e9893d1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -476,7 +476,7 @@ struct stmmac_ops { void (*set_filter)(struct mac_device_info *hw, struct net_device *dev); /* Flow control setting */ void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time); + unsigned int fc, unsigned int pause_time, u32 tx_cnt); /* Set power management mode (e.g. magic frame) */ void (*pmt)(struct mac_device_info *hw, unsigned long mode); /* Set/Get Unicast MAC addresses */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 19b9b3087099..3a95ad9357e3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -216,7 +216,8 @@ static void dwmac1000_set_filter(struct mac_device_info *hw, static void dwmac1000_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time) + unsigned int fc, unsigned int pause_time, + u32 tx_cnt) { void __iomem *ioaddr = hw->pcsr; /* Set flow such that DZPQ in Mac Register 6 is 0, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index e370ccec6176..524135e6dd89 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -131,7 +131,8 @@ static void dwmac100_set_filter(struct mac_device_info *hw, } static void dwmac100_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time) + unsigned int fc, unsigned int pause_time, + u32 tx_cnt) { void __iomem *ioaddr = hw->pcsr; unsigned int flow = MAC_FLOW_CTRL_ENABLE; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index e9b153f75538..3069defb7eb1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -336,11 +336,12 @@ static void dwmac4_set_filter(struct mac_device_info *hw, } static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time) + unsigned int fc, unsigned int pause_time, + u32 tx_cnt) { void __iomem *ioaddr = hw->pcsr; - u32 channel = STMMAC_CHAN0; /* FIXME */ unsigned int flow = 0; + u32 queue = 0; pr_debug("GMAC Flow-Control:\n"); if (fc & FLOW_RX) { @@ -350,13 +351,18 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, } if (fc & FLOW_TX) { pr_debug("\tTransmit Flow-Control ON\n"); - flow |= GMAC_TX_FLOW_CTRL_TFE; - writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel)); - if (duplex) { + if (duplex) pr_debug("\tduplex mode: PAUSE %d\n", pause_time); - flow |= (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT); - writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel)); + + for (queue = 0; queue < tx_cnt; queue++) { + flow |= GMAC_TX_FLOW_CTRL_TFE; + + if (duplex) + flow |= + (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT); + + writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue)); } } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 85d64114e159..4a5dc896044f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -481,6 +481,7 @@ stmmac_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct stmmac_priv *priv = netdev_priv(netdev); + u32 tx_cnt = priv->plat->tx_queues_to_use; struct phy_device *phy = netdev->phydev; int new_pause = FLOW_OFF; @@ -511,7 +512,7 @@ stmmac_set_pauseparam(struct net_device *netdev, } priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl, - priv->pause); + priv->pause, tx_cnt); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e1d5fe7f54a9..f453fc5a2eda 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -672,6 +672,19 @@ static void stmmac_release_ptp(struct stmmac_priv *priv) stmmac_ptp_unregister(priv); } +/** + * stmmac_mac_flow_ctrl - Configure flow control in all queues + * @priv: driver private structure + * Description: It is used for configuring the flow control in all queues + */ +static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex) +{ + u32 tx_cnt = priv->plat->tx_queues_to_use; + + priv->hw->mac->flow_ctrl(priv->hw, duplex, priv->flow_ctrl, + priv->pause, tx_cnt); +} + /** * stmmac_adjust_link - adjusts the link parameters * @dev: net device structure @@ -687,7 +700,6 @@ static void stmmac_adjust_link(struct net_device *dev) struct phy_device *phydev = dev->phydev; unsigned long flags; int new_state = 0; - unsigned int fc = priv->flow_ctrl, pause_time = priv->pause; if (!phydev) return; @@ -709,8 +721,7 @@ static void stmmac_adjust_link(struct net_device *dev) } /* Flow Control operation */ if (phydev->pause) - priv->hw->mac->flow_ctrl(priv->hw, phydev->duplex, - fc, pause_time); + stmmac_mac_flow_ctrl(priv, phydev->duplex); if (phydev->speed != priv->speed) { new_state = 1; From 8f71a88d3619db0abbca3bd18ba15a479a5abf1b Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:57 +0000 Subject: [PATCH 171/399] net: stmmac: prepare irq_status for mtl This patch prepares mac irq status treatment for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 + drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 2 +- .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 40 ++++++++++++------- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++ 4 files changed, 33 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 7a175e9893d1..23c9e2a1bb6f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -472,6 +472,8 @@ struct stmmac_ops { /* Handle extra events on specific interrupts hw dependent */ int (*host_irq_status)(struct mac_device_info *hw, struct stmmac_extra_stats *x); + /* Handle MTL interrupts */ + int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan); /* Multicast filter setting */ void (*set_filter)(struct mac_device_info *hw, struct net_device *dev); /* Flow control setting */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 773f25b8e403..1ddf75c0eab5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -175,7 +175,7 @@ enum power_event { #define MTL_OPERATION_RAA_WSP (0x1 << 2) #define MTL_INT_STATUS 0x00000c20 -#define MTL_INT_Q0 BIT(0) +#define MTL_INT_QX(x) BIT(x) #define MTL_RXQ_DMA_MAP0 0x00000c30 /* queue 0 to 3 */ #define MTL_RXQ_DMA_MAP1 0x00000c34 /* queue 4 to 7 */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 3069defb7eb1..f0f2dce79d09 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -416,11 +416,34 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x) } } +static int dwmac4_irq_mtl_status(struct mac_device_info *hw, u32 chan) +{ + void __iomem *ioaddr = hw->pcsr; + u32 mtl_int_qx_status; + int ret = 0; + + mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS); + + /* Check MTL Interrupt */ + if (mtl_int_qx_status & MTL_INT_QX(chan)) { + /* read Queue x Interrupt status */ + u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(chan)); + + if (status & MTL_RX_OVERFLOW_INT) { + /* clear Interrupt */ + writel(status | MTL_RX_OVERFLOW_INT, + ioaddr + MTL_CHAN_INT_CTRL(chan)); + ret = CORE_IRQ_MTL_RX_OVERFLOW; + } + } + + return ret; +} + static int dwmac4_irq_status(struct mac_device_info *hw, struct stmmac_extra_stats *x) { void __iomem *ioaddr = hw->pcsr; - u32 mtl_int_qx_status; u32 intr_status; int ret = 0; @@ -439,20 +462,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw, x->irq_receive_pmt_irq_n++; } - mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS); - /* Check MTL Interrupt: Currently only one queue is used: Q0. */ - if (mtl_int_qx_status & MTL_INT_Q0) { - /* read Queue 0 Interrupt status */ - u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0)); - - if (status & MTL_RX_OVERFLOW_INT) { - /* clear Interrupt */ - writel(status | MTL_RX_OVERFLOW_INT, - ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0)); - ret = CORE_IRQ_MTL_RX_OVERFLOW; - } - } - dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x); if (intr_status & PCS_RGSMIIIS_IRQ) dwmac4_phystatus(ioaddr, x); @@ -554,6 +563,7 @@ static const struct stmmac_ops dwmac4_ops = { .map_mtl_to_dma = dwmac4_map_mtl_dma, .dump_regs = dwmac4_dump_regs, .host_irq_status = dwmac4_irq_status, + .host_mtl_irq_status = dwmac4_irq_mtl_status, .flow_ctrl = dwmac4_flow_ctrl, .pmt = dwmac4_pmt, .set_umac_addr = dwmac4_set_umac_addr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f453fc5a2eda..2449487be534 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2901,6 +2901,11 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) { int status = priv->hw->mac->host_irq_status(priv->hw, &priv->xstats); + + if (priv->synopsys_id >= DWMAC_CORE_4_00) + status |= priv->hw->mac->host_mtl_irq_status(priv->hw, + STMMAC_CHAN0); + if (unlikely(status)) { /* For LPI we need to save the tx status */ if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE) From ad5a87d7e3c5fcea987728027a3fae2c2f067173 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:58 +0000 Subject: [PATCH 172/399] net: stmmac: mac debug prepared for multiple queues This patch prepares mac debug dump for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 3 +- .../ethernet/stmicro/stmmac/dwmac1000_core.c | 3 +- .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 103 +++++++++--------- .../ethernet/stmicro/stmmac/stmmac_ethtool.c | 5 +- 4 files changed, 62 insertions(+), 52 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 23c9e2a1bb6f..e7fb98569d2d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -491,7 +491,8 @@ struct stmmac_ops { void (*reset_eee_mode)(struct mac_device_info *hw); void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw); void (*set_eee_pls)(struct mac_device_info *hw, int link); - void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x); + void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 rx_queues, u32 tx_queues); /* PCS calls */ void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral, bool loopback); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 3a95ad9357e3..7f78f7746a5b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -413,7 +413,8 @@ static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv) dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv); } -static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x) +static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 rx_queues, u32 tx_queues) { u32 value = readl(ioaddr + GMAC_DEBUG); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f0f2dce79d09..670cfee415fd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -469,64 +469,69 @@ static int dwmac4_irq_status(struct mac_device_info *hw, return ret; } -static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x) +static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 rx_queues, u32 tx_queues) { u32 value; + u32 queue; - /* Currently only channel 0 is supported */ - value = readl(ioaddr + MTL_CHAN_TX_DEBUG(STMMAC_CHAN0)); + for (queue = 0; queue < tx_queues; queue++) { + value = readl(ioaddr + MTL_CHAN_TX_DEBUG(queue)); - if (value & MTL_DEBUG_TXSTSFSTS) - x->mtl_tx_status_fifo_full++; - if (value & MTL_DEBUG_TXFSTS) - x->mtl_tx_fifo_not_empty++; - if (value & MTL_DEBUG_TWCSTS) - x->mmtl_fifo_ctrl++; - if (value & MTL_DEBUG_TRCSTS_MASK) { - u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK) - >> MTL_DEBUG_TRCSTS_SHIFT; - if (trcsts == MTL_DEBUG_TRCSTS_WRITE) - x->mtl_tx_fifo_read_ctrl_write++; - else if (trcsts == MTL_DEBUG_TRCSTS_TXW) - x->mtl_tx_fifo_read_ctrl_wait++; - else if (trcsts == MTL_DEBUG_TRCSTS_READ) - x->mtl_tx_fifo_read_ctrl_read++; - else - x->mtl_tx_fifo_read_ctrl_idle++; + if (value & MTL_DEBUG_TXSTSFSTS) + x->mtl_tx_status_fifo_full++; + if (value & MTL_DEBUG_TXFSTS) + x->mtl_tx_fifo_not_empty++; + if (value & MTL_DEBUG_TWCSTS) + x->mmtl_fifo_ctrl++; + if (value & MTL_DEBUG_TRCSTS_MASK) { + u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK) + >> MTL_DEBUG_TRCSTS_SHIFT; + if (trcsts == MTL_DEBUG_TRCSTS_WRITE) + x->mtl_tx_fifo_read_ctrl_write++; + else if (trcsts == MTL_DEBUG_TRCSTS_TXW) + x->mtl_tx_fifo_read_ctrl_wait++; + else if (trcsts == MTL_DEBUG_TRCSTS_READ) + x->mtl_tx_fifo_read_ctrl_read++; + else + x->mtl_tx_fifo_read_ctrl_idle++; + } + if (value & MTL_DEBUG_TXPAUSED) + x->mac_tx_in_pause++; } - if (value & MTL_DEBUG_TXPAUSED) - x->mac_tx_in_pause++; - value = readl(ioaddr + MTL_CHAN_RX_DEBUG(STMMAC_CHAN0)); + for (queue = 0; queue < rx_queues; queue++) { + value = readl(ioaddr + MTL_CHAN_RX_DEBUG(queue)); - if (value & MTL_DEBUG_RXFSTS_MASK) { - u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK) - >> MTL_DEBUG_RRCSTS_SHIFT; + if (value & MTL_DEBUG_RXFSTS_MASK) { + u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK) + >> MTL_DEBUG_RRCSTS_SHIFT; - if (rxfsts == MTL_DEBUG_RXFSTS_FULL) - x->mtl_rx_fifo_fill_level_full++; - else if (rxfsts == MTL_DEBUG_RXFSTS_AT) - x->mtl_rx_fifo_fill_above_thresh++; - else if (rxfsts == MTL_DEBUG_RXFSTS_BT) - x->mtl_rx_fifo_fill_below_thresh++; - else - x->mtl_rx_fifo_fill_level_empty++; + if (rxfsts == MTL_DEBUG_RXFSTS_FULL) + x->mtl_rx_fifo_fill_level_full++; + else if (rxfsts == MTL_DEBUG_RXFSTS_AT) + x->mtl_rx_fifo_fill_above_thresh++; + else if (rxfsts == MTL_DEBUG_RXFSTS_BT) + x->mtl_rx_fifo_fill_below_thresh++; + else + x->mtl_rx_fifo_fill_level_empty++; + } + if (value & MTL_DEBUG_RRCSTS_MASK) { + u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >> + MTL_DEBUG_RRCSTS_SHIFT; + + if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH) + x->mtl_rx_fifo_read_ctrl_flush++; + else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT) + x->mtl_rx_fifo_read_ctrl_read_data++; + else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA) + x->mtl_rx_fifo_read_ctrl_status++; + else + x->mtl_rx_fifo_read_ctrl_idle++; + } + if (value & MTL_DEBUG_RWCSTS) + x->mtl_rx_fifo_ctrl_active++; } - if (value & MTL_DEBUG_RRCSTS_MASK) { - u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >> - MTL_DEBUG_RRCSTS_SHIFT; - - if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH) - x->mtl_rx_fifo_read_ctrl_flush++; - else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT) - x->mtl_rx_fifo_read_ctrl_read_data++; - else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA) - x->mtl_rx_fifo_read_ctrl_status++; - else - x->mtl_rx_fifo_read_ctrl_idle++; - } - if (value & MTL_DEBUG_RWCSTS) - x->mtl_rx_fifo_ctrl_active++; /* GMAC debug */ value = readl(ioaddr + GMAC_DEBUG); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 4a5dc896044f..61b9369a041e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -520,6 +520,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *dummy, u64 *data) { struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 tx_queues_count = priv->plat->tx_queues_to_use; int i, j = 0; /* Update the DMA HW counters for dwmac10/100 */ @@ -550,7 +552,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, if ((priv->hw->mac->debug) && (priv->synopsys_id >= DWMAC_CORE_3_50)) priv->hw->mac->debug(priv->ioaddr, - (void *)&priv->xstats); + (void *)&priv->xstats, + rx_queues_count, tx_queues_count); } for (i = 0; i < STMMAC_STATS_LEN; i++) { char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset; From 19d9187317979cf0c25f67017d2676149abc46b2 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 10 Mar 2017 18:24:59 +0000 Subject: [PATCH 173/399] net: stmmac: configuration of CBS in case of a TX AVB queue This patch adds the configuration of the AVB Credit-Based Shaper. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- .../devicetree/bindings/net/stmmac.txt | 22 +++++++-- drivers/net/ethernet/stmicro/stmmac/common.h | 4 ++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 33 +++++++++++++ .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 46 ++++++++++++++++++- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 29 ++++++++++++ .../ethernet/stmicro/stmmac/stmmac_platform.c | 29 ++++++++++-- include/linux/stmmac.h | 12 +++-- 7 files changed, 164 insertions(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index 04a258e2d4e0..a7b0e41cb264 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -92,8 +92,15 @@ Optional properties: - snps,tx-sched-dwrr: Deficit Weighted Round Robin - snps,tx-sched-sp: Strict priority - For each TX queue - - snps,weight: TX queue weight (if using a weighted algorithm) - + - snps,weight: TX queue weight (if using a DCB weight algorithm) + - Choose one of these modes: + - snps,dcb-algorithm: TX queue will be working in DCB + - snps,avb-algorithm: TX queue will be working in AVB + - Configure Credit Base Shaper (if AVB Mode selected): + - snps,send_slope: enable Low Power Interface + - snps,idle_slope: unlock on WoL + - snps,high_credit: max write outstanding req. limit + - snps,low_credit: max read outstanding req. limit Examples: stmmac_axi_setup: stmmac-axi-config { @@ -112,10 +119,19 @@ Examples: }; mtl_tx_setup: tx-queues-config { - snps,tx-queues-to-use = <1>; + snps,tx-queues-to-use = <2>; snps,tx-sched-wrr; queue0 { snps,weight = <0x10>; + snps,dcb-algorithm; + }; + + queue1 { + snps,avb-algorithm; + snps,send_slope = <0x1000>; + snps,idle_slope = <0x1000>; + snps,high_credit = <0x3E800>; + snps,low_credit = <0xFFC18000>; }; }; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index e7fb98569d2d..9f0d26da6813 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -467,6 +467,10 @@ struct stmmac_ops { u32 weight, u32 queue); /* RX MTL queue to RX dma mapping */ void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan); + /* Configure AV Algorithm */ + void (*config_cbs)(struct mac_device_info *hw, u32 send_slope, + u32 idle_slope, u32 high_credit, u32 low_credit, + u32 queue); /* Dump MAC registers */ void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space); /* Handle extra events on specific interrupts hw dependent */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 1ddf75c0eab5..54bcdb4d10db 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -233,6 +233,15 @@ enum power_event { #define MTL_OP_MODE_RTC_96 (2 << MTL_OP_MODE_RTC_SHIFT) #define MTL_OP_MODE_RTC_128 (3 << MTL_OP_MODE_RTC_SHIFT) +/* MTL ETS Control register */ +#define MTL_ETS_CTRL_BASE_ADDR 0x00000d10 +#define MTL_ETS_CTRL_BASE_OFFSET 0x40 +#define MTL_ETSX_CTRL_BASE_ADDR(x) (MTL_ETS_CTRL_BASE_ADDR + \ + ((x) * MTL_ETS_CTRL_BASE_OFFSET)) + +#define MTL_ETS_CTRL_CC BIT(3) +#define MTL_ETS_CTRL_AVALG BIT(2) + /* MTL Queue Quantum Weight */ #define MTL_TXQ_WEIGHT_BASE_ADDR 0x00000d18 #define MTL_TXQ_WEIGHT_BASE_OFFSET 0x40 @@ -240,6 +249,30 @@ enum power_event { ((x) * MTL_TXQ_WEIGHT_BASE_OFFSET)) #define MTL_TXQ_WEIGHT_ISCQW_MASK GENMASK(20, 0) +/* MTL sendSlopeCredit register */ +#define MTL_SEND_SLP_CRED_BASE_ADDR 0x00000d1c +#define MTL_SEND_SLP_CRED_OFFSET 0x40 +#define MTL_SEND_SLP_CREDX_BASE_ADDR(x) (MTL_SEND_SLP_CRED_BASE_ADDR + \ + ((x) * MTL_SEND_SLP_CRED_OFFSET)) + +#define MTL_SEND_SLP_CRED_SSC_MASK GENMASK(13, 0) + +/* MTL hiCredit register */ +#define MTL_HIGH_CRED_BASE_ADDR 0x00000d20 +#define MTL_HIGH_CRED_OFFSET 0x40 +#define MTL_HIGH_CREDX_BASE_ADDR(x) (MTL_HIGH_CRED_BASE_ADDR + \ + ((x) * MTL_HIGH_CRED_OFFSET)) + +#define MTL_HIGH_CRED_HC_MASK GENMASK(28, 0) + +/* MTL loCredit register */ +#define MTL_LOW_CRED_BASE_ADDR 0x00000d24 +#define MTL_LOW_CRED_OFFSET 0x40 +#define MTL_LOW_CREDX_BASE_ADDR(x) (MTL_LOW_CRED_BASE_ADDR + \ + ((x) * MTL_LOW_CRED_OFFSET)) + +#define MTL_HIGH_CRED_LC_MASK GENMASK(28, 0) + /* MTL debug */ #define MTL_DEBUG_TXSTSFSTS BIT(5) #define MTL_DEBUG_TXFSTS BIT(4) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 670cfee415fd..10599dbc232f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -66,9 +66,9 @@ static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 value = readl(ioaddr + GMAC_RXQ_CTRL0); value &= GMAC_RX_QUEUE_CLEAR(queue); - if (mode == MTL_RX_AVB) + if (mode == MTL_QUEUE_AVB) value |= GMAC_RX_AV_QUEUE_ENABLE(queue); - else if (mode == MTL_RX_DCB) + else if (mode == MTL_QUEUE_DCB) value |= GMAC_RX_DCB_QUEUE_ENABLE(queue); writel(value, ioaddr + GMAC_RXQ_CTRL0); @@ -155,6 +155,47 @@ static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan) writel(value, ioaddr + MTL_RXQ_DMA_MAP1); } +static void dwmac4_config_cbs(struct mac_device_info *hw, + u32 send_slope, u32 idle_slope, + u32 high_credit, u32 low_credit, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + pr_debug("Queue %d configured as AVB. Parameters:\n", queue); + pr_debug("\tsend_slope: 0x%08x\n", send_slope); + pr_debug("\tidle_slope: 0x%08x\n", idle_slope); + pr_debug("\thigh_credit: 0x%08x\n", high_credit); + pr_debug("\tlow_credit: 0x%08x\n", low_credit); + + /* enable AV algorithm */ + value = readl(ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue)); + value |= MTL_ETS_CTRL_AVALG; + value |= MTL_ETS_CTRL_CC; + writel(value, ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue)); + + /* configure send slope */ + value = readl(ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue)); + value &= ~MTL_SEND_SLP_CRED_SSC_MASK; + value |= send_slope & MTL_SEND_SLP_CRED_SSC_MASK; + writel(value, ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue)); + + /* configure idle slope (same register as tx weight) */ + dwmac4_set_mtl_tx_queue_weight(hw, idle_slope, queue); + + /* configure high credit */ + value = readl(ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue)); + value &= ~MTL_HIGH_CRED_HC_MASK; + value |= high_credit & MTL_HIGH_CRED_HC_MASK; + writel(value, ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue)); + + /* configure high credit */ + value = readl(ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue)); + value &= ~MTL_HIGH_CRED_LC_MASK; + value |= low_credit & MTL_HIGH_CRED_LC_MASK; + writel(value, ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue)); +} + static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space) { void __iomem *ioaddr = hw->pcsr; @@ -566,6 +607,7 @@ static const struct stmmac_ops dwmac4_ops = { .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, .map_mtl_to_dma = dwmac4_map_mtl_dma, + .config_cbs = dwmac4_config_cbs, .dump_regs = dwmac4_dump_regs, .host_irq_status = dwmac4_irq_status, .host_mtl_irq_status = dwmac4_irq_mtl_status, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2449487be534..915636ff2fc1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1670,6 +1670,31 @@ static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv) } } +/** + * stmmac_configure_cbs - Configure CBS in TX queue + * @priv: driver private structure + * Description: It is used for configuring CBS in AVB TX queues + */ +static void stmmac_configure_cbs(struct stmmac_priv *priv) +{ + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 mode_to_use; + u32 queue; + + for (queue = 0; queue < tx_queues_count; queue++) { + mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; + if (mode_to_use == MTL_QUEUE_DCB) + continue; + + priv->hw->mac->config_cbs(priv->hw, + priv->plat->tx_queues_cfg[queue].send_slope, + priv->plat->tx_queues_cfg[queue].idle_slope, + priv->plat->tx_queues_cfg[queue].high_credit, + priv->plat->tx_queues_cfg[queue].low_credit, + queue); + } +} + /** * stmmac_rx_queue_dma_chan_map - Map RX queue to RX dma channel * @priv: driver private structure @@ -1710,6 +1735,10 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) priv->hw->mac->prog_mtl_tx_algorithms(priv->hw, priv->plat->tx_sched_algorithm); + /* Configure CBS in AVB TX queues */ + if (tx_queues_count > 1 && priv->hw->mac->config_cbs) + stmmac_configure_cbs(priv); + /* Map RX MTL to DMA channels */ if (rx_queues_count > 1 && priv->hw->mac->map_mtl_to_dma) stmmac_rx_queue_dma_chan_map(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 0b76e3de502d..37f550ae76a5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -171,11 +171,11 @@ static void stmmac_mtl_setup(struct platform_device *pdev, break; if (of_property_read_bool(q_node, "snps,dcb-algorithm")) - plat->rx_queues_cfg[queue].mode_to_use = MTL_RX_DCB; + plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; else if (of_property_read_bool(q_node, "snps,avb-algorithm")) - plat->rx_queues_cfg[queue].mode_to_use = MTL_RX_AVB; + plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB; else - plat->rx_queues_cfg[queue].mode_to_use = MTL_RX_DCB; + plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; if (of_property_read_u8(q_node, "snps,map-to-dma-channel", &plat->rx_queues_cfg[queue].chan)) @@ -212,6 +212,29 @@ static void stmmac_mtl_setup(struct platform_device *pdev, &plat->tx_queues_cfg[queue].weight)) plat->tx_queues_cfg[queue].weight = 0x10 + queue; + if (of_property_read_bool(q_node, "snps,dcb-algorithm")) { + plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; + } else if (of_property_read_bool(q_node, + "snps,avb-algorithm")) { + plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB; + + /* Credit Base Shaper parameters used by AVB */ + if (of_property_read_u32(q_node, "snps,send_slope", + &plat->tx_queues_cfg[queue].send_slope)) + plat->tx_queues_cfg[queue].send_slope = 0x0; + if (of_property_read_u32(q_node, "snps,idle_slope", + &plat->tx_queues_cfg[queue].idle_slope)) + plat->tx_queues_cfg[queue].idle_slope = 0x0; + if (of_property_read_u32(q_node, "snps,high_credit", + &plat->tx_queues_cfg[queue].high_credit)) + plat->tx_queues_cfg[queue].high_credit = 0x0; + if (of_property_read_u32(q_node, "snps,low_credit", + &plat->tx_queues_cfg[queue].low_credit)) + plat->tx_queues_cfg[queue].low_credit = 0x0; + } else { + plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; + } + queue++; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 266ff2af91e5..be47b859e954 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -55,9 +55,9 @@ #define MTL_RX_ALGORITHM_SP 0x4 #define MTL_RX_ALGORITHM_WSP 0x5 -/* RX Queue Mode */ -#define MTL_RX_DCB 0x0 -#define MTL_RX_AVB 0x1 +/* RX/TX Queue Mode */ +#define MTL_QUEUE_DCB 0x0 +#define MTL_QUEUE_AVB 0x1 /* The MDC clock could be set higher than the IEEE 802.3 * specified frequency limit 0f 2.5 MHz, by programming a clock divider @@ -131,6 +131,12 @@ struct stmmac_rxq_cfg { struct stmmac_txq_cfg { u8 weight; + u8 mode_to_use; + /* Credit Base Shaper parameters */ + u32 send_slope; + u32 idle_slope; + u32 high_credit; + u32 low_credit; }; struct plat_stmmacenet_data { From 79c12a752cea61d41fd2f95600eaaaaafb99fe9e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:27 -0800 Subject: [PATCH 174/399] nfp: separate data path information from the reset of adapter structure Move all data path information into a separate structure. This way we will be able to allocate new data path with all new rings etc. and swap it in easily. No functional changes. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 105 +-- .../ethernet/netronome/nfp/nfp_net_common.c | 600 +++++++++--------- .../ethernet/netronome/nfp/nfp_net_debugfs.c | 4 +- .../ethernet/netronome/nfp/nfp_net_ethtool.c | 64 +- .../net/ethernet/netronome/nfp/nfp_net_main.c | 30 +- .../ethernet/netronome/nfp/nfp_net_offload.c | 30 +- .../ethernet/netronome/nfp/nfp_netvf_main.c | 15 +- 7 files changed, 435 insertions(+), 413 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 34f8c439f42f..7d2c38604372 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -50,14 +50,14 @@ #include "nfp_net_ctrl.h" -#define nn_err(nn, fmt, args...) netdev_err((nn)->netdev, fmt, ## args) -#define nn_warn(nn, fmt, args...) netdev_warn((nn)->netdev, fmt, ## args) -#define nn_info(nn, fmt, args...) netdev_info((nn)->netdev, fmt, ## args) -#define nn_dbg(nn, fmt, args...) netdev_dbg((nn)->netdev, fmt, ## args) -#define nn_warn_ratelimit(nn, fmt, args...) \ +#define nn_err(nn, fmt, args...) netdev_err((nn)->dp.netdev, fmt, ## args) +#define nn_warn(nn, fmt, args...) netdev_warn((nn)->dp.netdev, fmt, ## args) +#define nn_info(nn, fmt, args...) netdev_info((nn)->dp.netdev, fmt, ## args) +#define nn_dbg(nn, fmt, args...) netdev_dbg((nn)->dp.netdev, fmt, ## args) +#define nn_dp_warn(dp, fmt, args...) \ do { \ if (unlikely(net_ratelimit())) \ - netdev_warn((nn)->netdev, fmt, ## args); \ + netdev_warn((dp)->netdev, fmt, ## args); \ } while (0) /* Max time to wait for NFP to respond on updates (in seconds) */ @@ -434,18 +434,62 @@ struct nfp_stat_pair { }; /** - * struct nfp_net - NFP network device structure + * struct nfp_net_dp - NFP network device datapath data structure * @dev: Backpointer to struct device - * @netdev: Backpointer to net_device structure - * @is_vf: Is the driver attached to a VF? + * @netdev: Backpointer to net_device structure + * @is_vf: Is the driver attached to a VF? * @bpf_offload_skip_sw: Offloaded BPF program will not be rerun by cls_bpf * @bpf_offload_xdp: Offloaded BPF program is XDP * @chained_metadata_format: Firemware will use new metadata format - * @ctrl: Local copy of the control register/word. - * @fl_bufsz: Currently configured size of the freelist buffers + * @ctrl: Local copy of the control register/word. + * @fl_bufsz: Currently configured size of the freelist buffers * @rx_offset: Offset in the RX buffers where packet data starts * @xdp_prog: Installed XDP program - * @fw_ver: Firmware version + * @tx_rings: Array of pre-allocated TX ring structures + * @rx_rings: Array of pre-allocated RX ring structures + * + * @txd_cnt: Size of the TX ring in number of descriptors + * @rxd_cnt: Size of the RX ring in number of descriptors + * @num_r_vecs: Number of used ring vectors + * @num_tx_rings: Currently configured number of TX rings + * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP) + * @num_rx_rings: Currently configured number of RX rings + */ +struct nfp_net_dp { + struct device *dev; + struct net_device *netdev; + + unsigned is_vf:1; + unsigned bpf_offload_skip_sw:1; + unsigned bpf_offload_xdp:1; + unsigned chained_metadata_format:1; + + u32 ctrl; + u32 fl_bufsz; + + u32 rx_offset; + + struct bpf_prog *xdp_prog; + + struct nfp_net_tx_ring *tx_rings; + struct nfp_net_rx_ring *rx_rings; + + /* Cold data follows */ + + unsigned int txd_cnt; + unsigned int rxd_cnt; + + unsigned int num_r_vecs; + + unsigned int num_tx_rings; + unsigned int num_stack_tx_rings; + unsigned int num_rx_rings; +}; + +/** + * struct nfp_net - NFP network device structure + * @dp: Datapath structure + * @fw_ver: Firmware version * @cap: Capabilities advertised by the Firmware * @max_mtu: Maximum support MTU advertised by the Firmware * @rss_hfunc: RSS selected hash function @@ -457,17 +501,9 @@ struct nfp_stat_pair { * @rx_filter_change: Jiffies when statistics last changed * @rx_filter_stats_timer: Timer for polling filter offload statistics * @rx_filter_lock: Lock protecting timer state changes (teardown) + * @max_r_vecs: Number of allocated interrupt vectors for RX/TX * @max_tx_rings: Maximum number of TX rings supported by the Firmware * @max_rx_rings: Maximum number of RX rings supported by the Firmware - * @num_tx_rings: Currently configured number of TX rings - * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP) - * @num_rx_rings: Currently configured number of RX rings - * @txd_cnt: Size of the TX ring in number of descriptors - * @rxd_cnt: Size of the RX ring in number of descriptors - * @tx_rings: Array of pre-allocated TX ring structures - * @rx_rings: Array of pre-allocated RX ring structures - * @max_r_vecs: Number of allocated interrupt vectors for RX/TX - * @num_r_vecs: Number of used ring vectors * @r_vecs: Pre-allocated array of ring vectors * @irq_entries: Pre-allocated array of MSI-X entries * @lsc_handler: Handler for Link State Change interrupt @@ -502,25 +538,10 @@ struct nfp_stat_pair { * @eth_port: Translated ETH Table port entry */ struct nfp_net { - struct device *dev; - struct net_device *netdev; - - unsigned is_vf:1; - unsigned bpf_offload_skip_sw:1; - unsigned bpf_offload_xdp:1; - unsigned chained_metadata_format:1; - - u32 ctrl; - u32 fl_bufsz; - - u32 rx_offset; - - struct bpf_prog *xdp_prog; - - struct nfp_net_tx_ring *tx_rings; - struct nfp_net_rx_ring *rx_rings; + struct nfp_net_dp dp; struct nfp_net_fw_version fw_ver; + u32 cap; u32 max_mtu; @@ -537,18 +558,10 @@ struct nfp_net { unsigned int max_tx_rings; unsigned int max_rx_rings; - unsigned int num_tx_rings; - unsigned int num_stack_tx_rings; - unsigned int num_rx_rings; - int stride_tx; int stride_rx; - int txd_cnt; - int rxd_cnt; - unsigned int max_r_vecs; - unsigned int num_r_vecs; struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS]; struct msix_entry irq_entries[NFP_NET_MAX_IRQS]; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 2d964d030dbe..951d511643f1 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -86,18 +86,18 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver, } static dma_addr_t -nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz, +nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag, unsigned int bufsz, int direction) { - return dma_map_single(nn->dev, frag + NFP_NET_RX_BUF_HEADROOM, + return dma_map_single(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM, bufsz - NFP_NET_RX_BUF_NON_DATA, direction); } static void -nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr, +nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr, unsigned int bufsz, int direction) { - dma_unmap_single(nn->dev, dma_addr, + dma_unmap_single(dp->dev, dma_addr, bufsz - NFP_NET_RX_BUF_NON_DATA, direction); } @@ -329,19 +329,22 @@ void nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries, unsigned int n) { + struct nfp_net_dp *dp = &nn->dp; + nn->max_r_vecs = n - NFP_NET_NON_Q_VECTORS; - nn->num_r_vecs = nn->max_r_vecs; + dp->num_r_vecs = nn->max_r_vecs; memcpy(nn->irq_entries, irq_entries, sizeof(*irq_entries) * n); - if (nn->num_rx_rings > nn->num_r_vecs || - nn->num_tx_rings > nn->num_r_vecs) + if (dp->num_rx_rings > dp->num_r_vecs || + dp->num_tx_rings > dp->num_r_vecs) nn_warn(nn, "More rings (%d,%d) than vectors (%d).\n", - nn->num_rx_rings, nn->num_tx_rings, nn->num_r_vecs); + dp->num_rx_rings, dp->num_tx_rings, + dp->num_r_vecs); - nn->num_rx_rings = min(nn->num_r_vecs, nn->num_rx_rings); - nn->num_tx_rings = min(nn->num_r_vecs, nn->num_tx_rings); - nn->num_stack_tx_rings = nn->num_tx_rings; + dp->num_rx_rings = min(dp->num_r_vecs, dp->num_rx_rings); + dp->num_tx_rings = min(dp->num_r_vecs, dp->num_tx_rings); + dp->num_stack_tx_rings = dp->num_tx_rings; } /** @@ -396,11 +399,11 @@ static void nfp_net_read_link_status(struct nfp_net *nn) nn->link_up = link_up; if (nn->link_up) { - netif_carrier_on(nn->netdev); - netdev_info(nn->netdev, "NIC Link is Up\n"); + netif_carrier_on(nn->dp.netdev); + netdev_info(nn->dp.netdev, "NIC Link is Up\n"); } else { - netif_carrier_off(nn->netdev); - netdev_info(nn->netdev, "NIC Link is Down\n"); + netif_carrier_off(nn->dp.netdev); + netdev_info(nn->dp.netdev, "NIC Link is Down\n"); } out: spin_unlock_irqrestore(&nn->link_status_lock, flags); @@ -532,7 +535,7 @@ nfp_net_aux_irq_request(struct nfp_net *nn, u32 ctrl_offset, entry = &nn->irq_entries[vector_idx]; - snprintf(name, name_sz, format, netdev_name(nn->netdev)); + snprintf(name, name_sz, format, netdev_name(nn->dp.netdev)); err = request_irq(entry->vector, handler, 0, name, nn); if (err) { nn_err(nn, "Failed to request IRQ %d (err=%d).\n", @@ -619,7 +622,6 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q, /** * nfp_net_tx_tso() - Set up Tx descriptor for LSO - * @nn: NFP Net device * @r_vec: per-ring structure * @txbuf: Pointer to driver soft TX descriptor * @txd: Pointer to HW TX descriptor @@ -628,7 +630,7 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q, * Set up Tx descriptor for LSO, do nothing for non-LSO skbs. * Return error on packet header greater than maximum supported LSO header size. */ -static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, +static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec, struct nfp_net_tx_buf *txbuf, struct nfp_net_tx_desc *txd, struct sk_buff *skb) { @@ -659,7 +661,7 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, /** * nfp_net_tx_csum() - Set TX CSUM offload flags in TX descriptor - * @nn: NFP Net device + * @dp: NFP Net data path struct * @r_vec: per-ring structure * @txbuf: Pointer to driver soft TX descriptor * @txd: Pointer to TX descriptor @@ -668,7 +670,8 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, * This function sets the TX checksum flags in the TX descriptor based * on the configuration and the protocol of the packet to be transmitted. */ -static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, +static void nfp_net_tx_csum(struct nfp_net_dp *dp, + struct nfp_net_r_vector *r_vec, struct nfp_net_tx_buf *txbuf, struct nfp_net_tx_desc *txd, struct sk_buff *skb) { @@ -676,7 +679,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, struct iphdr *iph; u8 l4_hdr; - if (!(nn->ctrl & NFP_NET_CFG_CTRL_TXCSUM)) + if (!(dp->ctrl & NFP_NET_CFG_CTRL_TXCSUM)) return; if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -695,8 +698,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, } else if (ipv6h->version == 6) { l4_hdr = ipv6h->nexthdr; } else { - nn_warn_ratelimit(nn, "partial checksum but ipv=%x!\n", - iph->version); + nn_dp_warn(dp, "partial checksum but ipv=%x!\n", iph->version); return; } @@ -708,8 +710,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, txd->flags |= PCIE_DESC_TX_UDP_CSUM; break; default: - nn_warn_ratelimit(nn, "partial checksum but l4 proto=%x!\n", - l4_hdr); + nn_dp_warn(dp, "partial checksum but l4 proto=%x!\n", l4_hdr); return; } @@ -744,22 +745,24 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) struct nfp_net_r_vector *r_vec; struct nfp_net_tx_buf *txbuf; struct netdev_queue *nd_q; + struct nfp_net_dp *dp; dma_addr_t dma_addr; unsigned int fsize; int f, nr_frags; int wr_idx; u16 qidx; + dp = &nn->dp; qidx = skb_get_queue_mapping(skb); - tx_ring = &nn->tx_rings[qidx]; + tx_ring = &dp->tx_rings[qidx]; r_vec = tx_ring->r_vec; - nd_q = netdev_get_tx_queue(nn->netdev, qidx); + nd_q = netdev_get_tx_queue(dp->netdev, qidx); nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) { - nn_warn_ratelimit(nn, "TX ring %d busy. wrp=%u rdp=%u\n", - qidx, tx_ring->wr_p, tx_ring->rd_p); + nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n", + qidx, tx_ring->wr_p, tx_ring->rd_p); netif_tx_stop_queue(nd_q); u64_stats_update_begin(&r_vec->tx_sync); r_vec->tx_busy++; @@ -768,9 +771,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) } /* Start with the head skbuf */ - dma_addr = dma_map_single(nn->dev, skb->data, skb_headlen(skb), + dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); - if (dma_mapping_error(nn->dev, dma_addr)) + if (dma_mapping_error(dp->dev, dma_addr)) goto err_free; wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1); @@ -794,11 +797,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) txd->mss = 0; txd->l4_offset = 0; - nfp_net_tx_tso(nn, r_vec, txbuf, txd, skb); + nfp_net_tx_tso(r_vec, txbuf, txd, skb); - nfp_net_tx_csum(nn, r_vec, txbuf, txd, skb); + nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb); - if (skb_vlan_tag_present(skb) && nn->ctrl & NFP_NET_CFG_CTRL_TXVLAN) { + if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) { txd->flags |= PCIE_DESC_TX_VLAN; txd->vlan = cpu_to_le16(skb_vlan_tag_get(skb)); } @@ -812,9 +815,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[f]; fsize = skb_frag_size(frag); - dma_addr = skb_frag_dma_map(nn->dev, frag, 0, + dma_addr = skb_frag_dma_map(dp->dev, frag, 0, fsize, DMA_TO_DEVICE); - if (dma_mapping_error(nn->dev, dma_addr)) + if (dma_mapping_error(dp->dev, dma_addr)) goto err_unmap; wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1); @@ -853,7 +856,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) --f; while (f >= 0) { frag = &skb_shinfo(skb)->frags[f]; - dma_unmap_page(nn->dev, tx_ring->txbufs[wr_idx].dma_addr, + dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); tx_ring->txbufs[wr_idx].skb = NULL; tx_ring->txbufs[wr_idx].dma_addr = 0; @@ -862,13 +865,13 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) if (wr_idx < 0) wr_idx += tx_ring->cnt; } - dma_unmap_single(nn->dev, tx_ring->txbufs[wr_idx].dma_addr, + dma_unmap_single(dp->dev, tx_ring->txbufs[wr_idx].dma_addr, skb_headlen(skb), DMA_TO_DEVICE); tx_ring->txbufs[wr_idx].skb = NULL; tx_ring->txbufs[wr_idx].dma_addr = 0; tx_ring->txbufs[wr_idx].fidx = -2; err_free: - nn_warn_ratelimit(nn, "Failed to map DMA TX buffer\n"); + nn_dp_warn(dp, "Failed to map DMA TX buffer\n"); u64_stats_update_begin(&r_vec->tx_sync); r_vec->tx_errors++; u64_stats_update_end(&r_vec->tx_sync); @@ -885,7 +888,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; const struct skb_frag_struct *frag; struct netdev_queue *nd_q; u32 done_pkts = 0, done_bytes = 0; @@ -919,7 +922,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) if (fidx == -1) { /* unmap head */ - dma_unmap_single(nn->dev, tx_ring->txbufs[idx].dma_addr, + dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr, skb_headlen(skb), DMA_TO_DEVICE); done_pkts += tx_ring->txbufs[idx].pkt_cnt; @@ -927,7 +930,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) } else { /* unmap fragment */ frag = &skb_shinfo(skb)->frags[fidx]; - dma_unmap_page(nn->dev, tx_ring->txbufs[idx].dma_addr, + dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); } @@ -947,7 +950,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) r_vec->tx_pkts += done_pkts; u64_stats_update_end(&r_vec->tx_sync); - nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx); + nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx); netdev_tx_completed_queue(nd_q, done_pkts, done_bytes); if (nfp_net_tx_ring_should_wake(tx_ring)) { /* Make sure TX thread will see updated tx_ring->rd_p */ @@ -965,7 +968,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; u32 done_pkts = 0, done_bytes = 0; int idx, todo; u32 qcp_rd_p; @@ -988,8 +991,8 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) if (!tx_ring->txbufs[idx].frag) continue; - nfp_net_dma_unmap_rx(nn, tx_ring->txbufs[idx].dma_addr, - nn->fl_bufsz, DMA_BIDIRECTIONAL); + nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr, + dp->fl_bufsz, DMA_BIDIRECTIONAL); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); done_pkts++; @@ -1014,13 +1017,13 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) /** * nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers - * @nn: NFP Net device + * @dp: NFP Net data path struct * @tx_ring: TX ring structure * * Assumes that the device is stopped */ static void -nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) +nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; const struct skb_frag_struct *frag; @@ -1034,8 +1037,8 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) tx_buf = &tx_ring->txbufs[idx]; if (tx_ring == r_vec->xdp_ring) { - nfp_net_dma_unmap_rx(nn, tx_buf->dma_addr, - nn->fl_bufsz, DMA_BIDIRECTIONAL); + nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr, + dp->fl_bufsz, DMA_BIDIRECTIONAL); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); } else { struct sk_buff *skb = tx_ring->txbufs[idx].skb; @@ -1043,13 +1046,13 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) if (tx_buf->fidx == -1) { /* unmap head */ - dma_unmap_single(nn->dev, tx_buf->dma_addr, + dma_unmap_single(dp->dev, tx_buf->dma_addr, skb_headlen(skb), DMA_TO_DEVICE); } else { /* unmap fragment */ frag = &skb_shinfo(skb)->frags[tx_buf->fidx]; - dma_unmap_page(nn->dev, tx_buf->dma_addr, + dma_unmap_page(dp->dev, tx_buf->dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); } @@ -1076,7 +1079,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring) if (tx_ring == r_vec->xdp_ring) return; - nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx); + nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx); netdev_tx_reset_queue(nd_q); } @@ -1085,7 +1088,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); int i; - for (i = 0; i < nn->netdev->real_num_tx_queues; i++) { + for (i = 0; i < nn->dp.netdev->real_num_tx_queues; i++) { if (!netif_tx_queue_stopped(netdev_get_tx_queue(netdev, i))) continue; nn_warn(nn, "TX timeout on ring: %d\n", i); @@ -1096,15 +1099,15 @@ static void nfp_net_tx_timeout(struct net_device *netdev) /* Receive processing */ static unsigned int -nfp_net_calc_fl_bufsz(struct nfp_net *nn, unsigned int mtu) +nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp, unsigned int mtu) { unsigned int fl_bufsz; fl_bufsz = NFP_NET_RX_BUF_HEADROOM; - if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) + if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) fl_bufsz += NFP_NET_MAX_PREPEND; else - fl_bufsz += nn->rx_offset; + fl_bufsz += dp->rx_offset; fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu; fl_bufsz = SKB_DATA_ALIGN(fl_bufsz); @@ -1137,7 +1140,7 @@ static void * nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, unsigned int fl_bufsz, bool xdp) { - struct nfp_net *nn = rx_ring->r_vec->nfp_net; + struct nfp_net_dp *dp = &rx_ring->r_vec->nfp_net->dp; int direction; void *frag; @@ -1146,16 +1149,16 @@ nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, else frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD)); if (!frag) { - nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n"); + nn_dp_warn(dp, "Failed to alloc receive page frag\n"); return NULL; } direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - *dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction); - if (dma_mapping_error(nn->dev, *dma_addr)) { + *dma_addr = nfp_net_dma_map_rx(dp, frag, fl_bufsz, direction); + if (dma_mapping_error(dp->dev, *dma_addr)) { nfp_net_free_frag(frag, xdp); - nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n"); + nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); return NULL; } @@ -1163,23 +1166,24 @@ nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, } static void * -nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr) +nfp_net_napi_alloc_one(struct nfp_net_dp *dp, int direction, + dma_addr_t *dma_addr) { void *frag; - if (!nn->xdp_prog) - frag = napi_alloc_frag(nn->fl_bufsz); + if (!dp->xdp_prog) + frag = napi_alloc_frag(dp->fl_bufsz); else frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD)); if (!frag) { - nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n"); + nn_dp_warn(dp, "Failed to alloc receive page frag\n"); return NULL; } - *dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction); - if (dma_mapping_error(nn->dev, *dma_addr)) { - nfp_net_free_frag(frag, nn->xdp_prog); - nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n"); + *dma_addr = nfp_net_dma_map_rx(dp, frag, dp->fl_bufsz, direction); + if (dma_mapping_error(dp->dev, *dma_addr)) { + nfp_net_free_frag(frag, dp->xdp_prog); + nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); return NULL; } @@ -1247,7 +1251,7 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring) /** * nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring - * @nn: NFP Net device + * @dp: NFP Net data path struct * @rx_ring: RX ring to remove buffers from * @xdp: Whether XDP is enabled * @@ -1256,8 +1260,8 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring) * to restore required ring geometry. */ static void -nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, - bool xdp) +nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring, bool xdp) { int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; unsigned int i; @@ -1270,7 +1274,7 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, if (!rx_ring->rxbufs[i].frag) continue; - nfp_net_dma_unmap_rx(nn, rx_ring->rxbufs[i].dma_addr, + nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr, rx_ring->bufsz, direction); nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp); rx_ring->rxbufs[i].dma_addr = 0; @@ -1280,13 +1284,13 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, /** * nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW) - * @nn: NFP Net device + * @dp: NFP Net data path struct * @rx_ring: RX ring to remove buffers from * @xdp: Whether XDP is enabled */ static int -nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, - bool xdp) +nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring, bool xdp) { struct nfp_net_rx_buf *rxbufs; unsigned int i; @@ -1298,7 +1302,7 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr, rx_ring->bufsz, xdp); if (!rxbufs[i].frag) { - nfp_net_rx_ring_bufs_free(nn, rx_ring, xdp); + nfp_net_rx_ring_bufs_free(dp, rx_ring, xdp); return -ENOMEM; } } @@ -1335,17 +1339,18 @@ static int nfp_net_rx_csum_has_errors(u16 flags) /** * nfp_net_rx_csum() - set SKB checksum field based on RX descriptor flags - * @nn: NFP Net device + * @dp: NFP Net data path struct * @r_vec: per-ring structure * @rxd: Pointer to RX descriptor * @skb: Pointer to SKB */ -static void nfp_net_rx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, +static void nfp_net_rx_csum(struct nfp_net_dp *dp, + struct nfp_net_r_vector *r_vec, struct nfp_net_rx_desc *rxd, struct sk_buff *skb) { skb_checksum_none_assert(skb); - if (!(nn->netdev->features & NETIF_F_RXCSUM)) + if (!(dp->netdev->features & NETIF_F_RXCSUM)) return; if (nfp_net_rx_csum_has_errors(le16_to_cpu(rxd->rxd.flags))) { @@ -1462,7 +1467,7 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring, } static bool -nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, +nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, struct nfp_net_tx_ring *tx_ring, struct nfp_net_rx_buf *rxbuf, unsigned int pkt_off, unsigned int pkt_len) @@ -1478,7 +1483,7 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, return false; } - new_frag = nfp_net_napi_alloc_one(nn, DMA_BIDIRECTIONAL, &new_dma_addr); + new_frag = nfp_net_napi_alloc_one(dp, DMA_BIDIRECTIONAL, &new_dma_addr); if (unlikely(!new_frag)) { nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL); return false; @@ -1495,7 +1500,7 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring, txbuf->pkt_cnt = 1; txbuf->real_len = pkt_len; - dma_sync_single_for_device(nn->dev, rxbuf->dma_addr + pkt_off, + dma_sync_single_for_device(dp->dev, rxbuf->dma_addr + pkt_off, pkt_len, DMA_BIDIRECTIONAL); /* Build TX descriptor */ @@ -1538,7 +1543,7 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len) static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) { struct nfp_net_r_vector *r_vec = rx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; struct nfp_net_tx_ring *tx_ring; struct bpf_prog *xdp_prog; unsigned int true_bufsz; @@ -1548,9 +1553,9 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) int idx; rcu_read_lock(); - xdp_prog = READ_ONCE(nn->xdp_prog); + xdp_prog = READ_ONCE(dp->xdp_prog); rx_dma_map_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - true_bufsz = xdp_prog ? PAGE_SIZE : nn->fl_bufsz; + true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz; tx_ring = r_vec->xdp_ring; while (pkts_polled < budget) { @@ -1591,10 +1596,10 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) data_len = le16_to_cpu(rxd->rxd.data_len); pkt_len = data_len - meta_len; - if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) + if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) pkt_off = meta_len; else - pkt_off = nn->rx_offset; + pkt_off = dp->rx_offset; data_off = NFP_NET_RX_BUF_HEADROOM + pkt_off; /* Stats update */ @@ -1604,10 +1609,10 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) u64_stats_update_end(&r_vec->rx_sync); if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF && - nn->bpf_offload_xdp)) { + dp->bpf_offload_xdp)) { int act; - dma_sync_single_for_cpu(nn->dev, + dma_sync_single_for_cpu(dp->dev, rxbuf->dma_addr + pkt_off, pkt_len, DMA_BIDIRECTIONAL); act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off, @@ -1616,15 +1621,17 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) case XDP_PASS: break; case XDP_TX: - if (unlikely(!nfp_net_tx_xdp_buf(nn, rx_ring, + if (unlikely(!nfp_net_tx_xdp_buf(dp, rx_ring, tx_ring, rxbuf, - pkt_off, pkt_len))) - trace_xdp_exception(nn->netdev, xdp_prog, act); + pkt_off, + pkt_len))) + trace_xdp_exception(dp->netdev, + xdp_prog, act); continue; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: - trace_xdp_exception(nn->netdev, xdp_prog, act); + trace_xdp_exception(dp->netdev, xdp_prog, act); case XDP_DROP: nfp_net_rx_give_one(rx_ring, rxbuf->frag, rxbuf->dma_addr); @@ -1637,14 +1644,14 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL); continue; } - new_frag = nfp_net_napi_alloc_one(nn, rx_dma_map_dir, + new_frag = nfp_net_napi_alloc_one(dp, rx_dma_map_dir, &new_dma_addr); if (unlikely(!new_frag)) { nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb); continue; } - nfp_net_dma_unmap_rx(nn, rxbuf->dma_addr, nn->fl_bufsz, + nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr, dp->fl_bufsz, rx_dma_map_dir); nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr); @@ -1652,23 +1659,23 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) skb_reserve(skb, data_off); skb_put(skb, pkt_len); - if (!nn->chained_metadata_format) { - nfp_net_set_hash_desc(nn->netdev, skb, rxd); + if (!dp->chained_metadata_format) { + nfp_net_set_hash_desc(dp->netdev, skb, rxd); } else if (meta_len) { void *end; - end = nfp_net_parse_meta(nn->netdev, skb, meta_len); + end = nfp_net_parse_meta(dp->netdev, skb, meta_len); if (unlikely(end != skb->data)) { - nn_warn_ratelimit(nn, "invalid RX packet metadata\n"); + nn_dp_warn(dp, "invalid RX packet metadata\n"); nfp_net_rx_drop(r_vec, rx_ring, NULL, skb); continue; } } skb_record_rx_queue(skb, rx_ring->idx); - skb->protocol = eth_type_trans(skb, nn->netdev); + skb->protocol = eth_type_trans(skb, dp->netdev); - nfp_net_rx_csum(nn, r_vec, rxd, skb); + nfp_net_rx_csum(dp, r_vec, rxd, skb); if (rxd->rxd.flags & PCIE_DESC_RX_VLAN) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), @@ -1722,12 +1729,12 @@ static int nfp_net_poll(struct napi_struct *napi, int budget) static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; kfree(tx_ring->txbufs); if (tx_ring->txds) - dma_free_coherent(nn->dev, tx_ring->size, + dma_free_coherent(dp->dev, tx_ring->size, tx_ring->txds, tx_ring->dma); tx_ring->cnt = 0; @@ -1749,13 +1756,13 @@ static int nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; int sz; tx_ring->cnt = cnt; tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt; - tx_ring->txds = dma_zalloc_coherent(nn->dev, tx_ring->size, + tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); if (!tx_ring->txds) goto err_alloc; @@ -1766,7 +1773,7 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) goto err_alloc; if (!is_xdp) - netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask, + netif_set_xps_queue(dp->netdev, &r_vec->affinity_mask, tx_ring->idx); return 0; @@ -1813,17 +1820,16 @@ nfp_net_tx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s) { struct nfp_net_ring_set new = *s; - s->dcnt = nn->txd_cnt; - s->rings = nn->tx_rings; - s->n_rings = nn->num_tx_rings; + s->dcnt = nn->dp.txd_cnt; + s->rings = nn->dp.tx_rings; + s->n_rings = nn->dp.num_tx_rings; - nn->txd_cnt = new.dcnt; - nn->tx_rings = new.rings; - nn->num_tx_rings = new.n_rings; + nn->dp.txd_cnt = new.dcnt; + nn->dp.tx_rings = new.rings; + nn->dp.num_tx_rings = new.n_rings; } -static void -nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s) +static void nfp_net_tx_ring_set_free(struct nfp_net_ring_set *s) { struct nfp_net_tx_ring *rings = s->rings; unsigned int r; @@ -1841,12 +1847,12 @@ nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s) static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) { struct nfp_net_r_vector *r_vec = rx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; kfree(rx_ring->rxbufs); if (rx_ring->rxds) - dma_free_coherent(nn->dev, rx_ring->size, + dma_free_coherent(dp->dev, rx_ring->size, rx_ring->rxds, rx_ring->dma); rx_ring->cnt = 0; @@ -1869,14 +1875,14 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz, u32 cnt) { struct nfp_net_r_vector *r_vec = rx_ring->r_vec; - struct nfp_net *nn = r_vec->nfp_net; + struct nfp_net_dp *dp = &r_vec->nfp_net->dp; int sz; rx_ring->cnt = cnt; rx_ring->bufsz = fl_bufsz; rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt; - rx_ring->rxds = dma_zalloc_coherent(nn->dev, rx_ring->size, + rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->rxds) goto err_alloc; @@ -1897,7 +1903,7 @@ static struct nfp_net_rx_ring * nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, bool xdp) { - unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(nn, s->mtu); + unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, s->mtu); struct nfp_net_rx_ring *rings; unsigned int r; @@ -1911,7 +1917,7 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt)) goto err_free_prev; - if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r], xdp)) + if (nfp_net_rx_ring_bufs_alloc(&nn->dp, &rings[r], xdp)) goto err_free_ring; } @@ -1919,7 +1925,7 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, err_free_prev: while (r--) { - nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp); + nfp_net_rx_ring_bufs_free(&nn->dp, &rings[r], xdp); err_free_ring: nfp_net_rx_ring_free(&rings[r]); } @@ -1932,27 +1938,27 @@ nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s) { struct nfp_net_ring_set new = *s; - s->mtu = nn->netdev->mtu; - s->dcnt = nn->rxd_cnt; - s->rings = nn->rx_rings; - s->n_rings = nn->num_rx_rings; + s->mtu = nn->dp.netdev->mtu; + s->dcnt = nn->dp.rxd_cnt; + s->rings = nn->dp.rx_rings; + s->n_rings = nn->dp.num_rx_rings; - nn->netdev->mtu = new.mtu; - nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, new.mtu); - nn->rxd_cnt = new.dcnt; - nn->rx_rings = new.rings; - nn->num_rx_rings = new.n_rings; + nn->dp.netdev->mtu = new.mtu; + nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, new.mtu); + nn->dp.rxd_cnt = new.dcnt; + nn->dp.rx_rings = new.rings; + nn->dp.num_rx_rings = new.n_rings; } static void -nfp_net_rx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s, +nfp_net_rx_ring_set_free(struct nfp_net_dp *dp, struct nfp_net_ring_set *s, bool xdp) { struct nfp_net_rx_ring *rings = s->rings; unsigned int r; for (r = 0; r < s->n_rings; r++) { - nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp); + nfp_net_rx_ring_bufs_free(dp, &rings[r], xdp); nfp_net_rx_ring_free(&rings[r]); } @@ -1960,15 +1966,15 @@ nfp_net_rx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s, } static void -nfp_net_vector_assign_rings(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, - int idx) +nfp_net_vector_assign_rings(struct nfp_net_dp *dp, + struct nfp_net_r_vector *r_vec, int idx) { - r_vec->rx_ring = idx < nn->num_rx_rings ? &nn->rx_rings[idx] : NULL; + r_vec->rx_ring = idx < dp->num_rx_rings ? &dp->rx_rings[idx] : NULL; r_vec->tx_ring = - idx < nn->num_stack_tx_rings ? &nn->tx_rings[idx] : NULL; + idx < dp->num_stack_tx_rings ? &dp->tx_rings[idx] : NULL; - r_vec->xdp_ring = idx < nn->num_tx_rings - nn->num_stack_tx_rings ? - &nn->tx_rings[nn->num_stack_tx_rings + idx] : NULL; + r_vec->xdp_ring = idx < dp->num_tx_rings - dp->num_stack_tx_rings ? + &dp->tx_rings[dp->num_stack_tx_rings + idx] : NULL; } static int @@ -1978,11 +1984,11 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, int err; /* Setup NAPI */ - netif_napi_add(nn->netdev, &r_vec->napi, + netif_napi_add(nn->dp.netdev, &r_vec->napi, nfp_net_poll, NAPI_POLL_WEIGHT); snprintf(r_vec->name, sizeof(r_vec->name), - "%s-rxtx-%d", nn->netdev->name, idx); + "%s-rxtx-%d", nn->dp.netdev->name, idx); err = request_irq(r_vec->irq_vector, r_vec->handler, 0, r_vec->name, r_vec); if (err) { @@ -2053,13 +2059,13 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn) /* copy RX interrupt coalesce parameters */ value = (nn->rx_coalesce_max_frames << 16) | (factor * nn->rx_coalesce_usecs); - for (i = 0; i < nn->num_rx_rings; i++) + for (i = 0; i < nn->dp.num_rx_rings; i++) nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(i), value); /* copy TX interrupt coalesce parameters */ value = (nn->tx_coalesce_max_frames << 16) | (factor * nn->tx_coalesce_usecs); - for (i = 0; i < nn->num_tx_rings; i++) + for (i = 0; i < nn->dp.num_tx_rings; i++) nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(i), value); } @@ -2074,9 +2080,9 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn) static void nfp_net_write_mac_addr(struct nfp_net *nn) { nn_writel(nn, NFP_NET_CFG_MACADDR + 0, - get_unaligned_be32(nn->netdev->dev_addr)); + get_unaligned_be32(nn->dp.netdev->dev_addr)); nn_writew(nn, NFP_NET_CFG_MACADDR + 6, - get_unaligned_be16(nn->netdev->dev_addr + 4)); + get_unaligned_be16(nn->dp.netdev->dev_addr + 4)); } static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx) @@ -2100,7 +2106,7 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn) unsigned int r; int err; - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; new_ctrl &= ~NFP_NET_CFG_CTRL_ENABLE; update = NFP_NET_CFG_UPDATE_GEN; update |= NFP_NET_CFG_UPDATE_MSIX; @@ -2117,14 +2123,14 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn) if (err) nn_err(nn, "Could not disable device: %d\n", err); - for (r = 0; r < nn->num_rx_rings; r++) - nfp_net_rx_ring_reset(&nn->rx_rings[r]); - for (r = 0; r < nn->num_tx_rings; r++) - nfp_net_tx_ring_reset(nn, &nn->tx_rings[r]); - for (r = 0; r < nn->num_r_vecs; r++) + for (r = 0; r < nn->dp.num_rx_rings; r++) + nfp_net_rx_ring_reset(&nn->dp.rx_rings[r]); + for (r = 0; r < nn->dp.num_tx_rings; r++) + nfp_net_tx_ring_reset(&nn->dp, &nn->dp.tx_rings[r]); + for (r = 0; r < nn->dp.num_r_vecs; r++) nfp_net_vec_clear_ring_data(nn, r); - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; } static void @@ -2152,7 +2158,7 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn) unsigned int r; int err; - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; if (nn->cap & NFP_NET_CFG_CTRL_RSS) { nfp_net_rss_write_key(nn); @@ -2168,22 +2174,22 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn) update |= NFP_NET_CFG_UPDATE_IRQMOD; } - for (r = 0; r < nn->num_tx_rings; r++) - nfp_net_tx_ring_hw_cfg_write(nn, &nn->tx_rings[r], r); - for (r = 0; r < nn->num_rx_rings; r++) - nfp_net_rx_ring_hw_cfg_write(nn, &nn->rx_rings[r], r); + for (r = 0; r < nn->dp.num_tx_rings; r++) + nfp_net_tx_ring_hw_cfg_write(nn, &nn->dp.tx_rings[r], r); + for (r = 0; r < nn->dp.num_rx_rings; r++) + nfp_net_rx_ring_hw_cfg_write(nn, &nn->dp.rx_rings[r], r); - nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ? - 0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1); + nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->dp.num_tx_rings == 64 ? + 0xffffffffffffffffULL : ((u64)1 << nn->dp.num_tx_rings) - 1); - nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ? - 0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1); + nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->dp.num_rx_rings == 64 ? + 0xffffffffffffffffULL : ((u64)1 << nn->dp.num_rx_rings) - 1); nfp_net_write_mac_addr(nn); - nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu); + nn_writel(nn, NFP_NET_CFG_MTU, nn->dp.netdev->mtu); nn_writel(nn, NFP_NET_CFG_FLBUFSZ, - nn->fl_bufsz - NFP_NET_RX_BUF_NON_DATA); + nn->dp.fl_bufsz - NFP_NET_RX_BUF_NON_DATA); /* Enable device */ new_ctrl |= NFP_NET_CFG_CTRL_ENABLE; @@ -2196,18 +2202,18 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn) nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); err = nfp_net_reconfig(nn, update); - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; - for (r = 0; r < nn->num_rx_rings; r++) - nfp_net_rx_ring_fill_freelist(&nn->rx_rings[r]); + for (r = 0; r < nn->dp.num_rx_rings; r++) + nfp_net_rx_ring_fill_freelist(&nn->dp.rx_rings[r]); /* Since reconfiguration requests while NFP is down are ignored we * have to wipe the entire VXLAN configuration and reinitialize it. */ - if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) { + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN) { memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports)); memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt)); - udp_tunnel_get_rx_info(nn->netdev); + udp_tunnel_get_rx_info(nn->dp.netdev); } return err; @@ -2236,12 +2242,12 @@ static void nfp_net_open_stack(struct nfp_net *nn) { unsigned int r; - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { napi_enable(&nn->r_vecs[r].napi); enable_irq(nn->r_vecs[r].irq_vector); } - netif_tx_wake_all_queues(nn->netdev); + netif_tx_wake_all_queues(nn->dp.netdev); enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); nfp_net_read_link_status(nn); @@ -2251,18 +2257,18 @@ static int nfp_net_netdev_open(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, - .mtu = nn->netdev->mtu, - .dcnt = nn->rxd_cnt, + .n_rings = nn->dp.num_rx_rings, + .mtu = nn->dp.netdev->mtu, + .dcnt = nn->dp.rxd_cnt, }; struct nfp_net_ring_set tx = { - .n_rings = nn->num_tx_rings, - .dcnt = nn->txd_cnt, + .n_rings = nn->dp.num_tx_rings, + .dcnt = nn->dp.txd_cnt, }; int err, r; - if (nn->ctrl & NFP_NET_CFG_CTRL_ENABLE) { - nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->ctrl); + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_ENABLE) { + nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->dp.ctrl); return -EBUSY; } @@ -2283,33 +2289,33 @@ static int nfp_net_netdev_open(struct net_device *netdev) goto err_free_exn; disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r); if (err) goto err_cleanup_vec_p; } - nn->rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->xdp_prog); - if (!nn->rx_rings) { + nn->dp.rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->dp.xdp_prog); + if (!nn->dp.rx_rings) { err = -ENOMEM; goto err_cleanup_vec; } - nn->tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx, - nn->num_stack_tx_rings); - if (!nn->tx_rings) { + nn->dp.tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx, + nn->dp.num_stack_tx_rings); + if (!nn->dp.tx_rings) { err = -ENOMEM; goto err_free_rx_rings; } for (r = 0; r < nn->max_r_vecs; r++) - nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r); + nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r); - err = netif_set_real_num_tx_queues(netdev, nn->num_stack_tx_rings); + err = netif_set_real_num_tx_queues(netdev, nn->dp.num_stack_tx_rings); if (err) goto err_free_rings; - err = netif_set_real_num_rx_queues(netdev, nn->num_rx_rings); + err = netif_set_real_num_rx_queues(netdev, nn->dp.num_rx_rings); if (err) goto err_free_rings; @@ -2335,11 +2341,11 @@ static int nfp_net_netdev_open(struct net_device *netdev) return 0; err_free_rings: - nfp_net_tx_ring_set_free(nn, &tx); + nfp_net_tx_ring_set_free(&tx); err_free_rx_rings: - nfp_net_rx_ring_set_free(nn, &rx, nn->xdp_prog); + nfp_net_rx_ring_set_free(&nn->dp, &rx, nn->dp.xdp_prog); err_cleanup_vec: - r = nn->num_r_vecs; + r = nn->dp.num_r_vecs; err_cleanup_vec_p: while (r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); @@ -2358,15 +2364,15 @@ static void nfp_net_close_stack(struct nfp_net *nn) unsigned int r; disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); - netif_carrier_off(nn->netdev); + netif_carrier_off(nn->dp.netdev); nn->link_up = false; - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { disable_irq(nn->r_vecs[r].irq_vector); napi_disable(&nn->r_vecs[r].napi); } - netif_tx_disable(nn->netdev); + netif_tx_disable(nn->dp.netdev); } /** @@ -2377,17 +2383,18 @@ static void nfp_net_close_free_all(struct nfp_net *nn) { unsigned int r; - for (r = 0; r < nn->num_rx_rings; r++) { - nfp_net_rx_ring_bufs_free(nn, &nn->rx_rings[r], nn->xdp_prog); - nfp_net_rx_ring_free(&nn->rx_rings[r]); + for (r = 0; r < nn->dp.num_rx_rings; r++) { + nfp_net_rx_ring_bufs_free(&nn->dp, &nn->dp.rx_rings[r], + nn->dp.xdp_prog); + nfp_net_rx_ring_free(&nn->dp.rx_rings[r]); } - for (r = 0; r < nn->num_tx_rings; r++) - nfp_net_tx_ring_free(&nn->tx_rings[r]); - for (r = 0; r < nn->num_r_vecs; r++) + for (r = 0; r < nn->dp.num_tx_rings; r++) + nfp_net_tx_ring_free(&nn->dp.tx_rings[r]); + for (r = 0; r < nn->dp.num_r_vecs; r++) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); - kfree(nn->rx_rings); - kfree(nn->tx_rings); + kfree(nn->dp.rx_rings); + kfree(nn->dp.tx_rings); nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX); nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX); @@ -2401,8 +2408,8 @@ static int nfp_net_netdev_close(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - if (!(nn->ctrl & NFP_NET_CFG_CTRL_ENABLE)) { - nn_err(nn, "Dev is not up: 0x%08x\n", nn->ctrl); + if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_ENABLE)) { + nn_err(nn, "Dev is not up: 0x%08x\n", nn->dp.ctrl); return 0; } @@ -2427,7 +2434,7 @@ static void nfp_net_set_rx_mode(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); u32 new_ctrl; - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; if (netdev->flags & IFF_PROMISC) { if (nn->cap & NFP_NET_CFG_CTRL_PROMISC) @@ -2438,13 +2445,13 @@ static void nfp_net_set_rx_mode(struct net_device *netdev) new_ctrl &= ~NFP_NET_CFG_CTRL_PROMISC; } - if (new_ctrl == nn->ctrl) + if (new_ctrl == nn->dp.ctrl) return; nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); nfp_net_reconfig_post(nn, NFP_NET_CFG_UPDATE_GEN); - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; } static void nfp_net_rss_init_itbl(struct nfp_net *nn) @@ -2453,7 +2460,7 @@ static void nfp_net_rss_init_itbl(struct nfp_net *nn) for (i = 0; i < sizeof(nn->rss_itbl); i++) nn->rss_itbl[i] = - ethtool_rxfh_indir_default(i, nn->num_rx_rings); + ethtool_rxfh_indir_default(i, nn->dp.num_rx_rings); } static int @@ -2471,24 +2478,23 @@ nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs, if (tx) nfp_net_tx_ring_set_swap(nn, tx); - swap(*num_vecs, nn->num_r_vecs); - swap(*stack_tx_rings, nn->num_stack_tx_rings); - *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog); + swap(*num_vecs, nn->dp.num_r_vecs); + swap(*stack_tx_rings, nn->dp.num_stack_tx_rings); + *xdp_prog = xchg(&nn->dp.xdp_prog, *xdp_prog); for (r = 0; r < nn->max_r_vecs; r++) - nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r); + nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r); - if (!netif_is_rxfh_configured(nn->netdev)) + if (!netif_is_rxfh_configured(nn->dp.netdev)) nfp_net_rss_init_itbl(nn); - err = netif_set_real_num_rx_queues(nn->netdev, - nn->num_rx_rings); + err = netif_set_real_num_rx_queues(nn->dp.netdev, nn->dp.num_rx_rings); if (err) return err; - if (nn->netdev->real_num_tx_queues != nn->num_stack_tx_rings) { - err = netif_set_real_num_tx_queues(nn->netdev, - nn->num_stack_tx_rings); + if (nn->dp.netdev->real_num_tx_queues != nn->dp.num_stack_tx_rings) { + err = netif_set_real_num_tx_queues(nn->dp.netdev, + nn->dp.num_stack_tx_rings); if (err) return err; } @@ -2503,7 +2509,7 @@ nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog, /* XDP-enabled tests */ if (!xdp_prog) return 0; - if (rx && nfp_net_calc_fl_bufsz(nn, rx->mtu) > PAGE_SIZE) { + if (rx && nfp_net_calc_fl_bufsz(&nn->dp, rx->mtu) > PAGE_SIZE) { nn_warn(nn, "MTU too large w/ XDP enabled\n"); return -EINVAL; } @@ -2521,17 +2527,17 @@ nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog, struct nfp_net_ring_set *tx, unsigned int stack_tx_rings, unsigned int num_vecs) { - nn->netdev->mtu = rx ? rx->mtu : nn->netdev->mtu; - nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, nn->netdev->mtu); - nn->rxd_cnt = rx ? rx->dcnt : nn->rxd_cnt; - nn->txd_cnt = tx ? tx->dcnt : nn->txd_cnt; - nn->num_rx_rings = rx ? rx->n_rings : nn->num_rx_rings; - nn->num_tx_rings = tx ? tx->n_rings : nn->num_tx_rings; - nn->num_stack_tx_rings = stack_tx_rings; - nn->num_r_vecs = num_vecs; - *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog); + nn->dp.netdev->mtu = rx ? rx->mtu : nn->dp.netdev->mtu; + nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, nn->dp.netdev->mtu); + nn->dp.rxd_cnt = rx ? rx->dcnt : nn->dp.rxd_cnt; + nn->dp.txd_cnt = tx ? tx->dcnt : nn->dp.txd_cnt; + nn->dp.num_rx_rings = rx ? rx->n_rings : nn->dp.num_rx_rings; + nn->dp.num_tx_rings = tx ? tx->n_rings : nn->dp.num_tx_rings; + nn->dp.num_stack_tx_rings = stack_tx_rings; + nn->dp.num_r_vecs = num_vecs; + *xdp_prog = xchg(&nn->dp.xdp_prog, *xdp_prog); - if (!netif_is_rxfh_configured(nn->netdev)) + if (!netif_is_rxfh_configured(nn->dp.netdev)) nfp_net_rss_init_itbl(nn); } @@ -2542,24 +2548,24 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, unsigned int stack_tx_rings, num_vecs, r; int err; - stack_tx_rings = tx ? tx->n_rings : nn->num_tx_rings; + stack_tx_rings = tx ? tx->n_rings : nn->dp.num_tx_rings; if (*xdp_prog) - stack_tx_rings -= rx ? rx->n_rings : nn->num_rx_rings; + stack_tx_rings -= rx ? rx->n_rings : nn->dp.num_rx_rings; - num_vecs = max(rx ? rx->n_rings : nn->num_rx_rings, stack_tx_rings); + num_vecs = max(rx ? rx->n_rings : nn->dp.num_rx_rings, stack_tx_rings); err = nfp_net_check_config(nn, *xdp_prog, rx, tx); if (err) return err; - if (!netif_running(nn->netdev)) { + if (!netif_running(nn->dp.netdev)) { nfp_net_ring_reconfig_down(nn, xdp_prog, rx, tx, stack_tx_rings, num_vecs); return 0; } /* Prepare new rings */ - for (r = nn->num_r_vecs; r < num_vecs; r++) { + for (r = nn->dp.num_r_vecs; r < num_vecs; r++) { err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r); if (err) { num_vecs = r; @@ -2597,13 +2603,13 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n", err, err2); } - for (r = num_vecs - 1; r >= nn->num_r_vecs; r--) + for (r = num_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); if (rx) - nfp_net_rx_ring_set_free(nn, rx, *xdp_prog); + nfp_net_rx_ring_set_free(&nn->dp, rx, *xdp_prog); if (tx) - nfp_net_tx_ring_set_free(nn, tx); + nfp_net_tx_ring_set_free(tx); nfp_net_open_stack(nn); @@ -2611,9 +2617,9 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, err_free_rx: if (rx) - nfp_net_rx_ring_set_free(nn, rx, *xdp_prog); + nfp_net_rx_ring_set_free(&nn->dp, rx, *xdp_prog); err_cleanup_vecs: - for (r = num_vecs - 1; r >= nn->num_r_vecs; r--) + for (r = num_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); return err; } @@ -2622,12 +2628,12 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) { struct nfp_net *nn = netdev_priv(netdev); struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, + .n_rings = nn->dp.num_rx_rings, .mtu = new_mtu, - .dcnt = nn->rxd_cnt, + .dcnt = nn->dp.rxd_cnt, }; - return nfp_net_ring_reconfig(nn, &nn->xdp_prog, &rx, NULL); + return nfp_net_ring_reconfig(nn, &nn->dp.xdp_prog, &rx, NULL); } static void nfp_net_stat64(struct net_device *netdev, @@ -2636,7 +2642,7 @@ static void nfp_net_stat64(struct net_device *netdev, struct nfp_net *nn = netdev_priv(netdev); int r; - for (r = 0; r < nn->num_r_vecs; r++) { + for (r = 0; r < nn->dp.num_r_vecs; r++) { struct nfp_net_r_vector *r_vec = &nn->r_vecs[r]; u64 data[3]; unsigned int start; @@ -2683,7 +2689,7 @@ nfp_net_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, return -ENOTSUPP; if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn)) { - if (!nn->bpf_offload_xdp) + if (!nn->dp.bpf_offload_xdp) return nfp_net_bpf_offload(nn, tc->cls_bpf); else return -EBUSY; @@ -2702,7 +2708,7 @@ static int nfp_net_set_features(struct net_device *netdev, /* Assume this is not called with features we have not advertised */ - new_ctrl = nn->ctrl; + new_ctrl = nn->dp.ctrl; if (changed & NETIF_F_RXCSUM) { if (features & NETIF_F_RXCSUM) @@ -2746,7 +2752,7 @@ static int nfp_net_set_features(struct net_device *netdev, new_ctrl &= ~NFP_NET_CFG_CTRL_GATHER; } - if (changed & NETIF_F_HW_TC && nn->ctrl & NFP_NET_CFG_CTRL_BPF) { + if (changed & NETIF_F_HW_TC && nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) { nn_err(nn, "Cannot disable HW TC offload while in use\n"); return -EBUSY; } @@ -2754,16 +2760,16 @@ static int nfp_net_set_features(struct net_device *netdev, nn_dbg(nn, "Feature change 0x%llx -> 0x%llx (changed=0x%llx)\n", netdev->features, features, changed); - if (new_ctrl == nn->ctrl) + if (new_ctrl == nn->dp.ctrl) return 0; - nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->ctrl, new_ctrl); + nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->dp.ctrl, new_ctrl); nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN); if (err) return err; - nn->ctrl = new_ctrl; + nn->dp.ctrl = new_ctrl; return 0; } @@ -2846,7 +2852,7 @@ static void nfp_net_set_vxlan_port(struct nfp_net *nn, int idx, __be16 port) nn->vxlan_ports[idx] = port; - if (!(nn->ctrl & NFP_NET_CFG_CTRL_VXLAN)) + if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN)) return; BUILD_BUG_ON(NFP_NET_N_VXLAN_PORTS & 1); @@ -2925,8 +2931,8 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog) if (!nfp_net_ebpf_capable(nn)) return -EINVAL; - if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) { - if (!nn->bpf_offload_xdp) + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) { + if (!nn->dp.bpf_offload_xdp) return prog ? -EBUSY : 0; cmd.command = prog ? TC_CLSBPF_REPLACE : TC_CLSBPF_DESTROY; } else { @@ -2939,20 +2945,20 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog) /* Stop offload if replace not possible */ if (ret && cmd.command == TC_CLSBPF_REPLACE) nfp_net_xdp_offload(nn, NULL); - nn->bpf_offload_xdp = prog && !ret; + nn->dp.bpf_offload_xdp = prog && !ret; return ret; } static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) { struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, - .mtu = nn->netdev->mtu, - .dcnt = nn->rxd_cnt, + .n_rings = nn->dp.num_rx_rings, + .mtu = nn->dp.netdev->mtu, + .dcnt = nn->dp.rxd_cnt, }; struct nfp_net_ring_set tx = { - .n_rings = nn->num_tx_rings, - .dcnt = nn->txd_cnt, + .n_rings = nn->dp.num_tx_rings, + .dcnt = nn->dp.txd_cnt, }; int err; @@ -2960,16 +2966,16 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) nn_err(nn, "Does not support bpf_xdp_adjust_head()\n"); return -EOPNOTSUPP; } - if (!prog && !nn->xdp_prog) + if (!prog && !nn->dp.xdp_prog) return 0; - if (prog && nn->xdp_prog) { - prog = xchg(&nn->xdp_prog, prog); + if (prog && nn->dp.xdp_prog) { + prog = xchg(&nn->dp.xdp_prog, prog); bpf_prog_put(prog); - nfp_net_xdp_offload(nn, nn->xdp_prog); + nfp_net_xdp_offload(nn, nn->dp.xdp_prog); return 0; } - tx.n_rings += prog ? nn->num_rx_rings : -nn->num_rx_rings; + tx.n_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */ err = nfp_net_ring_reconfig(nn, &prog, &rx, &tx); @@ -2980,7 +2986,7 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) if (prog) bpf_prog_put(prog); - nfp_net_xdp_offload(nn, nn->xdp_prog); + nfp_net_xdp_offload(nn, nn->dp.xdp_prog); return 0; } @@ -2993,7 +2999,7 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp) case XDP_SETUP_PROG: return nfp_net_xdp_setup(nn, xdp->prog); case XDP_QUERY_PROG: - xdp->prog_attached = !!nn->xdp_prog; + xdp->prog_attached = !!nn->dp.xdp_prog; return 0; default: return -EINVAL; @@ -3025,9 +3031,9 @@ static const struct net_device_ops nfp_net_netdev_ops = { void nfp_net_info(struct nfp_net *nn) { nn_info(nn, "Netronome NFP-6xxx %sNetdev: TxQs=%d/%d RxQs=%d/%d\n", - nn->is_vf ? "VF " : "", - nn->num_tx_rings, nn->max_tx_rings, - nn->num_rx_rings, nn->max_rx_rings); + nn->dp.is_vf ? "VF " : "", + nn->dp.num_tx_rings, nn->max_tx_rings, + nn->dp.num_rx_rings, nn->max_rx_rings); nn_info(nn, "VER: %d.%d.%d.%d, Maximum supported MTU: %d\n", nn->fw_ver.resv, nn->fw_ver.class, nn->fw_ver.major, nn->fw_ver.minor, @@ -3079,22 +3085,24 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev, SET_NETDEV_DEV(netdev, &pdev->dev); nn = netdev_priv(netdev); - nn->netdev = netdev; - nn->dev = &pdev->dev; + nn->dp.netdev = netdev; + nn->dp.dev = &pdev->dev; nn->pdev = pdev; nn->max_tx_rings = max_tx_rings; nn->max_rx_rings = max_rx_rings; - nn->num_tx_rings = min_t(unsigned int, max_tx_rings, num_online_cpus()); - nn->num_rx_rings = min_t(unsigned int, max_rx_rings, + nn->dp.num_tx_rings = min_t(unsigned int, + max_tx_rings, num_online_cpus()); + nn->dp.num_rx_rings = min_t(unsigned int, max_rx_rings, netif_get_num_default_rss_queues()); - nn->num_r_vecs = max(nn->num_tx_rings, nn->num_rx_rings); - nn->num_r_vecs = min_t(unsigned int, nn->num_r_vecs, num_online_cpus()); + nn->dp.num_r_vecs = max(nn->dp.num_tx_rings, nn->dp.num_rx_rings); + nn->dp.num_r_vecs = min_t(unsigned int, + nn->dp.num_r_vecs, num_online_cpus()); - nn->txd_cnt = NFP_NET_TX_DESCS_DEFAULT; - nn->rxd_cnt = NFP_NET_RX_DESCS_DEFAULT; + nn->dp.txd_cnt = NFP_NET_TX_DESCS_DEFAULT; + nn->dp.rxd_cnt = NFP_NET_RX_DESCS_DEFAULT; spin_lock_init(&nn->reconfig_lock); spin_lock_init(&nn->rx_filter_lock); @@ -3114,7 +3122,7 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev, */ void nfp_net_netdev_free(struct nfp_net *nn) { - free_netdev(nn->netdev); + free_netdev(nn->dp.netdev); } /** @@ -3156,7 +3164,7 @@ static void nfp_net_rss_init(struct nfp_net *nn) func_bit = find_first_bit(&rss_cap_hfunc, NFP_NET_CFG_RSS_HFUNCS); if (func_bit == NFP_NET_CFG_RSS_HFUNCS) { - dev_warn(nn->dev, + dev_warn(nn->dp.dev, "Bad RSS config, defaulting to Toeplitz hash\n"); func_bit = ETH_RSS_HASH_TOP_BIT; } @@ -3196,7 +3204,7 @@ int nfp_net_netdev_init(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); int err; - nn->chained_metadata_format = nn->fw_ver.major > 3; + nn->dp.chained_metadata_format = nn->fw_ver.major > 3; /* Get some of the read-only fields from the BAR */ nn->cap = nn_readl(nn, NFP_NET_CFG_CAP); @@ -3206,16 +3214,16 @@ int nfp_net_netdev_init(struct net_device *netdev) /* Determine RX packet/metadata boundary offset */ if (nn->fw_ver.major >= 2) - nn->rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET); + nn->dp.rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET); else - nn->rx_offset = NFP_NET_RX_OFFSET; + nn->dp.rx_offset = NFP_NET_RX_OFFSET; /* Set default MTU and Freelist buffer size */ if (nn->max_mtu < NFP_NET_DEFAULT_MTU) netdev->mtu = nn->max_mtu; else netdev->mtu = NFP_NET_DEFAULT_MTU; - nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, netdev->mtu); + nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, netdev->mtu); /* Advertise/enable offloads based on capabilities * @@ -3226,31 +3234,31 @@ int nfp_net_netdev_init(struct net_device *netdev) netdev->hw_features = NETIF_F_HIGHDMA; if (nn->cap & NFP_NET_CFG_CTRL_RXCSUM) { netdev->hw_features |= NETIF_F_RXCSUM; - nn->ctrl |= NFP_NET_CFG_CTRL_RXCSUM; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXCSUM; } if (nn->cap & NFP_NET_CFG_CTRL_TXCSUM) { netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - nn->ctrl |= NFP_NET_CFG_CTRL_TXCSUM; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXCSUM; } if (nn->cap & NFP_NET_CFG_CTRL_GATHER) { netdev->hw_features |= NETIF_F_SG; - nn->ctrl |= NFP_NET_CFG_CTRL_GATHER; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_GATHER; } if ((nn->cap & NFP_NET_CFG_CTRL_LSO) && nn->fw_ver.major > 2) { netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; - nn->ctrl |= NFP_NET_CFG_CTRL_LSO; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_LSO; } if (nn->cap & NFP_NET_CFG_CTRL_RSS) { netdev->hw_features |= NETIF_F_RXHASH; nfp_net_rss_init(nn); - nn->ctrl |= NFP_NET_CFG_CTRL_RSS; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_RSS; } if (nn->cap & NFP_NET_CFG_CTRL_VXLAN && nn->cap & NFP_NET_CFG_CTRL_NVGRE) { if (nn->cap & NFP_NET_CFG_CTRL_LSO) netdev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL; - nn->ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE; netdev->hw_enc_features = netdev->hw_features; } @@ -3259,11 +3267,11 @@ int nfp_net_netdev_init(struct net_device *netdev) if (nn->cap & NFP_NET_CFG_CTRL_RXVLAN) { netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; - nn->ctrl |= NFP_NET_CFG_CTRL_RXVLAN; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXVLAN; } if (nn->cap & NFP_NET_CFG_CTRL_TXVLAN) { netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; - nn->ctrl |= NFP_NET_CFG_CTRL_TXVLAN; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXVLAN; } netdev->features = netdev->hw_features; @@ -3276,14 +3284,14 @@ int nfp_net_netdev_init(struct net_device *netdev) /* Allow L2 Broadcast and Multicast through by default, if supported */ if (nn->cap & NFP_NET_CFG_CTRL_L2BC) - nn->ctrl |= NFP_NET_CFG_CTRL_L2BC; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2BC; if (nn->cap & NFP_NET_CFG_CTRL_L2MC) - nn->ctrl |= NFP_NET_CFG_CTRL_L2MC; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2MC; /* Allow IRQ moderation, if supported */ if (nn->cap & NFP_NET_CFG_CTRL_IRQMOD) { nfp_net_irqmod_init(nn); - nn->ctrl |= NFP_NET_CFG_CTRL_IRQMOD; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD; } /* Stash the re-configuration queue away. First odd queue in TX Bar */ @@ -3322,9 +3330,9 @@ void nfp_net_netdev_clean(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - if (nn->xdp_prog) - bpf_prog_put(nn->xdp_prog); - if (nn->bpf_offload_xdp) + if (nn->dp.xdp_prog) + bpf_prog_put(nn->dp.xdp_prog); + if (nn->dp.bpf_offload_xdp) nfp_net_xdp_offload(nn, NULL); - unregister_netdev(nn->netdev); + unregister_netdev(nn->dp.netdev); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c index edfa59e51fdd..74125584260b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c @@ -54,7 +54,7 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data) goto out; nn = r_vec->nfp_net; rx_ring = r_vec->rx_ring; - if (!netif_running(nn->netdev)) + if (!netif_running(nn->dp.netdev)) goto out; rxd_cnt = rx_ring->cnt; @@ -145,7 +145,7 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data) if (!r_vec->nfp_net || !tx_ring) goto out; nn = r_vec->nfp_net; - if (!netif_running(nn->netdev)) + if (!netif_running(nn->dp.netdev)) goto out; txd_cnt = tx_ring->cnt; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index a1bca2dca0a5..4620c1bba96e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -127,9 +127,9 @@ static const struct _nfp_net_et_stats nfp_net_et_stats[] = { }; #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats) -#define NN_ET_RVEC_STATS_LEN (nn->num_r_vecs * 3) +#define NN_ET_RVEC_STATS_LEN (nn->dp.num_r_vecs * 3) #define NN_ET_RVEC_GATHER_STATS 7 -#define NN_ET_QUEUE_STATS_LEN ((nn->num_tx_rings + nn->num_rx_rings) * 2) +#define NN_ET_QUEUE_STATS_LEN ((nn->dp.num_tx_rings + nn->dp.num_rx_rings) * 2) #define NN_ET_STATS_LEN (NN_ET_GLOBAL_STATS_LEN + NN_ET_RVEC_GATHER_STATS + \ NN_ET_RVEC_STATS_LEN + NN_ET_QUEUE_STATS_LEN) @@ -180,29 +180,29 @@ static void nfp_net_get_ringparam(struct net_device *netdev, ring->rx_max_pending = NFP_NET_MAX_RX_DESCS; ring->tx_max_pending = NFP_NET_MAX_TX_DESCS; - ring->rx_pending = nn->rxd_cnt; - ring->tx_pending = nn->txd_cnt; + ring->rx_pending = nn->dp.rxd_cnt; + ring->tx_pending = nn->dp.txd_cnt; } static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt) { struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; struct nfp_net_ring_set rx = { - .n_rings = nn->num_rx_rings, - .mtu = nn->netdev->mtu, + .n_rings = nn->dp.num_rx_rings, + .mtu = nn->dp.netdev->mtu, .dcnt = rxd_cnt, }; struct nfp_net_ring_set tx = { - .n_rings = nn->num_tx_rings, + .n_rings = nn->dp.num_tx_rings, .dcnt = txd_cnt, }; - if (nn->rxd_cnt != rxd_cnt) + if (nn->dp.rxd_cnt != rxd_cnt) reconfig_rx = ℞ - if (nn->txd_cnt != txd_cnt) + if (nn->dp.txd_cnt != txd_cnt) reconfig_tx = &tx; - return nfp_net_ring_reconfig(nn, &nn->xdp_prog, + return nfp_net_ring_reconfig(nn, &nn->dp.xdp_prog, reconfig_rx, reconfig_tx); } @@ -224,11 +224,11 @@ static int nfp_net_set_ringparam(struct net_device *netdev, txd_cnt < NFP_NET_MIN_TX_DESCS || txd_cnt > NFP_NET_MAX_TX_DESCS) return -EINVAL; - if (nn->rxd_cnt == rxd_cnt && nn->txd_cnt == txd_cnt) + if (nn->dp.rxd_cnt == rxd_cnt && nn->dp.txd_cnt == txd_cnt) return 0; nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n", - nn->rxd_cnt, rxd_cnt, nn->txd_cnt, txd_cnt); + nn->dp.rxd_cnt, rxd_cnt, nn->dp.txd_cnt, txd_cnt); return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt); } @@ -246,7 +246,7 @@ static void nfp_net_get_strings(struct net_device *netdev, memcpy(p, nfp_net_et_stats[i].name, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } - for (i = 0; i < nn->num_r_vecs; i++) { + for (i = 0; i < nn->dp.num_r_vecs; i++) { sprintf(p, "rvec_%u_rx_pkts", i); p += ETH_GSTRING_LEN; sprintf(p, "rvec_%u_tx_pkts", i); @@ -268,13 +268,13 @@ static void nfp_net_get_strings(struct net_device *netdev, p += ETH_GSTRING_LEN; strncpy(p, "tx_lso", ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; - for (i = 0; i < nn->num_tx_rings; i++) { + for (i = 0; i < nn->dp.num_tx_rings; i++) { sprintf(p, "txq_%u_pkts", i); p += ETH_GSTRING_LEN; sprintf(p, "txq_%u_bytes", i); p += ETH_GSTRING_LEN; } - for (i = 0; i < nn->num_rx_rings; i++) { + for (i = 0; i < nn->dp.num_rx_rings; i++) { sprintf(p, "rxq_%u_pkts", i); p += ETH_GSTRING_LEN; sprintf(p, "rxq_%u_bytes", i); @@ -312,7 +312,7 @@ static void nfp_net_get_stats(struct net_device *netdev, break; } } - for (j = 0; j < nn->num_r_vecs; j++) { + for (j = 0; j < nn->dp.num_r_vecs; j++) { unsigned int start; do { @@ -338,13 +338,13 @@ static void nfp_net_get_stats(struct net_device *netdev, } for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++) data[i++] = gathered_stats[j]; - for (j = 0; j < nn->num_tx_rings; j++) { + for (j = 0; j < nn->dp.num_tx_rings; j++) { io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j); data[i++] = readq(io_p); io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8; data[i++] = readq(io_p); } - for (j = 0; j < nn->num_rx_rings; j++) { + for (j = 0; j < nn->dp.num_rx_rings; j++) { io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j); data[i++] = readq(io_p); io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8; @@ -411,7 +411,7 @@ static int nfp_net_get_rxnfc(struct net_device *netdev, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = nn->num_rx_rings; + cmd->data = nn->dp.num_rx_rings; return 0; case ETHTOOL_GRXFH: return nfp_net_get_rss_hash_opts(nn, cmd); @@ -745,16 +745,16 @@ static void nfp_net_get_channels(struct net_device *netdev, struct nfp_net *nn = netdev_priv(netdev); unsigned int num_tx_rings; - num_tx_rings = nn->num_tx_rings; - if (nn->xdp_prog) - num_tx_rings -= nn->num_rx_rings; + num_tx_rings = nn->dp.num_tx_rings; + if (nn->dp.xdp_prog) + num_tx_rings -= nn->dp.num_rx_rings; channel->max_rx = min(nn->max_rx_rings, nn->max_r_vecs); channel->max_tx = min(nn->max_tx_rings, nn->max_r_vecs); channel->max_combined = min(channel->max_rx, channel->max_tx); channel->max_other = NFP_NET_NON_Q_VECTORS; - channel->combined_count = min(nn->num_rx_rings, num_tx_rings); - channel->rx_count = nn->num_rx_rings - channel->combined_count; + channel->combined_count = min(nn->dp.num_rx_rings, num_tx_rings); + channel->rx_count = nn->dp.num_rx_rings - channel->combined_count; channel->tx_count = num_tx_rings - channel->combined_count; channel->other_count = NFP_NET_NON_Q_VECTORS; } @@ -765,25 +765,25 @@ static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx, struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; struct nfp_net_ring_set rx = { .n_rings = total_rx, - .mtu = nn->netdev->mtu, - .dcnt = nn->rxd_cnt, + .mtu = nn->dp.netdev->mtu, + .dcnt = nn->dp.rxd_cnt, }; struct nfp_net_ring_set tx = { .n_rings = total_tx, - .dcnt = nn->txd_cnt, + .dcnt = nn->dp.txd_cnt, }; - if (nn->num_rx_rings != total_rx) + if (nn->dp.num_rx_rings != total_rx) reconfig_rx = ℞ - if (nn->num_stack_tx_rings != total_tx || - (nn->xdp_prog && reconfig_rx)) + if (nn->dp.num_stack_tx_rings != total_tx || + (nn->dp.xdp_prog && reconfig_rx)) reconfig_tx = &tx; /* nfp_net_check_config() will catch tx.n_rings > nn->max_tx_rings */ - if (nn->xdp_prog) + if (nn->dp.xdp_prog) tx.n_rings += total_rx; - return nfp_net_ring_reconfig(nn, &nn->xdp_prog, + return nfp_net_ring_reconfig(nn, &nn->dp.xdp_prog, reconfig_rx, reconfig_tx); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 8a9b3f3b95a8..3935d19a273d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -130,7 +130,7 @@ static u8 __iomem *nfp_net_map_area(struct nfp_cpp *cpp, } static void -nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp, +nfp_net_get_mac_addr_hwinfo(struct nfp_net_dp *dp, struct nfp_cpp *cpp, unsigned int id) { u8 mac_addr[ETH_ALEN]; @@ -141,22 +141,22 @@ nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp, mac_str = nfp_hwinfo_lookup(cpp, name); if (!mac_str) { - dev_warn(nn->dev, "Can't lookup MAC address. Generate\n"); - eth_hw_addr_random(nn->netdev); + dev_warn(dp->dev, "Can't lookup MAC address. Generate\n"); + eth_hw_addr_random(dp->netdev); return; } if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx", &mac_addr[0], &mac_addr[1], &mac_addr[2], &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) { - dev_warn(nn->dev, + dev_warn(dp->dev, "Can't parse MAC address (%s). Generate.\n", mac_str); - eth_hw_addr_random(nn->netdev); + eth_hw_addr_random(dp->netdev); return; } - ether_addr_copy(nn->netdev->dev_addr, mac_addr); - ether_addr_copy(nn->netdev->perm_addr, mac_addr); + ether_addr_copy(dp->netdev->dev_addr, mac_addr); + ether_addr_copy(dp->netdev->perm_addr, mac_addr); } /** @@ -179,12 +179,12 @@ nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_pf *pf, unsigned int id) nn->eth_port = &pf->eth_tbl->ports[i]; - ether_addr_copy(nn->netdev->dev_addr, mac_addr); - ether_addr_copy(nn->netdev->perm_addr, mac_addr); + ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr); + ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr); return; } - nfp_net_get_mac_addr_hwinfo(nn, pf->cpp, id); + nfp_net_get_mac_addr_hwinfo(&nn->dp, pf->cpp, id); } static unsigned int nfp_net_pf_get_num_ports(struct nfp_pf *pf) @@ -309,7 +309,7 @@ nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar, nn->ctrl_bar = ctrl_bar; nn->tx_bar = tx_bar; nn->rx_bar = rx_bar; - nn->is_vf = 0; + nn->dp.is_vf = 0; nn->stride_rx = stride; nn->stride_tx = stride; @@ -331,7 +331,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn, */ nn->me_freq_mhz = 1200; - err = nfp_net_netdev_init(nn->netdev); + err = nfp_net_netdev_init(nn->dp.netdev); if (err) return err; @@ -400,7 +400,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf, /* Get MSI-X vectors */ wanted_irqs = 0; list_for_each_entry(nn, &pf->ports, port_list) - wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->num_r_vecs; + wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->dp.num_r_vecs; pf->irq_entries = kcalloc(wanted_irqs, sizeof(*pf->irq_entries), GFP_KERNEL); if (!pf->irq_entries) { @@ -445,7 +445,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf, err_prev_deinit: list_for_each_entry_continue_reverse(nn, &pf->ports, port_list) { nfp_net_debugfs_dir_clean(&nn->debugfs_dir); - nfp_net_netdev_clean(nn->netdev); + nfp_net_netdev_clean(nn->dp.netdev); } nfp_net_irqs_disable(pf->pdev); err_vec_free: @@ -571,7 +571,7 @@ void nfp_net_pci_remove(struct nfp_pf *pf) list_for_each_entry(nn, &pf->ports, port_list) { nfp_net_debugfs_dir_clean(&nn->debugfs_dir); - nfp_net_netdev_clean(nn->netdev); + nfp_net_netdev_clean(nn->dp.netdev); } nfp_net_pf_free_netdevs(pf); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c index f6ed1aa9d94b..b5b6f69d1e0f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c @@ -58,7 +58,7 @@ void nfp_net_filter_stats_timer(unsigned long data) spin_lock_bh(&nn->rx_filter_lock); - if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL); @@ -132,7 +132,7 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) return NN_ACT_TC_DROP; if (is_tcf_mirred_egress_redirect(a) && - tcf_mirred_ifindex(a) == nn->netdev->ifindex) + tcf_mirred_ifindex(a) == nn->dp.netdev->ifindex) return NN_ACT_TC_REDIR; } @@ -160,7 +160,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, act = ret; max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; - if (max_mtu < nn->netdev->mtu) { + if (max_mtu < nn->dp.netdev->mtu) { nn_info(nn, "BPF offload not supported with MTU larger than HW packet split boundary\n"); return -ENOTSUPP; } @@ -168,7 +168,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, start_off = nn_readw(nn, NFP_NET_CFG_BPF_START); done_off = nn_readw(nn, NFP_NET_CFG_BPF_DONE); - *code = dma_zalloc_coherent(nn->dev, code_sz, dma_addr, GFP_KERNEL); + *code = dma_zalloc_coherent(nn->dp.dev, code_sz, dma_addr, GFP_KERNEL); if (!*code) return -ENOMEM; @@ -180,7 +180,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn, return 0; out: - dma_free_coherent(nn->dev, code_sz, *code, *dma_addr); + dma_free_coherent(nn->dp.dev, code_sz, *code, *dma_addr); return ret; } @@ -193,7 +193,7 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags, u64 bpf_addr = dma_addr; int err; - nn->bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW); + nn->dp.bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW); if (dense_mode) bpf_addr |= NFP_NET_CFG_BPF_CFG_8CTX; @@ -207,13 +207,13 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags, nn_err(nn, "FW command error while loading BPF: %d\n", err); /* Enable passing packets through BPF function */ - nn->ctrl |= NFP_NET_CFG_CTRL_BPF; - nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl); + nn->dp.ctrl |= NFP_NET_CFG_CTRL_BPF; + nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN); if (err) nn_err(nn, "FW command error while enabling BPF: %d\n", err); - dma_free_coherent(nn->dev, code_sz, code, dma_addr); + dma_free_coherent(nn->dp.dev, code_sz, code, dma_addr); nfp_net_bpf_stats_reset(nn); mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL); @@ -221,16 +221,16 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags, static int nfp_net_bpf_stop(struct nfp_net *nn) { - if (!(nn->ctrl & NFP_NET_CFG_CTRL_BPF)) + if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)) return 0; spin_lock_bh(&nn->rx_filter_lock); - nn->ctrl &= ~NFP_NET_CFG_CTRL_BPF; + nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_BPF; spin_unlock_bh(&nn->rx_filter_lock); - nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl); + nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl); del_timer_sync(&nn->rx_filter_stats_timer); - nn->bpf_offload_skip_sw = 0; + nn->dp.bpf_offload_skip_sw = 0; return nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN); } @@ -254,7 +254,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) * frames which didn't have BPF applied in the hardware should * be fine if software fallback is available, though. */ - if (nn->bpf_offload_skip_sw) + if (nn->dp.bpf_offload_skip_sw) return -EBUSY; err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code, @@ -269,7 +269,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) return 0; case TC_CLSBPF_ADD: - if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) + if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) return -EBUSY; err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c index 39407f7cc586..bc0bdbc1c8fd 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c @@ -84,12 +84,12 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn) put_unaligned_be16(nn_readw(nn, NFP_NET_CFG_MACADDR + 6), &mac_addr[4]); if (!is_valid_ether_addr(mac_addr)) { - eth_hw_addr_random(nn->netdev); + eth_hw_addr_random(nn->dp.netdev); return; } - ether_addr_copy(nn->netdev->dev_addr, mac_addr); - ether_addr_copy(nn->netdev->perm_addr, mac_addr); + ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr); + ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr); } static int nfp_netvf_pci_probe(struct pci_dev *pdev, @@ -211,7 +211,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev, nn->fw_ver = fw_ver; nn->ctrl_bar = ctrl_bar; - nn->is_vf = 1; + nn->dp.is_vf = 1; nn->stride_tx = stride; nn->stride_rx = stride; @@ -268,7 +268,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev, num_irqs = nfp_net_irqs_alloc(pdev, vf->irq_entries, NFP_NET_MIN_PORT_IRQS, - NFP_NET_NON_Q_VECTORS + nn->num_r_vecs); + NFP_NET_NON_Q_VECTORS + + nn->dp.num_r_vecs); if (!num_irqs) { nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n"); err = -EIO; @@ -282,7 +283,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev, */ nn->me_freq_mhz = 1200; - err = nfp_net_netdev_init(nn->netdev); + err = nfp_net_netdev_init(nn->dp.netdev); if (err) goto err_irqs_disable; @@ -327,7 +328,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev) nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_debugfs_dir_clean(&vf->ddir); - nfp_net_netdev_clean(nn->netdev); + nfp_net_netdev_clean(nn->dp.netdev); nfp_net_irqs_disable(pdev); From d2b84397601f370ca11a5a37a40787d31af778b7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:28 -0800 Subject: [PATCH 175/399] nfp: move control BAR pointer into data path structure Control BAR pointer is used to unmask interrupts so it should be in the first cacheline of adapter structure. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 21 ++++++++++--------- .../ethernet/netronome/nfp/nfp_net_ethtool.c | 14 ++++++------- .../net/ethernet/netronome/nfp/nfp_net_main.c | 2 +- .../ethernet/netronome/nfp/nfp_netvf_main.c | 4 ++-- 4 files changed, 21 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 7d2c38604372..90a44fad6bd5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -447,6 +447,7 @@ struct nfp_stat_pair { * @xdp_prog: Installed XDP program * @tx_rings: Array of pre-allocated TX ring structures * @rx_rings: Array of pre-allocated RX ring structures + * @ctrl_bar: Pointer to mapped control BAR * * @txd_cnt: Size of the TX ring in number of descriptors * @rxd_cnt: Size of the RX ring in number of descriptors @@ -474,6 +475,8 @@ struct nfp_net_dp { struct nfp_net_tx_ring *tx_rings; struct nfp_net_rx_ring *rx_rings; + u8 __iomem *ctrl_bar; + /* Cold data follows */ unsigned int txd_cnt; @@ -527,7 +530,6 @@ struct nfp_net_dp { * @vxlan_ports: VXLAN ports for RX inner csum offload communicated to HW * @vxlan_usecnt: IPv4/IPv6 VXLAN port use counts * @qcp_cfg: Pointer to QCP queue used for configuration notification - * @ctrl_bar: Pointer to mapped control BAR * @tx_bar: Pointer to mapped TX queues * @rx_bar: Pointer to mapped FL/RX queues * @debugfs_dir: Device directory in debugfs @@ -595,7 +597,6 @@ struct nfp_net { u8 __iomem *qcp_cfg; - u8 __iomem *ctrl_bar; u8 __iomem *tx_bar; u8 __iomem *rx_bar; @@ -622,42 +623,42 @@ struct nfp_net_ring_set { */ static inline u16 nn_readb(struct nfp_net *nn, int off) { - return readb(nn->ctrl_bar + off); + return readb(nn->dp.ctrl_bar + off); } static inline void nn_writeb(struct nfp_net *nn, int off, u8 val) { - writeb(val, nn->ctrl_bar + off); + writeb(val, nn->dp.ctrl_bar + off); } static inline u16 nn_readw(struct nfp_net *nn, int off) { - return readw(nn->ctrl_bar + off); + return readw(nn->dp.ctrl_bar + off); } static inline void nn_writew(struct nfp_net *nn, int off, u16 val) { - writew(val, nn->ctrl_bar + off); + writew(val, nn->dp.ctrl_bar + off); } static inline u32 nn_readl(struct nfp_net *nn, int off) { - return readl(nn->ctrl_bar + off); + return readl(nn->dp.ctrl_bar + off); } static inline void nn_writel(struct nfp_net *nn, int off, u32 val) { - writel(val, nn->ctrl_bar + off); + writel(val, nn->dp.ctrl_bar + off); } static inline u64 nn_readq(struct nfp_net *nn, int off) { - return readq(nn->ctrl_bar + off); + return readq(nn->dp.ctrl_bar + off); } static inline void nn_writeq(struct nfp_net *nn, int off, u64 val) { - writeq(val, nn->ctrl_bar + off); + writeq(val, nn->dp.ctrl_bar + off); } /* Flush posted PCI writes by reading something without side effects */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 4620c1bba96e..969c30589f23 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -307,7 +307,7 @@ static void nfp_net_get_stats(struct net_device *netdev, break; case NFP_NET_DEV_ET_STATS: - io_p = nn->ctrl_bar + nfp_net_et_stats[i].off; + io_p = nn->dp.ctrl_bar + nfp_net_et_stats[i].off; data[i] = readq(io_p); break; } @@ -339,15 +339,15 @@ static void nfp_net_get_stats(struct net_device *netdev, for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++) data[i++] = gathered_stats[j]; for (j = 0; j < nn->dp.num_tx_rings; j++) { - io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j); + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j); data[i++] = readq(io_p); - io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8; + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8; data[i++] = readq(io_p); } for (j = 0; j < nn->dp.num_rx_rings; j++) { - io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j); + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j); data[i++] = readq(io_p); - io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8; + io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8; data[i++] = readq(io_p); } } @@ -461,7 +461,7 @@ static int nfp_net_set_rss_hash_opt(struct nfp_net *nn, if (new_rss_cfg == nn->rss_cfg) return 0; - writel(new_rss_cfg, nn->ctrl_bar + NFP_NET_CFG_RSS_CTRL); + writel(new_rss_cfg, nn->dp.ctrl_bar + NFP_NET_CFG_RSS_CTRL); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_RSS); if (err) return err; @@ -573,7 +573,7 @@ static void nfp_net_get_regs(struct net_device *netdev, regs->version = nn_readl(nn, NFP_NET_CFG_VERSION); for (i = 0; i < NFP_NET_CFG_BAR_SZ / sizeof(u32); i++) - regs_buf[i] = readl(nn->ctrl_bar + (i * sizeof(u32))); + regs_buf[i] = readl(nn->dp.ctrl_bar + (i * sizeof(u32))); } static int nfp_net_get_coalesce(struct net_device *netdev, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 3935d19a273d..2025cb7c6d90 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -306,7 +306,7 @@ nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar, nn->cpp = pf->cpp; nn->fw_ver = *fw_ver; - nn->ctrl_bar = ctrl_bar; + nn->dp.ctrl_bar = ctrl_bar; nn->tx_bar = tx_bar; nn->rx_bar = rx_bar; nn->dp.is_vf = 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c index bc0bdbc1c8fd..86e61be6f35c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c @@ -210,7 +210,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev, vf->nn = nn; nn->fw_ver = fw_ver; - nn->ctrl_bar = ctrl_bar; + nn->dp.ctrl_bar = ctrl_bar; nn->dp.is_vf = 1; nn->stride_tx = stride; nn->stride_rx = stride; @@ -338,7 +338,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev) } else { iounmap(vf->q_bar); } - iounmap(nn->ctrl_bar); + iounmap(nn->dp.ctrl_bar); nfp_net_netdev_free(nn); From 783496b0ddc2bd4ad561864138596ebb336a7100 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:29 -0800 Subject: [PATCH 176/399] nfp: pass new data path to ring reconfig Make callers of nfp_net_ring_reconfig() pass newly allocated data path structure. We will gradually make use of that structure instead of passing parameters around to all the allocation functions. This commit adds allocation and propagation of new data path struct, no parameters are converted, yet. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 5 +- .../ethernet/netronome/nfp/nfp_net_common.c | 108 ++++++++++++------ .../ethernet/netronome/nfp/nfp_net_ethtool.c | 14 ++- 3 files changed, 91 insertions(+), 36 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 90a44fad6bd5..74f6d485351f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -812,8 +812,11 @@ void nfp_net_irqs_disable(struct pci_dev *pdev); void nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries, unsigned int n); + +struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn); int -nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, +nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new, + struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx); #ifdef CONFIG_NFP_DEBUG diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 951d511643f1..7afefb44b642 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1127,6 +1127,7 @@ nfp_net_free_frag(void *frag, bool xdp) /** * nfp_net_rx_alloc_one() - Allocate and map page frag for RX + * @dp: NFP Net data path struct * @rx_ring: RX ring structure of the skb * @dma_addr: Pointer to storage for DMA address (output param) * @fl_bufsz: size of freelist buffers @@ -1137,10 +1138,10 @@ nfp_net_free_frag(void *frag, bool xdp) * Return: allocated page frag or NULL on failure. */ static void * -nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, +nfp_net_rx_alloc_one(struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, unsigned int fl_bufsz, bool xdp) { - struct nfp_net_dp *dp = &rx_ring->r_vec->nfp_net->dp; int direction; void *frag; @@ -1299,7 +1300,7 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp, for (i = 0; i < rx_ring->cnt - 1; i++) { rxbufs[i].frag = - nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr, + nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr, rx_ring->bufsz, xdp); if (!rxbufs[i].frag) { nfp_net_rx_ring_bufs_free(dp, rx_ring, xdp); @@ -1784,7 +1785,8 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) } static struct nfp_net_tx_ring * -nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, +nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, + struct nfp_net_ring_set *s, unsigned int num_stack_tx_rings) { struct nfp_net_tx_ring *rings; @@ -1900,10 +1902,10 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz, } static struct nfp_net_rx_ring * -nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, - bool xdp) +nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, + struct nfp_net_ring_set *s, bool xdp) { - unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, s->mtu); + unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(dp, s->mtu); struct nfp_net_rx_ring *rings; unsigned int r; @@ -1917,7 +1919,7 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt)) goto err_free_prev; - if (nfp_net_rx_ring_bufs_alloc(&nn->dp, &rings[r], xdp)) + if (nfp_net_rx_ring_bufs_alloc(dp, &rings[r], xdp)) goto err_free_ring; } @@ -1925,7 +1927,7 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s, err_free_prev: while (r--) { - nfp_net_rx_ring_bufs_free(&nn->dp, &rings[r], xdp); + nfp_net_rx_ring_bufs_free(dp, &rings[r], xdp); err_free_ring: nfp_net_rx_ring_free(&rings[r]); } @@ -2295,14 +2297,15 @@ static int nfp_net_netdev_open(struct net_device *netdev) goto err_cleanup_vec_p; } - nn->dp.rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->dp.xdp_prog); + nn->dp.rx_rings = nfp_net_rx_ring_set_prepare(nn, &nn->dp, &rx, + nn->dp.xdp_prog); if (!nn->dp.rx_rings) { err = -ENOMEM; goto err_cleanup_vec; } - nn->dp.tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx, - nn->dp.num_stack_tx_rings); + nn->dp.tx_rings = nfp_net_tx_ring_set_prepare(nn, &nn->dp, &tx, + nn->dp.num_stack_tx_rings); if (!nn->dp.tx_rings) { err = -ENOMEM; goto err_free_rx_rings; @@ -2464,7 +2467,8 @@ static void nfp_net_rss_init_itbl(struct nfp_net *nn) } static int -nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs, +nfp_net_ring_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp, + unsigned int *num_vecs, unsigned int *stack_tx_rings, struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, @@ -2502,14 +2506,35 @@ nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs, return __nfp_net_set_config_and_enable(nn); } +struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn) +{ + struct nfp_net_dp *new; + + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + *new = nn->dp; + + /* Clear things which need to be recomputed */ + new->fl_bufsz = 0; + new->tx_rings = NULL; + new->rx_rings = NULL; + new->num_r_vecs = 0; + new->num_stack_tx_rings = 0; + + return new; +} + static int -nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog, +nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp, + struct bpf_prog *xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) { /* XDP-enabled tests */ if (!xdp_prog) return 0; - if (rx && nfp_net_calc_fl_bufsz(&nn->dp, rx->mtu) > PAGE_SIZE) { + if (rx && nfp_net_calc_fl_bufsz(dp, rx->mtu) > PAGE_SIZE) { nn_warn(nn, "MTU too large w/ XDP enabled\n"); return -EINVAL; } @@ -2522,7 +2547,8 @@ nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog, } static void -nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog, +nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, + struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx, unsigned int stack_tx_rings, unsigned int num_vecs) @@ -2542,26 +2568,28 @@ nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog, } int -nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, +nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, + struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) { unsigned int stack_tx_rings, num_vecs, r; int err; - stack_tx_rings = tx ? tx->n_rings : nn->dp.num_tx_rings; + stack_tx_rings = tx ? tx->n_rings : dp->num_tx_rings; if (*xdp_prog) - stack_tx_rings -= rx ? rx->n_rings : nn->dp.num_rx_rings; + stack_tx_rings -= rx ? rx->n_rings : dp->num_rx_rings; - num_vecs = max(rx ? rx->n_rings : nn->dp.num_rx_rings, stack_tx_rings); + num_vecs = max(rx ? rx->n_rings : dp->num_rx_rings, stack_tx_rings); - err = nfp_net_check_config(nn, *xdp_prog, rx, tx); + err = nfp_net_check_config(nn, dp, *xdp_prog, rx, tx); if (err) - return err; + goto exit_free_dp; - if (!netif_running(nn->dp.netdev)) { - nfp_net_ring_reconfig_down(nn, xdp_prog, rx, tx, + if (!netif_running(dp->netdev)) { + nfp_net_ring_reconfig_down(nn, dp, xdp_prog, rx, tx, stack_tx_rings, num_vecs); - return 0; + err = 0; + goto exit_free_dp; } /* Prepare new rings */ @@ -2573,13 +2601,13 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, } } if (rx) { - if (!nfp_net_rx_ring_set_prepare(nn, rx, *xdp_prog)) { + if (!nfp_net_rx_ring_set_prepare(nn, dp, rx, *xdp_prog)) { err = -ENOMEM; goto err_cleanup_vecs; } } if (tx) { - if (!nfp_net_tx_ring_set_prepare(nn, tx, stack_tx_rings)) { + if (!nfp_net_tx_ring_set_prepare(nn, dp, tx, stack_tx_rings)) { err = -ENOMEM; goto err_free_rx; } @@ -2589,7 +2617,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, nfp_net_close_stack(nn); nfp_net_clear_config_and_disable(nn); - err = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings, + err = nfp_net_ring_swap_enable(nn, dp, &num_vecs, &stack_tx_rings, xdp_prog, rx, tx); if (err) { int err2; @@ -2597,7 +2625,8 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, nfp_net_clear_config_and_disable(nn); /* Try with old configuration and old rings */ - err2 = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings, + err2 = nfp_net_ring_swap_enable(nn, dp, &num_vecs, + &stack_tx_rings, xdp_prog, rx, tx); if (err2) nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n", @@ -2607,20 +2636,23 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog, nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); if (rx) - nfp_net_rx_ring_set_free(&nn->dp, rx, *xdp_prog); + nfp_net_rx_ring_set_free(dp, rx, *xdp_prog); if (tx) nfp_net_tx_ring_set_free(tx); nfp_net_open_stack(nn); +exit_free_dp: + kfree(dp); return err; err_free_rx: if (rx) - nfp_net_rx_ring_set_free(&nn->dp, rx, *xdp_prog); + nfp_net_rx_ring_set_free(dp, rx, *xdp_prog); err_cleanup_vecs: for (r = num_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); + kfree(dp); return err; } @@ -2632,8 +2664,13 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) .mtu = new_mtu, .dcnt = nn->dp.rxd_cnt, }; + struct nfp_net_dp *dp; - return nfp_net_ring_reconfig(nn, &nn->dp.xdp_prog, &rx, NULL); + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; + + return nfp_net_ring_reconfig(nn, dp, &nn->dp.xdp_prog, &rx, NULL); } static void nfp_net_stat64(struct net_device *netdev, @@ -2960,6 +2997,7 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) .n_rings = nn->dp.num_tx_rings, .dcnt = nn->dp.txd_cnt, }; + struct nfp_net_dp *dp; int err; if (prog && prog->xdp_adjust_head) { @@ -2975,10 +3013,14 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) return 0; } + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; + tx.n_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */ - err = nfp_net_ring_reconfig(nn, &prog, &rx, &tx); + err = nfp_net_ring_reconfig(nn, dp, &prog, &rx, &tx); if (err) return err; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 969c30589f23..326ccd74a4bf 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -196,13 +196,18 @@ static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt) .n_rings = nn->dp.num_tx_rings, .dcnt = txd_cnt, }; + struct nfp_net_dp *dp; if (nn->dp.rxd_cnt != rxd_cnt) reconfig_rx = ℞ if (nn->dp.txd_cnt != txd_cnt) reconfig_tx = &tx; - return nfp_net_ring_reconfig(nn, &nn->dp.xdp_prog, + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; + + return nfp_net_ring_reconfig(nn, dp, &nn->dp.xdp_prog, reconfig_rx, reconfig_tx); } @@ -772,6 +777,7 @@ static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx, .n_rings = total_tx, .dcnt = nn->dp.txd_cnt, }; + struct nfp_net_dp *dp; if (nn->dp.num_rx_rings != total_rx) reconfig_rx = ℞ @@ -783,7 +789,11 @@ static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx, if (nn->dp.xdp_prog) tx.n_rings += total_rx; - return nfp_net_ring_reconfig(nn, &nn->dp.xdp_prog, + dp = nfp_net_clone_dp(nn); + if (!dp) + return -ENOMEM; + + return nfp_net_ring_reconfig(nn, dp, &nn->dp.xdp_prog, reconfig_rx, reconfig_tx); } From 512e94dc3229a824190e310c899a3f6d08216477 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:30 -0800 Subject: [PATCH 177/399] nfp: use dp to carry number of stack tx rings and vectors Instead of passing variables around use dp to store number of tx rings for the stack and number of IRQ vectors. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/nfp_net_common.c | 62 +++++++++---------- 1 file changed, 31 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 7afefb44b642..52f0e9dfd15a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1786,8 +1786,7 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) static struct nfp_net_tx_ring * nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *s, - unsigned int num_stack_tx_rings) + struct nfp_net_ring_set *s) { struct nfp_net_tx_ring *rings; unsigned int r; @@ -1799,8 +1798,8 @@ nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, for (r = 0; r < s->n_rings; r++) { int bias = 0; - if (r >= num_stack_tx_rings) - bias = num_stack_tx_rings; + if (r >= dp->num_stack_tx_rings) + bias = dp->num_stack_tx_rings; nfp_net_tx_ring_init(&rings[r], &nn->r_vecs[r - bias], r); @@ -2304,8 +2303,7 @@ static int nfp_net_netdev_open(struct net_device *netdev) goto err_cleanup_vec; } - nn->dp.tx_rings = nfp_net_tx_ring_set_prepare(nn, &nn->dp, &tx, - nn->dp.num_stack_tx_rings); + nn->dp.tx_rings = nfp_net_tx_ring_set_prepare(nn, &nn->dp, &tx); if (!nn->dp.tx_rings) { err = -ENOMEM; goto err_free_rx_rings; @@ -2466,10 +2464,16 @@ static void nfp_net_rss_init_itbl(struct nfp_net *nn) ethtool_rxfh_indir_default(i, nn->dp.num_rx_rings); } +static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp) +{ + struct nfp_net_dp new_dp = *dp; + + *dp = nn->dp; + nn->dp = new_dp; +} + static int nfp_net_ring_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp, - unsigned int *num_vecs, - unsigned int *stack_tx_rings, struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) @@ -2482,8 +2486,8 @@ nfp_net_ring_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp, if (tx) nfp_net_tx_ring_set_swap(nn, tx); - swap(*num_vecs, nn->dp.num_r_vecs); - swap(*stack_tx_rings, nn->dp.num_stack_tx_rings); + swap(dp->num_r_vecs, nn->dp.num_r_vecs); + swap(dp->num_stack_tx_rings, nn->dp.num_stack_tx_rings); *xdp_prog = xchg(&nn->dp.xdp_prog, *xdp_prog); for (r = 0; r < nn->max_r_vecs; r++) @@ -2550,17 +2554,16 @@ static void nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, - struct nfp_net_ring_set *tx, - unsigned int stack_tx_rings, unsigned int num_vecs) + struct nfp_net_ring_set *tx) { + nfp_net_dp_swap(nn, dp); + nn->dp.netdev->mtu = rx ? rx->mtu : nn->dp.netdev->mtu; nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, nn->dp.netdev->mtu); nn->dp.rxd_cnt = rx ? rx->dcnt : nn->dp.rxd_cnt; nn->dp.txd_cnt = tx ? tx->dcnt : nn->dp.txd_cnt; nn->dp.num_rx_rings = rx ? rx->n_rings : nn->dp.num_rx_rings; nn->dp.num_tx_rings = tx ? tx->n_rings : nn->dp.num_tx_rings; - nn->dp.num_stack_tx_rings = stack_tx_rings; - nn->dp.num_r_vecs = num_vecs; *xdp_prog = xchg(&nn->dp.xdp_prog, *xdp_prog); if (!netif_is_rxfh_configured(nn->dp.netdev)) @@ -2572,31 +2575,31 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) { - unsigned int stack_tx_rings, num_vecs, r; - int err; + int r, err; - stack_tx_rings = tx ? tx->n_rings : dp->num_tx_rings; + dp->num_stack_tx_rings = tx ? tx->n_rings : dp->num_tx_rings; if (*xdp_prog) - stack_tx_rings -= rx ? rx->n_rings : dp->num_rx_rings; + dp->num_stack_tx_rings -= rx ? rx->n_rings : dp->num_rx_rings; - num_vecs = max(rx ? rx->n_rings : dp->num_rx_rings, stack_tx_rings); + dp->num_r_vecs = max(rx ? rx->n_rings : dp->num_rx_rings, + dp->num_stack_tx_rings); err = nfp_net_check_config(nn, dp, *xdp_prog, rx, tx); if (err) goto exit_free_dp; if (!netif_running(dp->netdev)) { - nfp_net_ring_reconfig_down(nn, dp, xdp_prog, rx, tx, - stack_tx_rings, num_vecs); + nfp_net_ring_reconfig_down(nn, dp, xdp_prog, rx, tx); + err = 0; goto exit_free_dp; } /* Prepare new rings */ - for (r = nn->dp.num_r_vecs; r < num_vecs; r++) { + for (r = nn->dp.num_r_vecs; r < dp->num_r_vecs; r++) { err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r); if (err) { - num_vecs = r; + dp->num_r_vecs = r; goto err_cleanup_vecs; } } @@ -2607,7 +2610,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, } } if (tx) { - if (!nfp_net_tx_ring_set_prepare(nn, dp, tx, stack_tx_rings)) { + if (!nfp_net_tx_ring_set_prepare(nn, dp, tx)) { err = -ENOMEM; goto err_free_rx; } @@ -2617,22 +2620,19 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, nfp_net_close_stack(nn); nfp_net_clear_config_and_disable(nn); - err = nfp_net_ring_swap_enable(nn, dp, &num_vecs, &stack_tx_rings, - xdp_prog, rx, tx); + err = nfp_net_ring_swap_enable(nn, dp, xdp_prog, rx, tx); if (err) { int err2; nfp_net_clear_config_and_disable(nn); /* Try with old configuration and old rings */ - err2 = nfp_net_ring_swap_enable(nn, dp, &num_vecs, - &stack_tx_rings, - xdp_prog, rx, tx); + err2 = nfp_net_ring_swap_enable(nn, dp, xdp_prog, rx, tx); if (err2) nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n", err, err2); } - for (r = num_vecs - 1; r >= nn->dp.num_r_vecs; r--) + for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); if (rx) @@ -2650,7 +2650,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, if (rx) nfp_net_rx_ring_set_free(dp, rx, *xdp_prog); err_cleanup_vecs: - for (r = num_vecs - 1; r >= nn->dp.num_r_vecs; r--) + for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); kfree(dp); return err; From 2195c2637f90e97ef8cd8f8e0fe11c1829e7f1f6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:31 -0800 Subject: [PATCH 178/399] nfp: use dp to carry fl_bufsz at reconfig time Use fl_bufsz member of data path struct to carry desired size of free list entries. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 3 - .../ethernet/netronome/nfp/nfp_net_common.c | 56 +++++++++---------- 2 files changed, 27 insertions(+), 32 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 74f6d485351f..ab5865b955dd 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -316,8 +316,6 @@ struct nfp_net_rx_buf { * @rxds: Virtual address of FL/RX ring in host memory * @dma: DMA address of the FL/RX ring * @size: Size, in bytes, of the FL/RX ring (needed to free) - * @bufsz: Buffer allocation size for convenience of management routines - * (NOTE: this is in second cache line, do not use on fast path!) */ struct nfp_net_rx_ring { struct nfp_net_r_vector *r_vec; @@ -339,7 +337,6 @@ struct nfp_net_rx_ring { dma_addr_t dma; unsigned int size; - unsigned int bufsz; } ____cacheline_aligned; /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 52f0e9dfd15a..92d4c2991a85 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -86,19 +86,19 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver, } static dma_addr_t -nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag, unsigned int bufsz, - int direction) +nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag, int direction) { return dma_map_single(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM, - bufsz - NFP_NET_RX_BUF_NON_DATA, direction); + dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA, + direction); } static void nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr, - unsigned int bufsz, int direction) + int direction) { dma_unmap_single(dp->dev, dma_addr, - bufsz - NFP_NET_RX_BUF_NON_DATA, direction); + dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA, direction); } /* Firmware reconfig @@ -992,7 +992,7 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) continue; nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr, - dp->fl_bufsz, DMA_BIDIRECTIONAL); + DMA_BIDIRECTIONAL); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); done_pkts++; @@ -1038,7 +1038,7 @@ nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) if (tx_ring == r_vec->xdp_ring) { nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr, - dp->fl_bufsz, DMA_BIDIRECTIONAL); + DMA_BIDIRECTIONAL); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); } else { struct sk_buff *skb = tx_ring->txbufs[idx].skb; @@ -1130,7 +1130,6 @@ nfp_net_free_frag(void *frag, bool xdp) * @dp: NFP Net data path struct * @rx_ring: RX ring structure of the skb * @dma_addr: Pointer to storage for DMA address (output param) - * @fl_bufsz: size of freelist buffers * @xdp: Whether XDP is enabled * * This function will allcate a new page frag, map it for DMA. @@ -1140,13 +1139,13 @@ nfp_net_free_frag(void *frag, bool xdp) static void * nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, - unsigned int fl_bufsz, bool xdp) + bool xdp) { int direction; void *frag; if (!xdp) - frag = netdev_alloc_frag(fl_bufsz); + frag = netdev_alloc_frag(dp->fl_bufsz); else frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD)); if (!frag) { @@ -1156,7 +1155,7 @@ nfp_net_rx_alloc_one(struct nfp_net_dp *dp, direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - *dma_addr = nfp_net_dma_map_rx(dp, frag, fl_bufsz, direction); + *dma_addr = nfp_net_dma_map_rx(dp, frag, direction); if (dma_mapping_error(dp->dev, *dma_addr)) { nfp_net_free_frag(frag, xdp); nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); @@ -1181,7 +1180,7 @@ nfp_net_napi_alloc_one(struct nfp_net_dp *dp, int direction, return NULL; } - *dma_addr = nfp_net_dma_map_rx(dp, frag, dp->fl_bufsz, direction); + *dma_addr = nfp_net_dma_map_rx(dp, frag, direction); if (dma_mapping_error(dp->dev, *dma_addr)) { nfp_net_free_frag(frag, dp->xdp_prog); nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); @@ -1276,7 +1275,7 @@ nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, continue; nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr, - rx_ring->bufsz, direction); + direction); nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp); rx_ring->rxbufs[i].dma_addr = 0; rx_ring->rxbufs[i].frag = NULL; @@ -1301,7 +1300,7 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp, for (i = 0; i < rx_ring->cnt - 1; i++) { rxbufs[i].frag = nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr, - rx_ring->bufsz, xdp); + xdp); if (!rxbufs[i].frag) { nfp_net_rx_ring_bufs_free(dp, rx_ring, xdp); return -ENOMEM; @@ -1652,8 +1651,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) continue; } - nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr, dp->fl_bufsz, - rx_dma_map_dir); + nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr, rx_dma_map_dir); nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr); @@ -1865,23 +1863,19 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) /** * nfp_net_rx_ring_alloc() - Allocate resource for a RX ring + * @dp: NFP Net data path struct * @rx_ring: RX ring to allocate - * @fl_bufsz: Size of buffers to allocate * @cnt: Ring buffer count * * Return: 0 on success, negative errno otherwise. */ static int -nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz, +nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, u32 cnt) { - struct nfp_net_r_vector *r_vec = rx_ring->r_vec; - struct nfp_net_dp *dp = &r_vec->nfp_net->dp; int sz; rx_ring->cnt = cnt; - rx_ring->bufsz = fl_bufsz; - rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt; rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); @@ -1904,7 +1898,6 @@ static struct nfp_net_rx_ring * nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, struct nfp_net_ring_set *s, bool xdp) { - unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(dp, s->mtu); struct nfp_net_rx_ring *rings; unsigned int r; @@ -1915,7 +1908,7 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, for (r = 0; r < s->n_rings; r++) { nfp_net_rx_ring_init(&rings[r], &nn->r_vecs[r], r); - if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt)) + if (nfp_net_rx_ring_alloc(dp, &rings[r], s->dcnt)) goto err_free_prev; if (nfp_net_rx_ring_bufs_alloc(dp, &rings[r], xdp)) @@ -1935,17 +1928,20 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, } static void -nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s) +nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_dp *dp, + struct nfp_net_ring_set *s) { struct nfp_net_ring_set new = *s; + struct nfp_net_dp new_dp = *dp; + dp->fl_bufsz = nn->dp.fl_bufsz; s->mtu = nn->dp.netdev->mtu; s->dcnt = nn->dp.rxd_cnt; s->rings = nn->dp.rx_rings; s->n_rings = nn->dp.num_rx_rings; nn->dp.netdev->mtu = new.mtu; - nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, new.mtu); + nn->dp.fl_bufsz = new_dp.fl_bufsz; nn->dp.rxd_cnt = new.dcnt; nn->dp.rx_rings = new.rings; nn->dp.num_rx_rings = new.n_rings; @@ -2482,7 +2478,7 @@ nfp_net_ring_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp, int err; if (rx) - nfp_net_rx_ring_set_swap(nn, rx); + nfp_net_rx_ring_set_swap(nn, dp, rx); if (tx) nfp_net_tx_ring_set_swap(nn, tx); @@ -2538,7 +2534,7 @@ nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp, /* XDP-enabled tests */ if (!xdp_prog) return 0; - if (rx && nfp_net_calc_fl_bufsz(dp, rx->mtu) > PAGE_SIZE) { + if (dp->fl_bufsz > PAGE_SIZE) { nn_warn(nn, "MTU too large w/ XDP enabled\n"); return -EINVAL; } @@ -2559,7 +2555,6 @@ nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, nfp_net_dp_swap(nn, dp); nn->dp.netdev->mtu = rx ? rx->mtu : nn->dp.netdev->mtu; - nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, nn->dp.netdev->mtu); nn->dp.rxd_cnt = rx ? rx->dcnt : nn->dp.rxd_cnt; nn->dp.txd_cnt = tx ? tx->dcnt : nn->dp.txd_cnt; nn->dp.num_rx_rings = rx ? rx->n_rings : nn->dp.num_rx_rings; @@ -2577,6 +2572,9 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, { int r, err; + dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp, + rx ? rx->mtu : nn->dp.netdev->mtu); + dp->num_stack_tx_rings = tx ? tx->n_rings : dp->num_tx_rings; if (*xdp_prog) dp->num_stack_tx_rings -= rx ? rx->n_rings : dp->num_rx_rings; From 76e1e1a89351832ea5d9f7b57677e7420ba6bc92 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:32 -0800 Subject: [PATCH 179/399] nfp: use dp to carry mtu at reconfig time Move the mtu member from ring set to data path struct. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 4 +++- .../ethernet/netronome/nfp/nfp_net_common.c | 23 ++++++++++--------- .../ethernet/netronome/nfp/nfp_net_ethtool.c | 2 -- 3 files changed, 15 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index ab5865b955dd..84774c281b61 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -452,6 +452,7 @@ struct nfp_stat_pair { * @num_tx_rings: Currently configured number of TX rings * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP) * @num_rx_rings: Currently configured number of RX rings + * @mtu: Device MTU */ struct nfp_net_dp { struct device *dev; @@ -484,6 +485,8 @@ struct nfp_net_dp { unsigned int num_tx_rings; unsigned int num_stack_tx_rings; unsigned int num_rx_rings; + + unsigned int mtu; }; /** @@ -610,7 +613,6 @@ struct nfp_net { struct nfp_net_ring_set { unsigned int n_rings; - unsigned int mtu; unsigned int dcnt; void *rings; }; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 92d4c2991a85..862e86cb5688 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1099,7 +1099,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev) /* Receive processing */ static unsigned int -nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp, unsigned int mtu) +nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp) { unsigned int fl_bufsz; @@ -1108,7 +1108,7 @@ nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp, unsigned int mtu) fl_bufsz += NFP_NET_MAX_PREPEND; else fl_bufsz += dp->rx_offset; - fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu; + fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + dp->mtu; fl_bufsz = SKB_DATA_ALIGN(fl_bufsz); fl_bufsz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1935,12 +1935,13 @@ nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_dp *dp, struct nfp_net_dp new_dp = *dp; dp->fl_bufsz = nn->dp.fl_bufsz; - s->mtu = nn->dp.netdev->mtu; + dp->mtu = nn->dp.netdev->mtu; s->dcnt = nn->dp.rxd_cnt; s->rings = nn->dp.rx_rings; s->n_rings = nn->dp.num_rx_rings; - nn->dp.netdev->mtu = new.mtu; + nn->dp.mtu = new_dp.mtu; + nn->dp.netdev->mtu = new_dp.mtu; nn->dp.fl_bufsz = new_dp.fl_bufsz; nn->dp.rxd_cnt = new.dcnt; nn->dp.rx_rings = new.rings; @@ -2255,7 +2256,6 @@ static int nfp_net_netdev_open(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); struct nfp_net_ring_set rx = { .n_rings = nn->dp.num_rx_rings, - .mtu = nn->dp.netdev->mtu, .dcnt = nn->dp.rxd_cnt, }; struct nfp_net_ring_set tx = { @@ -2466,6 +2466,8 @@ static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp) *dp = nn->dp; nn->dp = new_dp; + + nn->dp.netdev->mtu = new_dp.mtu; } static int @@ -2554,7 +2556,6 @@ nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, { nfp_net_dp_swap(nn, dp); - nn->dp.netdev->mtu = rx ? rx->mtu : nn->dp.netdev->mtu; nn->dp.rxd_cnt = rx ? rx->dcnt : nn->dp.rxd_cnt; nn->dp.txd_cnt = tx ? tx->dcnt : nn->dp.txd_cnt; nn->dp.num_rx_rings = rx ? rx->n_rings : nn->dp.num_rx_rings; @@ -2572,8 +2573,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, { int r, err; - dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp, - rx ? rx->mtu : nn->dp.netdev->mtu); + dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp); dp->num_stack_tx_rings = tx ? tx->n_rings : dp->num_tx_rings; if (*xdp_prog) @@ -2659,7 +2659,6 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) struct nfp_net *nn = netdev_priv(netdev); struct nfp_net_ring_set rx = { .n_rings = nn->dp.num_rx_rings, - .mtu = new_mtu, .dcnt = nn->dp.rxd_cnt, }; struct nfp_net_dp *dp; @@ -2668,6 +2667,8 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) if (!dp) return -ENOMEM; + dp->mtu = new_mtu; + return nfp_net_ring_reconfig(nn, dp, &nn->dp.xdp_prog, &rx, NULL); } @@ -2988,7 +2989,6 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) { struct nfp_net_ring_set rx = { .n_rings = nn->dp.num_rx_rings, - .mtu = nn->dp.netdev->mtu, .dcnt = nn->dp.rxd_cnt, }; struct nfp_net_ring_set tx = { @@ -3263,7 +3263,8 @@ int nfp_net_netdev_init(struct net_device *netdev) netdev->mtu = nn->max_mtu; else netdev->mtu = NFP_NET_DEFAULT_MTU; - nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp, netdev->mtu); + nn->dp.mtu = netdev->mtu; + nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp); /* Advertise/enable offloads based on capabilities * diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 326ccd74a4bf..eccb01f3659f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -189,7 +189,6 @@ static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt) struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; struct nfp_net_ring_set rx = { .n_rings = nn->dp.num_rx_rings, - .mtu = nn->dp.netdev->mtu, .dcnt = rxd_cnt, }; struct nfp_net_ring_set tx = { @@ -770,7 +769,6 @@ static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx, struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; struct nfp_net_ring_set rx = { .n_rings = total_rx, - .mtu = nn->dp.netdev->mtu, .dcnt = nn->dp.rxd_cnt, }; struct nfp_net_ring_set tx = { From 9dc6b116e21b9ff258334c09d78ce26caa5ade45 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:33 -0800 Subject: [PATCH 180/399] nfp: use dp to carry xdp_prog at reconfig time Use xdp_prog member of data path struct to carry the xdp_prog to alloc/free free functions. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 1 - .../ethernet/netronome/nfp/nfp_net_common.c | 82 ++++++++----------- .../ethernet/netronome/nfp/nfp_net_ethtool.c | 6 +- 3 files changed, 37 insertions(+), 52 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 84774c281b61..19dacc3f1269 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -815,7 +815,6 @@ nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries, struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn); int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new, - struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx); #ifdef CONFIG_NFP_DEBUG diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 862e86cb5688..6ab824a48d1d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1130,21 +1130,19 @@ nfp_net_free_frag(void *frag, bool xdp) * @dp: NFP Net data path struct * @rx_ring: RX ring structure of the skb * @dma_addr: Pointer to storage for DMA address (output param) - * @xdp: Whether XDP is enabled * * This function will allcate a new page frag, map it for DMA. * * Return: allocated page frag or NULL on failure. */ static void * -nfp_net_rx_alloc_one(struct nfp_net_dp *dp, - struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr, - bool xdp) +nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, + dma_addr_t *dma_addr) { int direction; void *frag; - if (!xdp) + if (!dp->xdp_prog) frag = netdev_alloc_frag(dp->fl_bufsz); else frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD)); @@ -1153,11 +1151,11 @@ nfp_net_rx_alloc_one(struct nfp_net_dp *dp, return NULL; } - direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + direction = dp->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; *dma_addr = nfp_net_dma_map_rx(dp, frag, direction); if (dma_mapping_error(dp->dev, *dma_addr)) { - nfp_net_free_frag(frag, xdp); + nfp_net_free_frag(frag, dp->xdp_prog); nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); return NULL; } @@ -1253,7 +1251,6 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring) * nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring * @dp: NFP Net data path struct * @rx_ring: RX ring to remove buffers from - * @xdp: Whether XDP is enabled * * Assumes that the device is stopped and buffers are in [0, ring->cnt - 1) * entries. After device is disabled nfp_net_rx_ring_reset() must be called @@ -1261,9 +1258,9 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring) */ static void nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, - struct nfp_net_rx_ring *rx_ring, bool xdp) + struct nfp_net_rx_ring *rx_ring) { - int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + int direction = dp->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; unsigned int i; for (i = 0; i < rx_ring->cnt - 1; i++) { @@ -1276,7 +1273,7 @@ nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr, direction); - nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp); + nfp_net_free_frag(rx_ring->rxbufs[i].frag, dp->xdp_prog); rx_ring->rxbufs[i].dma_addr = 0; rx_ring->rxbufs[i].frag = NULL; } @@ -1286,11 +1283,10 @@ nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, * nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW) * @dp: NFP Net data path struct * @rx_ring: RX ring to remove buffers from - * @xdp: Whether XDP is enabled */ static int nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp, - struct nfp_net_rx_ring *rx_ring, bool xdp) + struct nfp_net_rx_ring *rx_ring) { struct nfp_net_rx_buf *rxbufs; unsigned int i; @@ -1299,10 +1295,9 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp, for (i = 0; i < rx_ring->cnt - 1; i++) { rxbufs[i].frag = - nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr, - xdp); + nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr); if (!rxbufs[i].frag) { - nfp_net_rx_ring_bufs_free(dp, rx_ring, xdp); + nfp_net_rx_ring_bufs_free(dp, rx_ring); return -ENOMEM; } } @@ -1896,7 +1891,7 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, static struct nfp_net_rx_ring * nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *s, bool xdp) + struct nfp_net_ring_set *s) { struct nfp_net_rx_ring *rings; unsigned int r; @@ -1911,7 +1906,7 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, if (nfp_net_rx_ring_alloc(dp, &rings[r], s->dcnt)) goto err_free_prev; - if (nfp_net_rx_ring_bufs_alloc(dp, &rings[r], xdp)) + if (nfp_net_rx_ring_bufs_alloc(dp, &rings[r])) goto err_free_ring; } @@ -1919,7 +1914,7 @@ nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, err_free_prev: while (r--) { - nfp_net_rx_ring_bufs_free(dp, &rings[r], xdp); + nfp_net_rx_ring_bufs_free(dp, &rings[r]); err_free_ring: nfp_net_rx_ring_free(&rings[r]); } @@ -1949,14 +1944,13 @@ nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_dp *dp, } static void -nfp_net_rx_ring_set_free(struct nfp_net_dp *dp, struct nfp_net_ring_set *s, - bool xdp) +nfp_net_rx_ring_set_free(struct nfp_net_dp *dp, struct nfp_net_ring_set *s) { struct nfp_net_rx_ring *rings = s->rings; unsigned int r; for (r = 0; r < s->n_rings; r++) { - nfp_net_rx_ring_bufs_free(dp, &rings[r], xdp); + nfp_net_rx_ring_bufs_free(dp, &rings[r]); nfp_net_rx_ring_free(&rings[r]); } @@ -2292,8 +2286,7 @@ static int nfp_net_netdev_open(struct net_device *netdev) goto err_cleanup_vec_p; } - nn->dp.rx_rings = nfp_net_rx_ring_set_prepare(nn, &nn->dp, &rx, - nn->dp.xdp_prog); + nn->dp.rx_rings = nfp_net_rx_ring_set_prepare(nn, &nn->dp, &rx); if (!nn->dp.rx_rings) { err = -ENOMEM; goto err_cleanup_vec; @@ -2340,7 +2333,7 @@ static int nfp_net_netdev_open(struct net_device *netdev) err_free_rings: nfp_net_tx_ring_set_free(&tx); err_free_rx_rings: - nfp_net_rx_ring_set_free(&nn->dp, &rx, nn->dp.xdp_prog); + nfp_net_rx_ring_set_free(&nn->dp, &rx); err_cleanup_vec: r = nn->dp.num_r_vecs; err_cleanup_vec_p: @@ -2381,8 +2374,7 @@ static void nfp_net_close_free_all(struct nfp_net *nn) unsigned int r; for (r = 0; r < nn->dp.num_rx_rings; r++) { - nfp_net_rx_ring_bufs_free(&nn->dp, &nn->dp.rx_rings[r], - nn->dp.xdp_prog); + nfp_net_rx_ring_bufs_free(&nn->dp, &nn->dp.rx_rings[r]); nfp_net_rx_ring_free(&nn->dp.rx_rings[r]); } for (r = 0; r < nn->dp.num_tx_rings; r++) @@ -2472,7 +2464,6 @@ static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp) static int nfp_net_ring_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp, - struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) { @@ -2486,7 +2477,7 @@ nfp_net_ring_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp, swap(dp->num_r_vecs, nn->dp.num_r_vecs); swap(dp->num_stack_tx_rings, nn->dp.num_stack_tx_rings); - *xdp_prog = xchg(&nn->dp.xdp_prog, *xdp_prog); + dp->xdp_prog = xchg(&nn->dp.xdp_prog, dp->xdp_prog); for (r = 0; r < nn->max_r_vecs; r++) nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r); @@ -2530,11 +2521,10 @@ struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn) static int nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp, - struct bpf_prog *xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) { /* XDP-enabled tests */ - if (!xdp_prog) + if (!dp->xdp_prog) return 0; if (dp->fl_bufsz > PAGE_SIZE) { nn_warn(nn, "MTU too large w/ XDP enabled\n"); @@ -2550,7 +2540,6 @@ nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp, static void nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, - struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) { @@ -2560,7 +2549,6 @@ nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, nn->dp.txd_cnt = tx ? tx->dcnt : nn->dp.txd_cnt; nn->dp.num_rx_rings = rx ? rx->n_rings : nn->dp.num_rx_rings; nn->dp.num_tx_rings = tx ? tx->n_rings : nn->dp.num_tx_rings; - *xdp_prog = xchg(&nn->dp.xdp_prog, *xdp_prog); if (!netif_is_rxfh_configured(nn->dp.netdev)) nfp_net_rss_init_itbl(nn); @@ -2568,7 +2556,6 @@ nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, - struct bpf_prog **xdp_prog, struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) { int r, err; @@ -2576,18 +2563,18 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp); dp->num_stack_tx_rings = tx ? tx->n_rings : dp->num_tx_rings; - if (*xdp_prog) + if (dp->xdp_prog) dp->num_stack_tx_rings -= rx ? rx->n_rings : dp->num_rx_rings; dp->num_r_vecs = max(rx ? rx->n_rings : dp->num_rx_rings, dp->num_stack_tx_rings); - err = nfp_net_check_config(nn, dp, *xdp_prog, rx, tx); + err = nfp_net_check_config(nn, dp, rx, tx); if (err) goto exit_free_dp; if (!netif_running(dp->netdev)) { - nfp_net_ring_reconfig_down(nn, dp, xdp_prog, rx, tx); + nfp_net_ring_reconfig_down(nn, dp, rx, tx); err = 0; goto exit_free_dp; @@ -2602,7 +2589,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, } } if (rx) { - if (!nfp_net_rx_ring_set_prepare(nn, dp, rx, *xdp_prog)) { + if (!nfp_net_rx_ring_set_prepare(nn, dp, rx)) { err = -ENOMEM; goto err_cleanup_vecs; } @@ -2618,14 +2605,14 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, nfp_net_close_stack(nn); nfp_net_clear_config_and_disable(nn); - err = nfp_net_ring_swap_enable(nn, dp, xdp_prog, rx, tx); + err = nfp_net_ring_swap_enable(nn, dp, rx, tx); if (err) { int err2; nfp_net_clear_config_and_disable(nn); /* Try with old configuration and old rings */ - err2 = nfp_net_ring_swap_enable(nn, dp, xdp_prog, rx, tx); + err2 = nfp_net_ring_swap_enable(nn, dp, rx, tx); if (err2) nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n", err, err2); @@ -2634,7 +2621,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); if (rx) - nfp_net_rx_ring_set_free(dp, rx, *xdp_prog); + nfp_net_rx_ring_set_free(dp, rx); if (tx) nfp_net_tx_ring_set_free(tx); @@ -2646,7 +2633,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, err_free_rx: if (rx) - nfp_net_rx_ring_set_free(dp, rx, *xdp_prog); + nfp_net_rx_ring_set_free(dp, rx); err_cleanup_vecs: for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); @@ -2669,7 +2656,7 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) dp->mtu = new_mtu; - return nfp_net_ring_reconfig(nn, dp, &nn->dp.xdp_prog, &rx, NULL); + return nfp_net_ring_reconfig(nn, dp, &rx, NULL); } static void nfp_net_stat64(struct net_device *netdev, @@ -2987,6 +2974,7 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog) static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) { + struct bpf_prog *old_prog = nn->dp.xdp_prog; struct nfp_net_ring_set rx = { .n_rings = nn->dp.num_rx_rings, .dcnt = nn->dp.rxd_cnt, @@ -3015,16 +3003,16 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) if (!dp) return -ENOMEM; + dp->xdp_prog = prog; tx.n_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */ - err = nfp_net_ring_reconfig(nn, dp, &prog, &rx, &tx); + err = nfp_net_ring_reconfig(nn, dp, &rx, &tx); if (err) return err; - /* @prog got swapped and is now the old one */ - if (prog) - bpf_prog_put(prog); + if (old_prog) + bpf_prog_put(old_prog); nfp_net_xdp_offload(nn, nn->dp.xdp_prog); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index eccb01f3659f..63c1d9ab2335 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -206,8 +206,7 @@ static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt) if (!dp) return -ENOMEM; - return nfp_net_ring_reconfig(nn, dp, &nn->dp.xdp_prog, - reconfig_rx, reconfig_tx); + return nfp_net_ring_reconfig(nn, dp, reconfig_rx, reconfig_tx); } static int nfp_net_set_ringparam(struct net_device *netdev, @@ -791,8 +790,7 @@ static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx, if (!dp) return -ENOMEM; - return nfp_net_ring_reconfig(nn, dp, &nn->dp.xdp_prog, - reconfig_rx, reconfig_tx); + return nfp_net_ring_reconfig(nn, dp, reconfig_rx, reconfig_tx); } static int nfp_net_set_channels(struct net_device *netdev, From 892a7f700b361882105739632ccbd6ceb848c21d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:34 -0800 Subject: [PATCH 181/399] nfp: switch to using data path structures for reconfiguration Instead of passing around sets of rings and their parameters just store all information in the data path structure. We will no longer user xchg() on XDP programs when we swap programs while the traffic is guaranteed not to be flowing. This allows us to simply assign the entire data path structures instead of copying field by field. The optimization to reallocate only the rings on the side (RX/TX) which has been changed is also removed since it seems like it's not worth the code complexity. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 10 +- .../ethernet/netronome/nfp/nfp_net_common.c | 260 ++++++------------ .../ethernet/netronome/nfp/nfp_net_ethtool.c | 46 +--- 3 files changed, 89 insertions(+), 227 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 19dacc3f1269..5a92f6e41dae 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -611,12 +611,6 @@ struct nfp_net { struct nfp_eth_table_port *eth_port; }; -struct nfp_net_ring_set { - unsigned int n_rings; - unsigned int dcnt; - void *rings; -}; - /* Functions to read/write from/to a BAR * Performs any endian conversion necessary. */ @@ -813,9 +807,7 @@ nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries, unsigned int n); struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn); -int -nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new, - struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx); +int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new); #ifdef CONFIG_NFP_DEBUG void nfp_net_debugfs_create(void); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 6ab824a48d1d..a9359da64f80 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1740,20 +1740,20 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring) /** * nfp_net_tx_ring_alloc() - Allocate resource for a TX ring + * @dp: NFP Net data path struct * @tx_ring: TX Ring structure to allocate - * @cnt: Ring buffer count * @is_xdp: True if ring will be used for XDP * * Return: 0 on success, negative errno otherwise. */ static int -nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) +nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring, + bool is_xdp) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - struct nfp_net_dp *dp = &r_vec->nfp_net->dp; int sz; - tx_ring->cnt = cnt; + tx_ring->cnt = dp->txd_cnt; tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt; tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size, @@ -1777,61 +1777,45 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp) return -ENOMEM; } -static struct nfp_net_tx_ring * -nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *s) +static int nfp_net_tx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp) { - struct nfp_net_tx_ring *rings; unsigned int r; - rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL); - if (!rings) - return NULL; + dp->tx_rings = kcalloc(dp->num_tx_rings, sizeof(*dp->tx_rings), + GFP_KERNEL); + if (!dp->tx_rings) + return -ENOMEM; - for (r = 0; r < s->n_rings; r++) { + for (r = 0; r < dp->num_tx_rings; r++) { int bias = 0; if (r >= dp->num_stack_tx_rings) bias = dp->num_stack_tx_rings; - nfp_net_tx_ring_init(&rings[r], &nn->r_vecs[r - bias], r); + nfp_net_tx_ring_init(&dp->tx_rings[r], &nn->r_vecs[r - bias], + r); - if (nfp_net_tx_ring_alloc(&rings[r], s->dcnt, bias)) + if (nfp_net_tx_ring_alloc(dp, &dp->tx_rings[r], bias)) goto err_free_prev; } - return s->rings = rings; + return 0; err_free_prev: while (r--) - nfp_net_tx_ring_free(&rings[r]); - kfree(rings); - return NULL; + nfp_net_tx_ring_free(&dp->tx_rings[r]); + kfree(dp->tx_rings); + return -ENOMEM; } -static void -nfp_net_tx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s) +static void nfp_net_tx_rings_free(struct nfp_net_dp *dp) { - struct nfp_net_ring_set new = *s; - - s->dcnt = nn->dp.txd_cnt; - s->rings = nn->dp.tx_rings; - s->n_rings = nn->dp.num_tx_rings; - - nn->dp.txd_cnt = new.dcnt; - nn->dp.tx_rings = new.rings; - nn->dp.num_tx_rings = new.n_rings; -} - -static void nfp_net_tx_ring_set_free(struct nfp_net_ring_set *s) -{ - struct nfp_net_tx_ring *rings = s->rings; unsigned int r; - for (r = 0; r < s->n_rings; r++) - nfp_net_tx_ring_free(&rings[r]); + for (r = 0; r < dp->num_tx_rings; r++) + nfp_net_tx_ring_free(&dp->tx_rings[r]); - kfree(rings); + kfree(dp->tx_rings); } /** @@ -1860,17 +1844,15 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) * nfp_net_rx_ring_alloc() - Allocate resource for a RX ring * @dp: NFP Net data path struct * @rx_ring: RX ring to allocate - * @cnt: Ring buffer count * * Return: 0 on success, negative errno otherwise. */ static int -nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, - u32 cnt) +nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring) { int sz; - rx_ring->cnt = cnt; + rx_ring->cnt = dp->rxd_cnt; rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt; rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); @@ -1889,72 +1871,47 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, return -ENOMEM; } -static struct nfp_net_rx_ring * -nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *s) +static int nfp_net_rx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp) { - struct nfp_net_rx_ring *rings; unsigned int r; - rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL); - if (!rings) - return NULL; + dp->rx_rings = kcalloc(dp->num_rx_rings, sizeof(*dp->rx_rings), + GFP_KERNEL); + if (!dp->rx_rings) + return -ENOMEM; - for (r = 0; r < s->n_rings; r++) { - nfp_net_rx_ring_init(&rings[r], &nn->r_vecs[r], r); + for (r = 0; r < dp->num_rx_rings; r++) { + nfp_net_rx_ring_init(&dp->rx_rings[r], &nn->r_vecs[r], r); - if (nfp_net_rx_ring_alloc(dp, &rings[r], s->dcnt)) + if (nfp_net_rx_ring_alloc(dp, &dp->rx_rings[r])) goto err_free_prev; - if (nfp_net_rx_ring_bufs_alloc(dp, &rings[r])) + if (nfp_net_rx_ring_bufs_alloc(dp, &dp->rx_rings[r])) goto err_free_ring; } - return s->rings = rings; + return 0; err_free_prev: while (r--) { - nfp_net_rx_ring_bufs_free(dp, &rings[r]); + nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]); err_free_ring: - nfp_net_rx_ring_free(&rings[r]); + nfp_net_rx_ring_free(&dp->rx_rings[r]); } - kfree(rings); - return NULL; + kfree(dp->rx_rings); + return -ENOMEM; } -static void -nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *s) +static void nfp_net_rx_rings_free(struct nfp_net_dp *dp) { - struct nfp_net_ring_set new = *s; - struct nfp_net_dp new_dp = *dp; - - dp->fl_bufsz = nn->dp.fl_bufsz; - dp->mtu = nn->dp.netdev->mtu; - s->dcnt = nn->dp.rxd_cnt; - s->rings = nn->dp.rx_rings; - s->n_rings = nn->dp.num_rx_rings; - - nn->dp.mtu = new_dp.mtu; - nn->dp.netdev->mtu = new_dp.mtu; - nn->dp.fl_bufsz = new_dp.fl_bufsz; - nn->dp.rxd_cnt = new.dcnt; - nn->dp.rx_rings = new.rings; - nn->dp.num_rx_rings = new.n_rings; -} - -static void -nfp_net_rx_ring_set_free(struct nfp_net_dp *dp, struct nfp_net_ring_set *s) -{ - struct nfp_net_rx_ring *rings = s->rings; unsigned int r; - for (r = 0; r < s->n_rings; r++) { - nfp_net_rx_ring_bufs_free(dp, &rings[r]); - nfp_net_rx_ring_free(&rings[r]); + for (r = 0; r < dp->num_rx_rings; r++) { + nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]); + nfp_net_rx_ring_free(&dp->rx_rings[r]); } - kfree(rings); + kfree(dp->rx_rings); } static void @@ -2248,14 +2205,6 @@ static void nfp_net_open_stack(struct nfp_net *nn) static int nfp_net_netdev_open(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - struct nfp_net_ring_set rx = { - .n_rings = nn->dp.num_rx_rings, - .dcnt = nn->dp.rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = nn->dp.num_tx_rings, - .dcnt = nn->dp.txd_cnt, - }; int err, r; if (nn->dp.ctrl & NFP_NET_CFG_CTRL_ENABLE) { @@ -2286,17 +2235,13 @@ static int nfp_net_netdev_open(struct net_device *netdev) goto err_cleanup_vec_p; } - nn->dp.rx_rings = nfp_net_rx_ring_set_prepare(nn, &nn->dp, &rx); - if (!nn->dp.rx_rings) { - err = -ENOMEM; + err = nfp_net_rx_rings_prepare(nn, &nn->dp); + if (err) goto err_cleanup_vec; - } - nn->dp.tx_rings = nfp_net_tx_ring_set_prepare(nn, &nn->dp, &tx); - if (!nn->dp.tx_rings) { - err = -ENOMEM; + err = nfp_net_tx_rings_prepare(nn, &nn->dp); + if (err) goto err_free_rx_rings; - } for (r = 0; r < nn->max_r_vecs; r++) nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r); @@ -2331,9 +2276,9 @@ static int nfp_net_netdev_open(struct net_device *netdev) return 0; err_free_rings: - nfp_net_tx_ring_set_free(&tx); + nfp_net_tx_rings_free(&nn->dp); err_free_rx_rings: - nfp_net_rx_ring_set_free(&nn->dp, &rx); + nfp_net_rx_rings_free(&nn->dp); err_cleanup_vec: r = nn->dp.num_r_vecs; err_cleanup_vec_p: @@ -2460,31 +2405,21 @@ static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp) nn->dp = new_dp; nn->dp.netdev->mtu = new_dp.mtu; + + if (!netif_is_rxfh_configured(nn->dp.netdev)) + nfp_net_rss_init_itbl(nn); } -static int -nfp_net_ring_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *rx, - struct nfp_net_ring_set *tx) +static int nfp_net_dp_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp) { unsigned int r; int err; - if (rx) - nfp_net_rx_ring_set_swap(nn, dp, rx); - if (tx) - nfp_net_tx_ring_set_swap(nn, tx); - - swap(dp->num_r_vecs, nn->dp.num_r_vecs); - swap(dp->num_stack_tx_rings, nn->dp.num_stack_tx_rings); - dp->xdp_prog = xchg(&nn->dp.xdp_prog, dp->xdp_prog); + nfp_net_dp_swap(nn, dp); for (r = 0; r < nn->max_r_vecs; r++) nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r); - if (!netif_is_rxfh_configured(nn->dp.netdev)) - nfp_net_rss_init_itbl(nn); - err = netif_set_real_num_rx_queues(nn->dp.netdev, nn->dp.num_rx_rings); if (err) return err; @@ -2519,9 +2454,7 @@ struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn) return new; } -static int -nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) +static int nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp) { /* XDP-enabled tests */ if (!dp->xdp_prog) @@ -2530,7 +2463,7 @@ nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp, nn_warn(nn, "MTU too large w/ XDP enabled\n"); return -EINVAL; } - if (tx && tx->n_rings > nn->max_tx_rings) { + if (dp->num_tx_rings > nn->max_tx_rings) { nn_warn(nn, "Insufficient number of TX rings w/ XDP enabled\n"); return -EINVAL; } @@ -2538,44 +2471,24 @@ nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp, return 0; } -static void -nfp_net_ring_reconfig_down(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *rx, - struct nfp_net_ring_set *tx) -{ - nfp_net_dp_swap(nn, dp); - - nn->dp.rxd_cnt = rx ? rx->dcnt : nn->dp.rxd_cnt; - nn->dp.txd_cnt = tx ? tx->dcnt : nn->dp.txd_cnt; - nn->dp.num_rx_rings = rx ? rx->n_rings : nn->dp.num_rx_rings; - nn->dp.num_tx_rings = tx ? tx->n_rings : nn->dp.num_tx_rings; - - if (!netif_is_rxfh_configured(nn->dp.netdev)) - nfp_net_rss_init_itbl(nn); -} - -int -nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, - struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx) +int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp) { int r, err; dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp); - dp->num_stack_tx_rings = tx ? tx->n_rings : dp->num_tx_rings; + dp->num_stack_tx_rings = dp->num_tx_rings; if (dp->xdp_prog) - dp->num_stack_tx_rings -= rx ? rx->n_rings : dp->num_rx_rings; + dp->num_stack_tx_rings -= dp->num_rx_rings; - dp->num_r_vecs = max(rx ? rx->n_rings : dp->num_rx_rings, - dp->num_stack_tx_rings); + dp->num_r_vecs = max(dp->num_rx_rings, dp->num_stack_tx_rings); - err = nfp_net_check_config(nn, dp, rx, tx); + err = nfp_net_check_config(nn, dp); if (err) goto exit_free_dp; if (!netif_running(dp->netdev)) { - nfp_net_ring_reconfig_down(nn, dp, rx, tx); - + nfp_net_dp_swap(nn, dp); err = 0; goto exit_free_dp; } @@ -2588,31 +2501,27 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, goto err_cleanup_vecs; } } - if (rx) { - if (!nfp_net_rx_ring_set_prepare(nn, dp, rx)) { - err = -ENOMEM; - goto err_cleanup_vecs; - } - } - if (tx) { - if (!nfp_net_tx_ring_set_prepare(nn, dp, tx)) { - err = -ENOMEM; - goto err_free_rx; - } - } + + err = nfp_net_rx_rings_prepare(nn, dp); + if (err) + goto err_cleanup_vecs; + + err = nfp_net_tx_rings_prepare(nn, dp); + if (err) + goto err_free_rx; /* Stop device, swap in new rings, try to start the firmware */ nfp_net_close_stack(nn); nfp_net_clear_config_and_disable(nn); - err = nfp_net_ring_swap_enable(nn, dp, rx, tx); + err = nfp_net_dp_swap_enable(nn, dp); if (err) { int err2; nfp_net_clear_config_and_disable(nn); /* Try with old configuration and old rings */ - err2 = nfp_net_ring_swap_enable(nn, dp, rx, tx); + err2 = nfp_net_dp_swap_enable(nn, dp); if (err2) nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n", err, err2); @@ -2620,10 +2529,8 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); - if (rx) - nfp_net_rx_ring_set_free(dp, rx); - if (tx) - nfp_net_tx_ring_set_free(tx); + nfp_net_rx_rings_free(dp); + nfp_net_tx_rings_free(dp); nfp_net_open_stack(nn); exit_free_dp: @@ -2632,8 +2539,7 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, return err; err_free_rx: - if (rx) - nfp_net_rx_ring_set_free(dp, rx); + nfp_net_rx_rings_free(dp); err_cleanup_vecs: for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--) nfp_net_cleanup_vector(nn, &nn->r_vecs[r]); @@ -2644,10 +2550,6 @@ nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp, static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) { struct nfp_net *nn = netdev_priv(netdev); - struct nfp_net_ring_set rx = { - .n_rings = nn->dp.num_rx_rings, - .dcnt = nn->dp.rxd_cnt, - }; struct nfp_net_dp *dp; dp = nfp_net_clone_dp(nn); @@ -2656,7 +2558,7 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu) dp->mtu = new_mtu; - return nfp_net_ring_reconfig(nn, dp, &rx, NULL); + return nfp_net_ring_reconfig(nn, dp); } static void nfp_net_stat64(struct net_device *netdev, @@ -2975,14 +2877,6 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog) static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) { struct bpf_prog *old_prog = nn->dp.xdp_prog; - struct nfp_net_ring_set rx = { - .n_rings = nn->dp.num_rx_rings, - .dcnt = nn->dp.rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = nn->dp.num_tx_rings, - .dcnt = nn->dp.txd_cnt, - }; struct nfp_net_dp *dp; int err; @@ -3004,10 +2898,10 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) return -ENOMEM; dp->xdp_prog = prog; - tx.n_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; + dp->num_tx_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */ - err = nfp_net_ring_reconfig(nn, dp, &rx, &tx); + err = nfp_net_ring_reconfig(nn, dp); if (err) return err; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 63c1d9ab2335..ed22a813e579 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -186,27 +186,16 @@ static void nfp_net_get_ringparam(struct net_device *netdev, static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt) { - struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; - struct nfp_net_ring_set rx = { - .n_rings = nn->dp.num_rx_rings, - .dcnt = rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = nn->dp.num_tx_rings, - .dcnt = txd_cnt, - }; struct nfp_net_dp *dp; - if (nn->dp.rxd_cnt != rxd_cnt) - reconfig_rx = ℞ - if (nn->dp.txd_cnt != txd_cnt) - reconfig_tx = &tx; - dp = nfp_net_clone_dp(nn); if (!dp) return -ENOMEM; - return nfp_net_ring_reconfig(nn, dp, reconfig_rx, reconfig_tx); + dp->rxd_cnt = rxd_cnt; + dp->txd_cnt = txd_cnt; + + return nfp_net_ring_reconfig(nn, dp); } static int nfp_net_set_ringparam(struct net_device *netdev, @@ -765,32 +754,19 @@ static void nfp_net_get_channels(struct net_device *netdev, static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx, unsigned int total_tx) { - struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL; - struct nfp_net_ring_set rx = { - .n_rings = total_rx, - .dcnt = nn->dp.rxd_cnt, - }; - struct nfp_net_ring_set tx = { - .n_rings = total_tx, - .dcnt = nn->dp.txd_cnt, - }; struct nfp_net_dp *dp; - if (nn->dp.num_rx_rings != total_rx) - reconfig_rx = ℞ - if (nn->dp.num_stack_tx_rings != total_tx || - (nn->dp.xdp_prog && reconfig_rx)) - reconfig_tx = &tx; - - /* nfp_net_check_config() will catch tx.n_rings > nn->max_tx_rings */ - if (nn->dp.xdp_prog) - tx.n_rings += total_rx; - dp = nfp_net_clone_dp(nn); if (!dp) return -ENOMEM; - return nfp_net_ring_reconfig(nn, dp, reconfig_rx, reconfig_tx); + dp->num_rx_rings = total_rx; + dp->num_tx_rings = total_tx; + /* nfp_net_check_config() will catch num_tx_rings > nn->max_tx_rings */ + if (dp->xdp_prog) + dp->num_tx_rings += total_rx; + + return nfp_net_ring_reconfig(nn, dp); } static int nfp_net_set_channels(struct net_device *netdev, From c487e6b199eab3af14e54406d97cc3c149e591e1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:35 -0800 Subject: [PATCH 182/399] nfp: store dma direction in data path structure Instead of testing if xdp_prog is present store the dma direction in data path structure. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 11 +++-- .../ethernet/netronome/nfp/nfp_net_common.c | 45 +++++++------------ 2 files changed, 24 insertions(+), 32 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 5a92f6e41dae..db92463da440 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -438,6 +438,7 @@ struct nfp_stat_pair { * @bpf_offload_skip_sw: Offloaded BPF program will not be rerun by cls_bpf * @bpf_offload_xdp: Offloaded BPF program is XDP * @chained_metadata_format: Firemware will use new metadata format + * @rx_dma_dir: Mapping direction for RX buffers * @ctrl: Local copy of the control register/word. * @fl_bufsz: Currently configured size of the freelist buffers * @rx_offset: Offset in the RX buffers where packet data starts @@ -458,10 +459,12 @@ struct nfp_net_dp { struct device *dev; struct net_device *netdev; - unsigned is_vf:1; - unsigned bpf_offload_skip_sw:1; - unsigned bpf_offload_xdp:1; - unsigned chained_metadata_format:1; + u8 is_vf:1; + u8 bpf_offload_skip_sw:1; + u8 bpf_offload_xdp:1; + u8 chained_metadata_format:1; + + u8 rx_dma_dir; u32 ctrl; u32 fl_bufsz; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index a9359da64f80..ab03f2f301cd 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -85,20 +85,18 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver, put_unaligned_le32(reg, fw_ver); } -static dma_addr_t -nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag, int direction) +static dma_addr_t nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag) { return dma_map_single(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM, dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA, - direction); + dp->rx_dma_dir); } -static void -nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr, - int direction) +static void nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr) { dma_unmap_single(dp->dev, dma_addr, - dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA, direction); + dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA, + dp->rx_dma_dir); } /* Firmware reconfig @@ -991,8 +989,7 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) if (!tx_ring->txbufs[idx].frag) continue; - nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr, - DMA_BIDIRECTIONAL); + nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); done_pkts++; @@ -1037,8 +1034,7 @@ nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) tx_buf = &tx_ring->txbufs[idx]; if (tx_ring == r_vec->xdp_ring) { - nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr, - DMA_BIDIRECTIONAL); + nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr); __free_page(virt_to_page(tx_ring->txbufs[idx].frag)); } else { struct sk_buff *skb = tx_ring->txbufs[idx].skb; @@ -1139,7 +1135,6 @@ static void * nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr) { - int direction; void *frag; if (!dp->xdp_prog) @@ -1151,9 +1146,7 @@ nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, return NULL; } - direction = dp->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - - *dma_addr = nfp_net_dma_map_rx(dp, frag, direction); + *dma_addr = nfp_net_dma_map_rx(dp, frag); if (dma_mapping_error(dp->dev, *dma_addr)) { nfp_net_free_frag(frag, dp->xdp_prog); nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); @@ -1163,9 +1156,7 @@ nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, return frag; } -static void * -nfp_net_napi_alloc_one(struct nfp_net_dp *dp, int direction, - dma_addr_t *dma_addr) +static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr) { void *frag; @@ -1178,7 +1169,7 @@ nfp_net_napi_alloc_one(struct nfp_net_dp *dp, int direction, return NULL; } - *dma_addr = nfp_net_dma_map_rx(dp, frag, direction); + *dma_addr = nfp_net_dma_map_rx(dp, frag); if (dma_mapping_error(dp->dev, *dma_addr)) { nfp_net_free_frag(frag, dp->xdp_prog); nn_dp_warn(dp, "Failed to map DMA RX buffer\n"); @@ -1260,7 +1251,6 @@ static void nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring) { - int direction = dp->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; unsigned int i; for (i = 0; i < rx_ring->cnt - 1; i++) { @@ -1271,8 +1261,7 @@ nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp, if (!rx_ring->rxbufs[i].frag) continue; - nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr, - direction); + nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr); nfp_net_free_frag(rx_ring->rxbufs[i].frag, dp->xdp_prog); rx_ring->rxbufs[i].dma_addr = 0; rx_ring->rxbufs[i].frag = NULL; @@ -1478,7 +1467,7 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, return false; } - new_frag = nfp_net_napi_alloc_one(dp, DMA_BIDIRECTIONAL, &new_dma_addr); + new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr); if (unlikely(!new_frag)) { nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL); return false; @@ -1544,12 +1533,10 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) unsigned int true_bufsz; struct sk_buff *skb; int pkts_polled = 0; - int rx_dma_map_dir; int idx; rcu_read_lock(); xdp_prog = READ_ONCE(dp->xdp_prog); - rx_dma_map_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz; tx_ring = r_vec->xdp_ring; @@ -1639,14 +1626,13 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL); continue; } - new_frag = nfp_net_napi_alloc_one(dp, rx_dma_map_dir, - &new_dma_addr); + new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr); if (unlikely(!new_frag)) { nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb); continue; } - nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr, rx_dma_map_dir); + nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr); nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr); @@ -2899,6 +2885,7 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) dp->xdp_prog = prog; dp->num_tx_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; + dp->rx_dma_dir = prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */ err = nfp_net_ring_reconfig(nn, dp); @@ -3128,6 +3115,8 @@ int nfp_net_netdev_init(struct net_device *netdev) nn->dp.chained_metadata_format = nn->fw_ver.major > 3; + nn->dp.rx_dma_dir = DMA_FROM_DEVICE; + /* Get some of the read-only fields from the BAR */ nn->cap = nn_readl(nn, NFP_NET_CFG_CAP); nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU); From 97717aca618a85d9e52327b4509a3b95c2f8f121 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:36 -0800 Subject: [PATCH 183/399] nfp: validate rx offset from the BAR and size down it's field NFP_NET_CFG_RX_OFFSET is 32bit wide, make sure what we read from there is reasonable for packet headroom. This allows us to store the rx_offset in a 8bit variable. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 6 +++--- .../net/ethernet/netronome/nfp/nfp_net_common.c | 14 +++++++++++--- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index db92463da440..5f0547c6efb8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -439,9 +439,9 @@ struct nfp_stat_pair { * @bpf_offload_xdp: Offloaded BPF program is XDP * @chained_metadata_format: Firemware will use new metadata format * @rx_dma_dir: Mapping direction for RX buffers + * @rx_offset: Offset in the RX buffers where packet data starts * @ctrl: Local copy of the control register/word. * @fl_bufsz: Currently configured size of the freelist buffers - * @rx_offset: Offset in the RX buffers where packet data starts * @xdp_prog: Installed XDP program * @tx_rings: Array of pre-allocated TX ring structures * @rx_rings: Array of pre-allocated RX ring structures @@ -466,11 +466,11 @@ struct nfp_net_dp { u8 rx_dma_dir; + u8 rx_offset; + u32 ctrl; u32 fl_bufsz; - u32 rx_offset; - struct bpf_prog *xdp_prog; struct nfp_net_tx_ring *tx_rings; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index ab03f2f301cd..513f55dd746b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3124,10 +3124,18 @@ int nfp_net_netdev_init(struct net_device *netdev) nfp_net_write_mac_addr(nn); /* Determine RX packet/metadata boundary offset */ - if (nn->fw_ver.major >= 2) - nn->dp.rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET); - else + if (nn->fw_ver.major >= 2) { + u32 reg; + + reg = nn_readl(nn, NFP_NET_CFG_RX_OFFSET); + if (reg > NFP_NET_MAX_PREPEND) { + nn_err(nn, "Invalid rx offset: %d\n", reg); + return -EINVAL; + } + nn->dp.rx_offset = reg; + } else { nn->dp.rx_offset = NFP_NET_RX_OFFSET; + } /* Set default MTU and Freelist buffer size */ if (nn->max_mtu < NFP_NET_DEFAULT_MTU) From 1abae31953996283e1956af0b8ffa72c2b682e77 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:37 -0800 Subject: [PATCH 184/399] nfp: reorganize pkt_off variable Rename pkt_off variable to dma_off, it should hold data offset counting from beginning of DMA mapping. Compute the value only in XDP context. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/nfp_net_common.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 513f55dd746b..0e4fa6802733 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1453,7 +1453,7 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring, static bool nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, struct nfp_net_tx_ring *tx_ring, - struct nfp_net_rx_buf *rxbuf, unsigned int pkt_off, + struct nfp_net_rx_buf *rxbuf, unsigned int dma_off, unsigned int pkt_len) { struct nfp_net_tx_buf *txbuf; @@ -1484,14 +1484,14 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, txbuf->pkt_cnt = 1; txbuf->real_len = pkt_len; - dma_sync_single_for_device(dp->dev, rxbuf->dma_addr + pkt_off, + dma_sync_single_for_device(dp->dev, rxbuf->dma_addr + dma_off, pkt_len, DMA_BIDIRECTIONAL); /* Build TX descriptor */ txd = &tx_ring->txds[wr_idx]; txd->offset_eop = PCIE_DESC_TX_EOP; txd->dma_len = cpu_to_le16(pkt_len); - nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + pkt_off); + nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + dma_off); txd->data_len = cpu_to_le16(pkt_len); txd->flags = 0; @@ -1541,7 +1541,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) tx_ring = r_vec->xdp_ring; while (pkts_polled < budget) { - unsigned int meta_len, data_len, data_off, pkt_len, pkt_off; + unsigned int meta_len, data_len, data_off, pkt_len; struct nfp_net_rx_buf *rxbuf; struct nfp_net_rx_desc *rxd; dma_addr_t new_dma_addr; @@ -1579,10 +1579,9 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) pkt_len = data_len - meta_len; if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) - pkt_off = meta_len; + data_off = NFP_NET_RX_BUF_HEADROOM + meta_len; else - pkt_off = dp->rx_offset; - data_off = NFP_NET_RX_BUF_HEADROOM + pkt_off; + data_off = NFP_NET_RX_BUF_HEADROOM + dp->rx_offset; /* Stats update */ u64_stats_update_begin(&r_vec->rx_sync); @@ -1592,10 +1591,12 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF && dp->bpf_offload_xdp)) { + unsigned int dma_off; int act; + dma_off = data_off - NFP_NET_RX_BUF_HEADROOM; dma_sync_single_for_cpu(dp->dev, - rxbuf->dma_addr + pkt_off, + rxbuf->dma_addr + dma_off, pkt_len, DMA_BIDIRECTIONAL); act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off, pkt_len); @@ -1605,7 +1606,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) case XDP_TX: if (unlikely(!nfp_net_tx_xdp_buf(dp, rx_ring, tx_ring, rxbuf, - pkt_off, + dma_off, pkt_len))) trace_xdp_exception(dp->netdev, xdp_prog, act); From b92fb77f27af90d3ee785eedc326f80cb6190597 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:38 -0800 Subject: [PATCH 185/399] nfp: prepare metadata handling for xdp_adjust_head() XDP may require us to move metadata to make room for pushing headers. Track meta data location with a pointer and pass it explicitly to functions. While at it validate that meta_len from the descriptor is not bogus. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/nfp_net_common.c | 28 +++++++++++++------ 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 0e4fa6802733..fe7c3f6d820d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1385,24 +1385,21 @@ static void nfp_net_set_hash(struct net_device *netdev, struct sk_buff *skb, static void nfp_net_set_hash_desc(struct net_device *netdev, struct sk_buff *skb, - struct nfp_net_rx_desc *rxd) + void *data, struct nfp_net_rx_desc *rxd) { - struct nfp_net_rx_hash *rx_hash; + struct nfp_net_rx_hash *rx_hash = data; if (!(rxd->rxd.flags & PCIE_DESC_RX_RSS)) return; - rx_hash = (struct nfp_net_rx_hash *)(skb->data - sizeof(*rx_hash)); - nfp_net_set_hash(netdev, skb, get_unaligned_be32(&rx_hash->hash_type), &rx_hash->hash); } static void * nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb, - int meta_len) + void *data, int meta_len) { - u8 *data = skb->data - meta_len; u32 meta_info; meta_info = get_unaligned_be32(data); @@ -1546,6 +1543,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) struct nfp_net_rx_desc *rxd; dma_addr_t new_dma_addr; void *new_frag; + u8 *meta; idx = rx_ring->rd_p & (rx_ring->cnt - 1); @@ -1589,6 +1587,17 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) r_vec->rx_bytes += pkt_len; u64_stats_update_end(&r_vec->rx_sync); + /* Pointer to start of metadata */ + meta = rxbuf->frag + data_off - meta_len; + + if (unlikely(meta_len > NFP_NET_MAX_PREPEND || + (dp->rx_offset && meta_len > dp->rx_offset))) { + nn_dp_warn(dp, "oversized RX packet metadata %u\n", + meta_len); + nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL); + continue; + } + if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF && dp->bpf_offload_xdp)) { unsigned int dma_off; @@ -1641,12 +1650,13 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) skb_put(skb, pkt_len); if (!dp->chained_metadata_format) { - nfp_net_set_hash_desc(dp->netdev, skb, rxd); + nfp_net_set_hash_desc(dp->netdev, skb, meta, rxd); } else if (meta_len) { void *end; - end = nfp_net_parse_meta(dp->netdev, skb, meta_len); - if (unlikely(end != skb->data)) { + end = nfp_net_parse_meta(dp->netdev, skb, meta, + meta_len); + if (unlikely(end != meta + meta_len)) { nn_dp_warn(dp, "invalid RX packet metadata\n"); nfp_net_rx_drop(r_vec, rx_ring, NULL, skb); continue; From 6fe0c3b43804c9803a4a31c9d2ed8c2014bc0dc3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 10 Mar 2017 10:38:39 -0800 Subject: [PATCH 186/399] nfp: add support for xdp_adjust_head() Support prepending data from XDP. We are already always allocating some headroom because FW may prepend metadata to packets. xdp_adjust_head() can be supported by making sure that headroom is big enough for XDP. In case FW had prepended metadata to the packet, however, we have to move it out of the way before we call XDP. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 2 + .../ethernet/netronome/nfp/nfp_net_common.c | 98 +++++++++++++------ 2 files changed, 70 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 5f0547c6efb8..4d45f4573b57 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -439,6 +439,7 @@ struct nfp_stat_pair { * @bpf_offload_xdp: Offloaded BPF program is XDP * @chained_metadata_format: Firemware will use new metadata format * @rx_dma_dir: Mapping direction for RX buffers + * @rx_dma_off: Offset at which DMA packets (for XDP headroom) * @rx_offset: Offset in the RX buffers where packet data starts * @ctrl: Local copy of the control register/word. * @fl_bufsz: Currently configured size of the freelist buffers @@ -465,6 +466,7 @@ struct nfp_net_dp { u8 chained_metadata_format:1; u8 rx_dma_dir; + u8 rx_dma_off; u8 rx_offset; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index fe7c3f6d820d..f134f1808b9a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1100,6 +1100,7 @@ nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp) unsigned int fl_bufsz; fl_bufsz = NFP_NET_RX_BUF_HEADROOM; + fl_bufsz += dp->rx_dma_off; if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC) fl_bufsz += NFP_NET_MAX_PREPEND; else @@ -1181,11 +1182,13 @@ static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr) /** * nfp_net_rx_give_one() - Put mapped skb on the software and hardware rings + * @dp: NFP Net data path struct * @rx_ring: RX ring structure * @frag: page fragment buffer * @dma_addr: DMA address of skb mapping */ -static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring, +static void nfp_net_rx_give_one(const struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring, void *frag, dma_addr_t dma_addr) { unsigned int wr_idx; @@ -1199,7 +1202,8 @@ static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring, /* Fill freelist descriptor */ rx_ring->rxds[wr_idx].fld.reserved = 0; rx_ring->rxds[wr_idx].fld.meta_len_dd = 0; - nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, dma_addr); + nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, + dma_addr + dp->rx_dma_off); rx_ring->wr_p++; rx_ring->wr_ptr_add++; @@ -1296,14 +1300,17 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp, /** * nfp_net_rx_ring_fill_freelist() - Give buffers from the ring to FW + * @dp: NFP Net data path struct * @rx_ring: RX ring to fill */ -static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring) +static void +nfp_net_rx_ring_fill_freelist(struct nfp_net_dp *dp, + struct nfp_net_rx_ring *rx_ring) { unsigned int i; for (i = 0; i < rx_ring->cnt - 1; i++) - nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].frag, + nfp_net_rx_give_one(dp, rx_ring, rx_ring->rxbufs[i].frag, rx_ring->rxbufs[i].dma_addr); } @@ -1429,8 +1436,9 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb, } static void -nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring, - struct nfp_net_rx_buf *rxbuf, struct sk_buff *skb) +nfp_net_rx_drop(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec, + struct nfp_net_rx_ring *rx_ring, struct nfp_net_rx_buf *rxbuf, + struct sk_buff *skb) { u64_stats_update_begin(&r_vec->rx_sync); r_vec->rx_drops++; @@ -1442,7 +1450,7 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring, if (skb && rxbuf && skb->head == rxbuf->frag) page_ref_inc(virt_to_head_page(rxbuf->frag)); if (rxbuf) - nfp_net_rx_give_one(rx_ring, rxbuf->frag, rxbuf->dma_addr); + nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr); if (skb) dev_kfree_skb_any(skb); } @@ -1460,16 +1468,16 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, int wr_idx; if (unlikely(nfp_net_tx_full(tx_ring, 1))) { - nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL); + nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL); return false; } new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr); if (unlikely(!new_frag)) { - nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL); + nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL); return false; } - nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr); + nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr); wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1); @@ -1500,14 +1508,24 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, return true; } -static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len) +static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start, + unsigned int *off, unsigned int *len) { struct xdp_buff xdp; + void *orig_data; + int ret; - xdp.data = data; - xdp.data_end = data + len; + xdp.data_hard_start = hard_start; + xdp.data = data + *off; + xdp.data_end = data + *off + *len; - return bpf_prog_run_xdp(prog, &xdp); + orig_data = xdp.data; + ret = bpf_prog_run_xdp(prog, &xdp); + + *len -= xdp.data - orig_data; + *off += xdp.data - orig_data; + + return ret; } /** @@ -1539,6 +1557,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) while (pkts_polled < budget) { unsigned int meta_len, data_len, data_off, pkt_len; + u8 meta_prepend[NFP_NET_MAX_PREPEND]; struct nfp_net_rx_buf *rxbuf; struct nfp_net_rx_desc *rxd; dma_addr_t new_dma_addr; @@ -1580,6 +1599,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) data_off = NFP_NET_RX_BUF_HEADROOM + meta_len; else data_off = NFP_NET_RX_BUF_HEADROOM + dp->rx_offset; + data_off += dp->rx_dma_off; /* Stats update */ u64_stats_update_begin(&r_vec->rx_sync); @@ -1594,25 +1614,35 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) (dp->rx_offset && meta_len > dp->rx_offset))) { nn_dp_warn(dp, "oversized RX packet metadata %u\n", meta_len); - nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL); + nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL); continue; } if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF && dp->bpf_offload_xdp)) { unsigned int dma_off; + void *hard_start; int act; + hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM; dma_off = data_off - NFP_NET_RX_BUF_HEADROOM; - dma_sync_single_for_cpu(dp->dev, - rxbuf->dma_addr + dma_off, - pkt_len, DMA_BIDIRECTIONAL); - act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off, - pkt_len); + dma_sync_single_for_cpu(dp->dev, rxbuf->dma_addr, + dma_off + pkt_len, + DMA_BIDIRECTIONAL); + + /* Move prepend out of the way */ + if (xdp_prog->xdp_adjust_head) { + memcpy(meta_prepend, meta, meta_len); + meta = meta_prepend; + } + + act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start, + &data_off, &pkt_len); switch (act) { case XDP_PASS: break; case XDP_TX: + dma_off = data_off - NFP_NET_RX_BUF_HEADROOM; if (unlikely(!nfp_net_tx_xdp_buf(dp, rx_ring, tx_ring, rxbuf, dma_off, @@ -1625,7 +1655,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) case XDP_ABORTED: trace_xdp_exception(dp->netdev, xdp_prog, act); case XDP_DROP: - nfp_net_rx_give_one(rx_ring, rxbuf->frag, + nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr); continue; } @@ -1633,18 +1663,18 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) skb = build_skb(rxbuf->frag, true_bufsz); if (unlikely(!skb)) { - nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL); + nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL); continue; } new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr); if (unlikely(!new_frag)) { - nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb); + nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, skb); continue; } nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr); - nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr); + nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr); skb_reserve(skb, data_off); skb_put(skb, pkt_len); @@ -1658,7 +1688,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) meta_len); if (unlikely(end != meta + meta_len)) { nn_dp_warn(dp, "invalid RX packet metadata\n"); - nfp_net_rx_drop(r_vec, rx_ring, NULL, skb); + nfp_net_rx_drop(dp, r_vec, rx_ring, NULL, skb); continue; } } @@ -2151,7 +2181,7 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn) nn->dp.ctrl = new_ctrl; for (r = 0; r < nn->dp.num_rx_rings; r++) - nfp_net_rx_ring_fill_freelist(&nn->dp.rx_rings[r]); + nfp_net_rx_ring_fill_freelist(&nn->dp, &nn->dp.rx_rings[r]); /* Since reconfiguration requests while NFP is down are ignored we * have to wipe the entire VXLAN configuration and reinitialize it. @@ -2877,10 +2907,6 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) struct nfp_net_dp *dp; int err; - if (prog && prog->xdp_adjust_head) { - nn_err(nn, "Does not support bpf_xdp_adjust_head()\n"); - return -EOPNOTSUPP; - } if (!prog && !nn->dp.xdp_prog) return 0; if (prog && nn->dp.xdp_prog) { @@ -2897,6 +2923,11 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog) dp->xdp_prog = prog; dp->num_tx_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings; dp->rx_dma_dir = prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + if (prog) + dp->rx_dma_off = XDP_PACKET_HEADROOM - + (nn->dp.rx_offset ?: NFP_NET_MAX_PREPEND); + else + dp->rx_dma_off = 0; /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */ err = nfp_net_ring_reconfig(nn, dp); @@ -3124,6 +3155,13 @@ int nfp_net_netdev_init(struct net_device *netdev) struct nfp_net *nn = netdev_priv(netdev); int err; + /* XDP calls for 256 byte packet headroom which wouldn't fit in a u8. + * We, however, reuse the metadata prepend space for XDP buffers which + * is at least 1 byte long and as long as XDP headroom doesn't increase + * above 256 the *extra* XDP headroom will fit on 8 bits. + */ + BUILD_BUG_ON(XDP_PACKET_HEADROOM > 256); + nn->dp.chained_metadata_format = nn->fw_ver.major > 3; nn->dp.rx_dma_dir = DMA_FROM_DEVICE; From 0329b7daff75eddcf1df2eecf2cf97a91c33d0ee Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Sat, 11 Mar 2017 08:46:56 +0800 Subject: [PATCH 187/399] ambassador: use setup_timer Use setup_timer() instead of init_timer() to simplify the code. Signed-off-by: Geliang Tang Signed-off-by: David S. Miller --- drivers/atm/ambassador.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c index 4a610795b585..906705e5f776 100644 --- a/drivers/atm/ambassador.c +++ b/drivers/atm/ambassador.c @@ -2267,9 +2267,8 @@ static int amb_probe(struct pci_dev *pci_dev, dev->atm_dev->ci_range.vpi_bits = NUM_VPI_BITS; dev->atm_dev->ci_range.vci_bits = NUM_VCI_BITS; - init_timer(&dev->housekeeping); - dev->housekeeping.function = do_housekeeping; - dev->housekeeping.data = (unsigned long) dev; + setup_timer(&dev->housekeeping, do_housekeeping, + (unsigned long)dev); mod_timer(&dev->housekeeping, jiffies); // enable host interrupts From 27303fcf5734d84c8d018b79d1db154ceaf88df8 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Sat, 11 Mar 2017 08:46:59 +0800 Subject: [PATCH 188/399] drop_monitor: use setup_timer Use setup_timer() instead of init_timer() to simplify the code. Signed-off-by: Geliang Tang Signed-off-by: David S. Miller --- net/core/drop_monitor.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index fb55327dcfea..70ccda233bd1 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -412,9 +412,8 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); INIT_WORK(&data->dm_alert_work, send_dm_alert); - init_timer(&data->send_timer); - data->send_timer.data = (unsigned long)data; - data->send_timer.function = sched_send_work; + setup_timer(&data->send_timer, sched_send_work, + (unsigned long)data); spin_lock_init(&data->lock); reset_per_cpu_data(data); } From ff7b0d27208bd730aa71bd91087f0ff80ca60eda Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:51 +0100 Subject: [PATCH 189/399] mlxsw: spectrum: Add support for counter allocator Add implementation for counter allocator. The ASIC has special memory pool for various counting purposes. Counter memory is distributed between equal size banks. The static sub-pool configuration should specify the following parameters for each sub-pool: - Number of required banks. - Maximum entry size. Each module can add dedicated sub-pool or use existing one. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/Makefile | 3 +- .../net/ethernet/mellanox/mlxsw/resources.h | 2 + .../net/ethernet/mellanox/mlxsw/spectrum.c | 10 + .../net/ethernet/mellanox/mlxsw/spectrum.h | 2 + .../ethernet/mellanox/mlxsw/spectrum_cnt.c | 177 ++++++++++++++++++ .../ethernet/mellanox/mlxsw/spectrum_cnt.h | 54 ++++++ 6 files changed, 247 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 6b6c30deee83..95fcacf9c8be 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -15,7 +15,8 @@ obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_switchdev.o spectrum_router.o \ spectrum_kvdl.o spectrum_acl_tcam.o \ - spectrum_acl.o spectrum_flower.o + spectrum_acl.o spectrum_flower.o \ + spectrum_cnt.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o mlxsw_minimal-objs := minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index bce8c2e00630..15b808693f00 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -43,6 +43,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE, MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE, MLXSW_RES_ID_MAX_TRAP_GROUPS, + MLXSW_RES_ID_COUNTER_POOL_SIZE, MLXSW_RES_ID_MAX_SPAN, MLXSW_RES_ID_MAX_SYSTEM_PORT, MLXSW_RES_ID_MAX_LAG, @@ -75,6 +76,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002, [MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003, [MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201, + [MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410, [MLXSW_RES_ID_MAX_SPAN] = 0x2420, [MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502, [MLXSW_RES_ID_MAX_LAG] = 0x2520, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 2104ee47e965..b8237f98d470 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -66,6 +66,7 @@ #include "port.h" #include "trap.h" #include "txheader.h" +#include "spectrum_cnt.h" static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum"; static const char mlxsw_sp_driver_version[] = "1.0"; @@ -3224,6 +3225,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_acl_init; } + err = mlxsw_sp_counter_pool_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n"); + goto err_counter_pool_init; + } + err = mlxsw_sp_ports_create(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); @@ -3233,6 +3240,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, return 0; err_ports_create: + mlxsw_sp_counter_pool_fini(mlxsw_sp); +err_counter_pool_init: mlxsw_sp_acl_fini(mlxsw_sp); err_acl_init: mlxsw_sp_span_fini(mlxsw_sp); @@ -3255,6 +3264,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); mlxsw_sp_ports_remove(mlxsw_sp); + mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_router_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3bc1b0998654..dd59a9bf9085 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -246,6 +246,7 @@ struct mlxsw_sp_router { }; struct mlxsw_sp_acl; +struct mlxsw_sp_counter_pool; struct mlxsw_sp { struct { @@ -281,6 +282,7 @@ struct mlxsw_sp { DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE); } kvdl; + struct mlxsw_sp_counter_pool *counter_pool; struct { struct mlxsw_sp_span_entry *entries; int entries_count; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c new file mode 100644 index 000000000000..0cae75c415d4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c @@ -0,0 +1,177 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Arkadi Sharshevsky + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include +#include + +#include "spectrum_cnt.h" + +#define MLXSW_SP_COUNTER_POOL_BANK_SIZE 4096 + +struct mlxsw_sp_counter_sub_pool { + unsigned int base_index; + unsigned int size; + unsigned int entry_size; + unsigned int bank_count; +}; + +struct mlxsw_sp_counter_pool { + unsigned int pool_size; + unsigned long *usage; /* Usage bitmap */ + struct mlxsw_sp_counter_sub_pool *sub_pools; +}; + +static struct mlxsw_sp_counter_sub_pool mlxsw_sp_counter_sub_pools[] = {}; + +static int mlxsw_sp_counter_pool_validate(struct mlxsw_sp *mlxsw_sp) +{ + unsigned int total_bank_config = 0; + unsigned int pool_size; + int i; + + pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE); + /* Check config is valid, no bank over subscription */ + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++) + total_bank_config += mlxsw_sp_counter_sub_pools[i].bank_count; + if (total_bank_config > pool_size / MLXSW_SP_COUNTER_POOL_BANK_SIZE + 1) + return -EINVAL; + return 0; +} + +int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_counter_sub_pool *sub_pool; + struct mlxsw_sp_counter_pool *pool; + unsigned int base_index; + unsigned int map_size; + int i; + int err; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_POOL_SIZE)) + return -EIO; + + err = mlxsw_sp_counter_pool_validate(mlxsw_sp); + if (err) + return err; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return -ENOMEM; + + pool->pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE); + map_size = BITS_TO_LONGS(pool->pool_size) * sizeof(unsigned long); + + pool->usage = kzalloc(map_size, GFP_KERNEL); + if (!pool->usage) { + err = -ENOMEM; + goto err_usage_alloc; + } + + pool->sub_pools = mlxsw_sp_counter_sub_pools; + /* Allocation is based on bank count which should be + * specified for each sub pool statically. + */ + base_index = 0; + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++) { + sub_pool = &pool->sub_pools[i]; + sub_pool->size = sub_pool->bank_count * + MLXSW_SP_COUNTER_POOL_BANK_SIZE; + sub_pool->base_index = base_index; + base_index += sub_pool->size; + /* The last bank can't be fully used */ + if (sub_pool->base_index + sub_pool->size > pool->pool_size) + sub_pool->size = pool->pool_size - sub_pool->base_index; + } + + mlxsw_sp->counter_pool = pool; + return 0; + +err_usage_alloc: + kfree(pool); + return err; +} + +void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool; + + WARN_ON(find_first_bit(pool->usage, pool->pool_size) != + pool->pool_size); + kfree(pool->usage); + kfree(pool); +} + +int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int *p_counter_index) +{ + struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool; + struct mlxsw_sp_counter_sub_pool *sub_pool; + unsigned int entry_index; + unsigned int stop_index; + int i; + + sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id]; + stop_index = sub_pool->base_index + sub_pool->size; + entry_index = sub_pool->base_index; + + entry_index = find_next_zero_bit(pool->usage, stop_index, entry_index); + if (entry_index == stop_index) + return -ENOBUFS; + /* The sub-pools can contain non-integer number of entries + * so we must check for overflow + */ + if (entry_index + sub_pool->entry_size > stop_index) + return -ENOBUFS; + for (i = 0; i < sub_pool->entry_size; i++) + __set_bit(entry_index + i, pool->usage); + + *p_counter_index = entry_index; + return 0; +} + +void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int counter_index) +{ + struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool; + struct mlxsw_sp_counter_sub_pool *sub_pool; + int i; + + if (WARN_ON(counter_index >= pool->pool_size)) + return; + sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id]; + for (i = 0; i < sub_pool->entry_size; i++) + __clear_bit(counter_index + i, pool->usage); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h new file mode 100644 index 000000000000..5bf42d923edf --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h @@ -0,0 +1,54 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Arkadi Sharshevsky + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _MLXSW_SPECTRUM_CNT_H +#define _MLXSW_SPECTRUM_CNT_H + +#include "spectrum.h" + +enum mlxsw_sp_counter_sub_pool_id { + /* Placeholder before first pool registered */ + MLXSW_SP_COUNTER_SUB_POOL_PLACEHOLDER, +}; + +int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int *p_counter_index); +void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_counter_sub_pool_id sub_pool_id, + unsigned int counter_index); +int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp); + +#endif From 5766532abcee1e06897f3e1865c763f5d6eac495 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:52 +0100 Subject: [PATCH 190/399] mlxsw: reg: Add Monitoring General Purpose Counter Set register The MGPC register retrieves generic flow counter value. It will be used to query ACL counters. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 65 +++++++++++++++++++++++ 1 file changed, 65 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index eb94a5a4625d..393743c08650 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5506,6 +5506,70 @@ static inline void mlxsw_reg_mpsc_pack(char *payload, u8 local_port, bool e, mlxsw_reg_mpsc_rate_set(payload, rate); } +/* MGPC - Monitoring General Purpose Counter Set Register + * The MGPC register retrieves and sets the General Purpose Counter Set. + */ +#define MLXSW_REG_MGPC_ID 0x9081 +#define MLXSW_REG_MGPC_LEN 0x18 + +MLXSW_REG_DEFINE(mgpc, MLXSW_REG_MGPC_ID, MLXSW_REG_MGPC_LEN); + +enum mlxsw_reg_mgpc_counter_set_type { + /* No count */ + MLXSW_REG_MGPC_COUNTER_SET_TYPE_NO_COUT = 0x00, + /* Count packets and bytes */ + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, + /* Count only packets */ + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS = 0x05, +}; + +/* reg_mgpc_counter_set_type + * Counter set type. + * Access: OP + */ +MLXSW_ITEM32(reg, mgpc, counter_set_type, 0x00, 24, 8); + +/* reg_mgpc_counter_index + * Counter index. + * Access: Index + */ +MLXSW_ITEM32(reg, mgpc, counter_index, 0x00, 0, 24); + +enum mlxsw_reg_mgpc_opcode { + /* Nop */ + MLXSW_REG_MGPC_OPCODE_NOP = 0x00, + /* Clear counters */ + MLXSW_REG_MGPC_OPCODE_CLEAR = 0x08, +}; + +/* reg_mgpc_opcode + * Opcode. + * Access: OP + */ +MLXSW_ITEM32(reg, mgpc, opcode, 0x04, 28, 4); + +/* reg_mgpc_byte_counter + * Byte counter value. + * Access: RW + */ +MLXSW_ITEM64(reg, mgpc, byte_counter, 0x08, 0, 64); + +/* reg_mgpc_packet_counter + * Packet counter value. + * Access: RW + */ +MLXSW_ITEM64(reg, mgpc, packet_counter, 0x10, 0, 64); + +static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index, + enum mlxsw_reg_mgpc_opcode opcode, + enum mlxsw_reg_mgpc_counter_set_type set_type) +{ + MLXSW_REG_ZERO(mgpc, payload); + mlxsw_reg_mgpc_counter_index_set(payload, counter_index); + mlxsw_reg_mgpc_counter_set_type_set(payload, set_type); + mlxsw_reg_mgpc_opcode_set(payload, opcode); +} + /* SBPR - Shared Buffer Pools Register * ----------------------------------- * The SBPR configures and retrieves the shared buffer pools and configuration. @@ -5979,6 +6043,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mpar), MLXSW_REG(mlcr), MLXSW_REG(mpsc), + MLXSW_REG(mgpc), MLXSW_REG(sbpr), MLXSW_REG(sbcm), MLXSW_REG(sbpm), From 1abcbcc292ee6c66e659b2a7a5e84e5d151e9334 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:53 +0100 Subject: [PATCH 191/399] mlxsw: spectrum: Add support for generic flow counter allocation Add support for allocating generic flow counter. Generic flow counter can count packets or packets and bytes and can be assigned to different hardware processes. First use will be for counting packets and bytes of ACL rules, and will be introduced in the following patches. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/resources.h | 2 + .../net/ethernet/mellanox/mlxsw/spectrum.c | 54 +++++++++++++++++++ .../net/ethernet/mellanox/mlxsw/spectrum.h | 7 +++ .../ethernet/mellanox/mlxsw/spectrum_cnt.c | 23 +++++++- .../ethernet/mellanox/mlxsw/spectrum_cnt.h | 3 +- 5 files changed, 86 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index 15b808693f00..905a8e269f87 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -45,6 +45,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_MAX_TRAP_GROUPS, MLXSW_RES_ID_COUNTER_POOL_SIZE, MLXSW_RES_ID_MAX_SPAN, + MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES, MLXSW_RES_ID_MAX_SYSTEM_PORT, MLXSW_RES_ID_MAX_LAG, MLXSW_RES_ID_MAX_LAG_MEMBERS, @@ -78,6 +79,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201, [MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410, [MLXSW_RES_ID_MAX_SPAN] = 0x2420, + [MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443, [MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502, [MLXSW_RES_ID_MAX_LAG] = 0x2520, [MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b8237f98d470..af430484ed2f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -139,6 +139,60 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16); */ MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); +int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index, u64 *packets, + u64 *bytes) +{ + char mgpc_pl[MLXSW_REG_MGPC_LEN]; + int err; + + mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP, + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl); + if (err) + return err; + *packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl); + *bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl); + return 0; +} + +static int mlxsw_sp_flow_counter_clear(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index) +{ + char mgpc_pl[MLXSW_REG_MGPC_LEN]; + + mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_CLEAR, + MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl); +} + +int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, + unsigned int *p_counter_index) +{ + int err; + + err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW, + p_counter_index); + if (err) + return err; + err = mlxsw_sp_flow_counter_clear(mlxsw_sp, *p_counter_index); + if (err) + goto err_counter_clear; + return 0; + +err_counter_clear: + mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW, + *p_counter_index); + return err; +} + +void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index) +{ + mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW, + counter_index); +} + static void mlxsw_sp_txhdr_construct(struct sk_buff *skb, const struct mlxsw_tx_info *tx_info) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index dd59a9bf9085..b0500b878fb4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -679,5 +679,12 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, __be16 protocol, struct tc_cls_flower_offload *f); void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, struct tc_cls_flower_offload *f); +int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index, u64 *packets, + u64 *bytes); +int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, + unsigned int *p_counter_index); +void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c index 0cae75c415d4..1631e01908c0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c @@ -52,7 +52,11 @@ struct mlxsw_sp_counter_pool { struct mlxsw_sp_counter_sub_pool *sub_pools; }; -static struct mlxsw_sp_counter_sub_pool mlxsw_sp_counter_sub_pools[] = {}; +static struct mlxsw_sp_counter_sub_pool mlxsw_sp_counter_sub_pools[] = { + [MLXSW_SP_COUNTER_SUB_POOL_FLOW] = { + .bank_count = 6, + }, +}; static int mlxsw_sp_counter_pool_validate(struct mlxsw_sp *mlxsw_sp) { @@ -69,6 +73,19 @@ static int mlxsw_sp_counter_pool_validate(struct mlxsw_sp *mlxsw_sp) return 0; } +static int mlxsw_sp_counter_sub_pools_prepare(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_counter_sub_pool *sub_pool; + + /* Prepare generic flow pool*/ + sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_FLOW]; + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_PACKETS_BYTES)) + return -EIO; + sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, + COUNTER_SIZE_PACKETS_BYTES); + return 0; +} + int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_counter_sub_pool *sub_pool; @@ -85,6 +102,10 @@ int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) if (err) return err; + err = mlxsw_sp_counter_sub_pools_prepare(mlxsw_sp); + if (err) + return err; + pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h index 5bf42d923edf..031bc4abbe2d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h @@ -38,8 +38,7 @@ #include "spectrum.h" enum mlxsw_sp_counter_sub_pool_id { - /* Placeholder before first pool registered */ - MLXSW_SP_COUNTER_SUB_POOL_PLACEHOLDER, + MLXSW_SP_COUNTER_SUB_POOL_FLOW, }; int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp, From 7fd056c2ef50088b891f2044af52bbb28699f4e6 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:54 +0100 Subject: [PATCH 192/399] mlxsw: spectrum_acl_tcam: Add support for retrieving TCAM entry activity Add support for retrieving TCAM entry activity. In order to support ACL rule activity corresponding TCAM entry should be queried. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.h | 2 + .../mellanox/mlxsw/spectrum_acl_tcam.c | 42 +++++++++++++++++++ 2 files changed, 44 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index b0500b878fb4..26718b167352 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -607,6 +607,8 @@ struct mlxsw_sp_acl_profile_ops { void *ruleset_priv, void *rule_priv, struct mlxsw_sp_acl_rule_info *rulei); void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv); + int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv, + bool *activity); }; struct mlxsw_sp_acl_ops { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 6858439a1319..3a24289979d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -561,6 +561,24 @@ mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl); } +static int +mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region, + unsigned int offset, + bool *activity) +{ + char ptce2_pl[MLXSW_REG_PTCE2_LEN]; + int err; + + mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ, + region->tcam_region_info, offset); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl); + if (err) + return err; + *activity = mlxsw_reg_ptce2_a_get(ptce2_pl); + return 0; +} + #define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U) static int @@ -940,6 +958,19 @@ static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk); } +static int +mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_entry *entry, + bool *activity) +{ + struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; + struct mlxsw_sp_acl_tcam_region *region = chunk->region; + + return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region, + entry->parman_item.index, + activity); +} + static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_SRC_SYS_PORT, MLXSW_AFK_ELEMENT_DMAC, @@ -1048,6 +1079,16 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv) mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry); } +static int +mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp, + void *rule_priv, bool *activity) +{ + struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; + + return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry, + activity); +} + static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { .ruleset_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_ruleset), .ruleset_add = mlxsw_sp_acl_tcam_flower_ruleset_add, @@ -1057,6 +1098,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_rule), .rule_add = mlxsw_sp_acl_tcam_flower_rule_add, .rule_del = mlxsw_sp_acl_tcam_flower_rule_del, + .rule_activity_get = mlxsw_sp_acl_tcam_flower_rule_activity_get, }; static const struct mlxsw_sp_acl_profile_ops * From 096e914f69dcb07ee6f82f8507325e9668979395 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:55 +0100 Subject: [PATCH 193/399] mlxsw: spectrum: Add support for direct rule access Currently the ACL rules can be accessed only by hashing. In order to dump the activity the rules are also placed in a list. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 3c5ea7e41db0..1888092471ea 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -54,6 +54,7 @@ struct mlxsw_sp_acl { struct mlxsw_afa *afa; const struct mlxsw_sp_acl_ops *ops; struct rhashtable ruleset_ht; + struct list_head rules; unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -80,6 +81,7 @@ struct mlxsw_sp_acl_ruleset { struct mlxsw_sp_acl_rule { struct rhash_head ht_node; /* Member of rule HT */ + struct list_head list; unsigned long cookie; /* HT key */ struct mlxsw_sp_acl_ruleset *ruleset; struct mlxsw_sp_acl_rule_info *rulei; @@ -422,6 +424,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rhashtable_insert; + list_add_tail(&rule->list, &mlxsw_sp->acl->rules); return 0; err_rhashtable_insert: @@ -435,6 +438,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + list_del(&rule->list); rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node, mlxsw_sp_acl_rule_ht_params); ops->rule_del(mlxsw_sp, rule->priv); @@ -570,6 +574,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_rhashtable_init; + INIT_LIST_HEAD(&acl->rules); err = acl_ops->init(mlxsw_sp, acl->priv); if (err) goto err_acl_ops_init; @@ -594,6 +599,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) const struct mlxsw_sp_acl_ops *acl_ops = acl->ops; acl_ops->fini(mlxsw_sp, acl->priv); + WARN_ON(!list_empty(&acl->rules)); rhashtable_destroy(&acl->ruleset_ht); mlxsw_afa_destroy(acl->afa); mlxsw_afk_destroy(acl->afk); From 446a154187b9d9a35f97f9d981501d6b55d8d6ed Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:56 +0100 Subject: [PATCH 194/399] mlxsw: spectrum: Add periodic ACL rule activity update Introduce periodic task for dumping the activity status for the ACL rule TCAM entries. This is done in order to emulate last use statistics. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_acl.c | 74 ++++++++++++++++++- 1 file changed, 73 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 1888092471ea..d2f6cbb6a0c6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -50,11 +50,17 @@ #include "spectrum_acl_flex_keys.h" struct mlxsw_sp_acl { + struct mlxsw_sp *mlxsw_sp; struct mlxsw_afk *afk; struct mlxsw_afa *afa; const struct mlxsw_sp_acl_ops *ops; struct rhashtable ruleset_ht; struct list_head rules; + struct { + struct delayed_work dw; + unsigned long interval; /* ms */ +#define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000 + } rule_activity_update; unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -85,6 +91,7 @@ struct mlxsw_sp_acl_rule { unsigned long cookie; /* HT key */ struct mlxsw_sp_acl_ruleset *ruleset; struct mlxsw_sp_acl_rule_info *rulei; + u64 last_used; unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -459,6 +466,64 @@ mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule) return rule->rulei; } +static int mlxsw_sp_acl_rule_activity_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule *rule) +{ + struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; + const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + bool active; + int err; + + err = ops->rule_activity_get(mlxsw_sp, rule->priv, &active); + if (err) + return err; + if (active) + rule->last_used = jiffies; + return 0; +} + +static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl) +{ + struct mlxsw_sp_acl_rule *rule; + int err; + + /* Protect internal structures from changes */ + rtnl_lock(); + list_for_each_entry(rule, &acl->rules, list) { + err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp, + rule); + if (err) + goto err_rule_update; + } + rtnl_unlock(); + return 0; + +err_rule_update: + rtnl_unlock(); + return err; +} + +static void mlxsw_sp_acl_rule_activity_work_schedule(struct mlxsw_sp_acl *acl) +{ + unsigned long interval = acl->rule_activity_update.interval; + + mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, + msecs_to_jiffies(interval)); +} + +static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work) +{ + struct mlxsw_sp_acl *acl = container_of(work, struct mlxsw_sp_acl, + rule_activity_update.dw.work); + int err; + + err = mlxsw_sp_acl_rules_activity_update(acl); + if (err) + dev_err(acl->mlxsw_sp->bus_info->dev, "Could not update acl activity"); + + mlxsw_sp_acl_rule_activity_work_schedule(acl); +} + #define MLXSW_SP_KDVL_ACT_EXT_SIZE 1 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index, @@ -551,7 +616,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) if (!acl) return -ENOMEM; mlxsw_sp->acl = acl; - + acl->mlxsw_sp = mlxsw_sp; acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_FLEX_KEYS), mlxsw_sp_afk_blocks, @@ -580,6 +645,12 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) goto err_acl_ops_init; acl->ops = acl_ops; + + /* Create the delayed work for the rule activity_update */ + INIT_DELAYED_WORK(&acl->rule_activity_update.dw, + mlxsw_sp_acl_rul_activity_update_work); + acl->rule_activity_update.interval = MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS; + mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, 0); return 0; err_acl_ops_init: @@ -598,6 +669,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) struct mlxsw_sp_acl *acl = mlxsw_sp->acl; const struct mlxsw_sp_acl_ops *acl_ops = acl->ops; + cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw); acl_ops->fini(mlxsw_sp, acl->priv); WARN_ON(!list_empty(&acl->rules)); rhashtable_destroy(&acl->ruleset_ht); From 938ab60860e81f123460b56b8463d6b5d6c51ac7 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:57 +0100 Subject: [PATCH 195/399] mlxsw: spectrum: Add support for Policing and Counting action block Add support for Policing and Counting action block. This action block will be used to bind counter to TCAM entries. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../mellanox/mlxsw/core_acl_flex_actions.c | 51 +++++++++++++++++++ .../mellanox/mlxsw/core_acl_flex_actions.h | 2 + 2 files changed, 53 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index fe3c6ea16a99..a984c361926c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -760,3 +760,54 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, return err; } EXPORT_SYMBOL(mlxsw_afa_block_append_fwd); + +/* Policing and Counting Action + * ---------------------------- + * Policing and Counting action is used for binding policer and counter + * to ACL rules. + */ + +#define MLXSW_AFA_POLCNT_CODE 0x08 +#define MLXSW_AFA_POLCNT_SIZE 1 + +enum mlxsw_afa_polcnt_counter_set_type { + /* No count */ + MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_NO_COUNT = 0x00, + /* Count packets and bytes */ + MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, + /* Count only packets */ + MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS = 0x05, +}; + +/* afa_polcnt_counter_set_type + * Counter set type for flow counters. + */ +MLXSW_ITEM32(afa, polcnt, counter_set_type, 0x04, 24, 8); + +/* afa_polcnt_counter_index + * Counter index for flow counters. + */ +MLXSW_ITEM32(afa, polcnt, counter_index, 0x04, 0, 24); + +static inline void +mlxsw_afa_polcnt_pack(char *payload, + enum mlxsw_afa_polcnt_counter_set_type set_type, + u32 counter_index) +{ + mlxsw_afa_polcnt_counter_set_type_set(payload, set_type); + mlxsw_afa_polcnt_counter_index_set(payload, counter_index); +} + +int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block, + u32 counter_index) +{ + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_POLCNT_CODE, + MLXSW_AFA_POLCNT_SIZE); + if (!act) + return -ENOBUFS; + mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES, + counter_index); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_counter); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 6e103ac41d99..a03362c1ef32 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -64,5 +64,7 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, u8 local_port, bool in_port); int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, u16 vid, u8 pcp, u8 et); +int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block, + u32 counter_index); #endif From 4817072950ad38229991ab0019fa28fece39285b Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:58 +0100 Subject: [PATCH 196/399] mlxsw: spectrum: Add support for counters on TCAM entries Add support for packets and byte statistics on TCAM entries. The counters are allocated from the generic flow counters pool. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.h | 7 ++++ .../ethernet/mellanox/mlxsw/spectrum_acl.c | 35 +++++++++++++++++++ 2 files changed, 42 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 26718b167352..b4f32a6d0352 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -588,6 +588,8 @@ struct mlxsw_sp_acl_rule_info { unsigned int priority; struct mlxsw_afk_element_values values; struct mlxsw_afa_block *act_block; + unsigned int counter_index; + bool counter_valid; }; enum mlxsw_sp_acl_profile { @@ -652,6 +654,8 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp, int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u32 action, u16 vid, u16 proto, u8 prio); +int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei); struct mlxsw_sp_acl_rule; @@ -671,6 +675,9 @@ mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp, unsigned long cookie); struct mlxsw_sp_acl_rule_info * mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule); +int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule *rule, + u64 *packets, u64 *bytes, u64 *last_use); int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index d2f6cbb6a0c6..87d011171da9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -247,6 +247,27 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset); } +static int +mlxsw_sp_acl_rulei_counter_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei) +{ + int err; + + err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &rulei->counter_index); + if (err) + return err; + rulei->counter_valid = true; + return 0; +} + +static void +mlxsw_sp_acl_rulei_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei) +{ + rulei->counter_valid = false; + mlxsw_sp_flow_counter_free(mlxsw_sp, rulei->counter_index); +} + struct mlxsw_sp_acl_rule_info * mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl) { @@ -373,6 +394,13 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, } } +int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei) +{ + return mlxsw_afa_block_append_counter(rulei->act_block, + rulei->counter_index); +} + struct mlxsw_sp_acl_rule * mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset, @@ -396,8 +424,14 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, err = PTR_ERR(rule->rulei); goto err_rulei_create; } + + err = mlxsw_sp_acl_rulei_counter_alloc(mlxsw_sp, rule->rulei); + if (err) + goto err_counter_alloc; return rule; +err_counter_alloc: + mlxsw_sp_acl_rulei_destroy(rule->rulei); err_rulei_create: kfree(rule); err_alloc: @@ -410,6 +444,7 @@ void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; + mlxsw_sp_acl_rulei_counter_free(mlxsw_sp, rule->rulei); mlxsw_sp_acl_rulei_destroy(rule->rulei); kfree(rule); mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset); From 7c1b8eb175b69add8eac105409d2a59723574675 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sat, 11 Mar 2017 09:42:59 +0100 Subject: [PATCH 197/399] mlxsw: spectrum: Add support for TC flower offload statistics Add support for TC flower offload statistics including number of packets, bytes and last use timestamp. Currently the statistics are gathered on a per-rule basis. Signed-off-by: Arkadi Sharshvesky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 3 ++ .../net/ethernet/mellanox/mlxsw/spectrum.h | 2 + .../ethernet/mellanox/mlxsw/spectrum_acl.c | 28 +++++++++++ .../ethernet/mellanox/mlxsw/spectrum_flower.c | 49 +++++++++++++++++++ 4 files changed, 82 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index af430484ed2f..475499b6c989 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1434,6 +1434,9 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle, mlxsw_sp_flower_destroy(mlxsw_sp_port, ingress, tc->cls_flower); return 0; + case TC_CLSFLOWER_STATS: + return mlxsw_sp_flower_stats(mlxsw_sp_port, ingress, + tc->cls_flower); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index b4f32a6d0352..5502232b06cf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -688,6 +688,8 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, __be16 protocol, struct tc_cls_flower_offload *f); void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, struct tc_cls_flower_offload *f); +int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, + struct tc_cls_flower_offload *f); int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, unsigned int counter_index, u64 *packets, u64 *bytes); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 87d011171da9..4d6920d45026 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -92,6 +92,8 @@ struct mlxsw_sp_acl_rule { struct mlxsw_sp_acl_ruleset *ruleset; struct mlxsw_sp_acl_rule_info *rulei; u64 last_used; + u64 last_packets; + u64 last_bytes; unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -559,6 +561,32 @@ static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work) mlxsw_sp_acl_rule_activity_work_schedule(acl); } +int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule *rule, + u64 *packets, u64 *bytes, u64 *last_use) + +{ + struct mlxsw_sp_acl_rule_info *rulei; + u64 current_packets; + u64 current_bytes; + int err; + + rulei = mlxsw_sp_acl_rule_rulei(rule); + err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index, + ¤t_packets, ¤t_bytes); + if (err) + return err; + + *packets = current_packets - rule->last_packets; + *bytes = current_bytes - rule->last_bytes; + *last_use = rule->last_used; + + rule->last_bytes = current_bytes; + rule->last_packets = current_packets; + + return 0; +} + #define MLXSW_SP_KDVL_ACT_EXT_SIZE 1 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index f2ed0b3d5718..28bc989371c6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -56,6 +56,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, if (tc_no_actions(exts)) return 0; + /* Count action is inserted first */ + err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei); + if (err) + return err; + tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { if (is_tcf_gact_shot(a)) { @@ -346,3 +351,47 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); } + +int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, + struct tc_cls_flower_offload *f) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_acl_ruleset *ruleset; + struct mlxsw_sp_acl_rule *rule; + struct tc_action *a; + LIST_HEAD(actions); + u64 packets; + u64 lastuse; + u64 bytes; + int err; + + ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev, + ingress, + MLXSW_SP_ACL_PROFILE_FLOWER); + if (WARN_ON(IS_ERR(ruleset))) + return -EINVAL; + + rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie); + if (!rule) + return -EINVAL; + + err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &bytes, &packets, + &lastuse); + if (err) + goto err_rule_get_stats; + + preempt_disable(); + + tcf_exts_to_list(f->exts, &actions); + list_for_each_entry(a, &actions, list) + tcf_action_stats_update(a, bytes, packets, lastuse); + + preempt_enable(); + + mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); + return 0; + +err_rule_get_stats: + mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); + return err; +} From 4d294af2cd932e0c1b2534137b143920c17dffd6 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:47 -0500 Subject: [PATCH 198/399] net: dsa: mv88e6xxx: add port mask helper Add a mv88e6xxx_port_mask() helper to get the bitmask of ports in a switch chip, that will be used in several features. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 5 +++++ drivers/net/dsa/mv88e6xxx/port.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 6033f2f6260a..166b513ff751 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -944,6 +944,11 @@ static inline unsigned int mv88e6xxx_num_ports(struct mv88e6xxx_chip *chip) return chip->info->num_ports; } +static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip) +{ + return GENMASK(mv88e6xxx_num_ports(chip) - 1, 0); +} + int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 8875784c4718..9bb0f2134cba 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -539,7 +539,7 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map) { - const u16 mask = GENMASK(mv88e6xxx_num_ports(chip) - 1, 0); + const u16 mask = mv88e6xxx_port_mask(chip); u16 reg; int err; From 720c6343ef67de926251b0c1b3bb0b76d2cff946 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:48 -0500 Subject: [PATCH 199/399] net: dsa: mv88e6xxx: move ATU ageing time setter Move the ATU ageing time setter code in a new global1_atu.c file, which will be extended in future patches to contains all consequent Global (1) ATU support code. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/Makefile | 1 + drivers/net/dsa/mv88e6xxx/chip.c | 31 ++---------------- drivers/net/dsa/mv88e6xxx/global1.h | 3 ++ drivers/net/dsa/mv88e6xxx/global1_atu.c | 43 +++++++++++++++++++++++++ 4 files changed, 49 insertions(+), 29 deletions(-) create mode 100644 drivers/net/dsa/mv88e6xxx/global1_atu.c diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile index c36be318de1a..31d37a90cec7 100644 --- a/drivers/net/dsa/mv88e6xxx/Makefile +++ b/drivers/net/dsa/mv88e6xxx/Makefile @@ -1,5 +1,6 @@ obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o mv88e6xxx-objs := chip.o mv88e6xxx-objs += global1.o +mv88e6xxx-objs += global1_atu.o mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o mv88e6xxx-objs += port.o diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 03dc886ed3d6..b228b8491afc 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2697,33 +2697,6 @@ static int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr) return 0; } -static int mv88e6xxx_g1_set_age_time(struct mv88e6xxx_chip *chip, - unsigned int msecs) -{ - const unsigned int coeff = chip->info->age_time_coeff; - const unsigned int min = 0x01 * coeff; - const unsigned int max = 0xff * coeff; - u8 age_time; - u16 val; - int err; - - if (msecs < min || msecs > max) - return -ERANGE; - - /* Round to nearest multiple of coeff */ - age_time = (msecs + coeff / 2) / coeff; - - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); - if (err) - return err; - - /* AgeTime is 11:4 bits */ - val &= ~0xff0; - val |= age_time << 4; - - return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); -} - static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) { @@ -2731,7 +2704,7 @@ static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds, int err; mutex_lock(&chip->reg_lock); - err = mv88e6xxx_g1_set_age_time(chip, ageing_time); + err = mv88e6xxx_g1_atu_set_age_time(chip, ageing_time); mutex_unlock(&chip->reg_lock); return err; @@ -2783,7 +2756,7 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip) if (err) return err; - err = mv88e6xxx_g1_set_age_time(chip, 300000); + err = mv88e6xxx_g1_atu_set_age_time(chip, 300000); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 1aec7382c02d..b8d0fb519bab 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -38,4 +38,7 @@ int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); +int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, + unsigned int msecs); + #endif /* _MV88E6XXX_GLOBAL1_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c new file mode 100644 index 000000000000..4d0ada9efc6d --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -0,0 +1,43 @@ +/* + * Marvell 88E6xxx Address Translation Unit (ATU) support + * + * Copyright (c) 2008 Marvell Semiconductor + * Copyright (c) 2017 Savoir-faire Linux, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "mv88e6xxx.h" +#include "global1.h" + +/* Offset 0x0A: ATU Control Register */ + +int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, + unsigned int msecs) +{ + const unsigned int coeff = chip->info->age_time_coeff; + const unsigned int min = 0x01 * coeff; + const unsigned int max = 0xff * coeff; + u8 age_time; + u16 val; + int err; + + if (msecs < min || msecs > max) + return -ERANGE; + + /* Round to nearest multiple of coeff */ + age_time = (msecs + coeff / 2) / coeff; + + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); + if (err) + return err; + + /* AgeTime is 11:4 bits */ + val &= ~0xff0; + val |= age_time << 4; + + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); +} From a2ac29d2cccdaa647b67355786d961196140491b Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:49 -0500 Subject: [PATCH 200/399] net: dsa: mv88e6xxx: add ATU setup helper Move the configuration of the default ageing time in a new mv88e6xxx_atu_setup function. That function will be extended later to contain all ATU related configuration bits. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b228b8491afc..0ad8200f3321 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1306,6 +1306,11 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port, netdev_err(ds->ports[port].netdev, "failed to update state\n"); } +static int mv88e6xxx_atu_setup(struct mv88e6xxx_chip *chip) +{ + return mv88e6xxx_g1_atu_set_age_time(chip, 300000); +} + static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port) { struct mv88e6xxx_chip *chip = ds->priv; @@ -2756,10 +2761,6 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip) if (err) return err; - err = mv88e6xxx_g1_atu_set_age_time(chip, 300000); - if (err) - return err; - /* Clear all ATU entries */ err = _mv88e6xxx_atu_flush(chip, 0, true); if (err) @@ -2845,6 +2846,10 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) goto unlock; } + err = mv88e6xxx_atu_setup(chip); + if (err) + goto unlock; + /* Some generations have the configuration of sending reserved * management frames to the CPU in global2, others in * global1. Hence it does not fit the two setup functions From ea698f4f70937f02961f2041db82d4baf6c986d6 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:50 -0500 Subject: [PATCH 201/399] net: dsa: mv88e6xxx: setup message ports All interconnectable Marvell switch chips have an ATU Learn2All feature which allows newly learnt addresses to be spanned on ports marked as "Message Port". This commit configures the DSA ports as Message Port. Note that this has no effect until the Learn2All feature is enabled. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 12 ++++++++---- drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 1 + drivers/net/dsa/mv88e6xxx/port.c | 18 ++++++++++++++++++ drivers/net/dsa/mv88e6xxx/port.h | 2 ++ 4 files changed, 29 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 0ad8200f3321..5c1b5825fe6c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2504,6 +2504,13 @@ static int mv88e6xxx_setup_port_normal(struct mv88e6xxx_chip *chip, int port) return chip->info->ops->port_set_egress_unknowns(chip, port, false); } +static int mv88e6xxx_setup_message_port(struct mv88e6xxx_chip *chip, int port) +{ + bool message = dsa_is_dsa_port(chip->ds, port); + + return mv88e6xxx_port_set_message_port(chip, port, message); +} + static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) { struct dsa_switch *ds = chip->ds; @@ -2658,10 +2665,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } - /* Port Control 1: disable trunking, disable sending - * learning messages to this port. - */ - err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, 0x0000); + err = mv88e6xxx_setup_message_port(chip, port); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 166b513ff751..45205519b9fe 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -144,6 +144,7 @@ #define PORT_CONTROL_STATE_LEARNING 0x02 #define PORT_CONTROL_STATE_FORWARDING 0x03 #define PORT_CONTROL_1 0x05 +#define PORT_CONTROL_1_MESSAGE_PORT BIT(15) #define PORT_CONTROL_1_FID_11_4_MASK (0xff << 0) #define PORT_BASE_VLAN 0x06 #define PORT_BASE_VLAN_FID_3_0_MASK (0xf << 12) diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 9bb0f2134cba..40fe48188056 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -535,6 +535,24 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, /* Offset 0x05: Port Control 1 */ +int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port, + bool message_port) +{ + u16 val; + int err; + + err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, &val); + if (err) + return err; + + if (message_port) + val |= PORT_CONTROL_1_MESSAGE_PORT; + else + val &= ~PORT_CONTROL_1_MESSAGE_PORT; + + return mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, val); +} + /* Offset 0x06: Port Based VLAN Map */ int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map) diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index c83cbb3f4491..4328d6f29d4d 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -64,6 +64,8 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, bool on); int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port, u16 etype); +int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port, + bool message_port); int mv88e6165_port_jumbo_config(struct mv88e6xxx_chip *chip, int port); int mv88e6095_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port); int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port); From c3a7d4ade5a5ac5bec63382bda35a92629447efb Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:51 -0500 Subject: [PATCH 202/399] net: dsa: mv88e6xxx: enable ATU Learn2All The ATU Learn2All feature allows newly learnt addresses to be spanned on ports marked as "Message Port", currently all DSA ports. This commit enables this feature which is necessary and quite convenient for multi-chip switch fabrics. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 15 ++++++--------- drivers/net/dsa/mv88e6xxx/global1.h | 1 + drivers/net/dsa/mv88e6xxx/global1_atu.c | 17 +++++++++++++++++ 3 files changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 5c1b5825fe6c..1ee0c05f624e 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1308,6 +1308,12 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port, static int mv88e6xxx_atu_setup(struct mv88e6xxx_chip *chip) { + int err; + + err = mv88e6xxx_g1_atu_set_learn2all(chip, true); + if (err) + return err; + return mv88e6xxx_g1_atu_set_age_time(chip, 300000); } @@ -2756,15 +2762,6 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip) if (err < 0) return err; - /* Set the default address aging time to 5 minutes, and - * enable address learn messages to be sent to all message - * ports. - */ - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, - GLOBAL_ATU_CONTROL_LEARN2ALL); - if (err) - return err; - /* Clear all ATU entries */ err = _mv88e6xxx_atu_flush(chip, 0, true); if (err) diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index b8d0fb519bab..18322d05225a 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -38,6 +38,7 @@ int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); +int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all); int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, unsigned int msecs); diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 4d0ada9efc6d..843a21e05f7b 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -15,6 +15,23 @@ /* Offset 0x0A: ATU Control Register */ +int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all) +{ + u16 val; + int err; + + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); + if (err) + return err; + + if (learn2all) + val |= GLOBAL_ATU_CONTROL_LEARN2ALL; + else + val &= ~GLOBAL_ATU_CONTROL_LEARN2ALL; + + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); +} + int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, unsigned int msecs) { From 9c13c0267683733f549bb883220ab042028e1c7d Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:52 -0500 Subject: [PATCH 203/399] net: dsa: mv88e6xxx: rework ATU Load/Purge All Marvell switch chips have an ATU accessed using the same Global (1) register layout. Only the handling of the FID differs as more bits were necessary to support more and more databases. Add and use a fresh documented implementation of the ATU Load/Purge. The static mv88e6xxx_g1_atu_{fid_write,op_wait,op,data_write,mac_write} functions won't need to be exposed in the end so for the moment keep their counterparts _mv88e6xxx_atu_{wait,cmd,data_write,mac_write} as is, since they are still used by other ATU operations. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 22 +---- drivers/net/dsa/mv88e6xxx/global1.h | 2 + drivers/net/dsa/mv88e6xxx/global1_atu.c | 108 ++++++++++++++++++++++++ 3 files changed, 111 insertions(+), 21 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 1ee0c05f624e..95dbf581b54a 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2045,26 +2045,6 @@ static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_chip *chip, return 0; } -static int _mv88e6xxx_atu_load(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_atu_entry *entry) -{ - int ret; - - ret = _mv88e6xxx_atu_wait(chip); - if (ret < 0) - return ret; - - ret = _mv88e6xxx_atu_mac_write(chip, entry->mac); - if (ret < 0) - return ret; - - ret = _mv88e6xxx_atu_data_write(chip, entry); - if (ret < 0) - return ret; - - return _mv88e6xxx_atu_cmd(chip, entry->fid, GLOBAL_ATU_OP_LOAD_DB); -} - static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, struct mv88e6xxx_atu_entry *entry); @@ -2132,7 +2112,7 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, entry.state = state; } - return _mv88e6xxx_atu_load(chip, &entry); + return mv88e6xxx_g1_atu_loadpurge(chip, vlan.fid, &entry); } static int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 18322d05225a..2c03f2e04639 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -41,5 +41,7 @@ int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all); int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, unsigned int msecs); +int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry); #endif /* _MV88E6XXX_GLOBAL1_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 843a21e05f7b..09190559178b 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -13,6 +13,13 @@ #include "mv88e6xxx.h" #include "global1.h" +/* Offset 0x01: ATU FID Register */ + +static int mv88e6xxx_g1_atu_fid_write(struct mv88e6xxx_chip *chip, u16 fid) +{ + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid & 0xfff); +} + /* Offset 0x0A: ATU Control Register */ int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all) @@ -58,3 +65,104 @@ int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); } + +/* Offset 0x0B: ATU Operation Register */ + +static int mv88e6xxx_g1_atu_op_wait(struct mv88e6xxx_chip *chip) +{ + return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY); +} + +static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op) +{ + u16 val; + int err; + + /* FID bits are dispatched all around gradually as more are supported */ + if (mv88e6xxx_num_databases(chip) > 256) { + err = mv88e6xxx_g1_atu_fid_write(chip, fid); + if (err) + return err; + } else { + if (mv88e6xxx_num_databases(chip) > 16) { + /* ATU DBNum[7:4] are located in ATU Control 15:12 */ + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); + if (err) + return err; + + val = (val & 0x0fff) | ((fid << 8) & 0xf000); + err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val); + if (err) + return err; + } + + /* ATU DBNum[3:0] are located in ATU Operation 3:0 */ + op |= fid & 0xf; + } + + err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, op); + if (err) + return err; + + return mv88e6xxx_g1_atu_op_wait(chip); +} + +/* Offset 0x0C: ATU Data Register */ + +static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 data = entry->state & 0xf; + + if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { + if (entry->trunk) + data |= GLOBAL_ATU_DATA_TRUNK; + + data |= (entry->portv_trunkid & mv88e6xxx_port_mask(chip)) << 4; + } + + return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data); +} + +/* Offset 0x0D: ATU MAC Address Register Bytes 0 & 1 + * Offset 0x0E: ATU MAC Address Register Bytes 2 & 3 + * Offset 0x0F: ATU MAC Address Register Bytes 4 & 5 + */ + +static int mv88e6xxx_g1_atu_mac_write(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 val; + int i, err; + + for (i = 0; i < 3; i++) { + val = (entry->mac[i * 2] << 8) | entry->mac[i * 2 + 1]; + err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i, val); + if (err) + return err; + } + + return 0; +} + +/* Address Translation Unit operations */ + +int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry) +{ + int err; + + err = mv88e6xxx_g1_atu_op_wait(chip); + if (err) + return err; + + err = mv88e6xxx_g1_atu_mac_write(chip, entry); + if (err) + return err; + + err = mv88e6xxx_g1_atu_data_write(chip, entry); + if (err) + return err; + + return mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_LOAD_DB); +} From dabc1a968ae17bcd99c216f509be101dfdeac664 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:53 -0500 Subject: [PATCH 204/399] net: dsa: mv88e6xxx: rework ATU GetNext Add and use a fresh documented implementation of the ATU GetNext. Since it is not necessary to write the MAC address to iterate from, only do it once directly in the ATU GetNext operation, if the provided ATU entry structure is not valid. This makes the user code simpler. Also, there is no need to loop when getting a single ATU entry. So remove the mv88e6xxx_atu_get helper and add a simpler snippet in mv88e6xxx_port_db_load_purge to lookup a given MAC address. The _mv88e6xxx_atu_mac_{read,write} are not used anymore thus remove them. _mv88e6xxx_atu_data_{read,write} are still used so keep them. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 140 +++--------------------- drivers/net/dsa/mv88e6xxx/global1.h | 2 + drivers/net/dsa/mv88e6xxx/global1_atu.c | 66 +++++++++++ 3 files changed, 84 insertions(+), 124 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 95dbf581b54a..2d1ec0d79fb6 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2012,76 +2012,6 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, return err; } -static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_chip *chip, - const unsigned char *addr) -{ - int i, err; - - for (i = 0; i < 3; i++) { - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i, - (addr[i * 2] << 8) | addr[i * 2 + 1]); - if (err) - return err; - } - - return 0; -} - -static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_chip *chip, - unsigned char *addr) -{ - u16 val; - int i, err; - - for (i = 0; i < 3; i++) { - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val); - if (err) - return err; - - addr[i * 2] = val >> 8; - addr[i * 2 + 1] = val & 0xff; - } - - return 0; -} - -static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, - struct mv88e6xxx_atu_entry *entry); - -static int mv88e6xxx_atu_get(struct mv88e6xxx_chip *chip, int fid, - const u8 *addr, struct mv88e6xxx_atu_entry *entry) -{ - struct mv88e6xxx_atu_entry next; - int err; - - memcpy(next.mac, addr, ETH_ALEN); - eth_addr_dec(next.mac); - - err = _mv88e6xxx_atu_mac_write(chip, next.mac); - if (err) - return err; - - do { - err = _mv88e6xxx_atu_getnext(chip, fid, &next); - if (err) - return err; - - if (next.state == GLOBAL_ATU_DATA_STATE_UNUSED) - break; - - if (ether_addr_equal(next.mac, addr)) { - *entry = next; - return 0; - } - } while (ether_addr_greater(addr, next.mac)); - - memset(entry, 0, sizeof(*entry)); - entry->fid = fid; - ether_addr_copy(entry->mac, addr); - - return 0; -} - static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, const unsigned char *addr, u16 vid, u8 state) @@ -2098,10 +2028,21 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, if (err) return err; - err = mv88e6xxx_atu_get(chip, vlan.fid, addr, &entry); + entry.state = GLOBAL_ATU_DATA_STATE_UNUSED; + ether_addr_copy(entry.mac, addr); + eth_addr_dec(entry.mac); + + err = mv88e6xxx_g1_atu_getnext(chip, vlan.fid, &entry); if (err) return err; + /* Initialize a fresh ATU entry if it isn't found */ + if (entry.state == GLOBAL_ATU_DATA_STATE_UNUSED || + !ether_addr_equal(entry.mac, addr)) { + memset(&entry, 0, sizeof(entry)); + ether_addr_copy(entry.mac, addr); + } + /* Purge the ATU entry only if no port is using it anymore */ if (state == GLOBAL_ATU_DATA_STATE_UNUSED) { entry.portv_trunkid &= ~BIT(port); @@ -2152,68 +2093,19 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, return err; } -static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, - struct mv88e6xxx_atu_entry *entry) -{ - struct mv88e6xxx_atu_entry next = { 0 }; - u16 val; - int err; - - next.fid = fid; - - err = _mv88e6xxx_atu_wait(chip); - if (err) - return err; - - err = _mv88e6xxx_atu_cmd(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB); - if (err) - return err; - - err = _mv88e6xxx_atu_mac_read(chip, next.mac); - if (err) - return err; - - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val); - if (err) - return err; - - next.state = val & GLOBAL_ATU_DATA_STATE_MASK; - if (next.state != GLOBAL_ATU_DATA_STATE_UNUSED) { - unsigned int mask, shift; - - if (val & GLOBAL_ATU_DATA_TRUNK) { - next.trunk = true; - mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK; - shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT; - } else { - next.trunk = false; - mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK; - shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT; - } - - next.portv_trunkid = (val & mask) >> shift; - } - - *entry = next; - return 0; -} - static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, u16 fid, u16 vid, int port, struct switchdev_obj *obj, int (*cb)(struct switchdev_obj *obj)) { - struct mv88e6xxx_atu_entry addr = { - .mac = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, - }; + struct mv88e6xxx_atu_entry addr; int err; - err = _mv88e6xxx_atu_mac_write(chip, addr.mac); - if (err) - return err; + addr.state = GLOBAL_ATU_DATA_STATE_UNUSED; + eth_broadcast_addr(addr.mac); do { - err = _mv88e6xxx_atu_getnext(chip, fid, &addr); + err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 2c03f2e04639..8dd8ecc9f064 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -41,6 +41,8 @@ int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all); int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, unsigned int msecs); +int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry); int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, struct mv88e6xxx_atu_entry *entry); diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 09190559178b..94e940522849 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -109,6 +109,27 @@ static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op) /* Offset 0x0C: ATU Data Register */ +static int mv88e6xxx_g1_atu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 val; + int err; + + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val); + if (err) + return err; + + entry->state = val & 0xf; + if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { + if (val & GLOBAL_ATU_DATA_TRUNK) + entry->trunk = true; + + entry->portv_trunkid = (val >> 4) & mv88e6xxx_port_mask(chip); + } + + return 0; +} + static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip, struct mv88e6xxx_atu_entry *entry) { @@ -129,6 +150,24 @@ static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip, * Offset 0x0F: ATU MAC Address Register Bytes 4 & 5 */ +static int mv88e6xxx_g1_atu_mac_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_atu_entry *entry) +{ + u16 val; + int i, err; + + for (i = 0; i < 3; i++) { + err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val); + if (err) + return err; + + entry->mac[i * 2] = val >> 8; + entry->mac[i * 2 + 1] = val & 0xff; + } + + return 0; +} + static int mv88e6xxx_g1_atu_mac_write(struct mv88e6xxx_chip *chip, struct mv88e6xxx_atu_entry *entry) { @@ -147,6 +186,33 @@ static int mv88e6xxx_g1_atu_mac_write(struct mv88e6xxx_chip *chip, /* Address Translation Unit operations */ +int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry) +{ + int err; + + err = mv88e6xxx_g1_atu_op_wait(chip); + if (err) + return err; + + /* Write the MAC address to iterate from only once */ + if (entry->state == GLOBAL_ATU_DATA_STATE_UNUSED) { + err = mv88e6xxx_g1_atu_mac_write(chip, entry); + if (err) + return err; + } + + err = mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB); + if (err) + return err; + + err = mv88e6xxx_g1_atu_data_read(chip, entry); + if (err) + return err; + + return mv88e6xxx_g1_atu_mac_read(chip, entry); +} + int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, struct mv88e6xxx_atu_entry *entry) { From daefc94321ee146df2a750a4575bfbde98bad2d9 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:54 -0500 Subject: [PATCH 205/399] net: dsa: mv88e6xxx: rework ATU Flush Add a fresh documented implementation of the ATU Flush/Move operation. Use it to replace the current ATU Flush operation. _mv88e6xxx_atu_flush_move is still used by the Move operation so keep it until the Move operation is refactored in a next commit. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 22 ++++----------- drivers/net/dsa/mv88e6xxx/global1.h | 1 + drivers/net/dsa/mv88e6xxx/global1_atu.c | 37 +++++++++++++++++++++++++ 3 files changed, 43 insertions(+), 17 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 2d1ec0d79fb6..8b8c3cb167c1 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1210,17 +1210,6 @@ static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_chip *chip, return _mv88e6xxx_atu_cmd(chip, entry->fid, op); } -static int _mv88e6xxx_atu_flush(struct mv88e6xxx_chip *chip, - u16 fid, bool static_too) -{ - struct mv88e6xxx_atu_entry entry = { - .fid = fid, - .state = 0, /* EntryState bits must be 0 */ - }; - - return _mv88e6xxx_atu_flush_move(chip, &entry, static_too); -} - static int _mv88e6xxx_atu_move(struct mv88e6xxx_chip *chip, u16 fid, int from_port, int to_port, bool static_too) { @@ -1310,6 +1299,10 @@ static int mv88e6xxx_atu_setup(struct mv88e6xxx_chip *chip) { int err; + err = mv88e6xxx_g1_atu_flush(chip, 0, true); + if (err) + return err; + err = mv88e6xxx_g1_atu_set_learn2all(chip, true); if (err) return err; @@ -1714,7 +1707,7 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid) return -ENOSPC; /* Clear the database */ - return _mv88e6xxx_atu_flush(chip, *fid, true); + return mv88e6xxx_g1_atu_flush(chip, *fid, true); } static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid, @@ -2634,11 +2627,6 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip) if (err < 0) return err; - /* Clear all ATU entries */ - err = _mv88e6xxx_atu_flush(chip, 0, true); - if (err) - return err; - /* Configure the IP ToS mapping registers. */ err = mv88e6xxx_g1_write(chip, GLOBAL_IP_PRI_0, 0x0000); if (err) diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 8dd8ecc9f064..187acfc8ed37 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -45,5 +45,6 @@ int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, struct mv88e6xxx_atu_entry *entry); int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, struct mv88e6xxx_atu_entry *entry); +int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all); #endif /* _MV88E6XXX_GLOBAL1_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 94e940522849..7ec9b22feaee 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -232,3 +232,40 @@ int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, return mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_LOAD_DB); } + +static int mv88e6xxx_g1_atu_flushmove(struct mv88e6xxx_chip *chip, u16 fid, + struct mv88e6xxx_atu_entry *entry, + bool all) +{ + u16 op; + int err; + + err = mv88e6xxx_g1_atu_op_wait(chip); + if (err) + return err; + + err = mv88e6xxx_g1_atu_data_write(chip, entry); + if (err) + return err; + + /* Flush/Move all or non-static entries from all or a given database */ + if (all && fid) + op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB; + else if (fid) + op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB; + else if (all) + op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL; + else + op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC; + + return mv88e6xxx_g1_atu_op(chip, fid, op); +} + +int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all) +{ + struct mv88e6xxx_atu_entry entry = { + .state = 0, /* Null EntryState means Flush */ + }; + + return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all); +} From e606ca36bbf2e243171d42186573df254b33a123 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:55 -0500 Subject: [PATCH 206/399] net: dsa: mv88e6xxx: rework ATU Remove Add a fresh documented implementation of the ATU Move operation, and use it to replace the current ATU Remove operation. Note that not all Marvell switch chip support the ATU Move operation. For those supporting it, the number of bits used to mask the destination port may vary. 6352 and such use 4-bit, while 6390 use 5-bit. Thus add a new atu_move_port_mask member in the info structure to describe the presence and variant of ATU Move operation. Note that the ATU Move operation is not documented in the 6185 datasheet but the chip does support the operation. All remaining _mv88e6xxx_atu_* functions are now unused as well as the MV88E6XXX_FLAG_G1_ATU_FID flag, thus remove them. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 140 +++++------------------- drivers/net/dsa/mv88e6xxx/global1.h | 2 + drivers/net/dsa/mv88e6xxx/global1_atu.c | 29 +++++ drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 18 ++- 4 files changed, 67 insertions(+), 122 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8b8c3cb167c1..a11e5354f14f 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1066,11 +1066,6 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, mutex_unlock(&chip->reg_lock); } -static int _mv88e6xxx_atu_wait(struct mv88e6xxx_chip *chip) -{ - return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY); -} - static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e) { @@ -1130,111 +1125,6 @@ static int mv88e6xxx_set_eee(struct dsa_switch *ds, int port, return err; } -static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_chip *chip, u16 fid, u16 cmd) -{ - u16 val; - int err; - - if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G1_ATU_FID)) { - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid); - if (err) - return err; - } else if (mv88e6xxx_num_databases(chip) == 256) { - /* ATU DBNum[7:4] are located in ATU Control 15:12 */ - err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val); - if (err) - return err; - - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, - (val & 0xfff) | ((fid << 8) & 0xf000)); - if (err) - return err; - - /* ATU DBNum[3:0] are located in ATU Operation 3:0 */ - cmd |= fid & 0xf; - } - - err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, cmd); - if (err) - return err; - - return _mv88e6xxx_atu_wait(chip); -} - -static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_atu_entry *entry) -{ - u16 data = entry->state & GLOBAL_ATU_DATA_STATE_MASK; - - if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { - unsigned int mask, shift; - - if (entry->trunk) { - data |= GLOBAL_ATU_DATA_TRUNK; - mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK; - shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT; - } else { - mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK; - shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT; - } - - data |= (entry->portv_trunkid << shift) & mask; - } - - return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data); -} - -static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_atu_entry *entry, - bool static_too) -{ - int op; - int err; - - err = _mv88e6xxx_atu_wait(chip); - if (err) - return err; - - err = _mv88e6xxx_atu_data_write(chip, entry); - if (err) - return err; - - if (entry->fid) { - op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB : - GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB; - } else { - op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL : - GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC; - } - - return _mv88e6xxx_atu_cmd(chip, entry->fid, op); -} - -static int _mv88e6xxx_atu_move(struct mv88e6xxx_chip *chip, u16 fid, - int from_port, int to_port, bool static_too) -{ - struct mv88e6xxx_atu_entry entry = { - .trunk = false, - .fid = fid, - }; - - /* EntryState bits must be 0xF */ - entry.state = GLOBAL_ATU_DATA_STATE_MASK; - - /* ToPort and FromPort are respectively in PortVec bits 7:4 and 3:0 */ - entry.portv_trunkid = (to_port & 0x0f) << 4; - entry.portv_trunkid |= from_port & 0x0f; - - return _mv88e6xxx_atu_flush_move(chip, &entry, static_too); -} - -static int _mv88e6xxx_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, - int port, bool static_too) -{ - /* Destination port 0xF means remove the entries */ - return _mv88e6xxx_atu_move(chip, fid, port, 0x0f, static_too); -} - static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port) { struct dsa_switch *ds = chip->ds; @@ -1316,7 +1206,7 @@ static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port) int err; mutex_lock(&chip->reg_lock); - err = _mv88e6xxx_atu_remove(chip, 0, port, false); + err = mv88e6xxx_g1_atu_remove(chip, 0, port, false); mutex_unlock(&chip->reg_lock); if (err) @@ -1968,7 +1858,7 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip, if (err) return err; - return _mv88e6xxx_atu_remove(chip, vlan.fid, port, false); + return mv88e6xxx_g1_atu_remove(chip, vlan.fid, port, false); } static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, @@ -3688,6 +3578,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6097, .ops = &mv88e6085_ops, @@ -3703,6 +3594,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6095, .ops = &mv88e6095_ops, @@ -3718,6 +3610,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6097, .ops = &mv88e6097_ops, @@ -3733,6 +3626,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6165, .ops = &mv88e6123_ops, @@ -3748,6 +3642,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6185, .ops = &mv88e6131_ops, @@ -3763,6 +3658,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6165, .ops = &mv88e6161_ops, @@ -3778,6 +3674,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6165, .ops = &mv88e6165_ops, @@ -3793,6 +3690,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6171_ops, @@ -3808,6 +3706,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6172_ops, @@ -3823,6 +3722,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6175_ops, @@ -3838,6 +3738,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6176_ops, @@ -3853,6 +3754,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6185, .ops = &mv88e6185_ops, @@ -3869,6 +3771,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .tag_protocol = DSA_TAG_PROTO_DSA, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6190_ops, }, @@ -3883,6 +3786,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6190x_ops, @@ -3898,6 +3802,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6391_ops, @@ -3913,6 +3818,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6240_ops, @@ -3928,6 +3834,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6290_ops, @@ -3943,6 +3850,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6320, .ops = &mv88e6320_ops, @@ -3958,6 +3866,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 8, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6320, .ops = &mv88e6321_ops, @@ -3972,6 +3881,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .port_base_addr = 0x10, .global1_addr = 0x1b, .age_time_coeff = 3750, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6341, .ops = &mv88e6141_ops, @@ -3986,6 +3896,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .port_base_addr = 0x10, .global1_addr = 0x1b, .age_time_coeff = 3750, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6341, .ops = &mv88e6341_ops, @@ -4001,6 +3912,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6350_ops, @@ -4016,6 +3928,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6351, .ops = &mv88e6351_ops, @@ -4031,6 +3944,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 15000, .g1_irqs = 9, + .atu_move_port_mask = 0xf, .tag_protocol = DSA_TAG_PROTO_EDSA, .flags = MV88E6XXX_FLAGS_FAMILY_6352, .ops = &mv88e6352_ops, @@ -4045,6 +3959,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6390_ops, @@ -4059,6 +3974,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .global1_addr = 0x1b, .age_time_coeff = 3750, .g1_irqs = 9, + .atu_move_port_mask = 0x1f, .tag_protocol = DSA_TAG_PROTO_DSA, .flags = MV88E6XXX_FLAGS_FAMILY_6390, .ops = &mv88e6390x_ops, diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 187acfc8ed37..eece7418e67d 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -46,5 +46,7 @@ int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid, int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid, struct mv88e6xxx_atu_entry *entry); int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all); +int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port, + bool all); #endif /* _MV88E6XXX_GLOBAL1_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 7ec9b22feaee..d753e3eb1359 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -269,3 +269,32 @@ int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all) return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all); } + +static int mv88e6xxx_g1_atu_move(struct mv88e6xxx_chip *chip, u16 fid, + int from_port, int to_port, bool all) +{ + struct mv88e6xxx_atu_entry entry = { 0 }; + unsigned long mask; + int shift; + + if (!chip->info->atu_move_port_mask) + return -EOPNOTSUPP; + + mask = chip->info->atu_move_port_mask; + shift = bitmap_weight(&mask, 16); + + entry.state = 0xf, /* Full EntryState means Move */ + entry.portv_trunkid = from_port & mask; + entry.portv_trunkid |= (to_port & mask) << shift; + + return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all); +} + +int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port, + bool all) +{ + int from_port = port; + int to_port = chip->info->atu_move_port_mask; + + return mv88e6xxx_g1_atu_move(chip, fid, from_port, to_port, all); +} diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 45205519b9fe..1fca6fae2f83 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -552,7 +552,6 @@ enum mv88e6xxx_cap { #define MV88E6XXX_FLAG_SERDES BIT_ULL(MV88E6XXX_CAP_SERDES) -#define MV88E6XXX_FLAG_G1_ATU_FID BIT_ULL(MV88E6XXX_CAP_G1_ATU_FID) #define MV88E6XXX_FLAG_G1_VTU_FID BIT_ULL(MV88E6XXX_CAP_G1_VTU_FID) #define MV88E6XXX_FLAG_GLOBAL2 BIT_ULL(MV88E6XXX_CAP_GLOBAL2) @@ -595,8 +594,7 @@ enum mv88e6xxx_cap { MV88E6XXX_FLAGS_MULTI_CHIP) #define MV88E6XXX_FLAGS_FAMILY_6097 \ - (MV88E6XXX_FLAG_G1_ATU_FID | \ - MV88E6XXX_FLAG_G1_VTU_FID | \ + (MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ @@ -609,8 +607,7 @@ enum mv88e6xxx_cap { MV88E6XXX_FLAGS_PVT) #define MV88E6XXX_FLAGS_FAMILY_6165 \ - (MV88E6XXX_FLAG_G1_ATU_FID | \ - MV88E6XXX_FLAG_G1_VTU_FID | \ + (MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ @@ -642,7 +639,6 @@ enum mv88e6xxx_cap { #define MV88E6XXX_FLAGS_FAMILY_6341 \ (MV88E6XXX_FLAG_EEE | \ - MV88E6XXX_FLAG_G1_ATU_FID | \ MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ @@ -655,8 +651,7 @@ enum mv88e6xxx_cap { MV88E6XXX_FLAGS_SERDES) #define MV88E6XXX_FLAGS_FAMILY_6351 \ - (MV88E6XXX_FLAG_G1_ATU_FID | \ - MV88E6XXX_FLAG_G1_VTU_FID | \ + (MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ MV88E6XXX_FLAG_G2_MGMT_EN_2X | \ @@ -670,7 +665,6 @@ enum mv88e6xxx_cap { #define MV88E6XXX_FLAGS_FAMILY_6352 \ (MV88E6XXX_FLAG_EEE | \ - MV88E6XXX_FLAG_G1_ATU_FID | \ MV88E6XXX_FLAG_G1_VTU_FID | \ MV88E6XXX_FLAG_GLOBAL2 | \ MV88E6XXX_FLAG_G2_INT | \ @@ -708,11 +702,15 @@ struct mv88e6xxx_info { unsigned int g1_irqs; enum dsa_tag_protocol tag_protocol; unsigned long long flags; + + /* Mask for FromPort and ToPort value of PortVec used in ATU Move + * operation. 0 means that the ATU Move operation is not supported. + */ + u8 atu_move_port_mask; const struct mv88e6xxx_ops *ops; }; struct mv88e6xxx_atu_entry { - u16 fid; u8 state; bool trunk; u16 portv_trunkid; From d7f435f9671ed207231c3711d175a0178356514d Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:56 -0500 Subject: [PATCH 207/399] net: dsa: mv88e6xxx: rename new FID helper Rename the _mv88e6xxx_fid_new helper to mv88e6xxx_atu_new to get rid of the old underscore prefix naming convention and be consistent with the rest of the chip-wide ATU API. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index a11e5354f14f..df31c2c57e09 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1556,7 +1556,7 @@ static int _mv88e6xxx_stu_loadpurge(struct mv88e6xxx_chip *chip, return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE); } -static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid) +static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) { DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID); struct mv88e6xxx_vtu_entry vlan; @@ -1610,7 +1610,7 @@ static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid, }; int i, err; - err = _mv88e6xxx_fid_new(chip, &vlan.fid); + err = mv88e6xxx_atu_new(chip, &vlan.fid); if (err) return err; From 01bd96c8831e54a3ba2794c647a269d130872750 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:57 -0500 Subject: [PATCH 208/399] net: dsa: mv88e6xxx: rename the port vector member Not all Marvell switch chips support port trunking, which is embedded in the port vector data for ATU operations. Rename the portv_trunkid member of the mv88e6xxx_atu_entry structure to portvec to be more concise and consistent with the different chips. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 8 ++++---- drivers/net/dsa/mv88e6xxx/global1_atu.c | 8 ++++---- drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index df31c2c57e09..e9533d4919bc 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1928,11 +1928,11 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, /* Purge the ATU entry only if no port is using it anymore */ if (state == GLOBAL_ATU_DATA_STATE_UNUSED) { - entry.portv_trunkid &= ~BIT(port); - if (!entry.portv_trunkid) + entry.portvec &= ~BIT(port); + if (!entry.portvec) entry.state = GLOBAL_ATU_DATA_STATE_UNUSED; } else { - entry.portv_trunkid |= BIT(port); + entry.portvec |= BIT(port); entry.state = state; } @@ -1995,7 +1995,7 @@ static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, if (addr.state == GLOBAL_ATU_DATA_STATE_UNUSED) break; - if (addr.trunk || (addr.portv_trunkid & BIT(port)) == 0) + if (addr.trunk || (addr.portvec & BIT(port)) == 0) continue; if (obj->id == SWITCHDEV_OBJ_ID_PORT_FDB) { diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index d753e3eb1359..120b7f41a735 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -124,7 +124,7 @@ static int mv88e6xxx_g1_atu_data_read(struct mv88e6xxx_chip *chip, if (val & GLOBAL_ATU_DATA_TRUNK) entry->trunk = true; - entry->portv_trunkid = (val >> 4) & mv88e6xxx_port_mask(chip); + entry->portvec = (val >> 4) & mv88e6xxx_port_mask(chip); } return 0; @@ -139,7 +139,7 @@ static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip, if (entry->trunk) data |= GLOBAL_ATU_DATA_TRUNK; - data |= (entry->portv_trunkid & mv88e6xxx_port_mask(chip)) << 4; + data |= (entry->portvec & mv88e6xxx_port_mask(chip)) << 4; } return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data); @@ -284,8 +284,8 @@ static int mv88e6xxx_g1_atu_move(struct mv88e6xxx_chip *chip, u16 fid, shift = bitmap_weight(&mask, 16); entry.state = 0xf, /* Full EntryState means Move */ - entry.portv_trunkid = from_port & mask; - entry.portv_trunkid |= (to_port & mask) << shift; + entry.portvec = from_port & mask; + entry.portvec |= (to_port & mask) << shift; return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all); } diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 1fca6fae2f83..69acb4c40fdc 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -713,7 +713,7 @@ struct mv88e6xxx_info { struct mv88e6xxx_atu_entry { u8 state; bool trunk; - u16 portv_trunkid; + u16 portvec; u8 mac[ETH_ALEN]; }; From 6cd456f38207b56ba18c444d50fe49a7fe8b2a0a Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:58 -0500 Subject: [PATCH 209/399] net: dsa: add dsa_is_normal_port helper Introduce a dsa_is_normal_port helper to check if a given port is a normal user port as opposed to a CPU port or DSA link. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/net/dsa.h b/include/net/dsa.h index 4e13e695f025..bf0e42c2a6f7 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -248,6 +248,11 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) return !!((ds->dsa_port_mask) & (1 << p)); } +static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p) +{ + return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p); +} + static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; From 4314557c6505a14043717de01036dc0e3a357010 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:12:59 -0500 Subject: [PATCH 210/399] net: dsa: mv88e6xxx: rework port mode setup A switch port mode is defined by the association of its egress mode, its frame mode and if supported or required, the ether type value. Pack all this in a mv88e6xxx_set_port_mode function and provide helpers for the Normal Network mode, the DSA mode, and the Ether Type DSA mode, as well as an helper to setup a port's mode depending on its nature. Define PORT_ETH_TYPE_DEFAULT for the 0x9100 reset value of port E Type. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 114 ++++++++++++++------------ drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 1 + 2 files changed, 64 insertions(+), 51 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index e9533d4919bc..5f5023215ce1 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2199,69 +2199,82 @@ static int mv88e6xxx_serdes_power_on(struct mv88e6xxx_chip *chip) return err; } -static int mv88e6xxx_setup_port_dsa(struct mv88e6xxx_chip *chip, int port, - int upstream_port) +static int mv88e6xxx_set_port_mode(struct mv88e6xxx_chip *chip, int port, + enum mv88e6xxx_frame_mode frame, u16 egress, + u16 etype) { int err; - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_DSA); + if (!chip->info->ops->port_set_frame_mode) + return -EOPNOTSUPP; + + err = mv88e6xxx_port_set_egress_mode(chip, port, egress); if (err) return err; + err = chip->info->ops->port_set_frame_mode(chip, port, frame); + if (err) + return err; + + if (chip->info->ops->port_set_ether_type) + return chip->info->ops->port_set_ether_type(chip, port, etype); + + return 0; +} + +static int mv88e6xxx_set_port_mode_normal(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_NORMAL, + PORT_CONTROL_EGRESS_UNMODIFIED, + PORT_ETH_TYPE_DEFAULT); +} + +static int mv88e6xxx_set_port_mode_dsa(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_DSA, + PORT_CONTROL_EGRESS_UNMODIFIED, + PORT_ETH_TYPE_DEFAULT); +} + +static int mv88e6xxx_set_port_mode_edsa(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_set_port_mode(chip, port, + MV88E6XXX_FRAME_MODE_ETHERTYPE, + PORT_CONTROL_EGRESS_ADD_TAG, ETH_P_EDSA); +} + +static int mv88e6xxx_setup_port_mode(struct mv88e6xxx_chip *chip, int port) +{ + if (dsa_is_dsa_port(chip->ds, port)) + return mv88e6xxx_set_port_mode_dsa(chip, port); + + if (dsa_is_normal_port(chip->ds, port)) + return mv88e6xxx_set_port_mode_normal(chip, port); + + /* Setup CPU port mode depending on its supported tag format */ + if (chip->info->tag_protocol == DSA_TAG_PROTO_DSA) + return mv88e6xxx_set_port_mode_dsa(chip, port); + + if (chip->info->tag_protocol == DSA_TAG_PROTO_EDSA) + return mv88e6xxx_set_port_mode_edsa(chip, port); + + return -EINVAL; +} + +static int mv88e6xxx_setup_port_dsa(struct mv88e6xxx_chip *chip, int port, + int upstream_port) +{ return chip->info->ops->port_set_egress_unknowns( chip, port, port == upstream_port); } static int mv88e6xxx_setup_port_cpu(struct mv88e6xxx_chip *chip, int port) { - int err; - - switch (chip->info->tag_protocol) { - case DSA_TAG_PROTO_EDSA: - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_ETHERTYPE); - if (err) - return err; - - err = mv88e6xxx_port_set_egress_mode( - chip, port, PORT_CONTROL_EGRESS_ADD_TAG); - if (err) - return err; - - if (chip->info->ops->port_set_ether_type) - err = chip->info->ops->port_set_ether_type( - chip, port, ETH_P_EDSA); - break; - - case DSA_TAG_PROTO_DSA: - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_DSA); - if (err) - return err; - - err = mv88e6xxx_port_set_egress_mode( - chip, port, PORT_CONTROL_EGRESS_UNMODIFIED); - break; - default: - err = -EINVAL; - } - - if (err) - return err; - return chip->info->ops->port_set_egress_unknowns(chip, port, true); } static int mv88e6xxx_setup_port_normal(struct mv88e6xxx_chip *chip, int port) { - int err; - - err = chip->info->ops->port_set_frame_mode( - chip, port, MV88E6XXX_FRAME_MODE_NORMAL); - if (err) - return err; - return chip->info->ops->port_set_egress_unknowns(chip, port, false); } @@ -2325,6 +2338,10 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; + err = mv88e6xxx_setup_port_mode(chip, port); + if (err) + return err; + /* If this port is connected to a SerDes, make sure the SerDes is not * powered down. */ @@ -3554,11 +3571,6 @@ static const struct mv88e6xxx_ops mv88e6391_ops = { static int mv88e6xxx_verify_madatory_ops(struct mv88e6xxx_chip *chip, const struct mv88e6xxx_ops *ops) { - if (!ops->port_set_frame_mode) { - dev_err(chip->dev, "Missing port_set_frame_mode"); - return -EINVAL; - } - if (!ops->port_set_egress_unknowns) { dev_err(chip->dev, "Missing port_set_egress_mode"); return -EINVAL; diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 69acb4c40fdc..185be5434980 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -182,6 +182,7 @@ #define PORT_ATU_CONTROL 0x0c #define PORT_PRI_OVERRIDE 0x0d #define PORT_ETH_TYPE 0x0f +#define PORT_ETH_TYPE_DEFAULT 0x9100 #define PORT_IN_DISCARD_LO 0x10 #define PORT_IN_DISCARD_HI 0x11 #define PORT_IN_FILTERED 0x12 From 601aeed371a36e6675f3c7f7f6cf8bc181f1f276 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:13:00 -0500 Subject: [PATCH 211/399] net: dsa: mv88e6xxx: fix port egress flooding mode The Marvell switch ports can be configured to allow or prevent egress of frames with an unknown unicast or multicast destination address. Some switch chips such as 88E6095 and 88E6185 have two disjoint bits in Port Control Register (0x04) bit 2 "Forward Unknown" (for unicast) and Port Control 2 Register (0x08) bit 6 "Default Forward" (for multicast). Other chips such as 88E6085, 88E6123, 88E6352, and 88E6390 have a 2-bit value in Port Control Register (0x04) bits 3:2 "EgressFloods". The current code does not fully implement the disjoint bits variant and assigns incorrect ones to some chip models. Fix that with two implementation references (6185 and 6352 that I currently have) of a port_set_egress_floods operation (as named in datasheets). Old chips such as 88E6060 don't have egress flooding mode, so don't error out if the operation is not provided. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 107 ++++++++++---------------- drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 15 ++-- drivers/net/dsa/mv88e6xxx/port.c | 44 +++++++---- drivers/net/dsa/mv88e6xxx/port.h | 10 +-- 4 files changed, 82 insertions(+), 94 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 5f5023215ce1..0844df1b25e9 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2261,23 +2261,6 @@ static int mv88e6xxx_setup_port_mode(struct mv88e6xxx_chip *chip, int port) return -EINVAL; } -static int mv88e6xxx_setup_port_dsa(struct mv88e6xxx_chip *chip, int port, - int upstream_port) -{ - return chip->info->ops->port_set_egress_unknowns( - chip, port, port == upstream_port); -} - -static int mv88e6xxx_setup_port_cpu(struct mv88e6xxx_chip *chip, int port) -{ - return chip->info->ops->port_set_egress_unknowns(chip, port, true); -} - -static int mv88e6xxx_setup_port_normal(struct mv88e6xxx_chip *chip, int port) -{ - return chip->info->ops->port_set_egress_unknowns(chip, port, false); -} - static int mv88e6xxx_setup_message_port(struct mv88e6xxx_chip *chip, int port) { bool message = dsa_is_dsa_port(chip->ds, port); @@ -2285,6 +2268,18 @@ static int mv88e6xxx_setup_message_port(struct mv88e6xxx_chip *chip, int port) return mv88e6xxx_port_set_message_port(chip, port, message); } +static int mv88e6xxx_setup_egress_floods(struct mv88e6xxx_chip *chip, int port) +{ + bool flood = port == dsa_upstream_port(chip->ds); + + /* Upstream ports flood frames with unknown unicast or multicast DA */ + if (chip->info->ops->port_set_egress_floods) + return chip->info->ops->port_set_egress_floods(chip, port, + flood, flood); + + return 0; +} + static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) { struct dsa_switch *ds = chip->ds; @@ -2327,18 +2322,11 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; - if (dsa_is_cpu_port(ds, port)) { - err = mv88e6xxx_setup_port_cpu(chip, port); - } else if (dsa_is_dsa_port(ds, port)) { - err = mv88e6xxx_setup_port_dsa(chip, port, - dsa_upstream_port(ds)); - } else { - err = mv88e6xxx_setup_port_normal(chip, port); - } + err = mv88e6xxx_setup_port_mode(chip, port); if (err) return err; - err = mv88e6xxx_setup_port_mode(chip, port); + err = mv88e6xxx_setup_egress_floods(chip, port); if (err) return err; @@ -2847,7 +2835,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, @@ -2873,7 +2861,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, .port_set_frame_mode = mv88e6085_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6185_port_set_egress_floods, .port_set_upstream_port = mv88e6095_port_set_upstream_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -2895,7 +2883,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting, @@ -2920,7 +2908,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, .port_set_frame_mode = mv88e6085_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6085_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2942,7 +2930,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6185_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_set_upstream_port = mv88e6095_port_set_upstream_port, .port_jumbo_config = mv88e6165_port_jumbo_config, @@ -2971,7 +2959,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3017,7 +3005,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3046,7 +3034,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3073,7 +3061,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3102,7 +3090,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3127,7 +3115,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, .port_set_frame_mode = mv88e6085_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6185_port_set_egress_floods, .port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting, .port_set_upstream_port = mv88e6095_port_set_upstream_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, @@ -3156,7 +3144,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .stats_snapshot = mv88e6390_g1_stats_snapshot, @@ -3184,7 +3172,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .port_set_speed = mv88e6390x_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .stats_snapshot = mv88e6390_g1_stats_snapshot, @@ -3212,7 +3200,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .stats_snapshot = mv88e6390_g1_stats_snapshot, @@ -3240,7 +3228,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3269,7 +3257,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .port_set_cmode = mv88e6390x_port_set_cmode, @@ -3297,7 +3285,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3324,7 +3312,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3349,7 +3337,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3376,7 +3364,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3405,7 +3393,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .port_set_speed = mv88e6352_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3434,7 +3422,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3463,7 +3451,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3492,7 +3480,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3523,7 +3511,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_set_speed = mv88e6390x_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, @@ -3553,7 +3541,7 @@ static const struct mv88e6xxx_ops mv88e6391_ops = { .port_set_speed = mv88e6390_port_set_speed, .port_tag_remap = mv88e6390_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, - .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .stats_snapshot = mv88e6390_g1_stats_snapshot, @@ -3568,17 +3556,6 @@ static const struct mv88e6xxx_ops mv88e6391_ops = { .reset = mv88e6352_g1_reset, }; -static int mv88e6xxx_verify_madatory_ops(struct mv88e6xxx_chip *chip, - const struct mv88e6xxx_ops *ops) -{ - if (!ops->port_set_egress_unknowns) { - dev_err(chip->dev, "Missing port_set_egress_mode"); - return -EINVAL; - } - - return 0; -} - static const struct mv88e6xxx_info mv88e6xxx_table[] = { [MV88E6085] = { .prod_num = PORT_SWITCH_ID_PROD_NUM_6085, @@ -4269,10 +4246,6 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) chip->info = compat_info; - err = mv88e6xxx_verify_madatory_ops(chip, chip->info->ops); - if (err) - return err; - err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 185be5434980..bde7c775d559 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -132,12 +132,12 @@ #define PORT_CONTROL_TAG_IF_BOTH BIT(6) #define PORT_CONTROL_USE_IP BIT(5) #define PORT_CONTROL_USE_TAG BIT(4) -#define PORT_CONTROL_FORWARD_UNKNOWN_MC BIT(3) #define PORT_CONTROL_FORWARD_UNKNOWN BIT(2) -#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_DA (0x0 << 2) -#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_MULTICAST_DA (0x1 << 2) -#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_UNITCAST_DA (0x2 << 2) -#define PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA (0x3 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_MASK (0x3 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA (0x0 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA (0x1 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA (0x2 << 2) +#define PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA (0x3 << 2) #define PORT_CONTROL_STATE_MASK 0x03 #define PORT_CONTROL_STATE_DISABLED 0x00 #define PORT_CONTROL_STATE_BLOCKING 0x01 @@ -167,7 +167,6 @@ #define PORT_CONTROL_2_DISCARD_UNTAGGED BIT(8) #define PORT_CONTROL_2_MAP_DA BIT(7) #define PORT_CONTROL_2_DEFAULT_FORWARD BIT(6) -#define PORT_CONTROL_2_FORWARD_UNKNOWN BIT(6) #define PORT_CONTROL_2_EGRESS_MONITOR BIT(5) #define PORT_CONTROL_2_INGRESS_MONITOR BIT(4) #define PORT_CONTROL_2_UPSTREAM_MASK 0x0f @@ -864,8 +863,8 @@ struct mv88e6xxx_ops { int (*port_set_frame_mode)(struct mv88e6xxx_chip *chip, int port, enum mv88e6xxx_frame_mode mode); - int (*port_set_egress_unknowns)(struct mv88e6xxx_chip *chip, int port, - bool on); + int (*port_set_egress_floods)(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast); int (*port_set_ether_type)(struct mv88e6xxx_chip *chip, int port, u16 etype); int (*port_jumbo_config)(struct mv88e6xxx_chip *chip, int port); diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 40fe48188056..c918292217ff 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -497,8 +497,8 @@ int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port, return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg); } -int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on) +static int mv88e6185_port_set_forward_unknown(struct mv88e6xxx_chip *chip, + int port, bool unicast) { int err; u16 reg; @@ -507,7 +507,7 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (on) + if (unicast) reg |= PORT_CONTROL_FORWARD_UNKNOWN; else reg &= ~PORT_CONTROL_FORWARD_UNKNOWN; @@ -515,8 +515,8 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg); } -int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on) +int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast) { int err; u16 reg; @@ -525,10 +525,16 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (on) - reg |= PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA; + reg &= ~PORT_CONTROL_EGRESS_FLOODS_MASK; + + if (unicast && multicast) + reg |= PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA; + else if (unicast) + reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA; + else if (multicast) + reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA; else - reg &= ~PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA; + reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA; return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg); } @@ -690,8 +696,8 @@ static const char * const mv88e6xxx_port_8021q_mode_names[] = { [PORT_CONTROL_2_8021Q_SECURE] = "Secure", }; -int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on) +static int mv88e6185_port_set_default_forward(struct mv88e6xxx_chip *chip, + int port, bool multicast) { int err; u16 reg; @@ -700,14 +706,26 @@ int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (on) - reg |= PORT_CONTROL_2_FORWARD_UNKNOWN; + if (multicast) + reg |= PORT_CONTROL_2_DEFAULT_FORWARD; else - reg &= ~PORT_CONTROL_2_FORWARD_UNKNOWN; + reg &= ~PORT_CONTROL_2_DEFAULT_FORWARD; return mv88e6xxx_port_write(chip, port, PORT_CONTROL_2, reg); } +int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast) +{ + int err; + + err = mv88e6185_port_set_forward_unknown(chip, port, unicast); + if (err) + return err; + + return mv88e6185_port_set_default_forward(chip, port, multicast); +} + int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port) { diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 4328d6f29d4d..35d28d05c009 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -56,12 +56,10 @@ int mv88e6085_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port, enum mv88e6xxx_frame_mode mode); int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port, enum mv88e6xxx_frame_mode mode); -int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on); -int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on); -int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port, - bool on); +int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast); +int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port, + bool unicast, bool multicast); int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port, u16 etype); int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port, From c8c94891527a9e624a40a2e40c5934698443fd9c Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:13:01 -0500 Subject: [PATCH 212/399] net: dsa: mv88e6xxx: add port ATU learn limit op Add a new operation to disable the limiting of learnt MAC addresses. Setting such limit is not likely to be used soon, so provide a port_disable_learn_limit operation directly. This can be changed later for port_set_learn_limit when we'll need it. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 36 ++++++++++++++++++++++----- drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 1 + drivers/net/dsa/mv88e6xxx/port.c | 7 ++++++ drivers/net/dsa/mv88e6xxx/port.h | 3 +++ 4 files changed, 41 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 0844df1b25e9..06fe86309e27 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2401,15 +2401,15 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } + if (chip->info->ops->port_disable_learn_limit) { + err = chip->info->ops->port_disable_learn_limit(chip, port); + if (err) + return err; + } + if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) || mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) || mv88e6xxx_6320_family(chip) || mv88e6xxx_6341_family(chip)) { - /* Port ATU control: disable limiting the number of - * address database entries that this port is allowed - * to use. - */ - err = mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, - 0x0000); /* Priority Override: disable DA, SA and VTU priority * override. */ @@ -2839,6 +2839,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .port_set_ether_type = mv88e6351_port_set_ether_type, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2888,6 +2889,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2909,6 +2911,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .port_set_speed = mv88e6185_port_set_speed, .port_set_frame_mode = mv88e6085_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2964,6 +2967,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2983,6 +2987,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = { .port_set_link = mv88e6xxx_port_set_link, .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3010,6 +3015,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3039,6 +3045,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3066,6 +3073,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3095,6 +3103,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3147,6 +3156,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3175,6 +3185,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3203,6 +3214,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3233,6 +3245,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3261,6 +3274,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .port_set_cmode = mv88e6390x_port_set_cmode, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3290,6 +3304,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3317,6 +3332,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3342,6 +3358,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3369,6 +3386,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3398,6 +3416,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3427,6 +3446,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3456,6 +3476,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3486,6 +3507,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6390_port_pause_config, .port_set_cmode = mv88e6390x_port_set_cmode, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3516,6 +3538,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_jumbo_config = mv88e6165_port_jumbo_config, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3544,6 +3567,7 @@ static const struct mv88e6xxx_ops mv88e6391_ops = { .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, + .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index bde7c775d559..a2a0006d8c98 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -871,6 +871,7 @@ struct mv88e6xxx_ops { int (*port_egress_rate_limiting)(struct mv88e6xxx_chip *chip, int port); int (*port_pause_config)(struct mv88e6xxx_chip *chip, int port); + int (*port_disable_learn_limit)(struct mv88e6xxx_chip *chip, int port); /* CMODE control what PHY mode the MAC will use, eg. SGMII, RGMII, etc. * Some chips allow this to be configured on specific ports. diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index c918292217ff..8152fc96fa67 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -805,6 +805,13 @@ int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port) return mv88e6xxx_port_write(chip, port, PORT_RATE_CONTROL, 0x0001); } +/* Offset 0x0C: Port ATU Control */ + +int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, 0); +} + /* Offset 0x0f: Port Ether type */ int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port, diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 35d28d05c009..e9eccbf277b8 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -75,4 +75,7 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port); int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port); + +int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port); + #endif /* _MV88E6XXX_PORT_H */ From 9dbfb4e1ca45c069bd1156adedfbc95e0c24be28 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:13:02 -0500 Subject: [PATCH 213/399] net: dsa: mv88e6xxx: add port priority override op Add a new operation to disable the DA, SA and VTU priority override. Setting such limit is not likely to be used soon, so provide a port_disable_pri_override operation directly. This can be changed later for port_set_pri_override when we'll need it. Also remove the now obsolete mv88e6xxx_6320_family helper. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 39 ++++++++++++++++++--------- drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 1 + drivers/net/dsa/mv88e6xxx/port.c | 7 +++++ drivers/net/dsa/mv88e6xxx/port.h | 1 + 4 files changed, 35 insertions(+), 13 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 06fe86309e27..3354f99df378 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -687,11 +687,6 @@ static bool mv88e6xxx_6165_family(struct mv88e6xxx_chip *chip) return chip->info->family == MV88E6XXX_FAMILY_6165; } -static bool mv88e6xxx_6320_family(struct mv88e6xxx_chip *chip) -{ - return chip->info->family == MV88E6XXX_FAMILY_6320; -} - static bool mv88e6xxx_6341_family(struct mv88e6xxx_chip *chip) { return chip->info->family == MV88E6XXX_FAMILY_6341; @@ -2407,14 +2402,8 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } - if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) || - mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) || - mv88e6xxx_6320_family(chip) || mv88e6xxx_6341_family(chip)) { - /* Priority Override: disable DA, SA and VTU priority - * override. - */ - err = mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE, - 0x0000); + if (chip->info->ops->port_disable_pri_override) { + err = chip->info->ops->port_disable_pri_override(chip, port); if (err) return err; } @@ -2840,6 +2829,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2890,6 +2880,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2912,6 +2903,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .port_set_frame_mode = mv88e6085_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2968,6 +2960,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -2988,6 +2981,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = { .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_speed = mv88e6185_port_set_speed, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3016,6 +3010,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3046,6 +3041,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3074,6 +3070,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3104,6 +3101,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3157,6 +3155,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3186,6 +3185,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3215,6 +3215,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3246,6 +3247,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3275,6 +3277,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .port_pause_config = mv88e6390_port_pause_config, .port_set_cmode = mv88e6390x_port_set_cmode, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3305,6 +3308,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3333,6 +3337,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3359,6 +3364,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3387,6 +3393,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3417,6 +3424,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -3447,6 +3455,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3477,6 +3486,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6097_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, @@ -3508,6 +3518,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .port_pause_config = mv88e6390_port_pause_config, .port_set_cmode = mv88e6390x_port_set_cmode, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3539,6 +3550,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_config = mv88e6390_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3568,6 +3580,7 @@ static const struct mv88e6xxx_ops mv88e6391_ops = { .port_set_ether_type = mv88e6351_port_set_ether_type, .port_pause_config = mv88e6390_port_pause_config, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index a2a0006d8c98..75be2c339a49 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -872,6 +872,7 @@ struct mv88e6xxx_ops { int (*port_egress_rate_limiting)(struct mv88e6xxx_chip *chip, int port); int (*port_pause_config)(struct mv88e6xxx_chip *chip, int port); int (*port_disable_learn_limit)(struct mv88e6xxx_chip *chip, int port); + int (*port_disable_pri_override)(struct mv88e6xxx_chip *chip, int port); /* CMODE control what PHY mode the MAC will use, eg. SGMII, RGMII, etc. * Some chips allow this to be configured on specific ports. diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 8152fc96fa67..d4868bb50ed5 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -812,6 +812,13 @@ int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port) return mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, 0); } +/* Offset 0x0D: (Priority) Override Register */ + +int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port) +{ + return mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE, 0); +} + /* Offset 0x0f: Port Ether type */ int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port, diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index e9eccbf277b8..c2425ddab287 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -77,5 +77,6 @@ int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port); int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port); +int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port); #endif /* _MV88E6XXX_PORT_H */ From 0c68f666d4cc8835ed888ffdd58f76d4d8e2da51 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sat, 11 Mar 2017 16:13:03 -0500 Subject: [PATCH 214/399] etherdevice: remove unused eth_addr_greater eth_addr_greater() was introduced for the mv88e6xxx driver, but is not used anymore. There is no other user, thus remove this function. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index c62b709b1ce0..2d9f80848d4b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -446,21 +446,6 @@ static inline void eth_addr_dec(u8 *addr) u64_to_ether_addr(u, addr); } -/** - * ether_addr_greater - Compare two Ethernet addresses - * @addr1: Pointer to a six-byte array containing the Ethernet address - * @addr2: Pointer other six-byte array containing the Ethernet address - * - * Compare two Ethernet addresses, returns true addr1 is greater than addr2 - */ -static inline bool ether_addr_greater(const u8 *addr1, const u8 *addr2) -{ - u64 u1 = ether_addr_to_u64(addr1); - u64 u2 = ether_addr_to_u64(addr2); - - return u1 > u2; -} - /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure From 1bcf165ac6556dc55a596d524b8187d1ba7a8c7d Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Sun, 12 Mar 2017 05:02:54 -0400 Subject: [PATCH 215/399] r8169: replace init_timer with setup_timer Replace init_timer with setup_timer to simplify the source code. Signed-off-by: Zhu Yanjun Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 24b045b777b6..0a8f2817ea60 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -8453,9 +8453,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ? ~(RxBOVF | RxFOVF) : ~0; - init_timer(&tp->timer); - tp->timer.data = (unsigned long) dev; - tp->timer.function = rtl8169_phy_timer; + setup_timer(&tp->timer, rtl8169_phy_timer, (unsigned long)dev); tp->rtl_fw = RTL_FIRMWARE_UNKNOWN; From e33cc31630c3ca1de47c2470ec8d41dee0683b11 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 13 Mar 2017 00:00:03 -0700 Subject: [PATCH 216/399] sch_tbf: Remove bogus semicolon in if() conditional. Fixes: 49b499718fa1 ("net: sched: make default fifo qdiscs appear in the dump") Reported-by: kbuild test robot Signed-off-by: David S. Miller --- net/sched/sch_tbf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 40c29a801391..9850126129a3 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -396,7 +396,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; - if (child != &noop_qdisc); + if (child != &noop_qdisc) qdisc_hash_add(child, true); } q->limit = qopt->limit; From 84fba05511c8e0e1a6e6c8ec2c3c85616c39a8c1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Mar 2017 16:48:43 +0100 Subject: [PATCH 217/399] netfilter: provide nft_ctx in object init function this is needed by the upcoming ct helper object type -- we'd like to be able use the table family (ip, ip6, inet) to figure out which helper has to be requested. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 ++- net/netfilter/nf_tables_api.c | 7 ++++--- net/netfilter/nft_counter.c | 3 ++- net/netfilter/nft_quota.c | 3 ++- 4 files changed, 10 insertions(+), 6 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f0d46726d06e..49436849d7d7 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1017,7 +1017,8 @@ struct nft_object_type { unsigned int maxattr; struct module *owner; const struct nla_policy *policy; - int (*init)(const struct nlattr * const tb[], + int (*init)(const struct nft_ctx *ctx, + const struct nlattr *const tb[], struct nft_object *obj); void (*destroy)(struct nft_object *obj); int (*dump)(struct sk_buff *skb, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4559f5d66bcc..12cc5218de96 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4095,7 +4095,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, }; -static struct nft_object *nft_obj_init(const struct nft_object_type *type, +static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, + const struct nft_object_type *type, const struct nlattr *attr) { struct nlattr *tb[type->maxattr + 1]; @@ -4115,7 +4116,7 @@ static struct nft_object *nft_obj_init(const struct nft_object_type *type, if (obj == NULL) goto err1; - err = type->init((const struct nlattr * const *)tb, obj); + err = type->init(ctx, (const struct nlattr * const *)tb, obj); if (err < 0) goto err2; @@ -4223,7 +4224,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (IS_ERR(type)) return PTR_ERR(type); - obj = nft_obj_init(type, nla[NFTA_OBJ_DATA]); + obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { err = PTR_ERR(obj); goto err1; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 7f8422213341..67a710ebde09 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -82,7 +82,8 @@ static int nft_counter_do_init(const struct nlattr * const tb[], return 0; } -static int nft_counter_obj_init(const struct nlattr * const tb[], +static int nft_counter_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], struct nft_object *obj) { struct nft_counter_percpu_priv *priv = nft_obj_data(obj); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 2d6fe3559912..25e33159be57 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -99,7 +99,8 @@ static int nft_quota_do_init(const struct nlattr * const tb[], return 0; } -static int nft_quota_obj_init(const struct nlattr * const tb[], +static int nft_quota_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], struct nft_object *obj) { struct nft_quota *priv = nft_obj_data(obj); From 1a64edf54f55d7956cf5a0d95898bc1f84f9b818 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Mar 2017 16:48:44 +0100 Subject: [PATCH 218/399] netfilter: nft_ct: add helper set support this allows to assign connection tracking helpers to connections via nft objref infrastructure. The idea is to first specifiy a helper object: table ip filter { ct helper some-name { type "ftp" protocol tcp l3proto ip } } and then assign it via nft add ... ct helper set "some-name" helper assignment works for new conntracks only as we cannot expand the conntrack extension area once it has been committed to the main conntrack table. ipv4 and ipv6 protocols are tracked stored separately so we can also handle families that observe both ipv4 and ipv6 traffic. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 12 +- net/netfilter/nft_ct.c | 171 +++++++++++++++++++++++ 2 files changed, 182 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 4f7d75682c59..34c8d08b687a 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1259,10 +1259,20 @@ enum nft_fib_flags { NFTA_FIB_F_OIF = 1 << 4, /* restrict to oif */ }; +enum nft_ct_helper_attributes { + NFTA_CT_HELPER_UNSPEC, + NFTA_CT_HELPER_NAME, + NFTA_CT_HELPER_L3PROTO, + NFTA_CT_HELPER_L4PROTO, + __NFTA_CT_HELPER_MAX, +}; +#define NFTA_CT_HELPER_MAX (__NFTA_CT_HELPER_MAX - 1) + #define NFT_OBJECT_UNSPEC 0 #define NFT_OBJECT_COUNTER 1 #define NFT_OBJECT_QUOTA 2 -#define __NFT_OBJECT_MAX 3 +#define NFT_OBJECT_CT_HELPER 3 +#define __NFT_OBJECT_MAX 4 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index bf548a7a71ec..4144ae845bdd 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -32,6 +32,12 @@ struct nft_ct { }; }; +struct nft_ct_helper_obj { + struct nf_conntrack_helper *helper4; + struct nf_conntrack_helper *helper6; + u8 l4proto; +}; + #ifdef CONFIG_NF_CONNTRACK_ZONES static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template); static unsigned int nft_ct_pcpu_template_refcnt __read_mostly; @@ -730,6 +736,162 @@ static struct nft_expr_type nft_notrack_type __read_mostly = { .owner = THIS_MODULE, }; +static int nft_ct_helper_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_ct_helper_obj *priv = nft_obj_data(obj); + struct nf_conntrack_helper *help4, *help6; + char name[NF_CT_HELPER_NAME_LEN]; + int family = ctx->afi->family; + + if (!tb[NFTA_CT_HELPER_NAME] || !tb[NFTA_CT_HELPER_L4PROTO]) + return -EINVAL; + + priv->l4proto = nla_get_u8(tb[NFTA_CT_HELPER_L4PROTO]); + if (!priv->l4proto) + return -ENOENT; + + nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name)); + + if (tb[NFTA_CT_HELPER_L3PROTO]) + family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO])); + + help4 = NULL; + help6 = NULL; + + switch (family) { + case NFPROTO_IPV4: + if (ctx->afi->family == NFPROTO_IPV6) + return -EINVAL; + + help4 = nf_conntrack_helper_try_module_get(name, family, + priv->l4proto); + break; + case NFPROTO_IPV6: + if (ctx->afi->family == NFPROTO_IPV4) + return -EINVAL; + + help6 = nf_conntrack_helper_try_module_get(name, family, + priv->l4proto); + break; + case NFPROTO_NETDEV: /* fallthrough */ + case NFPROTO_BRIDGE: /* same */ + case NFPROTO_INET: + help4 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV4, + priv->l4proto); + help6 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV6, + priv->l4proto); + break; + default: + return -EAFNOSUPPORT; + } + + /* && is intentional; only error if INET found neither ipv4 or ipv6 */ + if (!help4 && !help6) + return -ENOENT; + + priv->helper4 = help4; + priv->helper6 = help6; + + return 0; +} + +static void nft_ct_helper_obj_destroy(struct nft_object *obj) +{ + struct nft_ct_helper_obj *priv = nft_obj_data(obj); + + if (priv->helper4) + module_put(priv->helper4->me); + if (priv->helper6) + module_put(priv->helper6->me); +} + +static void nft_ct_helper_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_ct_helper_obj *priv = nft_obj_data(obj); + struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb); + struct nf_conntrack_helper *to_assign = NULL; + struct nf_conn_help *help; + + if (!ct || + nf_ct_is_confirmed(ct) || + nf_ct_is_template(ct) || + priv->l4proto != nf_ct_protonum(ct)) + return; + + switch (nf_ct_l3num(ct)) { + case NFPROTO_IPV4: + to_assign = priv->helper4; + break; + case NFPROTO_IPV6: + to_assign = priv->helper6; + break; + default: + WARN_ON_ONCE(1); + return; + } + + if (!to_assign) + return; + + if (test_bit(IPS_HELPER_BIT, &ct->status)) + return; + + help = nf_ct_helper_ext_add(ct, to_assign, GFP_ATOMIC); + if (help) { + rcu_assign_pointer(help->helper, to_assign); + set_bit(IPS_HELPER_BIT, &ct->status); + } +} + +static int nft_ct_helper_obj_dump(struct sk_buff *skb, + struct nft_object *obj, bool reset) +{ + const struct nft_ct_helper_obj *priv = nft_obj_data(obj); + const struct nf_conntrack_helper *helper = priv->helper4; + u16 family; + + if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name)) + return -1; + + if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto)) + return -1; + + if (priv->helper4 && priv->helper6) + family = NFPROTO_INET; + else if (priv->helper6) + family = NFPROTO_IPV6; + else + family = NFPROTO_IPV4; + + if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family))) + return -1; + + return 0; +} + +static const struct nla_policy nft_ct_helper_policy[NFTA_CT_HELPER_MAX + 1] = { + [NFTA_CT_HELPER_NAME] = { .type = NLA_STRING, + .len = NF_CT_HELPER_NAME_LEN - 1 }, + [NFTA_CT_HELPER_L3PROTO] = { .type = NLA_U16 }, + [NFTA_CT_HELPER_L4PROTO] = { .type = NLA_U8 }, +}; + +static struct nft_object_type nft_ct_helper_obj __read_mostly = { + .type = NFT_OBJECT_CT_HELPER, + .size = sizeof(struct nft_ct_helper_obj), + .maxattr = NFTA_CT_HELPER_MAX, + .policy = nft_ct_helper_policy, + .eval = nft_ct_helper_obj_eval, + .init = nft_ct_helper_obj_init, + .destroy = nft_ct_helper_obj_destroy, + .dump = nft_ct_helper_obj_dump, + .owner = THIS_MODULE, +}; + static int __init nft_ct_module_init(void) { int err; @@ -744,7 +906,14 @@ static int __init nft_ct_module_init(void) if (err < 0) goto err1; + err = nft_register_obj(&nft_ct_helper_obj); + if (err < 0) + goto err2; + return 0; + +err2: + nft_unregister_expr(&nft_notrack_type); err1: nft_unregister_expr(&nft_ct_type); return err; @@ -752,6 +921,7 @@ static int __init nft_ct_module_init(void) static void __exit nft_ct_module_exit(void) { + nft_unregister_obj(&nft_ct_helper_obj); nft_unregister_expr(&nft_notrack_type); nft_unregister_expr(&nft_ct_type); } @@ -763,3 +933,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy "); MODULE_ALIAS_NFT_EXPR("ct"); MODULE_ALIAS_NFT_EXPR("notrack"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER); From 055c4b34b94f696d9bd9aad53a11378a0fc409c9 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 10 Mar 2017 18:08:02 +0100 Subject: [PATCH 219/399] netfilter: nft_fib: Support existence check Instead of the actual interface index or name, set destination register to just 1 or 0 depending on whether the lookup succeeded or not if NFTA_FIB_F_PRESENT was set in userspace. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_fib.h | 2 +- include/uapi/linux/netfilter/nf_tables.h | 1 + net/ipv4/netfilter/nft_fib_ipv4.c | 4 ++-- net/ipv6/netfilter/nft_fib_ipv6.c | 2 +- net/netfilter/nft_fib.c | 14 +++++++++----- 5 files changed, 14 insertions(+), 9 deletions(-) diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index 5ceb2205e4e3..381af9469e6a 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -32,6 +32,6 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); -void nft_fib_store_result(void *reg, enum nft_fib_result r, +void nft_fib_store_result(void *reg, const struct nft_fib *priv, const struct nft_pktinfo *pkt, int index); #endif diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 34c8d08b687a..8f3842690d17 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1257,6 +1257,7 @@ enum nft_fib_flags { NFTA_FIB_F_MARK = 1 << 2, /* use skb->mark */ NFTA_FIB_F_IIF = 1 << 3, /* restrict to iif */ NFTA_FIB_F_OIF = 1 << 4, /* restrict to oif */ + NFTA_FIB_F_PRESENT = 1 << 5, /* check existence only */ }; enum nft_ct_helper_attributes { diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 2981291910dd..f4e4462cb5bb 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -90,7 +90,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv->result, pkt, + nft_fib_store_result(dest, priv, pkt, nft_in(pkt)->ifindex); return; } @@ -99,7 +99,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (ipv4_is_zeronet(iph->saddr)) { if (ipv4_is_lbcast(iph->daddr) || ipv4_is_local_multicast(iph->daddr)) { - nft_fib_store_result(dest, priv->result, pkt, + nft_fib_store_result(dest, priv, pkt, get_ifindex(pkt->skb->dev)); return; } diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 765facf03d45..e8d88d82636b 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -159,7 +159,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv->result, pkt, + nft_fib_store_result(dest, priv, pkt, nft_in(pkt)->ifindex); return; } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index fd0b19303b0d..21df8cccea65 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -24,7 +24,8 @@ const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = { EXPORT_SYMBOL(nft_fib_policy); #define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \ - NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF) + NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \ + NFTA_FIB_F_PRESENT) int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) @@ -133,19 +134,22 @@ int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr) } EXPORT_SYMBOL_GPL(nft_fib_dump); -void nft_fib_store_result(void *reg, enum nft_fib_result r, +void nft_fib_store_result(void *reg, const struct nft_fib *priv, const struct nft_pktinfo *pkt, int index) { struct net_device *dev; u32 *dreg = reg; - switch (r) { + switch (priv->result) { case NFT_FIB_RESULT_OIF: - *dreg = index; + *dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index; break; case NFT_FIB_RESULT_OIFNAME: dev = dev_get_by_index_rcu(nft_net(pkt), index); - strncpy(reg, dev ? dev->name : "", IFNAMSIZ); + if (priv->flags & NFTA_FIB_F_PRESENT) + *dreg = !!dev; + else + strncpy(reg, dev ? dev->name : "", IFNAMSIZ); break; default: WARN_ON_ONCE(1); From fc09e4a75a12552b9374a5b0c5f5815aecf8c37a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 9 Mar 2017 12:57:15 +0100 Subject: [PATCH 220/399] netfilter: nf_conntrack: reduce resolve_normal_ct args also mark init_conntrack noinline, in most cases resolve_normal_ct will find an existing conntrack entry. text data bss dec hex filename 16735 5707 176 22618 585a net/netfilter/nf_conntrack_core.o 16687 5707 176 22570 582a net/netfilter/nf_conntrack_core.o Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 57 ++++++++++++++----------------- 1 file changed, 26 insertions(+), 31 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 071b97fcbefb..b0f2e8e65084 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1129,7 +1129,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free); /* Allocate a new conntrack: we return -ENOMEM if classification failed due to stress. Otherwise it really is unclassifiable. */ -static struct nf_conntrack_tuple_hash * +static noinline struct nf_conntrack_tuple_hash * init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_l3proto *l3proto, @@ -1237,21 +1237,20 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, return &ct->tuplehash[IP_CT_DIR_ORIGINAL]; } -/* On success, returns conntrack ptr, sets skb->_nfct | ctinfo */ -static inline struct nf_conn * +/* On success, returns 0, sets skb->_nfct | ctinfo */ +static int resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, struct nf_conntrack_l3proto *l3proto, - struct nf_conntrack_l4proto *l4proto, - int *set_reply, - enum ip_conntrack_info *ctinfo) + struct nf_conntrack_l4proto *l4proto) { const struct nf_conntrack_zone *zone; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; + enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; struct nf_conn *ct; u32 hash; @@ -1260,7 +1259,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, dataoff, l3num, protonum, net, &tuple, l3proto, l4proto)) { pr_debug("Can't get tuple\n"); - return NULL; + return 0; } /* look for tuple match */ @@ -1271,33 +1270,30 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, skb, dataoff, hash); if (!h) - return NULL; + return 0; if (IS_ERR(h)) - return (void *)h; + return PTR_ERR(h); } ct = nf_ct_tuplehash_to_ctrack(h); /* It exists; we have (non-exclusive) reference. */ if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) { - *ctinfo = IP_CT_ESTABLISHED_REPLY; - /* Please set reply bit if this packet OK */ - *set_reply = 1; + ctinfo = IP_CT_ESTABLISHED_REPLY; } else { /* Once we've had two way comms, always ESTABLISHED. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { pr_debug("normal packet for %p\n", ct); - *ctinfo = IP_CT_ESTABLISHED; + ctinfo = IP_CT_ESTABLISHED; } else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) { pr_debug("related packet for %p\n", ct); - *ctinfo = IP_CT_RELATED; + ctinfo = IP_CT_RELATED; } else { pr_debug("new packet for %p\n", ct); - *ctinfo = IP_CT_NEW; + ctinfo = IP_CT_NEW; } - *set_reply = 0; } - nf_ct_set(skb, ct, *ctinfo); - return ct; + nf_ct_set(skb, ct, ctinfo); + return 0; } unsigned int @@ -1311,7 +1307,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, unsigned int *timeouts; unsigned int dataoff; u_int8_t protonum; - int set_reply = 0; int ret; tmpl = nf_ct_get(skb, &ctinfo); @@ -1354,23 +1349,22 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, goto out; } repeat: - ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, - l3proto, l4proto, &set_reply, &ctinfo); - if (!ct) { - /* Not valid part of a connection */ - NF_CT_STAT_INC_ATOMIC(net, invalid); - ret = NF_ACCEPT; - goto out; - } - - if (IS_ERR(ct)) { + ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, + l3proto, l4proto); + if (ret < 0) { /* Too stressed to deal. */ NF_CT_STAT_INC_ATOMIC(net, drop); ret = NF_DROP; goto out; } - NF_CT_ASSERT(skb_nfct(skb)); + ct = nf_ct_get(skb, &ctinfo); + if (!ct) { + /* Not valid part of a connection */ + NF_CT_STAT_INC_ATOMIC(net, invalid); + ret = NF_ACCEPT; + goto out; + } /* Decide what timeout policy we want to apply to this flow. */ timeouts = nf_ct_timeout_lookup(net, ct, l4proto); @@ -1395,7 +1389,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, goto out; } - if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) + if (ctinfo == IP_CT_ESTABLISHED_REPLY && + !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_REPLY, ct); out: if (tmpl) From 2cb4bbd75bdf9d423b9f6c629f81eb66ee312fac Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 11 Mar 2017 14:08:09 +0800 Subject: [PATCH 221/399] netfilter: limit: use per-rule spinlock to improve the scalability The limit token is independent between each rules, so there's no need to use a global spinlock. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_limit.c | 10 +++++----- net/netfilter/xt_limit.c | 11 ++++++----- 2 files changed, 11 insertions(+), 10 deletions(-) diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index c6baf412236d..18dd57a52651 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -17,9 +17,8 @@ #include #include -static DEFINE_SPINLOCK(limit_lock); - struct nft_limit { + spinlock_t lock; u64 last; u64 tokens; u64 tokens_max; @@ -34,7 +33,7 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost) u64 now, tokens; s64 delta; - spin_lock_bh(&limit_lock); + spin_lock_bh(&limit->lock); now = ktime_get_ns(); tokens = limit->tokens + now - limit->last; if (tokens > limit->tokens_max) @@ -44,11 +43,11 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost) delta = tokens - cost; if (delta >= 0) { limit->tokens = delta; - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&limit->lock); return limit->invert; } limit->tokens = tokens; - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&limit->lock); return !limit->invert; } @@ -86,6 +85,7 @@ static int nft_limit_init(struct nft_limit *limit, limit->invert = true; } limit->last = ktime_get_ns(); + spin_lock_init(&limit->lock); return 0; } diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index dab962df1787..d27b5f1ea619 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -18,6 +18,7 @@ #include struct xt_limit_priv { + spinlock_t lock; unsigned long prev; uint32_t credit; }; @@ -32,8 +33,6 @@ MODULE_ALIAS("ip6t_limit"); * see net/sched/sch_tbf.c in the linux source tree */ -static DEFINE_SPINLOCK(limit_lock); - /* Rusty: This is my (non-mathematically-inclined) understanding of this algorithm. The `average rate' in jiffies becomes your initial amount of credit `credit' and the most credit you can ever have @@ -72,7 +71,7 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par) struct xt_limit_priv *priv = r->master; unsigned long now = jiffies; - spin_lock_bh(&limit_lock); + spin_lock_bh(&priv->lock); priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY; if (priv->credit > r->credit_cap) priv->credit = r->credit_cap; @@ -80,11 +79,11 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par) if (priv->credit >= r->cost) { /* We're not limited. */ priv->credit -= r->cost; - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&priv->lock); return true; } - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&priv->lock); return false; } @@ -126,6 +125,8 @@ static int limit_mt_check(const struct xt_mtchk_param *par) r->credit_cap = priv->credit; /* Credits full. */ r->cost = user2credits(r->avg); } + spin_lock_init(&priv->lock); + return 0; } From 03e5fd0e9bcc1f34b7a542786b34b8f771e7c260 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 12 Mar 2017 19:38:47 +0800 Subject: [PATCH 222/399] netfilter: nft_set_rbtree: use per-set rwlock to improve the scalability Karel Rericha reported that in his test case, ICMP packets going through boxes had normally about 5ms latency. But when running nft, actually listing the sets with interval flags, latency would go up to 30-100ms. This was observed when router throughput is from 600Mbps to 2Gbps. This is because we use a single global spinlock to protect the whole rbtree sets, so "dumping sets" will race with the "key lookup" inevitably. But actually they are all _readers_, so it's ok to convert the spinlock to rwlock to avoid competition between them. Also use per-set rwlock since each set is independent. Reported-by: Karel Rericha Tested-by: Karel Rericha Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_rbtree.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 78dfbf9588b3..e97e2fb53f0a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -18,9 +18,8 @@ #include #include -static DEFINE_SPINLOCK(nft_rbtree_lock); - struct nft_rbtree { + rwlock_t lock; struct rb_root root; }; @@ -44,14 +43,14 @@ static bool nft_rbtree_equal(const struct nft_set *set, const void *this, static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { - const struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; const void *this; int d; - spin_lock_bh(&nft_rbtree_lock); + read_lock_bh(&priv->lock); parent = priv->root.rb_node; while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); @@ -75,7 +74,7 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } if (nft_rbtree_interval_end(rbe)) goto out; - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); *ext = &rbe->ext; return true; @@ -85,12 +84,12 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_rbtree_interval_end(interval)) { - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); *ext = &interval->ext; return true; } out: - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); return false; } @@ -140,12 +139,13 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_set_ext **ext) { + struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe = elem->priv; int err; - spin_lock_bh(&nft_rbtree_lock); + write_lock_bh(&priv->lock); err = __nft_rbtree_insert(net, set, rbe, ext); - spin_unlock_bh(&nft_rbtree_lock); + write_unlock_bh(&priv->lock); return err; } @@ -157,9 +157,9 @@ static void nft_rbtree_remove(const struct net *net, struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe = elem->priv; - spin_lock_bh(&nft_rbtree_lock); + write_lock_bh(&priv->lock); rb_erase(&rbe->node, &priv->root); - spin_unlock_bh(&nft_rbtree_lock); + write_unlock_bh(&priv->lock); } static void nft_rbtree_activate(const struct net *net, @@ -224,12 +224,12 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { - const struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct nft_set_elem elem; struct rb_node *node; - spin_lock_bh(&nft_rbtree_lock); + read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); @@ -242,13 +242,13 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, iter->err = iter->fn(ctx, set, iter, &elem); if (iter->err < 0) { - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); return; } cont: iter->count++; } - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); } static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) @@ -262,6 +262,7 @@ static int nft_rbtree_init(const struct nft_set *set, { struct nft_rbtree *priv = nft_set_priv(set); + rwlock_init(&priv->lock); priv->root = RB_ROOT; return 0; } From 26d6851fd24ed5d88580d66b4c8384947d5ca29b Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Mon, 13 Mar 2017 10:07:07 +0000 Subject: [PATCH 223/399] net: stmmac: set default number of rx and tx queues in stmmac_pci This patch configures default number of RX and TX queues when using the pci glue driver. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 5c9e462276b9..cea472a7c335 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -88,6 +88,10 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat) /* Set the maxmtu to a default of JUMBO_LEN */ plat->maxmtu = JUMBO_LEN; + + /* Set default number of RX and TX queues to use */ + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; } static int quark_default_data(struct plat_stmmacenet_data *plat, From 68e5cfaffaca73bda1263c503f9b186a196dd97b Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Mon, 13 Mar 2017 10:36:29 +0000 Subject: [PATCH 224/399] net: stmmac: added default rx queue size in stmmac_dma_interrupt This patch adds the rx queue default size when dma interrupts are treated, since dma op mode can be also set there. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 915636ff2fc1..ec363e19cd79 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1455,6 +1455,9 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) int status; int rxfifosz = priv->plat->rx_fifo_size; + if (rxfifosz == 0) + rxfifosz = priv->dma_cap.rx_fifo_size; + status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats); if (likely((status & handle_rx)) || (status & handle_tx)) { if (likely(napi_schedule_prep(&priv->napi))) { From 17886c4705853fe402d06b2820ae155d38fb345e Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Thu, 9 Mar 2017 17:42:56 +0100 Subject: [PATCH 225/399] gtp: switch from struct socket to struct sock for the GTP sockets After enabling the UDP encapsulation, only the sk member is used. Holding the socket would prevent user space from closing the socket, but holding a reference to the sk member does not have the same effect. This change will make it simpler to later detach the sockets from the netdevice. Signed-off-by: Andreas Schultz Signed-off-by: David S. Miller --- drivers/net/gtp.c | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 89698741682f..e1b5af377fbc 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -66,8 +66,8 @@ struct pdp_ctx { struct gtp_dev { struct list_head list; - struct socket *sock0; - struct socket *sock1u; + struct sock *sk0; + struct sock *sk1u; struct net_device *dev; @@ -261,17 +261,19 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, static void gtp_encap_disable(struct gtp_dev *gtp) { - if (gtp->sock0 && gtp->sock0->sk) { - udp_sk(gtp->sock0->sk)->encap_type = 0; - rcu_assign_sk_user_data(gtp->sock0->sk, NULL); + if (gtp->sk0) { + udp_sk(gtp->sk0)->encap_type = 0; + rcu_assign_sk_user_data(gtp->sk0, NULL); + sock_put(gtp->sk0); } - if (gtp->sock1u && gtp->sock1u->sk) { - udp_sk(gtp->sock1u->sk)->encap_type = 0; - rcu_assign_sk_user_data(gtp->sock1u->sk, NULL); + if (gtp->sk1u) { + udp_sk(gtp->sk1u)->encap_type = 0; + rcu_assign_sk_user_data(gtp->sk1u, NULL); + sock_put(gtp->sk1u); } - gtp->sock0 = NULL; - gtp->sock1u = NULL; + gtp->sk0 = NULL; + gtp->sk1u = NULL; } static void gtp_encap_destroy(struct sock *sk) @@ -484,14 +486,14 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, switch (pctx->gtp_version) { case GTP_V0: - if (gtp->sock0) - sk = gtp->sock0->sk; + if (gtp->sk0) + sk = gtp->sk0; else sk = NULL; break; case GTP_V1: - if (gtp->sock1u) - sk = gtp->sock1u->sk; + if (gtp->sk1u) + sk = gtp->sk1u; else sk = NULL; break; @@ -504,7 +506,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, return -ENOENT; } - rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sock0->sk, + rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sk0, pctx->sgsn_addr_ip4.s_addr); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to SSGN %pI4\n", @@ -839,18 +841,20 @@ static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u); - gtp->sock0 = sock0; - gtp->sock1u = sock1u; + sock_hold(sock0->sk); + gtp->sk0 = sock0->sk; + sock_hold(sock1u->sk); + gtp->sk1u = sock1u->sk; tuncfg.sk_user_data = gtp; tuncfg.encap_rcv = gtp_encap_recv; tuncfg.encap_destroy = gtp_encap_destroy; tuncfg.encap_type = UDP_ENCAP_GTP0; - setup_udp_tunnel_sock(sock_net(gtp->sock0->sk), gtp->sock0, &tuncfg); + setup_udp_tunnel_sock(sock_net(gtp->sk0), sock0, &tuncfg); tuncfg.encap_type = UDP_ENCAP_GTP1U; - setup_udp_tunnel_sock(sock_net(gtp->sock1u->sk), gtp->sock1u, &tuncfg); + setup_udp_tunnel_sock(sock_net(gtp->sk1u), sock1u, &tuncfg); err = 0; err2: From 1e3a3abd8b28cfda9d0d0167e50e0fe11bc372a9 Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Thu, 9 Mar 2017 17:42:57 +0100 Subject: [PATCH 226/399] gtp: make GTP sockets in gtp_newlink optional Having both GTPv0-U and GTPv1-U is not always desirable. Fallback from GTPv1-U to GTPv0-U was depreciated from 3GPP Rel-8 onwards. Post Rel-8 implementation are discuraged from listening on the v0 port (see 3GPP TS 29.281, Sect. 1). A future change will completely decouple the sockets from the network device. Till then, at least one of the sockets needs to be specified (either v0 or v1), the other is optional. Signed-off-by: Andreas Schultz Signed-off-by: David S. Miller --- drivers/net/gtp.c | 144 ++++++++++++++++++++++++---------------------- 1 file changed, 76 insertions(+), 68 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index e1b5af377fbc..9aa2b355f2be 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -259,30 +259,30 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet); } -static void gtp_encap_disable(struct gtp_dev *gtp) -{ - if (gtp->sk0) { - udp_sk(gtp->sk0)->encap_type = 0; - rcu_assign_sk_user_data(gtp->sk0, NULL); - sock_put(gtp->sk0); - } - if (gtp->sk1u) { - udp_sk(gtp->sk1u)->encap_type = 0; - rcu_assign_sk_user_data(gtp->sk1u, NULL); - sock_put(gtp->sk1u); - } - - gtp->sk0 = NULL; - gtp->sk1u = NULL; -} - static void gtp_encap_destroy(struct sock *sk) { struct gtp_dev *gtp; gtp = rcu_dereference_sk_user_data(sk); - if (gtp) - gtp_encap_disable(gtp); + if (gtp) { + udp_sk(sk)->encap_type = 0; + rcu_assign_sk_user_data(sk, NULL); + sock_put(sk); + } +} + +static void gtp_encap_disable_sock(struct sock *sk) +{ + if (!sk) + return; + + gtp_encap_destroy(sk); +} + +static void gtp_encap_disable(struct gtp_dev *gtp) +{ + gtp_encap_disable_sock(gtp->sk0); + gtp_encap_disable_sock(gtp->sk1u); } /* UDP encapsulation receive handler. See net/ipv4/udp.c. @@ -642,27 +642,23 @@ static void gtp_link_setup(struct net_device *dev) static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); static void gtp_hashtable_free(struct gtp_dev *gtp); -static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, - int fd_gtp0, int fd_gtp1); +static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - int hashsize, err, fd0, fd1; struct gtp_dev *gtp; struct gtp_net *gn; + int hashsize, err; - if (!data[IFLA_GTP_FD0] || !data[IFLA_GTP_FD1]) + if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1]) return -EINVAL; gtp = netdev_priv(dev); - fd0 = nla_get_u32(data[IFLA_GTP_FD0]); - fd1 = nla_get_u32(data[IFLA_GTP_FD1]); - - err = gtp_encap_enable(dev, gtp, fd0, fd1); + err = gtp_encap_enable(gtp, data); if (err < 0) - goto out_err; + return err; if (!data[IFLA_GTP_PDP_HASHSIZE]) hashsize = 1024; @@ -690,7 +686,6 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, gtp_hashtable_free(gtp); out_encap: gtp_encap_disable(gtp); -out_err: return err; } @@ -805,63 +800,76 @@ static void gtp_hashtable_free(struct gtp_dev *gtp) kfree(gtp->tid_hash); } -static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp, - int fd_gtp0, int fd_gtp1) +static struct sock *gtp_encap_enable_socket(int fd, int type, + struct gtp_dev *gtp) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; - struct socket *sock0, *sock1u; + struct socket *sock; + struct sock *sk; int err; - netdev_dbg(dev, "enable gtp on %d, %d\n", fd_gtp0, fd_gtp1); + pr_debug("enable gtp on %d, %d\n", fd, type); - sock0 = sockfd_lookup(fd_gtp0, &err); - if (sock0 == NULL) { - netdev_dbg(dev, "socket fd=%d not found (gtp0)\n", fd_gtp0); - return -ENOENT; + sock = sockfd_lookup(fd, &err); + if (!sock) { + pr_debug("gtp socket fd=%d not found\n", fd); + return NULL; } - if (sock0->sk->sk_protocol != IPPROTO_UDP) { - netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp0); - err = -EINVAL; - goto err1; + if (sock->sk->sk_protocol != IPPROTO_UDP) { + pr_debug("socket fd=%d not UDP\n", fd); + sk = ERR_PTR(-EINVAL); + goto out_sock; } - sock1u = sockfd_lookup(fd_gtp1, &err); - if (sock1u == NULL) { - netdev_dbg(dev, "socket fd=%d not found (gtp1u)\n", fd_gtp1); - err = -ENOENT; - goto err1; + if (rcu_dereference_sk_user_data(sock->sk)) { + sk = ERR_PTR(-EBUSY); + goto out_sock; } - if (sock1u->sk->sk_protocol != IPPROTO_UDP) { - netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp1); - err = -EINVAL; - goto err2; - } - - netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u); - - sock_hold(sock0->sk); - gtp->sk0 = sock0->sk; - sock_hold(sock1u->sk); - gtp->sk1u = sock1u->sk; + sk = sock->sk; + sock_hold(sk); tuncfg.sk_user_data = gtp; + tuncfg.encap_type = type; tuncfg.encap_rcv = gtp_encap_recv; tuncfg.encap_destroy = gtp_encap_destroy; - tuncfg.encap_type = UDP_ENCAP_GTP0; - setup_udp_tunnel_sock(sock_net(gtp->sk0), sock0, &tuncfg); + setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg); - tuncfg.encap_type = UDP_ENCAP_GTP1U; - setup_udp_tunnel_sock(sock_net(gtp->sk1u), sock1u, &tuncfg); +out_sock: + sockfd_put(sock); + return sk; +} - err = 0; -err2: - sockfd_put(sock1u); -err1: - sockfd_put(sock0); - return err; +static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) +{ + struct sock *sk1u = NULL; + struct sock *sk0 = NULL; + + if (data[IFLA_GTP_FD0]) { + u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]); + + sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp); + if (IS_ERR(sk0)) + return PTR_ERR(sk0); + } + + if (data[IFLA_GTP_FD1]) { + u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]); + + sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp); + if (IS_ERR(sk1u)) { + if (sk0) + gtp_encap_disable_sock(sk0); + return PTR_ERR(sk1u); + } + } + + gtp->sk0 = sk0; + gtp->sk1u = sk1u; + + return 0; } static struct net_device *gtp_find_dev(struct net *net, int ifindex) From 3fb94617ca1b2f60119ae14643a83a66079fe4c9 Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Thu, 9 Mar 2017 17:42:58 +0100 Subject: [PATCH 227/399] gtp: merge gtp_get_net and gtp_genl_find_dev Both function are always used together with the final goal to get the gtp_dev. This simplifies the code by merging them together. The netdevice lookup is changed to use the regular dev_get_by_index. The gtp netdevice list is now only used to find the PDP contexts for imcomming packets. It can be completely eliminated Once the TEID hash is moved into the GTP socket. Signed-off-by: Andreas Schultz Signed-off-by: David S. Miller --- drivers/net/gtp.c | 144 ++++++++++++++++++++++------------------------ 1 file changed, 68 insertions(+), 76 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 9aa2b355f2be..74018ebcaf3a 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -744,21 +744,6 @@ static struct rtnl_link_ops gtp_link_ops __read_mostly = { .fill_info = gtp_fill_info, }; -static struct net *gtp_genl_get_net(struct net *src_net, struct nlattr *tb[]) -{ - struct net *net; - - /* Examine the link attributes and figure out which network namespace - * we are talking about. - */ - if (tb[GTPA_NET_NS_FD]) - net = get_net_ns_by_fd(nla_get_u32(tb[GTPA_NET_NS_FD])); - else - net = get_net(src_net); - - return net; -} - static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize) { int i; @@ -872,16 +857,30 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) return 0; } -static struct net_device *gtp_find_dev(struct net *net, int ifindex) +static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[]) { - struct gtp_net *gn = net_generic(net, gtp_net_id); - struct gtp_dev *gtp; + struct gtp_dev *gtp = NULL; + struct net_device *dev; + struct net *net; - list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) { - if (ifindex == gtp->dev->ifindex) - return gtp->dev; - } - return NULL; + /* Examine the link attributes and figure out which network namespace + * we are talking about. + */ + if (nla[GTPA_NET_NS_FD]) + net = get_net_ns_by_fd(nla_get_u32(nla[GTPA_NET_NS_FD])); + else + net = get_net(src_net); + + if (IS_ERR(net)) + return NULL; + + /* Check if there's an existing gtpX device to configure */ + dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK])); + if (dev->netdev_ops == >p_netdev_ops) + gtp = netdev_priv(dev); + + put_net(net); + return gtp; } static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) @@ -911,9 +910,9 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info) +static int ipv4_pdp_add(struct gtp_dev *gtp, struct genl_info *info) { - struct gtp_dev *gtp = netdev_priv(dev); + struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; struct pdp_ctx *pctx; bool found = false; @@ -990,8 +989,8 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info) static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) { - struct net_device *dev; - struct net *net; + struct gtp_dev *gtp; + int err; if (!info->attrs[GTPA_VERSION] || !info->attrs[GTPA_LINK] || @@ -1015,77 +1014,79 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - net = gtp_genl_get_net(sock_net(skb->sk), info->attrs); - if (IS_ERR(net)) - return PTR_ERR(net); + rcu_read_lock(); - /* Check if there's an existing gtpX device to configure */ - dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK])); - if (dev == NULL) { - put_net(net); - return -ENODEV; + gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); + if (!gtp) { + err = -ENODEV; + goto out_unlock; } - put_net(net); - return ipv4_pdp_add(dev, info); + err = ipv4_pdp_add(gtp, info); + +out_unlock: + rcu_read_unlock(); + return err; } static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) { - struct net_device *dev; struct pdp_ctx *pctx; struct gtp_dev *gtp; - struct net *net; + int err = 0; if (!info->attrs[GTPA_VERSION] || !info->attrs[GTPA_LINK]) return -EINVAL; - net = gtp_genl_get_net(sock_net(skb->sk), info->attrs); - if (IS_ERR(net)) - return PTR_ERR(net); + rcu_read_lock(); - /* Check if there's an existing gtpX device to configure */ - dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK])); - if (dev == NULL) { - put_net(net); - return -ENODEV; + gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); + if (!gtp) { + err = -ENODEV; + goto out_unlock; } - put_net(net); - - gtp = netdev_priv(dev); switch (nla_get_u32(info->attrs[GTPA_VERSION])) { case GTP_V0: - if (!info->attrs[GTPA_TID]) - return -EINVAL; + if (!info->attrs[GTPA_TID]) { + err = -EINVAL; + goto out_unlock; + } pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID])); break; case GTP_V1: - if (!info->attrs[GTPA_I_TEI]) - return -EINVAL; + if (!info->attrs[GTPA_I_TEI]) { + err = -EINVAL; + goto out_unlock; + } pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI])); break; default: - return -EINVAL; + err = -EINVAL; + goto out_unlock; } - if (pctx == NULL) - return -ENOENT; + if (!pctx) { + err = -ENOENT; + goto out_unlock; + } if (pctx->gtp_version == GTP_V0) - netdev_dbg(dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n", + netdev_dbg(gtp->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n", pctx->u.v0.tid, pctx); else if (pctx->gtp_version == GTP_V1) - netdev_dbg(dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", + netdev_dbg(gtp->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); hlist_del_rcu(&pctx->hlist_tid); hlist_del_rcu(&pctx->hlist_addr); kfree_rcu(pctx, rcu_head); - return 0; +out_unlock: + rcu_read_unlock(); + return err; } static struct genl_family gtp_genl_family; @@ -1129,11 +1130,9 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx = NULL; - struct net_device *dev; struct sk_buff *skb2; struct gtp_dev *gtp; u32 gtp_version; - struct net *net; int err; if (!info->attrs[GTPA_VERSION] || @@ -1149,21 +1148,14 @@ static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - net = gtp_genl_get_net(sock_net(skb->sk), info->attrs); - if (IS_ERR(net)) - return PTR_ERR(net); - - /* Check if there's an existing gtpX device to configure */ - dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK])); - if (dev == NULL) { - put_net(net); - return -ENODEV; - } - put_net(net); - - gtp = netdev_priv(dev); - rcu_read_lock(); + + gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); + if (!gtp) { + err = -ENODEV; + goto err_unlock; + } + if (gtp_version == GTP_V0 && info->attrs[GTPA_TID]) { u64 tid = nla_get_u64(info->attrs[GTPA_TID]); From 5b171f9cfe5e628c3537be159fa36fff1f5cec8f Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Thu, 9 Mar 2017 17:42:59 +0100 Subject: [PATCH 228/399] gtp: consolidate gtp socket rx path Add network device to gtp context in preparation for splitting the TEID from the network device. Use this to rework the socker rx path. Move the common RX part of v0 and v1 into a helper. Also move the final rx part into that helper as well. Signed-off-by: Andreas Schultz Signed-off-by: David S. Miller --- drivers/net/gtp.c | 80 ++++++++++++++++++++++++++--------------------- 1 file changed, 44 insertions(+), 36 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 74018ebcaf3a..0c6707a0d9d3 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -58,6 +58,8 @@ struct pdp_ctx { struct in_addr ms_addr_ip4; struct in_addr sgsn_addr_ip4; + struct net_device *dev; + atomic_t tx_seq; struct rcu_head rcu_head; }; @@ -175,6 +177,40 @@ static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx, return false; } +static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen, + bool xnet) +{ + struct pcpu_sw_netstats *stats; + + if (!gtp_check_src_ms(skb, pctx, hdrlen)) { + netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); + return 1; + } + + /* Get rid of the GTP + UDP headers. */ + if (iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet)) + return -1; + + netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n"); + + /* Now that the UDP and the GTP header have been removed, set up the + * new network header. This is required by the upper layer to + * calculate the transport header. + */ + skb_reset_network_header(skb); + + skb->dev = pctx->dev; + + stats = this_cpu_ptr(pctx->dev->tstats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); + + netif_rx(skb); + return 0; +} + /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, bool xnet) @@ -201,13 +237,7 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, return 1; } - if (!gtp_check_src_ms(skb, pctx, hdrlen)) { - netdev_dbg(gtp->dev, "No PDP ctx for this MS\n"); - return 1; - } - - /* Get rid of the GTP + UDP headers. */ - return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet); + return gtp_rx(pctx, skb, hdrlen, xnet); } static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, @@ -250,13 +280,7 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, return 1; } - if (!gtp_check_src_ms(skb, pctx, hdrlen)) { - netdev_dbg(gtp->dev, "No PDP ctx for this MS\n"); - return 1; - } - - /* Get rid of the GTP + UDP headers. */ - return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet); + return gtp_rx(pctx, skb, hdrlen, xnet); } static void gtp_encap_destroy(struct sock *sk) @@ -290,10 +314,9 @@ static void gtp_encap_disable(struct gtp_dev *gtp) */ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) { - struct pcpu_sw_netstats *stats; struct gtp_dev *gtp; + int ret = 0; bool xnet; - int ret; gtp = rcu_dereference_sk_user_data(sk); if (!gtp) @@ -319,33 +342,17 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) switch (ret) { case 1: netdev_dbg(gtp->dev, "pass up to the process\n"); - return 1; + break; case 0: - netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n"); break; case -1: netdev_dbg(gtp->dev, "GTP packet has been dropped\n"); kfree_skb(skb); - return 0; + ret = 0; + break; } - /* Now that the UDP and the GTP header have been removed, set up the - * new network header. This is required by the upper layer to - * calculate the transport header. - */ - skb_reset_network_header(skb); - - skb->dev = gtp->dev; - - stats = this_cpu_ptr(gtp->dev->tstats); - u64_stats_update_begin(&stats->syncp); - stats->rx_packets++; - stats->rx_bytes += skb->len; - u64_stats_update_end(&stats->syncp); - - netif_rx(skb); - - return 0; + return ret; } static int gtp_dev_init(struct net_device *dev) @@ -951,6 +958,7 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct genl_info *info) if (pctx == NULL) return -ENOMEM; + pctx->dev = gtp->dev; ipv4_pdp_fill(pctx, info); atomic_set(&pctx->tx_seq, 0); From d9e2dd122637034a0697bf268eed9233701b9dca Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Thu, 9 Mar 2017 17:43:00 +0100 Subject: [PATCH 229/399] gtp: unify genl_find_pdp and prepare for per socket lookup This unifies duplicate code into a helper. It also prepares the groundwork to add a lookup version that uses the socket to find attached pdp contexts. Signed-off-by: Andreas Schultz Signed-off-by: David S. Miller --- drivers/net/gtp.c | 121 +++++++++++++++++++--------------------------- 1 file changed, 50 insertions(+), 71 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 0c6707a0d9d3..bf4b352e06c4 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1037,55 +1037,67 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) return err; } +static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net, + struct nlattr *nla[]) +{ + struct gtp_dev *gtp; + + gtp = gtp_find_dev(net, nla); + if (!gtp) + return ERR_PTR(-ENODEV); + + if (nla[GTPA_MS_ADDRESS]) { + __be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]); + + return ipv4_pdp_find(gtp, ip); + } else if (nla[GTPA_VERSION]) { + u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]); + + if (gtp_version == GTP_V0 && nla[GTPA_TID]) + return gtp0_pdp_find(gtp, nla_get_u64(nla[GTPA_TID])); + else if (gtp_version == GTP_V1 && nla[GTPA_I_TEI]) + return gtp1_pdp_find(gtp, nla_get_u32(nla[GTPA_I_TEI])); + } + + return ERR_PTR(-EINVAL); +} + +static struct pdp_ctx *gtp_find_pdp(struct net *net, struct nlattr *nla[]) +{ + struct pdp_ctx *pctx; + + if (nla[GTPA_LINK]) + pctx = gtp_find_pdp_by_link(net, nla); + else + pctx = ERR_PTR(-EINVAL); + + if (!pctx) + pctx = ERR_PTR(-ENOENT); + + return pctx; +} + static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx; - struct gtp_dev *gtp; int err = 0; - if (!info->attrs[GTPA_VERSION] || - !info->attrs[GTPA_LINK]) + if (!info->attrs[GTPA_VERSION]) return -EINVAL; rcu_read_lock(); - gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); - if (!gtp) { - err = -ENODEV; - goto out_unlock; - } - - switch (nla_get_u32(info->attrs[GTPA_VERSION])) { - case GTP_V0: - if (!info->attrs[GTPA_TID]) { - err = -EINVAL; - goto out_unlock; - } - pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID])); - break; - case GTP_V1: - if (!info->attrs[GTPA_I_TEI]) { - err = -EINVAL; - goto out_unlock; - } - pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI])); - break; - - default: - err = -EINVAL; - goto out_unlock; - } - - if (!pctx) { - err = -ENOENT; + pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs); + if (IS_ERR(pctx)) { + err = PTR_ERR(pctx); goto out_unlock; } if (pctx->gtp_version == GTP_V0) - netdev_dbg(gtp->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n", + netdev_dbg(pctx->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n", pctx->u.v0.tid, pctx); else if (pctx->gtp_version == GTP_V1) - netdev_dbg(gtp->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", + netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); hlist_del_rcu(&pctx->hlist_tid); @@ -1139,49 +1151,16 @@ static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx = NULL; struct sk_buff *skb2; - struct gtp_dev *gtp; - u32 gtp_version; int err; - if (!info->attrs[GTPA_VERSION] || - !info->attrs[GTPA_LINK]) + if (!info->attrs[GTPA_VERSION]) return -EINVAL; - gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]); - switch (gtp_version) { - case GTP_V0: - case GTP_V1: - break; - default: - return -EINVAL; - } - rcu_read_lock(); - gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); - if (!gtp) { - err = -ENODEV; - goto err_unlock; - } - - if (gtp_version == GTP_V0 && - info->attrs[GTPA_TID]) { - u64 tid = nla_get_u64(info->attrs[GTPA_TID]); - - pctx = gtp0_pdp_find(gtp, tid); - } else if (gtp_version == GTP_V1 && - info->attrs[GTPA_I_TEI]) { - u32 tid = nla_get_u32(info->attrs[GTPA_I_TEI]); - - pctx = gtp1_pdp_find(gtp, tid); - } else if (info->attrs[GTPA_MS_ADDRESS]) { - __be32 ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); - - pctx = ipv4_pdp_find(gtp, ip); - } - - if (pctx == NULL) { - err = -ENOENT; + pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs); + if (IS_ERR(pctx)) { + err = PTR_ERR(pctx); goto err_unlock; } From 6b5e2e7401de30903ad05d3ef18e3a72d835ce24 Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Thu, 9 Mar 2017 17:43:01 +0100 Subject: [PATCH 230/399] gtp: consolidate pdp context destruction into helper Consolidate duplicate code into helper. Signed-off-by: Andreas Schultz Signed-off-by: David S. Miller --- drivers/net/gtp.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index bf4b352e06c4..d58f46fd766a 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -86,6 +86,8 @@ struct gtp_net { static u32 gtp_h_initval; +static void pdp_context_delete(struct pdp_ctx *pctx); + static inline u32 gtp0_hashfn(u64 tid) { u32 *tid32 = (u32 *) &tid; @@ -780,13 +782,10 @@ static void gtp_hashtable_free(struct gtp_dev *gtp) struct pdp_ctx *pctx; int i; - for (i = 0; i < gtp->hash_size; i++) { - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) { - hlist_del_rcu(&pctx->hlist_tid); - hlist_del_rcu(&pctx->hlist_addr); - kfree_rcu(pctx, rcu_head); - } - } + for (i = 0; i < gtp->hash_size; i++) + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + pdp_context_delete(pctx); + synchronize_rcu(); kfree(gtp->addr_hash); kfree(gtp->tid_hash); @@ -995,6 +994,13 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct genl_info *info) return 0; } +static void pdp_context_delete(struct pdp_ctx *pctx) +{ + hlist_del_rcu(&pctx->hlist_tid); + hlist_del_rcu(&pctx->hlist_addr); + kfree_rcu(pctx, rcu_head); +} + static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) { struct gtp_dev *gtp; @@ -1100,9 +1106,7 @@ static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); - hlist_del_rcu(&pctx->hlist_tid); - hlist_del_rcu(&pctx->hlist_addr); - kfree_rcu(pctx, rcu_head); + pdp_context_delete(pctx); out_unlock: rcu_read_unlock(); From 101cfbc155d082e8567f697f86f89853c790be5e Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Thu, 9 Mar 2017 17:43:02 +0100 Subject: [PATCH 231/399] gtp: add socket to pdp context Having the socket present in context simplifies the sending logic. It also fixes the invalid assumption that we have to use the same sending socket for all client IP's on a specific gtp interface. Signed-off-by: Andreas Schultz Signed-off-by: David S. Miller --- drivers/net/gtp.c | 94 +++++++++++++++++++++++------------------------ 1 file changed, 47 insertions(+), 47 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index d58f46fd766a..3e1854f34420 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -58,6 +58,7 @@ struct pdp_ctx { struct in_addr ms_addr_ip4; struct in_addr sgsn_addr_ip4; + struct sock *sk; struct net_device *dev; atomic_t tx_seq; @@ -179,8 +180,7 @@ static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx, return false; } -static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen, - bool xnet) +static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen) { struct pcpu_sw_netstats *stats; @@ -190,7 +190,8 @@ static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen } /* Get rid of the GTP + UDP headers. */ - if (iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet)) + if (iptunnel_pull_header(skb, hdrlen, skb->protocol, + !net_eq(sock_net(pctx->sk), dev_net(pctx->dev)))) return -1; netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n"); @@ -214,8 +215,7 @@ static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen } /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ -static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, - bool xnet) +static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp0_header); @@ -239,11 +239,10 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, return 1; } - return gtp_rx(pctx, skb, hdrlen, xnet); + return gtp_rx(pctx, skb, hdrlen); } -static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, - bool xnet) +static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp1_header); @@ -282,7 +281,7 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb, return 1; } - return gtp_rx(pctx, skb, hdrlen, xnet); + return gtp_rx(pctx, skb, hdrlen); } static void gtp_encap_destroy(struct sock *sk) @@ -318,7 +317,6 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct gtp_dev *gtp; int ret = 0; - bool xnet; gtp = rcu_dereference_sk_user_data(sk); if (!gtp) @@ -326,16 +324,14 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); - xnet = !net_eq(sock_net(sk), dev_net(gtp->dev)); - switch (udp_sk(sk)->encap_type) { case UDP_ENCAP_GTP0: netdev_dbg(gtp->dev, "received GTP0 packet\n"); - ret = gtp0_udp_encap_recv(gtp, skb, xnet); + ret = gtp0_udp_encap_recv(gtp, skb); break; case UDP_ENCAP_GTP1U: netdev_dbg(gtp->dev, "received GTP1U packet\n"); - ret = gtp1u_udp_encap_recv(gtp, skb, xnet); + ret = gtp1u_udp_encap_recv(gtp, skb); break; default: ret = -1; /* Shouldn't happen. */ @@ -378,8 +374,9 @@ static void gtp_dev_uninit(struct net_device *dev) free_percpu(dev->tstats); } -static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4, - const struct sock *sk, __be32 daddr) +static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, + const struct sock *sk, + __be32 daddr) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = sk->sk_bound_dev_if; @@ -388,7 +385,7 @@ static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4, fl4->flowi4_tos = RT_CONN_FLAGS(sk); fl4->flowi4_proto = sk->sk_protocol; - return ip_route_output_key(net, fl4); + return ip_route_output_key(sock_net(sk), fl4); } static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) @@ -477,7 +474,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, struct rtable *rt; struct flowi4 fl4; struct iphdr *iph; - struct sock *sk; __be16 df; int mtu; @@ -493,30 +489,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, } netdev_dbg(dev, "found PDP context %p\n", pctx); - switch (pctx->gtp_version) { - case GTP_V0: - if (gtp->sk0) - sk = gtp->sk0; - else - sk = NULL; - break; - case GTP_V1: - if (gtp->sk1u) - sk = gtp->sk1u; - else - sk = NULL; - break; - default: - return -ENOENT; - } - - if (!sk) { - netdev_dbg(dev, "no userspace socket is available, skip\n"); - return -ENOENT; - } - - rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sk0, - pctx->sgsn_addr_ip4.s_addr); + rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->sgsn_addr_ip4.s_addr); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to SSGN %pI4\n", &pctx->sgsn_addr_ip4.s_addr); @@ -561,7 +534,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, goto err_rt; } - gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev); + gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev); gtp_push_header(skb, pktinfo); return 0; @@ -916,7 +889,8 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int ipv4_pdp_add(struct gtp_dev *gtp, struct genl_info *info) +static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, + struct genl_info *info) { struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; @@ -957,6 +931,8 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct genl_info *info) if (pctx == NULL) return -ENOMEM; + sock_hold(sk); + pctx->sk = sk; pctx->dev = gtp->dev; ipv4_pdp_fill(pctx, info); atomic_set(&pctx->tx_seq, 0); @@ -994,16 +970,26 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct genl_info *info) return 0; } +static void pdp_context_free(struct rcu_head *head) +{ + struct pdp_ctx *pctx = container_of(head, struct pdp_ctx, rcu_head); + + sock_put(pctx->sk); + kfree(pctx); +} + static void pdp_context_delete(struct pdp_ctx *pctx) { hlist_del_rcu(&pctx->hlist_tid); hlist_del_rcu(&pctx->hlist_addr); - kfree_rcu(pctx, rcu_head); + call_rcu(&pctx->rcu_head, pdp_context_free); } static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) { + unsigned int version; struct gtp_dev *gtp; + struct sock *sk; int err; if (!info->attrs[GTPA_VERSION] || @@ -1012,7 +998,9 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) !info->attrs[GTPA_MS_ADDRESS]) return -EINVAL; - switch (nla_get_u32(info->attrs[GTPA_VERSION])) { + version = nla_get_u32(info->attrs[GTPA_VERSION]); + + switch (version) { case GTP_V0: if (!info->attrs[GTPA_TID] || !info->attrs[GTPA_FLOW]) @@ -1036,7 +1024,19 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } - err = ipv4_pdp_add(gtp, info); + if (version == GTP_V0) + sk = gtp->sk0; + else if (version == GTP_V1) + sk = gtp->sk1u; + else + sk = NULL; + + if (!sk) { + err = -ENODEV; + goto out_unlock; + } + + err = ipv4_pdp_add(gtp, sk, info); out_unlock: rcu_read_unlock(); From a062d19e941071bac9f67b61a4bd5f851fd4ede9 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 9 Mar 2017 23:10:13 +0100 Subject: [PATCH 232/399] net: net_netdev: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ntb_netdev.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 36877ba65516..4daf3d0926a8 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -372,18 +372,19 @@ static void ntb_get_drvinfo(struct net_device *ndev, strlcpy(info->bus_info, pci_name(dev->pdev), sizeof(info->bus_info)); } -static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ntb_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { - cmd->supported = SUPPORTED_Backplane; - cmd->advertising = ADVERTISED_Backplane; - ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN); - cmd->duplex = DUPLEX_FULL; - cmd->port = PORT_OTHER; - cmd->phy_address = 0; - cmd->transceiver = XCVR_DUMMY1; - cmd->autoneg = AUTONEG_ENABLE; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, Backplane); + + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_FULL; + cmd->base.port = PORT_OTHER; + cmd->base.phy_address = 0; + cmd->base.autoneg = AUTONEG_ENABLE; return 0; } @@ -391,7 +392,7 @@ static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) static const struct ethtool_ops ntb_ethtool_ops = { .get_drvinfo = ntb_get_drvinfo, .get_link = ethtool_op_get_link, - .get_settings = ntb_get_settings, + .get_link_ksettings = ntb_get_link_ksettings, }; static const struct ntb_queue_handlers ntb_netdev_handlers = { From 29ccc49d69615818743b2d31b16d698b6eea8aad Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sat, 11 Mar 2017 22:03:50 +0100 Subject: [PATCH 233/399] net: tun: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/tun.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index dc1b1dd9157c..c418f0a9d2d1 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2430,18 +2430,16 @@ static struct miscdevice tun_miscdev = { /* ethtool interface */ -static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int tun_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { - cmd->supported = 0; - cmd->advertising = 0; - ethtool_cmd_speed_set(cmd, SPEED_10); - cmd->duplex = DUPLEX_FULL; - cmd->port = PORT_TP; - cmd->phy_address = 0; - cmd->transceiver = XCVR_INTERNAL; - cmd->autoneg = AUTONEG_DISABLE; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + cmd->base.speed = SPEED_10; + cmd->base.duplex = DUPLEX_FULL; + cmd->base.port = PORT_TP; + cmd->base.phy_address = 0; + cmd->base.autoneg = AUTONEG_DISABLE; return 0; } @@ -2504,7 +2502,6 @@ static int tun_set_coalesce(struct net_device *dev, } static const struct ethtool_ops tun_ethtool_ops = { - .get_settings = tun_get_settings, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, @@ -2512,6 +2509,7 @@ static const struct ethtool_ops tun_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, + .get_link_ksettings = tun_get_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) From 3c9b803b87b5ecb4f15b24886f7f97116cc4e1d8 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 12 Mar 2017 18:02:36 +0100 Subject: [PATCH 234/399] net: usb: asix88179_178a: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/ax88179_178a.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index a3a7db0702d8..4a0ae7ce83f6 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -620,16 +620,18 @@ ax88179_get_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom, return 0; } -static int ax88179_get_settings(struct net_device *net, struct ethtool_cmd *cmd) +static int ax88179_get_link_ksettings(struct net_device *net, + struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); - return mii_ethtool_gset(&dev->mii, cmd); + return mii_ethtool_get_link_ksettings(&dev->mii, cmd); } -static int ax88179_set_settings(struct net_device *net, struct ethtool_cmd *cmd) +static int ax88179_set_link_ksettings(struct net_device *net, + const struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); - return mii_ethtool_sset(&dev->mii, cmd); + return mii_ethtool_set_link_ksettings(&dev->mii, cmd); } static int @@ -826,11 +828,11 @@ static const struct ethtool_ops ax88179_ethtool_ops = { .set_wol = ax88179_set_wol, .get_eeprom_len = ax88179_get_eeprom_len, .get_eeprom = ax88179_get_eeprom, - .get_settings = ax88179_get_settings, - .set_settings = ax88179_set_settings, .get_eee = ax88179_get_eee, .set_eee = ax88179_set_eee, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = ax88179_get_link_ksettings, + .set_link_ksettings = ax88179_set_link_ksettings, }; static void ax88179_set_multicast(struct net_device *net) From de1e98c69bc22870342a099c2fc1257b09b15b7a Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 12 Mar 2017 22:08:26 +0100 Subject: [PATCH 235/399] net: usb: catc: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/catc.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 0acc9b640419..fce92f0e5abd 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -688,29 +688,34 @@ static void catc_get_drvinfo(struct net_device *dev, usb_make_path(catc->usbdev, info->bus_info, sizeof(info->bus_info)); } -static int catc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int catc_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct catc *catc = netdev_priv(dev); if (!catc->is_f5u011) return -EOPNOTSUPP; - cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_TP; - cmd->advertising = ADVERTISED_10baseT_Half | ADVERTISED_TP; - ethtool_cmd_speed_set(cmd, SPEED_10); - cmd->duplex = DUPLEX_HALF; - cmd->port = PORT_TP; - cmd->phy_address = 0; - cmd->transceiver = XCVR_INTERNAL; - cmd->autoneg = AUTONEG_DISABLE; - cmd->maxtxpkt = 1; - cmd->maxrxpkt = 1; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); + + cmd->base.speed = SPEED_10; + cmd->base.duplex = DUPLEX_HALF; + cmd->base.port = PORT_TP; + cmd->base.phy_address = 0; + cmd->base.autoneg = AUTONEG_DISABLE; + return 0; } static const struct ethtool_ops ops = { .get_drvinfo = catc_get_drvinfo, - .get_settings = catc_get_settings, - .get_link = ethtool_op_get_link + .get_link = ethtool_op_get_link, + .get_link_ksettings = catc_get_link_ksettings, }; /* From 06144dcfd3b473a0b21c6c836ceb0a9cc4aab1c3 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 12 Mar 2017 22:41:58 +0100 Subject: [PATCH 236/399] net: usb: r8152: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Acked-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 986243c932cc..227e1fdd9228 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3800,7 +3800,8 @@ static void rtl8152_get_drvinfo(struct net_device *netdev, } static -int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd) +int rtl8152_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct r8152 *tp = netdev_priv(netdev); int ret; @@ -3814,7 +3815,7 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd) mutex_lock(&tp->control); - ret = mii_ethtool_gset(&tp->mii, cmd); + ret = mii_ethtool_get_link_ksettings(&tp->mii, cmd); mutex_unlock(&tp->control); @@ -3824,7 +3825,8 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd) return ret; } -static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int rtl8152_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct r8152 *tp = netdev_priv(dev); int ret; @@ -3835,11 +3837,12 @@ static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) mutex_lock(&tp->control); - ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex); + ret = rtl8152_set_speed(tp, cmd->base.autoneg, cmd->base.speed, + cmd->base.duplex); if (!ret) { - tp->autoneg = cmd->autoneg; - tp->speed = cmd->speed; - tp->duplex = cmd->duplex; + tp->autoneg = cmd->base.autoneg; + tp->speed = cmd->base.speed; + tp->duplex = cmd->base.duplex; } mutex_unlock(&tp->control); @@ -4117,8 +4120,6 @@ static int rtl8152_set_coalesce(struct net_device *netdev, static const struct ethtool_ops ops = { .get_drvinfo = rtl8152_get_drvinfo, - .get_settings = rtl8152_get_settings, - .set_settings = rtl8152_set_settings, .get_link = ethtool_op_get_link, .nway_reset = rtl8152_nway_reset, .get_msglevel = rtl8152_get_msglevel, @@ -4132,6 +4133,8 @@ static const struct ethtool_ops ops = { .set_coalesce = rtl8152_set_coalesce, .get_eee = rtl_ethtool_get_eee, .set_eee = rtl_ethtool_set_eee, + .get_link_ksettings = rtl8152_get_link_ksettings, + .set_link_ksettings = rtl8152_set_link_ksettings, }; static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) From b66239b6824f387361bf18747a7e93760ac3c0fb Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 12 Mar 2017 23:16:25 +0100 Subject: [PATCH 237/399] net: usb: rtl8150: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/rtl8150.c | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-) diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index c81c79110cef..daaa88a66f40 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -791,47 +791,52 @@ static void rtl8150_get_drvinfo(struct net_device *netdev, struct ethtool_drvinf usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); } -static int rtl8150_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +static int rtl8150_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ecmd) { rtl8150_t *dev = netdev_priv(netdev); short lpa, bmcr; + u32 supported; - ecmd->supported = (SUPPORTED_10baseT_Half | + supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII); - ecmd->port = PORT_TP; - ecmd->transceiver = XCVR_INTERNAL; - ecmd->phy_address = dev->phy; + ecmd->base.port = PORT_TP; + ecmd->base.phy_address = dev->phy; get_registers(dev, BMCR, 2, &bmcr); get_registers(dev, ANLP, 2, &lpa); if (bmcr & BMCR_ANENABLE) { u32 speed = ((lpa & (LPA_100HALF | LPA_100FULL)) ? SPEED_100 : SPEED_10); - ethtool_cmd_speed_set(ecmd, speed); - ecmd->autoneg = AUTONEG_ENABLE; + ecmd->base.speed = speed; + ecmd->base.autoneg = AUTONEG_ENABLE; if (speed == SPEED_100) - ecmd->duplex = (lpa & LPA_100FULL) ? + ecmd->base.duplex = (lpa & LPA_100FULL) ? DUPLEX_FULL : DUPLEX_HALF; else - ecmd->duplex = (lpa & LPA_10FULL) ? + ecmd->base.duplex = (lpa & LPA_10FULL) ? DUPLEX_FULL : DUPLEX_HALF; } else { - ecmd->autoneg = AUTONEG_DISABLE; - ethtool_cmd_speed_set(ecmd, ((bmcr & BMCR_SPEED100) ? - SPEED_100 : SPEED_10)); - ecmd->duplex = (bmcr & BMCR_FULLDPLX) ? + ecmd->base.autoneg = AUTONEG_DISABLE; + ecmd->base.speed = ((bmcr & BMCR_SPEED100) ? + SPEED_100 : SPEED_10); + ecmd->base.duplex = (bmcr & BMCR_FULLDPLX) ? DUPLEX_FULL : DUPLEX_HALF; } + + ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported, + supported); + return 0; } static const struct ethtool_ops ops = { .get_drvinfo = rtl8150_get_drvinfo, - .get_settings = rtl8150_get_settings, - .get_link = ethtool_op_get_link + .get_link = ethtool_op_get_link, + .get_link_ksettings = rtl8150_get_link_ksettings, }; static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) From 5b441ac8784c1e7f3c619f14da4c3f52e87348d5 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Fri, 10 Mar 2017 20:43:24 +0000 Subject: [PATCH 238/399] mpls: allow TTL propagation to IP packets to be configured Provide the ability to control on a per-route basis whether the TTL value from an MPLS packet is propagated to an IPv4/IPv6 packet when the last label is popped as per the theoretical model in RFC 3443 through a new route attribute, RTA_TTL_PROPAGATE which can be 0 to mean disable propagation and 1 to mean enable propagation. In order to provide the ability to change the behaviour for packets arriving with IPv4/IPv6 Explicit Null labels and to provide an easy way for a user to change the behaviour for all existing routes without having to reprogram them, a global knob is provided. This is done through the addition of a new per-namespace sysctl, "net.mpls.ip_ttl_propagate", which defaults to enabled. If the per-route attribute is set (either enabled or disabled) then it overrides the global configuration. Signed-off-by: Robert Shearman Acked-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/mpls-sysctl.txt | 11 +++ include/net/netns/mpls.h | 2 + include/uapi/linux/rtnetlink.h | 1 + net/mpls/af_mpls.c | 87 +++++++++++++++++++++--- net/mpls/internal.h | 7 ++ 5 files changed, 100 insertions(+), 8 deletions(-) diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt index 15d8d16934fd..9badd1d6685f 100644 --- a/Documentation/networking/mpls-sysctl.txt +++ b/Documentation/networking/mpls-sysctl.txt @@ -19,6 +19,17 @@ platform_labels - INTEGER Possible values: 0 - 1048575 Default: 0 +ip_ttl_propagate - BOOL + Control whether TTL is propagated from the IPv4/IPv6 header to + the MPLS header on imposing labels and propagated from the + MPLS header to the IPv4/IPv6 header on popping the last label. + + If disabled, the MPLS transport network will appear as a + single hop to transit traffic. + + 0 - disabled / RFC 3443 [Short] Pipe Model + 1 - enabled / RFC 3443 Uniform Model (default) + conf//input - BOOL Control whether packets can be input on this interface. diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index d29203651c01..08652eedabb2 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -9,8 +9,10 @@ struct mpls_route; struct ctl_table_header; struct netns_mpls { + int ip_ttl_propagate; size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; + struct ctl_table_header *ctl; }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 75fcf5eff093..3dd72aee4d32 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -319,6 +319,7 @@ enum rtattr_type_t { RTA_EXPIRES, RTA_PAD, RTA_UID, + RTA_TTL_PROPAGATE, __RTA_MAX }; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 3818686182b2..0e1046f21af8 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -32,6 +32,7 @@ #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) static int zero = 0; +static int one = 1; static int label_limit = (1 << 20) - 1; static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, @@ -220,8 +221,8 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, return &rt->rt_nh[nh_index]; } -static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, - struct mpls_entry_decoded dec) +static bool mpls_egress(struct net *net, struct mpls_route *rt, + struct sk_buff *skb, struct mpls_entry_decoded dec) { enum mpls_payload_type payload_type; bool success = false; @@ -246,22 +247,46 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, switch (payload_type) { case MPT_IPV4: { struct iphdr *hdr4 = ip_hdr(skb); + u8 new_ttl; skb->protocol = htons(ETH_P_IP); + + /* If propagating TTL, take the decremented TTL from + * the incoming MPLS header, otherwise decrement the + * TTL, but only if not 0 to avoid underflow. + */ + if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || + (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && + net->mpls.ip_ttl_propagate)) + new_ttl = dec.ttl; + else + new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0; + csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), - htons(dec.ttl << 8)); - hdr4->ttl = dec.ttl; + htons(new_ttl << 8)); + hdr4->ttl = new_ttl; success = true; break; } case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); - hdr6->hop_limit = dec.ttl; + + /* If propagating TTL, take the decremented TTL from + * the incoming MPLS header, otherwise decrement the + * hop limit, but only if not 0 to avoid underflow. + */ + if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || + (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && + net->mpls.ip_ttl_propagate)) + hdr6->hop_limit = dec.ttl; + else if (hdr6->hop_limit) + hdr6->hop_limit = hdr6->hop_limit - 1; success = true; break; } case MPT_UNSPEC: + /* Should have decided which protocol it is by now */ break; } @@ -361,7 +386,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ - if (!mpls_egress(rt, skb, dec)) + if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) goto err; } else { bool bos; @@ -412,6 +437,7 @@ static struct packet_type mpls_packet_type __read_mostly = { static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, + [RTA_TTL_PROPAGATE] = { .type = NLA_U8 }, }; struct mpls_route_config { @@ -421,6 +447,7 @@ struct mpls_route_config { u8 rc_via_alen; u8 rc_via[MAX_VIA_ALEN]; u32 rc_label; + u8 rc_ttl_propagate; u8 rc_output_labels; u32 rc_output_label[MAX_NEW_LABELS]; u32 rc_nlflags; @@ -856,6 +883,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) rt->rt_protocol = cfg->rc_protocol; rt->rt_payload_type = cfg->rc_payload_type; + rt->rt_ttl_propagate = cfg->rc_ttl_propagate; if (cfg->rc_mp) err = mpls_nh_build_multi(cfg, rt); @@ -1576,6 +1604,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; + cfg->rc_ttl_propagate = MPLS_TTL_PROP_DEFAULT; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; @@ -1622,6 +1651,17 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_mp_len = nla_len(nla); break; } + case RTA_TTL_PROPAGATE: + { + u8 ttl_propagate = nla_get_u8(nla); + + if (ttl_propagate > 1) + goto errout; + cfg->rc_ttl_propagate = ttl_propagate ? + MPLS_TTL_PROP_ENABLED : + MPLS_TTL_PROP_DISABLED; + break; + } default: /* Unsupported attribute */ goto errout; @@ -1682,6 +1722,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, if (nla_put_labels(skb, RTA_DST, 1, &label)) goto nla_put_failure; + + if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) { + bool ttl_propagate = + rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED; + + if (nla_put_u8(skb, RTA_TTL_PROPAGATE, + ttl_propagate)) + goto nla_put_failure; + } if (rt->rt_nhn == 1) { const struct mpls_nh *nh = rt->rt_nh; @@ -1792,7 +1841,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) - + nla_total_size(4); /* RTA_DST */ + + nla_total_size(4) /* RTA_DST */ + + nla_total_size(1); /* RTA_TTL_PROPAGATE */ if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; @@ -1876,6 +1926,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo); rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; + rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt0->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr, @@ -1889,6 +1940,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo); rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; + rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt2->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr, @@ -1970,6 +2022,9 @@ static int mpls_platform_labels(struct ctl_table *table, int write, return ret; } +#define MPLS_NS_SYSCTL_OFFSET(field) \ + (&((struct net *)0)->field) + static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", @@ -1978,21 +2033,37 @@ static const struct ctl_table mpls_table[] = { .mode = 0644, .proc_handler = mpls_platform_labels, }, + { + .procname = "ip_ttl_propagate", + .data = MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate), + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, { } }; static int mpls_net_init(struct net *net) { struct ctl_table *table; + int i; net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; + net->mpls.ip_ttl_propagate = 1; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) return -ENOMEM; - table[0].data = net; + /* Table data contains only offsets relative to the base of + * the mdev at this point, so make them absolute. + */ + for (i = 0; i < ARRAY_SIZE(mpls_table) - 1; i++) + table[i].data = (char *)net + (uintptr_t)table[i].data; + net->mpls.ctl = register_net_sysctl(net, "net/mpls", table); if (net->mpls.ctl == NULL) { kfree(table); diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 76360d8b9579..62928d8fabd1 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -90,6 +90,12 @@ struct mpls_nh { /* next hop label forwarding entry */ u8 nh_via_table; }; +enum mpls_ttl_propagation { + MPLS_TTL_PROP_DEFAULT, + MPLS_TTL_PROP_ENABLED, + MPLS_TTL_PROP_DISABLED, +}; + /* The route, nexthops and vias are stored together in the same memory * block: * @@ -116,6 +122,7 @@ struct mpls_route { /* next hop label forwarding entry */ u8 rt_protocol; u8 rt_payload_type; u8 rt_max_alen; + u8 rt_ttl_propagate; unsigned int rt_nhn; unsigned int rt_nhn_alive; struct mpls_nh rt_nh[0]; From a59166e470868d92f0813977817e99e699398af5 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Fri, 10 Mar 2017 20:43:25 +0000 Subject: [PATCH 239/399] mpls: allow TTL propagation from IP packets to be configured Allow TTL propagation from IP packets to MPLS packets to be configured. Add a new optional LWT attribute, MPLS_IPTUNNEL_TTL, which allows the TTL to be set in the resulting MPLS packet, with the value of 0 having the semantics of enabling propagation of the TTL from the IP header (i.e. non-zero values disable propagation). Also allow the configuration to be overridden globally by reusing the same sysctl to control whether the TTL is propagated from IP packets into the MPLS header. If the per-LWT attribute is set then it overrides the global configuration. If the TTL isn't propagated then a default TTL value is used which can be configured via a new sysctl, "net.mpls.default_ttl". This is kept separate from the configuration of whether IP TTL propagation is enabled as it can be used in the future when non-IP payloads are supported (i.e. where there is no payload TTL that can be propagated). Signed-off-by: Robert Shearman Acked-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/mpls-sysctl.txt | 8 +++ include/net/mpls_iptunnel.h | 2 + include/net/netns/mpls.h | 1 + include/uapi/linux/mpls_iptunnel.h | 2 + net/mpls/af_mpls.c | 11 ++++ net/mpls/mpls_iptunnel.c | 73 +++++++++++++++++++----- 6 files changed, 84 insertions(+), 13 deletions(-) diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt index 9badd1d6685f..2f24a1912a48 100644 --- a/Documentation/networking/mpls-sysctl.txt +++ b/Documentation/networking/mpls-sysctl.txt @@ -30,6 +30,14 @@ ip_ttl_propagate - BOOL 0 - disabled / RFC 3443 [Short] Pipe Model 1 - enabled / RFC 3443 Uniform Model (default) +default_ttl - BOOL + Default TTL value to use for MPLS packets where it cannot be + propagated from an IP header, either because one isn't present + or ip_ttl_propagate has been disabled. + + Possible values: 1 - 255 + Default: 255 + conf//input - BOOL Control whether packets can be input on this interface. diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h index 179253f9dcfd..a18af6a16eb5 100644 --- a/include/net/mpls_iptunnel.h +++ b/include/net/mpls_iptunnel.h @@ -19,6 +19,8 @@ struct mpls_iptunnel_encap { u32 label[MAX_NEW_LABELS]; u8 labels; + u8 ttl_propagate; + u8 default_ttl; }; static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate) diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index 08652eedabb2..6608b3693385 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -10,6 +10,7 @@ struct ctl_table_header; struct netns_mpls { int ip_ttl_propagate; + int default_ttl; size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h index d80a0498f77e..f5e45095b0bb 100644 --- a/include/uapi/linux/mpls_iptunnel.h +++ b/include/uapi/linux/mpls_iptunnel.h @@ -16,11 +16,13 @@ /* MPLS tunnel attributes * [RTA_ENCAP] = { * [MPLS_IPTUNNEL_DST] + * [MPLS_IPTUNNEL_TTL] * } */ enum { MPLS_IPTUNNEL_UNSPEC, MPLS_IPTUNNEL_DST, + MPLS_IPTUNNEL_TTL, __MPLS_IPTUNNEL_MAX, }; #define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0e1046f21af8..0c5d111abe36 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -34,6 +34,7 @@ static int zero = 0; static int one = 1; static int label_limit = (1 << 20) - 1; +static int ttl_max = 255; static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, @@ -2042,6 +2043,15 @@ static const struct ctl_table mpls_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "default_ttl", + .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl), + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &ttl_max, + }, { } }; @@ -2053,6 +2063,7 @@ static int mpls_net_init(struct net *net) net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; + net->mpls.default_ttl = 255; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index e4e4424f9eb1..22f71fce0bfb 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -29,6 +29,7 @@ static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = { [MPLS_IPTUNNEL_DST] = { .type = NLA_U32 }, + [MPLS_IPTUNNEL_TTL] = { .type = NLA_U8 }, }; static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) @@ -49,6 +50,7 @@ static int mpls_xmit(struct sk_buff *skb) struct rtable *rt = NULL; struct rt6_info *rt6 = NULL; struct mpls_dev *out_mdev; + struct net *net; int err = 0; bool bos; int i; @@ -56,17 +58,7 @@ static int mpls_xmit(struct sk_buff *skb) /* Find the output device */ out_dev = dst->dev; - - /* Obtain the ttl */ - if (dst->ops->family == AF_INET) { - ttl = ip_hdr(skb)->ttl; - rt = (struct rtable *)dst; - } else if (dst->ops->family == AF_INET6) { - ttl = ipv6_hdr(skb)->hop_limit; - rt6 = (struct rt6_info *)dst; - } else { - goto drop; - } + net = dev_net(out_dev); skb_orphan(skb); @@ -78,6 +70,38 @@ static int mpls_xmit(struct sk_buff *skb) tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate); + /* Obtain the ttl using the following set of rules. + * + * LWT ttl propagation setting: + * - disabled => use default TTL value from LWT + * - enabled => use TTL value from IPv4/IPv6 header + * - default => + * Global ttl propagation setting: + * - disabled => use default TTL value from global setting + * - enabled => use TTL value from IPv4/IPv6 header + */ + if (dst->ops->family == AF_INET) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ip_hdr(skb)->ttl; + rt = (struct rtable *)dst; + } else if (dst->ops->family == AF_INET6) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ipv6_hdr(skb)->hop_limit; + rt6 = (struct rt6_info *)dst; + } else { + goto drop; + } + /* Verify the destination can hold the packet */ new_header_size = mpls_encap_size(tun_encap_info); mtu = mpls_dev_mtu(out_dev); @@ -160,6 +184,17 @@ static int mpls_build_state(struct nlattr *nla, &tun_encap_info->labels, tun_encap_info->label); if (ret) goto errout; + + tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT; + + if (tb[MPLS_IPTUNNEL_TTL]) { + tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]); + /* TTL 0 implies propagate from IP header */ + tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ? + MPLS_TTL_PROP_DISABLED : + MPLS_TTL_PROP_ENABLED; + } + newts->type = LWTUNNEL_ENCAP_MPLS; newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT; newts->headroom = mpls_encap_size(tun_encap_info); @@ -186,6 +221,10 @@ static int mpls_fill_encap_info(struct sk_buff *skb, tun_encap_info->label)) goto nla_put_failure; + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT && + nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -195,10 +234,16 @@ static int mpls_fill_encap_info(struct sk_buff *skb, static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate) { struct mpls_iptunnel_encap *tun_encap_info; + int nlsize; tun_encap_info = mpls_lwtunnel_encap(lwtstate); - return nla_total_size(tun_encap_info->labels * 4); + nlsize = nla_total_size(tun_encap_info->labels * 4); + + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT) + nlsize += nla_total_size(1); + + return nlsize; } static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) @@ -207,7 +252,9 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b); int l; - if (a_hdr->labels != b_hdr->labels) + if (a_hdr->labels != b_hdr->labels || + a_hdr->ttl_propagate != b_hdr->ttl_propagate || + a_hdr->default_ttl != b_hdr->default_ttl) return 1; for (l = 0; l < MAX_NEW_LABELS; l++) From be086e7c53f1fac51eed14523b28f2214b548dd2 Mon Sep 17 00:00:00 2001 From: "Mintz, Yuval" Date: Sat, 11 Mar 2017 18:39:18 +0200 Subject: [PATCH 240/399] qed*: Utilize Firmware 8.15.3.0 This patch advances the qed* drivers into using the newer firmware - This solves several firmware bugs, mostly related [but not limited to] various init/deinit issues in various offloaded protocols. It also introduces a major 4-Cached SGE change in firmware, which can be seen in the storage drivers' changes. In addition, this firmware is required for supporting the new QL41xxx series of adapters; While this patch doesn't add the actual support, the firmware contains the necessary initialization & firmware logic to operate such adapters [actual support would be added later on]. Changes from Previous versions: ------------------------------- - V2 - fix kbuild-test robot warnings Signed-off-by: Tomer Tayar Signed-off-by: Ram Amrani Signed-off-by: Manish Rangankar Signed-off-by: Chad Dupuis Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/infiniband/hw/qedr/main.c | 5 +- drivers/infiniband/hw/qedr/qedr.h | 3 +- drivers/infiniband/hw/qedr/qedr_cm.c | 3 - drivers/infiniband/hw/qedr/qedr_hsi.h | 56 - drivers/infiniband/hw/qedr/verbs.c | 3 +- drivers/net/ethernet/qlogic/qed/qed.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 5 +- drivers/net/ethernet/qlogic/qed/qed_debug.c | 1564 ++++++++++------- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 764 +++++++- .../ethernet/qlogic/qed/qed_init_fw_funcs.c | 56 +- .../net/ethernet/qlogic/qed/qed_init_ops.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 48 +- .../net/ethernet/qlogic/qed/qed_reg_addr.h | 30 + drivers/net/ethernet/qlogic/qed/qed_roce.c | 222 ++- drivers/net/ethernet/qlogic/qed/qed_roce.h | 11 +- drivers/net/ethernet/qlogic/qed/qed_spq.c | 13 +- drivers/net/ethernet/qlogic/qede/qede.h | 2 +- drivers/scsi/qedf/Makefile | 2 +- drivers/scsi/qedf/drv_fcoe_fw_funcs.c | 190 ++ drivers/scsi/qedf/drv_fcoe_fw_funcs.h | 93 + drivers/scsi/qedf/drv_scsi_fw_funcs.c | 44 + drivers/scsi/qedf/drv_scsi_fw_funcs.h | 85 + drivers/scsi/qedf/qedf.h | 23 +- drivers/scsi/qedf/qedf_els.c | 25 +- drivers/scsi/qedf/qedf_io.c | 660 +++---- drivers/scsi/qedi/Makefile | 2 +- drivers/scsi/qedi/qedi_fw.c | 1022 +++++------ drivers/scsi/qedi/qedi_fw_api.c | 781 ++++++++ drivers/scsi/qedi/qedi_fw_iscsi.h | 117 ++ drivers/scsi/qedi/qedi_fw_scsi.h | 55 + drivers/scsi/qedi/qedi_iscsi.c | 12 +- drivers/scsi/qedi/qedi_iscsi.h | 2 +- drivers/scsi/qedi/qedi_version.h | 4 +- include/linux/qed/common_hsi.h | 30 +- include/linux/qed/eth_common.h | 3 + include/linux/qed/fcoe_common.h | 180 +- include/linux/qed/iscsi_common.h | 243 +-- include/linux/qed/roce_common.h | 17 + include/linux/qed/storage_common.h | 30 +- include/linux/qed/tcp_common.h | 1 + 40 files changed, 4208 insertions(+), 2202 deletions(-) delete mode 100644 drivers/infiniband/hw/qedr/qedr_hsi.h create mode 100644 drivers/scsi/qedf/drv_fcoe_fw_funcs.c create mode 100644 drivers/scsi/qedf/drv_fcoe_fw_funcs.h create mode 100644 drivers/scsi/qedf/drv_scsi_fw_funcs.c create mode 100644 drivers/scsi/qedf/drv_scsi_fw_funcs.h create mode 100644 drivers/scsi/qedi/qedi_fw_api.c create mode 100644 drivers/scsi/qedi/qedi_fw_iscsi.h create mode 100644 drivers/scsi/qedi/qedi_fw_scsi.h diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index b9b47e5cc8b3..ced0461d6e9f 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -587,9 +587,8 @@ void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle) #define EVENT_TYPE_CQ 1 #define EVENT_TYPE_QP 2 struct qedr_dev *dev = (struct qedr_dev *)context; - union event_ring_data *data = fw_handle; - u64 roce_handle64 = ((u64)data->roce_handle.hi << 32) + - data->roce_handle.lo; + struct regpair *async_handle = (struct regpair *)fw_handle; + u64 roce_handle64 = ((u64) async_handle->hi << 32) + async_handle->lo; u8 event_type = EVENT_TYPE_NOT_DEFINED; struct ib_event event; struct ib_cq *ibcq; diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index bb32e4792ec9..5cb9195513bd 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -38,7 +38,8 @@ #include #include #include -#include "qedr_hsi.h" +#include +#include "qedr_hsi_rdma.h" #define QEDR_MODULE_VERSION "8.10.10.0" #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA" diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c index 699632893dd9..a6280ce3e2a5 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_cm.c @@ -43,14 +43,11 @@ #include #include -#include "qedr_hsi.h" #include #include #include "qedr.h" -#include "qedr_hsi.h" #include "verbs.h" #include -#include "qedr_hsi.h" #include "qedr_cm.h" void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info) diff --git a/drivers/infiniband/hw/qedr/qedr_hsi.h b/drivers/infiniband/hw/qedr/qedr_hsi.h deleted file mode 100644 index 66d27521373f..000000000000 --- a/drivers/infiniband/hw/qedr/qedr_hsi.h +++ /dev/null @@ -1,56 +0,0 @@ -/* QLogic qedr NIC Driver - * Copyright (c) 2015-2016 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ -#ifndef __QED_HSI_ROCE__ -#define __QED_HSI_ROCE__ - -#include -#include -#include "qedr_hsi_rdma.h" - -/* Affiliated asynchronous events / errors enumeration */ -enum roce_async_events_type { - ROCE_ASYNC_EVENT_NONE = 0, - ROCE_ASYNC_EVENT_COMM_EST = 1, - ROCE_ASYNC_EVENT_SQ_DRAINED, - ROCE_ASYNC_EVENT_SRQ_LIMIT, - ROCE_ASYNC_EVENT_LAST_WQE_REACHED, - ROCE_ASYNC_EVENT_CQ_ERR, - ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR, - ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR, - ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR, - ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR, - ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR, - ROCE_ASYNC_EVENT_SRQ_EMPTY, - MAX_ROCE_ASYNC_EVENTS_TYPE -}; - -#endif /* __QED_HSI_ROCE__ */ diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 6b3bb32803bd..2091902848e6 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -43,7 +43,8 @@ #include #include -#include "qedr_hsi.h" +#include +#include "qedr_hsi_rdma.h" #include #include "qedr.h" #include "verbs.h" diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 00c17fa6545b..be99092d7209 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -51,7 +51,7 @@ #include "qed_hsi.h" extern const struct qed_common_ops qed_common_ops_pass; -#define DRV_MODULE_VERSION "8.10.10.20" +#define DRV_MODULE_VERSION "8.10.10.21" #define MAX_HWFNS_PER_DEVICE (4) #define NAME_SIZE 16 diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index d42d03df751a..89d210a54335 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -71,8 +71,7 @@ #define TM_ALIGN BIT(TM_SHIFT) #define TM_ELEM_SIZE 4 -/* For RoCE we configure to 64K to cover for RoCE max tasks 256K purpose. */ -#define ILT_DEFAULT_HW_P_SIZE (IS_ENABLED(CONFIG_QED_RDMA) ? 4 : 3) +#define ILT_DEFAULT_HW_P_SIZE 4 #define ILT_PAGE_IN_BYTES(hw_p_size) (1U << ((hw_p_size) + 12)) #define ILT_CFG_REG(cli, reg) PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET @@ -1126,7 +1125,7 @@ int qed_cxt_mngr_alloc(struct qed_hwfn *p_hwfn) clients[ILT_CLI_TSDM].first.reg = ILT_CFG_REG(TSDM, FIRST_ILT); clients[ILT_CLI_TSDM].last.reg = ILT_CFG_REG(TSDM, LAST_ILT); clients[ILT_CLI_TSDM].p_size.reg = ILT_CFG_REG(TSDM, P_SIZE); - /* default ILT page size for all clients is 32K */ + /* default ILT page size for all clients is 64K */ for (i = 0; i < ILT_CLI_MAX; i++) p_mngr->clients[i].p_size.val = ILT_DEFAULT_HW_P_SIZE; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 68f19ca57f96..5e81e8a7a109 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -17,7 +17,6 @@ /* Chip IDs enum */ enum chip_ids { - CHIP_RESERVED, CHIP_BB_B0, CHIP_K2, MAX_CHIP_IDS @@ -40,6 +39,7 @@ enum mem_groups { MEM_GROUP_BTB_RAM, MEM_GROUP_RDIF_CTX, MEM_GROUP_TDIF_CTX, + MEM_GROUP_CFC_MEM, MEM_GROUP_CONN_CFC_MEM, MEM_GROUP_TASK_CFC_MEM, MEM_GROUP_CAU_PI, @@ -72,6 +72,7 @@ static const char * const s_mem_group_names[] = { "BTB_RAM", "RDIF_CTX", "TDIF_CTX", + "CFC_MEM", "CONN_CFC_MEM", "TASK_CFC_MEM", "CAU_PI", @@ -185,13 +186,16 @@ struct dbg_array { u32 size_in_dwords; }; +struct chip_platform_defs { + u8 num_ports; + u8 num_pfs; + u8 num_vfs; +}; + /* Chip constant definitions */ struct chip_defs { const char *name; - struct { - u8 num_ports; - u8 num_pfs; - } per_platform[MAX_PLATFORM_IDS]; + struct chip_platform_defs per_platform[MAX_PLATFORM_IDS]; }; /* Platform constant definitions */ @@ -405,22 +409,23 @@ struct phy_defs { /***************************** Constant Arrays *******************************/ /* Debug arrays */ -static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {NULL} }; +static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} }; /* Chip constant definitions array */ static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = { - { "reserved", { {0, 0}, {0, 0}, {0, 0}, {0, 0} } }, { "bb_b0", - { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB}, {0, 0}, {0, 0}, {0, 0} } }, - { "k2", { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2}, {0, 0}, {0, 0}, {0, 0} } } + { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB, MAX_NUM_VFS_BB}, {0, 0, 0}, + {0, 0, 0}, {0, 0, 0} } }, + { "k2", + { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2, MAX_NUM_VFS_K2}, {0, 0, 0}, + {0, 0, 0}, {0, 0, 0} } } }; /* Storm constant definitions array */ static struct storm_defs s_storm_defs[] = { /* Tstorm */ {'T', BLOCK_TSEM, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, - DBG_BUS_CLIENT_RBCT}, true, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, true, TSEM_REG_FAST_MEMORY, TSEM_REG_DBG_FRAME_MODE, TSEM_REG_SLOW_DBG_ACTIVE, TSEM_REG_SLOW_DBG_MODE, TSEM_REG_DBG_MODE1_CFG, @@ -432,8 +437,7 @@ static struct storm_defs s_storm_defs[] = { 4, TCM_REG_SM_TASK_CTX}, /* Mstorm */ {'M', BLOCK_MSEM, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, - DBG_BUS_CLIENT_RBCM}, false, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, false, MSEM_REG_FAST_MEMORY, MSEM_REG_DBG_FRAME_MODE, MSEM_REG_SLOW_DBG_ACTIVE, MSEM_REG_SLOW_DBG_MODE, MSEM_REG_DBG_MODE1_CFG, @@ -445,8 +449,7 @@ static struct storm_defs s_storm_defs[] = { 7, MCM_REG_SM_TASK_CTX}, /* Ustorm */ {'U', BLOCK_USEM, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, - DBG_BUS_CLIENT_RBCU}, false, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, false, USEM_REG_FAST_MEMORY, USEM_REG_DBG_FRAME_MODE, USEM_REG_SLOW_DBG_ACTIVE, USEM_REG_SLOW_DBG_MODE, USEM_REG_DBG_MODE1_CFG, @@ -458,8 +461,7 @@ static struct storm_defs s_storm_defs[] = { 3, UCM_REG_SM_TASK_CTX}, /* Xstorm */ {'X', BLOCK_XSEM, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, - DBG_BUS_CLIENT_RBCX}, false, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, false, XSEM_REG_FAST_MEMORY, XSEM_REG_DBG_FRAME_MODE, XSEM_REG_SLOW_DBG_ACTIVE, XSEM_REG_SLOW_DBG_MODE, XSEM_REG_DBG_MODE1_CFG, @@ -471,8 +473,7 @@ static struct storm_defs s_storm_defs[] = { 0, 0}, /* Ystorm */ {'Y', BLOCK_YSEM, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, - DBG_BUS_CLIENT_RBCY}, false, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, false, YSEM_REG_FAST_MEMORY, YSEM_REG_DBG_FRAME_MODE, YSEM_REG_SLOW_DBG_ACTIVE, YSEM_REG_SLOW_DBG_MODE, YSEM_REG_DBG_MODE1_CFG, @@ -484,8 +485,7 @@ static struct storm_defs s_storm_defs[] = { 12, YCM_REG_SM_TASK_CTX}, /* Pstorm */ {'P', BLOCK_PSEM, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, - DBG_BUS_CLIENT_RBCS}, true, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, true, PSEM_REG_FAST_MEMORY, PSEM_REG_DBG_FRAME_MODE, PSEM_REG_SLOW_DBG_ACTIVE, PSEM_REG_SLOW_DBG_MODE, PSEM_REG_DBG_MODE1_CFG, @@ -499,8 +499,9 @@ static struct storm_defs s_storm_defs[] = { /* Block definitions array */ static struct block_defs block_grc_defs = { - "grc", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, + "grc", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, GRC_REG_DBG_SELECT, GRC_REG_DBG_DWORD_ENABLE, GRC_REG_DBG_SHIFT, GRC_REG_DBG_FORCE_VALID, GRC_REG_DBG_FORCE_FRAME, @@ -508,29 +509,30 @@ static struct block_defs block_grc_defs = { }; static struct block_defs block_miscs_defs = { - "miscs", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "miscs", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_misc_defs = { - "misc", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "misc", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_dbu_defs = { - "dbu", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "dbu", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_pglue_b_defs = { - "pglue_b", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH}, + "pglue_b", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH}, PGLUE_B_REG_DBG_SELECT, PGLUE_B_REG_DBG_DWORD_ENABLE, PGLUE_B_REG_DBG_SHIFT, PGLUE_B_REG_DBG_FORCE_VALID, PGLUE_B_REG_DBG_FORCE_FRAME, @@ -538,8 +540,9 @@ static struct block_defs block_pglue_b_defs = { }; static struct block_defs block_cnig_defs = { - "cnig", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + "cnig", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, CNIG_REG_DBG_SELECT_K2, CNIG_REG_DBG_DWORD_ENABLE_K2, CNIG_REG_DBG_SHIFT_K2, CNIG_REG_DBG_FORCE_VALID_K2, CNIG_REG_DBG_FORCE_FRAME_K2, @@ -547,15 +550,16 @@ static struct block_defs block_cnig_defs = { }; static struct block_defs block_cpmu_defs = { - "cpmu", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "cpmu", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISCS_PL_HV, 8 }; static struct block_defs block_ncsi_defs = { - "ncsi", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, + "ncsi", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, NCSI_REG_DBG_SELECT, NCSI_REG_DBG_DWORD_ENABLE, NCSI_REG_DBG_SHIFT, NCSI_REG_DBG_FORCE_VALID, NCSI_REG_DBG_FORCE_FRAME, @@ -563,15 +567,16 @@ static struct block_defs block_ncsi_defs = { }; static struct block_defs block_opte_defs = { - "opte", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "opte", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISCS_PL_HV, 4 }; static struct block_defs block_bmb_defs = { - "bmb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB}, + "bmb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB}, BMB_REG_DBG_SELECT, BMB_REG_DBG_DWORD_ENABLE, BMB_REG_DBG_SHIFT, BMB_REG_DBG_FORCE_VALID, BMB_REG_DBG_FORCE_FRAME, @@ -579,8 +584,9 @@ static struct block_defs block_bmb_defs = { }; static struct block_defs block_pcie_defs = { - "pcie", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + "pcie", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE, PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID, PCIE_REG_DBG_COMMON_FORCE_FRAME, @@ -588,15 +594,16 @@ static struct block_defs block_pcie_defs = { }; static struct block_defs block_mcp_defs = { - "mcp", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "mcp", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_mcp2_defs = { - "mcp2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, + "mcp2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, MCP2_REG_DBG_SELECT, MCP2_REG_DBG_DWORD_ENABLE, MCP2_REG_DBG_SHIFT, MCP2_REG_DBG_FORCE_VALID, MCP2_REG_DBG_FORCE_FRAME, @@ -604,8 +611,9 @@ static struct block_defs block_mcp2_defs = { }; static struct block_defs block_pswhst_defs = { - "pswhst", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswhst", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWHST_REG_DBG_SELECT, PSWHST_REG_DBG_DWORD_ENABLE, PSWHST_REG_DBG_SHIFT, PSWHST_REG_DBG_FORCE_VALID, PSWHST_REG_DBG_FORCE_FRAME, @@ -613,8 +621,9 @@ static struct block_defs block_pswhst_defs = { }; static struct block_defs block_pswhst2_defs = { - "pswhst2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswhst2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWHST2_REG_DBG_SELECT, PSWHST2_REG_DBG_DWORD_ENABLE, PSWHST2_REG_DBG_SHIFT, PSWHST2_REG_DBG_FORCE_VALID, PSWHST2_REG_DBG_FORCE_FRAME, @@ -622,8 +631,9 @@ static struct block_defs block_pswhst2_defs = { }; static struct block_defs block_pswrd_defs = { - "pswrd", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrd", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRD_REG_DBG_SELECT, PSWRD_REG_DBG_DWORD_ENABLE, PSWRD_REG_DBG_SHIFT, PSWRD_REG_DBG_FORCE_VALID, PSWRD_REG_DBG_FORCE_FRAME, @@ -631,8 +641,9 @@ static struct block_defs block_pswrd_defs = { }; static struct block_defs block_pswrd2_defs = { - "pswrd2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrd2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRD2_REG_DBG_SELECT, PSWRD2_REG_DBG_DWORD_ENABLE, PSWRD2_REG_DBG_SHIFT, PSWRD2_REG_DBG_FORCE_VALID, PSWRD2_REG_DBG_FORCE_FRAME, @@ -640,8 +651,9 @@ static struct block_defs block_pswrd2_defs = { }; static struct block_defs block_pswwr_defs = { - "pswwr", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswwr", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWWR_REG_DBG_SELECT, PSWWR_REG_DBG_DWORD_ENABLE, PSWWR_REG_DBG_SHIFT, PSWWR_REG_DBG_FORCE_VALID, PSWWR_REG_DBG_FORCE_FRAME, @@ -649,15 +661,16 @@ static struct block_defs block_pswwr_defs = { }; static struct block_defs block_pswwr2_defs = { - "pswwr2", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "pswwr2", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISC_PL_HV, 3 }; static struct block_defs block_pswrq_defs = { - "pswrq", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrq", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRQ_REG_DBG_SELECT, PSWRQ_REG_DBG_DWORD_ENABLE, PSWRQ_REG_DBG_SHIFT, PSWRQ_REG_DBG_FORCE_VALID, PSWRQ_REG_DBG_FORCE_FRAME, @@ -665,8 +678,9 @@ static struct block_defs block_pswrq_defs = { }; static struct block_defs block_pswrq2_defs = { - "pswrq2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "pswrq2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PSWRQ2_REG_DBG_SELECT, PSWRQ2_REG_DBG_DWORD_ENABLE, PSWRQ2_REG_DBG_SHIFT, PSWRQ2_REG_DBG_FORCE_VALID, PSWRQ2_REG_DBG_FORCE_FRAME, @@ -674,8 +688,9 @@ static struct block_defs block_pswrq2_defs = { }; static struct block_defs block_pglcs_defs = { - "pglcs", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + "pglcs", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, PGLCS_REG_DBG_SELECT, PGLCS_REG_DBG_DWORD_ENABLE, PGLCS_REG_DBG_SHIFT, PGLCS_REG_DBG_FORCE_VALID, PGLCS_REG_DBG_FORCE_FRAME, @@ -683,8 +698,9 @@ static struct block_defs block_pglcs_defs = { }; static struct block_defs block_ptu_defs = { - "ptu", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "ptu", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, PTU_REG_DBG_SELECT, PTU_REG_DBG_DWORD_ENABLE, PTU_REG_DBG_SHIFT, PTU_REG_DBG_FORCE_VALID, PTU_REG_DBG_FORCE_FRAME, @@ -692,8 +708,9 @@ static struct block_defs block_ptu_defs = { }; static struct block_defs block_dmae_defs = { - "dmae", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "dmae", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, DMAE_REG_DBG_SELECT, DMAE_REG_DBG_DWORD_ENABLE, DMAE_REG_DBG_SHIFT, DMAE_REG_DBG_FORCE_VALID, DMAE_REG_DBG_FORCE_FRAME, @@ -701,8 +718,9 @@ static struct block_defs block_dmae_defs = { }; static struct block_defs block_tcm_defs = { - "tcm", {true, true, true}, true, DBG_TSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "tcm", + {true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, TCM_REG_DBG_SELECT, TCM_REG_DBG_DWORD_ENABLE, TCM_REG_DBG_SHIFT, TCM_REG_DBG_FORCE_VALID, TCM_REG_DBG_FORCE_FRAME, @@ -710,8 +728,9 @@ static struct block_defs block_tcm_defs = { }; static struct block_defs block_mcm_defs = { - "mcm", {true, true, true}, true, DBG_MSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "mcm", + {true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, MCM_REG_DBG_SELECT, MCM_REG_DBG_DWORD_ENABLE, MCM_REG_DBG_SHIFT, MCM_REG_DBG_FORCE_VALID, MCM_REG_DBG_FORCE_FRAME, @@ -719,8 +738,9 @@ static struct block_defs block_mcm_defs = { }; static struct block_defs block_ucm_defs = { - "ucm", {true, true, true}, true, DBG_USTORM_ID, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "ucm", + {true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, UCM_REG_DBG_SELECT, UCM_REG_DBG_DWORD_ENABLE, UCM_REG_DBG_SHIFT, UCM_REG_DBG_FORCE_VALID, UCM_REG_DBG_FORCE_FRAME, @@ -728,8 +748,9 @@ static struct block_defs block_ucm_defs = { }; static struct block_defs block_xcm_defs = { - "xcm", {true, true, true}, true, DBG_XSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xcm", + {true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XCM_REG_DBG_SELECT, XCM_REG_DBG_DWORD_ENABLE, XCM_REG_DBG_SHIFT, XCM_REG_DBG_FORCE_VALID, XCM_REG_DBG_FORCE_FRAME, @@ -737,8 +758,9 @@ static struct block_defs block_xcm_defs = { }; static struct block_defs block_ycm_defs = { - "ycm", {true, true, true}, true, DBG_YSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "ycm", + {true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, YCM_REG_DBG_SELECT, YCM_REG_DBG_DWORD_ENABLE, YCM_REG_DBG_SHIFT, YCM_REG_DBG_FORCE_VALID, YCM_REG_DBG_FORCE_FRAME, @@ -746,8 +768,9 @@ static struct block_defs block_ycm_defs = { }; static struct block_defs block_pcm_defs = { - "pcm", {true, true, true}, true, DBG_PSTORM_ID, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "pcm", + {true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, PCM_REG_DBG_SELECT, PCM_REG_DBG_DWORD_ENABLE, PCM_REG_DBG_SHIFT, PCM_REG_DBG_FORCE_VALID, PCM_REG_DBG_FORCE_FRAME, @@ -755,8 +778,9 @@ static struct block_defs block_pcm_defs = { }; static struct block_defs block_qm_defs = { - "qm", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ}, + "qm", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ}, QM_REG_DBG_SELECT, QM_REG_DBG_DWORD_ENABLE, QM_REG_DBG_SHIFT, QM_REG_DBG_FORCE_VALID, QM_REG_DBG_FORCE_FRAME, @@ -764,8 +788,9 @@ static struct block_defs block_qm_defs = { }; static struct block_defs block_tm_defs = { - "tm", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "tm", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, TM_REG_DBG_SELECT, TM_REG_DBG_DWORD_ENABLE, TM_REG_DBG_SHIFT, TM_REG_DBG_FORCE_VALID, TM_REG_DBG_FORCE_FRAME, @@ -773,8 +798,9 @@ static struct block_defs block_tm_defs = { }; static struct block_defs block_dorq_defs = { - "dorq", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "dorq", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, DORQ_REG_DBG_SELECT, DORQ_REG_DBG_DWORD_ENABLE, DORQ_REG_DBG_SHIFT, DORQ_REG_DBG_FORCE_VALID, DORQ_REG_DBG_FORCE_FRAME, @@ -782,8 +808,9 @@ static struct block_defs block_dorq_defs = { }; static struct block_defs block_brb_defs = { - "brb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, + "brb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, BRB_REG_DBG_SELECT, BRB_REG_DBG_DWORD_ENABLE, BRB_REG_DBG_SHIFT, BRB_REG_DBG_FORCE_VALID, BRB_REG_DBG_FORCE_FRAME, @@ -791,8 +818,9 @@ static struct block_defs block_brb_defs = { }; static struct block_defs block_src_defs = { - "src", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "src", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, SRC_REG_DBG_SELECT, SRC_REG_DBG_DWORD_ENABLE, SRC_REG_DBG_SHIFT, SRC_REG_DBG_FORCE_VALID, SRC_REG_DBG_FORCE_FRAME, @@ -800,8 +828,9 @@ static struct block_defs block_src_defs = { }; static struct block_defs block_prs_defs = { - "prs", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, + "prs", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, PRS_REG_DBG_SELECT, PRS_REG_DBG_DWORD_ENABLE, PRS_REG_DBG_SHIFT, PRS_REG_DBG_FORCE_VALID, PRS_REG_DBG_FORCE_FRAME, @@ -809,8 +838,9 @@ static struct block_defs block_prs_defs = { }; static struct block_defs block_tsdm_defs = { - "tsdm", {true, true, true}, true, DBG_TSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "tsdm", + {true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, TSDM_REG_DBG_SELECT, TSDM_REG_DBG_DWORD_ENABLE, TSDM_REG_DBG_SHIFT, TSDM_REG_DBG_FORCE_VALID, TSDM_REG_DBG_FORCE_FRAME, @@ -818,8 +848,9 @@ static struct block_defs block_tsdm_defs = { }; static struct block_defs block_msdm_defs = { - "msdm", {true, true, true}, true, DBG_MSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "msdm", + {true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, MSDM_REG_DBG_SELECT, MSDM_REG_DBG_DWORD_ENABLE, MSDM_REG_DBG_SHIFT, MSDM_REG_DBG_FORCE_VALID, MSDM_REG_DBG_FORCE_FRAME, @@ -827,8 +858,9 @@ static struct block_defs block_msdm_defs = { }; static struct block_defs block_usdm_defs = { - "usdm", {true, true, true}, true, DBG_USTORM_ID, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "usdm", + {true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, USDM_REG_DBG_SELECT, USDM_REG_DBG_DWORD_ENABLE, USDM_REG_DBG_SHIFT, USDM_REG_DBG_FORCE_VALID, USDM_REG_DBG_FORCE_FRAME, @@ -836,8 +868,9 @@ static struct block_defs block_usdm_defs = { }; static struct block_defs block_xsdm_defs = { - "xsdm", {true, true, true}, true, DBG_XSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xsdm", + {true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XSDM_REG_DBG_SELECT, XSDM_REG_DBG_DWORD_ENABLE, XSDM_REG_DBG_SHIFT, XSDM_REG_DBG_FORCE_VALID, XSDM_REG_DBG_FORCE_FRAME, @@ -845,8 +878,9 @@ static struct block_defs block_xsdm_defs = { }; static struct block_defs block_ysdm_defs = { - "ysdm", {true, true, true}, true, DBG_YSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "ysdm", + {true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, YSDM_REG_DBG_SELECT, YSDM_REG_DBG_DWORD_ENABLE, YSDM_REG_DBG_SHIFT, YSDM_REG_DBG_FORCE_VALID, YSDM_REG_DBG_FORCE_FRAME, @@ -854,8 +888,9 @@ static struct block_defs block_ysdm_defs = { }; static struct block_defs block_psdm_defs = { - "psdm", {true, true, true}, true, DBG_PSTORM_ID, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "psdm", + {true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, PSDM_REG_DBG_SELECT, PSDM_REG_DBG_DWORD_ENABLE, PSDM_REG_DBG_SHIFT, PSDM_REG_DBG_FORCE_VALID, PSDM_REG_DBG_FORCE_FRAME, @@ -863,8 +898,9 @@ static struct block_defs block_psdm_defs = { }; static struct block_defs block_tsem_defs = { - "tsem", {true, true, true}, true, DBG_TSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "tsem", + {true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, TSEM_REG_DBG_SELECT, TSEM_REG_DBG_DWORD_ENABLE, TSEM_REG_DBG_SHIFT, TSEM_REG_DBG_FORCE_VALID, TSEM_REG_DBG_FORCE_FRAME, @@ -872,8 +908,9 @@ static struct block_defs block_tsem_defs = { }; static struct block_defs block_msem_defs = { - "msem", {true, true, true}, true, DBG_MSTORM_ID, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "msem", + {true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, MSEM_REG_DBG_SELECT, MSEM_REG_DBG_DWORD_ENABLE, MSEM_REG_DBG_SHIFT, MSEM_REG_DBG_FORCE_VALID, MSEM_REG_DBG_FORCE_FRAME, @@ -881,8 +918,9 @@ static struct block_defs block_msem_defs = { }; static struct block_defs block_usem_defs = { - "usem", {true, true, true}, true, DBG_USTORM_ID, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "usem", + {true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, USEM_REG_DBG_SELECT, USEM_REG_DBG_DWORD_ENABLE, USEM_REG_DBG_SHIFT, USEM_REG_DBG_FORCE_VALID, USEM_REG_DBG_FORCE_FRAME, @@ -890,8 +928,9 @@ static struct block_defs block_usem_defs = { }; static struct block_defs block_xsem_defs = { - "xsem", {true, true, true}, true, DBG_XSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xsem", + {true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XSEM_REG_DBG_SELECT, XSEM_REG_DBG_DWORD_ENABLE, XSEM_REG_DBG_SHIFT, XSEM_REG_DBG_FORCE_VALID, XSEM_REG_DBG_FORCE_FRAME, @@ -899,8 +938,9 @@ static struct block_defs block_xsem_defs = { }; static struct block_defs block_ysem_defs = { - "ysem", {true, true, true}, true, DBG_YSTORM_ID, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + "ysem", + {true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, YSEM_REG_DBG_SELECT, YSEM_REG_DBG_DWORD_ENABLE, YSEM_REG_DBG_SHIFT, YSEM_REG_DBG_FORCE_VALID, YSEM_REG_DBG_FORCE_FRAME, @@ -908,8 +948,9 @@ static struct block_defs block_ysem_defs = { }; static struct block_defs block_psem_defs = { - "psem", {true, true, true}, true, DBG_PSTORM_ID, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "psem", + {true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, PSEM_REG_DBG_SELECT, PSEM_REG_DBG_DWORD_ENABLE, PSEM_REG_DBG_SHIFT, PSEM_REG_DBG_FORCE_VALID, PSEM_REG_DBG_FORCE_FRAME, @@ -917,8 +958,9 @@ static struct block_defs block_psem_defs = { }; static struct block_defs block_rss_defs = { - "rss", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + "rss", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, RSS_REG_DBG_SELECT, RSS_REG_DBG_DWORD_ENABLE, RSS_REG_DBG_SHIFT, RSS_REG_DBG_FORCE_VALID, RSS_REG_DBG_FORCE_FRAME, @@ -926,8 +968,9 @@ static struct block_defs block_rss_defs = { }; static struct block_defs block_tmld_defs = { - "tmld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "tmld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, TMLD_REG_DBG_SELECT, TMLD_REG_DBG_DWORD_ENABLE, TMLD_REG_DBG_SHIFT, TMLD_REG_DBG_FORCE_VALID, TMLD_REG_DBG_FORCE_FRAME, @@ -935,8 +978,9 @@ static struct block_defs block_tmld_defs = { }; static struct block_defs block_muld_defs = { - "muld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "muld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, MULD_REG_DBG_SELECT, MULD_REG_DBG_DWORD_ENABLE, MULD_REG_DBG_SHIFT, MULD_REG_DBG_FORCE_VALID, MULD_REG_DBG_FORCE_FRAME, @@ -944,8 +988,9 @@ static struct block_defs block_muld_defs = { }; static struct block_defs block_yuld_defs = { - "yuld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + "yuld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, YULD_REG_DBG_SELECT, YULD_REG_DBG_DWORD_ENABLE, YULD_REG_DBG_SHIFT, YULD_REG_DBG_FORCE_VALID, YULD_REG_DBG_FORCE_FRAME, @@ -953,8 +998,9 @@ static struct block_defs block_yuld_defs = { }; static struct block_defs block_xyld_defs = { - "xyld", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + "xyld", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, XYLD_REG_DBG_SELECT, XYLD_REG_DBG_DWORD_ENABLE, XYLD_REG_DBG_SHIFT, XYLD_REG_DBG_FORCE_VALID, XYLD_REG_DBG_FORCE_FRAME, @@ -962,8 +1008,9 @@ static struct block_defs block_xyld_defs = { }; static struct block_defs block_prm_defs = { - "prm", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "prm", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, PRM_REG_DBG_SELECT, PRM_REG_DBG_DWORD_ENABLE, PRM_REG_DBG_SHIFT, PRM_REG_DBG_FORCE_VALID, PRM_REG_DBG_FORCE_FRAME, @@ -971,8 +1018,9 @@ static struct block_defs block_prm_defs = { }; static struct block_defs block_pbf_pb1_defs = { - "pbf_pb1", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + "pbf_pb1", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, PBF_PB1_REG_DBG_SELECT, PBF_PB1_REG_DBG_DWORD_ENABLE, PBF_PB1_REG_DBG_SHIFT, PBF_PB1_REG_DBG_FORCE_VALID, PBF_PB1_REG_DBG_FORCE_FRAME, @@ -981,8 +1029,9 @@ static struct block_defs block_pbf_pb1_defs = { }; static struct block_defs block_pbf_pb2_defs = { - "pbf_pb2", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + "pbf_pb2", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, PBF_PB2_REG_DBG_SELECT, PBF_PB2_REG_DBG_DWORD_ENABLE, PBF_PB2_REG_DBG_SHIFT, PBF_PB2_REG_DBG_FORCE_VALID, PBF_PB2_REG_DBG_FORCE_FRAME, @@ -991,8 +1040,9 @@ static struct block_defs block_pbf_pb2_defs = { }; static struct block_defs block_rpb_defs = { - "rpb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "rpb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, RPB_REG_DBG_SELECT, RPB_REG_DBG_DWORD_ENABLE, RPB_REG_DBG_SHIFT, RPB_REG_DBG_FORCE_VALID, RPB_REG_DBG_FORCE_FRAME, @@ -1000,8 +1050,9 @@ static struct block_defs block_rpb_defs = { }; static struct block_defs block_btb_defs = { - "btb", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV}, + "btb", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV}, BTB_REG_DBG_SELECT, BTB_REG_DBG_DWORD_ENABLE, BTB_REG_DBG_SHIFT, BTB_REG_DBG_FORCE_VALID, BTB_REG_DBG_FORCE_FRAME, @@ -1009,8 +1060,9 @@ static struct block_defs block_btb_defs = { }; static struct block_defs block_pbf_defs = { - "pbf", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + "pbf", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, PBF_REG_DBG_SELECT, PBF_REG_DBG_DWORD_ENABLE, PBF_REG_DBG_SHIFT, PBF_REG_DBG_FORCE_VALID, PBF_REG_DBG_FORCE_FRAME, @@ -1018,8 +1070,9 @@ static struct block_defs block_pbf_defs = { }; static struct block_defs block_rdif_defs = { - "rdif", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + "rdif", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, RDIF_REG_DBG_SELECT, RDIF_REG_DBG_DWORD_ENABLE, RDIF_REG_DBG_SHIFT, RDIF_REG_DBG_FORCE_VALID, RDIF_REG_DBG_FORCE_FRAME, @@ -1027,8 +1080,9 @@ static struct block_defs block_rdif_defs = { }; static struct block_defs block_tdif_defs = { - "tdif", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + "tdif", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, TDIF_REG_DBG_SELECT, TDIF_REG_DBG_DWORD_ENABLE, TDIF_REG_DBG_SHIFT, TDIF_REG_DBG_FORCE_VALID, TDIF_REG_DBG_FORCE_FRAME, @@ -1036,8 +1090,9 @@ static struct block_defs block_tdif_defs = { }; static struct block_defs block_cdu_defs = { - "cdu", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "cdu", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, CDU_REG_DBG_SELECT, CDU_REG_DBG_DWORD_ENABLE, CDU_REG_DBG_SHIFT, CDU_REG_DBG_FORCE_VALID, CDU_REG_DBG_FORCE_FRAME, @@ -1045,8 +1100,9 @@ static struct block_defs block_cdu_defs = { }; static struct block_defs block_ccfc_defs = { - "ccfc", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "ccfc", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, CCFC_REG_DBG_SELECT, CCFC_REG_DBG_DWORD_ENABLE, CCFC_REG_DBG_SHIFT, CCFC_REG_DBG_FORCE_VALID, CCFC_REG_DBG_FORCE_FRAME, @@ -1054,8 +1110,9 @@ static struct block_defs block_ccfc_defs = { }; static struct block_defs block_tcfc_defs = { - "tcfc", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + "tcfc", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, TCFC_REG_DBG_SELECT, TCFC_REG_DBG_DWORD_ENABLE, TCFC_REG_DBG_SHIFT, TCFC_REG_DBG_FORCE_VALID, TCFC_REG_DBG_FORCE_FRAME, @@ -1063,8 +1120,9 @@ static struct block_defs block_tcfc_defs = { }; static struct block_defs block_igu_defs = { - "igu", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "igu", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, IGU_REG_DBG_SELECT, IGU_REG_DBG_DWORD_ENABLE, IGU_REG_DBG_SHIFT, IGU_REG_DBG_FORCE_VALID, IGU_REG_DBG_FORCE_FRAME, @@ -1072,8 +1130,9 @@ static struct block_defs block_igu_defs = { }; static struct block_defs block_cau_defs = { - "cau", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + "cau", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, CAU_REG_DBG_SELECT, CAU_REG_DBG_DWORD_ENABLE, CAU_REG_DBG_SHIFT, CAU_REG_DBG_FORCE_VALID, CAU_REG_DBG_FORCE_FRAME, @@ -1081,8 +1140,9 @@ static struct block_defs block_cau_defs = { }; static struct block_defs block_umac_defs = { - "umac", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + "umac", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, UMAC_REG_DBG_SELECT, UMAC_REG_DBG_DWORD_ENABLE, UMAC_REG_DBG_SHIFT, UMAC_REG_DBG_FORCE_VALID, UMAC_REG_DBG_FORCE_FRAME, @@ -1090,22 +1150,23 @@ static struct block_defs block_umac_defs = { }; static struct block_defs block_xmac_defs = { - "xmac", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "xmac", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_dbg_defs = { - "dbg", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "dbg", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 3 }; static struct block_defs block_nig_defs = { - "nig", {true, true, true}, false, 0, - {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, + "nig", + {true, true}, false, 0, + {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, NIG_REG_DBG_SELECT, NIG_REG_DBG_DWORD_ENABLE, NIG_REG_DBG_SHIFT, NIG_REG_DBG_FORCE_VALID, NIG_REG_DBG_FORCE_FRAME, @@ -1113,8 +1174,9 @@ static struct block_defs block_nig_defs = { }; static struct block_defs block_wol_defs = { - "wol", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + "wol", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, WOL_REG_DBG_SELECT, WOL_REG_DBG_DWORD_ENABLE, WOL_REG_DBG_SHIFT, WOL_REG_DBG_FORCE_VALID, WOL_REG_DBG_FORCE_FRAME, @@ -1122,8 +1184,9 @@ static struct block_defs block_wol_defs = { }; static struct block_defs block_bmbn_defs = { - "bmbn", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB}, + "bmbn", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB}, BMBN_REG_DBG_SELECT, BMBN_REG_DBG_DWORD_ENABLE, BMBN_REG_DBG_SHIFT, BMBN_REG_DBG_FORCE_VALID, BMBN_REG_DBG_FORCE_FRAME, @@ -1131,15 +1194,16 @@ static struct block_defs block_bmbn_defs = { }; static struct block_defs block_ipc_defs = { - "ipc", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "ipc", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, true, false, DBG_RESET_REG_MISCS_PL_UA, 8 }; static struct block_defs block_nwm_defs = { - "nwm", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + "nwm", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, NWM_REG_DBG_SELECT, NWM_REG_DBG_DWORD_ENABLE, NWM_REG_DBG_SHIFT, NWM_REG_DBG_FORCE_VALID, NWM_REG_DBG_FORCE_FRAME, @@ -1147,22 +1211,29 @@ static struct block_defs block_nwm_defs = { }; static struct block_defs block_nws_defs = { - "nws", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, - 0, 0, 0, 0, 0, + "nws", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + NWS_REG_DBG_SELECT, NWS_REG_DBG_DWORD_ENABLE, + NWS_REG_DBG_SHIFT, NWS_REG_DBG_FORCE_VALID, + NWS_REG_DBG_FORCE_FRAME, true, false, DBG_RESET_REG_MISCS_PL_HV, 12 }; static struct block_defs block_ms_defs = { - "ms", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, - 0, 0, 0, 0, 0, + "ms", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + MS_REG_DBG_SELECT, MS_REG_DBG_DWORD_ENABLE, + MS_REG_DBG_SHIFT, MS_REG_DBG_FORCE_VALID, + MS_REG_DBG_FORCE_FRAME, true, false, DBG_RESET_REG_MISCS_PL_HV, 13 }; static struct block_defs block_phy_pcie_defs = { - "phy_pcie", {false, false, true}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + "phy_pcie", + {false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE, PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID, PCIE_REG_DBG_COMMON_FORCE_FRAME, @@ -1170,22 +1241,57 @@ static struct block_defs block_phy_pcie_defs = { }; static struct block_defs block_led_defs = { - "led", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "led", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, - true, true, DBG_RESET_REG_MISCS_PL_HV, 14 + true, false, DBG_RESET_REG_MISCS_PL_HV, 14 +}; + +static struct block_defs block_avs_wrap_defs = { + "avs_wrap", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_UA, 11 +}; + +static struct block_defs block_rgfs_defs = { + "rgfs", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_tgfs_defs = { + "tgfs", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_ptld_defs = { + "ptld", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_ypld_defs = { + "ypld", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_misc_aeu_defs = { - "misc_aeu", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "misc_aeu", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; static struct block_defs block_bar0_map_defs = { - "bar0_map", {false, false, false}, false, 0, - {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + "bar0_map", {false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, 0, 0, 0, 0, 0, false, false, MAX_DBG_RESET_REGS, 0 }; @@ -1269,6 +1375,11 @@ static struct block_defs *s_block_defs[MAX_BLOCK_ID] = { &block_ms_defs, &block_phy_pcie_defs, &block_led_defs, + &block_avs_wrap_defs, + &block_rgfs_defs, + &block_tgfs_defs, + &block_ptld_defs, + &block_ypld_defs, &block_misc_aeu_defs, &block_bar0_map_defs, }; @@ -1281,65 +1392,67 @@ static struct platform_defs s_platform_defs[] = { }; static struct grc_param_defs s_grc_param_defs[] = { - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_TSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_MSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_USTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_XSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_YSTORM */ - {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_PSTORM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_REGS */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RAM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PBUF */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IOR */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_VFC */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM_CTX */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_ILT */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RSS */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CAU */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_QM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MCP */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_RESERVED */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CFC */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IGU */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BRB */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BTB */ - {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BMB */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_NIG */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MULD */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PRS */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DMAE */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_TM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_SDM */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DIF */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_STATIC */ - {{0, 0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_UNSTALL */ - {{MAX_LCIDS, MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS, + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_TSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_MSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_USTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_XSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_YSTORM */ + {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_PSTORM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_REGS */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RAM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PBUF */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IOR */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_VFC */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM_CTX */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_ILT */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RSS */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CAU */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_QM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MCP */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_RESERVED */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CFC */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IGU */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BRB */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BTB */ + {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BMB */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_NIG */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MULD */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PRS */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DMAE */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_TM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_SDM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DIF */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_STATIC */ + {{0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_UNSTALL */ + {{MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS, MAX_LCIDS}, /* DBG_GRC_PARAM_NUM_LCIDS */ - {{MAX_LTIDS, MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS, + {{MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS, MAX_LTIDS}, /* DBG_GRC_PARAM_NUM_LTIDS */ - {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_EXCLUDE_ALL */ - {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_CRASH */ - {{0, 0, 0}, 0, 1, false, 1, 0}, /* DBG_GRC_PARAM_PARITY_SAFE */ - {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM */ - {{1, 1, 1}, 0, 1, false, 0, 1} /* DBG_GRC_PARAM_DUMP_PHY */ + {{0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_EXCLUDE_ALL */ + {{0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_CRASH */ + {{0, 0}, 0, 1, false, 1, 0}, /* DBG_GRC_PARAM_PARITY_SAFE */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM */ + {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PHY */ + {{0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_NO_MCP */ + {{0, 0}, 0, 1, false, 0, 0} /* DBG_GRC_PARAM_NO_FW_VER */ }; static struct rss_mem_defs s_rss_mem_defs[] = { { "rss_mem_cid", "rss_cid", 0, - {256, 256, 320}, - {32, 32, 32} }, + {256, 320}, + {32, 32} }, { "rss_mem_key_msb", "rss_key", 1024, - {128, 128, 208}, - {256, 256, 256} }, + {128, 208}, + {256, 256} }, { "rss_mem_key_lsb", "rss_key", 2048, - {128, 128, 208}, - {64, 64, 64} }, + {128, 208}, + {64, 64} }, { "rss_mem_info", "rss_info", 3072, - {128, 128, 208}, - {16, 16, 16} }, + {128, 208}, + {16, 16} }, { "rss_mem_ind", "rss_ind", 4096, - {(128 * 128), (128 * 128), (128 * 208)}, - {16, 16, 16} } + {(128 * 128), (128 * 208)}, + {16, 16} } }; static struct vfc_ram_defs s_vfc_ram_defs[] = { @@ -1352,32 +1465,32 @@ static struct vfc_ram_defs s_vfc_ram_defs[] = { static struct big_ram_defs s_big_ram_defs[] = { { "BRB", MEM_GROUP_BRB_MEM, MEM_GROUP_BRB_RAM, DBG_GRC_PARAM_DUMP_BRB, BRB_REG_BIG_RAM_ADDRESS, BRB_REG_BIG_RAM_DATA, - {4800, 4800, 5632} }, + {4800, 5632} }, { "BTB", MEM_GROUP_BTB_MEM, MEM_GROUP_BTB_RAM, DBG_GRC_PARAM_DUMP_BTB, BTB_REG_BIG_RAM_ADDRESS, BTB_REG_BIG_RAM_DATA, - {2880, 2880, 3680} }, + {2880, 3680} }, { "BMB", MEM_GROUP_BMB_MEM, MEM_GROUP_BMB_RAM, DBG_GRC_PARAM_DUMP_BMB, BMB_REG_BIG_RAM_ADDRESS, BMB_REG_BIG_RAM_DATA, - {1152, 1152, 1152} } + {1152, 1152} } }; static struct reset_reg_defs s_reset_regs_defs[] = { { MISCS_REG_RESET_PL_UA, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_UA */ + {true, true} }, /* DBG_RESET_REG_MISCS_PL_UA */ { MISCS_REG_RESET_PL_HV, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_HV */ + {true, true} }, /* DBG_RESET_REG_MISCS_PL_HV */ { MISCS_REG_RESET_PL_HV_2, 0x0, - {false, false, true} }, /* DBG_RESET_REG_MISCS_PL_HV_2 */ + {false, true} }, /* DBG_RESET_REG_MISCS_PL_HV_2 */ { MISC_REG_RESET_PL_UA, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_UA */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_UA */ { MISC_REG_RESET_PL_HV, 0x0, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_HV */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_HV */ { MISC_REG_RESET_PL_PDA_VMAIN_1, 0x4404040, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */ { MISC_REG_RESET_PL_PDA_VMAIN_2, 0x7c00007, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */ { MISC_REG_RESET_PL_PDA_VAUX, 0x2, - {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VAUX */ + {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VAUX */ }; static struct phy_defs s_phy_defs[] = { @@ -1410,6 +1523,26 @@ static u32 qed_read_unaligned_dword(u8 *buf) return dword; } +/* Returns the value of the specified GRC param */ +static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn, + enum dbg_grc_params grc_param) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + return dev_data->grc.param_val[grc_param]; +} + +/* Initializes the GRC parameters */ +static void qed_dbg_grc_init_params(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + if (!dev_data->grc.params_initialized) { + qed_dbg_grc_set_params_default(p_hwfn); + dev_data->grc.params_initialized = 1; + } +} + /* Initializes debug data for the specified device */ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -1431,6 +1564,10 @@ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn, dev_data->platform_id = PLATFORM_ASIC; dev_data->mode_enable[MODE_ASIC] = 1; + + /* Initializes the GRC parameters */ + qed_dbg_grc_init_params(p_hwfn); + dev_data->initialized = true; return DBG_STATUS_OK; } @@ -1561,7 +1698,7 @@ static u32 qed_dump_fw_ver_param(struct qed_hwfn *p_hwfn, int printed_chars; u32 offset = 0; - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) { /* Read FW image/version from PRAM in a non-reset SEMI */ bool found = false; u8 storm_id; @@ -1622,7 +1759,7 @@ static u32 qed_dump_mfw_ver_param(struct qed_hwfn *p_hwfn, { char mfw_ver_str[16] = EMPTY_FW_VERSION_STR; - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) { u32 global_section_offsize, global_section_addr, mfw_ver; u32 public_data_addr, global_section_offsize_addr; int printed_chars; @@ -1683,15 +1820,13 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn, bool dump, u8 num_specific_global_params) { + u8 num_params = NUM_COMMON_GLOBAL_PARAMS + num_specific_global_params; struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; u32 offset = 0; /* Find platform string and dump global params section header */ offset += qed_dump_section_hdr(dump_buf + offset, - dump, - "global_params", - NUM_COMMON_GLOBAL_PARAMS + - num_specific_global_params); + dump, "global_params", num_params); /* Store params */ offset += qed_dump_fw_ver_param(p_hwfn, p_ptt, dump_buf + offset, dump); @@ -1815,37 +1950,6 @@ static bool qed_is_mode_match(struct qed_hwfn *p_hwfn, u16 *modes_buf_offset) } } -/* Returns the value of the specified GRC param */ -static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn, - enum dbg_grc_params grc_param) -{ - struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - - return dev_data->grc.param_val[grc_param]; -} - -/* Clear all GRC params */ -static void qed_dbg_grc_clear_params(struct qed_hwfn *p_hwfn) -{ - struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u32 i; - - for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) - dev_data->grc.param_set_by_user[i] = 0; -} - -/* Assign default GRC param values */ -static void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn) -{ - struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u32 i; - - for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) - if (!dev_data->grc.param_set_by_user[i]) - dev_data->grc.param_val[i] = - s_grc_param_defs[i].default_val[dev_data->chip_id]; -} - /* Returns true if the specified entity (indicated by GRC param) should be * included in the dump, false otherwise. */ @@ -1971,7 +2075,7 @@ static void qed_grc_unreset_blocks(struct qed_hwfn *p_hwfn, } } -/* Returns the attention name offsets of the specified block */ +/* Returns the attention block data of the specified block */ static const struct dbg_attn_block_type_data * qed_get_block_attn_data(enum block_id block_id, enum dbg_attn_type attn_type) { @@ -2040,7 +2144,7 @@ static void qed_grc_clear_all_prty(struct qed_hwfn *p_hwfn, * The following parameters are dumped: * - 'count' = num_dumped_entries * - 'split' = split_type - * - 'id'i = split_id (dumped only if split_id >= 0) + * - 'id' = split_id (dumped only if split_id >= 0) * - 'param_name' = param_val (user param, dumped only if param_name != NULL and * param_val != NULL) */ @@ -2069,21 +2173,81 @@ static u32 qed_grc_dump_regs_hdr(u32 *dump_buf, return offset; } -/* Dumps GRC register/memory. Returns the dumped size in dwords. */ +/* Dumps the GRC registers in the specified address range. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, + bool dump, u32 addr, u32 len) +{ + u32 byte_addr = DWORDS_TO_BYTES(addr), offset = 0, i; + + if (dump) + for (i = 0; i < len; i++, byte_addr += BYTES_IN_DWORD, offset++) + *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr); + else + offset += len; + return offset; +} + +/* Dumps GRC registers sequence header. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_reg_entry_hdr(u32 *dump_buf, bool dump, u32 addr, + u32 len) +{ + if (dump) + *dump_buf = addr | (len << REG_DUMP_LEN_SHIFT); + return 1; +} + +/* Dumps GRC registers sequence. Returns the dumped size in dwords. */ static u32 qed_grc_dump_reg_entry(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *dump_buf, bool dump, u32 addr, u32 len) { - u32 offset = 0, i; + u32 offset = 0; + offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, len); + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, dump, addr, len); + return offset; +} + +/* Dumps GRC registers sequence with skip cycle. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_reg_entry_skip(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, + bool dump, u32 addr, u32 total_len, + u32 read_len, u32 skip_len) +{ + u32 offset = 0, reg_offset = 0; + + offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, total_len); if (dump) { - *(dump_buf + offset++) = addr | (len << REG_DUMP_LEN_SHIFT); - for (i = 0; i < len; i++, addr++, offset++) - *(dump_buf + offset) = qed_rd(p_hwfn, - p_ptt, - DWORDS_TO_BYTES(addr)); + while (reg_offset < total_len) { + u32 curr_len = min_t(u32, + read_len, + total_len - reg_offset); + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, addr, curr_len); + reg_offset += curr_len; + addr += curr_len; + if (reg_offset < total_len) { + curr_len = min_t(u32, + skip_len, + total_len - skip_len); + memset(dump_buf + offset, 0, + DWORDS_TO_BYTES(curr_len)); + offset += curr_len; + reg_offset += curr_len; + addr += curr_len; + } + } } else { - offset += len + 1; + offset += total_len; } return offset; @@ -2124,14 +2288,17 @@ static u32 qed_grc_dump_regs_entries(struct qed_hwfn *p_hwfn, const struct dbg_dump_reg *reg = (const struct dbg_dump_reg *) &input_regs_arr.ptr[input_offset]; + u32 addr, len; + addr = GET_FIELD(reg->data, + DBG_DUMP_REG_ADDRESS); + len = GET_FIELD(reg->data, DBG_DUMP_REG_LENGTH); offset += - qed_grc_dump_reg_entry(p_hwfn, p_ptt, - dump_buf + offset, dump, - GET_FIELD(reg->data, - DBG_DUMP_REG_ADDRESS), - GET_FIELD(reg->data, - DBG_DUMP_REG_LENGTH)); + qed_grc_dump_reg_entry(p_hwfn, p_ptt, + dump_buf + offset, + dump, + addr, + len); (*num_dumped_reg_entries)++; } } else { @@ -2194,8 +2361,14 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, const char *param_name, const char *param_val) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + struct chip_platform_defs *p_platform_defs; u32 offset = 0, input_offset = 0; - u8 port_id, pf_id; + struct chip_defs *p_chip_defs; + u8 port_id, pf_id, vf_id; + u16 fid; + + p_chip_defs = &s_chip_defs[dev_data->chip_id]; + p_platform_defs = &p_chip_defs->per_platform[dev_data->platform_id]; if (dump) DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping registers...\n"); @@ -2214,7 +2387,6 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, switch (split_type_id) { case SPLIT_TYPE_NONE: - case SPLIT_TYPE_VF: offset += qed_grc_dump_split_data(p_hwfn, p_ptt, curr_input_regs_arr, @@ -2227,10 +2399,7 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, param_val); break; case SPLIT_TYPE_PORT: - for (port_id = 0; - port_id < - s_chip_defs[dev_data->chip_id]. - per_platform[dev_data->platform_id].num_ports; + for (port_id = 0; port_id < p_platform_defs->num_ports; port_id++) { if (dump) qed_port_pretend(p_hwfn, p_ptt, @@ -2247,20 +2416,48 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, break; case SPLIT_TYPE_PF: case SPLIT_TYPE_PORT_PF: - for (pf_id = 0; - pf_id < - s_chip_defs[dev_data->chip_id]. - per_platform[dev_data->platform_id].num_pfs; + for (pf_id = 0; pf_id < p_platform_defs->num_pfs; pf_id++) { - if (dump) - qed_fid_pretend(p_hwfn, p_ptt, pf_id); - offset += qed_grc_dump_split_data(p_hwfn, - p_ptt, - curr_input_regs_arr, - dump_buf + offset, - dump, block_enable, - "pf", pf_id, param_name, - param_val); + u8 pfid_shift = + PXP_PRETEND_CONCRETE_FID_PFID_SHIFT; + + if (dump) { + fid = pf_id << pfid_shift; + qed_fid_pretend(p_hwfn, p_ptt, fid); + } + + offset += + qed_grc_dump_split_data(p_hwfn, p_ptt, + curr_input_regs_arr, + dump_buf + offset, + dump, block_enable, + "pf", pf_id, + param_name, + param_val); + } + break; + case SPLIT_TYPE_VF: + for (vf_id = 0; vf_id < p_platform_defs->num_vfs; + vf_id++) { + u8 vfvalid_shift = + PXP_PRETEND_CONCRETE_FID_VFVALID_SHIFT; + u8 vfid_shift = + PXP_PRETEND_CONCRETE_FID_VFID_SHIFT; + + if (dump) { + fid = BIT(vfvalid_shift) | + (vf_id << vfid_shift); + qed_fid_pretend(p_hwfn, p_ptt, fid); + } + + offset += + qed_grc_dump_split_data(p_hwfn, p_ptt, + curr_input_regs_arr, + dump_buf + offset, + dump, block_enable, + "vf", vf_id, + param_name, + param_val); } break; default: @@ -2271,8 +2468,11 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, } /* Pretend to original PF */ - if (dump) - qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id); + if (dump) { + fid = p_hwfn->rel_pf_id << PXP_PRETEND_CONCRETE_FID_PFID_SHIFT; + qed_fid_pretend(p_hwfn, p_ptt, fid); + } + return offset; } @@ -2291,13 +2491,14 @@ static u32 qed_grc_dump_reset_regs(struct qed_hwfn *p_hwfn, /* Write reset registers */ for (i = 0; i < MAX_DBG_RESET_REGS; i++) { if (s_reset_regs_defs[i].exists[dev_data->chip_id]) { + u32 addr = BYTES_TO_DWORDS(s_reset_regs_defs[i].addr); + offset += qed_grc_dump_reg_entry(p_hwfn, p_ptt, dump_buf + offset, dump, - BYTES_TO_DWORDS - (s_reset_regs_defs - [i].addr), 1); + addr, + 1); num_regs++; } } @@ -2339,6 +2540,7 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, &attn_reg_arr[reg_idx]; u16 modes_buf_offset; bool eval_mode; + u32 addr; /* Check mode */ eval_mode = GET_FIELD(reg_data->mode.data, @@ -2349,19 +2551,23 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, if (!eval_mode || qed_is_mode_match(p_hwfn, &modes_buf_offset)) { /* Mode match - read and dump registers */ - offset += qed_grc_dump_reg_entry(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - reg_data->mask_address, - 1); - offset += qed_grc_dump_reg_entry(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - GET_FIELD(reg_data->data, - DBG_ATTN_REG_STS_ADDRESS), - 1); + addr = reg_data->mask_address; + offset += + qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + 1); + addr = GET_FIELD(reg_data->data, + DBG_ATTN_REG_STS_ADDRESS); + offset += + qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + 1); num_reg_entries += 2; } } @@ -2369,18 +2575,21 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, /* Write storm stall status registers */ for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + u32 addr; + if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id] && dump) continue; + addr = + BYTES_TO_DWORDS(s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_STALLED); offset += qed_grc_dump_reg_entry(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - BYTES_TO_DWORDS(s_storm_defs[storm_id]. - sem_fast_mem_addr + - SEM_FAST_REG_STALLED), - 1); + p_ptt, + dump_buf + offset, + dump, + addr, + 1); num_reg_entries++; } @@ -2392,11 +2601,47 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, return offset; } +/* Dumps registers that can't be represented in the debug arrays */ +static u32 qed_grc_dump_special_regs(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + u32 offset = 0, addr; + + offset += qed_grc_dump_regs_hdr(dump_buf, + dump, 2, "eng", -1, NULL, NULL); + + /* Dump R/TDIF_REG_DEBUG_ERROR_INFO_SIZE (every 8'th register should be + * skipped). + */ + addr = BYTES_TO_DWORDS(RDIF_REG_DEBUG_ERROR_INFO); + offset += qed_grc_dump_reg_entry_skip(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + RDIF_REG_DEBUG_ERROR_INFO_SIZE, + 7, + 1); + addr = BYTES_TO_DWORDS(TDIF_REG_DEBUG_ERROR_INFO); + offset += + qed_grc_dump_reg_entry_skip(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + TDIF_REG_DEBUG_ERROR_INFO_SIZE, + 7, + 1); + + return offset; +} + /* Dumps a GRC memory header (section and params). * The following parameters are dumped: * name - name is dumped only if it's not NULL. - * addr - byte_addr is dumped only if name is NULL. - * len - dword_len is always dumped. + * addr - addr is dumped only if name is NULL. + * len - len is always dumped. * width - bit_width is dumped if it's not zero. * packed - packed=1 is dumped if it's not false. * mem_group - mem_group is always dumped. @@ -2408,8 +2653,8 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn, u32 *dump_buf, bool dump, const char *name, - u32 byte_addr, - u32 dword_len, + u32 addr, + u32 len, u32 bit_width, bool packed, const char *mem_group, @@ -2419,7 +2664,7 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn, u32 offset = 0; char buf[64]; - if (!dword_len) + if (!len) DP_NOTICE(p_hwfn, "Unexpected GRC Dump error: dumped memory size must be non-zero\n"); if (bit_width) @@ -2446,20 +2691,21 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping %d registers from %s...\n", - dword_len, buf); + len, buf); } else { /* Dump address */ offset += qed_dump_num_param(dump_buf + offset, - dump, "addr", byte_addr); - if (dump && dword_len > 64) + dump, "addr", + DWORDS_TO_BYTES(addr)); + if (dump && len > 64) DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping %d registers from address 0x%x...\n", - dword_len, byte_addr); + len, (u32)DWORDS_TO_BYTES(addr)); } /* Dump len */ - offset += qed_dump_num_param(dump_buf + offset, dump, "len", dword_len); + offset += qed_dump_num_param(dump_buf + offset, dump, "len", len); /* Dump bit width */ if (bit_width) @@ -2492,8 +2738,8 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn, u32 *dump_buf, bool dump, const char *name, - u32 byte_addr, - u32 dword_len, + u32 addr, + u32 len, u32 bit_width, bool packed, const char *mem_group, @@ -2505,21 +2751,14 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn, dump_buf + offset, dump, name, - byte_addr, - dword_len, + addr, + len, bit_width, packed, mem_group, is_storm, storm_letter); - if (dump) { - u32 i; - - for (i = 0; i < dword_len; - i++, byte_addr += BYTES_IN_DWORD, offset++) - *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr); - } else { - offset += dword_len; - } - + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, dump, addr, len); return offset; } @@ -2575,25 +2814,41 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn, if (qed_grc_is_mem_included(p_hwfn, (enum block_id)cond_hdr->block_id, mem_group_id)) { - u32 mem_byte_addr = - DWORDS_TO_BYTES(GET_FIELD(mem->dword0, - DBG_DUMP_MEM_ADDRESS)); + u32 mem_addr = GET_FIELD(mem->dword0, + DBG_DUMP_MEM_ADDRESS); u32 mem_len = GET_FIELD(mem->dword1, DBG_DUMP_MEM_LENGTH); + enum dbg_grc_params grc_param; char storm_letter = 'a'; bool is_storm = false; /* Update memory length for CCFC/TCFC memories * according to number of LCIDs/LTIDs. */ - if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) + if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) { + if (mem_len % MAX_LCIDS != 0) { + DP_NOTICE(p_hwfn, + "Invalid CCFC connection memory size\n"); + return 0; + } + + grc_param = DBG_GRC_PARAM_NUM_LCIDS; mem_len = qed_grc_get_param(p_hwfn, - DBG_GRC_PARAM_NUM_LCIDS) - * (mem_len / MAX_LCIDS); - else if (mem_group_id == MEM_GROUP_TASK_CFC_MEM) + grc_param) * + (mem_len / MAX_LCIDS); + } else if (mem_group_id == + MEM_GROUP_TASK_CFC_MEM) { + if (mem_len % MAX_LTIDS != 0) { + DP_NOTICE(p_hwfn, + "Invalid TCFC task memory size\n"); + return 0; + } + + grc_param = DBG_GRC_PARAM_NUM_LTIDS; mem_len = qed_grc_get_param(p_hwfn, - DBG_GRC_PARAM_NUM_LTIDS) - * (mem_len / MAX_LTIDS); + grc_param) * + (mem_len / MAX_LTIDS); + } /* If memory is associated with Storm, update * Storm details. @@ -2610,7 +2865,7 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn, /* Dump memory */ offset += qed_grc_dump_mem(p_hwfn, p_ptt, dump_buf + offset, dump, NULL, - mem_byte_addr, mem_len, 0, + mem_addr, mem_len, 0, false, s_mem_group_names[mem_group_id], is_storm, storm_letter); @@ -2799,29 +3054,31 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn, u32 offset = 0; for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { - if (qed_grc_is_storm_included(p_hwfn, - (enum dbg_storms)storm_id)) { - for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) { - u32 addr = - s_storm_defs[storm_id].sem_fast_mem_addr + - SEM_FAST_REG_STORM_REG_FILE + - DWORDS_TO_BYTES(IOR_SET_OFFSET(set_id)); + struct storm_defs *storm = &s_storm_defs[storm_id]; - buf[strlen(buf) - 1] = '0' + set_id; - offset += qed_grc_dump_mem(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - buf, - addr, - IORS_PER_SET, - 32, - false, - "ior", - true, - s_storm_defs - [storm_id].letter); - } + if (!qed_grc_is_storm_included(p_hwfn, + (enum dbg_storms)storm_id)) + continue; + + for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) { + u32 dwords, addr; + + dwords = storm->sem_fast_mem_addr + + SEM_FAST_REG_STORM_REG_FILE; + addr = BYTES_TO_DWORDS(dwords) + IOR_SET_OFFSET(set_id); + buf[strlen(buf) - 1] = '0' + set_id; + offset += qed_grc_dump_mem(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + buf, + addr, + IORS_PER_SET, + 32, + false, + "ior", + true, + storm->letter); } } @@ -2990,34 +3247,39 @@ static u32 qed_grc_dump_rss(struct qed_hwfn *p_hwfn, struct rss_mem_defs *rss_defs = &s_rss_mem_defs[rss_mem_id]; u32 num_entries = rss_defs->num_entries[dev_data->chip_id]; u32 entry_width = rss_defs->entry_width[dev_data->chip_id]; - u32 total_size = (num_entries * entry_width) / 32; + u32 total_dwords = (num_entries * entry_width) / 32; + u32 size = RSS_REG_RSS_RAM_DATA_SIZE; bool packed = (entry_width == 16); - u32 addr = rss_defs->addr; - u32 i, j; + u32 rss_addr = rss_defs->addr; + u32 i, addr; offset += qed_grc_dump_mem_hdr(p_hwfn, dump_buf + offset, dump, rss_defs->mem_name, - addr, - total_size, + 0, + total_dwords, entry_width, packed, rss_defs->type_name, false, 0); if (!dump) { - offset += total_size; + offset += total_dwords; continue; } /* Dump RSS data */ - for (i = 0; i < BYTES_TO_DWORDS(total_size); i++, addr++) { - qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, addr); - for (j = 0; j < BYTES_IN_DWORD; j++, offset++) - *(dump_buf + offset) = - qed_rd(p_hwfn, p_ptt, - RSS_REG_RSS_RAM_DATA + - DWORDS_TO_BYTES(j)); + for (i = 0; i < total_dwords; + i += RSS_REG_RSS_RAM_DATA_SIZE, rss_addr++) { + addr = BYTES_TO_DWORDS(RSS_REG_RSS_RAM_DATA); + qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, rss_addr); + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + + offset, + dump, + addr, + size); } } @@ -3030,19 +3292,19 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn, u32 *dump_buf, bool dump, u8 big_ram_id) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 total_blocks, ram_size, offset = 0, i; char mem_name[12] = "???_BIG_RAM"; char type_name[8] = "???_RAM"; - u32 ram_size, total_blocks; - u32 offset = 0, i, j; + struct big_ram_defs *big_ram; - total_blocks = - s_big_ram_defs[big_ram_id].num_of_blocks[dev_data->chip_id]; + big_ram = &s_big_ram_defs[big_ram_id]; + total_blocks = big_ram->num_of_blocks[dev_data->chip_id]; ram_size = total_blocks * BIG_RAM_BLOCK_SIZE_DWORDS; - strncpy(type_name, s_big_ram_defs[big_ram_id].instance_name, - strlen(s_big_ram_defs[big_ram_id].instance_name)); - strncpy(mem_name, s_big_ram_defs[big_ram_id].instance_name, - strlen(s_big_ram_defs[big_ram_id].instance_name)); + strncpy(type_name, big_ram->instance_name, + strlen(big_ram->instance_name)); + strncpy(mem_name, big_ram->instance_name, + strlen(big_ram->instance_name)); /* Dump memory header */ offset += qed_grc_dump_mem_hdr(p_hwfn, @@ -3059,13 +3321,17 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn, /* Read and dump Big RAM data */ for (i = 0; i < total_blocks / 2; i++) { - qed_wr(p_hwfn, p_ptt, s_big_ram_defs[big_ram_id].addr_reg_addr, - i); - for (j = 0; j < 2 * BIG_RAM_BLOCK_SIZE_DWORDS; j++, offset++) - *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, - s_big_ram_defs[big_ram_id]. - data_reg_addr + - DWORDS_TO_BYTES(j)); + u32 addr, len; + + qed_wr(p_hwfn, p_ptt, big_ram->addr_reg_addr, i); + addr = BYTES_TO_DWORDS(big_ram->data_reg_addr); + len = 2 * BIG_RAM_BLOCK_SIZE_DWORDS; + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + len); } return offset; @@ -3075,11 +3341,11 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) { bool block_enable[MAX_BLOCK_ID] = { 0 }; + u32 offset = 0, addr; bool halted = false; - u32 offset = 0; /* Halt MCP */ - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) { halted = !qed_mcp_halt(p_hwfn, p_ptt); if (!halted) DP_NOTICE(p_hwfn, "MCP halt failed!\n"); @@ -3091,7 +3357,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, dump_buf + offset, dump, NULL, - MCP_REG_SCRATCH, + BYTES_TO_DWORDS(MCP_REG_SCRATCH), MCP_REG_SCRATCH_SIZE, 0, false, "MCP", false, 0); @@ -3101,7 +3367,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, dump_buf + offset, dump, NULL, - MCP_REG_CPU_REG_FILE, + BYTES_TO_DWORDS(MCP_REG_CPU_REG_FILE), MCP_REG_CPU_REG_FILE_SIZE, 0, false, "MCP", false, 0); @@ -3115,12 +3381,13 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, /* Dump required non-MCP registers */ offset += qed_grc_dump_regs_hdr(dump_buf + offset, dump, 1, "eng", -1, "block", "MCP"); + addr = BYTES_TO_DWORDS(MISC_REG_SHARED_MEM_ADDR); offset += qed_grc_dump_reg_entry(p_hwfn, p_ptt, dump_buf + offset, dump, - BYTES_TO_DWORDS - (MISC_REG_SHARED_MEM_ADDR), 1); + addr, + 1); /* Release MCP */ if (halted && qed_mcp_resume(p_hwfn, p_ptt)) @@ -3212,7 +3479,7 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn, { u32 block_dwords = NUM_DBG_BUS_LINES * STATIC_DEBUG_LINE_DWORDS; struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u32 offset = 0, block_id, line_id, addr, i; + u32 offset = 0, block_id, line_id; struct block_defs *p_block_defs; if (dump) { @@ -3255,6 +3522,8 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn, if (dump && !dev_data->block_in_reset[block_id]) { u8 dbg_client_id = p_block_defs->dbg_client_id[dev_data->chip_id]; + u32 addr = BYTES_TO_DWORDS(DBG_REG_CALENDAR_OUT_DATA); + u32 len = STATIC_DEBUG_LINE_DWORDS; /* Enable block's client */ qed_bus_enable_clients(p_hwfn, p_ptt, @@ -3270,11 +3539,13 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn, 0xf, 0, 0, 0); /* Read debug line info */ - for (i = 0, addr = DBG_REG_CALENDAR_OUT_DATA; - i < STATIC_DEBUG_LINE_DWORDS; - i++, offset++, addr += BYTES_IN_DWORD) - dump_buf[offset] = qed_rd(p_hwfn, p_ptt, - addr); + offset += + qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + len); } /* Disable block's client and debug output */ @@ -3311,14 +3582,8 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn, u8 i, port_mode = 0; u32 offset = 0; - /* Check if emulation platform */ *num_dumped_dwords = 0; - /* Fill GRC parameters that were not set by the user with their default - * value. - */ - qed_dbg_grc_set_params_default(p_hwfn); - /* Find port mode */ if (dump) { switch (qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE)) { @@ -3370,15 +3635,14 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn, } /* Disable all parities using MFW command */ - if (dump) { + if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) { parities_masked = !qed_mcp_mask_parities(p_hwfn, p_ptt, 1); if (!parities_masked) { + DP_NOTICE(p_hwfn, + "Failed to mask parities using MFW\n"); if (qed_grc_get_param (p_hwfn, DBG_GRC_PARAM_PARITY_SAFE)) return DBG_STATUS_MCP_COULD_NOT_MASK_PRTY; - else - DP_NOTICE(p_hwfn, - "Failed to mask parities using MFW\n"); } } @@ -3409,6 +3673,11 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn, offset, dump, block_enable, NULL, NULL); + + /* Dump special registers */ + offset += qed_grc_dump_special_regs(p_hwfn, + p_ptt, + dump_buf + offset, dump); } /* Dump memories */ @@ -3583,9 +3852,9 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn, } if (mode_match) { - u32 grc_addr = - DWORDS_TO_BYTES(GET_FIELD(reg->data, - DBG_IDLE_CHK_INFO_REG_ADDRESS)); + u32 addr = + GET_FIELD(reg->data, + DBG_IDLE_CHK_INFO_REG_ADDRESS); /* Write register header */ struct dbg_idle_chk_result_reg_hdr *reg_hdr = @@ -3597,16 +3866,19 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn, memset(reg_hdr, 0, sizeof(*reg_hdr)); reg_hdr->size = reg->size; SET_FIELD(reg_hdr->data, - DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID, - rule->num_cond_regs + reg_id); + DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID, + rule->num_cond_regs + reg_id); /* Write register values */ - for (i = 0; i < reg->size; - i++, offset++, grc_addr += 4) - dump_buf[offset] = - qed_rd(p_hwfn, p_ptt, grc_addr); - } + offset += + qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + addr, + reg->size); } + } } return offset; @@ -3621,7 +3893,7 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; u32 cond_reg_values[IDLE_CHK_MAX_ENTRIES_SIZE]; - u32 i, j, offset = 0; + u32 i, offset = 0; u16 entry_id; u8 reg_id; @@ -3664,73 +3936,83 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, if (!check_rule && dump) continue; + if (!dump) { + u32 entry_dump_size = + qed_idle_chk_dump_failure(p_hwfn, + p_ptt, + dump_buf + offset, + false, + rule->rule_id, + rule, + 0, + NULL); + + offset += num_reg_entries * entry_dump_size; + (*num_failing_rules) += num_reg_entries; + continue; + } + /* Go over all register entries (number of entries is the same * for all condition registers). */ for (entry_id = 0; entry_id < num_reg_entries; entry_id++) { /* Read current entry of all condition registers */ - if (dump) { - u32 next_reg_offset = 0; + u32 next_reg_offset = 0; - for (reg_id = 0; - reg_id < rule->num_cond_regs; - reg_id++) { - const struct dbg_idle_chk_cond_reg - *reg = &cond_regs[reg_id]; + for (reg_id = 0; reg_id < rule->num_cond_regs; + reg_id++) { + const struct dbg_idle_chk_cond_reg *reg = + &cond_regs[reg_id]; - /* Find GRC address (if it's a memory, - * the address of the specific entry is - * calculated). - */ - u32 grc_addr = - DWORDS_TO_BYTES( - GET_FIELD(reg->data, - DBG_IDLE_CHK_COND_REG_ADDRESS)); + /* Find GRC address (if it's a memory,the + * address of the specific entry is calculated). + */ + u32 addr = + GET_FIELD(reg->data, + DBG_IDLE_CHK_COND_REG_ADDRESS); - if (reg->num_entries > 1 || - reg->start_entry > 0) { - u32 padded_entry_size = - reg->entry_size > 1 ? - roundup_pow_of_two - (reg->entry_size) : 1; + if (reg->num_entries > 1 || + reg->start_entry > 0) { + u32 padded_entry_size = + reg->entry_size > 1 ? + roundup_pow_of_two(reg->entry_size) : + 1; - grc_addr += - DWORDS_TO_BYTES( - (reg->start_entry + - entry_id) - * padded_entry_size); - } - - /* Read registers */ - if (next_reg_offset + reg->entry_size >= - IDLE_CHK_MAX_ENTRIES_SIZE) { - DP_NOTICE(p_hwfn, - "idle check registers entry is too large\n"); - return 0; - } - - for (j = 0; j < reg->entry_size; - j++, next_reg_offset++, - grc_addr += 4) - cond_reg_values[next_reg_offset] = - qed_rd(p_hwfn, p_ptt, grc_addr); + addr += (reg->start_entry + entry_id) * + padded_entry_size; } + + /* Read registers */ + if (next_reg_offset + reg->entry_size >= + IDLE_CHK_MAX_ENTRIES_SIZE) { + DP_NOTICE(p_hwfn, + "idle check registers entry is too large\n"); + return 0; + } + + next_reg_offset += + qed_grc_dump_addr_range(p_hwfn, + p_ptt, + cond_reg_values + + next_reg_offset, + dump, addr, + reg->entry_size); } /* Call rule's condition function - a return value of * true indicates failure. */ if ((*cond_arr[rule->cond_id])(cond_reg_values, - imm_values) || !dump) { + imm_values)) { offset += - qed_idle_chk_dump_failure(p_hwfn, - p_ptt, - dump_buf + offset, - dump, - rule->rule_id, - rule, - entry_id, - cond_reg_values); + qed_idle_chk_dump_failure(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + rule->rule_id, + rule, + entry_id, + cond_reg_values); (*num_failing_rules)++; break; } @@ -3818,13 +4100,18 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn, struct mcp_file_att file_att; /* Call NVRAM get file command */ - if (qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_GET_FILE_ATT, - image_type, &ret_mcp_resp, &ret_mcp_param, - &ret_txn_size, (u32 *)&file_att) != 0) - return DBG_STATUS_NVRAM_GET_IMAGE_FAILED; + int nvm_result = qed_mcp_nvm_rd_cmd(p_hwfn, + p_ptt, + DRV_MSG_CODE_NVM_GET_FILE_ATT, + image_type, + &ret_mcp_resp, + &ret_mcp_param, + &ret_txn_size, + (u32 *)&file_att); /* Check response */ - if ((ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK) + if (nvm_result || + (ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK) return DBG_STATUS_NVRAM_GET_IMAGE_FAILED; /* Update return values */ @@ -3944,7 +4231,6 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn, u32 running_mfw_addr = MCP_REG_SCRATCH + SECTION_OFFSET(spad_trace_offsize) + QED_SECTION_SIZE(spad_trace_offsize) + trace_data_size_bytes; - enum dbg_status status; u32 nvram_image_type; *running_bundle_id = qed_rd(p_hwfn, p_ptt, running_mfw_addr); @@ -3955,30 +4241,12 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn, nvram_image_type = (*running_bundle_id == DIR_ID_1) ? NVM_TYPE_MFW_TRACE1 : NVM_TYPE_MFW_TRACE2; - status = qed_find_nvram_image(p_hwfn, - p_ptt, - nvram_image_type, - trace_meta_offset_bytes, - trace_meta_size_bytes); - return status; -} - -/* Reads the MCP Trace data from the specified GRC address into the specified - * buffer. - */ -static void qed_mcp_trace_read_data(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - u32 grc_addr, u32 size_in_dwords, u32 *buf) -{ - u32 i; - - DP_VERBOSE(p_hwfn, - QED_MSG_DEBUG, - "mcp_trace_read_data: reading trace data of size %d dwords from GRC address 0x%x\n", - size_in_dwords, grc_addr); - for (i = 0; i < size_in_dwords; i++, grc_addr += BYTES_IN_DWORD) - buf[i] = qed_rd(p_hwfn, p_ptt, grc_addr); + return qed_find_nvram_image(p_hwfn, + p_ptt, + nvram_image_type, + trace_meta_offset_bytes, + trace_meta_size_bytes); } /* Reads the MCP Trace meta data (from NVRAM or buffer) into the specified @@ -4034,11 +4302,14 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, bool dump, u32 *num_dumped_dwords) { u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords; - u32 trace_meta_size_dwords, running_bundle_id, offset = 0; - u32 trace_meta_offset_bytes, trace_meta_size_bytes; + u32 trace_meta_size_dwords = 0, running_bundle_id, offset = 0; + u32 trace_meta_offset_bytes = 0, trace_meta_size_bytes = 0; enum dbg_status status; + bool mcp_access; int halted = 0; + mcp_access = !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP); + *num_dumped_dwords = 0; /* Get trace data info */ @@ -4060,7 +4331,7 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, * consistent if halt fails, MCP trace is taken anyway, with a small * risk that it may be corrupt. */ - if (dump) { + if (dump && mcp_access) { halted = !qed_mcp_halt(p_hwfn, p_ptt); if (!halted) DP_NOTICE(p_hwfn, "MCP halt failed!\n"); @@ -4078,13 +4349,12 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, dump, "size", trace_data_size_dwords); /* Read trace data from scratchpad into dump buffer */ - if (dump) - qed_mcp_trace_read_data(p_hwfn, - p_ptt, - trace_data_grc_addr, - trace_data_size_dwords, - dump_buf + offset); - offset += trace_data_size_dwords; + offset += qed_grc_dump_addr_range(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + BYTES_TO_DWORDS(trace_data_grc_addr), + trace_data_size_dwords); /* Resume MCP (only if halt succeeded) */ if (halted && qed_mcp_resume(p_hwfn, p_ptt) != 0) @@ -4095,38 +4365,38 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, dump, "mcp_trace_meta", 1); /* Read trace meta info */ - status = qed_mcp_trace_get_meta_info(p_hwfn, - p_ptt, - trace_data_size_bytes, - &running_bundle_id, - &trace_meta_offset_bytes, - &trace_meta_size_bytes); - if (status != DBG_STATUS_OK) - return status; - - /* Dump trace meta size param (trace_meta_size_bytes is always - * dword-aligned). - */ - trace_meta_size_dwords = BYTES_TO_DWORDS(trace_meta_size_bytes); - offset += qed_dump_num_param(dump_buf + offset, dump, "size", - trace_meta_size_dwords); - - /* Read trace meta image into dump buffer */ - if (dump) { - status = qed_mcp_trace_read_meta(p_hwfn, - p_ptt, - trace_meta_offset_bytes, - trace_meta_size_bytes, - dump_buf + offset); - if (status != DBG_STATUS_OK) - return status; + if (mcp_access) { + status = qed_mcp_trace_get_meta_info(p_hwfn, + p_ptt, + trace_data_size_bytes, + &running_bundle_id, + &trace_meta_offset_bytes, + &trace_meta_size_bytes); + if (status == DBG_STATUS_OK) + trace_meta_size_dwords = + BYTES_TO_DWORDS(trace_meta_size_bytes); } - offset += trace_meta_size_dwords; + /* Dump trace meta size param */ + offset += qed_dump_num_param(dump_buf + offset, + dump, "size", trace_meta_size_dwords); + + /* Read trace meta image into dump buffer */ + if (dump && trace_meta_size_dwords) + status = qed_mcp_trace_read_meta(p_hwfn, + p_ptt, + trace_meta_offset_bytes, + trace_meta_size_bytes, + dump_buf + offset); + if (status == DBG_STATUS_OK) + offset += trace_meta_size_dwords; *num_dumped_dwords = offset; - return DBG_STATUS_OK; + /* If no mcp access, indicate that the dump doesn't contain the meta + * data from NVRAM. + */ + return mcp_access ? status : DBG_STATUS_NVRAM_GET_IMAGE_FAILED; } /* Dump GRC FIFO */ @@ -4311,9 +4581,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + struct fw_asserts_ram_section *asserts; char storm_letter_str[2] = "?"; struct fw_info fw_info; - u32 offset = 0, i; + u32 offset = 0; u8 storm_id; /* Dump global params */ @@ -4323,8 +4594,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, offset += qed_dump_str_param(dump_buf + offset, dump, "dump-type", "fw-asserts"); for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { - u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx, - last_list_idx, element_addr; + u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx; + u32 last_list_idx, addr; if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id]) continue; @@ -4332,6 +4603,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, /* Read FW info for the current Storm */ qed_read_fw_info(p_hwfn, p_ptt, storm_id, &fw_info); + asserts = &fw_info.fw_asserts_section; + /* Dump FW Asserts section header and params */ storm_letter_str[0] = s_storm_defs[storm_id].letter; offset += qed_dump_section_hdr(dump_buf + offset, dump, @@ -4339,12 +4612,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, offset += qed_dump_str_param(dump_buf + offset, dump, "storm", storm_letter_str); offset += qed_dump_num_param(dump_buf + offset, dump, "size", - fw_info.fw_asserts_section. - list_element_dword_size); + asserts->list_element_dword_size); if (!dump) { - offset += fw_info.fw_asserts_section. - list_element_dword_size; + offset += asserts->list_element_dword_size; continue; } @@ -4352,28 +4623,22 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, fw_asserts_section_addr = s_storm_defs[storm_id].sem_fast_mem_addr + SEM_FAST_REG_INT_RAM + - RAM_LINES_TO_BYTES(fw_info.fw_asserts_section. - section_ram_line_offset); + RAM_LINES_TO_BYTES(asserts->section_ram_line_offset); next_list_idx_addr = fw_asserts_section_addr + - DWORDS_TO_BYTES(fw_info.fw_asserts_section. - list_next_index_dword_offset); + DWORDS_TO_BYTES(asserts->list_next_index_dword_offset); next_list_idx = qed_rd(p_hwfn, p_ptt, next_list_idx_addr); last_list_idx = (next_list_idx > 0 ? next_list_idx - : fw_info.fw_asserts_section.list_num_elements) - - 1; - element_addr = - fw_asserts_section_addr + - DWORDS_TO_BYTES(fw_info.fw_asserts_section. - list_dword_offset) + - last_list_idx * - DWORDS_TO_BYTES(fw_info.fw_asserts_section. - list_element_dword_size); - for (i = 0; - i < fw_info.fw_asserts_section.list_element_dword_size; - i++, offset++, element_addr += BYTES_IN_DWORD) - dump_buf[offset] = qed_rd(p_hwfn, p_ptt, element_addr); + : asserts->list_num_elements) - 1; + addr = BYTES_TO_DWORDS(fw_asserts_section_addr) + + asserts->list_dword_offset + + last_list_idx * asserts->list_element_dword_size; + offset += + qed_grc_dump_addr_range(p_hwfn, p_ptt, + dump_buf + offset, + dump, addr, + asserts->list_element_dword_size); } /* Dump last section */ @@ -4386,13 +4651,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr) { /* Convert binary data to debug arrays */ - u32 num_of_buffers = *(u32 *)bin_ptr; - struct bin_buffer_hdr *buf_array; + struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr; u8 buf_id; - buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1); - - for (buf_id = 0; buf_id < num_of_buffers; buf_id++) { + for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) { s_dbg_arrays[buf_id].ptr = (u32 *)(bin_ptr + buf_array[buf_id].offset); s_dbg_arrays[buf_id].size_in_dwords = @@ -4402,6 +4664,17 @@ enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr) return DBG_STATUS_OK; } +/* Assign default GRC param values */ +void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 i; + + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + dev_data->grc.param_val[i] = + s_grc_param_defs[i].default_val[dev_data->chip_id]; +} + enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size) @@ -4441,8 +4714,9 @@ enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn, /* GRC Dump */ status = qed_grc_dump(p_hwfn, p_ptt, dump_buf, true, num_dumped_dwords); - /* Clear all GRC params */ - qed_dbg_grc_clear_params(p_hwfn); + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + return status; } @@ -4495,6 +4769,10 @@ enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn, /* Idle Check Dump */ *num_dumped_dwords = qed_idle_chk_dump(p_hwfn, p_ptt, dump_buf, true); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + return DBG_STATUS_OK; } @@ -4519,11 +4797,15 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, u32 needed_buf_size_in_dwords; enum dbg_status status; - status = qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt, + /* validate buffer size */ + status = + qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt, &needed_buf_size_in_dwords); - if (status != DBG_STATUS_OK) + if (status != DBG_STATUS_OK && + status != DBG_STATUS_NVRAM_GET_IMAGE_FAILED) return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) return DBG_STATUS_DUMP_BUF_TOO_SMALL; @@ -4531,8 +4813,13 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, qed_update_blocks_reset_state(p_hwfn, p_ptt); /* Perform dump */ - return qed_mcp_trace_dump(p_hwfn, - p_ptt, dump_buf, true, num_dumped_dwords); + status = qed_mcp_trace_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, @@ -4567,8 +4854,14 @@ enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn, /* Update reset state */ qed_update_blocks_reset_state(p_hwfn, p_ptt); - return qed_reg_fifo_dump(p_hwfn, - p_ptt, dump_buf, true, num_dumped_dwords); + + status = qed_reg_fifo_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, @@ -4603,8 +4896,13 @@ enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn, /* Update reset state */ qed_update_blocks_reset_state(p_hwfn, p_ptt); - return qed_igu_fifo_dump(p_hwfn, - p_ptt, dump_buf, true, num_dumped_dwords); + + status = qed_igu_fifo_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status @@ -4641,9 +4939,16 @@ enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn, /* Update reset state */ qed_update_blocks_reset_state(p_hwfn, p_ptt); - return qed_protection_override_dump(p_hwfn, - p_ptt, - dump_buf, true, num_dumped_dwords); + + status = qed_protection_override_dump(p_hwfn, + p_ptt, + dump_buf, + true, num_dumped_dwords); + + /* Revert GRC params to their default */ + qed_dbg_grc_set_params_default(p_hwfn); + + return status; } enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn, @@ -5045,13 +5350,10 @@ static char s_temp_buf[MAX_MSG_LEN]; enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr) { /* Convert binary data to debug arrays */ - u32 num_of_buffers = *(u32 *)bin_ptr; - struct bin_buffer_hdr *buf_array; + struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr; u8 buf_id; - buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1); - - for (buf_id = 0; buf_id < num_of_buffers; buf_id++) { + for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) { s_dbg_arrays[buf_id].ptr = (u32 *)(bin_ptr + buf_array[buf_id].offset); s_dbg_arrays[buf_id].size_in_dwords = @@ -5874,16 +6176,16 @@ static enum dbg_status qed_parse_reg_fifo_dump(struct qed_hwfn *p_hwfn, results_offset += sprintf(qed_get_buf_ptr(results_buf, results_offset), - "raw: 0x%016llx, address: 0x%07llx, access: %-5s, pf: %2lld, vf: %s, port: %lld, privilege: %-3s, protection: %-12s, master: %-4s, errors: ", + "raw: 0x%016llx, address: 0x%07x, access: %-5s, pf: %2d, vf: %s, port: %d, privilege: %-3s, protection: %-12s, master: %-4s, errors: ", elements[i].data, - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, REG_FIFO_ELEMENT_ADDRESS) * REG_FIFO_ELEMENT_ADDR_FACTOR, s_access_strs[GET_FIELD(elements[i].data, REG_FIFO_ELEMENT_ACCESS)], - GET_FIELD(elements[i].data, - REG_FIFO_ELEMENT_PF), vf_str, - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_PF), vf_str, + (u32)GET_FIELD(elements[i].data, REG_FIFO_ELEMENT_PORT), s_privilege_strs[GET_FIELD(elements[i]. data, @@ -6189,13 +6491,13 @@ qed_parse_protection_override_dump(struct qed_hwfn *p_hwfn, results_offset += sprintf(qed_get_buf_ptr(results_buf, results_offset), - "window %2d, address: 0x%07x, size: %7lld regs, read: %lld, write: %lld, read protection: %-12s, write protection: %-12s\n", + "window %2d, address: 0x%07x, size: %7d regs, read: %d, write: %d, read protection: %-12s, write protection: %-12s\n", i, address, - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE), - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_READ), - GET_FIELD(elements[i].data, + (u32)GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_WRITE), s_protection_strs[GET_FIELD(elements[i].data, PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION)], @@ -6508,7 +6810,7 @@ static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn, */ rc = qed_features_lookup[feature_idx].get_size(p_hwfn, p_ptt, &buf_size_dwords); - if (rc != DBG_STATUS_OK) + if (rc != DBG_STATUS_OK && rc != DBG_STATUS_NVRAM_GET_IMAGE_FAILED) return rc; feature->buf_size = buf_size_dwords * sizeof(u32); feature->dump_buf = vmalloc(feature->buf_size); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 37c2bfb663bb..88ca78a297a0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -574,6 +574,7 @@ enum core_event_opcode { CORE_EVENT_TX_QUEUE_STOP, CORE_EVENT_RX_QUEUE_START, CORE_EVENT_RX_QUEUE_STOP, + CORE_EVENT_RX_QUEUE_FLUSH, MAX_CORE_EVENT_OPCODE }; @@ -625,6 +626,7 @@ enum core_ramrod_cmd_id { CORE_RAMROD_TX_QUEUE_START, CORE_RAMROD_RX_QUEUE_STOP, CORE_RAMROD_TX_QUEUE_STOP, + CORE_RAMROD_RX_QUEUE_FLUSH, MAX_CORE_RAMROD_CMD_ID }; @@ -698,7 +700,8 @@ struct core_rx_slow_path_cqe { u8 type; u8 ramrod_cmd_id; __le16 echo; - __le32 reserved1[7]; + struct core_rx_cqe_opaque_data opaque_data; + __le32 reserved1[5]; }; union core_rx_cqe_union { @@ -735,45 +738,46 @@ struct core_rx_stop_ramrod_data { __le16 reserved2[2]; }; -struct core_tx_bd_flags { - u8 as_bitfield; -#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1 -#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0 -#define CORE_TX_BD_FLAGS_VLAN_INSERTION_MASK 0x1 -#define CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT 1 -#define CORE_TX_BD_FLAGS_START_BD_MASK 0x1 -#define CORE_TX_BD_FLAGS_START_BD_SHIFT 2 -#define CORE_TX_BD_FLAGS_IP_CSUM_MASK 0x1 -#define CORE_TX_BD_FLAGS_IP_CSUM_SHIFT 3 -#define CORE_TX_BD_FLAGS_L4_CSUM_MASK 0x1 -#define CORE_TX_BD_FLAGS_L4_CSUM_SHIFT 4 -#define CORE_TX_BD_FLAGS_IPV6_EXT_MASK 0x1 -#define CORE_TX_BD_FLAGS_IPV6_EXT_SHIFT 5 -#define CORE_TX_BD_FLAGS_L4_PROTOCOL_MASK 0x1 -#define CORE_TX_BD_FLAGS_L4_PROTOCOL_SHIFT 6 -#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_MASK 0x1 -#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_SHIFT 7 +struct core_tx_bd_data { + __le16 as_bitfield; +#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_MASK 0x1 +#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_SHIFT 0 +#define CORE_TX_BD_DATA_VLAN_INSERTION_MASK 0x1 +#define CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT 1 +#define CORE_TX_BD_DATA_START_BD_MASK 0x1 +#define CORE_TX_BD_DATA_START_BD_SHIFT 2 +#define CORE_TX_BD_DATA_IP_CSUM_MASK 0x1 +#define CORE_TX_BD_DATA_IP_CSUM_SHIFT 3 +#define CORE_TX_BD_DATA_L4_CSUM_MASK 0x1 +#define CORE_TX_BD_DATA_L4_CSUM_SHIFT 4 +#define CORE_TX_BD_DATA_IPV6_EXT_MASK 0x1 +#define CORE_TX_BD_DATA_IPV6_EXT_SHIFT 5 +#define CORE_TX_BD_DATA_L4_PROTOCOL_MASK 0x1 +#define CORE_TX_BD_DATA_L4_PROTOCOL_SHIFT 6 +#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_MASK 0x1 +#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_SHIFT 7 +#define CORE_TX_BD_DATA_NBDS_MASK 0xF +#define CORE_TX_BD_DATA_NBDS_SHIFT 8 +#define CORE_TX_BD_DATA_ROCE_FLAV_MASK 0x1 +#define CORE_TX_BD_DATA_ROCE_FLAV_SHIFT 12 +#define CORE_TX_BD_DATA_IP_LEN_MASK 0x1 +#define CORE_TX_BD_DATA_IP_LEN_SHIFT 13 +#define CORE_TX_BD_DATA_RESERVED0_MASK 0x3 +#define CORE_TX_BD_DATA_RESERVED0_SHIFT 14 }; struct core_tx_bd { struct regpair addr; __le16 nbytes; __le16 nw_vlan_or_lb_echo; - u8 bitfield0; -#define CORE_TX_BD_NBDS_MASK 0xF -#define CORE_TX_BD_NBDS_SHIFT 0 -#define CORE_TX_BD_ROCE_FLAV_MASK 0x1 -#define CORE_TX_BD_ROCE_FLAV_SHIFT 4 -#define CORE_TX_BD_RESERVED0_MASK 0x7 -#define CORE_TX_BD_RESERVED0_SHIFT 5 - struct core_tx_bd_flags bd_flags; + struct core_tx_bd_data bd_data; __le16 bitfield1; #define CORE_TX_BD_L4_HDR_OFFSET_W_MASK 0x3FFF #define CORE_TX_BD_L4_HDR_OFFSET_W_SHIFT 0 #define CORE_TX_BD_TX_DST_MASK 0x1 #define CORE_TX_BD_TX_DST_SHIFT 14 -#define CORE_TX_BD_RESERVED1_MASK 0x1 -#define CORE_TX_BD_RESERVED1_SHIFT 15 +#define CORE_TX_BD_RESERVED_MASK 0x1 +#define CORE_TX_BD_RESERVED_SHIFT 15 }; enum core_tx_dest { @@ -800,6 +804,14 @@ struct core_tx_stop_ramrod_data { __le32 reserved0[2]; }; +enum dcb_dhcp_update_flag { + DONT_UPDATE_DCB_DHCP, + UPDATE_DCB, + UPDATE_DSCP, + UPDATE_DCB_DSCP, + MAX_DCB_DHCP_UPDATE_FLAG +}; + struct eth_mstorm_per_pf_stat { struct regpair gre_discard_pkts; struct regpair vxlan_discard_pkts; @@ -893,6 +905,12 @@ union event_ring_element { struct event_ring_next_addr next_addr; }; +enum fw_flow_ctrl_mode { + flow_ctrl_pause, + flow_ctrl_pfc, + MAX_FW_FLOW_CTRL_MODE +}; + /* Major and Minor hsi Versions */ struct hsi_fp_ver_struct { u8 minor_ver_arr[2]; @@ -921,6 +939,7 @@ enum malicious_vf_error_id { ETH_EDPM_OUT_OF_SYNC, ETH_TUNN_IPV6_EXT_NBD_ERR, ETH_CONTROL_PACKET_VIOLATION, + ETH_ANTI_SPOOFING_ERR, MAX_MALICIOUS_VF_ERROR_ID }; @@ -1106,8 +1125,9 @@ struct tstorm_per_port_stat { struct regpair ll2_mac_filter_discard; struct regpair ll2_conn_disabled_discard; struct regpair iscsi_irregular_pkt; - struct regpair reserved; + struct regpair fcoe_irregular_pkt; struct regpair roce_irregular_pkt; + struct regpair reserved; struct regpair eth_irregular_pkt; struct regpair reserved1; struct regpair preroce_irregular_pkt; @@ -1648,6 +1668,11 @@ enum block_addr { GRCBASE_MS = 0x6a0000, GRCBASE_PHY_PCIE = 0x620000, GRCBASE_LED = 0x6b8000, + GRCBASE_AVS_WRAP = 0x6b0000, + GRCBASE_RGFS = 0x19d0000, + GRCBASE_TGFS = 0x19e0000, + GRCBASE_PTLD = 0x19f0000, + GRCBASE_YPLD = 0x1a10000, GRCBASE_MISC_AEU = 0x8000, GRCBASE_BAR0_MAP = 0x1c00000, MAX_BLOCK_ADDR @@ -1732,6 +1757,11 @@ enum block_id { BLOCK_MS, BLOCK_PHY_PCIE, BLOCK_LED, + BLOCK_AVS_WRAP, + BLOCK_RGFS, + BLOCK_TGFS, + BLOCK_PTLD, + BLOCK_YPLD, BLOCK_MISC_AEU, BLOCK_BAR0_MAP, MAX_BLOCK_ID @@ -1783,9 +1813,9 @@ struct dbg_attn_reg_result { __le32 data; #define DBG_ATTN_REG_RESULT_STS_ADDRESS_MASK 0xFFFFFF #define DBG_ATTN_REG_RESULT_STS_ADDRESS_SHIFT 0 -#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_MASK 0xFF -#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_SHIFT 24 - __le16 attn_idx_offset; +#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_MASK 0xFF +#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_SHIFT 24 + __le16 block_attn_offset; __le16 reserved; __le32 sts_val; __le32 mask_val; @@ -1815,12 +1845,12 @@ struct dbg_mode_hdr { /* Attention register */ struct dbg_attn_reg { struct dbg_mode_hdr mode; - __le16 attn_idx_offset; + __le16 block_attn_offset; __le32 data; #define DBG_ATTN_REG_STS_ADDRESS_MASK 0xFFFFFF #define DBG_ATTN_REG_STS_ADDRESS_SHIFT 0 -#define DBG_ATTN_REG_NUM_ATTN_IDX_MASK 0xFF -#define DBG_ATTN_REG_NUM_ATTN_IDX_SHIFT 24 +#define DBG_ATTN_REG_NUM_REG_ATTN_MASK 0xFF +#define DBG_ATTN_REG_NUM_REG_ATTN_SHIFT 24 __le32 sts_clr_address; __le32 mask_address; }; @@ -2001,6 +2031,20 @@ enum dbg_bus_clients { MAX_DBG_BUS_CLIENTS }; +enum dbg_bus_constraint_ops { + DBG_BUS_CONSTRAINT_OP_EQ, + DBG_BUS_CONSTRAINT_OP_NE, + DBG_BUS_CONSTRAINT_OP_LT, + DBG_BUS_CONSTRAINT_OP_LTC, + DBG_BUS_CONSTRAINT_OP_LE, + DBG_BUS_CONSTRAINT_OP_LEC, + DBG_BUS_CONSTRAINT_OP_GT, + DBG_BUS_CONSTRAINT_OP_GTC, + DBG_BUS_CONSTRAINT_OP_GE, + DBG_BUS_CONSTRAINT_OP_GEC, + MAX_DBG_BUS_CONSTRAINT_OPS +}; + /* Debug Bus memory address */ struct dbg_bus_mem_addr { __le32 lo; @@ -2092,10 +2136,18 @@ struct dbg_bus_data { * DBG_BUS_TARGET_ID_PCI. */ __le16 reserved; - struct dbg_bus_block_data blocks[80];/* Debug Bus data for each block */ + struct dbg_bus_block_data blocks[88];/* Debug Bus data for each block */ struct dbg_bus_storm_data storms[6]; /* Debug Bus data for each block */ }; +enum dbg_bus_filter_types { + DBG_BUS_FILTER_TYPE_OFF, + DBG_BUS_FILTER_TYPE_PRE, + DBG_BUS_FILTER_TYPE_POST, + DBG_BUS_FILTER_TYPE_ON, + MAX_DBG_BUS_FILTER_TYPES +}; + /* Debug bus frame modes */ enum dbg_bus_frame_modes { DBG_BUS_FRAME_MODE_0HW_4ST = 0, /* 0 HW dwords, 4 Storm dwords */ @@ -2104,6 +2156,40 @@ enum dbg_bus_frame_modes { MAX_DBG_BUS_FRAME_MODES }; +enum dbg_bus_input_types { + DBG_BUS_INPUT_TYPE_STORM, + DBG_BUS_INPUT_TYPE_BLOCK, + MAX_DBG_BUS_INPUT_TYPES +}; + +enum dbg_bus_other_engine_modes { + DBG_BUS_OTHER_ENGINE_MODE_NONE, + DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_TX, + DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_RX, + DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_TX, + DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_RX, + MAX_DBG_BUS_OTHER_ENGINE_MODES +}; + +enum dbg_bus_post_trigger_types { + DBG_BUS_POST_TRIGGER_RECORD, + DBG_BUS_POST_TRIGGER_DROP, + MAX_DBG_BUS_POST_TRIGGER_TYPES +}; + +enum dbg_bus_pre_trigger_types { + DBG_BUS_PRE_TRIGGER_START_FROM_ZERO, + DBG_BUS_PRE_TRIGGER_NUM_CHUNKS, + DBG_BUS_PRE_TRIGGER_DROP, + MAX_DBG_BUS_PRE_TRIGGER_TYPES +}; + +enum dbg_bus_semi_frame_modes { + DBG_BUS_SEMI_FRAME_MODE_0SLOW_4FAST = 0, + DBG_BUS_SEMI_FRAME_MODE_4SLOW_0FAST = 3, + MAX_DBG_BUS_SEMI_FRAME_MODES +}; + /* Debug bus states */ enum dbg_bus_states { DBG_BUS_STATE_IDLE, /* debug bus idle state (not recording) */ @@ -2115,6 +2201,19 @@ enum dbg_bus_states { MAX_DBG_BUS_STATES }; +enum dbg_bus_storm_modes { + DBG_BUS_STORM_MODE_PRINTF, + DBG_BUS_STORM_MODE_PRAM_ADDR, + DBG_BUS_STORM_MODE_DRA_RW, + DBG_BUS_STORM_MODE_DRA_W, + DBG_BUS_STORM_MODE_LD_ST_ADDR, + DBG_BUS_STORM_MODE_DRA_FSM, + DBG_BUS_STORM_MODE_RH, + DBG_BUS_STORM_MODE_FOC, + DBG_BUS_STORM_MODE_EXT_STORE, + MAX_DBG_BUS_STORM_MODES +}; + /* Debug bus target IDs */ enum dbg_bus_targets { /* records debug bus to DBG block internal buffer */ @@ -2128,13 +2227,10 @@ enum dbg_bus_targets { /* GRC Dump data */ struct dbg_grc_data { - __le32 param_val[40]; /* Value of each GRC parameter. Array size must - * match the enum dbg_grc_params. - */ - u8 param_set_by_user[40]; /* Indicates for each GRC parameter if it was - * set by the user (0/1). Array size must - * match the enum dbg_grc_params. - */ + u8 params_initialized; + u8 reserved1; + __le16 reserved2; + __le32 param_val[48]; }; /* Debug GRC params */ @@ -2181,6 +2277,8 @@ enum dbg_grc_params { DBG_GRC_PARAM_PARITY_SAFE, DBG_GRC_PARAM_DUMP_CM, /* dump CM memories (0/1) */ DBG_GRC_PARAM_DUMP_PHY, /* dump PHY memories (0/1) */ + DBG_GRC_PARAM_NO_MCP, + DBG_GRC_PARAM_NO_FW_VER, MAX_DBG_GRC_PARAMS }; @@ -2280,7 +2378,7 @@ struct dbg_tools_data { struct dbg_bus_data bus; /* Debug Bus data */ struct idle_chk_data idle_chk; /* Idle Check data */ u8 mode_enable[40]; /* Indicates if a mode is enabled (0/1) */ - u8 block_in_reset[80]; /* Indicates if a block is in reset state (0/1). + u8 block_in_reset[88]; /* Indicates if a block is in reset state (0/1). */ u8 chip_id; /* Chip ID (from enum chip_ids) */ u8 platform_id; /* Platform ID (from enum platform_ids) */ @@ -2418,7 +2516,6 @@ enum init_modes { MODE_PORTS_PER_ENG_2, MODE_PORTS_PER_ENG_4, MODE_100G, - MODE_40G, MODE_RESERVED6, MAX_INIT_MODES }; @@ -2685,6 +2782,13 @@ struct iro { * @param bin_ptr - a pointer to the binary data with debug arrays. */ enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr); +/** + * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their + * default value. + * + * @param p_hwfn - HW device data + */ +void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn); /** * @brief qed_dbg_grc_get_dump_buf_size - Returns the required buffer size for * GRC Dump. @@ -3418,7 +3522,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, #define MSTORM_TPA_TIMEOUT_US_SIZE (IRO[21].size) #define MSTORM_ETH_PF_STAT_OFFSET(pf_id) \ (IRO[22].base + ((pf_id) * IRO[22].m1)) -#define MSTORM_ETH_PF_STAT_SIZE (IRO[21].size) +#define MSTORM_ETH_PF_STAT_SIZE (IRO[22].size) #define USTORM_QUEUE_STAT_OFFSET(stat_counter_id) \ (IRO[23].base + ((stat_counter_id) * IRO[23].m1)) #define USTORM_QUEUE_STAT_SIZE (IRO[23].size) @@ -3482,7 +3586,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, static const struct iro iro_arr[47] = { {0x0, 0x0, 0x0, 0x0, 0x8}, - {0x4cb0, 0x78, 0x0, 0x0, 0x78}, + {0x4cb0, 0x80, 0x0, 0x0, 0x80}, {0x6318, 0x20, 0x0, 0x0, 0x20}, {0xb00, 0x8, 0x0, 0x0, 0x4}, {0xa80, 0x8, 0x0, 0x0, 0x4}, @@ -3521,13 +3625,13 @@ static const struct iro iro_arr[47] = { {0xd888, 0x38, 0x0, 0x0, 0x24}, {0x12c38, 0x10, 0x0, 0x0, 0x8}, {0x11aa0, 0x38, 0x0, 0x0, 0x18}, - {0xa8c0, 0x30, 0x0, 0x0, 0x10}, - {0x86f8, 0x28, 0x0, 0x0, 0x18}, + {0xa8c0, 0x38, 0x0, 0x0, 0x10}, + {0x86f8, 0x30, 0x0, 0x0, 0x18}, {0x101f8, 0x10, 0x0, 0x0, 0x10}, {0xdd08, 0x48, 0x0, 0x0, 0x38}, {0x10660, 0x20, 0x0, 0x0, 0x20}, {0x2b80, 0x80, 0x0, 0x0, 0x10}, - {0x5000, 0x10, 0x0, 0x0, 0x10}, + {0x5020, 0x10, 0x0, 0x0, 0x10}, }; /* Runtime array offsets */ @@ -4595,6 +4699,12 @@ enum eth_ipv4_frag_type { MAX_ETH_IPV4_FRAG_TYPE }; +enum eth_ip_type { + ETH_IPV4, + ETH_IPV6, + MAX_ETH_IP_TYPE +}; + enum eth_ramrod_cmd_id { ETH_RAMROD_UNUSED, ETH_RAMROD_VPORT_START, @@ -4944,7 +5054,10 @@ struct vport_update_ramrod_data_cmn { u8 update_mtu_flg; __le16 mtu; - u8 reserved[2]; + u8 update_ctl_frame_checks_en_flg; + u8 ctl_frame_mac_check_en; + u8 ctl_frame_ethtype_check_en; + u8 reserved[15]; }; struct vport_update_ramrod_mcast { @@ -4962,6 +5075,492 @@ struct vport_update_ramrod_data { struct eth_vport_rss_config rss_config; }; +struct mstorm_eth_conn_ag_ctx { + u8 byte0; + u8 byte1; + u8 flags0; +#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define MSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 + u8 flags1; +#define MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 + __le16 word0; + __le16 word1; + __le32 reg0; + __le32 reg1; +}; + +struct xstorm_eth_conn_agctxdq_ext_ldpart { + u8 reserved0; + u8 eth_state; + u8 flags0; +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_SHIFT 7 + u8 flags1; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_SHIFT 7 + u8 flags2; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_SHIFT 6 + u8 flags3; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_SHIFT 6 + u8 flags4; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_SHIFT 6 + u8 flags5; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_SHIFT 6 + u8 flags6; +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_SHIFT 6 + u8 flags7; +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_SHIFT 7 + u8 flags8; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_SHIFT 7 + u8 flags9; +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_SHIFT 7 + u8 flags10; +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_SHIFT 7 + u8 flags11; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_SHIFT 7 + u8 flags12; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_SHIFT 7 + u8 flags13; +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_SHIFT 6 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_SHIFT 7 + u8 flags14; +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_SHIFT 0 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_SHIFT 1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_SHIFT 2 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_SHIFT 3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_SHIFT 4 +#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_MASK 0x3 +#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_SHIFT 6 + u8 edpm_event_id; + __le16 physical_q0; + __le16 quota; + __le16 edpm_num_bds; + __le16 tx_bd_cons; + __le16 tx_bd_prod; + __le16 tx_class; + __le16 conn_dpi; + u8 byte3; + u8 byte4; + u8 byte5; + u8 byte6; + __le32 reg0; + __le32 reg1; + __le32 reg2; + __le32 reg3; + __le32 reg4; +}; + +struct xstorm_eth_hw_conn_ag_ctx { + u8 reserved0; + u8 eth_state; + u8 flags0; +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT 7 + u8 flags1; +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 + u8 flags2; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT 6 + u8 flags3; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT 6 + u8 flags4; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT 6 + u8 flags5; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT 6 + u8 flags6; +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 + u8 flags7; +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT 7 + u8 flags8; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT 7 + u8 flags9; +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7 + u8 flags10; +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT 7 + u8 flags11; +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT 7 + u8 flags12; +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT 7 + u8 flags13; +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 + u8 flags14; +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT 6 + u8 edpm_event_id; + __le16 physical_q0; + __le16 quota; + __le16 edpm_num_bds; + __le16 tx_bd_cons; + __le16 tx_bd_prod; + __le16 tx_class; + __le16 conn_dpi; +}; + struct mstorm_rdma_task_st_ctx { struct regpair temp[4]; }; @@ -6165,7 +6764,7 @@ struct ystorm_roce_conn_st_ctx { }; struct xstorm_roce_conn_st_ctx { - struct regpair temp[22]; + struct regpair temp[24]; }; struct tstorm_roce_conn_st_ctx { @@ -6220,7 +6819,7 @@ struct roce_create_qp_req_ramrod_data { __le16 mtu; __le16 pd; __le16 sq_num_pages; - __le16 reseved2; + __le16 low_latency_phy_queue; struct regpair sq_pbl_addr; struct regpair orq_pbl_addr; __le16 local_mac_addr[3]; @@ -6234,7 +6833,7 @@ struct roce_create_qp_req_ramrod_data { u8 stats_counter_id; u8 reserved3[7]; __le32 cq_cid; - __le16 physical_queue0; + __le16 regular_latency_phy_queue; __le16 dpi; }; @@ -6282,15 +6881,16 @@ struct roce_create_qp_resp_ramrod_data { __le32 dst_gid[4]; struct regpair qp_handle_for_cqe; struct regpair qp_handle_for_async; - __le32 reserved2[2]; + __le16 low_latency_phy_queue; + u8 reserved2[6]; __le32 cq_cid; - __le16 physical_queue0; + __le16 regular_latency_phy_queue; __le16 dpi; }; struct roce_destroy_qp_req_output_params { __le32 num_bound_mw; - __le32 reserved; + __le32 cq_prod; }; struct roce_destroy_qp_req_ramrod_data { @@ -6299,7 +6899,7 @@ struct roce_destroy_qp_req_ramrod_data { struct roce_destroy_qp_resp_output_params { __le32 num_invalidated_mw; - __le32 reserved; + __le32 cq_prod; }; struct roce_destroy_qp_resp_ramrod_data { @@ -7426,6 +8026,7 @@ struct ystorm_fcoe_conn_st_ctx { u8 fcp_rsp_size; __le16 mss; struct regpair reserved; + __le16 min_frame_size; u8 protection_info_flags; #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_MASK 0x1 #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_SHIFT 0 @@ -7444,7 +8045,6 @@ struct ystorm_fcoe_conn_st_ctx { #define YSTORM_FCOE_CONN_ST_CTX_RSRV_MASK 0x3F #define YSTORM_FCOE_CONN_ST_CTX_RSRV_SHIFT 2 u8 fcp_xfer_size; - u8 reserved3[2]; }; struct fcoe_vlan_fields { @@ -8273,10 +8873,10 @@ struct xstorm_iscsi_conn_ag_ctx { #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_MASK 0x3 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_SHIFT 6 u8 flags7; -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_MASK 0x3 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_SHIFT 2 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_MASK 0x3 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_SHIFT 4 #define XSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 @@ -8322,10 +8922,10 @@ struct xstorm_iscsi_conn_ag_ctx { #define XSTORM_ISCSI_CONN_AG_CTX_CF18EN_SHIFT 0 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_MASK 0x1 -#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_SHIFT 3 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 #define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_MASK 0x1 @@ -8335,8 +8935,8 @@ struct xstorm_iscsi_conn_ag_ctx { #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_SHIFT 7 u8 flags11; -#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 1 #define XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_MASK 0x1 @@ -8440,7 +9040,7 @@ struct xstorm_iscsi_conn_ag_ctx { __le32 reg10; __le32 reg11; __le32 exp_stat_sn; - __le32 reg13; + __le32 ongoing_fast_rxmit_seq; __le32 reg14; __le32 reg15; __le32 reg16; @@ -8466,10 +9066,10 @@ struct tstorm_iscsi_conn_ag_ctx { #define TSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 #define TSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define TSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 -#define TSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 0 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_SHIFT 2 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4 #define TSTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 @@ -8490,10 +9090,10 @@ struct tstorm_iscsi_conn_ag_ctx { #define TSTORM_ISCSI_CONN_AG_CTX_CF10_SHIFT 2 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 4 -#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 -#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 5 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 -#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_SHIFT 5 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_SHIFT 6 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7 u8 flags4; @@ -8539,7 +9139,7 @@ struct tstorm_iscsi_conn_ag_ctx { __le32 reg6; __le32 reg7; __le32 reg8; - u8 byte2; + u8 cid_offload_cnt; u8 byte3; __le16 word0; }; @@ -9067,6 +9667,10 @@ struct dcb_dscp_map { struct public_global { u32 max_path; u32 max_ports; +#define MODE_1P 1 +#define MODE_2P 2 +#define MODE_3P 3 +#define MODE_4P 4 u32 debug_mb_offset; u32 phymod_dbg_mb_offset; struct couple_mode_teaming cmt; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index d891a6852695..2a50e2b7568f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -215,13 +215,6 @@ static void qed_cmdq_lines_voq_rt_init(struct qed_hwfn *p_hwfn, { u32 qm_line_crd; - /* In A0 - Limit the size of pbf queue so that only 511 commands with - * the minimum size of 4 (FCoE minimum size) - */ - bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev); - - if (is_bb_a0) - cmdq_lines = min_t(u32, cmdq_lines, 1022); qm_line_crd = QM_VOQ_LINE_CRD(cmdq_lines); OVERWRITE_RT_REG(p_hwfn, PBF_CMDQ_LINES_RT_OFFSET(voq), (u32)cmdq_lines); @@ -343,13 +336,11 @@ static void qed_tx_pq_map_rt_init( u16 first_pq_group = p_params->start_pq / QM_PF_QUEUE_GROUP_SIZE; u16 last_pq_group = (p_params->start_pq + num_pqs - 1) / QM_PF_QUEUE_GROUP_SIZE; - bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev); u16 i, pq_id, pq_group; /* a bit per Tx PQ indicating if the PQ is associated with a VF */ u32 tx_pq_vf_mask[MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE] = { 0 }; - u32 tx_pq_vf_mask_width = is_bb_a0 ? 32 : QM_PF_QUEUE_GROUP_SIZE; - u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / tx_pq_vf_mask_width; + u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE; u32 pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_pf_cids); u32 vport_pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_vf_cids); u32 mem_addr_4kb = base_mem_addr_4kb; @@ -371,6 +362,10 @@ static void qed_tx_pq_map_rt_init( bool is_vf_pq = (i >= p_params->num_pf_pqs); struct qm_rf_pq_map tx_pq_map; + bool rl_valid = p_params->pq_params[i].rl_valid && + (p_params->pq_params[i].vport_id < + MAX_QM_GLOBAL_RLS); + /* update first Tx PQ of VPORT/TC */ u8 vport_id_in_pf = p_params->pq_params[i].vport_id - p_params->start_vport; @@ -389,14 +384,18 @@ static void qed_tx_pq_map_rt_init( (p_params->pf_id << QM_WFQ_VP_PQ_PF_SHIFT)); } + + if (p_params->pq_params[i].rl_valid && !rl_valid) + DP_NOTICE(p_hwfn, + "Invalid VPORT ID for rate limiter configuration"); /* fill PQ map entry */ memset(&tx_pq_map, 0, sizeof(tx_pq_map)); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_PQ_VALID, 1); - SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_VALID, - p_params->pq_params[i].rl_valid ? 1 : 0); + SET_FIELD(tx_pq_map.reg, + QM_RF_PQ_MAP_RL_VALID, rl_valid ? 1 : 0); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VP_PQ_ID, first_tx_pq_id); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_ID, - p_params->pq_params[i].rl_valid ? + rl_valid ? p_params->pq_params[i].vport_id : 0); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VOQ, voq); SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_WRR_WEIGHT_GROUP, @@ -413,8 +412,9 @@ static void qed_tx_pq_map_rt_init( /* if PQ is associated with a VF, add indication * to PQ VF mask */ - tx_pq_vf_mask[pq_id / tx_pq_vf_mask_width] |= - (1 << (pq_id % tx_pq_vf_mask_width)); + tx_pq_vf_mask[pq_id / + QM_PF_QUEUE_GROUP_SIZE] |= + BIT((pq_id % QM_PF_QUEUE_GROUP_SIZE)); mem_addr_4kb += vport_pq_mem_4kb; } else { mem_addr_4kb += pq_mem_4kb; @@ -480,8 +480,8 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn, if (p_params->pf_id < MAX_NUM_PFS_BB) crd_reg_offset = QM_REG_WFQPFCRD_RT_OFFSET; else - crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET + - (p_params->pf_id % MAX_NUM_PFS_BB); + crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET; + crd_reg_offset += p_params->pf_id % MAX_NUM_PFS_BB; inc_val = QM_WFQ_INC_VAL(p_params->pf_wfq); if (!inc_val || inc_val > QM_WFQ_MAX_INC_VAL) { @@ -498,11 +498,11 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn, QM_WFQ_CRD_REG_SIGN_BIT); } - STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id, - inc_val); STORE_RT_REG(p_hwfn, QM_REG_WFQPFUPPERBOUND_RT_OFFSET + p_params->pf_id, QM_WFQ_UPPER_BOUND | QM_WFQ_CRD_REG_SIGN_BIT); + STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id, + inc_val); return 0; } @@ -576,6 +576,12 @@ static int qed_vport_rl_rt_init(struct qed_hwfn *p_hwfn, { u8 i, vport_id; + if (start_vport + num_vports >= MAX_QM_GLOBAL_RLS) { + DP_NOTICE(p_hwfn, + "Invalid VPORT ID for rate limiter configuration"); + return -1; + } + /* go over all PF VPORTs */ for (i = 0, vport_id = start_vport; i < num_vports; i++, vport_id++) { u32 inc_val = QM_RL_INC_VAL(vport_params[i].vport_rl); @@ -785,6 +791,12 @@ int qed_init_vport_rl(struct qed_hwfn *p_hwfn, { u32 inc_val = QM_RL_INC_VAL(vport_rl); + if (vport_id >= MAX_QM_GLOBAL_RLS) { + DP_NOTICE(p_hwfn, + "Invalid VPORT ID for rate limiter configuration"); + return -1; + } + if (inc_val > QM_RL_MAX_INC_VAL) { DP_NOTICE(p_hwfn, "Invalid VPORT rate-limit configuration"); return -1; @@ -940,12 +952,6 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, eth_geneve_enable ? 1 : 0); qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_IP_ENABLE, ip_geneve_enable ? 1 : 0); - /* comp ver */ - reg_val = (ip_geneve_enable || eth_geneve_enable) ? 1 : 0; - qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_COMP_VER, reg_val); - qed_wr(p_hwfn, p_ptt, PBF_REG_NGE_COMP_VER, reg_val); - qed_wr(p_hwfn, p_ptt, PRS_REG_NGE_COMP_VER, reg_val); - /* EDPM with geneve tunnel not supported in BB_B0 */ if (QED_IS_BB_B0(p_hwfn->cdev)) return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c index 243b64e0d4dc..4a2e7be5bf72 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c @@ -554,7 +554,7 @@ int qed_init_fw_data(struct qed_dev *cdev, const u8 *data) } /* First Dword contains metadata and should be skipped */ - buf_hdr = (struct bin_buffer_hdr *)(data + sizeof(u32)); + buf_hdr = (struct bin_buffer_hdr *)data; offset = buf_hdr[BIN_BUF_INIT_FW_VER_INFO].offset; fw->fw_ver_info = (struct fw_ver_info *)(data + offset); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 9a0b9af10a57..161d90376dae 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -594,7 +594,7 @@ static u8 qed_ll2_convert_rx_parse_to_tx_flags(u16 parse_flags) u8 bd_flags = 0; if (GET_FIELD(parse_flags, PARSING_AND_ERR_FLAGS_TAG8021QEXIST)) - SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_VLAN_INSERTION, 1); + SET_FIELD(bd_flags, CORE_TX_BD_DATA_VLAN_INSERTION, 1); return bd_flags; } @@ -755,8 +755,8 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn, p_buffer->placement_offset; parse_flags = p_buffer->parse_flags; bd_flags = qed_ll2_convert_rx_parse_to_tx_flags(parse_flags); - SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_FORCE_VLAN_MODE, 1); - SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_L4_PROTOCOL, 1); + SET_FIELD(bd_flags, CORE_TX_BD_DATA_FORCE_VLAN_MODE, 1); + SET_FIELD(bd_flags, CORE_TX_BD_DATA_L4_PROTOCOL, 1); rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1, p_buffer->vlan, bd_flags, @@ -1588,33 +1588,34 @@ static void qed_ll2_prepare_tx_packet_set(struct qed_hwfn *p_hwfn, p_tx->cur_send_frag_num++; } -static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, - struct qed_ll2_info *p_ll2, - struct qed_ll2_tx_packet *p_curp, - u8 num_of_bds, - enum core_tx_dest tx_dest, - u16 vlan, - u8 bd_flags, - u16 l4_hdr_offset_w, - enum core_roce_flavor_type type, - dma_addr_t first_frag, - u16 first_frag_len) +static void +qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, + struct qed_ll2_info *p_ll2, + struct qed_ll2_tx_packet *p_curp, + u8 num_of_bds, + enum core_tx_dest tx_dest, + u16 vlan, + u8 bd_flags, + u16 l4_hdr_offset_w, + enum core_roce_flavor_type roce_flavor, + dma_addr_t first_frag, + u16 first_frag_len) { struct qed_chain *p_tx_chain = &p_ll2->tx_queue.txq_chain; u16 prod_idx = qed_chain_get_prod_idx(p_tx_chain); struct core_tx_bd *start_bd = NULL; - u16 frag_idx; + u16 bd_data = 0, frag_idx; start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); start_bd->nw_vlan_or_lb_echo = cpu_to_le16(vlan); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W, cpu_to_le16(l4_hdr_offset_w)); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest); - start_bd->bd_flags.as_bitfield = bd_flags; - start_bd->bd_flags.as_bitfield |= CORE_TX_BD_FLAGS_START_BD_MASK << - CORE_TX_BD_FLAGS_START_BD_SHIFT; - SET_FIELD(start_bd->bitfield0, CORE_TX_BD_NBDS, num_of_bds); - SET_FIELD(start_bd->bitfield0, CORE_TX_BD_ROCE_FLAV, type); + bd_data |= bd_flags; + SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1); + SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, num_of_bds); + SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor); + start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data); DMA_REGPAIR_LE(start_bd->addr, first_frag); start_bd->nbytes = cpu_to_le16(first_frag_len); @@ -1639,9 +1640,8 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, struct core_tx_bd **p_bd = &p_curp->bds_set[frag_idx].txq_bd; *p_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); - (*p_bd)->bd_flags.as_bitfield = 0; + (*p_bd)->bd_data.as_bitfield = 0; (*p_bd)->bitfield1 = 0; - (*p_bd)->bitfield0 = 0; p_curp->bds_set[frag_idx].tx_frag = 0; p_curp->bds_set[frag_idx].frag_len = 0; } @@ -2238,11 +2238,11 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) /* Request HW to calculate IP csum */ if (!((vlan_get_protocol(skb) == htons(ETH_P_IPV6)) && ipv6_hdr(skb)->nexthdr == NEXTHDR_IPV6)) - flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT); + flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT); if (skb_vlan_tag_present(skb)) { vlan = skb_vlan_tag_get(skb); - flags |= BIT(CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT); + flags |= BIT(CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT); } rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev), diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index d59d9df60cd2..36ae361884e0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -356,6 +356,10 @@ 0x238804UL #define RDIF_REG_STOP_ON_ERROR \ 0x300040UL +#define RDIF_REG_DEBUG_ERROR_INFO \ + 0x300400UL +#define RDIF_REG_DEBUG_ERROR_INFO_SIZE \ + 64 #define SRC_REG_SOFT_RST \ 0x23874cUL #define TCFC_REG_ACTIVITY_COUNTER \ @@ -370,6 +374,10 @@ 0x1700004UL #define TDIF_REG_STOP_ON_ERROR \ 0x310040UL +#define TDIF_REG_DEBUG_ERROR_INFO \ + 0x310400UL +#define TDIF_REG_DEBUG_ERROR_INFO_SIZE \ + 64 #define UCM_REG_INIT \ 0x1280000UL #define UMAC_REG_IPG_HD_BKP_CNTL_BB_B0 \ @@ -1236,6 +1244,26 @@ 0x1901534UL #define USEM_REG_DBG_FORCE_FRAME \ 0x1901538UL +#define NWS_REG_DBG_SELECT \ + 0x700128UL +#define NWS_REG_DBG_DWORD_ENABLE \ + 0x70012cUL +#define NWS_REG_DBG_SHIFT \ + 0x700130UL +#define NWS_REG_DBG_FORCE_VALID \ + 0x700134UL +#define NWS_REG_DBG_FORCE_FRAME \ + 0x700138UL +#define MS_REG_DBG_SELECT \ + 0x6a0228UL +#define MS_REG_DBG_DWORD_ENABLE \ + 0x6a022cUL +#define MS_REG_DBG_SHIFT \ + 0x6a0230UL +#define MS_REG_DBG_FORCE_VALID \ + 0x6a0234UL +#define MS_REG_DBG_FORCE_FRAME \ + 0x6a0238UL #define PCIE_REG_DBG_COMMON_SELECT \ 0x054398UL #define PCIE_REG_DBG_COMMON_DWORD_ENABLE \ @@ -1448,6 +1476,8 @@ 0x000b48UL #define RSS_REG_RSS_RAM_DATA \ 0x238c20UL +#define RSS_REG_RSS_RAM_DATA_SIZE \ + 4 #define MISC_REG_BLOCK_256B_EN \ 0x008c14UL #define NWS_REG_NWS_CMU \ diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index d9ff6b28591c..4bef5c59627c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -66,13 +66,27 @@ #include "qed_roce.h" #include "qed_ll2.h" -void qed_async_roce_event(struct qed_hwfn *p_hwfn, - struct event_ring_entry *p_eqe) -{ - struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; +static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid); - p_rdma_info->events.affiliated_event(p_rdma_info->events.context, - p_eqe->opcode, &p_eqe->data); +void qed_roce_async_event(struct qed_hwfn *p_hwfn, + u8 fw_event_code, union rdma_eqe_data *rdma_data) +{ + if (fw_event_code == ROCE_ASYNC_EVENT_DESTROY_QP_DONE) { + u16 icid = + (u16)le32_to_cpu(rdma_data->rdma_destroy_qp_data.cid); + + /* icid release in this async event can occur only if the icid + * was offloaded to the FW. In case it wasn't offloaded this is + * handled in qed_roce_sp_destroy_qp. + */ + qed_roce_free_real_icid(p_hwfn, icid); + } else { + struct qed_rdma_events *events = &p_hwfn->p_rdma_info->events; + + events->affiliated_event(p_hwfn->p_rdma_info->events.context, + fw_event_code, + &rdma_data->async_handle); + } } static int qed_rdma_bmap_alloc(struct qed_hwfn *p_hwfn, @@ -113,6 +127,15 @@ static int qed_rdma_bmap_alloc_id(struct qed_hwfn *p_hwfn, return 0; } +static void qed_bmap_set_id(struct qed_hwfn *p_hwfn, + struct qed_bmap *bmap, u32 id_num) +{ + if (id_num >= bmap->max_count) + return; + + __set_bit(id_num, bmap->bitmap); +} + static void qed_bmap_release_id(struct qed_hwfn *p_hwfn, struct qed_bmap *bmap, u32 id_num) { @@ -129,6 +152,15 @@ static void qed_bmap_release_id(struct qed_hwfn *p_hwfn, } } +static int qed_bmap_test_id(struct qed_hwfn *p_hwfn, + struct qed_bmap *bmap, u32 id_num) +{ + if (id_num >= bmap->max_count) + return -1; + + return test_bit(id_num, bmap->bitmap); +} + static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id) { /* First sb id for RoCE is after all the l2 sb */ @@ -170,7 +202,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, /* Queue zone lines are shared between RoCE and L2 in such a way that * they can be used by each without obstructing the other. */ - p_rdma_info->queue_zone_base = (u16)FEAT_NUM(p_hwfn, QED_L2_QUEUE); + p_rdma_info->queue_zone_base = (u16)RESC_START(p_hwfn, QED_L2_QUEUE); + p_rdma_info->max_queue_zones = (u16)RESC_NUM(p_hwfn, QED_L2_QUEUE); /* Allocate a struct with device params and fill it */ p_rdma_info->dev = kzalloc(sizeof(*p_rdma_info->dev), GFP_KERNEL); @@ -248,9 +281,18 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, goto free_tid_map; } + /* Allocate bitmap for cids used for responders/requesters. */ + rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->real_cid_map, num_cons); + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Failed to allocate real cid bitmap, rc = %d\n", rc); + goto free_cid_map; + } DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocation successful\n"); return 0; +free_cid_map: + kfree(p_rdma_info->cid_map.bitmap); free_tid_map: kfree(p_rdma_info->tid_map.bitmap); free_toggle_map: @@ -273,7 +315,22 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn) { + struct qed_bmap *rcid_map = &p_hwfn->p_rdma_info->real_cid_map; struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; + int wait_count = 0; + + /* when destroying a_RoCE QP the control is returned to the user after + * the synchronous part. The asynchronous part may take a little longer. + * We delay for a short while if an async destroy QP is still expected. + * Beyond the added delay we clear the bitmap anyway. + */ + while (bitmap_weight(rcid_map->bitmap, rcid_map->max_count)) { + msleep(100); + if (wait_count++ > 20) { + DP_NOTICE(p_hwfn, "cid bitmap wait timed out\n"); + break; + } + } kfree(p_rdma_info->cid_map.bitmap); kfree(p_rdma_info->tid_map.bitmap); @@ -724,6 +781,14 @@ static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod) u32 addr; p_hwfn = (struct qed_hwfn *)rdma_cxt; + + if (qz_offset > p_hwfn->p_rdma_info->max_queue_zones) { + DP_NOTICE(p_hwfn, + "queue zone offset %d is too large (max is %d)\n", + qz_offset, p_hwfn->p_rdma_info->max_queue_zones); + return; + } + qz_num = p_hwfn->p_rdma_info->queue_zone_base + qz_offset; addr = GTT_BAR0_MAP_REG_USDM_RAM + USTORM_COMMON_QUEUE_CONS_OFFSET(qz_num); @@ -1080,6 +1145,14 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode) return flavor; } +void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid) +{ + spin_lock_bh(&p_hwfn->p_rdma_info->lock); + qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid); + qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid + 1); + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid) { struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; @@ -1139,6 +1212,13 @@ static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid) return rc; } +static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid) +{ + spin_lock_bh(&p_hwfn->p_rdma_info->lock); + qed_bmap_set_id(p_hwfn, &p_hwfn->p_rdma_info->real_cid_map, cid); + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) { @@ -1147,7 +1227,8 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, union qed_qm_pq_params qm_params; enum roce_flavor roce_flavor; struct qed_spq_entry *p_ent; - u16 physical_queue0 = 0; + u16 regular_latency_queue; + enum protocol_type proto; int rc; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid); @@ -1229,15 +1310,19 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo); p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi); p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo); - p_ramrod->stats_counter_id = p_hwfn->rel_pf_id; p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->rq_cq_id); memset(&qm_params, 0, sizeof(qm_params)); qm_params.roce.qpid = qp->icid >> 1; - physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params); + regular_latency_queue = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, + &qm_params); + + p_ramrod->regular_latency_phy_queue = + cpu_to_le16(regular_latency_queue); + p_ramrod->low_latency_phy_queue = + cpu_to_le16(regular_latency_queue); - p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0); p_ramrod->dpi = cpu_to_le16(qp->dpi); qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr); @@ -1253,13 +1338,19 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn, rc = qed_spq_post(p_hwfn, p_ent, NULL); - DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d physical_queue0 = 0x%x\n", - rc, physical_queue0); + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "rc = %d regular physical queue = 0x%x\n", rc, + regular_latency_queue); if (rc) goto err; qp->resp_offloaded = true; + qp->cq_prod = 0; + + proto = p_hwfn->p_rdma_info->proto; + qed_roce_set_real_cid(p_hwfn, qp->icid - + qed_cxt_get_proto_cid_start(p_hwfn, proto)); return rc; @@ -1280,7 +1371,8 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, union qed_qm_pq_params qm_params; enum roce_flavor roce_flavor; struct qed_spq_entry *p_ent; - u16 physical_queue0 = 0; + u16 regular_latency_queue; + enum protocol_type proto; int rc; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid); @@ -1351,15 +1443,19 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo); p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi); p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo); - p_ramrod->stats_counter_id = p_hwfn->rel_pf_id; - p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | - qp->sq_cq_id); + p_ramrod->cq_cid = + cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id); memset(&qm_params, 0, sizeof(qm_params)); qm_params.roce.qpid = qp->icid >> 1; - physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params); + regular_latency_queue = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, + &qm_params); + + p_ramrod->regular_latency_phy_queue = + cpu_to_le16(regular_latency_queue); + p_ramrod->low_latency_phy_queue = + cpu_to_le16(regular_latency_queue); - p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0); p_ramrod->dpi = cpu_to_le16(qp->dpi); qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr); @@ -1378,6 +1474,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn, goto err; qp->req_offloaded = true; + proto = p_hwfn->p_rdma_info->proto; + qed_roce_set_real_cid(p_hwfn, + qp->icid + 1 - + qed_cxt_get_proto_cid_start(p_hwfn, proto)); return rc; @@ -1577,7 +1677,8 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn, static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp, - u32 *num_invalidated_mw) + u32 *num_invalidated_mw, + u32 *cq_prod) { struct roce_destroy_qp_resp_output_params *p_ramrod_res; struct roce_destroy_qp_resp_ramrod_data *p_ramrod; @@ -1588,8 +1689,22 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid); - if (!qp->resp_offloaded) + *num_invalidated_mw = 0; + *cq_prod = qp->cq_prod; + + if (!qp->resp_offloaded) { + /* If a responder was never offload, we need to free the cids + * allocated in create_qp as a FW async event will never arrive + */ + u32 cid; + + cid = qp->icid - + qed_cxt_get_proto_cid_start(p_hwfn, + p_hwfn->p_rdma_info->proto); + qed_roce_free_cid_pair(p_hwfn, (u16)cid); + return 0; + } /* Get SPQ entry */ memset(&init_data, 0, sizeof(init_data)); @@ -1624,6 +1739,8 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, goto err; *num_invalidated_mw = le32_to_cpu(p_ramrod_res->num_invalidated_mw); + *cq_prod = le32_to_cpu(p_ramrod_res->cq_prod); + qp->cq_prod = *cq_prod; /* Free IRQ - only if ramrod succeeded, in case FW is still using it */ dma_free_coherent(&p_hwfn->cdev->pdev->dev, @@ -1827,10 +1944,8 @@ static int qed_roce_query_qp(struct qed_hwfn *p_hwfn, out_params->draining = false; - if (rq_err_state) + if (rq_err_state || sq_err_state) qp->cur_state = QED_ROCE_QP_STATE_ERR; - else if (sq_err_state) - qp->cur_state = QED_ROCE_QP_STATE_SQE; else if (sq_draining) out_params->draining = true; out_params->state = qp->cur_state; @@ -1849,10 +1964,9 @@ static int qed_roce_query_qp(struct qed_hwfn *p_hwfn, static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) { - struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; u32 num_invalidated_mw = 0; u32 num_bound_mw = 0; - u32 start_cid; + u32 cq_prod; int rc; /* Destroys the specified QP */ @@ -1866,7 +1980,8 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) if (qp->cur_state != QED_ROCE_QP_STATE_RESET) { rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp, - &num_invalidated_mw); + &num_invalidated_mw, + &cq_prod); if (rc) return rc; @@ -1881,21 +1996,6 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp) "number of invalidate memory windows is different from bounded ones\n"); return -EINVAL; } - - spin_lock_bh(&p_rdma_info->lock); - - start_cid = qed_cxt_get_proto_cid_start(p_hwfn, - p_rdma_info->proto); - - /* Release responder's icid */ - qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, - qp->icid - start_cid); - - /* Release requester's icid */ - qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, - qp->icid + 1 - start_cid); - - spin_unlock_bh(&p_rdma_info->lock); } return 0; @@ -2110,12 +2210,19 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn, return rc; } else if (qp->cur_state == QED_ROCE_QP_STATE_RESET) { /* Any state -> RESET */ + u32 cq_prod; + + /* Send destroy responder ramrod */ + rc = qed_roce_sp_destroy_qp_responder(p_hwfn, + qp, + &num_invalidated_mw, + &cq_prod); - rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp, - &num_invalidated_mw); if (rc) return rc; + qp->cq_prod = cq_prod; + rc = qed_roce_sp_destroy_qp_requester(p_hwfn, qp, &num_bound_mw); @@ -2454,6 +2561,31 @@ static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid) return rc; } +static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid) +{ + struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info; + u32 start_cid, cid, xcid; + + /* an even icid belongs to a responder while an odd icid belongs to a + * requester. The 'cid' received as an input can be either. We calculate + * the "partner" icid and call it xcid. Only if both are free then the + * "cid" map can be cleared. + */ + start_cid = qed_cxt_get_proto_cid_start(p_hwfn, p_rdma_info->proto); + cid = icid - start_cid; + xcid = cid ^ 1; + + spin_lock_bh(&p_rdma_info->lock); + + qed_bmap_release_id(p_hwfn, &p_rdma_info->real_cid_map, cid); + if (qed_bmap_test_id(p_hwfn, &p_rdma_info->real_cid_map, xcid) == 0) { + qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, cid); + qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, xcid); + } + + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + static void *qed_rdma_get_rdma_ctx(struct qed_dev *cdev) { return QED_LEADING_HWFN(cdev); @@ -2773,7 +2905,7 @@ static int qed_roce_ll2_tx(struct qed_dev *cdev, : QED_LL2_RROCE; if (pkt->roce_mode == ROCE_V2_IPV4) - flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT); + flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT); /* Tx header */ rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev), roce_ll2->handle, diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h index 36cf4b2ab7fa..3ccc08a7c995 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.h +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h @@ -82,6 +82,7 @@ struct qed_rdma_info { struct qed_bmap qp_map; struct qed_bmap srq_map; struct qed_bmap cid_map; + struct qed_bmap real_cid_map; struct qed_bmap dpi_map; struct qed_bmap toggle_bits; struct qed_rdma_events events; @@ -92,6 +93,7 @@ struct qed_rdma_info { u32 num_qps; u32 num_mrs; u16 queue_zone_base; + u16 max_queue_zones; enum protocol_type proto; }; @@ -153,6 +155,7 @@ struct qed_rdma_qp { dma_addr_t irq_phys_addr; u8 irq_num_pages; bool resp_offloaded; + u32 cq_prod; u8 remote_mac_addr[6]; u8 local_mac_addr[6]; @@ -163,8 +166,8 @@ struct qed_rdma_qp { #if IS_ENABLED(CONFIG_QED_RDMA) void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); -void qed_async_roce_event(struct qed_hwfn *p_hwfn, - struct event_ring_entry *p_eqe); +void qed_roce_async_event(struct qed_hwfn *p_hwfn, + u8 fw_event_code, union rdma_eqe_data *rdma_data); void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn, u8 connection_handle, void *cookie, @@ -187,7 +190,9 @@ void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn, u16 src_mac_addr_lo, bool b_last_packet); #else static inline void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {} -static inline void qed_async_roce_event(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) {} +static inline void qed_roce_async_event(struct qed_hwfn *p_hwfn, + u8 fw_event_code, + union rdma_eqe_data *rdma_data) {} static inline void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn, u8 connection_handle, void *cookie, diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 645328a9f0cf..54fbe3789cf3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -296,9 +296,12 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) { switch (p_eqe->protocol_id) { +#if IS_ENABLED(CONFIG_QED_RDMA) case PROTOCOLID_ROCE: - qed_async_roce_event(p_hwfn, p_eqe); + qed_roce_async_event(p_hwfn, p_eqe->opcode, + &p_eqe->data.rdma_data); return 0; +#endif case PROTOCOLID_COMMON: return qed_sriov_eqe_event(p_hwfn, p_eqe->opcode, @@ -306,14 +309,6 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn, case PROTOCOLID_ISCSI: if (!IS_ENABLED(CONFIG_QED_ISCSI)) return -EINVAL; - if (p_eqe->opcode == ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES) { - u32 cid = le32_to_cpu(p_eqe->data.iscsi_info.cid); - - qed_ooo_release_connection_isles(p_hwfn, - p_hwfn->p_ooo_info, - cid); - return 0; - } if (p_hwfn->p_iscsi_info->event_cb) { struct qed_iscsi_info *p_iscsi = p_hwfn->p_iscsi_info; diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index f2aaef2cfb86..8d02fb6c19d7 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -50,7 +50,7 @@ #define QEDE_MAJOR_VERSION 8 #define QEDE_MINOR_VERSION 10 #define QEDE_REVISION_VERSION 10 -#define QEDE_ENGINEERING_VERSION 20 +#define QEDE_ENGINEERING_VERSION 21 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "." \ __stringify(QEDE_MINOR_VERSION) "." \ __stringify(QEDE_REVISION_VERSION) "." \ diff --git a/drivers/scsi/qedf/Makefile b/drivers/scsi/qedf/Makefile index 64e9f507ce32..414f2a772a5f 100644 --- a/drivers/scsi/qedf/Makefile +++ b/drivers/scsi/qedf/Makefile @@ -1,5 +1,5 @@ obj-$(CONFIG_QEDF) := qedf.o qedf-y = qedf_dbg.o qedf_main.o qedf_io.o qedf_fip.o \ - qedf_attr.o qedf_els.o + qedf_attr.o qedf_els.o drv_scsi_fw_funcs.o drv_fcoe_fw_funcs.o qedf-$(CONFIG_DEBUG_FS) += qedf_debugfs.o diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.c b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c new file mode 100644 index 000000000000..bb812db48da6 --- /dev/null +++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c @@ -0,0 +1,190 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#include "drv_fcoe_fw_funcs.h" +#include "drv_scsi_fw_funcs.h" + +#define FCOE_RX_ID ((u32)0x0000FFFF) + +static inline void init_common_sqe(struct fcoe_task_params *task_params, + enum fcoe_sqe_request_type request_type) +{ + memset(task_params->sqe, 0, sizeof(*(task_params->sqe))); + SET_FIELD(task_params->sqe->flags, FCOE_WQE_REQ_TYPE, + request_type); + task_params->sqe->task_id = task_params->itid; +} + +int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params, + struct scsi_sgl_task_params *sgl_task_params, + struct regpair sense_data_buffer_phys_addr, + u32 task_retry_id, + u8 fcp_cmd_payload[32]) +{ + struct fcoe_task_context *ctx = task_params->context; + struct ystorm_fcoe_task_st_ctx *y_st_ctx; + struct tstorm_fcoe_task_st_ctx *t_st_ctx; + struct ustorm_fcoe_task_ag_ctx *u_ag_ctx; + struct mstorm_fcoe_task_st_ctx *m_st_ctx; + u32 io_size, val; + bool slow_sgl; + + memset(ctx, 0, sizeof(*(ctx))); + slow_sgl = scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge); + io_size = (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR ? + task_params->tx_io_size : task_params->rx_io_size); + + /* Ystorm ctx */ + y_st_ctx = &ctx->ystorm_st_context; + y_st_ctx->data_2_trns_rem = cpu_to_le32(io_size); + y_st_ctx->task_rety_identifier = cpu_to_le32(task_retry_id); + y_st_ctx->task_type = task_params->task_type; + memcpy(&y_st_ctx->tx_info_union.fcp_cmd_payload, + fcp_cmd_payload, sizeof(struct fcoe_fcp_cmd_payload)); + + /* Tstorm ctx */ + t_st_ctx = &ctx->tstorm_st_context; + t_st_ctx->read_only.dev_type = (task_params->is_tape_device == 1 ? + FCOE_TASK_DEV_TYPE_TAPE : + FCOE_TASK_DEV_TYPE_DISK); + t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid); + val = cpu_to_le32(task_params->cq_rss_number); + t_st_ctx->read_only.glbl_q_num = val; + t_st_ctx->read_only.fcp_cmd_trns_size = cpu_to_le32(io_size); + t_st_ctx->read_only.task_type = task_params->task_type; + SET_FIELD(t_st_ctx->read_write.flags, + FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1); + t_st_ctx->read_write.rx_id = cpu_to_le32(FCOE_RX_ID); + + /* Ustorm ctx */ + u_ag_ctx = &ctx->ustorm_ag_context; + u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number); + + /* Mstorm buffer for sense/rsp data placement */ + m_st_ctx = &ctx->mstorm_st_context; + val = cpu_to_le32(sense_data_buffer_phys_addr.hi); + m_st_ctx->rsp_buf_addr.hi = val; + val = cpu_to_le32(sense_data_buffer_phys_addr.lo); + m_st_ctx->rsp_buf_addr.lo = val; + + if (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) { + /* Ystorm ctx */ + y_st_ctx->expect_first_xfer = 1; + + /* Set the amount of super SGEs. Can be up to 4. */ + SET_FIELD(y_st_ctx->sgl_mode, + YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, + (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL)); + init_scsi_sgl_context(&y_st_ctx->sgl_params, + &y_st_ctx->data_desc, + sgl_task_params); + + /* Mstorm ctx */ + SET_FIELD(m_st_ctx->flags, + MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, + (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL)); + } else { + /* Tstorm ctx */ + SET_FIELD(t_st_ctx->read_write.flags, + FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE, + (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL)); + + /* Mstorm ctx */ + m_st_ctx->data_2_trns_rem = cpu_to_le32(io_size); + init_scsi_sgl_context(&m_st_ctx->sgl_params, + &m_st_ctx->data_desc, + sgl_task_params); + } + + init_common_sqe(task_params, SEND_FCOE_CMD); + return 0; +} + +int init_initiator_midpath_unsolicited_fcoe_task( + struct fcoe_task_params *task_params, + struct fcoe_tx_mid_path_params *mid_path_fc_header, + struct scsi_sgl_task_params *tx_sgl_task_params, + struct scsi_sgl_task_params *rx_sgl_task_params, + u8 fw_to_place_fc_header) +{ + struct fcoe_task_context *ctx = task_params->context; + struct ystorm_fcoe_task_st_ctx *y_st_ctx; + struct tstorm_fcoe_task_st_ctx *t_st_ctx; + struct ustorm_fcoe_task_ag_ctx *u_ag_ctx; + struct mstorm_fcoe_task_st_ctx *m_st_ctx; + u32 val; + + memset(ctx, 0, sizeof(*(ctx))); + + /* Init Ystorm */ + y_st_ctx = &ctx->ystorm_st_context; + init_scsi_sgl_context(&y_st_ctx->sgl_params, + &y_st_ctx->data_desc, + tx_sgl_task_params); + SET_FIELD(y_st_ctx->sgl_mode, + YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, SCSI_FAST_SGL); + y_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->tx_io_size); + y_st_ctx->task_type = task_params->task_type; + memcpy(&y_st_ctx->tx_info_union.tx_params.mid_path, + mid_path_fc_header, sizeof(struct fcoe_tx_mid_path_params)); + + /* Init Mstorm */ + m_st_ctx = &ctx->mstorm_st_context; + init_scsi_sgl_context(&m_st_ctx->sgl_params, + &m_st_ctx->data_desc, + rx_sgl_task_params); + SET_FIELD(m_st_ctx->flags, + MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER, + fw_to_place_fc_header); + m_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->rx_io_size); + + /* Init Tstorm */ + t_st_ctx = &ctx->tstorm_st_context; + t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid); + val = cpu_to_le32(task_params->cq_rss_number); + t_st_ctx->read_only.glbl_q_num = val; + t_st_ctx->read_only.task_type = task_params->task_type; + SET_FIELD(t_st_ctx->read_write.flags, + FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1); + t_st_ctx->read_write.rx_id = cpu_to_le32(FCOE_RX_ID); + + /* Init Ustorm */ + u_ag_ctx = &ctx->ustorm_ag_context; + u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number); + + /* Init SQE */ + init_common_sqe(task_params, SEND_FCOE_MIDPATH); + task_params->sqe->additional_info_union.burst_length = + tx_sgl_task_params->total_buffer_size; + SET_FIELD(task_params->sqe->flags, + FCOE_WQE_NUM_SGES, tx_sgl_task_params->num_sges); + SET_FIELD(task_params->sqe->flags, FCOE_WQE_SGL_MODE, + SCSI_FAST_SGL); + + return 0; +} + +int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params) +{ + init_common_sqe(task_params, SEND_FCOE_ABTS_REQUEST); + return 0; +} + +int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params) +{ + init_common_sqe(task_params, FCOE_EXCHANGE_CLEANUP); + return 0; +} + +int init_initiator_sequence_recovery_fcoe_task( + struct fcoe_task_params *task_params, u32 off) +{ + init_common_sqe(task_params, FCOE_SEQUENCE_RECOVERY); + task_params->sqe->additional_info_union.seq_rec_updated_offset = off; + return 0; +} diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.h b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h new file mode 100644 index 000000000000..617529b058f4 --- /dev/null +++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h @@ -0,0 +1,93 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#ifndef _FCOE_FW_FUNCS_H +#define _FCOE_FW_FUNCS_H +#include "drv_scsi_fw_funcs.h" +#include "qedf_hsi.h" +#include + +struct fcoe_task_params { + /* Output parameter [set/filled by the HSI function] */ + struct fcoe_task_context *context; + + /* Output parameter [set/filled by the HSI function] */ + struct fcoe_wqe *sqe; + enum fcoe_task_type task_type; + u32 tx_io_size; /* in bytes */ + u32 rx_io_size; /* in bytes */ + u32 conn_cid; + u16 itid; + u8 cq_rss_number; + + /* Whether it's Tape device or not (0=Disk, 1=Tape) */ + u8 is_tape_device; +}; + +/** + * @brief init_initiator_rw_fcoe_task - Initializes FCoE task context for + * read/write task types and init fcoe_sqe + * + * @param task_params - Pointer to task parameters struct + * @param sgl_task_params - Pointer to SGL task params + * @param sense_data_buffer_phys_addr - Pointer to sense data buffer + * @param task_retry_id - retry identification - Used only for Tape device + * @param fcp_cmnd_payload - FCP CMD Payload + */ +int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params, + struct scsi_sgl_task_params *sgl_task_params, + struct regpair sense_data_buffer_phys_addr, + u32 task_retry_id, + u8 fcp_cmd_payload[32]); + +/** + * @brief init_initiator_midpath_fcoe_task - Initializes FCoE task context for + * midpath/unsolicited task types and init fcoe_sqe + * + * @param task_params - Pointer to task parameters struct + * @param mid_path_fc_header - FC header + * @param tx_sgl_task_params - Pointer to Tx SGL task params + * @param rx_sgl_task_params - Pointer to Rx SGL task params + * @param fw_to_place_fc_header - Indication if the FW will place the FC header + * in addition to the data arrives. + */ +int init_initiator_midpath_unsolicited_fcoe_task( + struct fcoe_task_params *task_params, + struct fcoe_tx_mid_path_params *mid_path_fc_header, + struct scsi_sgl_task_params *tx_sgl_task_params, + struct scsi_sgl_task_params *rx_sgl_task_params, + u8 fw_to_place_fc_header); + +/** + * @brief init_initiator_abort_fcoe_task - Initializes FCoE task context for + * abort task types and init fcoe_sqe + * + * @param task_params - Pointer to task parameters struct + */ +int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params); + +/** + * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for + * cleanup task types and init fcoe_sqe + * + * + * @param task_params - Pointer to task parameters struct + */ +int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params); + +/** + * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for + * sequence recovery task types and init fcoe_sqe + * + * + * @param task_params - Pointer to task parameters struct + * @param desired_offset - The desired offest the task will be re-sent from + */ +int init_initiator_sequence_recovery_fcoe_task( + struct fcoe_task_params *task_params, + u32 desired_offset); +#endif diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.c b/drivers/scsi/qedf/drv_scsi_fw_funcs.c new file mode 100644 index 000000000000..11e0cc082ec0 --- /dev/null +++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.c @@ -0,0 +1,44 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#include "drv_scsi_fw_funcs.h" + +#define SCSI_NUM_SGES_IN_CACHE 0x4 + +bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge) +{ + return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge); +} + +void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct scsi_sgl_task_params *sgl_task_params) +{ + /* no need to check for sgl_task_params->sgl validity */ + u8 num_sges_to_init = sgl_task_params->num_sges > + SCSI_NUM_SGES_IN_CACHE ? SCSI_NUM_SGES_IN_CACHE : + sgl_task_params->num_sges; + u8 sge_index; + u32 val; + + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo); + ctx_sgl_params->sgl_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi); + ctx_sgl_params->sgl_addr.hi = val; + val = cpu_to_le32(sgl_task_params->total_buffer_size); + ctx_sgl_params->sgl_total_length = val; + ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges); + + for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) { + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo); + ctx_data_desc->sge[sge_index].sge_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi); + ctx_data_desc->sge[sge_index].sge_addr.hi = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len); + ctx_data_desc->sge[sge_index].sge_len = val; + } +} diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.h b/drivers/scsi/qedf/drv_scsi_fw_funcs.h new file mode 100644 index 000000000000..9cb45410bc45 --- /dev/null +++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.h @@ -0,0 +1,85 @@ +/* QLogic FCoE Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ +#ifndef _SCSI_FW_FUNCS_H +#define _SCSI_FW_FUNCS_H +#include +#include +#include + +struct scsi_sgl_task_params { + struct scsi_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + + /* true if SGL contains a small (< 4KB) SGE in middle(not 1st or last) + * -> relevant for tx only + */ + bool small_mid_sge; +}; + +struct scsi_dif_task_params { + u32 initial_ref_tag; + bool initial_ref_tag_is_valid; + u16 application_tag; + u16 application_tag_mask; + u16 dif_block_size_log; + bool dif_on_network; + bool dif_on_host; + u8 host_guard_type; + u8 protection_type; + u8 ref_tag_mask; + bool crc_seed; + + /* Enable Connection error upon DIF error (segments with DIF errors are + * dropped) + */ + bool tx_dif_conn_err_en; + bool ignore_app_tag; + bool keep_ref_tag_const; + bool validate_guard; + bool validate_app_tag; + bool validate_ref_tag; + bool forward_guard; + bool forward_app_tag; + bool forward_ref_tag; + bool forward_app_tag_with_mask; + bool forward_ref_tag_with_mask; +}; + +struct scsi_initiator_cmd_params { + /* for cdb_size > default CDB size (extended CDB > 16 bytes) -> + * pointer to the CDB buffer SGE + */ + struct scsi_sge extended_cdb_sge; + + /* Physical address of sense data buffer for sense data - 256B buffer */ + struct regpair sense_data_buffer_phys_addr; +}; + +/** + * @brief scsi_is_slow_sgl - checks for slow SGL + * + * @param num_sges - number of sges in SGL + * @param small_mid_sge - True is the SGL contains an SGE which is smaller than + * 4KB and its not the 1st or last SGE in the SGL + */ +bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge); + +/** + * @brief init_scsi_sgl_context - initializes SGL task context + * + * @param sgl_params - SGL context parameters to initialize (output parameter) + * @param data_desc - context struct containing SGEs array to set (output + * parameter) + * @param sgl_task_params - SGL parameters (input) + */ +void init_scsi_sgl_context(struct scsi_sgl_params *sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct scsi_sgl_task_params *sgl_task_params); +#endif diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h index 96346a1b1515..40aeb6bb96a2 100644 --- a/drivers/scsi/qedf/qedf.h +++ b/drivers/scsi/qedf/qedf.h @@ -26,6 +26,7 @@ #include #include "qedf_version.h" #include "qedf_dbg.h" +#include "drv_fcoe_fw_funcs.h" /* Helpers to extract upper and lower 32-bits of pointer */ #define U64_HI(val) ((u32)(((u64)(val)) >> 32)) @@ -59,19 +60,17 @@ #define UPSTREAM_KEEP 1 struct qedf_mp_req { - uint8_t tm_flags; - uint32_t req_len; void *req_buf; dma_addr_t req_buf_dma; - struct fcoe_sge *mp_req_bd; + struct scsi_sge *mp_req_bd; dma_addr_t mp_req_bd_dma; struct fc_frame_header req_fc_hdr; uint32_t resp_len; void *resp_buf; dma_addr_t resp_buf_dma; - struct fcoe_sge *mp_resp_bd; + struct scsi_sge *mp_resp_bd; dma_addr_t mp_resp_bd_dma; struct fc_frame_header resp_fc_hdr; }; @@ -119,6 +118,7 @@ struct qedf_ioreq { #define QEDF_CMD_IN_CLEANUP 0x2 #define QEDF_CMD_SRR_SENT 0x3 u8 io_req_flags; + uint8_t tm_flags; struct qedf_rport *fcport; unsigned long flags; enum qedf_ioreq_event event; @@ -130,6 +130,8 @@ struct qedf_ioreq { struct completion tm_done; struct completion abts_done; struct fcoe_task_context *task; + struct fcoe_task_params *task_params; + struct scsi_sgl_task_params *sgl_task_params; int idx; /* * Need to allocate enough room for both sense data and FCP response data @@ -199,8 +201,8 @@ struct qedf_rport { dma_addr_t sq_pbl_dma; u32 sq_pbl_size; u32 sid; -#define QEDF_RPORT_TYPE_DISK 1 -#define QEDF_RPORT_TYPE_TAPE 2 +#define QEDF_RPORT_TYPE_DISK 0 +#define QEDF_RPORT_TYPE_TAPE 1 uint dev_type; /* Disk or tape */ struct list_head peers; }; @@ -391,7 +393,7 @@ struct qedf_ctx { struct io_bdt { struct qedf_ioreq *io_req; - struct fcoe_sge *bd_tbl; + struct scsi_sge *bd_tbl; dma_addr_t bd_tbl_dma; u16 bd_valid; }; @@ -400,7 +402,7 @@ struct qedf_cmd_mgr { struct qedf_ctx *qedf; u16 idx; struct io_bdt **io_bdt_pool; -#define FCOE_PARAMS_NUM_TASKS 4096 +#define FCOE_PARAMS_NUM_TASKS 2048 struct qedf_ioreq cmds[FCOE_PARAMS_NUM_TASKS]; spinlock_t lock; atomic_t free_list_cnt; @@ -465,9 +467,8 @@ extern void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req, unsigned int timer_msec); extern int qedf_init_mp_req(struct qedf_ioreq *io_req); extern void qedf_init_mp_task(struct qedf_ioreq *io_req, - struct fcoe_task_context *task_ctx); -extern void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, - u32 ptu_invalidate, enum fcoe_task_type req_type, u32 offset); + struct fcoe_task_context *task_ctx, struct fcoe_wqe *wqe); +extern u16 qedf_get_sqe_idx(struct qedf_rport *fcport); extern void qedf_ring_doorbell(struct qedf_rport *fcport); extern void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, struct qedf_ioreq *els_req); diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c index 59f3e5c73a13..c505d41f6dc8 100644 --- a/drivers/scsi/qedf/qedf_els.c +++ b/drivers/scsi/qedf/qedf_els.c @@ -25,6 +25,9 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op, uint16_t xid; uint32_t start_time = jiffies / HZ; uint32_t current_time; + struct fcoe_wqe *sqe; + unsigned long flags; + u16 sqe_idx; QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending ELS\n"); @@ -113,20 +116,25 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op, /* Obtain exchange id */ xid = els_req->xid; + spin_lock_irqsave(&fcport->rport_lock, flags); + + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + /* Initialize task context for this IO request */ task = qedf_get_task_mem(&qedf->tasks, xid); - qedf_init_mp_task(els_req, task); + qedf_init_mp_task(els_req, task, sqe); /* Put timer on original I/O request */ if (timer_msec) qedf_cmd_timer_set(qedf, els_req, timer_msec); - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0); - /* Ring doorbell */ QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Ringing doorbell for ELS " "req\n"); qedf_ring_doorbell(fcport); + spin_unlock_irqrestore(&fcport->rport_lock, flags); els_err: return rc; } @@ -604,6 +612,8 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req, struct qedf_rport *fcport; unsigned long flags; struct qedf_els_cb_arg *cb_arg; + struct fcoe_wqe *sqe; + u16 sqe_idx; fcport = orig_io_req->fcport; @@ -631,8 +641,13 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req, spin_lock_irqsave(&fcport->rport_lock, flags); - qedf_add_to_sq(fcport, orig_io_req->xid, 0, - FCOE_TASK_TYPE_SEQUENCE_CLEANUP, offset); + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + orig_io_req->task_params->sqe = sqe; + + init_initiator_sequence_recovery_fcoe_task(orig_io_req->task_params, + offset); qedf_ring_doorbell(fcport); spin_unlock_irqrestore(&fcport->rport_lock, flags); diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index ee0dcf9d3aba..af2294635ab2 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -96,7 +96,7 @@ void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr) if (!cmgr->io_bdt_pool) goto free_cmd_pool; - bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge); + bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge); for (i = 0; i < num_ios; i++) { bdt_info = cmgr->io_bdt_pool[i]; if (bdt_info->bd_tbl) { @@ -119,6 +119,8 @@ void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr) for (i = 0; i < num_ios; i++) { io_req = &cmgr->cmds[i]; + kfree(io_req->sgl_task_params); + kfree(io_req->task_params); /* Make sure we free per command sense buffer */ if (io_req->sense_buffer) dma_free_coherent(&qedf->pdev->dev, @@ -178,7 +180,7 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) spin_lock_init(&cmgr->lock); /* - * Initialize list of qedf_ioreq. + * Initialize I/O request fields. */ xid = QEDF_MIN_XID; @@ -196,6 +198,29 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) GFP_KERNEL); if (!io_req->sense_buffer) goto mem_err; + + /* Allocate task parameters to pass to f/w init funcions */ + io_req->task_params = kzalloc(sizeof(*io_req->task_params), + GFP_KERNEL); + if (!io_req->task_params) { + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to allocate task_params for xid=0x%x\n", + i); + goto mem_err; + } + + /* + * Allocate scatter/gather list info to pass to f/w init + * functions. + */ + io_req->sgl_task_params = kzalloc( + sizeof(struct scsi_sgl_task_params), GFP_KERNEL); + if (!io_req->sgl_task_params) { + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to allocate sgl_task_params for xid=0x%x\n", + i); + goto mem_err; + } } /* Allocate pool of io_bdts - one for each qedf_ioreq */ @@ -211,8 +236,8 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) cmgr->io_bdt_pool[i] = kmalloc(sizeof(struct io_bdt), GFP_KERNEL); if (!cmgr->io_bdt_pool[i]) { - QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc " - "io_bdt_pool[%d].\n", i); + QEDF_WARN(&(qedf->dbg_ctx), + "Failed to alloc io_bdt_pool[%d].\n", i); goto mem_err; } } @@ -220,11 +245,11 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf) for (i = 0; i < num_ios; i++) { bdt_info = cmgr->io_bdt_pool[i]; bdt_info->bd_tbl = dma_alloc_coherent(&qedf->pdev->dev, - QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge), + QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge), &bdt_info->bd_tbl_dma, GFP_KERNEL); if (!bdt_info->bd_tbl) { - QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc " - "bdt_tbl[%d].\n", i); + QEDF_WARN(&(qedf->dbg_ctx), + "Failed to alloc bdt_tbl[%d].\n", i); goto mem_err; } } @@ -318,6 +343,7 @@ struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type) } bd_tbl->io_req = io_req; io_req->cmd_type = cmd_type; + io_req->tm_flags = 0; /* Reset sequence offset data */ io_req->rx_buf_off = 0; @@ -336,10 +362,9 @@ static void qedf_free_mp_resc(struct qedf_ioreq *io_req) { struct qedf_mp_req *mp_req = &(io_req->mp_req); struct qedf_ctx *qedf = io_req->fcport->qedf; - uint64_t sz = sizeof(struct fcoe_sge); + uint64_t sz = sizeof(struct scsi_sge); /* clear tm flags */ - mp_req->tm_flags = 0; if (mp_req->mp_req_bd) { dma_free_coherent(&qedf->pdev->dev, sz, mp_req->mp_req_bd, mp_req->mp_req_bd_dma); @@ -387,7 +412,7 @@ void qedf_release_cmd(struct kref *ref) static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len, int bd_index) { - struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl; + struct scsi_sge *bd = io_req->bd_tbl->bd_tbl; int frag_size, sg_frags; sg_frags = 0; @@ -398,7 +423,7 @@ static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len, frag_size = sg_len; bd[bd_index + sg_frags].sge_addr.lo = U64_LO(addr); bd[bd_index + sg_frags].sge_addr.hi = U64_HI(addr); - bd[bd_index + sg_frags].size = (uint16_t)frag_size; + bd[bd_index + sg_frags].sge_len = (uint16_t)frag_size; addr += (u64)frag_size; sg_frags++; @@ -413,7 +438,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) struct Scsi_Host *host = sc->device->host; struct fc_lport *lport = shost_priv(host); struct qedf_ctx *qedf = lport_priv(lport); - struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl; + struct scsi_sge *bd = io_req->bd_tbl->bd_tbl; struct scatterlist *sg; int byte_count = 0; int sg_count = 0; @@ -439,7 +464,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) bd[bd_count].sge_addr.lo = (addr & 0xffffffff); bd[bd_count].sge_addr.hi = (addr >> 32); - bd[bd_count].size = (u16)sg_len; + bd[bd_count].sge_len = (u16)sg_len; return ++bd_count; } @@ -480,7 +505,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) sg_frags = 1; bd[bd_count].sge_addr.lo = U64_LO(addr); bd[bd_count].sge_addr.hi = U64_HI(addr); - bd[bd_count].size = (uint16_t)sg_len; + bd[bd_count].sge_len = (uint16_t)sg_len; } bd_count += sg_frags; @@ -498,7 +523,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req) static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req) { struct scsi_cmnd *sc = io_req->sc_cmd; - struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl; + struct scsi_sge *bd = io_req->bd_tbl->bd_tbl; int bd_count; if (scsi_sg_count(sc)) { @@ -508,7 +533,7 @@ static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req) } else { bd_count = 0; bd[0].sge_addr.lo = bd[0].sge_addr.hi = 0; - bd[0].size = 0; + bd[0].sge_len = 0; } io_req->bd_tbl->bd_valid = bd_count; @@ -529,430 +554,223 @@ static void qedf_build_fcp_cmnd(struct qedf_ioreq *io_req, /* 4 bytes: flag info */ fcp_cmnd->fc_pri_ta = 0; - fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags; + fcp_cmnd->fc_tm_flags = io_req->tm_flags; fcp_cmnd->fc_flags = io_req->io_req_flags; fcp_cmnd->fc_cmdref = 0; /* Populate data direction */ - if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) - fcp_cmnd->fc_flags |= FCP_CFL_WRDATA; - else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) + if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) { fcp_cmnd->fc_flags |= FCP_CFL_RDDATA; + } else { + if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) + fcp_cmnd->fc_flags |= FCP_CFL_WRDATA; + else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) + fcp_cmnd->fc_flags |= FCP_CFL_RDDATA; + } fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE; /* 16 bytes: CDB information */ - memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len); + if (io_req->cmd_type != QEDF_TASK_MGMT_CMD) + memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len); /* 4 bytes: FCP data length */ fcp_cmnd->fc_dl = htonl(io_req->data_xfer_len); - } static void qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport, - struct qedf_ioreq *io_req, u32 *ptu_invalidate, - struct fcoe_task_context *task_ctx) + struct qedf_ioreq *io_req, struct fcoe_task_context *task_ctx, + struct fcoe_wqe *sqe) { enum fcoe_task_type task_type; struct scsi_cmnd *sc_cmd = io_req->sc_cmd; struct io_bdt *bd_tbl = io_req->bd_tbl; - union fcoe_data_desc_ctx *data_desc; - u32 *fcp_cmnd; + u8 fcp_cmnd[32]; u32 tmp_fcp_cmnd[8]; - int cnt, i; - int bd_count; + int bd_count = 0; struct qedf_ctx *qedf = fcport->qedf; uint16_t cq_idx = smp_processor_id() % qedf->num_queues; - u8 tmp_sgl_mode = 0; - u8 mst_sgl_mode = 0; + struct regpair sense_data_buffer_phys_addr; + u32 tx_io_size = 0; + u32 rx_io_size = 0; + int i, cnt; - memset(task_ctx, 0, sizeof(struct fcoe_task_context)); + /* Note init_initiator_rw_fcoe_task memsets the task context */ io_req->task = task_ctx; + memset(task_ctx, 0, sizeof(struct fcoe_task_context)); + memset(io_req->task_params, 0, sizeof(struct fcoe_task_params)); + memset(io_req->sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); - if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) - task_type = FCOE_TASK_TYPE_WRITE_INITIATOR; - else + /* Set task type bassed on DMA directio of command */ + if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) { task_type = FCOE_TASK_TYPE_READ_INITIATOR; - - /* Y Storm context */ - task_ctx->ystorm_st_context.expect_first_xfer = 1; - task_ctx->ystorm_st_context.data_2_trns_rem = io_req->data_xfer_len; - /* Check if this is required */ - task_ctx->ystorm_st_context.ox_id = io_req->xid; - task_ctx->ystorm_st_context.task_rety_identifier = - io_req->task_retry_identifier; - - /* T Storm ag context */ - SET_FIELD(task_ctx->tstorm_ag_context.flags0, - TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, PROTOCOLID_FCOE); - task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid; - - /* T Storm st context */ - SET_FIELD(task_ctx->tstorm_st_context.read_write.flags, - FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, - 1); - task_ctx->tstorm_st_context.read_write.rx_id = 0xffff; - - task_ctx->tstorm_st_context.read_only.dev_type = - FCOE_TASK_DEV_TYPE_DISK; - task_ctx->tstorm_st_context.read_only.conf_supported = 0; - task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid; - - /* Completion queue for response. */ - task_ctx->tstorm_st_context.read_only.glbl_q_num = cq_idx; - task_ctx->tstorm_st_context.read_only.fcp_cmd_trns_size = - io_req->data_xfer_len; - task_ctx->tstorm_st_context.read_write.e_d_tov_exp_timeout_val = - lport->e_d_tov; - - task_ctx->ustorm_ag_context.global_cq_num = cq_idx; - io_req->fp_idx = cq_idx; - - bd_count = bd_tbl->bd_valid; - if (task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) { - /* Setup WRITE task */ - struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl; - - task_ctx->ystorm_st_context.task_type = - FCOE_TASK_TYPE_WRITE_INITIATOR; - data_desc = &task_ctx->ystorm_st_context.data_desc; - - if (io_req->use_slowpath) { - SET_FIELD(task_ctx->ystorm_st_context.sgl_mode, - YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, - FCOE_SLOW_SGL); - data_desc->slow.base_sgl_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->slow.remainder_num_sges = bd_count; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - qedf->slow_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SLOW_SGE; - } else { - SET_FIELD(task_ctx->ystorm_st_context.sgl_mode, - YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, - (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count : - FCOE_MUL_FAST_SGES); - - if (bd_count == 1) { - data_desc->single_sge.sge_addr.lo = - fcoe_bd_tbl->sge_addr.lo; - data_desc->single_sge.sge_addr.hi = - fcoe_bd_tbl->sge_addr.hi; - data_desc->single_sge.size = - fcoe_bd_tbl->size; - data_desc->single_sge.is_valid_sge = 0; - qedf->single_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SINGLE_SGE; - } else { - data_desc->fast.sgl_start_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_start_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_byte_offset = - data_desc->fast.sgl_start_addr.lo & - (QEDF_PAGE_SIZE - 1); - if (data_desc->fast.sgl_byte_offset > 0) - QEDF_ERR(&(qedf->dbg_ctx), - "byte_offset=%u for xid=0x%x.\n", - io_req->xid, - data_desc->fast.sgl_byte_offset); - data_desc->fast.task_reuse_cnt = - io_req->reuse_count; - io_req->reuse_count++; - if (io_req->reuse_count == QEDF_MAX_REUSE) { - *ptu_invalidate = 1; - io_req->reuse_count = 0; - } - qedf->fast_sge_ios++; - io_req->sge_type = QEDF_IOREQ_FAST_SGE; - } - } - - /* T Storm context */ - task_ctx->tstorm_st_context.read_only.task_type = - FCOE_TASK_TYPE_WRITE_INITIATOR; - - /* M Storm context */ - tmp_sgl_mode = GET_FIELD(task_ctx->ystorm_st_context.sgl_mode, - YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE); - SET_FIELD(task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE, - tmp_sgl_mode); - } else { - /* Setup READ task */ - - /* M Storm context */ - struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl; - - data_desc = &task_ctx->mstorm_st_context.fp.data_desc; - task_ctx->mstorm_st_context.fp.data_2_trns_rem = - io_req->data_xfer_len; - - if (io_req->use_slowpath) { - SET_FIELD( - task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE, - FCOE_SLOW_SGL); - data_desc->slow.base_sgl_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->slow.remainder_num_sges = - bd_count; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - qedf->slow_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SLOW_SGE; + if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) { + task_type = FCOE_TASK_TYPE_WRITE_INITIATOR; + tx_io_size = io_req->data_xfer_len; } else { - SET_FIELD( - task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE, - (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count : - FCOE_MUL_FAST_SGES); - - if (bd_count == 1) { - data_desc->single_sge.sge_addr.lo = - fcoe_bd_tbl->sge_addr.lo; - data_desc->single_sge.sge_addr.hi = - fcoe_bd_tbl->sge_addr.hi; - data_desc->single_sge.size = - fcoe_bd_tbl->size; - data_desc->single_sge.is_valid_sge = 0; - qedf->single_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SINGLE_SGE; - } else { - data_desc->fast.sgl_start_addr.lo = - U64_LO(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_start_addr.hi = - U64_HI(bd_tbl->bd_tbl_dma); - data_desc->fast.sgl_byte_offset = 0; - data_desc->fast.task_reuse_cnt = - io_req->reuse_count; - io_req->reuse_count++; - if (io_req->reuse_count == QEDF_MAX_REUSE) { - *ptu_invalidate = 1; - io_req->reuse_count = 0; - } - qedf->fast_sge_ios++; - io_req->sge_type = QEDF_IOREQ_FAST_SGE; - } + task_type = FCOE_TASK_TYPE_READ_INITIATOR; + rx_io_size = io_req->data_xfer_len; } - - /* Y Storm context */ - task_ctx->ystorm_st_context.expect_first_xfer = 0; - task_ctx->ystorm_st_context.task_type = - FCOE_TASK_TYPE_READ_INITIATOR; - - /* T Storm context */ - task_ctx->tstorm_st_context.read_only.task_type = - FCOE_TASK_TYPE_READ_INITIATOR; - mst_sgl_mode = GET_FIELD( - task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode, - FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE); - SET_FIELD(task_ctx->tstorm_st_context.read_write.flags, - FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE, - mst_sgl_mode); } + /* Setup the fields for fcoe_task_params */ + io_req->task_params->context = task_ctx; + io_req->task_params->sqe = sqe; + io_req->task_params->task_type = task_type; + io_req->task_params->tx_io_size = tx_io_size; + io_req->task_params->rx_io_size = rx_io_size; + io_req->task_params->conn_cid = fcport->fw_cid; + io_req->task_params->itid = io_req->xid; + io_req->task_params->cq_rss_number = cq_idx; + io_req->task_params->is_tape_device = fcport->dev_type; + + /* Fill in information for scatter/gather list */ + if (io_req->cmd_type != QEDF_TASK_MGMT_CMD) { + bd_count = bd_tbl->bd_valid; + io_req->sgl_task_params->sgl = bd_tbl->bd_tbl; + io_req->sgl_task_params->sgl_phys_addr.lo = + U64_LO(bd_tbl->bd_tbl_dma); + io_req->sgl_task_params->sgl_phys_addr.hi = + U64_HI(bd_tbl->bd_tbl_dma); + io_req->sgl_task_params->num_sges = bd_count; + io_req->sgl_task_params->total_buffer_size = + scsi_bufflen(io_req->sc_cmd); + io_req->sgl_task_params->small_mid_sge = + io_req->use_slowpath; + } + + /* Fill in physical address of sense buffer */ + sense_data_buffer_phys_addr.lo = U64_LO(io_req->sense_buffer_dma); + sense_data_buffer_phys_addr.hi = U64_HI(io_req->sense_buffer_dma); + /* fill FCP_CMND IU */ - fcp_cmnd = (u32 *)task_ctx->ystorm_st_context.tx_info_union.fcp_cmd_payload.opaque; - qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)&tmp_fcp_cmnd); + qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tmp_fcp_cmnd); /* Swap fcp_cmnd since FC is big endian */ cnt = sizeof(struct fcp_cmnd) / sizeof(u32); - for (i = 0; i < cnt; i++) { - *fcp_cmnd = cpu_to_be32(tmp_fcp_cmnd[i]); - fcp_cmnd++; + tmp_fcp_cmnd[i] = cpu_to_be32(tmp_fcp_cmnd[i]); } + memcpy(fcp_cmnd, tmp_fcp_cmnd, sizeof(struct fcp_cmnd)); - /* M Storm context - Sense buffer */ - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo = - U64_LO(io_req->sense_buffer_dma); - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi = - U64_HI(io_req->sense_buffer_dma); + init_initiator_rw_fcoe_task(io_req->task_params, + io_req->sgl_task_params, + sense_data_buffer_phys_addr, + io_req->task_retry_identifier, fcp_cmnd); + + /* Increment SGL type counters */ + if (bd_count == 1) { + qedf->single_sge_ios++; + io_req->sge_type = QEDF_IOREQ_SINGLE_SGE; + } else if (io_req->use_slowpath) { + qedf->slow_sge_ios++; + io_req->sge_type = QEDF_IOREQ_SLOW_SGE; + } else { + qedf->fast_sge_ios++; + io_req->sge_type = QEDF_IOREQ_FAST_SGE; + } } void qedf_init_mp_task(struct qedf_ioreq *io_req, - struct fcoe_task_context *task_ctx) + struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe) { struct qedf_mp_req *mp_req = &(io_req->mp_req); struct qedf_rport *fcport = io_req->fcport; struct qedf_ctx *qedf = io_req->fcport->qedf; struct fc_frame_header *fc_hdr; - enum fcoe_task_type task_type = 0; - union fcoe_data_desc_ctx *data_desc; + struct fcoe_tx_mid_path_params task_fc_hdr; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; - QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Initializing MP task " - "for cmd_type = %d\n", io_req->cmd_type); + QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, + "Initializing MP task for cmd_type=%d\n", + io_req->cmd_type); qedf->control_requests++; - /* Obtain task_type */ - if ((io_req->cmd_type == QEDF_TASK_MGMT_CMD) || - (io_req->cmd_type == QEDF_ELS)) { - task_type = FCOE_TASK_TYPE_MIDPATH; - } else if (io_req->cmd_type == QEDF_ABTS) { - task_type = FCOE_TASK_TYPE_ABTS; - } - + memset(&tx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); memset(task_ctx, 0, sizeof(struct fcoe_task_context)); + memset(&task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params)); /* Setup the task from io_req for easy reference */ io_req->task = task_ctx; - QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "task type = %d\n", - task_type); + /* Setup the fields for fcoe_task_params */ + io_req->task_params->context = task_ctx; + io_req->task_params->sqe = sqe; + io_req->task_params->task_type = FCOE_TASK_TYPE_MIDPATH; + io_req->task_params->tx_io_size = io_req->data_xfer_len; + /* rx_io_size tells the f/w how large a response buffer we have */ + io_req->task_params->rx_io_size = PAGE_SIZE; + io_req->task_params->conn_cid = fcport->fw_cid; + io_req->task_params->itid = io_req->xid; + /* Return middle path commands on CQ 0 */ + io_req->task_params->cq_rss_number = 0; + io_req->task_params->is_tape_device = fcport->dev_type; - /* YSTORM only */ - { - /* Initialize YSTORM task context */ - struct fcoe_tx_mid_path_params *task_fc_hdr = - &task_ctx->ystorm_st_context.tx_info_union.tx_params.mid_path; - memset(task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params)); - task_ctx->ystorm_st_context.task_rety_identifier = - io_req->task_retry_identifier; + fc_hdr = &(mp_req->req_fc_hdr); + /* Set OX_ID and RX_ID based on driver task id */ + fc_hdr->fh_ox_id = io_req->xid; + fc_hdr->fh_rx_id = htons(0xffff); - /* Init SGL parameters */ - if ((task_type == FCOE_TASK_TYPE_MIDPATH) || - (task_type == FCOE_TASK_TYPE_UNSOLICITED)) { - data_desc = &task_ctx->ystorm_st_context.data_desc; - data_desc->slow.base_sgl_addr.lo = - U64_LO(mp_req->mp_req_bd_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(mp_req->mp_req_bd_dma); - data_desc->slow.remainder_num_sges = 1; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - } + /* Set up FC header information */ + task_fc_hdr.parameter = fc_hdr->fh_parm_offset; + task_fc_hdr.r_ctl = fc_hdr->fh_r_ctl; + task_fc_hdr.type = fc_hdr->fh_type; + task_fc_hdr.cs_ctl = fc_hdr->fh_cs_ctl; + task_fc_hdr.df_ctl = fc_hdr->fh_df_ctl; + task_fc_hdr.rx_id = fc_hdr->fh_rx_id; + task_fc_hdr.ox_id = fc_hdr->fh_ox_id; - fc_hdr = &(mp_req->req_fc_hdr); - if (task_type == FCOE_TASK_TYPE_MIDPATH) { - fc_hdr->fh_ox_id = io_req->xid; - fc_hdr->fh_rx_id = htons(0xffff); - } else if (task_type == FCOE_TASK_TYPE_UNSOLICITED) { - fc_hdr->fh_rx_id = io_req->xid; - } + /* Set up s/g list parameters for request buffer */ + tx_sgl_task_params.sgl = mp_req->mp_req_bd; + tx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_req_bd_dma); + tx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_req_bd_dma); + tx_sgl_task_params.num_sges = 1; + /* Set PAGE_SIZE for now since sg element is that size ??? */ + tx_sgl_task_params.total_buffer_size = io_req->data_xfer_len; + tx_sgl_task_params.small_mid_sge = 0; - /* Fill FC Header into middle path buffer */ - task_fc_hdr->parameter = fc_hdr->fh_parm_offset; - task_fc_hdr->r_ctl = fc_hdr->fh_r_ctl; - task_fc_hdr->type = fc_hdr->fh_type; - task_fc_hdr->cs_ctl = fc_hdr->fh_cs_ctl; - task_fc_hdr->df_ctl = fc_hdr->fh_df_ctl; - task_fc_hdr->rx_id = fc_hdr->fh_rx_id; - task_fc_hdr->ox_id = fc_hdr->fh_ox_id; + /* Set up s/g list parameters for request buffer */ + rx_sgl_task_params.sgl = mp_req->mp_resp_bd; + rx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_resp_bd_dma); + rx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_resp_bd_dma); + rx_sgl_task_params.num_sges = 1; + /* Set PAGE_SIZE for now since sg element is that size ??? */ + rx_sgl_task_params.total_buffer_size = PAGE_SIZE; + rx_sgl_task_params.small_mid_sge = 0; - task_ctx->ystorm_st_context.data_2_trns_rem = - io_req->data_xfer_len; - task_ctx->ystorm_st_context.task_type = task_type; - } - /* TSTORM ONLY */ - { - task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid; - task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid; - /* Always send middle-path repsonses on CQ #0 */ - task_ctx->tstorm_st_context.read_only.glbl_q_num = 0; - io_req->fp_idx = 0; - SET_FIELD(task_ctx->tstorm_ag_context.flags0, - TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, - PROTOCOLID_FCOE); - task_ctx->tstorm_st_context.read_only.task_type = task_type; - SET_FIELD(task_ctx->tstorm_st_context.read_write.flags, - FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, - 1); - task_ctx->tstorm_st_context.read_write.rx_id = 0xffff; - } + /* + * Last arg is 0 as previous code did not set that we wanted the + * fc header information. + */ + init_initiator_midpath_unsolicited_fcoe_task(io_req->task_params, + &task_fc_hdr, + &tx_sgl_task_params, + &rx_sgl_task_params, 0); - /* MSTORM only */ - { - if (task_type == FCOE_TASK_TYPE_MIDPATH) { - /* Initialize task context */ - data_desc = &task_ctx->mstorm_st_context.fp.data_desc; - - /* Set cache sges address and length */ - data_desc->slow.base_sgl_addr.lo = - U64_LO(mp_req->mp_resp_bd_dma); - data_desc->slow.base_sgl_addr.hi = - U64_HI(mp_req->mp_resp_bd_dma); - data_desc->slow.remainder_num_sges = 1; - data_desc->slow.curr_sge_off = 0; - data_desc->slow.curr_sgl_index = 0; - - /* - * Also need to fil in non-fastpath response address - * for middle path commands. - */ - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo = - U64_LO(mp_req->mp_resp_bd_dma); - task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi = - U64_HI(mp_req->mp_resp_bd_dma); - } - } - - /* USTORM ONLY */ - { - task_ctx->ustorm_ag_context.global_cq_num = 0; - } - - /* I/O stats. Middle path commands always use slow SGEs */ - qedf->slow_sge_ios++; - io_req->sge_type = QEDF_IOREQ_SLOW_SGE; + /* Midpath requests always consume 1 SGE */ + qedf->single_sge_ios++; } -void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, u32 ptu_invalidate, - enum fcoe_task_type req_type, u32 offset) +/* Presumed that fcport->rport_lock is held */ +u16 qedf_get_sqe_idx(struct qedf_rport *fcport) { - struct fcoe_wqe *sqe; uint16_t total_sqe = (fcport->sq_mem_size)/(sizeof(struct fcoe_wqe)); + u16 rval; - sqe = &fcport->sq[fcport->sq_prod_idx]; + rval = fcport->sq_prod_idx; + /* Adjust ring index */ fcport->sq_prod_idx++; fcport->fw_sq_prod_idx++; if (fcport->sq_prod_idx == total_sqe) fcport->sq_prod_idx = 0; - switch (req_type) { - case FCOE_TASK_TYPE_WRITE_INITIATOR: - case FCOE_TASK_TYPE_READ_INITIATOR: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_CMD); - if (ptu_invalidate) - SET_FIELD(sqe->flags, FCOE_WQE_INVALIDATE_PTU, 1); - break; - case FCOE_TASK_TYPE_MIDPATH: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_MIDPATH); - break; - case FCOE_TASK_TYPE_ABTS: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, - SEND_FCOE_ABTS_REQUEST); - break; - case FCOE_TASK_TYPE_EXCHANGE_CLEANUP: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, - FCOE_EXCHANGE_CLEANUP); - break; - case FCOE_TASK_TYPE_SEQUENCE_CLEANUP: - SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, - FCOE_SEQUENCE_RECOVERY); - /* NOTE: offset param only used for sequence recovery */ - sqe->additional_info_union.seq_rec_updated_offset = offset; - break; - case FCOE_TASK_TYPE_UNSOLICITED: - break; - default: - break; - } - - sqe->task_id = xid; - - /* Make sure SQ data is coherent */ - wmb(); - + return rval; } void qedf_ring_doorbell(struct qedf_rport *fcport) @@ -1029,7 +847,8 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req) struct fcoe_task_context *task_ctx; u16 xid; enum fcoe_task_type req_type = 0; - u32 ptu_invalidate = 0; + struct fcoe_wqe *sqe; + u16 sqe_idx; /* Initialize rest of io_req fileds */ io_req->data_xfer_len = scsi_bufflen(sc_cmd); @@ -1061,6 +880,16 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req) return -EAGAIN; } + if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) { + QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n"); + kref_put(&io_req->refcount, qedf_release_cmd); + } + + /* Obtain free SQE */ + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + /* Get the task context */ task_ctx = qedf_get_task_mem(&qedf->tasks, xid); if (!task_ctx) { @@ -1070,15 +899,7 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req) return -EINVAL; } - qedf_init_task(fcport, lport, io_req, &ptu_invalidate, task_ctx); - - if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) { - QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n"); - kref_put(&io_req->refcount, qedf_release_cmd); - } - - /* Obtain free SQ entry */ - qedf_add_to_sq(fcport, xid, ptu_invalidate, req_type, 0); + qedf_init_task(fcport, lport, io_req, task_ctx, sqe); /* Ring doorbell */ qedf_ring_doorbell(fcport); @@ -1661,6 +1482,8 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts) u32 r_a_tov = 0; int rc = 0; unsigned long flags; + struct fcoe_wqe *sqe; + u16 sqe_idx; r_a_tov = rdata->r_a_tov; lport = qedf->lport; @@ -1712,10 +1535,12 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts) spin_lock_irqsave(&fcport->rport_lock, flags); - /* Add ABTS to send queue */ - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_ABTS, 0); + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + io_req->task_params->sqe = sqe; - /* Ring doorbell */ + init_initiator_abort_fcoe_task(io_req->task_params); qedf_ring_doorbell(fcport); spin_unlock_irqrestore(&fcport->rport_lock, flags); @@ -1784,8 +1609,8 @@ void qedf_process_abts_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, int qedf_init_mp_req(struct qedf_ioreq *io_req) { struct qedf_mp_req *mp_req; - struct fcoe_sge *mp_req_bd; - struct fcoe_sge *mp_resp_bd; + struct scsi_sge *mp_req_bd; + struct scsi_sge *mp_resp_bd; struct qedf_ctx *qedf = io_req->fcport->qedf; dma_addr_t addr; uint64_t sz; @@ -1819,7 +1644,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req) } /* Allocate and map mp_req_bd and mp_resp_bd */ - sz = sizeof(struct fcoe_sge); + sz = sizeof(struct scsi_sge); mp_req->mp_req_bd = dma_alloc_coherent(&qedf->pdev->dev, sz, &mp_req->mp_req_bd_dma, GFP_KERNEL); if (!mp_req->mp_req_bd) { @@ -1841,7 +1666,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req) mp_req_bd = mp_req->mp_req_bd; mp_req_bd->sge_addr.lo = U64_LO(addr); mp_req_bd->sge_addr.hi = U64_HI(addr); - mp_req_bd->size = QEDF_PAGE_SIZE; + mp_req_bd->sge_len = QEDF_PAGE_SIZE; /* * MP buffer is either a task mgmt command or an ELS. @@ -1852,7 +1677,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req) addr = mp_req->resp_buf_dma; mp_resp_bd->sge_addr.lo = U64_LO(addr); mp_resp_bd->sge_addr.hi = U64_HI(addr); - mp_resp_bd->size = QEDF_PAGE_SIZE; + mp_resp_bd->sge_len = QEDF_PAGE_SIZE; return 0; } @@ -1895,6 +1720,8 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req, int tmo = 0; int rc = SUCCESS; unsigned long flags; + struct fcoe_wqe *sqe; + u16 sqe_idx; fcport = io_req->fcport; if (!fcport) { @@ -1940,12 +1767,16 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req, init_completion(&io_req->tm_done); - /* Obtain free SQ entry */ spin_lock_irqsave(&fcport->rport_lock, flags); - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_EXCHANGE_CLEANUP, 0); - /* Ring doorbell */ + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + io_req->task_params->sqe = sqe; + + init_initiator_cleanup_fcoe_task(io_req->task_params); qedf_ring_doorbell(fcport); + spin_unlock_irqrestore(&fcport->rport_lock, flags); tmo = wait_for_completion_timeout(&io_req->tm_done, @@ -1991,16 +1822,15 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd, uint8_t tm_flags) { struct qedf_ioreq *io_req; - struct qedf_mp_req *tm_req; struct fcoe_task_context *task; - struct fc_frame_header *fc_hdr; - struct fcp_cmnd *fcp_cmnd; struct qedf_ctx *qedf = fcport->qedf; + struct fc_lport *lport = qedf->lport; int rc = 0; uint16_t xid; - uint32_t sid, did; int tmo = 0; unsigned long flags; + struct fcoe_wqe *sqe; + u16 sqe_idx; if (!sc_cmd) { QEDF_ERR(&(qedf->dbg_ctx), "invalid arg\n"); @@ -2031,36 +1861,14 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd, /* Set the return CPU to be the same as the request one */ io_req->cpu = smp_processor_id(); - tm_req = (struct qedf_mp_req *)&(io_req->mp_req); - - rc = qedf_init_mp_req(io_req); - if (rc == FAILED) { - QEDF_ERR(&(qedf->dbg_ctx), "Task mgmt MP request init " - "failed\n"); - kref_put(&io_req->refcount, qedf_release_cmd); - goto reset_tmf_err; - } - /* Set TM flags */ - io_req->io_req_flags = 0; - tm_req->tm_flags = tm_flags; + io_req->io_req_flags = QEDF_READ; + io_req->data_xfer_len = 0; + io_req->tm_flags = tm_flags; /* Default is to return a SCSI command when an error occurs */ io_req->return_scsi_cmd_on_abts = true; - /* Fill FCP_CMND */ - qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tm_req->req_buf); - fcp_cmnd = (struct fcp_cmnd *)tm_req->req_buf; - memset(fcp_cmnd->fc_cdb, 0, FCP_CMND_LEN); - fcp_cmnd->fc_dl = 0; - - /* Fill FC header */ - fc_hdr = &(tm_req->req_fc_hdr); - sid = fcport->sid; - did = fcport->rdata->ids.port_id; - __fc_fill_fc_hdr(fc_hdr, FC_RCTL_DD_UNSOL_CMD, sid, did, - FC_TYPE_FCP, FC_FC_FIRST_SEQ | FC_FC_END_SEQ | - FC_FC_SEQ_INIT, 0); /* Obtain exchange id */ xid = io_req->xid; @@ -2069,16 +1877,18 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd, /* Initialize task context for this IO request */ task = qedf_get_task_mem(&qedf->tasks, xid); - qedf_init_mp_task(io_req, task); init_completion(&io_req->tm_done); - /* Obtain free SQ entry */ spin_lock_irqsave(&fcport->rport_lock, flags); - qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0); - /* Ring doorbell */ + sqe_idx = qedf_get_sqe_idx(fcport); + sqe = &fcport->sq[sqe_idx]; + memset(sqe, 0, sizeof(struct fcoe_wqe)); + + qedf_init_task(fcport, lport, io_req, task, sqe); qedf_ring_doorbell(fcport); + spin_unlock_irqrestore(&fcport->rport_lock, flags); tmo = wait_for_completion_timeout(&io_req->tm_done, @@ -2162,14 +1972,6 @@ void qedf_process_tmf_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, struct qedf_ioreq *io_req) { struct fcoe_cqe_rsp_info *fcp_rsp; - struct fcoe_cqe_midpath_info *mp_info; - - - /* Get TMF response length from CQE */ - mp_info = &cqe->cqe_info.midpath_info; - io_req->mp_req.resp_len = mp_info->data_placement_size; - QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, - "Response len is %d.\n", io_req->mp_req.resp_len); fcp_rsp = &cqe->cqe_info.rsp_info; qedf_parse_fcp_rsp(io_req, fcp_rsp); diff --git a/drivers/scsi/qedi/Makefile b/drivers/scsi/qedi/Makefile index 2b3e16b24299..90a6925577cc 100644 --- a/drivers/scsi/qedi/Makefile +++ b/drivers/scsi/qedi/Makefile @@ -1,5 +1,5 @@ obj-$(CONFIG_QEDI) := qedi.o qedi-y := qedi_main.o qedi_iscsi.o qedi_fw.o qedi_sysfs.o \ - qedi_dbg.o + qedi_dbg.o qedi_fw_api.o qedi-$(CONFIG_DEBUG_FS) += qedi_debugfs.o diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index c9f0ef4e11b3..eca40b0513a3 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -14,6 +14,8 @@ #include "qedi.h" #include "qedi_iscsi.h" #include "qedi_gbl.h" +#include "qedi_fw_iscsi.h" +#include "qedi_fw_scsi.h" static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, struct iscsi_task *mtask); @@ -53,8 +55,8 @@ static void qedi_process_logout_resp(struct qedi_ctx *qedi, resp_hdr->exp_cmdsn = cpu_to_be32(cqe_logout_response->exp_cmd_sn); resp_hdr->max_cmdsn = cpu_to_be32(cqe_logout_response->max_cmd_sn); - resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time2wait); - resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time2retain); + resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time_2_wait); + resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time_2_retain); QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID, "Freeing tid=0x%x for cid=0x%x\n", @@ -975,81 +977,6 @@ void qedi_fp_process_cqes(struct qedi_work *work) return; } -static void qedi_add_to_sq(struct qedi_conn *qedi_conn, struct iscsi_task *task, - u16 tid, uint16_t ptu_invalidate, int is_cleanup) -{ - struct iscsi_wqe *wqe; - struct iscsi_wqe_field *cont_field; - struct qedi_endpoint *ep; - struct scsi_cmnd *sc = task->sc; - struct iscsi_login_req *login_hdr; - struct qedi_cmd *cmd = task->dd_data; - - login_hdr = (struct iscsi_login_req *)task->hdr; - ep = qedi_conn->ep; - wqe = &ep->sq[ep->sq_prod_idx]; - - memset(wqe, 0, sizeof(*wqe)); - - ep->sq_prod_idx++; - ep->fw_sq_prod_idx++; - if (ep->sq_prod_idx == QEDI_SQ_SIZE) - ep->sq_prod_idx = 0; - - if (is_cleanup) { - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_TASK_CLEANUP); - wqe->task_id = tid; - return; - } - - if (ptu_invalidate) { - SET_FIELD(wqe->flags, ISCSI_WQE_PTU_INVALIDATE, - ISCSI_WQE_SET_PTU_INVALIDATE); - } - - cont_field = &wqe->cont_prevtid_union.cont_field; - - switch (task->hdr->opcode & ISCSI_OPCODE_MASK) { - case ISCSI_OP_LOGIN: - case ISCSI_OP_TEXT: - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_MIDDLE_PATH); - SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, - 1); - cont_field->contlen_cdbsize_field = ntoh24(login_hdr->dlength); - break; - case ISCSI_OP_LOGOUT: - case ISCSI_OP_NOOP_OUT: - case ISCSI_OP_SCSI_TMFUNC: - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_NORMAL); - break; - default: - if (!sc) - break; - - SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE, - ISCSI_WQE_TYPE_NORMAL); - cont_field->contlen_cdbsize_field = - (sc->sc_data_direction == DMA_TO_DEVICE) ? - scsi_bufflen(sc) : 0; - if (cmd->use_slowpath) - SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, 0); - else - SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, - (sc->sc_data_direction == - DMA_TO_DEVICE) ? - min((u16)QEDI_FAST_SGE_COUNT, - (u16)cmd->io_tbl.sge_valid) : 0); - break; - } - - wqe->task_id = tid; - /* Make sure SQ data is coherent */ - wmb(); -} - static void qedi_ring_doorbell(struct qedi_conn *qedi_conn) { struct iscsi_db_data dbell = { 0 }; @@ -1076,96 +1003,116 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn) qedi_conn->iscsi_conn_id); } +static u16 qedi_get_wqe_idx(struct qedi_conn *qedi_conn) +{ + struct qedi_endpoint *ep; + u16 rval; + + ep = qedi_conn->ep; + rval = ep->sq_prod_idx; + + /* Increament SQ index */ + ep->sq_prod_idx++; + ep->fw_sq_prod_idx++; + if (ep->sq_prod_idx == QEDI_SQ_SIZE) + ep->sq_prod_idx = 0; + + return rval; +} + int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, struct iscsi_task *task) { - struct qedi_ctx *qedi = qedi_conn->qedi; + struct iscsi_login_req_hdr login_req_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; struct iscsi_task_context *fw_task_ctx; + struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_login_req *login_hdr; - struct iscsi_login_req_hdr *fw_login_req = NULL; - struct iscsi_cached_sge_ctx *cached_sge = NULL; - struct iscsi_sge *single_sge = NULL; - struct iscsi_sge *req_sge = NULL; - struct iscsi_sge *resp_sge = NULL; + struct scsi_sge *req_sge = NULL; + struct scsi_sge *resp_sge = NULL; struct qedi_cmd *qedi_cmd; - s16 ptu_invalidate = 0; + struct qedi_endpoint *ep; s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; qedi_cmd = (struct qedi_cmd *)task->dd_data; + ep = qedi_conn->ep; login_hdr = (struct iscsi_login_req *)task->hdr; tid = qedi_get_task_idx(qedi); if (tid == -1) return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_login_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.login_req; - fw_login_req->opcode = login_hdr->opcode; - fw_login_req->version_min = login_hdr->min_version; - fw_login_req->version_max = login_hdr->max_version; - fw_login_req->flags_attr = login_hdr->flags; - fw_login_req->isid_tabc = *((u16 *)login_hdr->isid + 2); - fw_login_req->isid_d = *((u32 *)login_hdr->isid); - fw_login_req->tsih = login_hdr->tsih; + memset(&task_params, 0, sizeof(task_params)); + memset(&login_req_pdu_header, 0, sizeof(login_req_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + /* Update header info */ + login_req_pdu_header.opcode = login_hdr->opcode; + login_req_pdu_header.version_min = login_hdr->min_version; + login_req_pdu_header.version_max = login_hdr->max_version; + login_req_pdu_header.flags_attr = login_hdr->flags; + login_req_pdu_header.isid_tabc = swab32p((u32 *)login_hdr->isid); + login_req_pdu_header.isid_d = swab16p((u16 *)&login_hdr->isid[4]); + + login_req_pdu_header.tsih = login_hdr->tsih; + login_req_pdu_header.hdr_second_dword = ntoh24(login_hdr->dlength); + qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); - fw_login_req->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_login_req->cid = qedi_conn->iscsi_conn_id; - fw_login_req->cmd_sn = be32_to_cpu(login_hdr->cmdsn); - fw_login_req->exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn); - fw_login_req->exp_stat_sn = 0; + login_req_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + login_req_pdu_header.cid = qedi_conn->iscsi_conn_id; + login_req_pdu_header.cmd_sn = be32_to_cpu(login_hdr->cmdsn); + login_req_pdu_header.exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn); + login_req_pdu_header.exp_stat_sn = 0; - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } + /* Fill tx AHS and rx buffer */ + tx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.req_dma_addr); + tx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); + tx_sgl_task_params.total_buffer_size = ntoh24(login_hdr->dlength); + tx_sgl_task_params.num_sges = 1; - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - cached_sge = - &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_len = req_sge->sge_len; - cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr); - cached_sge->sge.sge_addr.hi = - (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); + rx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.resp_dma_addr); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); + rx_sgl_task_params.total_buffer_size = resp_sge->sge_len; + rx_sgl_task_params.num_sges = 1; - /* Mstorm context */ - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - fw_task_ctx->mstorm_st_context.task_type = 0x2; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = ntoh24(login_hdr->dlength); + task_params.rx_io_size = resp_sge->sge_len; - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - fw_task_ctx->mstorm_st_context.sgl_size = 1; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = - ntoh24(login_hdr->dlength); - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - fw_task_ctx->ustorm_st_context.task_type = 0x2; - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - fw_task_ctx->ustorm_ag_context.exp_data_acked = - ntoh24(login_hdr->dlength); - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_login_request_task(&task_params, + &login_req_pdu_header, + &tx_sgl_task_params, + &rx_sgl_task_params); + if (rval) + return -1; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1173,7 +1120,6 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); return 0; } @@ -1181,65 +1127,64 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn, struct iscsi_task *task) { - struct qedi_ctx *qedi = qedi_conn->qedi; - struct iscsi_logout_req_hdr *fw_logout_req = NULL; - struct iscsi_task_context *fw_task_ctx = NULL; + struct iscsi_logout_req_hdr logout_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; + struct iscsi_task_context *fw_task_ctx; struct iscsi_logout *logout_hdr = NULL; - struct qedi_cmd *qedi_cmd = NULL; - s16 tid = 0; - s16 ptu_invalidate = 0; + struct qedi_ctx *qedi = qedi_conn->qedi; + struct qedi_cmd *qedi_cmd; + struct qedi_endpoint *ep; + s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; qedi_cmd = (struct qedi_cmd *)task->dd_data; logout_hdr = (struct iscsi_logout *)task->hdr; + ep = qedi_conn->ep; tid = qedi_get_task_idx(qedi); if (tid == -1) return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); - + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); + qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_logout_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.logout_req; - fw_logout_req->opcode = ISCSI_OPCODE_LOGOUT_REQUEST; - fw_logout_req->reason_code = 0x80 | logout_hdr->flags; + memset(&task_params, 0, sizeof(task_params)); + memset(&logout_pdu_header, 0, sizeof(logout_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + + /* Update header info */ + logout_pdu_header.opcode = logout_hdr->opcode; + logout_pdu_header.reason_code = 0x80 | logout_hdr->flags; qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); - fw_logout_req->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_logout_req->exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn); - fw_logout_req->cmd_sn = be32_to_cpu(logout_hdr->cmdsn); + logout_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + logout_pdu_header.exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn); + logout_pdu_header.cmd_sn = be32_to_cpu(logout_hdr->cmdsn); + logout_pdu_header.cid = qedi_conn->iscsi_conn_id; - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - fw_logout_req->cid = qedi_conn->iscsi_conn_id; - fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0; + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = 0; + task_params.rx_io_size = 0; - /* Mstorm context */ - fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); + rval = init_initiator_logout_request_task(&task_params, + &logout_pdu_header, + NULL, NULL); + if (rval) + return -1; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1247,9 +1192,7 @@ int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn, qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); - return 0; } @@ -1533,47 +1476,46 @@ static void qedi_tmf_work(struct work_struct *work) static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, struct iscsi_task *mtask) { - struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data; + struct iscsi_tmf_request_hdr tmf_pdu_header; + struct iscsi_task_params task_params; struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_task_context *fw_task_ctx; - struct iscsi_tmf_request_hdr *fw_tmf_request; - struct iscsi_sge *single_sge; - struct qedi_cmd *qedi_cmd; - struct qedi_cmd *cmd; + struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data; struct iscsi_task *ctask; struct iscsi_tm *tmf_hdr; - struct iscsi_sge *req_sge; - struct iscsi_sge *resp_sge; - u32 lun[2]; - s16 tid = 0, ptu_invalidate = 0; + struct qedi_cmd *qedi_cmd; + struct qedi_cmd *cmd; + struct qedi_endpoint *ep; + u32 scsi_lun[2]; + s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; - qedi_cmd = (struct qedi_cmd *)mtask->dd_data; tmf_hdr = (struct iscsi_tm *)mtask->hdr; + qedi_cmd = (struct qedi_cmd *)mtask->dd_data; + ep = qedi_conn->ep; - tid = qedi_cmd->task_id; - qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd); + tid = qedi_get_task_idx(qedi); + if (tid == -1) + return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); - fw_tmf_request = &fw_task_ctx->ystorm_st_context.pdu_hdr.tmf_request; - fw_tmf_request->itt = qedi_set_itt(tid, get_itt(mtask->itt)); - fw_tmf_request->cmd_sn = be32_to_cpu(tmf_hdr->cmdsn); + qedi_cmd->task_id = tid; - memcpy(lun, &tmf_hdr->lun, sizeof(struct scsi_lun)); - fw_tmf_request->lun.lo = be32_to_cpu(lun[0]); - fw_tmf_request->lun.hi = be32_to_cpu(lun[1]); + memset(&task_params, 0, sizeof(task_params)); + memset(&tmf_pdu_header, 0, sizeof(tmf_pdu_header)); - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; + /* Update header info */ + qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd); + tmf_pdu_header.itt = qedi_set_itt(tid, get_itt(mtask->itt)); + tmf_pdu_header.cmd_sn = be32_to_cpu(tmf_hdr->cmdsn); + + memcpy(scsi_lun, &tmf_hdr->lun, sizeof(struct scsi_lun)); + tmf_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]); + tmf_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]); if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) == ISCSI_TM_FUNC_ABORT_TASK) { @@ -1584,53 +1526,34 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, return 0; } cmd = (struct qedi_cmd *)ctask->dd_data; - fw_tmf_request->rtt = + tmf_pdu_header.rtt = qedi_set_itt(cmd->task_id, get_itt(tmf_hdr->rtt)); } else { - fw_tmf_request->rtt = ISCSI_RESERVED_TAG; + tmf_pdu_header.rtt = ISCSI_RESERVED_TAG; } - fw_tmf_request->opcode = tmf_hdr->opcode; - fw_tmf_request->function = tmf_hdr->flags; - fw_tmf_request->hdr_second_dword = ntoh24(tmf_hdr->dlength); - fw_tmf_request->ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn); + tmf_pdu_header.opcode = tmf_hdr->opcode; + tmf_pdu_header.function = tmf_hdr->flags; + tmf_pdu_header.hdr_second_dword = ntoh24(tmf_hdr->dlength); + tmf_pdu_header.ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn); - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = 0; + task_params.rx_io_size = 0; - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - fw_task_ctx->mstorm_st_context.sgl_size = 1; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0; - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]); - fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]); - - QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, - "Add TMF to SQ, tmf tid=0x%x, itt=0x%x, cid=0x%x\n", - tid, mtask->itt, qedi_conn->iscsi_conn_id); + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_tmf_request_task(&task_params, + &tmf_pdu_header); + if (rval) + return -1; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1638,7 +1561,6 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn, qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, mtask, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); return 0; } @@ -1689,101 +1611,98 @@ int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn, int qedi_send_iscsi_text(struct qedi_conn *qedi_conn, struct iscsi_task *task) { - struct qedi_ctx *qedi = qedi_conn->qedi; + struct iscsi_text_request_hdr text_request_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; struct iscsi_task_context *fw_task_ctx; - struct iscsi_text_request_hdr *fw_text_request; - struct iscsi_cached_sge_ctx *cached_sge; - struct iscsi_sge *single_sge; - struct qedi_cmd *qedi_cmd; - /* For 6.5 hdr iscsi_hdr */ + struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_text *text_hdr; - struct iscsi_sge *req_sge; - struct iscsi_sge *resp_sge; - s16 ptu_invalidate = 0; + struct scsi_sge *req_sge = NULL; + struct scsi_sge *resp_sge = NULL; + struct qedi_cmd *qedi_cmd; + struct qedi_endpoint *ep; s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; qedi_cmd = (struct qedi_cmd *)task->dd_data; text_hdr = (struct iscsi_text *)task->hdr; + ep = qedi_conn->ep; tid = qedi_get_task_idx(qedi); if (tid == -1) return -ENOMEM; - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_text_request = - &fw_task_ctx->ystorm_st_context.pdu_hdr.text_request; - fw_text_request->opcode = text_hdr->opcode; - fw_text_request->flags_attr = text_hdr->flags; + memset(&task_params, 0, sizeof(task_params)); + memset(&text_request_pdu_header, 0, sizeof(text_request_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + + /* Update header info */ + text_request_pdu_header.opcode = text_hdr->opcode; + text_request_pdu_header.flags_attr = text_hdr->flags; qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); - fw_text_request->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_text_request->ttt = text_hdr->ttt; - fw_text_request->cmd_sn = be32_to_cpu(text_hdr->cmdsn); - fw_text_request->exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn); - fw_text_request->hdr_second_dword = ntoh24(text_hdr->dlength); + text_request_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + text_request_pdu_header.ttt = text_hdr->ttt; + text_request_pdu_header.cmd_sn = be32_to_cpu(text_hdr->cmdsn); + text_request_pdu_header.exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn); + text_request_pdu_header.hdr_second_dword = ntoh24(text_hdr->dlength); - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - - cached_sge = - &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_len = req_sge->sge_len; - cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr); - cached_sge->sge.sge_addr.hi = + /* Fill tx AHS and rx buffer */ + tx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.req_dma_addr); + tx_sgl_task_params.sgl_phys_addr.hi = (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); + tx_sgl_task_params.total_buffer_size = req_sge->sge_len; + tx_sgl_task_params.num_sges = 1; - /* Mstorm context */ - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - fw_task_ctx->mstorm_st_context.task_type = 0x2; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; + rx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.resp_dma_addr); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); + rx_sgl_task_params.total_buffer_size = resp_sge->sge_len; + rx_sgl_task_params.num_sges = 1; - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - fw_task_ctx->mstorm_st_context.sgl_size = 1; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = ntoh24(text_hdr->dlength); + task_params.rx_io_size = resp_sge->sge_len; - /* Ustorm context */ - fw_task_ctx->ustorm_ag_context.exp_data_acked = - ntoh24(text_hdr->dlength); - fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = - ntoh24(text_hdr->dlength); - fw_task_ctx->ustorm_st_context.exp_data_sn = - be32_to_cpu(text_hdr->exp_statsn); - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - fw_task_ctx->ustorm_st_context.task_type = 0x2; - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_text_request_task(&task_params, + &text_request_pdu_header, + &tx_sgl_task_params, + &rx_sgl_task_params); + if (rval) + return -1; - /* Add command in active command list */ spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); qedi_cmd->io_cmd_in_list = true; qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); - return 0; } @@ -1791,58 +1710,62 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, struct iscsi_task *task, char *datap, int data_len, int unsol) { + struct iscsi_nop_out_hdr nop_out_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct iscsi_task_params task_params; struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_task_context *fw_task_ctx; - struct iscsi_nop_out_hdr *fw_nop_out; - struct qedi_cmd *qedi_cmd; - /* For 6.5 hdr iscsi_hdr */ struct iscsi_nopout *nopout_hdr; - struct iscsi_cached_sge_ctx *cached_sge; - struct iscsi_sge *single_sge; - struct iscsi_sge *req_sge; - struct iscsi_sge *resp_sge; - u32 lun[2]; - s16 ptu_invalidate = 0; + struct scsi_sge *req_sge = NULL; + struct scsi_sge *resp_sge = NULL; + struct qedi_cmd *qedi_cmd; + struct qedi_endpoint *ep; + u32 scsi_lun[2]; s16 tid = 0; + u16 sq_idx = 0; + int rval = 0; - req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; - resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; qedi_cmd = (struct qedi_cmd *)task->dd_data; nopout_hdr = (struct iscsi_nopout *)task->hdr; + ep = qedi_conn->ep; tid = qedi_get_task_idx(qedi); - if (tid == -1) { - QEDI_WARN(&qedi->dbg_ctx, "Invalid tid\n"); + if (tid == -1) return -ENOMEM; - } - - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); + qedi_cmd->task_id = tid; - /* Ystorm context */ - fw_nop_out = &fw_task_ctx->ystorm_st_context.pdu_hdr.nop_out; - SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1); - SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0); + memset(&task_params, 0, sizeof(task_params)); + memset(&nop_out_pdu_header, 0, sizeof(nop_out_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); - memcpy(lun, &nopout_hdr->lun, sizeof(struct scsi_lun)); - fw_nop_out->lun.lo = be32_to_cpu(lun[0]); - fw_nop_out->lun.hi = be32_to_cpu(lun[1]); + /* Update header info */ + nop_out_pdu_header.opcode = nopout_hdr->opcode; + SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1); + SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0); + + memcpy(scsi_lun, &nopout_hdr->lun, sizeof(struct scsi_lun)); + nop_out_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]); + nop_out_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]); + nop_out_pdu_header.cmd_sn = be32_to_cpu(nopout_hdr->cmdsn); + nop_out_pdu_header.exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn); qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd); if (nopout_hdr->ttt != ISCSI_TTT_ALL_ONES) { - fw_nop_out->itt = be32_to_cpu(nopout_hdr->itt); - fw_nop_out->ttt = be32_to_cpu(nopout_hdr->ttt); - fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0; - fw_task_ctx->ystorm_st_context.state.local_comp = 1; - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1); + nop_out_pdu_header.itt = be32_to_cpu(nopout_hdr->itt); + nop_out_pdu_header.ttt = be32_to_cpu(nopout_hdr->ttt); } else { - fw_nop_out->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_nop_out->ttt = ISCSI_TTT_ALL_ONES; - fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0; + nop_out_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + nop_out_pdu_header.ttt = ISCSI_TTT_ALL_ONES; spin_lock(&qedi_conn->list_lock); list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list); @@ -1851,53 +1774,46 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, spin_unlock(&qedi_conn->list_lock); } - fw_nop_out->opcode = ISCSI_OPCODE_NOP_OUT; - fw_nop_out->cmd_sn = be32_to_cpu(nopout_hdr->cmdsn); - fw_nop_out->exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn); + /* Fill tx AHS and rx buffer */ + if (data_len) { + tx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.req_dma_addr); + tx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); + tx_sgl_task_params.total_buffer_size = data_len; + tx_sgl_task_params.num_sges = 1; - cached_sge = - &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_len = req_sge->sge_len; - cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr); - cached_sge->sge.sge_addr.hi = - (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); - - /* Mstorm context */ - fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id; - - single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge; - single_sge->sge_addr.lo = resp_sge->sge_addr.lo; - single_sge->sge_addr.hi = resp_sge->sge_addr.hi; - single_sge->sge_len = resp_sge->sge_len; - fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len; - - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; + rx_sgl_task_params.sgl = + (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(qedi_conn->gen_pdu.resp_dma_addr); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); + rx_sgl_task_params.total_buffer_size = resp_sge->sge_len; + rx_sgl_task_params.num_sges = 1; } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len; - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = data_len; - fw_task_ctx->ustorm_st_context.exp_data_sn = 0; - fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH; - fw_task_ctx->ustorm_st_context.cq_rss_number = 0; - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = 0; + task_params.tx_io_size = data_len; + task_params.rx_io_size = resp_sge->sge_len; - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; - fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]); - fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]); + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + rval = init_initiator_nop_out_task(&task_params, + &nop_out_pdu_header, + &tx_sgl_task_params, + &rx_sgl_task_params); + if (rval) + return -1; - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); return 0; } @@ -1905,7 +1821,7 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len, int bd_index) { - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; + struct scsi_sge *bd = cmd->io_tbl.sge_tbl; int frag_size, sg_frags; sg_frags = 0; @@ -1938,7 +1854,7 @@ static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len, static int qedi_map_scsi_sg(struct qedi_ctx *qedi, struct qedi_cmd *cmd) { struct scsi_cmnd *sc = cmd->scsi_cmd; - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; + struct scsi_sge *bd = cmd->io_tbl.sge_tbl; struct scatterlist *sg; int byte_count = 0; int bd_count = 0; @@ -2040,7 +1956,7 @@ static void qedi_iscsi_map_sg_list(struct qedi_cmd *cmd) if (bd_count == 0) return; } else { - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; + struct scsi_sge *bd = cmd->io_tbl.sge_tbl; bd[0].sge_addr.lo = 0; bd[0].sge_addr.hi = 0; @@ -2136,244 +2052,182 @@ int qedi_iscsi_send_ioreq(struct iscsi_task *task) struct qedi_conn *qedi_conn = conn->dd_data; struct qedi_cmd *cmd = task->dd_data; struct scsi_cmnd *sc = task->sc; + struct iscsi_cmd_hdr cmd_pdu_header; + struct scsi_sgl_task_params tx_sgl_task_params; + struct scsi_sgl_task_params rx_sgl_task_params; + struct scsi_sgl_task_params *prx_sgl = NULL; + struct scsi_sgl_task_params *ptx_sgl = NULL; + struct iscsi_task_params task_params; + struct iscsi_conn_params conn_params; + struct scsi_initiator_cmd_params cmd_params; struct iscsi_task_context *fw_task_ctx; - struct iscsi_cached_sge_ctx *cached_sge; - struct iscsi_phys_sgl_ctx *phys_sgl; - struct iscsi_virt_sgl_ctx *virt_sgl; - struct ystorm_iscsi_task_st_ctx *yst_cxt; - struct mstorm_iscsi_task_st_ctx *mst_cxt; - struct iscsi_sgl *sgl_struct; - struct iscsi_sge *single_sge; + struct iscsi_cls_conn *cls_conn; struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr; - struct iscsi_sge *bd = cmd->io_tbl.sge_tbl; - enum iscsi_task_type task_type; - struct iscsi_cmd_hdr *fw_cmd; - u32 lun[2]; - u32 exp_data; - u16 cq_idx = smp_processor_id() % qedi->num_queues; - s16 ptu_invalidate = 0; + enum iscsi_task_type task_type = MAX_ISCSI_TASK_TYPE; + struct qedi_endpoint *ep; + u32 scsi_lun[2]; s16 tid = 0; - u8 num_fast_sgs; + u16 sq_idx = 0; + u16 cq_idx; + int rval = 0; + + ep = qedi_conn->ep; + cls_conn = qedi_conn->cls_conn; + conn = cls_conn->dd_data; + + qedi_iscsi_map_sg_list(cmd); + int_to_scsilun(sc->device->lun, (struct scsi_lun *)scsi_lun); tid = qedi_get_task_idx(qedi); if (tid == -1) return -ENOMEM; - qedi_iscsi_map_sg_list(cmd); - - int_to_scsilun(sc->device->lun, (struct scsi_lun *)lun); - fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid); - + fw_task_ctx = + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); + cmd->task_id = tid; - /* Ystorm context */ - fw_cmd = &fw_task_ctx->ystorm_st_context.pdu_hdr.cmd; - SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_ATTR, ISCSI_ATTR_SIMPLE); + memset(&task_params, 0, sizeof(task_params)); + memset(&cmd_pdu_header, 0, sizeof(cmd_pdu_header)); + memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params)); + memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params)); + memset(&conn_params, 0, sizeof(conn_params)); + memset(&cmd_params, 0, sizeof(cmd_params)); + cq_idx = smp_processor_id() % qedi->num_queues; + /* Update header info */ + SET_FIELD(cmd_pdu_header.flags_attr, ISCSI_CMD_HDR_ATTR, + ISCSI_ATTR_SIMPLE); if (sc->sc_data_direction == DMA_TO_DEVICE) { - if (conn->session->initial_r2t_en) { - exp_data = min((conn->session->imm_data_en * - conn->max_xmit_dlength), - conn->session->first_burst); - exp_data = min(exp_data, scsi_bufflen(sc)); - fw_task_ctx->ustorm_ag_context.exp_data_acked = - cpu_to_le32(exp_data); - } else { - fw_task_ctx->ustorm_ag_context.exp_data_acked = - min(conn->session->first_burst, scsi_bufflen(sc)); - } - - SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_WRITE, 1); + SET_FIELD(cmd_pdu_header.flags_attr, + ISCSI_CMD_HDR_WRITE, 1); task_type = ISCSI_TASK_TYPE_INITIATOR_WRITE; } else { - if (scsi_bufflen(sc)) - SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_READ, 1); + SET_FIELD(cmd_pdu_header.flags_attr, + ISCSI_CMD_HDR_READ, 1); task_type = ISCSI_TASK_TYPE_INITIATOR_READ; } - fw_cmd->lun.lo = be32_to_cpu(lun[0]); - fw_cmd->lun.hi = be32_to_cpu(lun[1]); + cmd_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]); + cmd_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]); qedi_update_itt_map(qedi, tid, task->itt, cmd); - fw_cmd->itt = qedi_set_itt(tid, get_itt(task->itt)); - fw_cmd->expected_transfer_length = scsi_bufflen(sc); - fw_cmd->cmd_sn = be32_to_cpu(hdr->cmdsn); - fw_cmd->opcode = hdr->opcode; - qedi_cpy_scsi_cdb(sc, (u32 *)fw_cmd->cdb); + cmd_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt)); + cmd_pdu_header.expected_transfer_length = cpu_to_be32(hdr->data_length); + cmd_pdu_header.hdr_second_dword = ntoh24(hdr->dlength); + cmd_pdu_header.cmd_sn = be32_to_cpu(hdr->cmdsn); + cmd_pdu_header.opcode = hdr->opcode; + qedi_cpy_scsi_cdb(sc, (u32 *)cmd_pdu_header.cdb); - /* Mstorm context */ - fw_task_ctx->mstorm_st_context.sense_db.lo = (u32)cmd->sense_buffer_dma; - fw_task_ctx->mstorm_st_context.sense_db.hi = - (u32)((u64)cmd->sense_buffer_dma >> 32); - fw_task_ctx->mstorm_ag_context.task_cid = qedi_conn->iscsi_conn_id; - fw_task_ctx->mstorm_st_context.task_type = task_type; - - if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) { - ptu_invalidate = 1; - qedi->tid_reuse_count[tid] = 0; - } - fw_task_ctx->ystorm_st_context.state.reuse_count = - qedi->tid_reuse_count[tid]; - fw_task_ctx->mstorm_st_context.reuse_count = - qedi->tid_reuse_count[tid]++; - - /* Ustorm context */ - fw_task_ctx->ustorm_st_context.rem_rcv_len = scsi_bufflen(sc); - fw_task_ctx->ustorm_st_context.exp_data_transfer_len = scsi_bufflen(sc); - fw_task_ctx->ustorm_st_context.exp_data_sn = - be32_to_cpu(hdr->exp_statsn); - fw_task_ctx->ustorm_st_context.task_type = task_type; - fw_task_ctx->ustorm_st_context.cq_rss_number = cq_idx; - fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id; - - SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1, - USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.flags, - USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0); - - num_fast_sgs = (cmd->io_tbl.sge_valid ? - min((u16)QEDI_FAST_SGE_COUNT, - (u16)cmd->io_tbl.sge_valid) : 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, num_fast_sgs); - - fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]); - fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]); - - QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "Total sge count [%d]\n", - cmd->io_tbl.sge_valid); - - yst_cxt = &fw_task_ctx->ystorm_st_context; - mst_cxt = &fw_task_ctx->mstorm_st_context; - /* Tx path */ + /* Fill tx AHS and rx buffer */ if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) { - /* not considering superIO or FastIO */ - if (cmd->io_tbl.sge_valid == 1) { - cached_sge = &yst_cxt->state.sgl_ctx_union.cached_sge; - cached_sge->sge.sge_addr.lo = bd[0].sge_addr.lo; - cached_sge->sge.sge_addr.hi = bd[0].sge_addr.hi; - cached_sge->sge.sge_len = bd[0].sge_len; - qedi->cached_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) { - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - phys_sgl = &yst_cxt->state.sgl_ctx_union.phys_sgl; - phys_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma); - phys_sgl->sgl_base.hi = - (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - phys_sgl->sgl_size = cmd->io_tbl.sge_valid; - qedi->slow_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) { - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, - min((u16)QEDI_FAST_SGE_COUNT, - (u16)cmd->io_tbl.sge_valid)); - virt_sgl = &yst_cxt->state.sgl_ctx_union.virt_sgl; - virt_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma); - virt_sgl->sgl_base.hi = + tx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl; + tx_sgl_task_params.sgl_phys_addr.lo = + (u32)(cmd->io_tbl.sge_tbl_dma); + tx_sgl_task_params.sgl_phys_addr.hi = (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - virt_sgl->sgl_initial_offset = - (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1); - qedi->fast_sgls++; - } - fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid; - fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc); - } else { - /* Rx path */ - if (cmd->io_tbl.sge_valid == 1) { - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SINGLE_SGE, 1); - single_sge = &mst_cxt->sgl_union.single_sge; - single_sge->sge_addr.lo = bd[0].sge_addr.lo; - single_sge->sge_addr.hi = bd[0].sge_addr.hi; - single_sge->sge_len = bd[0].sge_len; - qedi->cached_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) { - sgl_struct = &mst_cxt->sgl_union.sgl_struct; - sgl_struct->sgl_addr.lo = - (u32)(cmd->io_tbl.sge_tbl_dma); - sgl_struct->sgl_addr.hi = - (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 1); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - sgl_struct->updated_sge_size = 0; - sgl_struct->updated_sge_offset = 0; - qedi->slow_sgls++; - } else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) { - sgl_struct = &mst_cxt->sgl_union.sgl_struct; - sgl_struct->sgl_addr.lo = - (u32)(cmd->io_tbl.sge_tbl_dma); - sgl_struct->sgl_addr.hi = - (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); - sgl_struct->byte_offset = - (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1); - SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags, - ISCSI_MFLAGS_SLOW_IO, 0); - SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map, - ISCSI_REG1_NUM_FAST_SGES, 0); - sgl_struct->updated_sge_size = 0; - sgl_struct->updated_sge_offset = 0; - qedi->fast_sgls++; - } - fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid; - fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc); + tx_sgl_task_params.total_buffer_size = scsi_bufflen(sc); + tx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid; + if (cmd->use_slowpath) + tx_sgl_task_params.small_mid_sge = true; + } else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ) { + rx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl; + rx_sgl_task_params.sgl_phys_addr.lo = + (u32)(cmd->io_tbl.sge_tbl_dma); + rx_sgl_task_params.sgl_phys_addr.hi = + (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32); + rx_sgl_task_params.total_buffer_size = scsi_bufflen(sc); + rx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid; } - if (cmd->io_tbl.sge_valid == 1) - /* Singel-SGL */ - qedi->use_cached_sge = true; - else { - if (cmd->use_slowpath) - qedi->use_slow_sge = true; - else - qedi->use_fast_sge = true; - } + /* Add conn param */ + conn_params.first_burst_length = conn->session->first_burst; + conn_params.max_send_pdu_length = conn->max_xmit_dlength; + conn_params.max_burst_length = conn->session->max_burst; + if (conn->session->initial_r2t_en) + conn_params.initial_r2t = true; + if (conn->session->imm_data_en) + conn_params.immediate_data = true; + + /* Add cmd params */ + cmd_params.sense_data_buffer_phys_addr.lo = (u32)cmd->sense_buffer_dma; + cmd_params.sense_data_buffer_phys_addr.hi = + (u32)((u64)cmd->sense_buffer_dma >> 32); + /* Fill fw input params */ + task_params.context = fw_task_ctx; + task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id; + task_params.itid = tid; + task_params.cq_rss_number = cq_idx; + if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) + task_params.tx_io_size = scsi_bufflen(sc); + else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ) + task_params.rx_io_size = scsi_bufflen(sc); + + sq_idx = qedi_get_wqe_idx(qedi_conn); + task_params.sqe = &ep->sq[sq_idx]; + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, - "%s: %s-SGL: num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x", + "%s: %s-SGL: sg_len=0x%x num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x\n", (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) ? "Write " : "Read ", (cmd->io_tbl.sge_valid == 1) ? "Single" : (cmd->use_slowpath ? "SLOW" : "FAST"), - (u16)cmd->io_tbl.sge_valid, (u32)(cmd->io_tbl.sge_tbl_dma), + (u16)cmd->io_tbl.sge_valid, scsi_bufflen(sc), + (u32)(cmd->io_tbl.sge_tbl_dma), (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32)); - /* Add command in active command list */ + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + + if (task_params.tx_io_size != 0) + ptx_sgl = &tx_sgl_task_params; + if (task_params.rx_io_size != 0) + prx_sgl = &rx_sgl_task_params; + + rval = init_initiator_rw_iscsi_task(&task_params, &conn_params, + &cmd_params, &cmd_pdu_header, + ptx_sgl, prx_sgl, + NULL); + if (rval) + return -1; + spin_lock(&qedi_conn->list_lock); list_add_tail(&cmd->io_cmd, &qedi_conn->active_cmd_list); cmd->io_cmd_in_list = true; qedi_conn->active_cmd_count++; spin_unlock(&qedi_conn->list_lock); - qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false); qedi_ring_doorbell(qedi_conn); - if (qedi_io_tracing) - qedi_trace_io(qedi, task, tid, QEDI_IO_TRACE_REQ); - return 0; } int qedi_iscsi_cleanup_task(struct iscsi_task *task, bool mark_cmd_node_deleted) { + struct iscsi_task_params task_params; + struct qedi_endpoint *ep; struct iscsi_conn *conn = task->conn; struct qedi_conn *qedi_conn = conn->dd_data; struct qedi_cmd *cmd = task->dd_data; - s16 ptu_invalidate = 0; + u16 sq_idx = 0; + int rval = 0; QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "issue cleanup tid=0x%x itt=0x%x task_state=%d cmd_state=0%x cid=0x%x\n", cmd->task_id, get_itt(task->itt), task->state, cmd->state, qedi_conn->iscsi_conn_id); - qedi_add_to_sq(qedi_conn, task, cmd->task_id, ptu_invalidate, true); - qedi_ring_doorbell(qedi_conn); + memset(&task_params, 0, sizeof(task_params)); + ep = qedi_conn->ep; + sq_idx = qedi_get_wqe_idx(qedi_conn); + + task_params.sqe = &ep->sq[sq_idx]; + memset(task_params.sqe, 0, sizeof(struct iscsi_wqe)); + task_params.itid = cmd->task_id; + + rval = init_cleanup_task(&task_params); + if (rval) + return rval; + + qedi_ring_doorbell(qedi_conn); return 0; } diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c new file mode 100644 index 000000000000..fd354d4e03eb --- /dev/null +++ b/drivers/scsi/qedi/qedi_fw_api.c @@ -0,0 +1,781 @@ +/* QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#include +#include +#include "qedi_hsi.h" +#include + +#include "qedi_fw_iscsi.h" +#include "qedi_fw_scsi.h" + +#define SCSI_NUM_SGES_IN_CACHE 0x4 + +static bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge) +{ + return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge); +} + +static +void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct scsi_sgl_task_params *sgl_task_params) +{ + u8 sge_index; + u8 num_sges; + u32 val; + + num_sges = (sgl_task_params->num_sges > SCSI_NUM_SGES_IN_CACHE) ? + SCSI_NUM_SGES_IN_CACHE : sgl_task_params->num_sges; + + /* sgl params */ + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo); + ctx_sgl_params->sgl_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi); + ctx_sgl_params->sgl_addr.hi = val; + val = cpu_to_le32(sgl_task_params->total_buffer_size); + ctx_sgl_params->sgl_total_length = val; + ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges); + + for (sge_index = 0; sge_index < num_sges; sge_index++) { + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo); + ctx_data_desc->sge[sge_index].sge_addr.lo = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi); + ctx_data_desc->sge[sge_index].sge_addr.hi = val; + val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len); + ctx_data_desc->sge[sge_index].sge_len = val; + } +} + +static u32 calc_rw_task_size(struct iscsi_task_params *task_params, + enum iscsi_task_type task_type, + struct scsi_sgl_task_params *sgl_task_params, + struct scsi_dif_task_params *dif_task_params) +{ + u32 io_size; + + if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE || + task_type == ISCSI_TASK_TYPE_TARGET_READ) + io_size = task_params->tx_io_size; + else + io_size = task_params->rx_io_size; + + if (!io_size) + return 0; + + if (!dif_task_params) + return io_size; + + return !dif_task_params->dif_on_network ? + io_size : sgl_task_params->total_buffer_size; +} + +static void +init_dif_context_flags(struct iscsi_dif_flags *ctx_dif_flags, + struct scsi_dif_task_params *dif_task_params) +{ + if (!dif_task_params) + return; + + SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_PROT_INTERVAL_SIZE_LOG, + dif_task_params->dif_block_size_log); + SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_DIF_TO_PEER, + dif_task_params->dif_on_network ? 1 : 0); + SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_HOST_INTERFACE, + dif_task_params->dif_on_host ? 1 : 0); +} + +static void init_sqe(struct iscsi_task_params *task_params, + struct scsi_sgl_task_params *sgl_task_params, + struct scsi_dif_task_params *dif_task_params, + struct iscsi_common_hdr *pdu_header, + struct scsi_initiator_cmd_params *cmd_params, + enum iscsi_task_type task_type, + bool is_cleanup) +{ + if (!task_params->sqe) + return; + + memset(task_params->sqe, 0, sizeof(*task_params->sqe)); + task_params->sqe->task_id = cpu_to_le16(task_params->itid); + if (is_cleanup) { + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_TASK_CLEANUP); + return; + } + + switch (task_type) { + case ISCSI_TASK_TYPE_INITIATOR_WRITE: + { + u32 buf_size = 0; + u32 num_sges = 0; + + init_dif_context_flags(&task_params->sqe->prot_flags, + dif_task_params); + + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_NORMAL); + + if (task_params->tx_io_size) { + buf_size = calc_rw_task_size(task_params, task_type, + sgl_task_params, + dif_task_params); + + if (scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge)) + num_sges = ISCSI_WQE_NUM_SGES_SLOWIO; + else + num_sges = min(sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR); + } + + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, num_sges); + SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN, + buf_size); + + if (GET_FIELD(pdu_header->hdr_second_dword, + ISCSI_CMD_HDR_TOTAL_AHS_LEN)) + SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CDB_SIZE, + cmd_params->extended_cdb_sge.sge_len); + } + break; + case ISCSI_TASK_TYPE_INITIATOR_READ: + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_NORMAL); + + if (GET_FIELD(pdu_header->hdr_second_dword, + ISCSI_CMD_HDR_TOTAL_AHS_LEN)) + SET_FIELD(task_params->sqe->contlen_cdbsize, + ISCSI_WQE_CDB_SIZE, + cmd_params->extended_cdb_sge.sge_len); + break; + case ISCSI_TASK_TYPE_LOGIN_RESPONSE: + case ISCSI_TASK_TYPE_MIDPATH: + { + bool advance_statsn = true; + + if (task_type == ISCSI_TASK_TYPE_LOGIN_RESPONSE) + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_LOGIN); + else + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE, + ISCSI_WQE_TYPE_MIDDLE_PATH); + + if (task_type == ISCSI_TASK_TYPE_MIDPATH) { + u8 opcode = GET_FIELD(pdu_header->hdr_first_byte, + ISCSI_COMMON_HDR_OPCODE); + + if (opcode != ISCSI_OPCODE_TEXT_RESPONSE && + (opcode != ISCSI_OPCODE_NOP_IN || + pdu_header->itt == ISCSI_TTT_ALL_ONES)) + advance_statsn = false; + } + + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_RESPONSE, + advance_statsn ? 1 : 0); + + if (task_params->tx_io_size) { + SET_FIELD(task_params->sqe->contlen_cdbsize, + ISCSI_WQE_CONT_LEN, task_params->tx_io_size); + + if (scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge)) + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, + ISCSI_WQE_NUM_SGES_SLOWIO); + else + SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, + min(sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR)); + } + } + break; + default: + break; + } +} + +static void init_default_iscsi_task(struct iscsi_task_params *task_params, + struct data_hdr *pdu_header, + enum iscsi_task_type task_type) +{ + struct iscsi_task_context *context; + u16 index; + u32 val; + + context = task_params->context; + memset(context, 0, sizeof(*context)); + + for (index = 0; index < + ARRAY_SIZE(context->ystorm_st_context.pdu_hdr.data.data); + index++) { + val = cpu_to_le32(pdu_header->data[index]); + context->ystorm_st_context.pdu_hdr.data.data[index] = val; + } + + context->mstorm_st_context.task_type = task_type; + context->mstorm_ag_context.task_cid = + cpu_to_le16(task_params->conn_icid); + + SET_FIELD(context->ustorm_ag_context.flags1, + USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); + + context->ustorm_st_context.task_type = task_type; + context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number; + context->ustorm_ag_context.icid = cpu_to_le16(task_params->conn_icid); +} + +static +void init_initiator_rw_cdb_ystorm_context(struct ystorm_iscsi_task_st_ctx *ystc, + struct scsi_initiator_cmd_params *cmd) +{ + union iscsi_task_hdr *ctx_pdu_hdr = &ystc->pdu_hdr; + u32 val; + + if (!cmd->extended_cdb_sge.sge_len) + return; + + SET_FIELD(ctx_pdu_hdr->ext_cdb_cmd.hdr_second_dword, + ISCSI_EXT_CDB_CMD_HDR_CDB_SIZE, + cmd->extended_cdb_sge.sge_len); + val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.lo); + ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.lo = val; + val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.hi); + ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.hi = val; + val = cpu_to_le32(cmd->extended_cdb_sge.sge_len); + ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_len = val; +} + +static +void init_ustorm_task_contexts(struct ustorm_iscsi_task_st_ctx *ustorm_st_cxt, + struct ustorm_iscsi_task_ag_ctx *ustorm_ag_cxt, + u32 remaining_recv_len, + u32 expected_data_transfer_len, + u8 num_sges, bool tx_dif_conn_err_en) +{ + u32 val; + + ustorm_st_cxt->rem_rcv_len = cpu_to_le32(remaining_recv_len); + ustorm_ag_cxt->exp_data_acked = cpu_to_le32(expected_data_transfer_len); + val = cpu_to_le32(expected_data_transfer_len); + ustorm_st_cxt->exp_data_transfer_len = val; + SET_FIELD(ustorm_st_cxt->reg1.reg1_map, ISCSI_REG1_NUM_SGES, num_sges); + SET_FIELD(ustorm_ag_cxt->flags2, + USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN, + tx_dif_conn_err_en ? 1 : 0); +} + +static +void set_rw_exp_data_acked_and_cont_len(struct iscsi_task_context *context, + struct iscsi_conn_params *conn_params, + enum iscsi_task_type task_type, + u32 task_size, + u32 exp_data_transfer_len, + u8 total_ahs_length) +{ + u32 max_unsolicited_data = 0, val; + + if (total_ahs_length && + (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE || + task_type == ISCSI_TASK_TYPE_INITIATOR_READ)) + SET_FIELD(context->ustorm_st_context.flags2, + USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST, 1); + + switch (task_type) { + case ISCSI_TASK_TYPE_INITIATOR_WRITE: + if (!conn_params->initial_r2t) + max_unsolicited_data = conn_params->first_burst_length; + else if (conn_params->immediate_data) + max_unsolicited_data = + min(conn_params->first_burst_length, + conn_params->max_send_pdu_length); + + context->ustorm_ag_context.exp_data_acked = + cpu_to_le32(total_ahs_length == 0 ? + min(exp_data_transfer_len, + max_unsolicited_data) : + ((u32)(total_ahs_length + + ISCSI_AHS_CNTL_SIZE))); + break; + case ISCSI_TASK_TYPE_TARGET_READ: + val = cpu_to_le32(exp_data_transfer_len); + context->ustorm_ag_context.exp_data_acked = val; + break; + case ISCSI_TASK_TYPE_INITIATOR_READ: + context->ustorm_ag_context.exp_data_acked = + cpu_to_le32((total_ahs_length == 0 ? 0 : + total_ahs_length + + ISCSI_AHS_CNTL_SIZE)); + break; + case ISCSI_TASK_TYPE_TARGET_WRITE: + val = cpu_to_le32(task_size); + context->ustorm_ag_context.exp_cont_len = val; + break; + default: + break; + } +} + +static +void init_rtdif_task_context(struct rdif_task_context *rdif_context, + struct tdif_task_context *tdif_context, + struct scsi_dif_task_params *dif_task_params, + enum iscsi_task_type task_type) +{ + u32 val; + + if (!dif_task_params->dif_on_network || !dif_task_params->dif_on_host) + return; + + if (task_type == ISCSI_TASK_TYPE_TARGET_WRITE || + task_type == ISCSI_TASK_TYPE_INITIATOR_READ) { + rdif_context->app_tag_value = + cpu_to_le16(dif_task_params->application_tag); + rdif_context->partial_crc_value = cpu_to_le16(0xffff); + val = cpu_to_le32(dif_task_params->initial_ref_tag); + rdif_context->initial_ref_tag = val; + rdif_context->app_tag_mask = + cpu_to_le16(dif_task_params->application_tag_mask); + SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_CRC_SEED, + dif_task_params->crc_seed ? 1 : 0); + SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_HOSTGUARDTYPE, + dif_task_params->host_guard_type); + SET_FIELD(rdif_context->flags0, + RDIF_TASK_CONTEXT_PROTECTIONTYPE, + dif_task_params->protection_type); + SET_FIELD(rdif_context->flags0, + RDIF_TASK_CONTEXT_INITIALREFTAGVALID, 1); + SET_FIELD(rdif_context->flags0, + RDIF_TASK_CONTEXT_KEEPREFTAGCONST, + dif_task_params->keep_ref_tag_const ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_VALIDATEAPPTAG, + (dif_task_params->validate_app_tag && + dif_task_params->dif_on_network) ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_VALIDATEGUARD, + (dif_task_params->validate_guard && + dif_task_params->dif_on_network) ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_VALIDATEREFTAG, + (dif_task_params->validate_ref_tag && + dif_task_params->dif_on_network) ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_HOSTINTERFACE, + dif_task_params->dif_on_host ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_NETWORKINTERFACE, + dif_task_params->dif_on_network ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDGUARD, + dif_task_params->forward_guard ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDAPPTAG, + dif_task_params->forward_app_tag ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDREFTAG, + dif_task_params->forward_ref_tag ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK, + dif_task_params->forward_app_tag_with_mask ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK, + dif_task_params->forward_ref_tag_with_mask ? 1 : 0); + SET_FIELD(rdif_context->flags1, + RDIF_TASK_CONTEXT_INTERVALSIZE, + dif_task_params->dif_block_size_log - 9); + SET_FIELD(rdif_context->state, + RDIF_TASK_CONTEXT_REFTAGMASK, + dif_task_params->ref_tag_mask); + SET_FIELD(rdif_context->state, RDIF_TASK_CONTEXT_IGNOREAPPTAG, + dif_task_params->ignore_app_tag); + } + + if (task_type == ISCSI_TASK_TYPE_TARGET_READ || + task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) { + tdif_context->app_tag_value = + cpu_to_le16(dif_task_params->application_tag); + tdif_context->partial_crc_valueB = + cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000); + tdif_context->partial_crc_value_a = + cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000); + SET_FIELD(tdif_context->flags0, TDIF_TASK_CONTEXT_CRC_SEED, + dif_task_params->crc_seed ? 1 : 0); + + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_SETERRORWITHEOP, + dif_task_params->tx_dif_conn_err_en ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDGUARD, + dif_task_params->forward_guard ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDAPPTAG, + dif_task_params->forward_app_tag ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDREFTAG, + dif_task_params->forward_ref_tag ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_INTERVALSIZE, + dif_task_params->dif_block_size_log - 9); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_HOSTINTERFACE, + dif_task_params->dif_on_host ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_NETWORKINTERFACE, + dif_task_params->dif_on_network ? 1 : 0); + val = cpu_to_le32(dif_task_params->initial_ref_tag); + tdif_context->initial_ref_tag = val; + tdif_context->app_tag_mask = + cpu_to_le16(dif_task_params->application_tag_mask); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_HOSTGUARDTYPE, + dif_task_params->host_guard_type); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_PROTECTIONTYPE, + dif_task_params->protection_type); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_INITIALREFTAGVALID, + dif_task_params->initial_ref_tag_is_valid ? 1 : 0); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_KEEPREFTAGCONST, + dif_task_params->keep_ref_tag_const ? 1 : 0); + SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_VALIDATEGUARD, + (dif_task_params->validate_guard && + dif_task_params->dif_on_host) ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_VALIDATEAPPTAG, + (dif_task_params->validate_app_tag && + dif_task_params->dif_on_host) ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_VALIDATEREFTAG, + (dif_task_params->validate_ref_tag && + dif_task_params->dif_on_host) ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK, + dif_task_params->forward_app_tag_with_mask ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK, + dif_task_params->forward_ref_tag_with_mask ? 1 : 0); + SET_FIELD(tdif_context->flags1, + TDIF_TASK_CONTEXT_REFTAGMASK, + dif_task_params->ref_tag_mask); + SET_FIELD(tdif_context->flags0, + TDIF_TASK_CONTEXT_IGNOREAPPTAG, + dif_task_params->ignore_app_tag ? 1 : 0); + } +} + +static void set_local_completion_context(struct iscsi_task_context *context) +{ + SET_FIELD(context->ystorm_st_context.state.flags, + YSTORM_ISCSI_TASK_STATE_LOCAL_COMP, 1); + SET_FIELD(context->ustorm_st_context.flags, + USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1); +} + +static int init_rw_iscsi_task(struct iscsi_task_params *task_params, + enum iscsi_task_type task_type, + struct iscsi_conn_params *conn_params, + struct iscsi_common_hdr *pdu_header, + struct scsi_sgl_task_params *sgl_task_params, + struct scsi_initiator_cmd_params *cmd_params, + struct scsi_dif_task_params *dif_task_params) +{ + u32 exp_data_transfer_len = conn_params->max_burst_length; + struct iscsi_task_context *cxt; + bool slow_io = false; + u32 task_size, val; + u8 num_sges = 0; + + task_size = calc_rw_task_size(task_params, task_type, sgl_task_params, + dif_task_params); + + init_default_iscsi_task(task_params, (struct data_hdr *)pdu_header, + task_type); + + cxt = task_params->context; + + val = cpu_to_le32(task_size); + cxt->ystorm_st_context.pdu_hdr.cmd.expected_transfer_length = val; + init_initiator_rw_cdb_ystorm_context(&cxt->ystorm_st_context, + cmd_params); + val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.lo); + cxt->mstorm_st_context.sense_db.lo = val; + + val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.hi); + cxt->mstorm_st_context.sense_db.hi = val; + + if (task_params->tx_io_size) { + init_dif_context_flags(&cxt->ystorm_st_context.state.dif_flags, + dif_task_params); + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + sgl_task_params); + + slow_io = scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge); + + num_sges = !slow_io ? min_t(u16, sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR) : + ISCSI_WQE_NUM_SGES_SLOWIO; + + if (slow_io) { + SET_FIELD(cxt->ystorm_st_context.state.flags, + YSTORM_ISCSI_TASK_STATE_SLOW_IO, 1); + } + } else if (task_params->rx_io_size) { + init_dif_context_flags(&cxt->mstorm_st_context.dif_flags, + dif_task_params); + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + sgl_task_params); + num_sges = !scsi_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge) ? + min_t(u16, sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR) : + ISCSI_WQE_NUM_SGES_SLOWIO; + cxt->mstorm_st_context.rem_task_size = cpu_to_le32(task_size); + } + + if (exp_data_transfer_len > task_size || + task_type != ISCSI_TASK_TYPE_TARGET_WRITE) + exp_data_transfer_len = task_size; + + init_ustorm_task_contexts(&task_params->context->ustorm_st_context, + &task_params->context->ustorm_ag_context, + task_size, exp_data_transfer_len, num_sges, + dif_task_params ? + dif_task_params->tx_dif_conn_err_en : false); + + set_rw_exp_data_acked_and_cont_len(task_params->context, conn_params, + task_type, task_size, + exp_data_transfer_len, + GET_FIELD(pdu_header->hdr_second_dword, + ISCSI_CMD_HDR_TOTAL_AHS_LEN)); + + if (dif_task_params) + init_rtdif_task_context(&task_params->context->rdif_context, + &task_params->context->tdif_context, + dif_task_params, task_type); + + init_sqe(task_params, sgl_task_params, dif_task_params, pdu_header, + cmd_params, task_type, false); + + return 0; +} + +int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params, + struct iscsi_conn_params *conn_params, + struct scsi_initiator_cmd_params *cmd_params, + struct iscsi_cmd_hdr *cmd_header, + struct scsi_sgl_task_params *tx_sgl_params, + struct scsi_sgl_task_params *rx_sgl_params, + struct scsi_dif_task_params *dif_task_params) +{ + if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_WRITE)) + return init_rw_iscsi_task(task_params, + ISCSI_TASK_TYPE_INITIATOR_WRITE, + conn_params, + (struct iscsi_common_hdr *)cmd_header, + tx_sgl_params, cmd_params, + dif_task_params); + else if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_READ)) + return init_rw_iscsi_task(task_params, + ISCSI_TASK_TYPE_INITIATOR_READ, + conn_params, + (struct iscsi_common_hdr *)cmd_header, + rx_sgl_params, cmd_params, + dif_task_params); + else + return -1; +} + +int init_initiator_login_request_task(struct iscsi_task_params *task_params, + struct iscsi_login_req_hdr *login_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)login_header, + ISCSI_TASK_TYPE_MIDPATH); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_params->total_buffer_size : 0, 0, + 0); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_params); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_params->total_buffer_size : 0); + + init_sqe(task_params, tx_params, NULL, + (struct iscsi_common_hdr *)login_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_nop_out_task(struct iscsi_task_params *task_params, + struct iscsi_nop_out_hdr *nop_out_pdu_header, + struct scsi_sgl_task_params *tx_sgl_task_params, + struct scsi_sgl_task_params *rx_sgl_task_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)nop_out_pdu_header, + ISCSI_TASK_TYPE_MIDPATH); + + if (nop_out_pdu_header->itt == ISCSI_ITT_ALL_ONES) + set_local_completion_context(task_params->context); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_sgl_task_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_sgl_task_params); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_sgl_task_params->total_buffer_size : 0, + 0, 0); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : + 0); + + init_sqe(task_params, tx_sgl_task_params, NULL, + (struct iscsi_common_hdr *)nop_out_pdu_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_logout_request_task(struct iscsi_task_params *task_params, + struct iscsi_logout_req_hdr *logout_hdr, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)logout_hdr, + ISCSI_TASK_TYPE_MIDPATH); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_params); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_params->total_buffer_size : 0, + 0, 0); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_params->total_buffer_size : 0); + + init_sqe(task_params, tx_params, NULL, + (struct iscsi_common_hdr *)logout_hdr, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_tmf_request_task(struct iscsi_task_params *task_params, + struct iscsi_tmf_request_hdr *tmf_header) +{ + init_default_iscsi_task(task_params, (struct data_hdr *)tmf_header, + ISCSI_TASK_TYPE_MIDPATH); + + init_sqe(task_params, NULL, NULL, + (struct iscsi_common_hdr *)tmf_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_initiator_text_request_task(struct iscsi_task_params *task_params, + struct iscsi_text_request_hdr *text_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params) +{ + struct iscsi_task_context *cxt; + + cxt = task_params->context; + + init_default_iscsi_task(task_params, + (struct data_hdr *)text_header, + ISCSI_TASK_TYPE_MIDPATH); + + if (task_params->tx_io_size) + init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params, + &cxt->ystorm_st_context.state.data_desc, + tx_params); + + if (task_params->rx_io_size) + init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params, + &cxt->mstorm_st_context.data_desc, + rx_params); + + cxt->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_params->total_buffer_size : 0); + + init_ustorm_task_contexts(&cxt->ustorm_st_context, + &cxt->ustorm_ag_context, + task_params->rx_io_size ? + rx_params->total_buffer_size : 0, + task_params->tx_io_size ? + tx_params->total_buffer_size : 0, 0, 0); + + init_sqe(task_params, tx_params, NULL, + (struct iscsi_common_hdr *)text_header, NULL, + ISCSI_TASK_TYPE_MIDPATH, false); + + return 0; +} + +int init_cleanup_task(struct iscsi_task_params *task_params) +{ + init_sqe(task_params, NULL, NULL, NULL, NULL, ISCSI_TASK_TYPE_MIDPATH, + true); + return 0; +} diff --git a/drivers/scsi/qedi/qedi_fw_iscsi.h b/drivers/scsi/qedi/qedi_fw_iscsi.h new file mode 100644 index 000000000000..b6f24f91849d --- /dev/null +++ b/drivers/scsi/qedi/qedi_fw_iscsi.h @@ -0,0 +1,117 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QEDI_FW_ISCSI_H_ +#define _QEDI_FW_ISCSI_H_ + +#include "qedi_fw_scsi.h" + +struct iscsi_task_params { + struct iscsi_task_context *context; + struct iscsi_wqe *sqe; + u32 tx_io_size; + u32 rx_io_size; + u16 conn_icid; + u16 itid; + u8 cq_rss_number; +}; + +struct iscsi_conn_params { + u32 first_burst_length; + u32 max_send_pdu_length; + u32 max_burst_length; + bool initial_r2t; + bool immediate_data; +}; + +/* @brief init_initiator_read_iscsi_task - initializes iSCSI Initiator Read + * task context. + * + * @param task_params - Pointer to task parameters struct + * @param conn_params - Connection Parameters + * @param cmd_params - command specific parameters + * @param cmd_pdu_header - PDU Header Parameters + * @param sgl_task_params - Pointer to SGL task params + * @param dif_task_params - Pointer to DIF parameters struct + */ +int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params, + struct iscsi_conn_params *conn_params, + struct scsi_initiator_cmd_params *cmd_params, + struct iscsi_cmd_hdr *cmd_pdu_header, + struct scsi_sgl_task_params *tx_sgl_params, + struct scsi_sgl_task_params *rx_sgl_params, + struct scsi_dif_task_params *dif_task_params); + +/* @brief init_initiator_login_request_task - initializes iSCSI Initiator Login + * Request task context. + * + * @param task_params - Pointer to task parameters struct + * @param login_req_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to SGL task params + * @param rx_sgl_task_params - Pointer to SGL task params + */ +int init_initiator_login_request_task(struct iscsi_task_params *task_params, + struct iscsi_login_req_hdr *login_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params); + +/* @brief init_initiator_nop_out_task - initializes iSCSI Initiator NOP Out + * task context. + * + * @param task_params - Pointer to task parameters struct + * @param nop_out_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to SGL task params + * @param rx_sgl_task_params - Pointer to SGL task params + */ +int init_initiator_nop_out_task(struct iscsi_task_params *task_params, + struct iscsi_nop_out_hdr *nop_out_pdu_header, + struct scsi_sgl_task_params *tx_sgl_params, + struct scsi_sgl_task_params *rx_sgl_params); + +/* @brief init_initiator_logout_request_task - initializes iSCSI Initiator + * Logout Request task context. + * + * @param task_params - Pointer to task parameters struct + * @param logout_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to SGL task params + * @param rx_sgl_task_params - Pointer to SGL task params + */ +int init_initiator_logout_request_task(struct iscsi_task_params *task_params, + struct iscsi_logout_req_hdr *logout_hdr, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params); + +/* @brief init_initiator_tmf_request_task - initializes iSCSI Initiator TMF + * task context. + * + * @param task_params - Pointer to task parameters struct + * @param tmf_pdu_header - PDU Header Parameters + */ +int init_initiator_tmf_request_task(struct iscsi_task_params *task_params, + struct iscsi_tmf_request_hdr *tmf_header); + +/* @brief init_initiator_text_request_task - initializes iSCSI Initiator Text + * Request task context. + * + * @param task_params - Pointer to task parameters struct + * @param text_request_pdu_header - PDU Header Parameters + * @param tx_sgl_task_params - Pointer to Tx SGL task params + * @param rx_sgl_task_params - Pointer to Rx SGL task params + */ +int init_initiator_text_request_task(struct iscsi_task_params *task_params, + struct iscsi_text_request_hdr *text_header, + struct scsi_sgl_task_params *tx_params, + struct scsi_sgl_task_params *rx_params); + +/* @brief init_cleanup_task - initializes Clean task (SQE) + * + * @param task_params - Pointer to task parameters struct + */ +int init_cleanup_task(struct iscsi_task_params *task_params); +#endif diff --git a/drivers/scsi/qedi/qedi_fw_scsi.h b/drivers/scsi/qedi/qedi_fw_scsi.h new file mode 100644 index 000000000000..cdaf918f1019 --- /dev/null +++ b/drivers/scsi/qedi/qedi_fw_scsi.h @@ -0,0 +1,55 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QEDI_FW_SCSI_H_ +#define _QEDI_FW_SCSI_H_ + +#include +#include +#include "qedi_hsi.h" +#include + +struct scsi_sgl_task_params { + struct scsi_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + bool small_mid_sge; +}; + +struct scsi_dif_task_params { + u32 initial_ref_tag; + bool initial_ref_tag_is_valid; + u16 application_tag; + u16 application_tag_mask; + u16 dif_block_size_log; + bool dif_on_network; + bool dif_on_host; + u8 host_guard_type; + u8 protection_type; + u8 ref_tag_mask; + bool crc_seed; + bool tx_dif_conn_err_en; + bool ignore_app_tag; + bool keep_ref_tag_const; + bool validate_guard; + bool validate_app_tag; + bool validate_ref_tag; + bool forward_guard; + bool forward_app_tag; + bool forward_ref_tag; + bool forward_app_tag_with_mask; + bool forward_ref_tag_with_mask; +}; + +struct scsi_initiator_cmd_params { + struct scsi_sge extended_cdb_sge; + struct regpair sense_data_buffer_phys_addr; +}; +#endif diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index b9f79d36142d..d5eff68507e5 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -175,7 +175,7 @@ static void qedi_destroy_cmd_pool(struct qedi_ctx *qedi, if (cmd->io_tbl.sge_tbl) dma_free_coherent(&qedi->pdev->dev, QEDI_ISCSI_MAX_BDS_PER_CMD * - sizeof(struct iscsi_sge), + sizeof(struct scsi_sge), cmd->io_tbl.sge_tbl, cmd->io_tbl.sge_tbl_dma); @@ -191,7 +191,7 @@ static int qedi_alloc_sget(struct qedi_ctx *qedi, struct iscsi_session *session, struct qedi_cmd *cmd) { struct qedi_io_bdt *io = &cmd->io_tbl; - struct iscsi_sge *sge; + struct scsi_sge *sge; io->sge_tbl = dma_alloc_coherent(&qedi->pdev->dev, QEDI_ISCSI_MAX_BDS_PER_CMD * @@ -708,22 +708,20 @@ static void qedi_conn_get_stats(struct iscsi_cls_conn *cls_conn, static void qedi_iscsi_prep_generic_pdu_bd(struct qedi_conn *qedi_conn) { - struct iscsi_sge *bd_tbl; + struct scsi_sge *bd_tbl; - bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; + bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl; bd_tbl->sge_addr.hi = (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32); bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.req_dma_addr; bd_tbl->sge_len = qedi_conn->gen_pdu.req_wr_ptr - qedi_conn->gen_pdu.req_buf; - bd_tbl->reserved0 = 0; - bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; + bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl; bd_tbl->sge_addr.hi = (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32); bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.resp_dma_addr; bd_tbl->sge_len = ISCSI_DEF_MAX_RECV_SEG_LEN; - bd_tbl->reserved0 = 0; } static int qedi_iscsi_send_generic_request(struct iscsi_task *task) diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h index d3c06bbddb4e..3247287cb0e7 100644 --- a/drivers/scsi/qedi/qedi_iscsi.h +++ b/drivers/scsi/qedi/qedi_iscsi.h @@ -102,7 +102,7 @@ struct qedi_endpoint { #define QEDI_SQ_WQES_MIN 16 struct qedi_io_bdt { - struct iscsi_sge *sge_tbl; + struct scsi_sge *sge_tbl; dma_addr_t sge_tbl_dma; u16 sge_valid; }; diff --git a/drivers/scsi/qedi/qedi_version.h b/drivers/scsi/qedi/qedi_version.h index 9543a1b139d4..d61e3ac22e67 100644 --- a/drivers/scsi/qedi/qedi_version.h +++ b/drivers/scsi/qedi/qedi_version.h @@ -7,8 +7,8 @@ * this source tree. */ -#define QEDI_MODULE_VERSION "8.10.3.0" +#define QEDI_MODULE_VERSION "8.10.4.0" #define QEDI_DRIVER_MAJOR_VER 8 #define QEDI_DRIVER_MINOR_VER 10 -#define QEDI_DRIVER_REV_VER 3 +#define QEDI_DRIVER_REV_VER 4 #define QEDI_DRIVER_ENG_VER 0 diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 52966b9bfde3..fbab6e0514f0 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -100,8 +100,8 @@ #define MAX_NUM_LL2_TX_STATS_COUNTERS 32 #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 10 -#define FW_REVISION_VERSION 10 +#define FW_MINOR_VERSION 15 +#define FW_REVISION_VERSION 3 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -187,6 +187,9 @@ /* DEMS */ #define DQ_DEMS_LEGACY 0 +#define DQ_DEMS_TOE_MORE_TO_SEND 3 +#define DQ_DEMS_TOE_LOCAL_ADV_WND 4 +#define DQ_DEMS_ROCE_CQ_CONS 7 /* XCM agg val selection */ #define DQ_XCM_AGG_VAL_SEL_WORD2 0 @@ -214,6 +217,9 @@ #define DQ_XCM_ISCSI_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3 #define DQ_XCM_ISCSI_EXP_STAT_SN_CMD DQ_XCM_AGG_VAL_SEL_REG6 #define DQ_XCM_ROCE_SQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_TOE_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_TOE_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3 +#define DQ_XCM_TOE_LOCAL_ADV_WND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG4 /* UCM agg val selection (HW) */ #define DQ_UCM_AGG_VAL_SEL_WORD0 0 @@ -269,6 +275,8 @@ #define DQ_XCM_ISCSI_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19) #define DQ_XCM_ISCSI_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) #define DQ_XCM_ISCSI_PROC_ONLY_CLEANUP_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF23) +#define DQ_XCM_TOE_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_TOE_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) /* UCM agg counter flag selection (HW) */ #define DQ_UCM_AGG_FLG_SHIFT_CF0 0 @@ -285,6 +293,9 @@ #define DQ_UCM_ETH_PMD_RX_ARM_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) #define DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4) #define DQ_UCM_ROCE_CQ_ARM_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) +#define DQ_UCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF3) +#define DQ_UCM_TOE_SLOW_PATH_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4) +#define DQ_UCM_TOE_DQ_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) /* TCM agg counter flag selection (HW) */ #define DQ_TCM_AGG_FLG_SHIFT_CF0 0 @@ -301,6 +312,9 @@ #define DQ_TCM_FCOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) #define DQ_TCM_ISCSI_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) #define DQ_TCM_ISCSI_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) +#define DQ_TCM_TOE_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) +#define DQ_TCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) +#define DQ_TCM_IWARP_POST_RQ_CF_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) /* PWM address mapping */ #define DQ_PWM_OFFSET_DPM_BASE 0x0 @@ -689,6 +703,16 @@ struct iscsi_eqe_data { #define ISCSI_EQE_DATA_RESERVED0_SHIFT 7 }; +struct rdma_eqe_destroy_qp { + __le32 cid; + u8 reserved[4]; +}; + +union rdma_eqe_data { + struct regpair async_handle; + struct rdma_eqe_destroy_qp rdma_destroy_qp_data; +}; + struct malicious_vf_eqe_data { u8 vf_id; u8 err_id; @@ -705,9 +729,9 @@ union event_ring_data { u8 bytes[8]; struct vf_pf_channel_eqe_data vf_pf_channel; struct iscsi_eqe_data iscsi_info; + union rdma_eqe_data rdma_data; struct malicious_vf_eqe_data malicious_vf; struct initial_cleanup_eqe_data vf_init_cleanup; - struct regpair roce_handle; }; /* Event Ring Entry */ diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 4b402fb0eaad..34d93eb5bfba 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -49,6 +49,9 @@ #define ETH_RX_CQE_PAGE_SIZE_BYTES 4096 #define ETH_RX_NUM_NEXT_PAGE_BDS 2 +#define ETH_MAX_TUNN_LSO_INNER_IPV4_OFFSET 253 +#define ETH_MAX_TUNN_LSO_INNER_IPV6_OFFSET 251 + #define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1 #define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18 #define ETH_TX_MAX_BDS_PER_LSO_PACKET 255 diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index 2e417a45c5f7..947a635d04bb 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -109,13 +109,6 @@ struct fcoe_conn_terminate_ramrod_data { struct regpair terminate_params_addr; }; -struct fcoe_fast_sgl_ctx { - struct regpair sgl_start_addr; - __le32 sgl_byte_offset; - __le16 task_reuse_cnt; - __le16 init_offset_in_first_sge; -}; - struct fcoe_slow_sgl_ctx { struct regpair base_sgl_addr; __le16 curr_sge_off; @@ -124,23 +117,16 @@ struct fcoe_slow_sgl_ctx { __le16 reserved; }; -struct fcoe_sge { - struct regpair sge_addr; - __le16 size; - __le16 reserved0; - u8 reserved1[3]; - u8 is_valid_sge; -}; - -union fcoe_data_desc_ctx { - struct fcoe_fast_sgl_ctx fast; - struct fcoe_slow_sgl_ctx slow; - struct fcoe_sge single_sge; -}; - union fcoe_dix_desc_ctx { struct fcoe_slow_sgl_ctx dix_sgl; - struct fcoe_sge cached_dix_sge; + struct scsi_sge cached_dix_sge; +}; + +struct fcoe_fast_sgl_ctx { + struct regpair sgl_start_addr; + __le32 sgl_byte_offset; + __le16 task_reuse_cnt; + __le16 init_offset_in_first_sge; }; struct fcoe_fcp_cmd_payload { @@ -172,57 +158,6 @@ enum fcoe_mode_type { MAX_FCOE_MODE_TYPE }; -struct fcoe_mstorm_fcoe_task_st_ctx_fp { - __le16 flags; -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_MASK 0x7FFF -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_SHIFT 0 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_SHIFT 15 - __le16 difDataResidue; - __le16 parent_id; - __le16 single_sge_saved_offset; - __le32 data_2_trns_rem; - __le32 offset_in_io; - union fcoe_dix_desc_ctx dix_desc; - union fcoe_data_desc_ctx data_desc; -}; - -struct fcoe_mstorm_fcoe_task_st_ctx_non_fp { - __le16 flags; -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_MASK 0x3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_SHIFT 0 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_SHIFT 2 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_SHIFT 3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_MASK 0xF -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_SHIFT 4 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_MASK 0x3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_SHIFT 8 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_SHIFT 10 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_SHIFT 11 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_SHIFT 12 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_SHIFT 13 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_SHIFT 14 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_MASK 0x1 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_SHIFT 15 - u8 tx_rx_sgl_mode; -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_MASK 0x7 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_SHIFT 0 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_MASK 0x7 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_SHIFT 3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_MASK 0x3 -#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_SHIFT 6 - u8 rsrv2; - __le32 num_prm_zero_read; - struct regpair rsp_buf_addr; -}; - struct fcoe_rx_stat { struct regpair fcoe_rx_byte_cnt; struct regpair fcoe_rx_data_pkt_cnt; @@ -236,16 +171,6 @@ struct fcoe_rx_stat { __le32 rsrv; }; -enum fcoe_sgl_mode { - FCOE_SLOW_SGL, - FCOE_SINGLE_FAST_SGE, - FCOE_2_FAST_SGE, - FCOE_3_FAST_SGE, - FCOE_4_FAST_SGE, - FCOE_MUL_FAST_SGES, - MAX_FCOE_SGL_MODE -}; - struct fcoe_stat_ramrod_data { struct regpair stat_params_addr; }; @@ -328,22 +253,24 @@ union fcoe_tx_info_union_ctx { struct ystorm_fcoe_task_st_ctx { u8 task_type; u8 sgl_mode; -#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x7 +#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1 #define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 0 -#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK 0x1F -#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT 3 +#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK 0x7F +#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT 1 u8 cached_dix_sge; u8 expect_first_xfer; __le32 num_pbf_zero_write; union protection_info_union_ctx protection_info_union; __le32 data_2_trns_rem; + struct scsi_sgl_params sgl_params; + u8 reserved1[12]; union fcoe_tx_info_union_ctx tx_info_union; union fcoe_dix_desc_ctx dix_desc; - union fcoe_data_desc_ctx data_desc; + struct scsi_cached_sges data_desc; __le16 ox_id; __le16 rx_id; __le32 task_rety_identifier; - __le32 reserved1[2]; + u8 reserved2[8]; }; struct ystorm_fcoe_task_ag_ctx { @@ -484,22 +411,22 @@ struct tstorm_fcoe_task_ag_ctx { struct fcoe_tstorm_fcoe_task_st_ctx_read_write { union fcoe_cleanup_addr_exp_ro_union cleanup_addr_exp_ro_union; __le16 flags; -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK 0x7 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK 0x1 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_SHIFT 0 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT 3 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT 1 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT 4 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT 2 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT 5 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT 3 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 6 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 4 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_MASK 0x1 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT 7 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT 5 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_MASK 0x3 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT 8 -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK 0x3F -#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT 10 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT 6 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK 0xFF +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT 8 __le16 seq_cnt; u8 seq_id; u8 ooo_rx_seq_id; @@ -582,8 +509,34 @@ struct mstorm_fcoe_task_ag_ctx { }; struct mstorm_fcoe_task_st_ctx { - struct fcoe_mstorm_fcoe_task_st_ctx_non_fp non_fp; - struct fcoe_mstorm_fcoe_task_st_ctx_fp fp; + struct regpair rsp_buf_addr; + __le32 rsrv[2]; + struct scsi_sgl_params sgl_params; + __le32 data_2_trns_rem; + __le32 data_buffer_offset; + __le16 parent_id; + __le16 flags; +#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_MASK 0xF +#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_SHIFT 0 +#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_SHIFT 4 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_SHIFT 6 +#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_SHIFT 7 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_SHIFT 8 +#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_SHIFT 10 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_SHIFT 11 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_SHIFT 12 +#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 13 +#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_SHIFT 14 + struct scsi_cached_sges data_desc; }; struct ustorm_fcoe_task_ag_ctx { @@ -646,6 +599,7 @@ struct ustorm_fcoe_task_ag_ctx { struct fcoe_task_context { struct ystorm_fcoe_task_st_ctx ystorm_st_context; + struct regpair ystorm_st_padding[2]; struct tdif_task_context tdif_context; struct ystorm_fcoe_task_ag_ctx ystorm_ag_context; struct tstorm_fcoe_task_ag_ctx tstorm_ag_context; @@ -668,20 +622,20 @@ struct fcoe_tx_stat { struct fcoe_wqe { __le16 task_id; __le16 flags; -#define FCOE_WQE_REQ_TYPE_MASK 0xF -#define FCOE_WQE_REQ_TYPE_SHIFT 0 -#define FCOE_WQE_SGL_MODE_MASK 0x7 -#define FCOE_WQE_SGL_MODE_SHIFT 4 -#define FCOE_WQE_CONTINUATION_MASK 0x1 -#define FCOE_WQE_CONTINUATION_SHIFT 7 -#define FCOE_WQE_INVALIDATE_PTU_MASK 0x1 -#define FCOE_WQE_INVALIDATE_PTU_SHIFT 8 -#define FCOE_WQE_SUPER_IO_MASK 0x1 -#define FCOE_WQE_SUPER_IO_SHIFT 9 -#define FCOE_WQE_SEND_AUTO_RSP_MASK 0x1 -#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 10 -#define FCOE_WQE_RESERVED0_MASK 0x1F -#define FCOE_WQE_RESERVED0_SHIFT 11 +#define FCOE_WQE_REQ_TYPE_MASK 0xF +#define FCOE_WQE_REQ_TYPE_SHIFT 0 +#define FCOE_WQE_SGL_MODE_MASK 0x1 +#define FCOE_WQE_SGL_MODE_SHIFT 4 +#define FCOE_WQE_CONTINUATION_MASK 0x1 +#define FCOE_WQE_CONTINUATION_SHIFT 5 +#define FCOE_WQE_SEND_AUTO_RSP_MASK 0x1 +#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 6 +#define FCOE_WQE_RESERVED_MASK 0x1 +#define FCOE_WQE_RESERVED_SHIFT 7 +#define FCOE_WQE_NUM_SGES_MASK 0xF +#define FCOE_WQE_NUM_SGES_SHIFT 8 +#define FCOE_WQE_RESERVED1_MASK 0xF +#define FCOE_WQE_RESERVED1_SHIFT 12 union fcoe_additional_info_union additional_info_union; }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 4c5747babcf6..69949f8e354b 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -39,17 +39,9 @@ /* iSCSI HSI constants */ #define ISCSI_DEFAULT_MTU (1500) -/* Current iSCSI HSI version number composed of two fields (16 bit) */ -#define ISCSI_HSI_MAJOR_VERSION (0) -#define ISCSI_HSI_MINOR_VERSION (0) - /* KWQ (kernel work queue) layer codes */ #define ISCSI_SLOW_PATH_LAYER_CODE (6) -/* CQE completion status */ -#define ISCSI_EQE_COMPLETION_SUCCESS (0x0) -#define ISCSI_EQE_RST_CONN_RCVD (0x1) - /* iSCSI parameter defaults */ #define ISCSI_DEFAULT_HEADER_DIGEST (0) #define ISCSI_DEFAULT_DATA_DIGEST (0) @@ -68,6 +60,10 @@ #define ISCSI_MIN_VAL_MAX_OUTSTANDING_R2T (1) #define ISCSI_MAX_VAL_MAX_OUTSTANDING_R2T (0xff) +#define ISCSI_AHS_CNTL_SIZE 4 + +#define ISCSI_WQE_NUM_SGES_SLOWIO (0xf) + /* iSCSI reserved params */ #define ISCSI_ITT_ALL_ONES (0xffffffff) #define ISCSI_TTT_ALL_ONES (0xffffffff) @@ -173,19 +169,6 @@ struct iscsi_async_msg_hdr { __le32 reserved7; }; -struct iscsi_sge { - struct regpair sge_addr; - __le16 sge_len; - __le16 reserved0; - __le32 reserved1; -}; - -struct iscsi_cached_sge_ctx { - struct iscsi_sge sge; - struct regpair reserved; - __le32 dsgl_curr_offset[2]; -}; - struct iscsi_cmd_hdr { __le16 reserved1; u8 flags_attr; @@ -229,8 +212,13 @@ struct iscsi_common_hdr { #define ISCSI_COMMON_HDR_DATA_SEG_LEN_SHIFT 0 #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_MASK 0xFF #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_SHIFT 24 - __le32 lun_reserved[4]; - __le32 data[6]; + struct regpair lun_reserved; + __le32 itt; + __le32 ttt; + __le32 cmdstat_sn; + __le32 exp_statcmd_sn; + __le32 max_cmd_sn; + __le32 data[3]; }; struct iscsi_conn_offload_params { @@ -246,8 +234,10 @@ struct iscsi_conn_offload_params { #define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 -#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x3F -#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 2 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x1F +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 3 u8 pbl_page_size_log; u8 pbe_page_size_log; u8 default_cq; @@ -278,8 +268,12 @@ struct iscsi_conn_update_ramrod_params { #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_SHIFT 2 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_MASK 0x1 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_SHIFT 3 -#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0xF -#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 4 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_SHIFT 4 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_SHIFT 5 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x3 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 6 u8 reserved0[3]; __le32 max_seq_size; __le32 max_send_pdu_length; @@ -312,7 +306,7 @@ struct iscsi_ext_cdb_cmd_hdr { __le32 expected_transfer_length; __le32 cmd_sn; __le32 exp_stat_sn; - struct iscsi_sge cdb_sge; + struct scsi_sge cdb_sge; }; struct iscsi_login_req_hdr { @@ -519,8 +513,8 @@ struct iscsi_logout_response_hdr { __le32 exp_cmd_sn; __le32 max_cmd_sn; __le32 reserved4; - __le16 time2retain; - __le16 time2wait; + __le16 time_2_retain; + __le16 time_2_wait; __le32 reserved5[1]; }; @@ -602,7 +596,7 @@ struct iscsi_tmf_response_hdr { #define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 struct regpair reserved0; __le32 itt; - __le32 rtt; + __le32 reserved1; __le32 stat_sn; __le32 exp_cmd_sn; __le32 max_cmd_sn; @@ -641,7 +635,7 @@ struct iscsi_reject_hdr { #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_MASK 0xFF #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_SHIFT 24 struct regpair reserved0; - __le32 reserved1; + __le32 all_ones; __le32 reserved2; __le32 stat_sn; __le32 exp_cmd_sn; @@ -688,7 +682,9 @@ struct iscsi_cqe_solicited { __le16 itid; u8 task_type; u8 fw_dbg_field; - __le32 reserved1[2]; + u8 caused_conn_err; + u8 reserved0[3]; + __le32 reserved1[1]; union iscsi_task_hdr iscsi_hdr; }; @@ -727,35 +723,6 @@ enum iscsi_cqe_unsolicited_type { MAX_ISCSI_CQE_UNSOLICITED_TYPE }; -struct iscsi_virt_sgl_ctx { - struct regpair sgl_base; - struct regpair dsgl_base; - __le32 sgl_initial_offset; - __le32 dsgl_initial_offset; - __le32 dsgl_curr_offset[2]; -}; - -struct iscsi_sgl_var_params { - u8 sgl_ptr; - u8 dsgl_ptr; - __le16 sge_offset; - __le16 dsge_offset; -}; - -struct iscsi_phys_sgl_ctx { - struct regpair sgl_base; - struct regpair dsgl_base; - u8 sgl_size; - u8 dsgl_size; - __le16 reserved; - struct iscsi_sgl_var_params var_params[2]; -}; - -union iscsi_data_desc_ctx { - struct iscsi_virt_sgl_ctx virt_sgl; - struct iscsi_phys_sgl_ctx phys_sgl; - struct iscsi_cached_sge_ctx cached_sge; -}; struct iscsi_debug_modes { u8 flags; @@ -771,8 +738,10 @@ struct iscsi_debug_modes { #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_SHIFT 4 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_MASK 0x1 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_SHIFT 5 -#define ISCSI_DEBUG_MODES_RESERVED0_MASK 0x3 -#define ISCSI_DEBUG_MODES_RESERVED0_SHIFT 6 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_SHIFT 6 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_SHIFT 7 }; struct iscsi_dif_flags { @@ -806,7 +775,6 @@ enum iscsi_eqe_opcode { ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2, ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR, ISCSI_EVENT_TYPE_TCP_CONN_ERROR, - ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES, MAX_ISCSI_EQE_OPCODE }; @@ -856,31 +824,11 @@ enum iscsi_error_types { ISCSI_CONN_ERROR_PROTOCOL_ERR_DIF_TX, ISCSI_CONN_ERROR_SENSE_DATA_LENGTH, ISCSI_CONN_ERROR_DATA_PLACEMENT_ERROR, + ISCSI_CONN_ERROR_INVALID_ITT, ISCSI_ERROR_UNKNOWN, MAX_ISCSI_ERROR_TYPES }; -struct iscsi_mflags { - u8 mflags; -#define ISCSI_MFLAGS_SLOW_IO_MASK 0x1 -#define ISCSI_MFLAGS_SLOW_IO_SHIFT 0 -#define ISCSI_MFLAGS_SINGLE_SGE_MASK 0x1 -#define ISCSI_MFLAGS_SINGLE_SGE_SHIFT 1 -#define ISCSI_MFLAGS_RESERVED_MASK 0x3F -#define ISCSI_MFLAGS_RESERVED_SHIFT 2 -}; - -struct iscsi_sgl { - struct regpair sgl_addr; - __le16 updated_sge_size; - __le16 updated_sge_offset; - __le32 byte_offset; -}; - -union iscsi_mstorm_sgl { - struct iscsi_sgl sgl_struct; - struct iscsi_sge single_sge; -}; enum iscsi_ramrod_cmd_id { ISCSI_RAMROD_CMD_ID_UNUSED = 0, @@ -896,10 +844,10 @@ enum iscsi_ramrod_cmd_id { struct iscsi_reg1 { __le32 reg1_map; -#define ISCSI_REG1_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_REG1_NUM_FAST_SGES_SHIFT 0 -#define ISCSI_REG1_RESERVED1_MASK 0x1FFFFFFF -#define ISCSI_REG1_RESERVED1_SHIFT 3 +#define ISCSI_REG1_NUM_SGES_MASK 0xF +#define ISCSI_REG1_NUM_SGES_SHIFT 0 +#define ISCSI_REG1_RESERVED1_MASK 0xFFFFFFF +#define ISCSI_REG1_RESERVED1_SHIFT 4 }; union iscsi_seq_num { @@ -967,22 +915,33 @@ struct iscsi_spe_func_init { }; struct ystorm_iscsi_task_state { - union iscsi_data_desc_ctx sgl_ctx_union; - __le32 buffer_offset[2]; - __le16 bytes_nxt_dif; - __le16 rxmit_bytes_nxt_dif; - union iscsi_seq_num seq_num_union; - u8 dif_bytes_leftover; - u8 rxmit_dif_bytes_leftover; - __le16 reuse_count; - struct iscsi_dif_flags dif_flags; - u8 local_comp; + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; __le32 exp_r2t_sn; - __le32 sgl_offset[2]; + __le32 buffer_offset; + union iscsi_seq_num seq_num; + struct iscsi_dif_flags dif_flags; + u8 flags; +#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_MASK 0x1 +#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_SHIFT 0 +#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_MASK 0x1 +#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_SHIFT 1 +#define YSTORM_ISCSI_TASK_STATE_RESERVED0_MASK 0x3F +#define YSTORM_ISCSI_TASK_STATE_RESERVED0_SHIFT 2 +}; + +struct ystorm_iscsi_task_rxmit_opt { + __le32 fast_rxmit_sge_offset; + __le32 scan_start_buffer_offset; + __le32 fast_rxmit_buffer_offset; + u8 scan_start_sgl_index; + u8 fast_rxmit_sgl_index; + __le16 reserved; }; struct ystorm_iscsi_task_st_ctx { struct ystorm_iscsi_task_state state; + struct ystorm_iscsi_task_rxmit_opt rxmit_opt; union iscsi_task_hdr pdu_hdr; }; @@ -1152,25 +1111,16 @@ struct ustorm_iscsi_task_ag_ctx { }; struct mstorm_iscsi_task_st_ctx { - union iscsi_mstorm_sgl sgl_union; - struct iscsi_dif_flags dif_flags; - struct iscsi_mflags flags; - u8 sgl_size; - u8 host_sge_index; - __le16 dix_cur_sge_offset; - __le16 dix_cur_sge_size; - __le32 data_offset_rtid; - u8 dif_offset; - u8 dix_sgl_size; - u8 dix_sge_index; - u8 task_type; - struct regpair sense_db; - struct regpair dix_sgl_cur_sge; + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; __le32 rem_task_size; - __le16 reuse_count; - __le16 dif_data_residue; - u8 reserved0[4]; - __le32 reserved1[1]; + __le32 data_buffer_offset; + u8 task_type; + struct iscsi_dif_flags dif_flags; + u8 reserved0[2]; + struct regpair sense_db; + __le32 expected_itt; + __le32 reserved1; }; struct ustorm_iscsi_task_st_ctx { @@ -1184,7 +1134,7 @@ struct ustorm_iscsi_task_st_ctx { #define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_SHIFT 0 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_MASK 0x7F #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_SHIFT 1 - u8 reserved2; + struct iscsi_dif_flags dif_flags; __le16 reserved3; __le32 reserved4; __le32 reserved5; @@ -1207,10 +1157,10 @@ struct ustorm_iscsi_task_st_ctx { #define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 -#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_MASK 0x1 -#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_SHIFT 4 -#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_MASK 0x1 -#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_SHIFT 5 +#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4 +#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_MASK 0x1 @@ -1220,7 +1170,6 @@ struct ustorm_iscsi_task_st_ctx { struct iscsi_task_context { struct ystorm_iscsi_task_st_ctx ystorm_st_context; - struct regpair ystorm_st_padding[2]; struct ystorm_iscsi_task_ag_ctx ystorm_ag_context; struct regpair ystorm_ag_padding[2]; struct tdif_task_context tdif_context; @@ -1272,32 +1221,22 @@ struct iscsi_uhqe { #define ISCSI_UHQE_TASK_ID_LO_SHIFT 24 }; -struct iscsi_wqe_field { - __le32 contlen_cdbsize_field; -#define ISCSI_WQE_FIELD_CONT_LEN_MASK 0xFFFFFF -#define ISCSI_WQE_FIELD_CONT_LEN_SHIFT 0 -#define ISCSI_WQE_FIELD_CDB_SIZE_MASK 0xFF -#define ISCSI_WQE_FIELD_CDB_SIZE_SHIFT 24 -}; - -union iscsi_wqe_field_union { - struct iscsi_wqe_field cont_field; - __le32 prev_tid; -}; struct iscsi_wqe { __le16 task_id; u8 flags; #define ISCSI_WQE_WQE_TYPE_MASK 0x7 #define ISCSI_WQE_WQE_TYPE_SHIFT 0 -#define ISCSI_WQE_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_WQE_NUM_FAST_SGES_SHIFT 3 -#define ISCSI_WQE_PTU_INVALIDATE_MASK 0x1 -#define ISCSI_WQE_PTU_INVALIDATE_SHIFT 6 +#define ISCSI_WQE_NUM_SGES_MASK 0xF +#define ISCSI_WQE_NUM_SGES_SHIFT 3 #define ISCSI_WQE_RESPONSE_MASK 0x1 #define ISCSI_WQE_RESPONSE_SHIFT 7 struct iscsi_dif_flags prot_flags; - union iscsi_wqe_field_union cont_prevtid_union; + __le32 contlen_cdbsize; +#define ISCSI_WQE_CONT_LEN_MASK 0xFFFFFF +#define ISCSI_WQE_CONT_LEN_SHIFT 0 +#define ISCSI_WQE_CDB_SIZE_MASK 0xFF +#define ISCSI_WQE_CDB_SIZE_SHIFT 24 }; enum iscsi_wqe_type { @@ -1318,17 +1257,15 @@ struct iscsi_xhqe { u8 total_ahs_length; u8 opcode; u8 flags; -#define ISCSI_XHQE_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_XHQE_NUM_FAST_SGES_SHIFT 0 -#define ISCSI_XHQE_FINAL_MASK 0x1 -#define ISCSI_XHQE_FINAL_SHIFT 3 -#define ISCSI_XHQE_SUPER_IO_MASK 0x1 -#define ISCSI_XHQE_SUPER_IO_SHIFT 4 -#define ISCSI_XHQE_STATUS_BIT_MASK 0x1 -#define ISCSI_XHQE_STATUS_BIT_SHIFT 5 -#define ISCSI_XHQE_RESERVED_MASK 0x3 -#define ISCSI_XHQE_RESERVED_SHIFT 6 - union iscsi_seq_num seq_num_union; +#define ISCSI_XHQE_FINAL_MASK 0x1 +#define ISCSI_XHQE_FINAL_SHIFT 0 +#define ISCSI_XHQE_STATUS_BIT_MASK 0x1 +#define ISCSI_XHQE_STATUS_BIT_SHIFT 1 +#define ISCSI_XHQE_NUM_SGES_MASK 0xF +#define ISCSI_XHQE_NUM_SGES_SHIFT 2 +#define ISCSI_XHQE_RESERVED0_MASK 0x3 +#define ISCSI_XHQE_RESERVED0_SHIFT 6 + union iscsi_seq_num seq_num; __le16 reserved1; }; diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index bad02df213df..866f063026de 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -38,4 +38,21 @@ #define ROCE_MAX_QPS (32 * 1024) +enum roce_async_events_type { + ROCE_ASYNC_EVENT_NONE = 0, + ROCE_ASYNC_EVENT_COMM_EST = 1, + ROCE_ASYNC_EVENT_SQ_DRAINED, + ROCE_ASYNC_EVENT_SRQ_LIMIT, + ROCE_ASYNC_EVENT_LAST_WQE_REACHED, + ROCE_ASYNC_EVENT_CQ_ERR, + ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR, + ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR, + ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR, + ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR, + ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR, + ROCE_ASYNC_EVENT_SRQ_EMPTY, + ROCE_ASYNC_EVENT_DESTROY_QP_DONE, + MAX_ROCE_ASYNC_EVENTS_TYPE +}; + #endif /* __ROCE_COMMON__ */ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 03f3e37ab059..08df82a096b6 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -40,6 +40,8 @@ #define BDQ_ID_IMM_DATA (1) #define BDQ_NUM_IDS (2) +#define SCSI_NUM_SGES_SLOW_SGL_THR 8 + #define BDQ_MAX_EXTERNAL_RING_SIZE (1 << 15) struct scsi_bd { @@ -52,6 +54,16 @@ struct scsi_bdq_ram_drv_data { __le16 reserved0[3]; }; +struct scsi_sge { + struct regpair sge_addr; + __le32 sge_len; + __le32 reserved; +}; + +struct scsi_cached_sges { + struct scsi_sge sge[4]; +}; + struct scsi_drv_cmdq { __le16 cmdq_cons; __le16 reserved0; @@ -99,11 +111,19 @@ struct scsi_ram_per_bdq_resource_drv_data { struct scsi_bdq_ram_drv_data drv_data_per_bdq_id[BDQ_NUM_IDS]; }; -struct scsi_sge { - struct regpair sge_addr; - __le16 sge_len; - __le16 reserved0; - __le32 reserved1; +enum scsi_sgl_mode { + SCSI_TX_SLOW_SGL, + SCSI_FAST_SGL, + MAX_SCSI_SGL_MODE +}; + +struct scsi_sgl_params { + struct regpair sgl_addr; + __le32 sgl_total_length; + __le32 sge_offset; + __le16 sgl_num_sges; + u8 sgl_index; + u8 reserved; }; struct scsi_terminate_extra_params { diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index 46fe7856f1b2..a5e843268f0e 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -173,6 +173,7 @@ enum tcp_seg_placement_event { TCP_EVENT_ADD_ISLE_RIGHT, TCP_EVENT_ADD_ISLE_LEFT, TCP_EVENT_JOIN, + TCP_EVENT_DELETE_ISLES, TCP_EVENT_NOP, MAX_TCP_SEG_PLACEMENT_EVENT }; From c55fa3cccbc2c672e7f118be8f7484e53a8e9e77 Mon Sep 17 00:00:00 2001 From: Francois Romieu Date: Sat, 11 Mar 2017 19:41:36 -0500 Subject: [PATCH 241/399] atm: remove an unnecessary loop Andrey reported this kernel warning: WARNING: CPU: 0 PID: 4114 at kernel/sched/core.c:7737 __might_sleep+0x149/0x1a0 do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait+0x182/0x530 The deeply nested alloc_skb is a problem. Diagnosis: nesting is wrong. It makes zero sense. Fix it and the implicit task state change problem automagically goes away. alloc_skb() does not need to be in the "while" loop. alloc_skb() does not need to be in the {prepare_to_wait/add_wait_queue ... finish_wait/remove_wait_queue} block. I claim that: - alloc_tx() should only perform the "wait_for_decent_tx_drain" part - alloc_skb() ought to be done directly in vcc_sendmsg - alloc_skb() failure can be handled gracefully in vcc_sendmsg - alloc_skb() may use a (m->msg_flags & MSG_DONTWAIT) dependent GFP_{KERNEL / ATOMIC} flag Reported-by: Andrey Konovalov Reviewed-and-Tested-by: Chas Williams <3chas3@gmail.com> Signed-off-by: Chas Williams <3chas3@gmail.com> Signed-off-by: David S. Miller --- net/atm/common.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/net/atm/common.c b/net/atm/common.c index 9613381f5db0..f06422f4108d 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -62,21 +62,16 @@ static void vcc_remove_socket(struct sock *sk) write_unlock_irq(&vcc_sklist_lock); } -static struct sk_buff *alloc_tx(struct atm_vcc *vcc, unsigned int size) +static bool vcc_tx_ready(struct atm_vcc *vcc, unsigned int size) { - struct sk_buff *skb; struct sock *sk = sk_atm(vcc); if (sk_wmem_alloc_get(sk) && !atm_may_send(vcc, size)) { pr_debug("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n", sk_wmem_alloc_get(sk), size, sk->sk_sndbuf); - return NULL; + return false; } - while (!(skb = alloc_skb(size, GFP_KERNEL))) - schedule(); - pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); - return skb; + return true; } static void vcc_sock_destruct(struct sock *sk) @@ -606,7 +601,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) eff = (size+3) & ~3; /* align to word boundary */ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); error = 0; - while (!(skb = alloc_tx(vcc, eff))) { + while (!vcc_tx_ready(vcc, eff)) { if (m->msg_flags & MSG_DONTWAIT) { error = -EAGAIN; break; @@ -628,6 +623,15 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) finish_wait(sk_sleep(sk), &wait); if (error) goto out; + + skb = alloc_skb(eff, GFP_KERNEL); + if (!skb) { + error = -ENOMEM; + goto out; + } + pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); + atomic_add(skb->truesize, &sk->sk_wmem_alloc); + skb->dev = NULL; /* for paths shared with net_device interfaces */ ATM_SKB(skb)->atm_options = vcc->atm_options; if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { From cda792c3f9b77acc3f42e4947d30f3a46e4da183 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:31 -0700 Subject: [PATCH 242/399] net: phy: bcm-phylib: replace obsolete EEE macro references The macros MDIO_AN_EEE_ADV_100TX and MDIO_AN_EEE_ADV_1000T are now considered obsolete and are replaced in the kernel with the generic macros MDIO_EEE_100TX and MDIO_EEE_1000T respectively. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm-phy-lib.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index ab9ad689617c..9656dbeb5de5 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Broadcom Corporation + * Copyright (C) 2015-2017 Broadcom * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as @@ -221,9 +221,9 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable) return val; if (enable) - val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T); + val |= (MDIO_EEE_100TX | MDIO_EEE_1000T); else - val &= ~(MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T); + val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T); phy_write_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV, MDIO_MMD_AN, (u32)val); From 83ee102a6998f808ac4c626e8f72344f0a355527 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:32 -0700 Subject: [PATCH 243/399] net: phy: bcm7xxx: add support for 28nm EPHY This commit adds support for the internal fast ethernet 10/100 PHY found in the BCM7260, BCM7268, and BCM7271 devices. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 215 +++++++++++++++++++++++++++++++++++++- include/linux/brcmphy.h | 3 + 2 files changed, 216 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index d1c2614dad3a..caa9f6e17f34 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -1,7 +1,7 @@ /* * Broadcom BCM7xxx internal transceivers support. * - * Copyright (C) 2014, Broadcom Corporation + * Copyright (C) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -19,7 +19,7 @@ /* Broadcom BCM7xxx internal PHY registers */ -/* 40nm only register definitions */ +/* EPHY only register definitions */ #define MII_BCM7XXX_100TX_AUX_CTL 0x10 #define MII_BCM7XXX_100TX_FALSE_CAR 0x13 #define MII_BCM7XXX_100TX_DISC 0x14 @@ -27,6 +27,19 @@ #define MII_BCM7XXX_64CLK_MDIO BIT(12) #define MII_BCM7XXX_TEST 0x1f #define MII_BCM7XXX_SHD_MODE_2 BIT(2) +#define MII_BCM7XXX_SHD_2_ADDR_CTRL 0xe +#define MII_BCM7XXX_SHD_2_CTRL_STAT 0xf +#define MII_BCM7XXX_SHD_2_BIAS_TRIM 0x1a +#define MII_BCM7XXX_SHD_3_AN_EEE_ADV 0x3 +#define MII_BCM7XXX_SHD_3_PCS_CTRL_2 0x6 +#define MII_BCM7XXX_PCS_CTRL_2_DEF 0x4400 +#define MII_BCM7XXX_SHD_3_AN_STAT 0xb +#define MII_BCM7XXX_AN_NULL_MSG_EN BIT(0) +#define MII_BCM7XXX_AN_EEE_EN BIT(1) +#define MII_BCM7XXX_SHD_3_EEE_THRESH 0xe +#define MII_BCM7XXX_EEE_THRESH_DEF 0x50 +#define MII_BCM7XXX_SHD_3_TL4 0x23 +#define MII_BCM7XXX_TL4_RST_MSK (BIT(2) | BIT(1)) /* 28nm only register definitions */ #define MISC_ADDR(base, channel) base, channel @@ -286,6 +299,181 @@ static int phy_set_clr_bits(struct phy_device *dev, int location, return v; } +static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev) +{ + int ret; + + /* set shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Set current trim values INT_trim = -1, Ext_trim =0 */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_BIAS_TRIM, 0x3BE0); + if (ret < 0) + goto reset_shadow_mode; + + /* Cal reset */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_TL4); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MII_BCM7XXX_TL4_RST_MSK, 0); + if (ret < 0) + goto reset_shadow_mode; + + /* Cal reset disable */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_TL4); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + 0, MII_BCM7XXX_TL4_RST_MSK); + if (ret < 0) + goto reset_shadow_mode; + +reset_shadow_mode: + /* reset shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); + if (ret < 0) + return ret; + + return 0; +} + +/* The 28nm EPHY does not support Clause 45 (MMD) used by bcm-phy-lib */ +static int bcm7xxx_28nm_ephy_apd_enable(struct phy_device *phydev) +{ + int ret; + + /* set shadow mode 1 */ + ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST, + MII_BRCM_FET_BT_SRE, 0); + if (ret < 0) + return ret; + + /* Enable auto-power down */ + ret = phy_set_clr_bits(phydev, MII_BRCM_FET_SHDW_AUXSTAT2, + MII_BRCM_FET_SHDW_AS2_APDE, 0); + if (ret < 0) + return ret; + + /* reset shadow mode 1 */ + ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST, 0, + MII_BRCM_FET_BT_SRE); + if (ret < 0) + return ret; + + return 0; +} + +static int bcm7xxx_28nm_ephy_eee_enable(struct phy_device *phydev) +{ + int ret; + + /* set shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Advertise supported modes */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_AN_EEE_ADV); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MDIO_EEE_100TX); + if (ret < 0) + goto reset_shadow_mode; + + /* Restore Defaults */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_PCS_CTRL_2); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MII_BCM7XXX_PCS_CTRL_2_DEF); + if (ret < 0) + goto reset_shadow_mode; + + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_EEE_THRESH); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + MII_BCM7XXX_EEE_THRESH_DEF); + if (ret < 0) + goto reset_shadow_mode; + + /* Enable EEE autonegotiation */ + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, + MII_BCM7XXX_SHD_3_AN_STAT); + if (ret < 0) + goto reset_shadow_mode; + ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, + (MII_BCM7XXX_AN_NULL_MSG_EN | MII_BCM7XXX_AN_EEE_EN)); + if (ret < 0) + goto reset_shadow_mode; + +reset_shadow_mode: + /* reset shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); + if (ret < 0) + return ret; + + /* Restart autoneg */ + phy_write(phydev, MII_BMCR, + (BMCR_SPEED100 | BMCR_ANENABLE | BMCR_ANRESTART)); + + return 0; +} + +static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev) +{ + u8 rev = phydev->phy_id & ~phydev->drv->phy_id_mask; + int ret = 0; + + pr_info_once("%s: %s PHY revision: 0x%02x\n", + phydev_name(phydev), phydev->drv->name, rev); + + /* Dummy read to a register to workaround a possible issue upon reset + * where the internal inverter may not allow the first MDIO transaction + * to pass the MDIO management controller and make us return 0xffff for + * such reads. + */ + phy_read(phydev, MII_BMSR); + + /* Apply AFE software work-around if necessary */ + if (rev == 0x01) { + ret = bcm7xxx_28nm_ephy_01_afe_config_init(phydev); + if (ret) + return ret; + } + + ret = bcm7xxx_28nm_ephy_eee_enable(phydev); + if (ret) + return ret; + + return bcm7xxx_28nm_ephy_apd_enable(phydev); +} + +static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev) +{ + int ret; + + /* Re-apply workarounds coming out suspend/resume */ + ret = bcm7xxx_28nm_ephy_config_init(phydev); + if (ret) + return ret; + + return genphy_config_aneg(phydev); +} + static int bcm7xxx_config_init(struct phy_device *phydev) { int ret; @@ -434,6 +622,23 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) .probe = bcm7xxx_28nm_probe, \ } +#define BCM7XXX_28NM_EPHY(_oui, _name) \ +{ \ + .phy_id = (_oui), \ + .phy_id_mask = 0xfffffff0, \ + .name = _name, \ + .features = PHY_BASIC_FEATURES, \ + .flags = PHY_IS_INTERNAL, \ + .config_init = bcm7xxx_28nm_ephy_config_init, \ + .config_aneg = genphy_config_aneg, \ + .read_status = genphy_read_status, \ + .resume = bcm7xxx_28nm_ephy_resume, \ + .get_sset_count = bcm_phy_get_sset_count, \ + .get_strings = bcm_phy_get_strings, \ + .get_stats = bcm7xxx_28nm_get_phy_stats, \ + .probe = bcm7xxx_28nm_probe, \ +} + #define BCM7XXX_40NM_EPHY(_oui, _name) \ { \ .phy_id = (_oui), \ @@ -450,6 +655,9 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"), + BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"), + BCM7XXX_28NM_EPHY(PHY_ID_BCM7268, "Broadcom BCM7268"), + BCM7XXX_28NM_EPHY(PHY_ID_BCM7271, "Broadcom BCM7271"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7278, "Broadcom BCM7278"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"), @@ -466,6 +674,9 @@ static struct phy_driver bcm7xxx_driver[] = { static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM7250, 0xfffffff0, }, + { PHY_ID_BCM7260, 0xfffffff0, }, + { PHY_ID_BCM7268, 0xfffffff0, }, + { PHY_ID_BCM7271, 0xfffffff0, }, { PHY_ID_BCM7278, 0xfffffff0, }, { PHY_ID_BCM7364, 0xfffffff0, }, { PHY_ID_BCM7366, 0xfffffff0, }, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 55e517130311..abcda9b458ab 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -25,6 +25,9 @@ #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM7250 0xae025280 +#define PHY_ID_BCM7260 0xae025190 +#define PHY_ID_BCM7268 0xae025090 +#define PHY_ID_BCM7271 0xae0253b0 #define PHY_ID_BCM7278 0xae0251a0 #define PHY_ID_BCM7364 0xae025260 #define PHY_ID_BCM7366 0x600d8490 From c298ede2fe21e034ab6ba4f15340fadc03ae9663 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:33 -0700 Subject: [PATCH 244/399] net: bcmgenet: simplify circular pointer arithmetic A 2's complement subtraction will always do a borrow, so masking off the sign bits is the same as conditionally adding (mask+1). Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/genet/bcmgenet.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index f92896835d2a..2c008b09c4e3 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1,7 +1,7 @@ /* * Broadcom GENET (Gigabit Ethernet) controller driver * - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1175,13 +1175,9 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, unsigned int txbds_processed = 0; /* Compute how many buffers are transmitted since last xmit call */ - c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX); - c_index &= DMA_C_INDEX_MASK; - - if (likely(c_index >= ring->c_index)) - txbds_ready = c_index - ring->c_index; - else - txbds_ready = (DMA_C_INDEX_MASK + 1) - ring->c_index + c_index; + c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX) + & DMA_C_INDEX_MASK; + txbds_ready = (c_index - ring->c_index) & DMA_C_INDEX_MASK; netif_dbg(priv, tx_done, dev, "%s ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n", @@ -1611,12 +1607,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, } p_index &= DMA_P_INDEX_MASK; - - if (likely(p_index >= ring->c_index)) - rxpkttoprocess = p_index - ring->c_index; - else - rxpkttoprocess = (DMA_C_INDEX_MASK + 1) - ring->c_index + - p_index; + rxpkttoprocess = (p_index - ring->c_index) & DMA_C_INDEX_MASK; netif_dbg(priv, rx_status, dev, "RDMA: rxpkttoprocess=%d\n", rxpkttoprocess); From 556c2cf4eff18bb7f41056796d2d37b48239278b Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:34 -0700 Subject: [PATCH 245/399] net: bcmgenet: remove meaningless lines An assortment of non-functional lines are removed to reduce confusion and some typos in comments are corrected. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 2c008b09c4e3..22c92f5a9829 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -605,7 +605,7 @@ static int bcmgenet_set_coalesce(struct net_device *dev, /* GENET TDMA hardware does not support a configurable timeout, but will * always generate an interrupt either after MBDONE packets have been - * transmitted, or when the ring is emtpy. + * transmitted, or when the ring is empty. */ if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high || ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low) @@ -1834,10 +1834,8 @@ static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) /* Mask all interrupts.*/ bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET); bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR); - bcmgenet_intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR); bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET); bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR); - bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR); } static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv) @@ -1926,7 +1924,6 @@ static int init_umac(struct bcmgenet_priv *priv) bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); - /* Enable rx/tx engine.*/ dev_dbg(kdev, "done init umac\n"); return 0; @@ -2836,7 +2833,7 @@ static int bcmgenet_close(struct net_device *dev) if (ret) return ret; - /* Disable MAC transmit. TX DMA disabled have to done before this */ + /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); /* tx reclaim */ @@ -3115,22 +3112,18 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus; genet_dma_ring_regs = genet_dma_ring_regs_v4; priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS; - priv->version = GENET_V4; } else if (GENET_IS_V3(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus; genet_dma_ring_regs = genet_dma_ring_regs_v123; priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS; - priv->version = GENET_V3; } else if (GENET_IS_V2(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v2; genet_dma_ring_regs = genet_dma_ring_regs_v123; priv->dma_rx_chk_bit = DMA_RX_CHK_V12; - priv->version = GENET_V2; } else if (GENET_IS_V1(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v1; genet_dma_ring_regs = genet_dma_ring_regs_v123; priv->dma_rx_chk_bit = DMA_RX_CHK_V12; - priv->version = GENET_V1; } /* enum genet_version starts at 1 */ @@ -3397,7 +3390,7 @@ static int bcmgenet_suspend(struct device *d) if (ret) return ret; - /* Disable MAC transmit. TX DMA disabled have to done before this */ + /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); /* tx reclaim */ From 6689da155bdcd17abfe4d3a8b1e245d9ed4b5f2c Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:35 -0700 Subject: [PATCH 246/399] net: bcmgenet: manage dma interrupts in napi code This commit moves DMA interrupt enabling out of init_umac() and adds the masking of these interrupts to the napi enable and disable code. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/genet/bcmgenet.c | 39 +++++++++++-------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 22c92f5a9829..9be884021679 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1862,8 +1862,6 @@ static int init_umac(struct bcmgenet_priv *priv) int ret; u32 reg; u32 int0_enable = 0; - u32 int1_enable = 0; - int i; dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n"); @@ -1890,12 +1888,6 @@ static int init_umac(struct bcmgenet_priv *priv) bcmgenet_intr_disable(priv); - /* Enable Rx default queue 16 interrupts */ - int0_enable |= UMAC_IRQ_RXDMA_DONE; - - /* Enable Tx default queue 16 interrupts */ - int0_enable |= UMAC_IRQ_TXDMA_DONE; - /* Configure backpressure vectors for MoCA */ if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { reg = bcmgenet_bp_mc_get(priv); @@ -1913,16 +1905,7 @@ static int init_umac(struct bcmgenet_priv *priv) if (priv->hw_params->flags & GENET_HAS_MDIO_INTR) int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR); - /* Enable Rx priority queue interrupts */ - for (i = 0; i < priv->hw_params->rx_queues; ++i) - int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i)); - - /* Enable Tx priority queue interrupts */ - for (i = 0; i < priv->hw_params->tx_queues; ++i) - int1_enable |= (1 << i); - bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); - bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); dev_dbg(kdev, "done init umac\n"); @@ -2055,22 +2038,33 @@ static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv) static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_enable = UMAC_IRQ_TXDMA_DONE; + u32 int1_enable = 0; struct bcmgenet_tx_ring *ring; for (i = 0; i < priv->hw_params->tx_queues; ++i) { ring = &priv->tx_rings[i]; napi_enable(&ring->napi); + int1_enable |= (1 << i); } ring = &priv->tx_rings[DESC_INDEX]; napi_enable(&ring->napi); + + bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); + bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); } static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_disable = UMAC_IRQ_TXDMA_DONE; + u32 int1_disable = 0xffff; struct bcmgenet_tx_ring *ring; + bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET); + bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET); + for (i = 0; i < priv->hw_params->tx_queues; ++i) { ring = &priv->tx_rings[i]; napi_disable(&ring->napi); @@ -2183,22 +2177,33 @@ static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv) static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_enable = UMAC_IRQ_RXDMA_DONE; + u32 int1_enable = 0; struct bcmgenet_rx_ring *ring; for (i = 0; i < priv->hw_params->rx_queues; ++i) { ring = &priv->rx_rings[i]; napi_enable(&ring->napi); + int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i)); } ring = &priv->rx_rings[DESC_INDEX]; napi_enable(&ring->napi); + + bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); + bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); } static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv) { unsigned int i; + u32 int0_disable = UMAC_IRQ_RXDMA_DONE; + u32 int1_disable = 0xffff << UMAC_IRQ1_RX_INTR_SHIFT; struct bcmgenet_rx_ring *ring; + bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET); + bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET); + for (i = 0; i < priv->hw_params->rx_queues; ++i) { ring = &priv->rx_rings[i]; napi_disable(&ring->napi); From b1ec494deea8322e88063c8a6bee903255a0590d Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:36 -0700 Subject: [PATCH 247/399] net: bcmgenet: remove handling of wol interrupts from isr0 The bcmgenet_wol_isr() handler performs the necessary processing for waking from a GENET event. There is no necessary functionality behind servicing the UMAC_IRQ_MPD_R event in the handling of isr0. Therefore the code that unmasks and masks this interrupt and that gets invoked in response to it is removed by this commit. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 10 +--------- .../net/ethernet/broadcom/genet/bcmgenet_wol.c | 15 +-------------- 2 files changed, 2 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 9be884021679..661ca1b39c89 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2455,13 +2455,6 @@ static void bcmgenet_irq_task(struct work_struct *work) netif_dbg(priv, intr, priv->dev, "%s\n", __func__); - if (priv->irq0_stat & UMAC_IRQ_MPD_R) { - priv->irq0_stat &= ~UMAC_IRQ_MPD_R; - netif_dbg(priv, wol, priv->dev, - "magic packet detected, waking up\n"); - bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC); - } - /* Link UP/DOWN event */ if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) { phy_mac_interrupt(priv->phydev, @@ -2558,8 +2551,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) UMAC_IRQ_PHY_DET_F | UMAC_IRQ_LINK_EVENT | UMAC_IRQ_HFB_SM | - UMAC_IRQ_HFB_MM | - UMAC_IRQ_MPD_R)) { + UMAC_IRQ_HFB_MM)) { /* all other interested interrupts handled in bottom half */ schedule_work(&priv->bcmgenet_irq_work); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index b97122926d3a..2fbd027f0148 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -1,7 +1,7 @@ /* * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support * - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -127,7 +127,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode) { struct net_device *dev = priv->dev; - u32 cpu_mask_clear; int retries = 0; u32 reg; @@ -173,18 +172,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); } - /* Enable the MPD interrupt */ - cpu_mask_clear = UMAC_IRQ_MPD_R; - - bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, INTRL2_CPU_MASK_CLEAR); - return 0; } void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode) { - u32 cpu_mask_set; u32 reg; if (mode != GENET_POWER_WOL_MAGIC) { @@ -201,10 +194,4 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, reg &= ~CMD_CRC_FWD; bcmgenet_umac_writel(priv, reg, UMAC_CMD); priv->crc_fwd_en = 0; - - /* Stop monitoring magic packet IRQ */ - cpu_mask_set = UMAC_IRQ_MPD_R; - - /* Stop monitoring magic packet IRQ */ - bcmgenet_intrl2_0_writel(priv, cpu_mask_set, INTRL2_CPU_MASK_SET); } From d5810ca3252a5bf61e5b2fc789da456e0f65ba8c Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:37 -0700 Subject: [PATCH 248/399] net: bcmgenet: clear status to reduce spurious interrupts Since the DMA interrupt status is latched and the DMA servicing can be polled, it is a good idea to clear the latched status of a DMA interrupt before performing the service that would be invoked by the interrupt. This prevents old status from causing spurious interrupts when the interrupt is unmasked at a later time. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/genet/bcmgenet.c | 21 ++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 661ca1b39c89..1f94ba1773dd 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1174,6 +1174,14 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, unsigned int txbds_ready; unsigned int txbds_processed = 0; + /* Clear status before servicing to reduce spurious interrupts */ + if (ring->index == DESC_INDEX) + bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE, + INTRL2_CPU_CLEAR); + else + bcmgenet_intrl2_1_writel(priv, (1 << ring->index), + INTRL2_CPU_CLEAR); + /* Compute how many buffers are transmitted since last xmit call */ c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX) & DMA_C_INDEX_MASK; @@ -1584,10 +1592,21 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, unsigned long dma_flag; int len; unsigned int rxpktprocessed = 0, rxpkttoprocess; - unsigned int p_index; + unsigned int p_index, mask; unsigned int discards; unsigned int chksum_ok = 0; + /* Clear status before servicing to reduce spurious interrupts */ + if (ring->index == DESC_INDEX) { + bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE, + INTRL2_CPU_CLEAR); + } else { + mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index); + bcmgenet_intrl2_1_writel(priv, + mask, + INTRL2_CPU_CLEAR); + } + p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX); discards = (p_index >> DMA_P_INDEX_DISCARD_CNT_SHIFT) & From c4d453d2b14d4c844fd6b492fbd16ce0615a59d8 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:38 -0700 Subject: [PATCH 249/399] net: bcmgenet: correct return value of __bcmgenet_tx_reclaim The reclaim function should return the number of buffer descriptors reclaimed, not just the number corresponding to skb packets. Also, remove the unnecessary computation when updating the consumer index. While this is not a functional problem it could degrade performance of napi in a fragmented transmit stream. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 1f94ba1773dd..d90d366b286f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1218,7 +1218,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, } ring->free_bds += txbds_processed; - ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK; + ring->c_index = c_index; dev->stats.tx_packets += pkts_compl; dev->stats.tx_bytes += bytes_compl; @@ -1231,7 +1231,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, netif_tx_wake_queue(txq); } - return pkts_compl; + return txbds_processed; } static unsigned int bcmgenet_tx_reclaim(struct net_device *dev, From 54fecff3461143bfc4c4f0431e9145e8748977ce Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:39 -0700 Subject: [PATCH 250/399] net: bcmgenet: return EOPNOTSUPP for unknown ioctl commands This commit changes the ioctl handling behavior to return the EOPNOTSUPP error code instead of the EINVAL error code when an unknown ioctl command value is detected. It also removes some redundant parsing of the ioctl command value and allows the SIOCSHWTSTAMP value to be handled. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/genet/bcmgenet.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index d90d366b286f..3b49c14128e2 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1062,27 +1062,14 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct bcmgenet_priv *priv = netdev_priv(dev); - int val = 0; if (!netif_running(dev)) return -EINVAL; - switch (cmd) { - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSMIIREG: - if (!priv->phydev) - val = -ENODEV; - else - val = phy_mii_ioctl(priv->phydev, rq, cmd); - break; + if (!priv->phydev) + return -ENODEV; - default: - val = -EINVAL; - break; - } - - return val; + return phy_mii_ioctl(priv->phydev, rq, cmd); } static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv, From 75835695ad6362c94b918ef28799ed6b593f947c Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:40 -0700 Subject: [PATCH 251/399] dt-bindings: net: document bcmgenet WoL interrupt A third interrupt cell can be provided to optionally specify the interrupt used for handling Wake on LAN events. Typically the wake up handling uses a separate interrupt controller, so the interrupts-extended property is used to accommodate this. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/brcm,bcmgenet.txt | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt index 10587bdadbbe..01a70463cbc5 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt @@ -4,9 +4,12 @@ Required properties: - compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2", "brcm,genet-v3", "brcm,genet-v4". - reg: address and length of the register set for the device -- interrupts: must be two cells, the first cell is the general purpose - interrupt line, while the second cell is the interrupt for the ring - RX and TX queues operating in ring mode +- interrupts and/or interrupts-extended: must be two cells, the first cell + is the general purpose interrupt line, while the second cell is the + interrupt for the ring RX and TX queues operating in ring mode. An + optional third interrupt cell for Wake-on-LAN can be specified. + See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt + for information on the property specifics. - phy-mode: see ethernet.txt file in the same directory - #address-cells: should be 1 - #size-cells: should be 1 From 0ce5aa1d6c97425ae0fd4082066049edcaffe01b Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:41 -0700 Subject: [PATCH 252/399] dt-bindings: net: update bcmgenet binding for GENETv5 The device tree documentation must be updated to reflect the new compatible strings "brcm,genet-v5" and "brcm,genet-mdio-v5" used by the GENETv5 driver. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../devicetree/bindings/net/brcm,bcmgenet.txt | 10 +++++----- .../devicetree/bindings/net/brcm,unimac-mdio.txt | 5 +++-- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt index 01a70463cbc5..26c77d985faf 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt @@ -2,7 +2,7 @@ Required properties: - compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2", - "brcm,genet-v3", "brcm,genet-v4". + "brcm,genet-v3", "brcm,genet-v4", "brcm,genet-v5". - reg: address and length of the register set for the device - interrupts and/or interrupts-extended: must be two cells, the first cell is the general purpose interrupt line, while the second cell is the @@ -32,15 +32,15 @@ Optional properties: Required child nodes: -- mdio bus node: this node should always be present regarless of the PHY +- mdio bus node: this node should always be present regardless of the PHY configuration of the GENET instance MDIO bus node required properties: - compatible: should contain one of "brcm,genet-mdio-v1", "brcm,genet-mdio-v2" - "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", the version has to match the - parent node compatible property (e.g: brcm,genet-v4 pairs with - brcm,genet-mdio-v4) + "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5", the version + has to match the parent node compatible property (e.g: brcm,genet-v4 pairs + with brcm,genet-mdio-v4) - reg: address and length relative to the parent node base register address - #address-cells: address cell for MDIO bus addressing, should be 1 - #size-cells: size of the cells for MDIO bus addressing, should be 0 diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt index ab0bb4247d14..4648948f7c3b 100644 --- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt +++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt @@ -2,8 +2,9 @@ Required properties: - compatible: should one from "brcm,genet-mdio-v1", "brcm,genet-mdio-v2", - "brcm,genet-mdio-v3", "brcm,genet-mdio-v4" or "brcm,unimac-mdio" -- reg: address and length of the regsiter set for the device, first one is the + "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5" or + "brcm,unimac-mdio" +- reg: address and length of the register set for the device, first one is the base register, and the second one is optional and for indirect accesses to larger than 16-bits MDIO transactions - reg-names: name(s) of the register must be "mdio" and optional "mdio_indir_rw" From 421380856d9c7466a28a1410cce2055acaf84ffd Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 13 Mar 2017 17:41:42 -0700 Subject: [PATCH 253/399] net: bcmgenet: add support for the GENETv5 hardware This commit adds support for the GENETv5 implementation. The GENETv5 reports a major version of 6 instead of 5 so compensate for this when verifying the configuration of the driver. Also the EPHY revision is now contained in the MDIO registers of the PHY so the EPHY revision of 0 in GENET_VER_FMT is expected for GENETv5. Signed-off-by: Doug Berger Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/genet/bcmgenet.c | 91 +++++++++++++++---- .../net/ethernet/broadcom/genet/bcmgenet.h | 12 ++- drivers/net/ethernet/broadcom/genet/bcmmii.c | 60 ++++++------ drivers/net/phy/mdio-bcm-unimac.c | 3 +- 4 files changed, 117 insertions(+), 49 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 3b49c14128e2..d848ac58189c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1011,8 +1011,17 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv, /* Power down LED */ if (priv->hw_params->flags & GENET_HAS_EXT) { reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= (EXT_PWR_DOWN_PHY | - EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); + if (GENET_IS_V5(priv)) + reg |= EXT_PWR_DOWN_PHY_EN | + EXT_PWR_DOWN_PHY_RD | + EXT_PWR_DOWN_PHY_SD | + EXT_PWR_DOWN_PHY_RX | + EXT_PWR_DOWN_PHY_TX | + EXT_IDDQ_GLBL_PWR; + else + reg |= EXT_PWR_DOWN_PHY; + + reg |= (EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); bcmgenet_phy_power_set(priv->dev, false); @@ -1037,12 +1046,34 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, switch (mode) { case GENET_POWER_PASSIVE: - reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_PHY | - EXT_PWR_DOWN_BIAS); - /* fallthrough */ + reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); + if (GENET_IS_V5(priv)) { + reg &= ~(EXT_PWR_DOWN_PHY_EN | + EXT_PWR_DOWN_PHY_RD | + EXT_PWR_DOWN_PHY_SD | + EXT_PWR_DOWN_PHY_RX | + EXT_PWR_DOWN_PHY_TX | + EXT_IDDQ_GLBL_PWR); + reg |= EXT_PHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + mdelay(1); + + reg &= ~EXT_PHY_RESET; + } else { + reg &= ~EXT_PWR_DOWN_PHY; + reg |= EXT_PWR_DN_EN_LD; + } + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + bcmgenet_phy_power_set(priv->dev, true); + bcmgenet_mii_reset(priv->dev); + break; + case GENET_POWER_CABLE_SENSE: /* enable APD */ - reg |= EXT_PWR_DN_EN_LD; + if (!GENET_IS_V5(priv)) { + reg |= EXT_PWR_DN_EN_LD; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + } break; case GENET_POWER_WOL_MAGIC: bcmgenet_wol_power_up_cfg(priv, mode); @@ -1050,12 +1081,6 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, default: break; } - - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - if (mode == GENET_POWER_PASSIVE) { - bcmgenet_phy_power_set(priv->dev, true); - bcmgenet_mii_reset(priv->dev); - } } /* ioctl handle special commands that are not present in ethtool. */ @@ -3101,6 +3126,25 @@ static struct bcmgenet_hw_params bcmgenet_hw_params[] = { .flags = GENET_HAS_40BITS | GENET_HAS_EXT | GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET, }, + [GENET_V5] = { + .tx_queues = 4, + .tx_bds_per_q = 32, + .rx_queues = 0, + .rx_bds_per_q = 0, + .bp_in_en_shift = 17, + .bp_in_mask = 0x1ffff, + .hfb_filter_cnt = 48, + .hfb_filter_size = 128, + .qtag_mask = 0x3F, + .tbuf_offset = 0x0600, + .hfb_offset = 0x8000, + .hfb_reg_offset = 0xfc00, + .rdma_offset = 0x2000, + .tdma_offset = 0x4000, + .words_per_bd = 3, + .flags = GENET_HAS_40BITS | GENET_HAS_EXT | + GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET, + }, }; /* Infer hardware parameters from the detected GENET version */ @@ -3111,7 +3155,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) u8 major; u16 gphy_rev; - if (GENET_IS_V4(priv)) { + if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) { bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus; genet_dma_ring_regs = genet_dma_ring_regs_v4; priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS; @@ -3136,7 +3180,9 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) /* Read GENET HW version */ reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL); major = (reg >> 24 & 0x0f); - if (major == 5) + if (major == 6) + major = 5; + else if (major == 5) major = 4; else if (major == 0) major = 1; @@ -3164,16 +3210,22 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) */ gphy_rev = reg & 0xffff; + if (GENET_IS_V5(priv)) { + /* The EPHY revision should come from the MDIO registers of + * the PHY not from GENET. + */ + if (gphy_rev != 0) { + pr_warn("GENET is reporting EPHY revision: 0x%04x\n", + gphy_rev); + } /* This is the good old scheme, just GPHY major, no minor nor patch */ - if ((gphy_rev & 0xf0) != 0) + } else if ((gphy_rev & 0xf0) != 0) { priv->gphy_rev = gphy_rev << 8; - /* This is the new scheme, GPHY major rolls over with 0x10 = rev G0 */ - else if ((gphy_rev & 0xff00) != 0) + } else if ((gphy_rev & 0xff00) != 0) { priv->gphy_rev = gphy_rev; - /* This is reserved so should require special treatment */ - else if (gphy_rev == 0 || gphy_rev == 0x01ff) { + } else if (gphy_rev == 0 || gphy_rev == 0x01ff) { pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev); return; } @@ -3206,6 +3258,7 @@ static const struct of_device_id bcmgenet_match[] = { { .compatible = "brcm,genet-v2", .data = (void *)GENET_V2 }, { .compatible = "brcm,genet-v3", .data = (void *)GENET_V3 }, { .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 }, + { .compatible = "brcm,genet-v5", .data = (void *)GENET_V5 }, { }, }; MODULE_DEVICE_TABLE(of, bcmgenet_match); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 1e2dc34d331a..1001d9131ba8 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -351,8 +351,14 @@ struct bcmgenet_mib_counters { #define EXT_PWR_DN_EN_LD (1 << 3) #define EXT_ENERGY_DET (1 << 4) #define EXT_IDDQ_FROM_PHY (1 << 5) +#define EXT_IDDQ_GLBL_PWR (1 << 7) #define EXT_PHY_RESET (1 << 8) #define EXT_ENERGY_DET_MASK (1 << 12) +#define EXT_PWR_DOWN_PHY_TX (1 << 16) +#define EXT_PWR_DOWN_PHY_RX (1 << 17) +#define EXT_PWR_DOWN_PHY_SD (1 << 18) +#define EXT_PWR_DOWN_PHY_RD (1 << 19) +#define EXT_PWR_DOWN_PHY_EN (1 << 20) #define EXT_RGMII_OOB_CTRL 0x0C #define RGMII_LINK (1 << 4) @@ -495,13 +501,15 @@ enum bcmgenet_version { GENET_V1 = 1, GENET_V2, GENET_V3, - GENET_V4 + GENET_V4, + GENET_V5 }; #define GENET_IS_V1(p) ((p)->version == GENET_V1) #define GENET_IS_V2(p) ((p)->version == GENET_V2) #define GENET_IS_V3(p) ((p)->version == GENET_V3) #define GENET_IS_V4(p) ((p)->version == GENET_V4) +#define GENET_IS_V5(p) ((p)->version == GENET_V5) /* Hardware flags */ #define GENET_HAS_40BITS (1 << 0) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index e87607621e62..8df47c90cfc5 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -1,7 +1,7 @@ /* * Broadcom GENET MDIO routines * - * Copyright (c) 2014 Broadcom Corporation + * Copyright (c) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -195,29 +195,31 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable) u32 reg = 0; /* EXT_GPHY_CTRL is only valid for GENETv4 and onward */ - if (!GENET_IS_V4(priv)) - return; + if (GENET_IS_V4(priv)) { + reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL); + if (enable) { + reg &= ~EXT_CK25_DIS; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); - reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL); - if (enable) { - reg &= ~EXT_CK25_DIS; + reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN); + reg |= EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + + reg &= ~EXT_GPHY_RESET; + } else { + reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | + EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + reg |= EXT_CK25_DIS; + } bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - mdelay(1); - - reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN); - reg |= EXT_GPHY_RESET; - bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - mdelay(1); - - reg &= ~EXT_GPHY_RESET; + udelay(60); } else { - reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | EXT_GPHY_RESET; - bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); mdelay(1); - reg |= EXT_CK25_DIS; } - bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - udelay(60); } static void bcmgenet_internal_phy_setup(struct net_device *dev) @@ -227,10 +229,12 @@ static void bcmgenet_internal_phy_setup(struct net_device *dev) /* Power up PHY */ bcmgenet_phy_power_set(dev, true); - /* enable APD */ - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= EXT_PWR_DN_EN_LD; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + if (!GENET_IS_V5(priv)) { + /* enable APD */ + reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); + reg |= EXT_PWR_DN_EN_LD; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + } bcmgenet_mii_reset(dev); } @@ -238,10 +242,12 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) { u32 reg; - /* Speed settings are set in bcmgenet_mii_setup() */ - reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL); - reg |= LED_ACT_SOURCE_MAC; - bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL); + if (!GENET_IS_V5(priv)) { + /* Speed settings are set in bcmgenet_mii_setup() */ + reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL); + reg |= LED_ACT_SOURCE_MAC; + bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL); + } if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET) fixed_phy_set_link_update(priv->phydev, diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c index 8c73b2e771dd..34395230ce70 100644 --- a/drivers/net/phy/mdio-bcm-unimac.c +++ b/drivers/net/phy/mdio-bcm-unimac.c @@ -1,7 +1,7 @@ /* * Broadcom UniMAC MDIO bus controller driver * - * Copyright (C) 2014, Broadcom Corporation + * Copyright (C) 2014-2017 Broadcom * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -228,6 +228,7 @@ static int unimac_mdio_remove(struct platform_device *pdev) } static const struct of_device_id unimac_mdio_ids[] = { + { .compatible = "brcm,genet-mdio-v5", }, { .compatible = "brcm,genet-mdio-v4", }, { .compatible = "brcm,genet-mdio-v3", }, { .compatible = "brcm,genet-mdio-v2", }, From b418c5276a41c821c25410542df83d283bbc0b2a Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Mon, 13 Mar 2017 01:43:45 -0400 Subject: [PATCH 254/399] rds: ib: drop unnecessary rdma_reject When rdma_accept fails, rdma_reject is called in it. As such, it is not necessary to execute rdma_reject again. Cc: Joe Jin Cc: Junxiao Bi Acked-by: Santosh Shilimkar Signed-off-by: Zhu Yanjun Signed-off-by: David S. Miller --- net/rds/ib_cm.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index ce3775abc6e7..11d535b16125 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -677,9 +677,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, event->param.conn.initiator_depth); /* rdma_accept() calls rdma_reject() internally if it fails */ - err = rdma_accept(cm_id, &conn_param); - if (err) - rds_ib_conn_error(conn, "rdma_accept failed (%d)\n", err); + if (rdma_accept(cm_id, &conn_param)) + rds_ib_conn_error(conn, "rdma_accept failed\n"); out: if (conn) From ea69c883644a5c574ab518ae86ca3ce58e101072 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Mon, 13 Mar 2017 01:43:46 -0400 Subject: [PATCH 255/399] rds: ib: remove redundant ib_dealloc_fmr The function ib_dealloc_fmr will never be called. As such, it should be removed. Cc: Joe Jin Cc: Junxiao Bi Reviewed-by: Yuval Shaia Reviewed-by: Johannes Thumshirn Acked-by: Santosh Shilimkar Signed-off-by: Zhu Yanjun Signed-off-by: David S. Miller --- net/rds/ib_fmr.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 4fe8f4fec4ee..249ae1c783cb 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -78,12 +78,9 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) return ibmr; out_no_cigar: - if (ibmr) { - if (fmr->fmr) - ib_dealloc_fmr(fmr->fmr); - kfree(ibmr); - } + kfree(ibmr); atomic_dec(&pool->item_count); + return ERR_PTR(err); } From edd08f96db4f06beb09acdd71e00b07a1f6c13ca Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Mon, 13 Mar 2017 01:43:47 -0400 Subject: [PATCH 256/399] rds: ib: add the static type to the function The function rds_ib_map_fmr is used only in the ib_fmr.c file. As such, the static type is added to limit it in this file. Cc: Joe Jin Cc: Junxiao Bi Acked-by: Santosh Shilimkar Signed-off-by: Zhu Yanjun Signed-off-by: David S. Miller --- net/rds/ib_fmr.c | 5 +++-- net/rds/ib_mr.h | 2 -- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 249ae1c783cb..c936b0d47693 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -84,8 +84,9 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) return ERR_PTR(err); } -int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr, - struct scatterlist *sg, unsigned int nents) +static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, + struct rds_ib_mr *ibmr, struct scatterlist *sg, + unsigned int nents) { struct ib_device *dev = rds_ibdev->dev; struct rds_ib_fmr *fmr = &ibmr->u.fmr; diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 5d6e98a79a5e..0ea4ab017a8c 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -125,8 +125,6 @@ void rds_ib_mr_exit(void); void __rds_ib_teardown_mr(struct rds_ib_mr *); void rds_ib_teardown_mr(struct rds_ib_mr *); struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *, int); -int rds_ib_map_fmr(struct rds_ib_device *, struct rds_ib_mr *, - struct scatterlist *, unsigned int); struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *); int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *, int, struct rds_ib_mr **); struct rds_ib_mr *rds_ib_reg_fmr(struct rds_ib_device *, struct scatterlist *, From 569f41d187ac2c9a9809b9f4e27109fc558053eb Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Mon, 13 Mar 2017 01:43:48 -0400 Subject: [PATCH 257/399] rds: ib: unmap the scatter/gather list when error When some errors occur, the scatter/gather list mapped to DMA addresses should be handled. Cc: Joe Jin Cc: Junxiao Bi Acked-by: Santosh Shilimkar Signed-off-by: Zhu Yanjun Signed-off-by: David S. Miller --- net/rds/ib_fmr.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index c936b0d47693..86ef907067bb 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -112,29 +112,39 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, u64 dma_addr = ib_sg_dma_address(dev, &scat[i]); if (dma_addr & ~PAGE_MASK) { - if (i > 0) + if (i > 0) { + ib_dma_unmap_sg(dev, sg, nents, + DMA_BIDIRECTIONAL); return -EINVAL; - else + } else { ++page_cnt; + } } if ((dma_addr + dma_len) & ~PAGE_MASK) { - if (i < sg_dma_len - 1) + if (i < sg_dma_len - 1) { + ib_dma_unmap_sg(dev, sg, nents, + DMA_BIDIRECTIONAL); return -EINVAL; - else + } else { ++page_cnt; + } } len += dma_len; } page_cnt += len >> PAGE_SHIFT; - if (page_cnt > ibmr->pool->fmr_attr.max_pages) + if (page_cnt > ibmr->pool->fmr_attr.max_pages) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); return -EINVAL; + } dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC, rdsibdev_to_node(rds_ibdev)); - if (!dma_pages) + if (!dma_pages) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); return -ENOMEM; + } page_cnt = 0; for (i = 0; i < sg_dma_len; ++i) { @@ -147,8 +157,10 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, } ret = ib_map_phys_fmr(fmr->fmr, dma_pages, page_cnt, io_addr); - if (ret) + if (ret) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); goto out; + } /* Success - we successfully remapped the MR, so we can * safely tear down the old mapping. From 942c56ad07d111714899ec4bfb32212a65f40ac5 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Mon, 13 Mar 2017 23:04:48 -0700 Subject: [PATCH 258/399] lwtunnel: remove unused but set variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit silences the below warning: net/core/lwtunnel.c: In function ‘lwtunnel_valid_encap_type_attr’: net/core/lwtunnel.c:165:17: warning: variable ‘nla’ set but not used [-Wunused-but-set-variable] Fixes: 9ed59592e3e3 ("lwtunnel: fix autoload of lwt modules") Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- net/core/lwtunnel.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 6df9f8fabf0c..b5888190223c 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -162,7 +162,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; struct nlattr *attrs; - struct nlattr *nla; u16 encap_type; int attrlen; @@ -170,7 +169,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { attrs = rtnh_attrs(rtnh); - nla = nla_find(attrs, attrlen, RTA_ENCAP); nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla_entype) { From 9c79ddaa0f962d1f26537a670b0652ff509a6fe0 Mon Sep 17 00:00:00 2001 From: "Mintz, Yuval" Date: Tue, 14 Mar 2017 16:23:54 +0200 Subject: [PATCH 259/399] qed*: Add support for QL41xxx adapters This adds the necessary infrastructure changes for initializing and working with the new series of QL41xxx adapaters. It also adds 2 new PCI device-IDs to qede: - 0x8070 for QL41xxx PFs - 0x8090 for VFs spawning from QL41xxx PFs Signed-off-by: Tomer Tayar Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 29 ++- drivers/net/ethernet/qlogic/qed/qed_debug.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_dev.c | 186 ++++++++++++--- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 61 ++++- drivers/net/ethernet/qlogic/qed/qed_l2.c | 184 +++++++++------ drivers/net/ethernet/qlogic/qed/qed_main.c | 7 +- drivers/net/ethernet/qlogic/qed/qed_mcp.h | 9 +- drivers/net/ethernet/qlogic/qed/qed_ptp.c | 12 +- .../net/ethernet/qlogic/qed/qed_reg_addr.h | 17 +- drivers/net/ethernet/qlogic/qed/qed_sriov.c | 30 ++- drivers/net/ethernet/qlogic/qede/qede.h | 43 +++- .../net/ethernet/qlogic/qede/qede_ethtool.c | 85 ++++--- drivers/net/ethernet/qlogic/qede/qede_main.c | 218 ++++++++++-------- include/linux/qed/qed_if.h | 48 +++- include/linux/qed/rdma_common.h | 3 +- 15 files changed, 628 insertions(+), 306 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index be99092d7209..ca30a27df035 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -219,7 +219,9 @@ enum QED_PORT_MODE { QED_PORT_MODE_DE_4X20G, QED_PORT_MODE_DE_1X40G, QED_PORT_MODE_DE_2X25G, - QED_PORT_MODE_DE_1X25G + QED_PORT_MODE_DE_1X25G, + QED_PORT_MODE_DE_4X25G, + QED_PORT_MODE_DE_2X10G, }; enum qed_dev_cap { @@ -364,7 +366,8 @@ struct qed_hwfn { #define IS_LEAD_HWFN(edev) (!((edev)->my_id)) u8 rel_pf_id; /* Relative to engine*/ u8 abs_pf_id; -#define QED_PATH_ID(_p_hwfn) ((_p_hwfn)->abs_pf_id & 1) +#define QED_PATH_ID(_p_hwfn) \ + (QED_IS_K2((_p_hwfn)->cdev) ? 0 : ((_p_hwfn)->abs_pf_id & 1)) u8 port_id; bool b_active; @@ -523,9 +526,7 @@ struct qed_dev { u8 dp_level; char name[NAME_SIZE]; - u8 type; -#define QED_DEV_TYPE_BB (0 << 0) -#define QED_DEV_TYPE_AH BIT(0) + enum qed_dev_type type; /* Translate type/revision combo into the proper conditions */ #define QED_IS_BB(dev) ((dev)->type == QED_DEV_TYPE_BB) #define QED_IS_BB_A0(dev) (QED_IS_BB(dev) && \ @@ -540,6 +541,9 @@ struct qed_dev { u16 vendor_id; u16 device_id; +#define QED_DEV_ID_MASK 0xff00 +#define QED_DEV_ID_MASK_BB 0x1600 +#define QED_DEV_ID_MASK_AH 0x8000 u16 chip_num; #define CHIP_NUM_MASK 0xffff @@ -654,10 +658,16 @@ struct qed_dev { u32 rdma_max_srq_sge; }; -#define NUM_OF_VFS(dev) MAX_NUM_VFS_BB -#define NUM_OF_L2_QUEUES(dev) MAX_NUM_L2_QUEUES_BB -#define NUM_OF_SBS(dev) MAX_SB_PER_PATH_BB -#define NUM_OF_ENG_PFS(dev) MAX_NUM_PFS_BB +#define NUM_OF_VFS(dev) (QED_IS_BB(dev) ? MAX_NUM_VFS_BB \ + : MAX_NUM_VFS_K2) +#define NUM_OF_L2_QUEUES(dev) (QED_IS_BB(dev) ? MAX_NUM_L2_QUEUES_BB \ + : MAX_NUM_L2_QUEUES_K2) +#define NUM_OF_PORTS(dev) (QED_IS_BB(dev) ? MAX_NUM_PORTS_BB \ + : MAX_NUM_PORTS_K2) +#define NUM_OF_SBS(dev) (QED_IS_BB(dev) ? MAX_SB_PER_PATH_BB \ + : MAX_SB_PER_PATH_K2) +#define NUM_OF_ENG_PFS(dev) (QED_IS_BB(dev) ? MAX_NUM_PFS_BB \ + : MAX_NUM_PFS_K2) /** * @brief qed_concrete_to_sw_fid - get the sw function id from @@ -694,6 +704,7 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); #define QED_LEADING_HWFN(dev) (&dev->hwfns[0]) +int qed_device_num_engines(struct qed_dev *cdev); /* Other Linux specific common definitions */ #define DP_NAME(cdev) ((cdev)->name) diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 5e81e8a7a109..483241b4b05d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -1557,7 +1557,7 @@ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn, dev_data->mode_enable[MODE_K2] = 1; } else if (QED_IS_BB_B0(p_hwfn->cdev)) { dev_data->chip_id = CHIP_BB_B0; - dev_data->mode_enable[MODE_BB_B0] = 1; + dev_data->mode_enable[MODE_BB] = 1; } else { return DBG_STATUS_UNKNOWN_CHIP; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index e2a081ceaf52..bd4f43ffb5a1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -674,11 +674,19 @@ int qed_final_cleanup(struct qed_hwfn *p_hwfn, return rc; } -static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) +static int qed_calc_hw_mode(struct qed_hwfn *p_hwfn) { int hw_mode = 0; - hw_mode = (1 << MODE_BB_B0); + if (QED_IS_BB_B0(p_hwfn->cdev)) { + hw_mode |= 1 << MODE_BB; + } else if (QED_IS_AH(p_hwfn->cdev)) { + hw_mode |= 1 << MODE_K2; + } else { + DP_NOTICE(p_hwfn, "Unknown chip type %#x\n", + p_hwfn->cdev->type); + return -EINVAL; + } switch (p_hwfn->cdev->num_ports_in_engines) { case 1: @@ -693,7 +701,7 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) default: DP_NOTICE(p_hwfn, "num_ports_in_engine = %d not supported\n", p_hwfn->cdev->num_ports_in_engines); - return; + return -EINVAL; } switch (p_hwfn->cdev->mf_mode) { @@ -719,6 +727,8 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) DP_VERBOSE(p_hwfn, (NETIF_MSG_PROBE | NETIF_MSG_IFUP), "Configuring function for hw_mode: 0x%08x\n", p_hwfn->hw_info.hw_mode); + + return 0; } /* Init run time data for all PFs on an engine. */ @@ -754,10 +764,10 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, struct qed_qm_info *qm_info = &p_hwfn->qm_info; struct qed_qm_common_rt_init_params params; struct qed_dev *cdev = p_hwfn->cdev; + u8 vf_id, max_num_vfs; u16 num_pfs, pf_id; u32 concrete_fid; int rc = 0; - u8 vf_id; qed_init_cau_rt_data(cdev); @@ -814,7 +824,8 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id); } - for (vf_id = 0; vf_id < MAX_NUM_VFS_BB; vf_id++) { + max_num_vfs = QED_IS_AH(cdev) ? MAX_NUM_VFS_K2 : MAX_NUM_VFS_BB; + for (vf_id = 0; vf_id < max_num_vfs; vf_id++) { concrete_fid = qed_vfid_to_concrete(p_hwfn, vf_id); qed_fid_pretend(p_hwfn, p_ptt, (u16) concrete_fid); qed_wr(p_hwfn, p_ptt, CCFC_REG_STRONG_ENABLE_VF, 0x1); @@ -1135,7 +1146,9 @@ int qed_hw_init(struct qed_dev *cdev, /* Enable DMAE in PXP */ rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true); - qed_calc_hw_mode(p_hwfn); + rc = qed_calc_hw_mode(p_hwfn); + if (rc) + return rc; rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt, &load_code); if (rc) { @@ -1485,10 +1498,25 @@ static void qed_hw_hwfn_free(struct qed_hwfn *p_hwfn) static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn) { /* clear indirect access */ - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_88_F0, 0); - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_8C_F0, 0); - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_90_F0, 0); - qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_94_F0, 0); + if (QED_IS_AH(p_hwfn->cdev)) { + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_E8_F0_K2, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_EC_F0_K2, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_F0_F0_K2, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_F4_F0_K2, 0); + } else { + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_88_F0_BB, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_8C_F0_BB, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_90_F0_BB, 0); + qed_wr(p_hwfn, p_hwfn->p_main_ptt, + PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0); + } /* Clean Previous errors if such exist */ qed_wr(p_hwfn, p_hwfn->p_main_ptt, @@ -1610,6 +1638,7 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, enum qed_resources res_id) { u8 num_funcs = p_hwfn->num_funcs_on_engine; + bool b_ah = QED_IS_AH(p_hwfn->cdev); struct qed_sb_cnt_info sb_cnt_info; u32 dflt_resc_num = 0; @@ -1620,17 +1649,22 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, dflt_resc_num = sb_cnt_info.sb_cnt; break; case QED_L2_QUEUE: - dflt_resc_num = MAX_NUM_L2_QUEUES_BB / num_funcs; + dflt_resc_num = (b_ah ? MAX_NUM_L2_QUEUES_K2 + : MAX_NUM_L2_QUEUES_BB) / num_funcs; break; case QED_VPORT: dflt_resc_num = MAX_NUM_VPORTS_BB / num_funcs; + dflt_resc_num = (b_ah ? MAX_NUM_VPORTS_K2 + : MAX_NUM_VPORTS_BB) / num_funcs; break; case QED_RSS_ENG: - dflt_resc_num = ETH_RSS_ENGINE_NUM_BB / num_funcs; + dflt_resc_num = (b_ah ? ETH_RSS_ENGINE_NUM_K2 + : ETH_RSS_ENGINE_NUM_BB) / num_funcs; break; case QED_PQ: /* The granularity of the PQs is 8 */ - dflt_resc_num = MAX_QM_TX_QUEUES_BB / num_funcs; + dflt_resc_num = (b_ah ? MAX_QM_TX_QUEUES_K2 + : MAX_QM_TX_QUEUES_BB) / num_funcs; dflt_resc_num &= ~0x7; break; case QED_RL: @@ -1642,7 +1676,8 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, dflt_resc_num = ETH_NUM_MAC_FILTERS / num_funcs; break; case QED_ILT: - dflt_resc_num = PXP_NUM_ILT_RECORDS_BB / num_funcs; + dflt_resc_num = (b_ah ? PXP_NUM_ILT_RECORDS_K2 + : PXP_NUM_ILT_RECORDS_BB) / num_funcs; break; case QED_LL2_QUEUE: dflt_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs; @@ -1653,7 +1688,10 @@ static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn, dflt_resc_num = NUM_OF_CMDQS_CQS / num_funcs; break; case QED_RDMA_STATS_QUEUE: - dflt_resc_num = RDMA_NUM_STATISTIC_COUNTERS_BB / num_funcs; + dflt_resc_num = (b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2 + : RDMA_NUM_STATISTIC_COUNTERS_BB) / + num_funcs; + break; default: break; @@ -1780,6 +1818,7 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn, static int qed_hw_get_resc(struct qed_hwfn *p_hwfn) { + bool b_ah = QED_IS_AH(p_hwfn->cdev); u8 res_id; int rc; @@ -1790,7 +1829,8 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn) } /* Sanity for ILT */ - if ((RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB)) { + if ((b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_K2)) || + (!b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB))) { DP_NOTICE(p_hwfn, "Can't assign ILT pages [%08x,...,%08x]\n", RESC_START(p_hwfn, QED_ILT), RESC_END(p_hwfn, QED_ILT) - 1); @@ -1860,9 +1900,15 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G: p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X25G; break; + case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G: + p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X10G; + break; case NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G: p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_1X25G; break; + case NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G: + p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_4X25G; + break; default: DP_NOTICE(p_hwfn, "Unknown port mode in 0x%08x\n", core_cfg); break; @@ -1976,8 +2022,9 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u8 num_funcs, enabled_func_idx = p_hwfn->rel_pf_id; u32 reg_function_hide, tmp, eng_mask, low_pfs_mask; + struct qed_dev *cdev = p_hwfn->cdev; - num_funcs = MAX_NUM_PFS_BB; + num_funcs = QED_IS_AH(cdev) ? MAX_NUM_PFS_K2 : MAX_NUM_PFS_BB; /* Bit 0 of MISCS_REG_FUNCTION_HIDE indicates whether the bypass values * in the other bits are selected. @@ -1990,12 +2037,17 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) reg_function_hide = qed_rd(p_hwfn, p_ptt, MISCS_REG_FUNCTION_HIDE); if (reg_function_hide & 0x1) { - if (QED_PATH_ID(p_hwfn) && p_hwfn->cdev->num_hwfns == 1) { - num_funcs = 0; - eng_mask = 0xaaaa; + if (QED_IS_BB(cdev)) { + if (QED_PATH_ID(p_hwfn) && cdev->num_hwfns == 1) { + num_funcs = 0; + eng_mask = 0xaaaa; + } else { + num_funcs = 1; + eng_mask = 0x5554; + } } else { num_funcs = 1; - eng_mask = 0x5554; + eng_mask = 0xfffe; } /* Get the number of the enabled functions on the engine */ @@ -2027,24 +2079,12 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine); } -static int -qed_get_hw_info(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - enum qed_pci_personality personality) +static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) { u32 port_mode; - int rc; - /* Since all information is common, only first hwfns should do this */ - if (IS_LEAD_HWFN(p_hwfn)) { - rc = qed_iov_hw_info(p_hwfn); - if (rc) - return rc; - } - - /* Read the port mode */ - port_mode = qed_rd(p_hwfn, p_ptt, - CNIG_REG_NW_PORT_MODE_BB_B0); + port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB_B0); if (port_mode < 3) { p_hwfn->cdev->num_ports_in_engines = 1; @@ -2057,6 +2097,54 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, /* Default num_ports_in_engines to something */ p_hwfn->cdev->num_ports_in_engines = 1; } +} + +static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + u32 port; + int i; + + p_hwfn->cdev->num_ports_in_engines = 0; + + for (i = 0; i < MAX_NUM_PORTS_K2; i++) { + port = qed_rd(p_hwfn, p_ptt, + CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4)); + if (port & 1) + p_hwfn->cdev->num_ports_in_engines++; + } + + if (!p_hwfn->cdev->num_ports_in_engines) { + DP_NOTICE(p_hwfn, "All NIG ports are inactive\n"); + + /* Default num_ports_in_engine to something */ + p_hwfn->cdev->num_ports_in_engines = 1; + } +} + +static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + if (QED_IS_BB(p_hwfn->cdev)) + qed_hw_info_port_num_bb(p_hwfn, p_ptt); + else + qed_hw_info_port_num_ah(p_hwfn, p_ptt); +} + +static int +qed_get_hw_info(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum qed_pci_personality personality) +{ + int rc; + + /* Since all information is common, only first hwfns should do this */ + if (IS_LEAD_HWFN(p_hwfn)) { + rc = qed_iov_hw_info(p_hwfn); + if (rc) + return rc; + } + + qed_hw_info_port_num(p_hwfn, p_ptt); qed_hw_get_nvm_info(p_hwfn, p_ptt); @@ -2096,19 +2184,33 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, static int qed_get_dev_info(struct qed_dev *cdev) { struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + u16 device_id_mask; u32 tmp; /* Read Vendor Id / Device Id */ pci_read_config_word(cdev->pdev, PCI_VENDOR_ID, &cdev->vendor_id); pci_read_config_word(cdev->pdev, PCI_DEVICE_ID, &cdev->device_id); + /* Determine type */ + device_id_mask = cdev->device_id & QED_DEV_ID_MASK; + switch (device_id_mask) { + case QED_DEV_ID_MASK_BB: + cdev->type = QED_DEV_TYPE_BB; + break; + case QED_DEV_ID_MASK_AH: + cdev->type = QED_DEV_TYPE_AH; + break; + default: + DP_NOTICE(p_hwfn, "Unknown device id 0x%x\n", cdev->device_id); + return -EBUSY; + } + cdev->chip_num = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_NUM); cdev->chip_rev = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_REV); MASK_FIELD(CHIP_REV, cdev->chip_rev); - cdev->type = QED_DEV_TYPE_BB; /* Learn number of HW-functions */ tmp = qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CMT_ENABLED_FOR_PAIR); @@ -2128,7 +2230,10 @@ static int qed_get_dev_info(struct qed_dev *cdev) MASK_FIELD(CHIP_METAL, cdev->chip_metal); DP_INFO(cdev->hwfns, - "Chip details - Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n", + "Chip details - %s %c%d, Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n", + QED_IS_BB(cdev) ? "BB" : "AH", + 'A' + cdev->chip_rev, + (int)cdev->chip_metal, cdev->chip_num, cdev->chip_rev, cdev->chip_bond_id, cdev->chip_metal); @@ -3364,3 +3469,8 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) memset(p_hwfn->qm_info.wfq_data, 0, sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports); } + +int qed_device_num_engines(struct qed_dev *cdev) +{ + return QED_IS_BB(cdev) ? 2 : 1; +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 88ca78a297a0..e9acdc96ba84 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -2502,7 +2502,7 @@ struct fw_info_location { enum init_modes { MODE_RESERVED, - MODE_BB_B0, + MODE_BB, MODE_K2, MODE_ASIC, MODE_RESERVED2, @@ -9431,11 +9431,24 @@ struct eth_stats { u64 r511; u64 r1023; u64 r1518; - u64 r1522; - u64 r2047; - u64 r4095; - u64 r9216; - u64 r16383; + + union { + struct { + u64 r1522; + u64 r2047; + u64 r4095; + u64 r9216; + u64 r16383; + } bb0; + struct { + u64 unused1; + u64 r1519_to_max; + u64 unused2; + u64 unused3; + u64 unused4; + } ah0; + } u0; + u64 rfcs; u64 rxcf; u64 rxpf; @@ -9452,14 +9465,36 @@ struct eth_stats { u64 t511; u64 t1023; u64 t1518; - u64 t2047; - u64 t4095; - u64 t9216; - u64 t16383; + + union { + struct { + u64 t2047; + u64 t4095; + u64 t9216; + u64 t16383; + } bb1; + struct { + u64 t1519_to_max; + u64 unused6; + u64 unused7; + u64 unused8; + } ah1; + } u1; + u64 txpf; u64 txpp; - u64 tlpiec; - u64 tncl; + + union { + struct { + u64 tlpiec; + u64 tncl; + } bb2; + struct { + u64 unused9; + u64 unused10; + } ah2; + } u2; + u64 rbyte; u64 rxuca; u64 rxmca; @@ -10263,6 +10298,8 @@ struct nvm_cfg1_glob { #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G 0xC #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G 0xD #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G 0xE +#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G 0xF + u32 e_lane_cfg1; u32 e_lane_cfg2; u32 f_lane_cfg1; diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index df932be5a4e5..4385ccbb5efb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1470,13 +1470,20 @@ static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn, memset(&pstats, 0, sizeof(pstats)); qed_memcpy_from(p_hwfn, p_ptt, &pstats, pstats_addr, pstats_len); - p_stats->tx_ucast_bytes += HILO_64_REGPAIR(pstats.sent_ucast_bytes); - p_stats->tx_mcast_bytes += HILO_64_REGPAIR(pstats.sent_mcast_bytes); - p_stats->tx_bcast_bytes += HILO_64_REGPAIR(pstats.sent_bcast_bytes); - p_stats->tx_ucast_pkts += HILO_64_REGPAIR(pstats.sent_ucast_pkts); - p_stats->tx_mcast_pkts += HILO_64_REGPAIR(pstats.sent_mcast_pkts); - p_stats->tx_bcast_pkts += HILO_64_REGPAIR(pstats.sent_bcast_pkts); - p_stats->tx_err_drop_pkts += HILO_64_REGPAIR(pstats.error_drop_pkts); + p_stats->common.tx_ucast_bytes += + HILO_64_REGPAIR(pstats.sent_ucast_bytes); + p_stats->common.tx_mcast_bytes += + HILO_64_REGPAIR(pstats.sent_mcast_bytes); + p_stats->common.tx_bcast_bytes += + HILO_64_REGPAIR(pstats.sent_bcast_bytes); + p_stats->common.tx_ucast_pkts += + HILO_64_REGPAIR(pstats.sent_ucast_pkts); + p_stats->common.tx_mcast_pkts += + HILO_64_REGPAIR(pstats.sent_mcast_pkts); + p_stats->common.tx_bcast_pkts += + HILO_64_REGPAIR(pstats.sent_bcast_pkts); + p_stats->common.tx_err_drop_pkts += + HILO_64_REGPAIR(pstats.error_drop_pkts); } static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn, @@ -1502,10 +1509,10 @@ static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn, memset(&tstats, 0, sizeof(tstats)); qed_memcpy_from(p_hwfn, p_ptt, &tstats, tstats_addr, tstats_len); - p_stats->mftag_filter_discards += - HILO_64_REGPAIR(tstats.mftag_filter_discard); - p_stats->mac_filter_discards += - HILO_64_REGPAIR(tstats.eth_mac_filter_discard); + p_stats->common.mftag_filter_discards += + HILO_64_REGPAIR(tstats.mftag_filter_discard); + p_stats->common.mac_filter_discards += + HILO_64_REGPAIR(tstats.eth_mac_filter_discard); } static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn, @@ -1539,12 +1546,15 @@ static void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn, memset(&ustats, 0, sizeof(ustats)); qed_memcpy_from(p_hwfn, p_ptt, &ustats, ustats_addr, ustats_len); - p_stats->rx_ucast_bytes += HILO_64_REGPAIR(ustats.rcv_ucast_bytes); - p_stats->rx_mcast_bytes += HILO_64_REGPAIR(ustats.rcv_mcast_bytes); - p_stats->rx_bcast_bytes += HILO_64_REGPAIR(ustats.rcv_bcast_bytes); - p_stats->rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts); - p_stats->rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts); - p_stats->rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts); + p_stats->common.rx_ucast_bytes += + HILO_64_REGPAIR(ustats.rcv_ucast_bytes); + p_stats->common.rx_mcast_bytes += + HILO_64_REGPAIR(ustats.rcv_mcast_bytes); + p_stats->common.rx_bcast_bytes += + HILO_64_REGPAIR(ustats.rcv_bcast_bytes); + p_stats->common.rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts); + p_stats->common.rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts); + p_stats->common.rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts); } static void __qed_get_vport_mstats_addrlen(struct qed_hwfn *p_hwfn, @@ -1578,23 +1588,26 @@ static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn, memset(&mstats, 0, sizeof(mstats)); qed_memcpy_from(p_hwfn, p_ptt, &mstats, mstats_addr, mstats_len); - p_stats->no_buff_discards += HILO_64_REGPAIR(mstats.no_buff_discard); - p_stats->packet_too_big_discard += - HILO_64_REGPAIR(mstats.packet_too_big_discard); - p_stats->ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard); - p_stats->tpa_coalesced_pkts += - HILO_64_REGPAIR(mstats.tpa_coalesced_pkts); - p_stats->tpa_coalesced_events += - HILO_64_REGPAIR(mstats.tpa_coalesced_events); - p_stats->tpa_aborts_num += HILO_64_REGPAIR(mstats.tpa_aborts_num); - p_stats->tpa_coalesced_bytes += - HILO_64_REGPAIR(mstats.tpa_coalesced_bytes); + p_stats->common.no_buff_discards += + HILO_64_REGPAIR(mstats.no_buff_discard); + p_stats->common.packet_too_big_discard += + HILO_64_REGPAIR(mstats.packet_too_big_discard); + p_stats->common.ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard); + p_stats->common.tpa_coalesced_pkts += + HILO_64_REGPAIR(mstats.tpa_coalesced_pkts); + p_stats->common.tpa_coalesced_events += + HILO_64_REGPAIR(mstats.tpa_coalesced_events); + p_stats->common.tpa_aborts_num += + HILO_64_REGPAIR(mstats.tpa_aborts_num); + p_stats->common.tpa_coalesced_bytes += + HILO_64_REGPAIR(mstats.tpa_coalesced_bytes); } static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_eth_stats *p_stats) { + struct qed_eth_stats_common *p_common = &p_stats->common; struct port_stats port_stats; int j; @@ -1605,54 +1618,75 @@ static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, offsetof(struct public_port, stats), sizeof(port_stats)); - p_stats->rx_64_byte_packets += port_stats.eth.r64; - p_stats->rx_65_to_127_byte_packets += port_stats.eth.r127; - p_stats->rx_128_to_255_byte_packets += port_stats.eth.r255; - p_stats->rx_256_to_511_byte_packets += port_stats.eth.r511; - p_stats->rx_512_to_1023_byte_packets += port_stats.eth.r1023; - p_stats->rx_1024_to_1518_byte_packets += port_stats.eth.r1518; - p_stats->rx_1519_to_1522_byte_packets += port_stats.eth.r1522; - p_stats->rx_1519_to_2047_byte_packets += port_stats.eth.r2047; - p_stats->rx_2048_to_4095_byte_packets += port_stats.eth.r4095; - p_stats->rx_4096_to_9216_byte_packets += port_stats.eth.r9216; - p_stats->rx_9217_to_16383_byte_packets += port_stats.eth.r16383; - p_stats->rx_crc_errors += port_stats.eth.rfcs; - p_stats->rx_mac_crtl_frames += port_stats.eth.rxcf; - p_stats->rx_pause_frames += port_stats.eth.rxpf; - p_stats->rx_pfc_frames += port_stats.eth.rxpp; - p_stats->rx_align_errors += port_stats.eth.raln; - p_stats->rx_carrier_errors += port_stats.eth.rfcr; - p_stats->rx_oversize_packets += port_stats.eth.rovr; - p_stats->rx_jabbers += port_stats.eth.rjbr; - p_stats->rx_undersize_packets += port_stats.eth.rund; - p_stats->rx_fragments += port_stats.eth.rfrg; - p_stats->tx_64_byte_packets += port_stats.eth.t64; - p_stats->tx_65_to_127_byte_packets += port_stats.eth.t127; - p_stats->tx_128_to_255_byte_packets += port_stats.eth.t255; - p_stats->tx_256_to_511_byte_packets += port_stats.eth.t511; - p_stats->tx_512_to_1023_byte_packets += port_stats.eth.t1023; - p_stats->tx_1024_to_1518_byte_packets += port_stats.eth.t1518; - p_stats->tx_1519_to_2047_byte_packets += port_stats.eth.t2047; - p_stats->tx_2048_to_4095_byte_packets += port_stats.eth.t4095; - p_stats->tx_4096_to_9216_byte_packets += port_stats.eth.t9216; - p_stats->tx_9217_to_16383_byte_packets += port_stats.eth.t16383; - p_stats->tx_pause_frames += port_stats.eth.txpf; - p_stats->tx_pfc_frames += port_stats.eth.txpp; - p_stats->tx_lpi_entry_count += port_stats.eth.tlpiec; - p_stats->tx_total_collisions += port_stats.eth.tncl; - p_stats->rx_mac_bytes += port_stats.eth.rbyte; - p_stats->rx_mac_uc_packets += port_stats.eth.rxuca; - p_stats->rx_mac_mc_packets += port_stats.eth.rxmca; - p_stats->rx_mac_bc_packets += port_stats.eth.rxbca; - p_stats->rx_mac_frames_ok += port_stats.eth.rxpok; - p_stats->tx_mac_bytes += port_stats.eth.tbyte; - p_stats->tx_mac_uc_packets += port_stats.eth.txuca; - p_stats->tx_mac_mc_packets += port_stats.eth.txmca; - p_stats->tx_mac_bc_packets += port_stats.eth.txbca; - p_stats->tx_mac_ctrl_frames += port_stats.eth.txcf; + p_common->rx_64_byte_packets += port_stats.eth.r64; + p_common->rx_65_to_127_byte_packets += port_stats.eth.r127; + p_common->rx_128_to_255_byte_packets += port_stats.eth.r255; + p_common->rx_256_to_511_byte_packets += port_stats.eth.r511; + p_common->rx_512_to_1023_byte_packets += port_stats.eth.r1023; + p_common->rx_1024_to_1518_byte_packets += port_stats.eth.r1518; + p_common->rx_crc_errors += port_stats.eth.rfcs; + p_common->rx_mac_crtl_frames += port_stats.eth.rxcf; + p_common->rx_pause_frames += port_stats.eth.rxpf; + p_common->rx_pfc_frames += port_stats.eth.rxpp; + p_common->rx_align_errors += port_stats.eth.raln; + p_common->rx_carrier_errors += port_stats.eth.rfcr; + p_common->rx_oversize_packets += port_stats.eth.rovr; + p_common->rx_jabbers += port_stats.eth.rjbr; + p_common->rx_undersize_packets += port_stats.eth.rund; + p_common->rx_fragments += port_stats.eth.rfrg; + p_common->tx_64_byte_packets += port_stats.eth.t64; + p_common->tx_65_to_127_byte_packets += port_stats.eth.t127; + p_common->tx_128_to_255_byte_packets += port_stats.eth.t255; + p_common->tx_256_to_511_byte_packets += port_stats.eth.t511; + p_common->tx_512_to_1023_byte_packets += port_stats.eth.t1023; + p_common->tx_1024_to_1518_byte_packets += port_stats.eth.t1518; + p_common->tx_pause_frames += port_stats.eth.txpf; + p_common->tx_pfc_frames += port_stats.eth.txpp; + p_common->rx_mac_bytes += port_stats.eth.rbyte; + p_common->rx_mac_uc_packets += port_stats.eth.rxuca; + p_common->rx_mac_mc_packets += port_stats.eth.rxmca; + p_common->rx_mac_bc_packets += port_stats.eth.rxbca; + p_common->rx_mac_frames_ok += port_stats.eth.rxpok; + p_common->tx_mac_bytes += port_stats.eth.tbyte; + p_common->tx_mac_uc_packets += port_stats.eth.txuca; + p_common->tx_mac_mc_packets += port_stats.eth.txmca; + p_common->tx_mac_bc_packets += port_stats.eth.txbca; + p_common->tx_mac_ctrl_frames += port_stats.eth.txcf; for (j = 0; j < 8; j++) { - p_stats->brb_truncates += port_stats.brb.brb_truncate[j]; - p_stats->brb_discards += port_stats.brb.brb_discard[j]; + p_common->brb_truncates += port_stats.brb.brb_truncate[j]; + p_common->brb_discards += port_stats.brb.brb_discard[j]; + } + + if (QED_IS_BB(p_hwfn->cdev)) { + struct qed_eth_stats_bb *p_bb = &p_stats->bb; + + p_bb->rx_1519_to_1522_byte_packets += + port_stats.eth.u0.bb0.r1522; + p_bb->rx_1519_to_2047_byte_packets += + port_stats.eth.u0.bb0.r2047; + p_bb->rx_2048_to_4095_byte_packets += + port_stats.eth.u0.bb0.r4095; + p_bb->rx_4096_to_9216_byte_packets += + port_stats.eth.u0.bb0.r9216; + p_bb->rx_9217_to_16383_byte_packets += + port_stats.eth.u0.bb0.r16383; + p_bb->tx_1519_to_2047_byte_packets += + port_stats.eth.u1.bb1.t2047; + p_bb->tx_2048_to_4095_byte_packets += + port_stats.eth.u1.bb1.t4095; + p_bb->tx_4096_to_9216_byte_packets += + port_stats.eth.u1.bb1.t9216; + p_bb->tx_9217_to_16383_byte_packets += + port_stats.eth.u1.bb1.t16383; + p_bb->tx_lpi_entry_count += port_stats.eth.u2.bb2.tlpiec; + p_bb->tx_total_collisions += port_stats.eth.u2.bb2.tncl; + } else { + struct qed_eth_stats_ah *p_ah = &p_stats->ah; + + p_ah->rx_1519_to_max_byte_packets += + port_stats.eth.u0.ah0.r1519_to_max; + p_ah->tx_1519_to_max_byte_packets = + port_stats.eth.u1.ah1.t1519_to_max; } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index eef30a598b40..766c6f39ea63 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -238,6 +238,7 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->rdma_supported = (cdev->hwfns[0].hw_info.personality == QED_PCI_ETH_ROCE); dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]); + dev_info->dev_type = cdev->type; ether_addr_copy(dev_info->hw_mac, cdev->hwfns[0].hw_info.hw_mac_addr); if (IS_PF(cdev)) { @@ -1653,8 +1654,10 @@ void qed_get_protocol_stats(struct qed_dev *cdev, switch (type) { case QED_MCP_LAN_STATS: qed_get_vport_stats(cdev, ð_stats); - stats->lan_stats.ucast_rx_pkts = eth_stats.rx_ucast_pkts; - stats->lan_stats.ucast_tx_pkts = eth_stats.tx_ucast_pkts; + stats->lan_stats.ucast_rx_pkts = + eth_stats.common.rx_ucast_pkts; + stats->lan_stats.ucast_tx_pkts = + eth_stats.common.tx_ucast_pkts; stats->lan_stats.fcs_err = -1; break; case QED_MCP_FCOE_STATS: diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 368e88de146c..bdbfd6d4485e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -479,11 +479,10 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn, rel_pfid) #define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id) -/* TODO - this is only correct as long as only BB is supported, and - * no port-swapping is implemented; Afterwards we'll need to fix it. - */ -#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \ - ((_p_hwfn)->cdev->num_ports_in_engines * 2)) +#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \ + ((_p_hwfn)->cdev->num_ports_in_engines * \ + qed_device_num_engines((_p_hwfn)->cdev))) + struct qed_mcp_info { /* Spinlock used for protecting the access to the MFW mailbox */ spinlock_t lock; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c index d27aa85da23c..80c9c0b172dd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c @@ -262,12 +262,20 @@ static int qed_ptp_hw_enable(struct qed_dev *cdev) qed_wr(p_hwfn, p_ptt, NIG_REG_TS_OUTPUT_ENABLE_PDA, 0x1); /* Pause free running counter */ - qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2); + if (QED_IS_BB_B0(p_hwfn->cdev)) + qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2); + if (QED_IS_AH(p_hwfn->cdev)) + qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 2); qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_LSB, 0); qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_MSB, 0); /* Resume free running counter */ - qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4); + if (QED_IS_BB_B0(p_hwfn->cdev)) + qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4); + if (QED_IS_AH(p_hwfn->cdev)) { + qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 4); + qed_wr(p_hwfn, p_ptt, NIG_REG_PTP_LATCH_OSTS_PKT_TIME, 1); + } /* Disable drift register */ qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_DRIFT_CNTR_CONF, 0x0); diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index 36ae361884e0..6d4ac7e2ee83 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -160,13 +160,13 @@ 0x2e0704UL #define CCFC_REG_STRONG_ENABLE_PF \ 0x2e0708UL -#define PGLUE_B_REG_PGL_ADDR_88_F0 \ +#define PGLUE_B_REG_PGL_ADDR_88_F0_BB \ 0x2aa404UL -#define PGLUE_B_REG_PGL_ADDR_8C_F0 \ +#define PGLUE_B_REG_PGL_ADDR_8C_F0_BB \ 0x2aa408UL -#define PGLUE_B_REG_PGL_ADDR_90_F0 \ +#define PGLUE_B_REG_PGL_ADDR_90_F0_BB \ 0x2aa40cUL -#define PGLUE_B_REG_PGL_ADDR_94_F0 \ +#define PGLUE_B_REG_PGL_ADDR_94_F0_BB \ 0x2aa410UL #define PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR \ 0x2aa138UL @@ -1550,4 +1550,13 @@ #define NIG_REG_TIMESYNC_GEN_REG_BB 0x500d00UL #define NIG_REG_TSGEN_FREE_CNT_VALUE_LSB 0x5088a8UL #define NIG_REG_TSGEN_FREE_CNT_VALUE_MSB 0x5088acUL +#define NIG_REG_PTP_LATCH_OSTS_PKT_TIME 0x509040UL + +#define PGLUE_B_REG_PGL_ADDR_E8_F0_K2 0x2aaf98UL +#define PGLUE_B_REG_PGL_ADDR_EC_F0_K2 0x2aaf9cUL +#define PGLUE_B_REG_PGL_ADDR_F0_F0_K2 0x2aafa0UL +#define PGLUE_B_REG_PGL_ADDR_F4_F0_K2 0x2aafa4UL +#define NIG_REG_TSGEN_FREECNT_UPDATE_K2 0x509008UL +#define CNIG_REG_NIG_PORT0_CONF_K2 0x218200UL + #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 253c2bbe1e4e..16f503c9b0af 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -557,14 +557,30 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn) return 0; } - /* Calculate the first VF index - this is a bit tricky; Basically, - * VFs start at offset 16 relative to PF0, and 2nd engine VFs begin - * after the first engine's VFs. + /* First VF index based on offset is tricky: + * - If ARI is supported [likely], offset - (16 - pf_id) would + * provide the number for eng0. 2nd engine Vfs would begin + * after the first engine's VFs. + * - If !ARI, VFs would start on next device. + * so offset - (256 - pf_id) would provide the number. + * Utilize the fact that (256 - pf_id) is achieved only by later + * to diffrentiate between the two. */ - cdev->p_iov_info->first_vf_in_pf = p_hwfn->cdev->p_iov_info->offset + - p_hwfn->abs_pf_id - 16; - if (QED_PATH_ID(p_hwfn)) - cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB; + + if (p_hwfn->cdev->p_iov_info->offset < (256 - p_hwfn->abs_pf_id)) { + u32 first = p_hwfn->cdev->p_iov_info->offset + + p_hwfn->abs_pf_id - 16; + + cdev->p_iov_info->first_vf_in_pf = first; + + if (QED_PATH_ID(p_hwfn)) + cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB; + } else { + u32 first = p_hwfn->cdev->p_iov_info->offset + + p_hwfn->abs_pf_id - 256; + + cdev->p_iov_info->first_vf_in_pf = first; + } DP_VERBOSE(p_hwfn, QED_MSG_IOV, "First VF in hwfn 0x%08x\n", diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 8d02fb6c19d7..e73a4a5165ee 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -58,7 +58,7 @@ #define DRV_MODULE_SYM qede -struct qede_stats { +struct qede_stats_common { u64 no_buff_discards; u64 packet_too_big_discard; u64 ttl0_discard; @@ -90,11 +90,6 @@ struct qede_stats { u64 rx_256_to_511_byte_packets; u64 rx_512_to_1023_byte_packets; u64 rx_1024_to_1518_byte_packets; - u64 rx_1519_to_1522_byte_packets; - u64 rx_1519_to_2047_byte_packets; - u64 rx_2048_to_4095_byte_packets; - u64 rx_4096_to_9216_byte_packets; - u64 rx_9217_to_16383_byte_packets; u64 rx_crc_errors; u64 rx_mac_crtl_frames; u64 rx_pause_frames; @@ -111,17 +106,39 @@ struct qede_stats { u64 tx_256_to_511_byte_packets; u64 tx_512_to_1023_byte_packets; u64 tx_1024_to_1518_byte_packets; + u64 tx_pause_frames; + u64 tx_pfc_frames; + u64 brb_truncates; + u64 brb_discards; + u64 tx_mac_ctrl_frames; +}; + +struct qede_stats_bb { + u64 rx_1519_to_1522_byte_packets; + u64 rx_1519_to_2047_byte_packets; + u64 rx_2048_to_4095_byte_packets; + u64 rx_4096_to_9216_byte_packets; + u64 rx_9217_to_16383_byte_packets; u64 tx_1519_to_2047_byte_packets; u64 tx_2048_to_4095_byte_packets; u64 tx_4096_to_9216_byte_packets; u64 tx_9217_to_16383_byte_packets; - u64 tx_pause_frames; - u64 tx_pfc_frames; u64 tx_lpi_entry_count; u64 tx_total_collisions; - u64 brb_truncates; - u64 brb_discards; - u64 tx_mac_ctrl_frames; +}; + +struct qede_stats_ah { + u64 rx_1519_to_max_byte_packets; + u64 tx_1519_to_max_byte_packets; +}; + +struct qede_stats { + struct qede_stats_common common; + + union { + struct qede_stats_bb bb; + struct qede_stats_ah ah; + }; }; struct qede_vlan { @@ -158,6 +175,10 @@ struct qede_dev { struct qed_dev_eth_info dev_info; #define QEDE_MAX_RSS_CNT(edev) ((edev)->dev_info.num_queues) #define QEDE_MAX_TSS_CNT(edev) ((edev)->dev_info.num_queues) +#define QEDE_IS_BB(edev) \ + ((edev)->dev_info.common.dev_type == QED_DEV_TYPE_BB) +#define QEDE_IS_AH(edev) \ + ((edev)->dev_info.common.dev_type == QED_DEV_TYPE_AH) struct qede_fastpath *fp_array; u8 req_num_tx; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 897953133245..4dcfe9614731 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -75,16 +75,33 @@ static const struct { QEDE_TQSTAT(stopped_cnt), }; -#define QEDE_STAT_OFFSET(stat_name) (offsetof(struct qede_stats, stat_name)) -#define QEDE_STAT_STRING(stat_name) (#stat_name) -#define _QEDE_STAT(stat_name, pf_only) \ - {QEDE_STAT_OFFSET(stat_name), QEDE_STAT_STRING(stat_name), pf_only} -#define QEDE_PF_STAT(stat_name) _QEDE_STAT(stat_name, true) -#define QEDE_STAT(stat_name) _QEDE_STAT(stat_name, false) +#define QEDE_STAT_OFFSET(stat_name, type, base) \ + (offsetof(type, stat_name) + (base)) +#define QEDE_STAT_STRING(stat_name) (#stat_name) +#define _QEDE_STAT(stat_name, type, base, attr) \ + {QEDE_STAT_OFFSET(stat_name, type, base), \ + QEDE_STAT_STRING(stat_name), \ + attr} +#define QEDE_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_common, 0, 0x0) +#define QEDE_PF_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_common, 0, \ + BIT(QEDE_STAT_PF_ONLY)) +#define QEDE_PF_BB_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_bb, \ + offsetof(struct qede_stats, bb), \ + BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_BB_ONLY)) +#define QEDE_PF_AH_STAT(stat_name) \ + _QEDE_STAT(stat_name, struct qede_stats_ah, \ + offsetof(struct qede_stats, ah), \ + BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_AH_ONLY)) static const struct { u64 offset; char string[ETH_GSTRING_LEN]; - bool pf_only; + unsigned long attr; +#define QEDE_STAT_PF_ONLY 0 +#define QEDE_STAT_BB_ONLY 1 +#define QEDE_STAT_AH_ONLY 2 } qede_stats_arr[] = { QEDE_STAT(rx_ucast_bytes), QEDE_STAT(rx_mcast_bytes), @@ -106,22 +123,23 @@ static const struct { QEDE_PF_STAT(rx_256_to_511_byte_packets), QEDE_PF_STAT(rx_512_to_1023_byte_packets), QEDE_PF_STAT(rx_1024_to_1518_byte_packets), - QEDE_PF_STAT(rx_1519_to_1522_byte_packets), - QEDE_PF_STAT(rx_1519_to_2047_byte_packets), - QEDE_PF_STAT(rx_2048_to_4095_byte_packets), - QEDE_PF_STAT(rx_4096_to_9216_byte_packets), - QEDE_PF_STAT(rx_9217_to_16383_byte_packets), + QEDE_PF_BB_STAT(rx_1519_to_1522_byte_packets), + QEDE_PF_BB_STAT(rx_1519_to_2047_byte_packets), + QEDE_PF_BB_STAT(rx_2048_to_4095_byte_packets), + QEDE_PF_BB_STAT(rx_4096_to_9216_byte_packets), + QEDE_PF_BB_STAT(rx_9217_to_16383_byte_packets), + QEDE_PF_AH_STAT(rx_1519_to_max_byte_packets), QEDE_PF_STAT(tx_64_byte_packets), QEDE_PF_STAT(tx_65_to_127_byte_packets), QEDE_PF_STAT(tx_128_to_255_byte_packets), QEDE_PF_STAT(tx_256_to_511_byte_packets), QEDE_PF_STAT(tx_512_to_1023_byte_packets), QEDE_PF_STAT(tx_1024_to_1518_byte_packets), - QEDE_PF_STAT(tx_1519_to_2047_byte_packets), - QEDE_PF_STAT(tx_2048_to_4095_byte_packets), - QEDE_PF_STAT(tx_4096_to_9216_byte_packets), - QEDE_PF_STAT(tx_9217_to_16383_byte_packets), - + QEDE_PF_BB_STAT(tx_1519_to_2047_byte_packets), + QEDE_PF_BB_STAT(tx_2048_to_4095_byte_packets), + QEDE_PF_BB_STAT(tx_4096_to_9216_byte_packets), + QEDE_PF_BB_STAT(tx_9217_to_16383_byte_packets), + QEDE_PF_AH_STAT(tx_1519_to_max_byte_packets), QEDE_PF_STAT(rx_mac_crtl_frames), QEDE_PF_STAT(tx_mac_ctrl_frames), QEDE_PF_STAT(rx_pause_frames), @@ -136,8 +154,8 @@ static const struct { QEDE_PF_STAT(rx_jabbers), QEDE_PF_STAT(rx_undersize_packets), QEDE_PF_STAT(rx_fragments), - QEDE_PF_STAT(tx_lpi_entry_count), - QEDE_PF_STAT(tx_total_collisions), + QEDE_PF_BB_STAT(tx_lpi_entry_count), + QEDE_PF_BB_STAT(tx_total_collisions), QEDE_PF_STAT(brb_truncates), QEDE_PF_STAT(brb_discards), QEDE_STAT(no_buff_discards), @@ -155,6 +173,12 @@ static const struct { }; #define QEDE_NUM_STATS ARRAY_SIZE(qede_stats_arr) +#define QEDE_STAT_IS_PF_ONLY(i) \ + test_bit(QEDE_STAT_PF_ONLY, &qede_stats_arr[i].attr) +#define QEDE_STAT_IS_BB_ONLY(i) \ + test_bit(QEDE_STAT_BB_ONLY, &qede_stats_arr[i].attr) +#define QEDE_STAT_IS_AH_ONLY(i) \ + test_bit(QEDE_STAT_AH_ONLY, &qede_stats_arr[i].attr) enum { QEDE_PRI_FLAG_CMT, @@ -213,6 +237,13 @@ static void qede_get_strings_stats_rxq(struct qede_dev *edev, } } +static bool qede_is_irrelevant_stat(struct qede_dev *edev, int stat_index) +{ + return (IS_VF(edev) && QEDE_STAT_IS_PF_ONLY(stat_index)) || + (QEDE_IS_BB(edev) && QEDE_STAT_IS_AH_ONLY(stat_index)) || + (QEDE_IS_AH(edev) && QEDE_STAT_IS_BB_ONLY(stat_index)); +} + static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf) { struct qede_fastpath *fp; @@ -234,7 +265,7 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf) /* Account for non-queue statistics */ for (i = 0; i < QEDE_NUM_STATS; i++) { - if (IS_VF(edev) && qede_stats_arr[i].pf_only) + if (qede_is_irrelevant_stat(edev, i)) continue; strcpy(buf, qede_stats_arr[i].string); buf += ETH_GSTRING_LEN; @@ -309,7 +340,7 @@ static void qede_get_ethtool_stats(struct net_device *dev, } for (i = 0; i < QEDE_NUM_STATS; i++) { - if (IS_VF(edev) && qede_stats_arr[i].pf_only) + if (qede_is_irrelevant_stat(edev, i)) continue; *buf = *((u64 *)(((void *)&edev->stats) + qede_stats_arr[i].offset)); @@ -323,17 +354,13 @@ static void qede_get_ethtool_stats(struct net_device *dev, static int qede_get_sset_count(struct net_device *dev, int stringset) { struct qede_dev *edev = netdev_priv(dev); - int num_stats = QEDE_NUM_STATS; + int num_stats = QEDE_NUM_STATS, i; switch (stringset) { case ETH_SS_STATS: - if (IS_VF(edev)) { - int i; - - for (i = 0; i < QEDE_NUM_STATS; i++) - if (qede_stats_arr[i].pf_only) - num_stats--; - } + for (i = 0; i < QEDE_NUM_STATS; i++) + if (qede_is_irrelevant_stat(edev, i)) + num_stats--; /* Account for the Regular Tx statistics */ num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 3a78c3f25157..abd99109e532 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -84,6 +84,8 @@ static const struct qed_eth_ops *qed_ops; #define CHIP_NUM_57980S_50 0x1654 #define CHIP_NUM_57980S_25 0x1656 #define CHIP_NUM_57980S_IOV 0x1664 +#define CHIP_NUM_AH 0x8070 +#define CHIP_NUM_AH_IOV 0x8090 #ifndef PCI_DEVICE_ID_NX2_57980E #define PCI_DEVICE_ID_57980S_40 CHIP_NUM_57980S_40 @@ -93,6 +95,9 @@ static const struct qed_eth_ops *qed_ops; #define PCI_DEVICE_ID_57980S_50 CHIP_NUM_57980S_50 #define PCI_DEVICE_ID_57980S_25 CHIP_NUM_57980S_25 #define PCI_DEVICE_ID_57980S_IOV CHIP_NUM_57980S_IOV +#define PCI_DEVICE_ID_AH CHIP_NUM_AH +#define PCI_DEVICE_ID_AH_IOV CHIP_NUM_AH_IOV + #endif enum qede_pci_private { @@ -109,6 +114,10 @@ static const struct pci_device_id qede_pci_tbl[] = { {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_25), QEDE_PRIVATE_PF}, #ifdef CONFIG_QED_SRIOV {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF}, +#endif + {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH), QEDE_PRIVATE_PF}, +#ifdef CONFIG_QED_SRIOV + {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH_IOV), QEDE_PRIVATE_VF}, #endif { 0 } }; @@ -314,122 +323,135 @@ static int qede_close(struct net_device *ndev); void qede_fill_by_demand_stats(struct qede_dev *edev) { + struct qede_stats_common *p_common = &edev->stats.common; struct qed_eth_stats stats; edev->ops->get_vport_stats(edev->cdev, &stats); - edev->stats.no_buff_discards = stats.no_buff_discards; - edev->stats.packet_too_big_discard = stats.packet_too_big_discard; - edev->stats.ttl0_discard = stats.ttl0_discard; - edev->stats.rx_ucast_bytes = stats.rx_ucast_bytes; - edev->stats.rx_mcast_bytes = stats.rx_mcast_bytes; - edev->stats.rx_bcast_bytes = stats.rx_bcast_bytes; - edev->stats.rx_ucast_pkts = stats.rx_ucast_pkts; - edev->stats.rx_mcast_pkts = stats.rx_mcast_pkts; - edev->stats.rx_bcast_pkts = stats.rx_bcast_pkts; - edev->stats.mftag_filter_discards = stats.mftag_filter_discards; - edev->stats.mac_filter_discards = stats.mac_filter_discards; - edev->stats.tx_ucast_bytes = stats.tx_ucast_bytes; - edev->stats.tx_mcast_bytes = stats.tx_mcast_bytes; - edev->stats.tx_bcast_bytes = stats.tx_bcast_bytes; - edev->stats.tx_ucast_pkts = stats.tx_ucast_pkts; - edev->stats.tx_mcast_pkts = stats.tx_mcast_pkts; - edev->stats.tx_bcast_pkts = stats.tx_bcast_pkts; - edev->stats.tx_err_drop_pkts = stats.tx_err_drop_pkts; - edev->stats.coalesced_pkts = stats.tpa_coalesced_pkts; - edev->stats.coalesced_events = stats.tpa_coalesced_events; - edev->stats.coalesced_aborts_num = stats.tpa_aborts_num; - edev->stats.non_coalesced_pkts = stats.tpa_not_coalesced_pkts; - edev->stats.coalesced_bytes = stats.tpa_coalesced_bytes; + p_common->no_buff_discards = stats.common.no_buff_discards; + p_common->packet_too_big_discard = stats.common.packet_too_big_discard; + p_common->ttl0_discard = stats.common.ttl0_discard; + p_common->rx_ucast_bytes = stats.common.rx_ucast_bytes; + p_common->rx_mcast_bytes = stats.common.rx_mcast_bytes; + p_common->rx_bcast_bytes = stats.common.rx_bcast_bytes; + p_common->rx_ucast_pkts = stats.common.rx_ucast_pkts; + p_common->rx_mcast_pkts = stats.common.rx_mcast_pkts; + p_common->rx_bcast_pkts = stats.common.rx_bcast_pkts; + p_common->mftag_filter_discards = stats.common.mftag_filter_discards; + p_common->mac_filter_discards = stats.common.mac_filter_discards; - edev->stats.rx_64_byte_packets = stats.rx_64_byte_packets; - edev->stats.rx_65_to_127_byte_packets = stats.rx_65_to_127_byte_packets; - edev->stats.rx_128_to_255_byte_packets = - stats.rx_128_to_255_byte_packets; - edev->stats.rx_256_to_511_byte_packets = - stats.rx_256_to_511_byte_packets; - edev->stats.rx_512_to_1023_byte_packets = - stats.rx_512_to_1023_byte_packets; - edev->stats.rx_1024_to_1518_byte_packets = - stats.rx_1024_to_1518_byte_packets; - edev->stats.rx_1519_to_1522_byte_packets = - stats.rx_1519_to_1522_byte_packets; - edev->stats.rx_1519_to_2047_byte_packets = - stats.rx_1519_to_2047_byte_packets; - edev->stats.rx_2048_to_4095_byte_packets = - stats.rx_2048_to_4095_byte_packets; - edev->stats.rx_4096_to_9216_byte_packets = - stats.rx_4096_to_9216_byte_packets; - edev->stats.rx_9217_to_16383_byte_packets = - stats.rx_9217_to_16383_byte_packets; - edev->stats.rx_crc_errors = stats.rx_crc_errors; - edev->stats.rx_mac_crtl_frames = stats.rx_mac_crtl_frames; - edev->stats.rx_pause_frames = stats.rx_pause_frames; - edev->stats.rx_pfc_frames = stats.rx_pfc_frames; - edev->stats.rx_align_errors = stats.rx_align_errors; - edev->stats.rx_carrier_errors = stats.rx_carrier_errors; - edev->stats.rx_oversize_packets = stats.rx_oversize_packets; - edev->stats.rx_jabbers = stats.rx_jabbers; - edev->stats.rx_undersize_packets = stats.rx_undersize_packets; - edev->stats.rx_fragments = stats.rx_fragments; - edev->stats.tx_64_byte_packets = stats.tx_64_byte_packets; - edev->stats.tx_65_to_127_byte_packets = stats.tx_65_to_127_byte_packets; - edev->stats.tx_128_to_255_byte_packets = - stats.tx_128_to_255_byte_packets; - edev->stats.tx_256_to_511_byte_packets = - stats.tx_256_to_511_byte_packets; - edev->stats.tx_512_to_1023_byte_packets = - stats.tx_512_to_1023_byte_packets; - edev->stats.tx_1024_to_1518_byte_packets = - stats.tx_1024_to_1518_byte_packets; - edev->stats.tx_1519_to_2047_byte_packets = - stats.tx_1519_to_2047_byte_packets; - edev->stats.tx_2048_to_4095_byte_packets = - stats.tx_2048_to_4095_byte_packets; - edev->stats.tx_4096_to_9216_byte_packets = - stats.tx_4096_to_9216_byte_packets; - edev->stats.tx_9217_to_16383_byte_packets = - stats.tx_9217_to_16383_byte_packets; - edev->stats.tx_pause_frames = stats.tx_pause_frames; - edev->stats.tx_pfc_frames = stats.tx_pfc_frames; - edev->stats.tx_lpi_entry_count = stats.tx_lpi_entry_count; - edev->stats.tx_total_collisions = stats.tx_total_collisions; - edev->stats.brb_truncates = stats.brb_truncates; - edev->stats.brb_discards = stats.brb_discards; - edev->stats.tx_mac_ctrl_frames = stats.tx_mac_ctrl_frames; + p_common->tx_ucast_bytes = stats.common.tx_ucast_bytes; + p_common->tx_mcast_bytes = stats.common.tx_mcast_bytes; + p_common->tx_bcast_bytes = stats.common.tx_bcast_bytes; + p_common->tx_ucast_pkts = stats.common.tx_ucast_pkts; + p_common->tx_mcast_pkts = stats.common.tx_mcast_pkts; + p_common->tx_bcast_pkts = stats.common.tx_bcast_pkts; + p_common->tx_err_drop_pkts = stats.common.tx_err_drop_pkts; + p_common->coalesced_pkts = stats.common.tpa_coalesced_pkts; + p_common->coalesced_events = stats.common.tpa_coalesced_events; + p_common->coalesced_aborts_num = stats.common.tpa_aborts_num; + p_common->non_coalesced_pkts = stats.common.tpa_not_coalesced_pkts; + p_common->coalesced_bytes = stats.common.tpa_coalesced_bytes; + + p_common->rx_64_byte_packets = stats.common.rx_64_byte_packets; + p_common->rx_65_to_127_byte_packets = + stats.common.rx_65_to_127_byte_packets; + p_common->rx_128_to_255_byte_packets = + stats.common.rx_128_to_255_byte_packets; + p_common->rx_256_to_511_byte_packets = + stats.common.rx_256_to_511_byte_packets; + p_common->rx_512_to_1023_byte_packets = + stats.common.rx_512_to_1023_byte_packets; + p_common->rx_1024_to_1518_byte_packets = + stats.common.rx_1024_to_1518_byte_packets; + p_common->rx_crc_errors = stats.common.rx_crc_errors; + p_common->rx_mac_crtl_frames = stats.common.rx_mac_crtl_frames; + p_common->rx_pause_frames = stats.common.rx_pause_frames; + p_common->rx_pfc_frames = stats.common.rx_pfc_frames; + p_common->rx_align_errors = stats.common.rx_align_errors; + p_common->rx_carrier_errors = stats.common.rx_carrier_errors; + p_common->rx_oversize_packets = stats.common.rx_oversize_packets; + p_common->rx_jabbers = stats.common.rx_jabbers; + p_common->rx_undersize_packets = stats.common.rx_undersize_packets; + p_common->rx_fragments = stats.common.rx_fragments; + p_common->tx_64_byte_packets = stats.common.tx_64_byte_packets; + p_common->tx_65_to_127_byte_packets = + stats.common.tx_65_to_127_byte_packets; + p_common->tx_128_to_255_byte_packets = + stats.common.tx_128_to_255_byte_packets; + p_common->tx_256_to_511_byte_packets = + stats.common.tx_256_to_511_byte_packets; + p_common->tx_512_to_1023_byte_packets = + stats.common.tx_512_to_1023_byte_packets; + p_common->tx_1024_to_1518_byte_packets = + stats.common.tx_1024_to_1518_byte_packets; + p_common->tx_pause_frames = stats.common.tx_pause_frames; + p_common->tx_pfc_frames = stats.common.tx_pfc_frames; + p_common->brb_truncates = stats.common.brb_truncates; + p_common->brb_discards = stats.common.brb_discards; + p_common->tx_mac_ctrl_frames = stats.common.tx_mac_ctrl_frames; + + if (QEDE_IS_BB(edev)) { + struct qede_stats_bb *p_bb = &edev->stats.bb; + + p_bb->rx_1519_to_1522_byte_packets = + stats.bb.rx_1519_to_1522_byte_packets; + p_bb->rx_1519_to_2047_byte_packets = + stats.bb.rx_1519_to_2047_byte_packets; + p_bb->rx_2048_to_4095_byte_packets = + stats.bb.rx_2048_to_4095_byte_packets; + p_bb->rx_4096_to_9216_byte_packets = + stats.bb.rx_4096_to_9216_byte_packets; + p_bb->rx_9217_to_16383_byte_packets = + stats.bb.rx_9217_to_16383_byte_packets; + p_bb->tx_1519_to_2047_byte_packets = + stats.bb.tx_1519_to_2047_byte_packets; + p_bb->tx_2048_to_4095_byte_packets = + stats.bb.tx_2048_to_4095_byte_packets; + p_bb->tx_4096_to_9216_byte_packets = + stats.bb.tx_4096_to_9216_byte_packets; + p_bb->tx_9217_to_16383_byte_packets = + stats.bb.tx_9217_to_16383_byte_packets; + p_bb->tx_lpi_entry_count = stats.bb.tx_lpi_entry_count; + p_bb->tx_total_collisions = stats.bb.tx_total_collisions; + } else { + struct qede_stats_ah *p_ah = &edev->stats.ah; + + p_ah->rx_1519_to_max_byte_packets = + stats.ah.rx_1519_to_max_byte_packets; + p_ah->tx_1519_to_max_byte_packets = + stats.ah.tx_1519_to_max_byte_packets; + } } static void qede_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct qede_dev *edev = netdev_priv(dev); + struct qede_stats_common *p_common; qede_fill_by_demand_stats(edev); + p_common = &edev->stats.common; - stats->rx_packets = edev->stats.rx_ucast_pkts + - edev->stats.rx_mcast_pkts + - edev->stats.rx_bcast_pkts; - stats->tx_packets = edev->stats.tx_ucast_pkts + - edev->stats.tx_mcast_pkts + - edev->stats.tx_bcast_pkts; + stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts + + p_common->rx_bcast_pkts; + stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts + + p_common->tx_bcast_pkts; - stats->rx_bytes = edev->stats.rx_ucast_bytes + - edev->stats.rx_mcast_bytes + - edev->stats.rx_bcast_bytes; + stats->rx_bytes = p_common->rx_ucast_bytes + p_common->rx_mcast_bytes + + p_common->rx_bcast_bytes; + stats->tx_bytes = p_common->tx_ucast_bytes + p_common->tx_mcast_bytes + + p_common->tx_bcast_bytes; - stats->tx_bytes = edev->stats.tx_ucast_bytes + - edev->stats.tx_mcast_bytes + - edev->stats.tx_bcast_bytes; + stats->tx_errors = p_common->tx_err_drop_pkts; + stats->multicast = p_common->rx_mcast_pkts + p_common->rx_bcast_pkts; - stats->tx_errors = edev->stats.tx_err_drop_pkts; - stats->multicast = edev->stats.rx_mcast_pkts + - edev->stats.rx_bcast_pkts; + stats->rx_fifo_errors = p_common->no_buff_discards; - stats->rx_fifo_errors = edev->stats.no_buff_discards; - - stats->collisions = edev->stats.tx_total_collisions; - stats->rx_crc_errors = edev->stats.rx_crc_errors; - stats->rx_frame_errors = edev->stats.rx_align_errors; + if (QEDE_IS_BB(edev)) + stats->collisions = edev->stats.bb.tx_total_collisions; + stats->rx_crc_errors = p_common->rx_crc_errors; + stats->rx_frame_errors = p_common->rx_align_errors; } #ifdef CONFIG_QED_SRIOV diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index fde56c436f71..8e0065c52857 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -300,6 +300,11 @@ struct qed_sb_info { struct qed_dev *cdev; }; +enum qed_dev_type { + QED_DEV_TYPE_BB, + QED_DEV_TYPE_AH, +}; + struct qed_dev_info { unsigned long pci_mem_start; unsigned long pci_mem_end; @@ -325,6 +330,8 @@ struct qed_dev_info { u16 mtu; bool wol_support; + + enum qed_dev_type dev_type; }; enum qed_sb_type { @@ -752,7 +759,7 @@ enum qed_mf_mode { QED_MF_NPAR, }; -struct qed_eth_stats { +struct qed_eth_stats_common { u64 no_buff_discards; u64 packet_too_big_discard; u64 ttl0_discard; @@ -784,11 +791,6 @@ struct qed_eth_stats { u64 rx_256_to_511_byte_packets; u64 rx_512_to_1023_byte_packets; u64 rx_1024_to_1518_byte_packets; - u64 rx_1519_to_1522_byte_packets; - u64 rx_1519_to_2047_byte_packets; - u64 rx_2048_to_4095_byte_packets; - u64 rx_4096_to_9216_byte_packets; - u64 rx_9217_to_16383_byte_packets; u64 rx_crc_errors; u64 rx_mac_crtl_frames; u64 rx_pause_frames; @@ -805,14 +807,8 @@ struct qed_eth_stats { u64 tx_256_to_511_byte_packets; u64 tx_512_to_1023_byte_packets; u64 tx_1024_to_1518_byte_packets; - u64 tx_1519_to_2047_byte_packets; - u64 tx_2048_to_4095_byte_packets; - u64 tx_4096_to_9216_byte_packets; - u64 tx_9217_to_16383_byte_packets; u64 tx_pause_frames; u64 tx_pfc_frames; - u64 tx_lpi_entry_count; - u64 tx_total_collisions; u64 brb_truncates; u64 brb_discards; u64 rx_mac_bytes; @@ -827,6 +823,34 @@ struct qed_eth_stats { u64 tx_mac_ctrl_frames; }; +struct qed_eth_stats_bb { + u64 rx_1519_to_1522_byte_packets; + u64 rx_1519_to_2047_byte_packets; + u64 rx_2048_to_4095_byte_packets; + u64 rx_4096_to_9216_byte_packets; + u64 rx_9217_to_16383_byte_packets; + u64 tx_1519_to_2047_byte_packets; + u64 tx_2048_to_4095_byte_packets; + u64 tx_4096_to_9216_byte_packets; + u64 tx_9217_to_16383_byte_packets; + u64 tx_lpi_entry_count; + u64 tx_total_collisions; +}; + +struct qed_eth_stats_ah { + u64 rx_1519_to_max_byte_packets; + u64 tx_1519_to_max_byte_packets; +}; + +struct qed_eth_stats { + struct qed_eth_stats_common common; + + union { + struct qed_eth_stats_bb bb; + struct qed_eth_stats_ah ah; + }; +}; + #define QED_SB_IDX 0x0002 #define RX_PI 0 diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index f773aa5e746f..72c770f9f666 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -52,7 +52,8 @@ #define RDMA_MAX_PDS (64 * 1024) #define RDMA_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS -#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB +#define RDMA_NUM_STATISTIC_COUNTERS_K2 MAX_NUM_VPORTS_K2 +#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB #define RDMA_TASK_TYPE (PROTOCOLID_ROCE) From 96a39aed25e6559b160786117df124084feb9080 Mon Sep 17 00:00:00 2001 From: Aaron Salter Date: Fri, 2 Dec 2016 12:33:02 -0800 Subject: [PATCH 260/399] i40e: Acquire NVM lock before reads on all devices Acquire NVM lock before reads on all devices. Previously, locks were only used for X722 and later. Fixes an issue where simultaneous X710 NVM accesses were interfering with each other. Change-ID: If570bb7acf958cef58725ec2a2011cead6f80638 Signed-off-by: Aaron Salter Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_nvm.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 38ee18f11124..800bd55d0159 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -292,14 +292,14 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, { enum i40e_status_code ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { - ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); - if (!ret_code) { + ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (!ret_code) { + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { ret_code = i40e_read_nvm_word_aq(hw, offset, data); - i40e_release_nvm(hw); + } else { + ret_code = i40e_read_nvm_word_srctl(hw, offset, data); } - } else { - ret_code = i40e_read_nvm_word_srctl(hw, offset, data); + i40e_release_nvm(hw); } return ret_code; } From d60be2ca9c42e127702a8fd556d696b101f3c09b Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 24 Jan 2017 10:23:58 -0800 Subject: [PATCH 261/399] i40e: fix up recent proxy and wol bits for X722_SUPPORT Some opcodes added & reordered to be in numerical order with the rest of the opcodes. This patch adds admin queue structs to support Wake on LAN feature for X722. Signed-off-by: Shannon Nelson Signed-off-by: Carolyn Wyborny Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/i40e/i40e_adminq_cmd.h | 65 ++++++++++++++++++- .../ethernet/intel/i40evf/i40e_adminq_cmd.h | 65 ++++++++++++++++++- 2 files changed, 128 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 451f48b7540a..251074c677c4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -132,6 +132,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + /* LAA */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -139,6 +143,10 @@ enum i40e_admin_queue_opc { /* PXE */ i40e_aqc_opc_clear_pxe_mode = 0x0110, + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + /* internal switch commands */ i40e_aqc_opc_get_switch_config = 0x0200, i40e_aqc_opc_add_statistics = 0x0201, @@ -177,6 +185,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_remove_control_packet_filter = 0x025B, i40e_aqc_opc_add_cloud_filters = 0x025C, i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, @@ -563,6 +572,56 @@ struct i40e_aqc_clear_pxe { I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); +/* Set WoL Filter (0x0120) */ + +struct i40e_aqc_set_wol_filter { + __le16 filter_index; +#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ + I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) + +#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 +#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ + I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) + __le16 cmd_flags; +#define I40E_AQC_SET_WOL_FILTER 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 +#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 +#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 + __le16 valid_flags; +#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 + u8 reserved[2]; + __le32 address_high; + __le32 address_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); + +struct i40e_aqc_set_wol_filter_data { + u8 filter[128]; + u8 mask[16]; +}; + +I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); + +/* Get Wake Reason (0x0121) */ + +struct i40e_aqc_get_wake_reason_completion { + u8 reserved_1[2]; + __le16 wake_reason; +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) + u8 reserved_2[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); + /* Switch configuration commands (0x02xx) */ /* Used by many indirect commands that only pass an seid and a buffer in the @@ -645,6 +704,8 @@ struct i40e_aqc_set_port_parameters { #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 __le16 bad_frame_vsi; +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF __le16 default_seid; /* reserved for command */ u8 reserved[10]; }; @@ -696,6 +757,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); /* Set Switch Configuration (direct 0x0205) */ struct i40e_aqc_set_switch_config { __le16 flags; +/* flags used for both fields below */ #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; @@ -1844,11 +1906,12 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 external_power_ability; + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 +#define I40E_AQ_PWR_CLASS_MASK 0x03 u8 reserved[4]; }; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index eeb9864bc5b1..c28cb8f27243 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -132,6 +132,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + /* LAA */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -139,6 +143,10 @@ enum i40e_admin_queue_opc { /* PXE */ i40e_aqc_opc_clear_pxe_mode = 0x0110, + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + /* internal switch commands */ i40e_aqc_opc_get_switch_config = 0x0200, i40e_aqc_opc_add_statistics = 0x0201, @@ -177,6 +185,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_remove_control_packet_filter = 0x025B, i40e_aqc_opc_add_cloud_filters = 0x025C, i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, @@ -558,6 +567,56 @@ struct i40e_aqc_clear_pxe { I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); +/* Set WoL Filter (0x0120) */ + +struct i40e_aqc_set_wol_filter { + __le16 filter_index; +#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ + I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) + +#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 +#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ + I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) + __le16 cmd_flags; +#define I40E_AQC_SET_WOL_FILTER 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 +#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 +#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 + __le16 valid_flags; +#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 + u8 reserved[2]; + __le32 address_high; + __le32 address_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); + +struct i40e_aqc_set_wol_filter_data { + u8 filter[128]; + u8 mask[16]; +}; + +I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); + +/* Get Wake Reason (0x0121) */ + +struct i40e_aqc_get_wake_reason_completion { + u8 reserved_1[2]; + __le16 wake_reason; +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) + u8 reserved_2[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); + /* Switch configuration commands (0x02xx) */ /* Used by many indirect commands that only pass an seid and a buffer in the @@ -640,6 +699,8 @@ struct i40e_aqc_set_port_parameters { #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 __le16 bad_frame_vsi; +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF __le16 default_seid; /* reserved for command */ u8 reserved[10]; }; @@ -691,6 +752,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); /* Set Switch Configuration (direct 0x0205) */ struct i40e_aqc_set_switch_config { __le16 flags; +/* flags used for both fields below */ #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; @@ -1839,11 +1901,12 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 external_power_ability; + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 +#define I40E_AQ_PWR_CLASS_MASK 0x03 u8 reserved[4]; }; From ed0e894de7c1339be55ca0dcc11783d923ac5248 Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Tue, 24 Jan 2017 10:23:59 -0800 Subject: [PATCH 262/399] i40evf: add client interface In preparation for upcoming RDMA-capable hardware, add a client interface to the VF driver. This is a slightly-simplified version of the PF client interface, with the names changed to protect the innocent. Due to the nature of the VF<->PF interactions, the client interface sometimes needs to call back into itself to pass messages. Because of this, we can't use the coarse-grained locking like the PF's client interface uses. Instead, we handle all client interactions in a separate thread so the watchdog can still run and process virtual channel messages. Signed-off-by: Mitch Williams Signed-off-by: Jesse Brandeburg Signed-off-by: Anjali Singhai Jain Signed-off-by: Avinash Dayanand Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40evf/Makefile | 2 +- .../net/ethernet/intel/i40evf/i40e_virtchnl.h | 33 + drivers/net/ethernet/intel/i40evf/i40evf.h | 29 +- .../net/ethernet/intel/i40evf/i40evf_client.c | 563 ++++++++++++++++++ .../net/ethernet/intel/i40evf/i40evf_client.h | 166 ++++++ .../net/ethernet/intel/i40evf/i40evf_main.c | 83 ++- .../ethernet/intel/i40evf/i40evf_virtchnl.c | 13 +- 7 files changed, 879 insertions(+), 10 deletions(-) create mode 100644 drivers/net/ethernet/intel/i40evf/i40evf_client.c create mode 100644 drivers/net/ethernet/intel/i40evf/i40evf_client.h diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile index 3a423836a565..827c7a6ed0ba 100644 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ b/drivers/net/ethernet/intel/i40evf/Makefile @@ -32,5 +32,5 @@ obj-$(CONFIG_I40EVF) += i40evf.o i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \ - i40e_txrx.o i40e_common.o i40e_adminq.o + i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h index d38a2b2aea2b..f431fbc4a3e7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h @@ -81,7 +81,9 @@ enum i40e_virtchnl_ops { I40E_VIRTCHNL_OP_GET_STATS = 15, I40E_VIRTCHNL_OP_FCOE = 16, I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + I40E_VIRTCHNL_OP_IWARP = 20, I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21, + I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22, I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23, I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24, I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, @@ -393,6 +395,37 @@ struct i40e_virtchnl_pf_event { int severity; }; +/* I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP + * VF uses this message to request PF to map IWARP vectors to IWARP queues. + * The request for this originates from the VF IWARP driver through + * a client interface between VF LAN and VF IWARP driver. + * A vector could have an AEQ and CEQ attached to it although + * there is a single AEQ per VF IWARP instance in which case + * most vectors will have an INVALID_IDX for aeq and valid idx for ceq. + * There will never be a case where there will be multiple CEQs attached + * to a single vector. + * PF configures interrupt mapping and returns status. + */ + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_virtchnl_iwarp_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_virtchnl_iwarp_qvlist_info { + u32 num_vectors; + struct i40e_virtchnl_iwarp_qv_info qv_info[1]; +}; + /* VF reset states - these are written into the RSTAT register: * I40E_VFGEN_RSTAT1 on the PF * I40E_VFGEN_RSTAT on the VF diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 00c42d803276..b2b48511f457 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -60,6 +60,7 @@ struct i40e_vsi { int base_vector; u16 work_limit; u16 qs_handle; + void *priv; /* client driver data reference. */ }; /* How many Rx Buffers do we bundle into one write to the hardware ? */ @@ -169,6 +170,7 @@ enum i40evf_state_t { enum i40evf_critical_section_t { __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */ + __I40EVF_IN_CLIENT_TASK, }; /* make common code happy */ #define __I40E_DOWN __I40EVF_DOWN @@ -178,6 +180,7 @@ struct i40evf_adapter { struct timer_list watchdog_timer; struct work_struct reset_task; struct work_struct adminq_task; + struct delayed_work client_task; struct delayed_work init_task; struct i40e_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -195,7 +198,10 @@ struct i40evf_adapter { u64 hw_csum_rx_error; u32 rx_desc_count; int num_msix_vectors; + int num_iwarp_msix; + int iwarp_base_vector; u32 client_pending; + struct i40e_client_instance *cinst; struct msix_entry *msix_entries; u32 flags; @@ -211,8 +217,11 @@ struct i40evf_adapter { #define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12) #define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13) #define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14) -#define I40EVF_FLAG_PROMISC_ON BIT(15) -#define I40EVF_FLAG_ALLMULTI_ON BIT(16) +#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15) +#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16) +#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17) +#define I40EVF_FLAG_PROMISC_ON BIT(18) +#define I40EVF_FLAG_ALLMULTI_ON BIT(19) /* duplicates for common code */ #define I40E_FLAG_FDIR_ATR_ENABLED 0 #define I40E_FLAG_DCB_ENABLED 0 @@ -258,10 +267,11 @@ struct i40evf_adapter { bool link_up; enum i40e_aq_link_speed link_speed; enum i40e_virtchnl_ops current_op; -#define CLIENT_ENABLED(_a) ((_a)->vf_res ? \ +#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ (_a)->vf_res->vf_offload_flags & \ I40E_VIRTCHNL_VF_OFFLOAD_IWARP : \ 0) +#define CLIENT_ENABLED(_a) ((_a)->cinst) /* RSS by the PF should be preferred over RSS via other methods. */ #define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \ I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -292,6 +302,12 @@ struct i40evf_adapter { /* Ethtool Private Flags */ +/* lan device */ +struct i40e_device { + struct list_head list; + struct i40evf_adapter *vf; +}; + /* needed by i40evf_ethtool.c */ extern char i40evf_driver_name[]; extern const char i40evf_driver_version[]; @@ -337,4 +353,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, enum i40e_virtchnl_ops v_opcode, i40e_status v_retval, u8 *msg, u16 msglen); int i40evf_config_rss(struct i40evf_adapter *adapter); +int i40evf_lan_add_device(struct i40evf_adapter *adapter); +int i40evf_lan_del_device(struct i40evf_adapter *adapter); +void i40evf_client_subtask(struct i40evf_adapter *adapter); +void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); +void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); +void i40evf_notify_client_open(struct i40e_vsi *vsi); +void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); #endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c new file mode 100644 index 000000000000..5b43e5b6e2eb --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.c @@ -0,0 +1,563 @@ +#include +#include + +#include "i40evf.h" +#include "i40e_prototype.h" +#include "i40evf_client.h" + +static +const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR; +static struct i40e_client *vf_registered_client; +static LIST_HEAD(i40evf_devices); +static DEFINE_MUTEX(i40evf_device_mutex); + +static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); + +static int i40evf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info); + +static struct i40e_ops i40evf_lan_ops = { + .virtchnl_send = i40evf_client_virtchnl_send, + .setup_qvlist = i40evf_client_setup_qvlist, +}; + +/** + * i40evf_notify_client_message - call the client message receive callback + * @vsi: the VSI associated with this client + * @msg: message buffer + * @len: length of message + * + * If there is a client to this VSI, call the client + **/ +void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + + if (!vsi) + return; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->virtchnl_receive) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance virtchnl_receive function\n"); + return; + } + cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client, + msg, len); +} + +/** + * i40evf_notify_client_l2_params - call the client notify callback + * @vsi: the VSI with l2 param changes + * + * If there is a client to this VSI, call the client + **/ +void i40evf_notify_client_l2_params(struct i40e_vsi *vsi) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + struct i40e_params params; + + if (!vsi) + return; + memset(¶ms, 0, sizeof(params)); + params.mtu = vsi->netdev->mtu; + params.link_up = vsi->back->link_up; + params.qos.prio_qos[0].qs_handle = vsi->qs_handle; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->l2_param_change) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance l2_param_change function\n"); + return; + } + cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client, + ¶ms); +} + +/** + * i40evf_notify_client_open - call the client open callback + * @vsi: the VSI with netdev opened + * + * If there is a client to this netdev, call the client with open + **/ +void i40evf_notify_client_open(struct i40e_vsi *vsi) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + int ret; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->open) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance open function\n"); + return; + } + if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) { + ret = cinst->client->ops->open(&cinst->lan_info, cinst->client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + } +} + +/** + * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map + * @ldev: pointer to L2 context. + * + * Return 0 on success or < 0 on error + **/ +static int i40evf_client_release_qvlist(struct i40e_info *ldev) +{ + struct i40evf_adapter *adapter = ldev->vf; + i40e_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = i40e_aq_send_msg_to_pf(&adapter->hw, + I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, + I40E_SUCCESS, NULL, 0, NULL); + + if (err) + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector release message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * i40evf_notify_client_close - call the client close callback + * @vsi: the VSI with netdev closed + * @reset: true when close called due to reset pending + * + * If there is a client to this netdev, call the client with close + **/ +void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->close) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance close function\n"); + return; + } + cinst->client->ops->close(&cinst->lan_info, cinst->client, reset); + i40evf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); +} + +/** + * i40evf_client_add_instance - add a client instance to the instance list + * @adapter: pointer to the board struct + * @client: pointer to a client struct in the client list. + * + * Returns cinst ptr on success, NULL on failure + **/ +static struct i40e_client_instance * +i40evf_client_add_instance(struct i40evf_adapter *adapter) +{ + struct i40e_client_instance *cinst = NULL; + struct netdev_hw_addr *mac = NULL; + struct i40e_vsi *vsi = &adapter->vsi; + int i; + + if (!vf_registered_client) + goto out; + + if (adapter->cinst) { + cinst = adapter->cinst; + goto out; + } + + cinst = kzalloc(sizeof(*cinst), GFP_KERNEL); + if (!cinst) + goto out; + + cinst->lan_info.vf = (void *)adapter; + cinst->lan_info.netdev = vsi->netdev; + cinst->lan_info.pcidev = adapter->pdev; + cinst->lan_info.fid = 0; + cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF; + cinst->lan_info.hw_addr = adapter->hw.hw_addr; + cinst->lan_info.ops = &i40evf_lan_ops; + cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR; + cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR; + cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD; + set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state); + + cinst->lan_info.msix_count = adapter->num_iwarp_msix; + cinst->lan_info.msix_entries = + &adapter->msix_entries[adapter->iwarp_base_vector]; + + for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { + cinst->lan_info.params.qos.prio_qos[i].tc = 0; + cinst->lan_info.params.qos.prio_qos[i].qs_handle = + vsi->qs_handle; + } + + mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list, + struct netdev_hw_addr, list); + if (mac) + ether_addr_copy(cinst->lan_info.lanmac, mac->addr); + else + dev_err(&adapter->pdev->dev, "MAC address list is empty!\n"); + + cinst->client = vf_registered_client; + adapter->cinst = cinst; +out: + return cinst; +} + +/** + * i40evf_client_del_instance - removes a client instance from the list + * @adapter: pointer to the board struct + * @client: pointer to the client struct + * + **/ +static +void i40evf_client_del_instance(struct i40evf_adapter *adapter) +{ + kfree(adapter->cinst); + adapter->cinst = NULL; +} + +/** + * i40evf_client_subtask - client maintenance work + * @adapter: board private structure + **/ +void i40evf_client_subtask(struct i40evf_adapter *adapter) +{ + struct i40e_client *client = vf_registered_client; + struct i40e_client_instance *cinst; + int ret = 0; + + if (adapter->state < __I40EVF_DOWN) + return; + + /* first check client is registered */ + if (!client) + return; + + /* Add the client instance to the instance list */ + cinst = i40evf_client_add_instance(adapter); + if (!cinst) + return; + + dev_info(&adapter->pdev->dev, "Added instance of Client %s\n", + client->name); + + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + /* Send an Open request to the client */ + + if (client->ops && client->ops->open) + ret = client->ops->open(&cinst->lan_info, client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cinst->state); + else + /* remove client instance */ + i40evf_client_del_instance(adapter); + } +} + +/** + * i40evf_lan_add_device - add a lan device struct to the list of lan devices + * @adapter: pointer to the board struct + * + * Returns 0 on success or none 0 on error + **/ +int i40evf_lan_add_device(struct i40evf_adapter *adapter) +{ + struct i40e_device *ldev; + int ret = 0; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + if (ldev->vf == adapter) { + ret = -EEXIST; + goto out; + } + } + ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); + if (!ldev) { + ret = -ENOMEM; + goto out; + } + ldev->vf = adapter; + INIT_LIST_HEAD(&ldev->list); + list_add(&ldev->list, &i40evf_devices); + dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + + /* Since in some cases register may have happened before a device gets + * added, we can schedule a subtask to go initiate the clients. + */ + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + +out: + mutex_unlock(&i40evf_device_mutex); + return ret; +} + +/** + * i40evf_lan_del_device - removes a lan device from the device list + * @adapter: pointer to the board struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_lan_del_device(struct i40evf_adapter *adapter) +{ + struct i40e_device *ldev, *tmp; + int ret = -ENODEV; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) { + if (ldev->vf == adapter) { + dev_info(&adapter->pdev->dev, + "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + list_del(&ldev->list); + kfree(ldev); + ret = 0; + break; + } + } + + mutex_unlock(&i40evf_device_mutex); + return ret; +} + +/** + * i40evf_client_release - release client specific resources + * @client: pointer to the registered client + * + **/ +static void i40evf_client_release(struct i40e_client *client) +{ + struct i40e_client_instance *cinst; + struct i40e_device *ldev; + struct i40evf_adapter *adapter; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + adapter = ldev->vf; + cinst = adapter->cinst; + if (!cinst) + continue; + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + if (client->ops && client->ops->close) + client->ops->close(&cinst->lan_info, client, + false); + i40evf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + + dev_warn(&adapter->pdev->dev, + "Client %s instance closed\n", client->name); + } + /* delete the client instance */ + i40evf_client_del_instance(adapter); + dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n", + client->name); + } + mutex_unlock(&i40evf_device_mutex); +} + +/** + * i40evf_client_prepare - prepare client specific resources + * @client: pointer to the registered client + * + **/ +static void i40evf_client_prepare(struct i40e_client *client) +{ + struct i40e_device *ldev; + struct i40evf_adapter *adapter; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + adapter = ldev->vf; + /* Signal the watchdog to service the client */ + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + } + mutex_unlock(&i40evf_device_mutex); +} + +/** + * i40evf_client_virtchnl_send - send a message to the PF instance + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @msg: pointer to message buffer + * @len: message length + * + * Return 0 on success or < 0 on error + **/ +static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len) +{ + struct i40evf_adapter *adapter = ldev->vf; + i40e_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = i40e_aq_send_msg_to_pf(&adapter->hw, I40E_VIRTCHNL_OP_IWARP, + I40E_SUCCESS, msg, len, NULL); + if (err) + dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @qv_info: queue and vector list + * + * Return 0 on success or < 0 on error + **/ +static int i40evf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info) +{ + struct i40e_virtchnl_iwarp_qvlist_info *v_qvlist_info; + struct i40evf_adapter *adapter = ldev->vf; + struct i40e_qv_info *qv_info; + i40e_status err; + u32 v_idx, i; + u32 msg_size; + + if (adapter->aq_required) + return -EAGAIN; + + /* A quick check on whether the vectors belong to the client */ + for (i = 0; i < qvlist_info->num_vectors; i++) { + qv_info = &qvlist_info->qv_info[i]; + if (!qv_info) + continue; + v_idx = qv_info->v_idx; + if ((v_idx >= + (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) || + (v_idx < adapter->iwarp_base_vector)) + return -EINVAL; + } + + v_qvlist_info = (struct i40e_virtchnl_iwarp_qvlist_info *)qvlist_info; + msg_size = sizeof(struct i40e_virtchnl_iwarp_qvlist_info) + + (sizeof(struct i40e_virtchnl_iwarp_qv_info) * + (v_qvlist_info->num_vectors - 1)); + + adapter->client_pending |= BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP); + err = i40e_aq_send_msg_to_pf(&adapter->hw, + I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, + I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL); + + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector config message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + goto out; + } + + err = -EBUSY; + for (i = 0; i < 5; i++) { + msleep(100); + if (!(adapter->client_pending & + BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) { + err = 0; + break; + } + } +out: + return err; +} + +/** + * i40evf_register_client - Register a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_register_client(struct i40e_client *client) +{ + int ret = 0; + + if (!client) { + ret = -EIO; + goto out; + } + + if (strlen(client->name) == 0) { + pr_info("i40evf: Failed to register client with no name\n"); + ret = -EIO; + goto out; + } + + if (vf_registered_client) { + pr_info("i40evf: Client %s has already been registered!\n", + client->name); + ret = -EEXIST; + goto out; + } + + if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) || + (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) { + pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n", + client->name); + pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n", + client->version.major, client->version.minor, + client->version.build, + i40evf_client_interface_version_str); + ret = -EIO; + goto out; + } + + vf_registered_client = client; + + i40evf_client_prepare(client); + + pr_info("i40evf: Registered client %s with return code %d\n", + client->name, ret); +out: + return ret; +} +EXPORT_SYMBOL(i40evf_register_client); + +/** + * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_unregister_client(struct i40e_client *client) +{ + int ret = 0; + + /* When a unregister request comes through we would have to send + * a close for each of the client instances that were opened. + * client_release function is called to handle this. + */ + i40evf_client_release(client); + + if (vf_registered_client != client) { + pr_info("i40evf: Client %s has not been registered\n", + client->name); + ret = -ENODEV; + goto out; + } + vf_registered_client = NULL; + pr_info("i40evf: Unregistered client %s\n", client->name); +out: + return ret; +} +EXPORT_SYMBOL(i40evf_unregister_client); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h new file mode 100644 index 000000000000..7d283c7506a5 --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.h @@ -0,0 +1,166 @@ +#ifndef _I40E_CLIENT_H_ +#define _I40E_CLIENT_H_ + +#define I40EVF_CLIENT_STR_LENGTH 10 + +/* Client interface version should be updated anytime there is a change in the + * existing APIs or data structures. + */ +#define I40EVF_CLIENT_VERSION_MAJOR 0 +#define I40EVF_CLIENT_VERSION_MINOR 01 +#define I40EVF_CLIENT_VERSION_BUILD 00 +#define I40EVF_CLIENT_VERSION_STR \ + __stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \ + __stringify(I40EVF_CLIENT_VERSION_MINOR) "." \ + __stringify(I40EVF_CLIENT_VERSION_BUILD) + +struct i40e_client_version { + u8 major; + u8 minor; + u8 build; + u8 rsvd; +}; + +enum i40e_client_state { + __I40E_CLIENT_NULL, + __I40E_CLIENT_REGISTERED +}; + +enum i40e_client_instance_state { + __I40E_CLIENT_INSTANCE_NONE, + __I40E_CLIENT_INSTANCE_OPENED, +}; + +struct i40e_ops; +struct i40e_client; + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_qvlist_info { + u32 num_vectors; + struct i40e_qv_info qv_info[1]; +}; + +#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF + +/* set of LAN parameters useful for clients managed by LAN */ + +/* Struct to hold per priority info */ +struct i40e_prio_qos_params { + u16 qs_handle; /* qs handle for prio */ + u8 tc; /* TC mapped to prio */ + u8 reserved; +}; + +#define I40E_CLIENT_MAX_USER_PRIORITY 8 +/* Struct to hold Client QoS */ +struct i40e_qos_params { + struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY]; +}; + +struct i40e_params { + struct i40e_qos_params qos; + u16 mtu; + u16 link_up; /* boolean */ +}; + +/* Structure to hold LAN device info for a client device */ +struct i40e_info { + struct i40e_client_version version; + u8 lanmac[6]; + struct net_device *netdev; + struct pci_dev *pcidev; + u8 __iomem *hw_addr; + u8 fid; /* function id, PF id or VF id */ +#define I40E_CLIENT_FTYPE_PF 0 +#define I40E_CLIENT_FTYPE_VF 1 + u8 ftype; /* function type, PF or VF */ + void *vf; /* cast to i40evf_adapter */ + + /* All L2 params that could change during the life span of the device + * and needs to be communicated to the client when they change + */ + struct i40e_params params; + struct i40e_ops *ops; + + u16 msix_count; /* number of msix vectors*/ + /* Array down below will be dynamically allocated based on msix_count */ + struct msix_entry *msix_entries; + u16 itr_index; /* Which ITR index the PE driver is suppose to use */ +}; + +struct i40e_ops { + /* setup_q_vector_list enables queues with a particular vector */ + int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client, + struct i40e_qvlist_info *qv_info); + + u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client, + u8 *msg, u16 len); + + /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/ + void (*request_reset)(struct i40e_info *ldev, + struct i40e_client *client); +}; + +struct i40e_client_ops { + /* Should be called from register_client() or whenever the driver is + * ready to create a specific client instance. + */ + int (*open)(struct i40e_info *ldev, struct i40e_client *client); + + /* Should be closed when netdev is unavailable or when unregister + * call comes in. If the close happens due to a reset, set the reset + * bit to true. + */ + void (*close)(struct i40e_info *ldev, struct i40e_client *client, + bool reset); + + /* called when some l2 managed parameters changes - mss */ + void (*l2_param_change)(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_params *params); + + /* called when a message is received from the PF */ + int (*virtchnl_receive)(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); +}; + +/* Client device */ +struct i40e_client_instance { + struct list_head list; + struct i40e_info lan_info; + struct i40e_client *client; + unsigned long state; +}; + +struct i40e_client { + struct list_head list; /* list of registered clients */ + char name[I40EVF_CLIENT_STR_LENGTH]; + struct i40e_client_version version; + unsigned long state; /* client state */ + atomic_t ref_cnt; /* Count of all the client devices of this kind */ + u32 flags; +#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) +#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) + u8 type; +#define I40E_CLIENT_IWARP 0 + struct i40e_client_ops *ops; /* client ops provided by the client */ +}; + +/* used by clients */ +int i40evf_register_client(struct i40e_client *client); +int i40evf_unregister_client(struct i40e_client *client); +#endif /* _I40E_CLIENT_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f35dcaac5bb7..9492b20da557 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -26,6 +26,7 @@ #include "i40evf.h" #include "i40e_prototype.h" +#include "i40evf_client.h" static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter); static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter); static int i40evf_close(struct net_device *netdev); @@ -1058,6 +1059,8 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter) i40evf_napi_enable_all(adapter); adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES; + if (CLIENT_ENABLED(adapter)) + adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN; mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } @@ -1685,6 +1688,7 @@ static void i40evf_watchdog_task(struct work_struct *work) i40evf_set_promiscuous(adapter, 0); goto watchdog_done; } + schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); if (adapter->state == __I40EVF_RUNNING) i40evf_request_stats(adapter); @@ -1773,10 +1777,17 @@ static void i40evf_reset_task(struct work_struct *work) u32 reg_val; int i = 0, err; - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) usleep_range(500, 1000); - + if (CLIENT_ENABLED(adapter)) { + adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN | + I40EVF_FLAG_CLIENT_NEEDS_CLOSE | + I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS | + I40EVF_FLAG_SERVICE_CLIENT_REQUESTED); + cancel_delayed_work_sync(&adapter->client_task); + i40evf_notify_client_close(&adapter->vsi, true); + } i40evf_misc_irq_disable(adapter); if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) { adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED; @@ -1819,6 +1830,7 @@ static void i40evf_reset_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); i40evf_disable_vf(adapter); + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -1861,9 +1873,8 @@ static void i40evf_reset_task(struct work_struct *work) } adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; - /* Open RDMA Client again */ - adapter->aq_required |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); i40evf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -1979,6 +1990,48 @@ static void i40evf_adminq_task(struct work_struct *work) i40evf_misc_irq_enable(adapter); } +/** + * i40evf_client_task - worker thread to perform client work + * @work: pointer to work_struct containing our data + * + * This task handles client interactions. Because client calls can be + * reentrant, we can't handle them in the watchdog. + **/ +static void i40evf_client_task(struct work_struct *work) +{ + struct i40evf_adapter *adapter = + container_of(work, struct i40evf_adapter, client_task.work); + + /* If we can't get the client bit, just give up. We'll be rescheduled + * later. + */ + + if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) + return; + + if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) { + i40evf_client_subtask(adapter); + adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) { + i40evf_notify_client_close(&adapter->vsi, false); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) { + i40evf_notify_client_open(&adapter->vsi); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { + i40evf_notify_client_l2_params(&adapter->vsi); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS; + } +out: + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); +} + /** * i40evf_free_all_tx_resources - Free Tx Resources for All Queues * @adapter: board private structure @@ -2148,6 +2201,8 @@ static int i40evf_close(struct net_device *netdev) set_bit(__I40E_DOWN, &adapter->vsi.state); + if (CLIENT_ENABLED(adapter)) + adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE; i40evf_down(adapter); adapter->state = __I40EVF_DOWN_PENDING; @@ -2188,6 +2243,10 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) struct i40evf_adapter *adapter = netdev_priv(netdev); netdev->mtu = new_mtu; + if (CLIENT_ENABLED(adapter)) { + i40evf_notify_client_l2_params(&adapter->vsi); + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + } adapter->flags |= I40EVF_FLAG_RESET_NEEDED; schedule_work(&adapter->reset_task); @@ -2581,6 +2640,12 @@ static void i40evf_init_task(struct work_struct *work) adapter->netdev_registered = true; netif_tx_stop_all_queues(netdev); + if (CLIENT_ALLOWED(adapter)) { + err = i40evf_lan_add_device(adapter); + if (err) + dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", + err); + } dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr); if (netdev->features & NETIF_F_GRO) @@ -2745,6 +2810,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->reset_task, i40evf_reset_task); INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task); + INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task); INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task); schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); @@ -2857,14 +2923,21 @@ static void i40evf_remove(struct pci_dev *pdev) struct i40evf_adapter *adapter = netdev_priv(netdev); struct i40evf_mac_filter *f, *ftmp; struct i40e_hw *hw = &adapter->hw; + int err; cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); - + cancel_delayed_work_sync(&adapter->client_task); if (adapter->netdev_registered) { unregister_netdev(netdev); adapter->netdev_registered = false; } + if (CLIENT_ALLOWED(adapter)) { + err = i40evf_lan_del_device(adapter); + if (err) + dev_warn(&pdev->dev, "Failed to delete client device: %d\n", + err); + } /* Shut down all the garbage mashers on the detention level */ adapter->state = __I40EVF_REMOVE; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index bee58af390e1..a2a7354426a3 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -26,6 +26,7 @@ #include "i40evf.h" #include "i40e_prototype.h" +#include "i40evf_client.h" /* busy wait delay in msec */ #define I40EVF_BUSY_WAIT_DELAY 10 @@ -999,6 +1000,16 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (v_opcode != adapter->current_op) return; break; + case I40E_VIRTCHNL_OP_IWARP: + /* Gobble zero-length replies from the PF. They indicate that + * a previous message was received OK, and the client doesn't + * care about that. + */ + if (msglen && CLIENT_ENABLED(adapter)) + i40evf_notify_client_message(&adapter->vsi, + msg, msglen); + break; + case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: adapter->client_pending &= ~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP)); @@ -1014,7 +1025,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } break; default: - if (v_opcode != adapter->current_op) + if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", adapter->current_op, v_opcode); break; From 0ef2d5afb12d379f4dd5df696219a01b88bb778a Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Tue, 24 Jan 2017 10:24:00 -0800 Subject: [PATCH 263/399] i40e: KISS the client interface (KISS is Keep It Simple, Stupid. Or is it?) The client interface vastly overengineered for what it needs to do. It was originally designed to support multiple clients on multiple netdevs, possibly even with multiple drivers. None of this happened, and now we know that there will only ever be one client for i40e (i40iw) and one for i40evf (i40iwvf). So, time for some KISS. Since i40e and i40evf are a Dynasty, we'll simplify this one to match the VF interface. First, be a Destroyer and remove all of the lists and locks required to support multiple clients. Keep one static around to keep track of one client, and track the client instances for each netdev in the driver's pf (or adapter) struct. Now it's Almost Human. Since we already know the client type is iWarp, get rid of any checks for this. Same for VSI type - it's always going to be the same type, so it's just a Parasite. While we're at it, fix up some comments. This makes the function headers actually match the functions. These changes reduce code complexity, simplify maintenance, squash some lurking timing bugs, and allow us to Rock and Roll All Nite. Change-ID: I1ea79948ad73b8685272451440a34507f9a9012e Signed-off-by: Mitch Williams Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 8 +- drivers/net/ethernet/intel/i40e/i40e_client.c | 457 ++++++------------ drivers/net/ethernet/intel/i40e/i40e_client.h | 8 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 32 +- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +- 5 files changed, 179 insertions(+), 328 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 82d8040fa418..9b2bb8d971cc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -348,8 +348,10 @@ struct i40e_pf { #define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) #define I40E_FLAG_HAVE_CRT_RETIMER BIT_ULL(52) #define I40E_FLAG_PTP_L4_CAPABLE BIT_ULL(53) -#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(54) +#define I40E_FLAG_CLIENT_RESET BIT_ULL(54) #define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) +#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) +#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(57) /* tracks features that get auto disabled by errors */ u64 auto_disable_flags; @@ -358,6 +360,7 @@ struct i40e_pf { struct i40e_fcoe fcoe; #endif /* I40E_FCOE */ + struct i40e_client_instance *cinst; bool stat_offsets_loaded; struct i40e_hw_port_stats stats; struct i40e_hw_port_stats stats_offsets; @@ -813,8 +816,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi); void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset); void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs); void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id); -int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, - enum i40e_client_type type); +int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id); /** * i40e_irq_dynamic_enable - Enable default interrupt generation settings * @vsi: pointer to a vsi diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index d570219efd9f..a9f0d22a7cf4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -32,16 +32,10 @@ #include "i40e_client.h" static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR; - +static struct i40e_client *registered_client; static LIST_HEAD(i40e_devices); static DEFINE_MUTEX(i40e_device_mutex); -static LIST_HEAD(i40e_clients); -static DEFINE_MUTEX(i40e_client_mutex); - -static LIST_HEAD(i40e_client_instances); -static DEFINE_MUTEX(i40e_client_instance_mutex); - static int i40e_client_virtchnl_send(struct i40e_info *ldev, struct i40e_client *client, u32 vf_id, u8 *msg, u16 len); @@ -66,28 +60,6 @@ static struct i40e_ops i40e_lan_ops = { .update_vsi_ctxt = i40e_client_update_vsi_ctxt, }; -/** - * i40e_client_type_to_vsi_type - convert client type to vsi type - * @client_type: the i40e_client type - * - * returns the related vsi type value - **/ -static -enum i40e_vsi_type i40e_client_type_to_vsi_type(enum i40e_client_type type) -{ - switch (type) { - case I40E_CLIENT_IWARP: - return I40E_VSI_IWARP; - - case I40E_CLIENT_VMDQ2: - return I40E_VSI_VMDQ2; - - default: - pr_err("i40e: Client type unknown\n"); - return I40E_VSI_TYPE_UNKNOWN; - } -} - /** * i40e_client_get_params - Get the params that can change at runtime * @vsi: the VSI with the message @@ -134,31 +106,22 @@ int i40e_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params) void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->virtchnl_receive) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance virtual channel receive routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == vsi->back) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->virtchnl_receive) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance virtual channel receive routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort virtchnl_receive\n"); - continue; - } - cdev->client->ops->virtchnl_receive(&cdev->lan_info, - cdev->client, - vf_id, msg, len); - } } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort virtchnl_receive\n"); + return; + } + cdev->client->ops->virtchnl_receive(&cdev->lan_info, cdev->client, + vf_id, msg, len); } /** @@ -169,39 +132,28 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len) **/ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; struct i40e_params params; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->l2_param_change) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance l2_param_change routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == vsi->back) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->l2_param_change) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance l2_param_change routine\n"); - continue; - } - memset(¶ms, 0, sizeof(params)); - i40e_client_get_params(vsi, ¶ms); - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); - continue; - } - cdev->lan_info.params = params; - cdev->client->ops->l2_param_change(&cdev->lan_info, - cdev->client, - ¶ms); - } } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); + return; + } + memcpy(&cdev->lan_info.params, ¶ms, sizeof(struct i40e_params)); + cdev->client->ops->l2_param_change(&cdev->lan_info, cdev->client, + ¶ms); } /** - * i40e_client_release_qvlist + * i40e_client_release_qvlist - release MSI-X vector mapping for client * @ldev: pointer to L2 context. * **/ @@ -237,26 +189,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev) **/ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->close) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance close routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.netdev == vsi->netdev) { - if (!cdev->client || - !cdev->client->ops || !cdev->client->ops->close) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance close routine\n"); - continue; - } - cdev->client->ops->close(&cdev->lan_info, cdev->client, - reset); - clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); - i40e_client_release_qvlist(&cdev->lan_info); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->close(&cdev->lan_info, cdev->client, reset); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + i40e_client_release_qvlist(&cdev->lan_info); } /** @@ -268,30 +213,20 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) **/ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; - if (!pf) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->vf_reset) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance VF reset routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_reset) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF reset routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n"); - continue; - } - cdev->client->ops->vf_reset(&cdev->lan_info, - cdev->client, vf_id); - } } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n"); + return; + } + cdev->client->ops->vf_reset(&cdev->lan_info, cdev->client, vf_id); } /** @@ -303,30 +238,21 @@ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id) **/ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; - if (!pf) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->vf_enable) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance VF enable routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_enable) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF enable routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n"); - continue; - } - cdev->client->ops->vf_enable(&cdev->lan_info, - cdev->client, num_vfs); - } } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n"); + return; + } + cdev->client->ops->vf_enable(&cdev->lan_info, cdev->client, num_vfs); } /** @@ -337,37 +263,25 @@ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs) * If there is a client of the specified type attached to this PF, call * its vf_capable routine **/ -int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, - enum i40e_client_type type) +int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; int capable = false; - if (!pf) - return false; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_capable || - !(cdev->client->type == type)) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF capability routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-capable\n"); - continue; - } - capable = cdev->client->ops->vf_capable(&cdev->lan_info, - cdev->client, - vf_id); - break; - } + if (!cdev || !cdev->client) + goto out; + if (!cdev->client->ops || !cdev->client->ops->vf_capable) { + dev_info(&pf->pdev->dev, + "Cannot locate client instance VF capability routine\n"); + goto out; } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) + goto out; + + capable = cdev->client->ops->vf_capable(&cdev->lan_info, + cdev->client, + vf_id); +out: return capable; } @@ -377,27 +291,19 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, * @client: pointer to a client struct in the client list. * @existing: if there was already an existing instance * - * Returns cdev ptr on success or if already exists, NULL on failure **/ -static -struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, - struct i40e_client *client, - bool *existing) +static void i40e_client_add_instance(struct i40e_pf *pf) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = NULL; struct netdev_hw_addr *mac = NULL; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if ((cdev->lan_info.pf == pf) && (cdev->client == client)) { - *existing = true; - goto out; - } - } + if (!registered_client || pf->cinst) + return; + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) - goto out; + return; cdev->lan_info.pf = (void *)pf; cdev->lan_info.netdev = vsi->netdev; @@ -417,7 +323,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, if (i40e_client_get_params(vsi, &cdev->lan_info.params)) { kfree(cdev); cdev = NULL; - goto out; + return; } cdev->lan_info.msix_count = pf->num_iwarp_msix; @@ -430,41 +336,20 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, else dev_err(&pf->pdev->dev, "MAC address list is empty!\n"); - cdev->client = client; - INIT_LIST_HEAD(&cdev->list); - list_add(&cdev->list, &i40e_client_instances); -out: - mutex_unlock(&i40e_client_instance_mutex); - return cdev; + cdev->client = registered_client; + pf->cinst = cdev; } /** * i40e_client_del_instance - removes a client instance from the list * @pf: pointer to the board struct * - * Returns 0 on success or non-0 on error **/ static -int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client) +void i40e_client_del_instance(struct i40e_pf *pf) { - struct i40e_client_instance *cdev, *tmp; - int ret = -ENODEV; - - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) { - if ((cdev->lan_info.pf != pf) || (cdev->client != client)) - continue; - - dev_info(&pf->pdev->dev, "Deleted instance of Client %s, of dev %d bus=0x%02x func=0x%02x)\n", - client->name, pf->hw.pf_id, - pf->hw.bus.device, pf->hw.bus.func); - list_del(&cdev->list); - kfree(cdev); - ret = 0; - break; - } - mutex_unlock(&i40e_client_instance_mutex); - return ret; + kfree(pf->cinst); + pf->cinst = NULL; } /** @@ -473,67 +358,50 @@ int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client) **/ void i40e_client_subtask(struct i40e_pf *pf) { + struct i40e_client *client = registered_client; struct i40e_client_instance *cdev; - struct i40e_client *client; - bool existing = false; + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; int ret = 0; if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED)) return; pf->flags &= ~I40E_FLAG_SERVICE_CLIENT_REQUESTED; + cdev = pf->cinst; /* If we're down or resetting, just bail */ if (test_bit(__I40E_DOWN, &pf->state) || test_bit(__I40E_CONFIG_BUSY, &pf->state)) return; - /* Check client state and instantiate client if client registered */ - mutex_lock(&i40e_client_mutex); - list_for_each_entry(client, &i40e_clients, list) { - /* first check client is registered */ - if (!test_bit(__I40E_CLIENT_REGISTERED, &client->state)) - continue; + if (!client || !cdev) + return; - /* Do we also need the LAN VSI to be up, to create instance */ - if (!(client->flags & I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE)) { - /* check if L2 VSI is up, if not we are not ready */ - if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state)) - continue; - } else { - dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n", - client->name); - } - - /* Add the client instance to the instance list */ - cdev = i40e_client_add_instance(pf, client, &existing); - if (!cdev) - continue; - - if (!existing) { - dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x dev=0x%02x func=0x%02x\n", - client->name, pf->hw.pf_id, - pf->hw.bus.bus_id, pf->hw.bus.device, - pf->hw.bus.func); - } - - mutex_lock(&i40e_client_instance_mutex); - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - /* Send an Open request to the client */ - if (client->ops && client->ops->open) - ret = client->ops->open(&cdev->lan_info, - client); - if (!ret) { - set_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state); - } else { - /* remove client instance */ - i40e_client_del_instance(pf, client); + /* Here we handle client opens. If the client is down, but + * the netdev is up, then open the client. + */ + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + if (!test_bit(__I40E_DOWN, &vsi->state) && + client->ops && client->ops->open) { + set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + ret = client->ops->open(&cdev->lan_info, client); + if (ret) { + /* Remove failed client instance */ + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state); + i40e_client_del_instance(pf); } } - mutex_unlock(&i40e_client_instance_mutex); + } else { + /* Likewise for client close. If the client is up, but the netdev + * is down, then close the client. + */ + if (test_bit(__I40E_DOWN, &vsi->state) && + client->ops && client->ops->close) { + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + client->ops->close(&cdev->lan_info, client, false); + i40e_client_release_qvlist(&cdev->lan_info); + } } - mutex_unlock(&i40e_client_mutex); } /** @@ -601,7 +469,6 @@ int i40e_lan_del_device(struct i40e_pf *pf) break; } } - mutex_unlock(&i40e_device_mutex); return ret; } @@ -610,22 +477,24 @@ int i40e_lan_del_device(struct i40e_pf *pf) * i40e_client_release - release client specific resources * @client: pointer to the registered client * - * Return 0 on success or < 0 on error **/ -static int i40e_client_release(struct i40e_client *client) +static void i40e_client_release(struct i40e_client *client) { - struct i40e_client_instance *cdev, *tmp; + struct i40e_client_instance *cdev; + struct i40e_device *ldev; struct i40e_pf *pf; - int ret = 0; - LIST_HEAD(cdevs_tmp); - - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) { - if (strncmp(cdev->client->name, client->name, - I40E_CLIENT_STR_LENGTH)) + mutex_lock(&i40e_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { + pf = ldev->pf; + cdev = pf->cinst; + if (!cdev) continue; - pf = (struct i40e_pf *)cdev->lan_info.pf; + + while (test_and_set_bit(__I40E_SERVICE_SCHED, + &pf->state)) + usleep_range(500, 1000); + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { if (client->ops && client->ops->close) client->ops->close(&cdev->lan_info, client, @@ -637,18 +506,13 @@ static int i40e_client_release(struct i40e_client *client) "Client %s instance for PF id %d closed\n", client->name, pf->hw.pf_id); } - /* delete the client instance from the list */ - list_move(&cdev->list, &cdevs_tmp); + /* delete the client instance */ + i40e_client_del_instance(pf); dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n", client->name); + clear_bit(__I40E_SERVICE_SCHED, &pf->state); } - mutex_unlock(&i40e_client_instance_mutex); - - /* free the client device and release its vsi */ - list_for_each_entry_safe(cdev, tmp, &cdevs_tmp, list) { - kfree(cdev); - } - return ret; + mutex_unlock(&i40e_device_mutex); } /** @@ -664,6 +528,7 @@ static void i40e_client_prepare(struct i40e_client *client) mutex_lock(&i40e_device_mutex); list_for_each_entry(ldev, &i40e_devices, list) { pf = ldev->pf; + i40e_client_add_instance(pf); /* Start the client subtask */ pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; i40e_service_event_schedule(pf); @@ -792,8 +657,8 @@ static void i40e_client_request_reset(struct i40e_info *ldev, break; default: dev_warn(&pf->pdev->dev, - "Client %s instance for PF id %d request an unsupported reset: %d.\n", - client->name, pf->hw.pf_id, reset_level); + "Client for PF id %d requested an unsupported reset: %d.\n", + pf->hw.pf_id, reset_level); break; } @@ -852,8 +717,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, } else { update = false; dev_warn(&pf->pdev->dev, - "Client %s instance for PF id %d request an unsupported Config: %x.\n", - client->name, pf->hw.pf_id, flag); + "Client for PF id %d request an unsupported Config: %x.\n", + pf->hw.pf_id, flag); } if (update) { @@ -878,7 +743,6 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, int i40e_register_client(struct i40e_client *client) { int ret = 0; - enum i40e_vsi_type vsi_type; if (!client) { ret = -EIO; @@ -891,11 +755,9 @@ int i40e_register_client(struct i40e_client *client) goto out; } - mutex_lock(&i40e_client_mutex); - if (i40e_client_is_registered(client)) { + if (registered_client) { pr_info("i40e: Client %s has already been registered!\n", client->name); - mutex_unlock(&i40e_client_mutex); ret = -EEXIST; goto out; } @@ -908,22 +770,11 @@ int i40e_register_client(struct i40e_client *client) client->version.major, client->version.minor, client->version.build, i40e_client_interface_version_str); - mutex_unlock(&i40e_client_mutex); ret = -EIO; goto out; } - vsi_type = i40e_client_type_to_vsi_type(client->type); - if (vsi_type == I40E_VSI_TYPE_UNKNOWN) { - pr_info("i40e: Failed to register client %s due to unknown client type %d\n", - client->name, client->type); - mutex_unlock(&i40e_client_mutex); - ret = -EIO; - goto out; - } - list_add(&client->list, &i40e_clients); - set_bit(__I40E_CLIENT_REGISTERED, &client->state); - mutex_unlock(&i40e_client_mutex); + registered_client = client; i40e_client_prepare(client); @@ -943,29 +794,21 @@ int i40e_unregister_client(struct i40e_client *client) { int ret = 0; - /* When a unregister request comes through we would have to send - * a close for each of the client instances that were opened. - * client_release function is called to handle this. - */ - mutex_lock(&i40e_client_mutex); - if (!client || i40e_client_release(client)) { - ret = -EIO; - goto out; - } - - /* TODO: check if device is in reset, or if that matters? */ - if (!i40e_client_is_registered(client)) { + if (registered_client != client) { pr_info("i40e: Client %s has not been registered\n", client->name); ret = -ENODEV; goto out; } - clear_bit(__I40E_CLIENT_REGISTERED, &client->state); - list_del(&client->list); - pr_info("i40e: Unregistered client %s with return code %d\n", - client->name, ret); + registered_client = NULL; + /* When a unregister request comes through we would have to send + * a close for each of the client instances that were opened. + * client_release function is called to handle this. + */ + i40e_client_release(client); + + pr_info("i40e: Unregistered client %s\n", client->name); out: - mutex_unlock(&i40e_client_mutex); return ret; } EXPORT_SYMBOL(i40e_unregister_client); diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h index 528bd79b05fe..15b21a5315b5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.h +++ b/drivers/net/ethernet/intel/i40e/i40e_client.h @@ -57,11 +57,6 @@ enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_OPENED, }; -enum i40e_client_type { - I40E_CLIENT_IWARP, - I40E_CLIENT_VMDQ2 -}; - struct i40e_ops; struct i40e_client; @@ -214,7 +209,8 @@ struct i40e_client { u32 flags; #define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) #define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) - enum i40e_client_type type; + u8 type; +#define I40E_CLIENT_IWARP 0 const struct i40e_client_ops *ops; /* client ops provided by the client */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e8a8351c8ea9..3d7f179af6be 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2487,13 +2487,15 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; netdev_info(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); netdev->mtu = new_mtu; if (netif_running(netdev)) i40e_vsi_reinit_locked(vsi); - i40e_notify_client_of_l2_param_changes(vsi); + pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED | + I40E_FLAG_CLIENT_L2_CHANGE); return 0; } @@ -4463,17 +4465,16 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi) **/ static void i40e_vsi_close(struct i40e_vsi *vsi) { - bool reset = false; - + struct i40e_pf *pf = vsi->back; if (!test_and_set_bit(__I40E_DOWN, &vsi->state)) i40e_down(vsi); i40e_vsi_free_irq(vsi); i40e_vsi_free_tx_resources(vsi); i40e_vsi_free_rx_resources(vsi); vsi->current_netdev_flags = 0; - if (test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) - reset = true; - i40e_notify_client_of_netdev_close(vsi, reset); + pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; + if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) + pf->flags |= I40E_FLAG_CLIENT_RESET; } /** @@ -5542,8 +5543,6 @@ void i40e_down(struct i40e_vsi *vsi) i40e_clean_rx_ring(vsi->rx_rings[i]); } - i40e_notify_client_of_netdev_close(vsi, false); - } /** @@ -6021,8 +6020,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, i40e_service_event_schedule(pf); } else { i40e_pf_unquiesce_all_vsi(pf); - /* Notify the client for the DCB changes */ - i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]); + pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED | + I40E_FLAG_CLIENT_L2_CHANGE); } exit: @@ -7411,7 +7410,18 @@ static void i40e_service_task(struct work_struct *work) i40e_vc_process_vflr_event(pf); i40e_watchdog_subtask(pf); i40e_fdir_reinit_subtask(pf); - i40e_client_subtask(pf); + if (pf->flags & I40E_FLAG_CLIENT_RESET) { + /* Client subtask will reopen next time through. */ + i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true); + pf->flags &= ~I40E_FLAG_CLIENT_RESET; + } else { + i40e_client_subtask(pf); + if (pf->flags & I40E_FLAG_CLIENT_L2_CHANGE) { + i40e_notify_client_of_l2_param_changes( + pf->vsi[pf->lan_vsi]); + pf->flags &= ~I40E_FLAG_CLIENT_L2_CHANGE; + } + } i40e_sync_filters_subtask(pf); i40e_sync_udp_filters_subtask(pf); i40e_clean_adminq_subtask(pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 78460c52b7c4..25ee5af2d136 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1359,7 +1359,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) if (!vsi->info.pvid) vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN; - if (i40e_vf_client_capable(pf, vf->vf_id, I40E_CLIENT_IWARP) && + if (i40e_vf_client_capable(pf, vf->vf_id) && (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_IWARP)) { vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_IWARP; set_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states); From c0cf70a6fc373570f86c6dc4799d775363b9946e Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 24 Jan 2017 10:24:01 -0800 Subject: [PATCH 264/399] i40e: don't add more vectors to num_lan_msix than number of CPUs This is a solution to avoid adding too many queues to num_lan_msix. A recent refactor of queue pairs accidentally added all remaining vectors to the num_lan_msix which can have adverse performance issues, due to enabling more queues than the number of CPU cores. This patch removes the old calculation, and replaces it with a simple algorithm. 1) add queue pairs up to num_online_cpus(), but capped at half of total vectors 2) then add alternative features such as flow directory and similar 3) finally, add the remaining vectors back to queue pairs, but capped such that the total number of queue pairs does not exceed num_online_cpus(). Change-ID: I668abf67d5011a1248866daba8885f4ff00cb8d9 Signed-off-by: Jacob Keller Signed-off-by: Harshitha Ramamurthy Signed-off-by: Carolyn Wyborny Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 30 ++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3d7f179af6be..cb678ed7a2ad 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7819,6 +7819,7 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors) static int i40e_init_msix(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; + int cpus, extra_vectors; int vectors_left; int v_budget, i; int v_actual; @@ -7854,10 +7855,16 @@ static int i40e_init_msix(struct i40e_pf *pf) vectors_left--; } - /* reserve vectors for the main PF traffic queues */ - pf->num_lan_msix = min_t(int, num_online_cpus(), vectors_left); + /* reserve some vectors for the main PF traffic queues. Initially we + * only reserve at most 50% of the available vectors, in the case that + * the number of online CPUs is large. This ensures that we can enable + * extra features as well. Once we've enabled the other features, we + * will use any remaining vectors to reach as close as we can to the + * number of online CPUs. + */ + cpus = num_online_cpus(); + pf->num_lan_msix = min_t(int, cpus, vectors_left / 2); vectors_left -= pf->num_lan_msix; - v_budget += pf->num_lan_msix; /* reserve one vector for sideband flow director */ if (pf->flags & I40E_FLAG_FD_SB_ENABLED) { @@ -7920,6 +7927,23 @@ static int i40e_init_msix(struct i40e_pf *pf) } } + /* On systems with a large number of SMP cores, we previously limited + * the number of vectors for num_lan_msix to be at most 50% of the + * available vectors, to allow for other features. Now, we add back + * the remaining vectors. However, we ensure that the total + * num_lan_msix will not exceed num_online_cpus(). To do this, we + * calculate the number of vectors we can add without going over the + * cap of CPUs. For systems with a small number of CPUs this will be + * zero. + */ + extra_vectors = min_t(int, cpus - pf->num_lan_msix, vectors_left); + pf->num_lan_msix += extra_vectors; + vectors_left -= extra_vectors; + + WARN(vectors_left < 0, + "Calculation of remaining vectors underflowed. This is an accounting bug when determining total MSI-X vectors.\n"); + + v_budget += pf->num_lan_msix; pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry), GFP_KERNEL); if (!pf->msix_entries) From c271dd6c391b535226cf1a81aaad9f33cb5899d3 Mon Sep 17 00:00:00 2001 From: Lihong Yang Date: Mon, 30 Jan 2017 12:29:32 -0800 Subject: [PATCH 265/399] i40e: fix ethtool to get EEPROM data from X722 interface Currently ethtool -e will error out with a X722 interface as its EEPROM has a scope limit at offset 0x5B9FFF. This patch fixes the issue by setting the EEPROM length to the scope limit to avoid NVM read failure beyond that. Change-ID: I0b7d4dd6c7f2a57cace438af5dffa0f44c229372 Signed-off-by: Lihong Yang Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index a22e26200bcc..3aefc9e20439 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1165,6 +1165,11 @@ static int i40e_get_eeprom_len(struct net_device *netdev) struct i40e_hw *hw = &np->vsi->back->hw; u32 val; +#define X722_EEPROM_SCOPE_LIMIT 0x5B9FFF + if (hw->mac.type == I40E_MAC_X722) { + val = X722_EEPROM_SCOPE_LIMIT + 1; + return val; + } val = (rd32(hw, I40E_GLPCI_LBARCTRL) & I40E_GLPCI_LBARCTRL_FL_SIZE_MASK) >> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT; From 26f77e53cfee2b1b066071353be03988897e23c3 Mon Sep 17 00:00:00 2001 From: Lihong Yang Date: Mon, 30 Jan 2017 12:29:33 -0800 Subject: [PATCH 266/399] i40e: fix RSS queues only operating on PF0 This patch fixes the issue that RSS offloading only works on PF0 by using the direct register writing of the hash keys for the VFs instead of using the admin queue command to do so. Change-ID: Ia02cda7dbaa23def342e8786097a2c03db6f580b Signed-off-by: Lihong Yang Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 11 +++-------- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 6 ++---- 2 files changed, 5 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index cb678ed7a2ad..e577ff8a9c76 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8394,13 +8394,10 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed, if (vsi->type == I40E_VSI_MAIN) { for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i), - seed_dw[i]); + wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]); } else if (vsi->type == I40E_VSI_SRIOV) { for (i = 0; i <= I40E_VFQF_HKEY1_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, - I40E_VFQF_HKEY1(i, vf_id), - seed_dw[i]); + wr32(hw, I40E_VFQF_HKEY1(i, vf_id), seed_dw[i]); } else { dev_err(&pf->pdev->dev, "Cannot set RSS seed - invalid VSI type\n"); } @@ -8418,9 +8415,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed, if (lut_size != I40E_VF_HLUT_ARRAY_SIZE) return -EINVAL; for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, - I40E_VFQF_HLUT1(i, vf_id), - lut_dw[i]); + wr32(hw, I40E_VFQF_HLUT1(i, vf_id), lut_dw[i]); } else { dev_err(&pf->pdev->dev, "Cannot set RSS LUT - invalid VSI type\n"); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 25ee5af2d136..115a7286ab8f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -702,10 +702,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) dev_info(&pf->pdev->dev, "Could not allocate VF broadcast filter\n"); spin_unlock_bh(&vsi->mac_filter_hash_lock); - i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), - (u32)hena); - i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), - (u32)(hena >> 32)); + wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena); + wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32)); } /* program mac filter */ From 3954b39102677c879d7663621fb9a7e0da349274 Mon Sep 17 00:00:00 2001 From: Filip Sadowski Date: Mon, 30 Jan 2017 12:29:34 -0800 Subject: [PATCH 267/399] i40e: Clarify steps in MAC/VLAN filters initialization routine This patch clarifies the reason for removal of automatically firmware-generated filter and explicit addition of filter which accepts frames with any VLAN id. Change-ID: Iabf180b6d61c4d8a36d3bcf8457c377a6f2aca0e Signed-off-by: Filip Sadowski Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e577ff8a9c76..414685c683d7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9461,10 +9461,10 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, hw->mac.perm_addr); - /* The following steps are necessary to prevent reception - * of tagged packets - some older NVM configurations load a - * default a MAC-VLAN filter that accepts any tagged packet - * which must be replaced by a normal filter. + /* The following steps are necessary to properly keep track of + * MAC-VLAN filters loaded into firmware - first we remove + * filter that is automatically generated by firmware and then + * add new filter both to the driver hash table and firmware. */ i40e_rm_default_mac_filter(vsi, mac_addr); spin_lock_bh(&vsi->mac_filter_hash_lock); From 59605bc09630c2b577858c371edf89c099b5f925 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 30 Jan 2017 12:29:35 -0800 Subject: [PATCH 268/399] i40e/i40evf: Add support for mapping pages with DMA attributes This patch adds support for DMA_ATTR_SKIP_CPU_SYNC and DMA_ATTR_WEAK_ORDERING. By enabling both of these for the Rx path we are able to see performance improvements on architectures that implement either one due to the fact that page mapping and unmapping only has to sync what is actually being used instead of the entire buffer. In addition by enabling the weak ordering attribute enables a performance improvement for architectures that can associate a memory ordering with a DMA buffer such as Sparc. Change-ID: If176824e8231c5b24b8a5d55b339a6026738fc75 Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 31 ++++++++++++++++--- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 3 ++ drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 31 ++++++++++++++++--- drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 3 ++ 4 files changed, 58 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 97d46058d71d..86e4991a03a7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1010,7 +1010,6 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) **/ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) { - struct device *dev = rx_ring->dev; unsigned long bi_size; u16 i; @@ -1030,7 +1029,20 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_bi->page) continue; - dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_bi->dma, + rx_bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); __free_pages(rx_bi->page, 0); rx_bi->page = NULL; @@ -1159,7 +1171,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use @@ -1219,6 +1234,12 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) if (!i40e_alloc_mapped_page(rx_ring, bi)) goto no_buffers; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ @@ -1685,8 +1706,8 @@ struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring, rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, - DMA_FROM_DEVICE); + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, + DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); } /* clear contents of buffer_info */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index f80979025c01..49c7b2089d8e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -133,6 +133,9 @@ enum i40e_dyn_idx_t { #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 #define i40e_rx_desc i40e_32byte_rx_desc +#define I40E_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index c91fcf43ccbc..d7790c08e523 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -493,7 +493,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring) **/ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) { - struct device *dev = rx_ring->dev; unsigned long bi_size; u16 i; @@ -513,7 +512,20 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_bi->page) continue; - dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_bi->dma, + rx_bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); __free_pages(rx_bi->page, 0); rx_bi->page = NULL; @@ -642,7 +654,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + PAGE_SIZE, + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use @@ -702,6 +717,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) if (!i40e_alloc_mapped_page(rx_ring, bi)) goto no_buffers; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + I40E_RXBUFFER_2048, + DMA_FROM_DEVICE); + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ @@ -1158,8 +1179,8 @@ struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring, rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, - DMA_FROM_DEVICE); + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, + DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); } /* clear contents of buffer_info */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 8274ba68bd32..013512124e6a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -120,6 +120,9 @@ enum i40e_dyn_idx_t { #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 #define i40e_rx_desc i40e_32byte_rx_desc +#define I40E_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) From 4dbc56613962bfa597c345d8eff839870293c0a5 Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Mon, 30 Jan 2017 12:29:36 -0800 Subject: [PATCH 269/399] i40e: Allow untrusted VFs to have more filters Our original filter limit of 8 was based on behavior that we saw from Linux VMs. Now we're running Other Operating Systems under KVM and we see that they commonly use more MAC filters. Since it seems weird to require people to enable trusted VFs just to boot their OS, bump the number of filters allowed by default. Change-ID: I76b2dcb2ad6017e39231ad3096c3fb6f065eef5e Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 115a7286ab8f..cfe8b78dac0e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1851,7 +1851,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } /* If the VF is not trusted restrict the number of MAC/VLAN it can program */ -#define I40E_VC_MAX_MAC_ADDR_PER_VF 8 +#define I40E_VC_MAX_MAC_ADDR_PER_VF 12 #define I40E_VC_MAX_VLAN_PER_VF 8 /** From 15990832cd3e7e8904f8dacdabfa33adb9a836d6 Mon Sep 17 00:00:00 2001 From: Bimmy Pujari Date: Mon, 30 Jan 2017 12:29:37 -0800 Subject: [PATCH 270/399] i40e/i40evf: Change version from 1.6.27 to 2.1.7 Signed-off-by: Bimmy Pujari Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 6 +++--- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 414685c683d7..4d305fb1f188 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,9 +39,9 @@ static const char i40e_driver_string[] = #define DRV_KERN "-k" -#define DRV_VERSION_MAJOR 1 -#define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 27 +#define DRV_VERSION_MAJOR 2 +#define DRV_VERSION_MINOR 1 +#define DRV_VERSION_BUILD 7 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 9492b20da557..6d666bde9df5 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -37,9 +37,9 @@ static const char i40evf_driver_string[] = #define DRV_KERN "-k" -#define DRV_VERSION_MAJOR 1 -#define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 27 +#define DRV_VERSION_MAJOR 2 +#define DRV_VERSION_MINOR 1 +#define DRV_VERSION_BUILD 7 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ From b77ac975930741f0b6612b18e55d7a72c81ea2ac Mon Sep 17 00:00:00 2001 From: Harshitha Ramamurthy Date: Fri, 3 Feb 2017 10:57:42 -0800 Subject: [PATCH 271/399] i40e: rename auto_disable_flags to hw_disabled_flags A previous commit introduced a field that tracks the features that are disabled due to HW resource limitations as opposed to the featured disabled by the user. This patch changes the name of the field to make it more readable since it might get confusing when looking at code containing both the flags field and the auto_disable_features field together. Change-ID: Idcc9888659698f6fe3ccff17c8c3f09b5026f708 Signed-off-by: Harshitha Ramamurthy Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 8 ++++-- .../net/ethernet/intel/i40e/i40e_ethtool.c | 10 +++---- drivers/net/ethernet/intel/i40e/i40e_main.c | 28 +++++++++---------- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 20 ++++++------- 4 files changed, 35 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 9b2bb8d971cc..a5cf5d11d0e7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -353,8 +353,12 @@ struct i40e_pf { #define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) #define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(57) - /* tracks features that get auto disabled by errors */ - u64 auto_disable_flags; + /* Tracks features that are disabled due to hw limitations. + * If a bit is set here, it means that the corresponding + * bit in the 'flags' field is cleared i.e that feature + * is disabled + */ + u64 hw_disabled_flags; #ifdef I40E_FCOE struct i40e_fcoe fcoe; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 3aefc9e20439..a933c6c2aff8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2717,7 +2717,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED)) return -EOPNOTSUPP; - if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED) + if (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED) return -ENOSPC; if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) || @@ -3059,7 +3059,7 @@ static u32 i40e_get_priv_flags(struct net_device *dev) I40E_PRIV_FLAGS_FD_ATR : 0; ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ? I40E_PRIV_FLAGS_VEB_STATS : 0; - ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ? + ret_flags |= pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ? 0 : I40E_PRIV_FLAGS_HW_ATR_EVICT; if (pf->hw.pf_id == 0) { ret_flags |= pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT ? @@ -3099,7 +3099,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) pf->flags |= I40E_FLAG_FD_ATR_ENABLED; } else { pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; /* flush current ATR settings */ set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); @@ -3144,9 +3144,9 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) && (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)) - pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE; else - pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE; /* if needed, issue reset to cause things to take effect */ if (reset_required) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 4d305fb1f188..113b32911f1b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1101,13 +1101,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) &osd->rx_lpi_count, &nsd->rx_lpi_count); if (pf->flags & I40E_FLAG_FD_SB_ENABLED && - !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) + !(pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) nsd->fd_sb_status = true; else nsd->fd_sb_status = false; if (pf->flags & I40E_FLAG_FD_ATR_ENABLED && - !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + !(pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) nsd->fd_atr_status = true; else nsd->fd_atr_status = false; @@ -5467,7 +5467,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi) /* reset fd counters */ pf->fd_add_err = pf->fd_atr_cnt = 0; if (pf->fd_tcp_rule > 0) { - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n"); pf->fd_tcp_rule = 0; @@ -6143,8 +6143,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) (pf->fd_add_err == 0) || (i40e_get_current_atr_cnt(pf) < pf->fd_atr_cnt)) { if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED; + (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) { + pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n"); } @@ -6155,9 +6155,9 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) */ if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) { if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED) && + (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED) && (pf->fd_tcp_rule == 0)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n"); } @@ -6209,7 +6209,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } pf->fd_flush_timestamp = jiffies; - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; /* flush all filters */ wr32(&pf->hw, I40E_PFQF_CTL_1, I40E_PFQF_CTL_1_CLEARFDTABLE_MASK); @@ -6229,7 +6229,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) /* replay sideband filters */ i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]); if (!disable_atr) - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n"); @@ -8872,9 +8872,9 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.aq.api_min_ver > 4))) { /* Supported in FW API version higher than 1.4 */ pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; - pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } else { - pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } pf->eeprom_version = 0xDEAD; @@ -8935,14 +8935,14 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features) i40e_fdir_filter_exit(pf); } pf->flags &= ~I40E_FLAG_FD_SB_ENABLED; - pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED; /* reset fd counters */ pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0; pf->fdir_pf_active_filters = 0; /* if ATR was auto disabled it can be re-enabled. */ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) { + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR re-enabled.\n"); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 86e4991a03a7..6eb5dc4168f3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -291,7 +291,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; } else { pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ? (pf->fd_tcp_rule - 1) : 0; @@ -299,7 +299,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; } } @@ -484,8 +484,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf); if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) && - (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) { + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); } @@ -498,11 +498,11 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, */ if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) { if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && - !(pf->auto_disable_flags & + !(pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) { if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n"); - pf->auto_disable_flags |= + pf->hw_disabled_flags |= I40E_FLAG_FD_SB_ENABLED; } } @@ -2100,7 +2100,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) return; - if ((pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + if ((pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) return; /* if sampling is disabled do nothing */ @@ -2134,10 +2134,10 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, th = (struct tcphdr *)(hdr.network + hlen); /* Due to lack of space, no more new filters can be programmed */ - if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + if (th->syn && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) return; if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) { + (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) { /* HW ATR eviction will take care of removing filters on FIN * and RST packets. */ @@ -2200,7 +2200,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TXD_FLTR_QW1_CNTINDEX_MASK; if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) + (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK; fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype); From 6deee2221e110f6574988120dba6cab7e7313f44 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:45 +0000 Subject: [PATCH 272/399] net: stmmac: prepare dma op mode config for multiple queues This patch prepares DMA Operation Mode configuration for multiple queues. The work consisted on breaking the DMA operation Mode configuration function into RX and TX scope and adapting its mechanism in stmmac_main. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 3 + .../net/ethernet/stmicro/stmmac/dwmac4_dma.c | 118 +++++++++--------- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 82 +++++++++--- 3 files changed, 124 insertions(+), 79 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 9f0d26da6813..13bd3d4e381f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -424,6 +424,9 @@ struct stmmac_dma_ops { * An invalid value enables the store-and-forward mode */ void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode, int rxfifosz); + void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel, + int fifosz); + void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel); /* To track extra statistic (if supported) */ void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 6ac6b2600a7c..6285e8ad340d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -182,70 +182,26 @@ static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt) writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(i)); } -static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, - int rxmode, u32 channel, int rxfifosz) +static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, + u32 channel, int fifosz) { - unsigned int rqs = rxfifosz / 256 - 1; - u32 mtl_tx_op, mtl_rx_op, mtl_rx_int; - - /* Following code only done for channel 0, other channels not yet - * supported. - */ - mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); - - if (txmode == SF_DMA_MODE) { - pr_debug("GMAC: enable TX store and forward mode\n"); - /* Transmit COE type 2 cannot be done in cut-through mode. */ - mtl_tx_op |= MTL_OP_MODE_TSF; - } else { - pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode); - mtl_tx_op &= ~MTL_OP_MODE_TSF; - mtl_tx_op &= MTL_OP_MODE_TTC_MASK; - /* Set the transmit threshold */ - if (txmode <= 32) - mtl_tx_op |= MTL_OP_MODE_TTC_32; - else if (txmode <= 64) - mtl_tx_op |= MTL_OP_MODE_TTC_64; - else if (txmode <= 96) - mtl_tx_op |= MTL_OP_MODE_TTC_96; - else if (txmode <= 128) - mtl_tx_op |= MTL_OP_MODE_TTC_128; - else if (txmode <= 192) - mtl_tx_op |= MTL_OP_MODE_TTC_192; - else if (txmode <= 256) - mtl_tx_op |= MTL_OP_MODE_TTC_256; - else if (txmode <= 384) - mtl_tx_op |= MTL_OP_MODE_TTC_384; - else - mtl_tx_op |= MTL_OP_MODE_TTC_512; - } - /* For an IP with DWC_EQOS_NUM_TXQ == 1, the fields TXQEN and TQS are RO - * with reset values: TXQEN on, TQS == DWC_EQOS_TXFIFO_SIZE. - * For an IP with DWC_EQOS_NUM_TXQ > 1, the fields TXQEN and TQS are R/W - * with reset values: TXQEN off, TQS 256 bytes. - * - * Write the bits in both cases, since it will have no effect when RO. - * For DWC_EQOS_NUM_TXQ > 1, the top bits in MTL_OP_MODE_TQS_MASK might - * be RO, however, writing the whole TQS field will result in a value - * equal to DWC_EQOS_TXFIFO_SIZE, just like for DWC_EQOS_NUM_TXQ == 1. - */ - mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK; - writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel)); + unsigned int rqs = fifosz / 256 - 1; + u32 mtl_rx_op, mtl_rx_int; mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel)); - if (rxmode == SF_DMA_MODE) { + if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable RX store and forward mode\n"); mtl_rx_op |= MTL_OP_MODE_RSF; } else { - pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode); + pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode); mtl_rx_op &= ~MTL_OP_MODE_RSF; mtl_rx_op &= MTL_OP_MODE_RTC_MASK; - if (rxmode <= 32) + if (mode <= 32) mtl_rx_op |= MTL_OP_MODE_RTC_32; - else if (rxmode <= 64) + else if (mode <= 64) mtl_rx_op |= MTL_OP_MODE_RTC_64; - else if (rxmode <= 96) + else if (mode <= 96) mtl_rx_op |= MTL_OP_MODE_RTC_96; else mtl_rx_op |= MTL_OP_MODE_RTC_128; @@ -255,7 +211,7 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT; /* enable flow control only if each channel gets 4 KiB or more FIFO */ - if (rxfifosz >= 4096) { + if (fifosz >= 4096) { unsigned int rfd, rfa; mtl_rx_op |= MTL_OP_MODE_EHFC; @@ -266,7 +222,7 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, * Set Threshold for Deactivating Flow Control to min 1 frame, * i.e. 1500 bytes. */ - switch (rxfifosz) { + switch (fifosz) { case 4096: /* This violates the above formula because of FIFO size * limit therefore overflow may occur in spite of this. @@ -306,11 +262,49 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode, ioaddr + MTL_CHAN_INT_CTRL(channel)); } -static void dwmac4_dma_operation_mode(void __iomem *ioaddr, int txmode, - int rxmode, int rxfifosz) +static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, + u32 channel) { - /* Only Channel 0 is actually configured and used */ - dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0, rxfifosz); + u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); + + if (mode == SF_DMA_MODE) { + pr_debug("GMAC: enable TX store and forward mode\n"); + /* Transmit COE type 2 cannot be done in cut-through mode. */ + mtl_tx_op |= MTL_OP_MODE_TSF; + } else { + pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode); + mtl_tx_op &= ~MTL_OP_MODE_TSF; + mtl_tx_op &= MTL_OP_MODE_TTC_MASK; + /* Set the transmit threshold */ + if (mode <= 32) + mtl_tx_op |= MTL_OP_MODE_TTC_32; + else if (mode <= 64) + mtl_tx_op |= MTL_OP_MODE_TTC_64; + else if (mode <= 96) + mtl_tx_op |= MTL_OP_MODE_TTC_96; + else if (mode <= 128) + mtl_tx_op |= MTL_OP_MODE_TTC_128; + else if (mode <= 192) + mtl_tx_op |= MTL_OP_MODE_TTC_192; + else if (mode <= 256) + mtl_tx_op |= MTL_OP_MODE_TTC_256; + else if (mode <= 384) + mtl_tx_op |= MTL_OP_MODE_TTC_384; + else + mtl_tx_op |= MTL_OP_MODE_TTC_512; + } + /* For an IP with DWC_EQOS_NUM_TXQ == 1, the fields TXQEN and TQS are RO + * with reset values: TXQEN on, TQS == DWC_EQOS_TXFIFO_SIZE. + * For an IP with DWC_EQOS_NUM_TXQ > 1, the fields TXQEN and TQS are R/W + * with reset values: TXQEN off, TQS 256 bytes. + * + * Write the bits in both cases, since it will have no effect when RO. + * For DWC_EQOS_NUM_TXQ > 1, the top bits in MTL_OP_MODE_TQS_MASK might + * be RO, however, writing the whole TQS field will result in a value + * equal to DWC_EQOS_TXFIFO_SIZE, just like for DWC_EQOS_NUM_TXQ == 1. + */ + mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK; + writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel)); } static void dwmac4_get_hw_feature(void __iomem *ioaddr, @@ -387,7 +381,8 @@ const struct stmmac_dma_ops dwmac4_dma_ops = { .init = dwmac4_dma_init, .axi = dwmac4_dma_axi, .dump_regs = dwmac4_dump_dma_regs, - .dma_mode = dwmac4_dma_operation_mode, + .dma_rx_mode = dwmac4_dma_rx_chan_op_mode, + .dma_tx_mode = dwmac4_dma_tx_chan_op_mode, .enable_dma_irq = dwmac4_enable_dma_irq, .disable_dma_irq = dwmac4_disable_dma_irq, .start_tx = dwmac4_dma_start_tx, @@ -409,7 +404,8 @@ const struct stmmac_dma_ops dwmac410_dma_ops = { .init = dwmac4_dma_init, .axi = dwmac4_dma_axi, .dump_regs = dwmac4_dump_dma_regs, - .dma_mode = dwmac4_dma_operation_mode, + .dma_rx_mode = dwmac4_dma_rx_chan_op_mode, + .dma_tx_mode = dwmac4_dma_tx_chan_op_mode, .enable_dma_irq = dwmac410_enable_dma_irq, .disable_dma_irq = dwmac4_disable_dma_irq, .start_tx = dwmac4_dma_start_tx, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ec363e19cd79..c4e4a5328951 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1285,14 +1285,20 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv) */ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) { + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; int rxfifosz = priv->plat->rx_fifo_size; + u32 txmode = 0; + u32 rxmode = 0; + u32 chan = 0; if (rxfifosz == 0) rxfifosz = priv->dma_cap.rx_fifo_size; - if (priv->plat->force_thresh_dma_mode) - priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, rxfifosz); - else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) { + if (priv->plat->force_thresh_dma_mode) { + txmode = tc; + rxmode = tc; + } else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) { /* * In case of GMAC, SF mode can be enabled * to perform the TX COE in HW. This depends on: @@ -1300,12 +1306,26 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) * 2) There is no bugged Jumbo frame support * that needs to not insert csum in the TDES. */ - priv->hw->dma->dma_mode(priv->ioaddr, SF_DMA_MODE, SF_DMA_MODE, - rxfifosz); + txmode = SF_DMA_MODE; + rxmode = SF_DMA_MODE; priv->xstats.threshold = SF_DMA_MODE; - } else - priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE, + } else { + txmode = tc; + rxmode = SF_DMA_MODE; + } + + /* configure all channels */ + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + for (chan = 0; chan < rx_channels_count; chan++) + priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, + rxfifosz); + + for (chan = 0; chan < tx_channels_count; chan++) + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + } else { + priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); + } } /** @@ -1443,6 +1463,34 @@ static void stmmac_tx_err(struct stmmac_priv *priv) netif_wake_queue(priv->dev); } +/** + * stmmac_set_dma_operation_mode - Set DMA operation mode by channel + * @priv: driver private structure + * @txmode: TX operating mode + * @rxmode: RX operating mode + * @chan: channel index + * Description: it is used for configuring of the DMA operation mode in + * runtime in order to program the tx/rx DMA thresholds or Store-And-Forward + * mode. + */ +static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, + u32 rxmode, u32 chan) +{ + int rxfifosz = priv->plat->rx_fifo_size; + + if (rxfifosz == 0) + rxfifosz = priv->dma_cap.rx_fifo_size; + + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, + rxfifosz); + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + } else { + priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, + rxfifosz); + } +} + /** * stmmac_dma_interrupt - DMA ISR * @priv: driver private structure @@ -1452,11 +1500,8 @@ static void stmmac_tx_err(struct stmmac_priv *priv) */ static void stmmac_dma_interrupt(struct stmmac_priv *priv) { + u32 chan = STMMAC_CHAN0; int status; - int rxfifosz = priv->plat->rx_fifo_size; - - if (rxfifosz == 0) - rxfifosz = priv->dma_cap.rx_fifo_size; status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats); if (likely((status & handle_rx)) || (status & handle_tx)) { @@ -1471,11 +1516,12 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) (tc <= 256)) { tc += 64; if (priv->plat->force_thresh_dma_mode) - priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, - rxfifosz); + stmmac_set_dma_operation_mode(priv->ioaddr, + tc, tc, chan); else - priv->hw->dma->dma_mode(priv->ioaddr, tc, - SF_DMA_MODE, rxfifosz); + stmmac_set_dma_operation_mode(priv->ioaddr, tc, + SF_DMA_MODE, chan); + priv->xstats.threshold = tc; } } else if (unlikely(status == tx_hard_error)) @@ -1749,6 +1795,9 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) /* Enable MAC RX Queues */ if (rx_queues_count > 1 && priv->hw->mac->rx_queue_enable) stmmac_mac_enable_rx_queues(priv); + + /* Set the HW DMA mode and the COE */ + stmmac_dma_operation_mode(priv); } /** @@ -1812,9 +1861,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) else stmmac_set_mac(priv->ioaddr, true); - /* Set the HW DMA mode and the COE */ - stmmac_dma_operation_mode(priv); - stmmac_mmc_setup(priv); if (init_ptp) { From 4f513ecd2f60d9ebd2ac0fa4cd0b5d0612d70233 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:46 +0000 Subject: [PATCH 273/399] net: stmmac: enable/disable dma irq prepared for multiple queues This patch prepares the DMA IRQ enable/disable process for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h | 6 +++--- drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c | 12 ++++++------ drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 +++++++------ 6 files changed, 22 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 13bd3d4e381f..0351b5408372 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -431,8 +431,8 @@ struct stmmac_dma_ops { void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, void __iomem *ioaddr); void (*enable_dma_transmission) (void __iomem *ioaddr); - void (*enable_dma_irq) (void __iomem *ioaddr); - void (*disable_dma_irq) (void __iomem *ioaddr); + void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan); + void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan); void (*start_tx) (void __iomem *ioaddr); void (*stop_tx) (void __iomem *ioaddr); void (*start_rx) (void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index 1b06df749e2b..393a657cd9ff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -185,9 +185,9 @@ int dwmac4_dma_reset(void __iomem *ioaddr); void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr); -void dwmac4_enable_dma_irq(void __iomem *ioaddr); -void dwmac410_enable_dma_irq(void __iomem *ioaddr); -void dwmac4_disable_dma_irq(void __iomem *ioaddr); +void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan); void dwmac4_dma_start_tx(void __iomem *ioaddr); void dwmac4_dma_stop_tx(void __iomem *ioaddr); void dwmac4_dma_start_rx(void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index c7326d5b2f43..c9327911e29a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -104,21 +104,21 @@ void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len) writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(STMMAC_CHAN0)); } -void dwmac4_enable_dma_irq(void __iomem *ioaddr) +void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + - DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + DMA_CHAN_INTR_ENA(chan)); } -void dwmac410_enable_dma_irq(void __iomem *ioaddr) +void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10, - ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + ioaddr + DMA_CHAN_INTR_ENA(chan)); } -void dwmac4_disable_dma_irq(void __iomem *ioaddr) +void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan) { - writel(0, ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + writel(0, ioaddr + DMA_CHAN_INTR_ENA(chan)); } int dwmac4_dma_interrupt(void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 56e485f79077..dec0816565f3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -137,8 +137,8 @@ #define DMA_CONTROL_FTF 0x00100000 /* Flush transmit FIFO */ void dwmac_enable_dma_transmission(void __iomem *ioaddr); -void dwmac_enable_dma_irq(void __iomem *ioaddr); -void dwmac_disable_dma_irq(void __iomem *ioaddr); +void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan); +void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan); void dwmac_dma_start_tx(void __iomem *ioaddr); void dwmac_dma_stop_tx(void __iomem *ioaddr); void dwmac_dma_start_rx(void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index e60bfca2a763..285cfc9b3361 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -47,12 +47,12 @@ void dwmac_enable_dma_transmission(void __iomem *ioaddr) writel(1, ioaddr + DMA_XMT_POLL_DEMAND); } -void dwmac_enable_dma_irq(void __iomem *ioaddr) +void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA); } -void dwmac_disable_dma_irq(void __iomem *ioaddr) +void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan) { writel(0, ioaddr + DMA_INTR_ENA); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c4e4a5328951..18cf58c16dc3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1422,14 +1422,14 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) netif_tx_unlock(priv->dev); } -static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv) +static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv, u32 chan) { - priv->hw->dma->enable_dma_irq(priv->ioaddr); + priv->hw->dma->enable_dma_irq(priv->ioaddr, chan); } -static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv) +static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan) { - priv->hw->dma->disable_dma_irq(priv->ioaddr); + priv->hw->dma->disable_dma_irq(priv->ioaddr, chan); } /** @@ -1506,7 +1506,7 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats); if (likely((status & handle_rx)) || (status & handle_tx)) { if (likely(napi_schedule_prep(&priv->napi))) { - stmmac_disable_dma_irq(priv); + stmmac_disable_dma_irq(priv, chan); __napi_schedule(&priv->napi); } } @@ -2832,6 +2832,7 @@ static int stmmac_poll(struct napi_struct *napi, int budget) { struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi); int work_done = 0; + u32 chan = STMMAC_CHAN0; priv->xstats.napi_poll++; stmmac_tx_clean(priv); @@ -2839,7 +2840,7 @@ static int stmmac_poll(struct napi_struct *napi, int budget) work_done = stmmac_rx(priv, budget); if (work_done < budget) { napi_complete_done(napi, work_done); - stmmac_enable_dma_irq(priv); + stmmac_enable_dma_irq(priv, chan); } return work_done; } From ae4f0d46830814e11ec91b8c76ebf3ae3f8140d7 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:47 +0000 Subject: [PATCH 274/399] net: stmmac: rx/tx dma start/stop prepared for multiple queues This patch prepares the RX/TX DMA stop/start process for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 8 +- .../net/ethernet/stmicro/stmmac/dwmac4_dma.h | 8 +- .../net/ethernet/stmicro/stmmac/dwmac4_lib.c | 24 ++-- .../net/ethernet/stmicro/stmmac/dwmac_dma.h | 8 +- .../net/ethernet/stmicro/stmmac/dwmac_lib.c | 8 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 108 ++++++++++++++++-- 6 files changed, 125 insertions(+), 39 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 0351b5408372..042b4828efaa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -433,10 +433,10 @@ struct stmmac_dma_ops { void (*enable_dma_transmission) (void __iomem *ioaddr); void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan); void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan); - void (*start_tx) (void __iomem *ioaddr); - void (*stop_tx) (void __iomem *ioaddr); - void (*start_rx) (void __iomem *ioaddr); - void (*stop_rx) (void __iomem *ioaddr); + void (*start_tx)(void __iomem *ioaddr, u32 chan); + void (*stop_tx)(void __iomem *ioaddr, u32 chan); + void (*start_rx)(void __iomem *ioaddr, u32 chan); + void (*stop_rx)(void __iomem *ioaddr, u32 chan); int (*dma_interrupt) (void __iomem *ioaddr, struct stmmac_extra_stats *x); /* If supported then get the optional core features */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index 393a657cd9ff..2c19042b47df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -188,10 +188,10 @@ void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr); void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan); void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan); void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan); -void dwmac4_dma_start_tx(void __iomem *ioaddr); -void dwmac4_dma_stop_tx(void __iomem *ioaddr); -void dwmac4_dma_start_rx(void __iomem *ioaddr); -void dwmac4_dma_stop_rx(void __iomem *ioaddr); +void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan); +void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan); +void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan); +void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan); int dwmac4_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x); void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index c9327911e29a..3512d18f626b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -45,49 +45,49 @@ void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(0)); } -void dwmac4_dma_start_tx(void __iomem *ioaddr) +void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan)); value |= DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value |= GMAC_CONFIG_TE; writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_dma_stop_tx(void __iomem *ioaddr) +void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan)); value &= ~DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value &= ~GMAC_CONFIG_TE; writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_dma_start_rx(void __iomem *ioaddr) +void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); value |= DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value |= GMAC_CONFIG_RE; writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_dma_stop_rx(void __iomem *ioaddr) +void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); value &= ~DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0)); + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); value = readl(ioaddr + GMAC_CONFIG); value &= ~GMAC_CONFIG_RE; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index dec0816565f3..6c6cc7137ee0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -139,10 +139,10 @@ void dwmac_enable_dma_transmission(void __iomem *ioaddr); void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan); void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan); -void dwmac_dma_start_tx(void __iomem *ioaddr); -void dwmac_dma_stop_tx(void __iomem *ioaddr); -void dwmac_dma_start_rx(void __iomem *ioaddr); -void dwmac_dma_stop_rx(void __iomem *ioaddr); +void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan); +void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan); +void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan); +void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan); int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x); int dwmac_dma_reset(void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 285cfc9b3361..7be60c3a24e8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -57,28 +57,28 @@ void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan) writel(0, ioaddr + DMA_INTR_ENA); } -void dwmac_dma_start_tx(void __iomem *ioaddr) +void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value |= DMA_CONTROL_ST; writel(value, ioaddr + DMA_CONTROL); } -void dwmac_dma_stop_tx(void __iomem *ioaddr) +void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value &= ~DMA_CONTROL_ST; writel(value, ioaddr + DMA_CONTROL); } -void dwmac_dma_start_rx(void __iomem *ioaddr) +void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value |= DMA_CONTROL_SR; writel(value, ioaddr + DMA_CONTROL); } -void dwmac_dma_stop_rx(void __iomem *ioaddr) +void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan) { u32 value = readl(ioaddr + DMA_CONTROL); value &= ~DMA_CONTROL_SR; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 18cf58c16dc3..a537276e1055 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1277,6 +1277,96 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv) } } +/** + * stmmac_start_rx_dma - start RX DMA channel + * @priv: driver private structure + * @chan: RX channel index + * Description: + * This starts a RX DMA channel + */ +static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA RX processes started in channel %d\n", chan); + priv->hw->dma->start_rx(priv->ioaddr, chan); +} + +/** + * stmmac_start_tx_dma - start TX DMA channel + * @priv: driver private structure + * @chan: TX channel index + * Description: + * This starts a TX DMA channel + */ +static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA TX processes started in channel %d\n", chan); + priv->hw->dma->start_tx(priv->ioaddr, chan); +} + +/** + * stmmac_stop_rx_dma - stop RX DMA channel + * @priv: driver private structure + * @chan: RX channel index + * Description: + * This stops a RX DMA channel + */ +static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA RX processes stopped in channel %d\n", chan); + priv->hw->dma->stop_rx(priv->ioaddr, chan); +} + +/** + * stmmac_stop_tx_dma - stop TX DMA channel + * @priv: driver private structure + * @chan: TX channel index + * Description: + * This stops a TX DMA channel + */ +static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan) +{ + netdev_dbg(priv->dev, "DMA TX processes stopped in channel %d\n", chan); + priv->hw->dma->stop_tx(priv->ioaddr, chan); +} + +/** + * stmmac_start_all_dma - start all RX and TX DMA channels + * @priv: driver private structure + * Description: + * This starts all the RX and TX DMA channels + */ +static void stmmac_start_all_dma(struct stmmac_priv *priv) +{ + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 chan = 0; + + for (chan = 0; chan < rx_channels_count; chan++) + stmmac_start_rx_dma(priv, chan); + + for (chan = 0; chan < tx_channels_count; chan++) + stmmac_start_tx_dma(priv, chan); +} + +/** + * stmmac_stop_all_dma - stop all RX and TX DMA channels + * @priv: driver private structure + * Description: + * This stops the RX and TX DMA channels + */ +static void stmmac_stop_all_dma(struct stmmac_priv *priv) +{ + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 chan = 0; + + for (chan = 0; chan < rx_channels_count; chan++) + stmmac_stop_rx_dma(priv, chan); + + for (chan = 0; chan < tx_channels_count; chan++) + stmmac_stop_tx_dma(priv, chan); +} + /** * stmmac_dma_operation_mode - HW DMA operation mode * @priv: driver private structure @@ -1440,10 +1530,11 @@ static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan) */ static void stmmac_tx_err(struct stmmac_priv *priv) { + u32 chan = STMMAC_CHAN0; int i; netif_stop_queue(priv->dev); - priv->hw->dma->stop_tx(priv->ioaddr); + stmmac_stop_tx_dma(priv, chan); dma_free_tx_skbufs(priv); for (i = 0; i < DMA_TX_SIZE; i++) if (priv->extend_desc) @@ -1457,7 +1548,7 @@ static void stmmac_tx_err(struct stmmac_priv *priv) priv->dirty_tx = 0; priv->cur_tx = 0; netdev_reset_queue(priv->dev); - priv->hw->dma->start_tx(priv->ioaddr); + stmmac_start_tx_dma(priv, chan); priv->dev->stats.tx_errors++; netif_wake_queue(priv->dev); @@ -1882,9 +1973,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) __func__); #endif /* Start the ball rolling... */ - netdev_dbg(priv->dev, "DMA RX/TX processes started...\n"); - priv->hw->dma->start_tx(priv->ioaddr); - priv->hw->dma->start_rx(priv->ioaddr); + stmmac_start_all_dma(priv); priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS; @@ -2070,8 +2159,7 @@ static int stmmac_release(struct net_device *dev) free_irq(priv->lpi_irq, dev); /* Stop TX/RX DMA and clear the descriptors */ - priv->hw->dma->stop_tx(priv->ioaddr); - priv->hw->dma->stop_rx(priv->ioaddr); + stmmac_stop_all_dma(priv); /* Release and free the Rx/Tx resources */ free_dma_desc_resources(priv); @@ -3546,8 +3634,7 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); - priv->hw->dma->stop_rx(priv->ioaddr); - priv->hw->dma->stop_tx(priv->ioaddr); + stmmac_stop_all_dma(priv); stmmac_set_mac(priv->ioaddr, false); netif_carrier_off(ndev); @@ -3593,8 +3680,7 @@ int stmmac_suspend(struct device *dev) napi_disable(&priv->napi); /* Stop TX/RX DMA */ - priv->hw->dma->stop_tx(priv->ioaddr); - priv->hw->dma->stop_rx(priv->ioaddr); + stmmac_stop_all_dma(priv); /* Enable Power down mode by programming the PMT regs */ if (device_may_wakeup(priv->device)) { From 4e593262290c3488ca7ab8b41a5c70c284e12b57 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:48 +0000 Subject: [PATCH 275/399] net: stmmac: prepare stmmac_tx_err for multiple queues This patch prepares stmmac_err for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a537276e1055..b166c05e2a5d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1525,12 +1525,12 @@ static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan) /** * stmmac_tx_err - to manage the tx error * @priv: driver private structure + * @chan: channel index * Description: it cleans the descriptors and restarts the transmission * in case of transmission errors. */ -static void stmmac_tx_err(struct stmmac_priv *priv) +static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) { - u32 chan = STMMAC_CHAN0; int i; netif_stop_queue(priv->dev); @@ -1616,7 +1616,7 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) priv->xstats.threshold = tc; } } else if (unlikely(status == tx_hard_error)) - stmmac_tx_err(priv); + stmmac_tx_err(priv, chan); } /** @@ -2944,9 +2944,10 @@ static int stmmac_poll(struct napi_struct *napi, int budget) static void stmmac_tx_timeout(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 chan = STMMAC_CHAN0; /* Clear Tx resources and restart transmitting again */ - stmmac_tx_err(priv); + stmmac_tx_err(priv, chan); } /** From d62a107a4f154c9aa826dbe03ac2322a389b37b5 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:49 +0000 Subject: [PATCH 276/399] net: stmmac: prepare dma interrupt treatment for multiple queues This patch prepares DMA interrupts treatment for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- .../net/ethernet/stmicro/stmmac/dwmac4_dma.h | 2 +- .../net/ethernet/stmicro/stmmac/dwmac4_lib.c | 8 +-- .../net/ethernet/stmicro/stmmac/dwmac_dma.h | 3 +- .../net/ethernet/stmicro/stmmac/dwmac_lib.c | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 53 +++++++++++-------- 6 files changed, 40 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 042b4828efaa..6dfb7f31898e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -438,7 +438,7 @@ struct stmmac_dma_ops { void (*start_rx)(void __iomem *ioaddr, u32 chan); void (*stop_rx)(void __iomem *ioaddr, u32 chan); int (*dma_interrupt) (void __iomem *ioaddr, - struct stmmac_extra_stats *x); + struct stmmac_extra_stats *x, u32 chan); /* If supported then get the optional core features */ void (*get_hw_feature)(void __iomem *ioaddr, struct dma_features *dma_cap); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index 2c19042b47df..946dc14fe77f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -193,7 +193,7 @@ void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan); void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan); void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan); int dwmac4_dma_interrupt(void __iomem *ioaddr, - struct stmmac_extra_stats *x); + struct stmmac_extra_stats *x, u32 chan); void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len); void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len); void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 3512d18f626b..fcd8ec8a240b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -122,11 +122,11 @@ void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan) } int dwmac4_dma_interrupt(void __iomem *ioaddr, - struct stmmac_extra_stats *x) + struct stmmac_extra_stats *x, u32 chan) { int ret = 0; - u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(0)); + u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan)); /* ABNORMAL interrupts */ if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) { @@ -153,7 +153,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, if (likely(intr_status & DMA_CHAN_STATUS_RI)) { u32 value; - value = readl(ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0)); + value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); /* to schedule NAPI on real RIE event. */ if (likely(value & DMA_CHAN_INTR_ENA_RIE)) { x->rx_normal_irq_n++; @@ -172,7 +172,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, * status [21-0] expect reserved bits [5-3] */ writel((intr_status & 0x3fffc7), - ioaddr + DMA_CHAN_STATUS(STMMAC_CHAN0)); + ioaddr + DMA_CHAN_STATUS(chan)); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 6c6cc7137ee0..9091df86723a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -143,7 +143,8 @@ void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan); void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan); void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan); void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan); -int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x); +int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 chan); int dwmac_dma_reset(void __iomem *ioaddr); #endif /* __DWMAC_DMA_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 7be60c3a24e8..38f94305aab5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -156,7 +156,7 @@ static void show_rx_process_state(unsigned int status) #endif int dwmac_dma_interrupt(void __iomem *ioaddr, - struct stmmac_extra_stats *x) + struct stmmac_extra_stats *x, u32 chan) { int ret = 0; /* read the status register (CSR5) */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b166c05e2a5d..79a792a0c12e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1591,32 +1591,41 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, */ static void stmmac_dma_interrupt(struct stmmac_priv *priv) { - u32 chan = STMMAC_CHAN0; + u32 tx_channel_count = priv->plat->tx_queues_to_use; int status; + u32 chan; - status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats); - if (likely((status & handle_rx)) || (status & handle_tx)) { - if (likely(napi_schedule_prep(&priv->napi))) { - stmmac_disable_dma_irq(priv, chan); - __napi_schedule(&priv->napi); + for (chan = 0; chan < tx_channel_count; chan++) { + status = priv->hw->dma->dma_interrupt(priv->ioaddr, + &priv->xstats, chan); + if (likely((status & handle_rx)) || (status & handle_tx)) { + if (likely(napi_schedule_prep(&priv->napi))) { + stmmac_disable_dma_irq(priv, chan); + __napi_schedule(&priv->napi); + } + } + + if (unlikely(status & tx_hard_error_bump_tc)) { + /* Try to bump up the dma threshold on this failure */ + if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && + (tc <= 256)) { + tc += 64; + if (priv->plat->force_thresh_dma_mode) + stmmac_set_dma_operation_mode(priv, + tc, + tc, + chan); + else + stmmac_set_dma_operation_mode(priv, + tc, + SF_DMA_MODE, + chan); + priv->xstats.threshold = tc; + } + } else if (unlikely(status == tx_hard_error)) { + stmmac_tx_err(priv, chan); } } - if (unlikely(status & tx_hard_error_bump_tc)) { - /* Try to bump up the dma threshold on this failure */ - if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && - (tc <= 256)) { - tc += 64; - if (priv->plat->force_thresh_dma_mode) - stmmac_set_dma_operation_mode(priv->ioaddr, - tc, tc, chan); - else - stmmac_set_dma_operation_mode(priv->ioaddr, tc, - SF_DMA_MODE, chan); - - priv->xstats.threshold = tc; - } - } else if (unlikely(status == tx_hard_error)) - stmmac_tx_err(priv, chan); } /** From 3c55d4d08bc9e94901a26eb57c9aa0b8c76a18c0 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:50 +0000 Subject: [PATCH 277/399] net: stmmac: rx watchdog config prepared for multiple queues This patch adds rx watchdog configuration for all queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 8 ++++---- drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- 5 files changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 6dfb7f31898e..5fa23b13d3cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -443,7 +443,7 @@ struct stmmac_dma_ops { void (*get_hw_feature)(void __iomem *ioaddr, struct dma_features *dma_cap); /* Program the HW RX Watchdog */ - void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt); + void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan); void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len); void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len); void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index d3654a447046..471a9aa6ac94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -247,7 +247,8 @@ static void dwmac1000_get_hw_feature(void __iomem *ioaddr, dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24; } -static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt) +static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt, + u32 number_chan) { writel(riwt, ioaddr + DMA_RX_WATCHDOG); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 6285e8ad340d..74177f9d640b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -174,12 +174,12 @@ static void dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 *reg_space) _dwmac4_dump_dma_regs(ioaddr, i, reg_space); } -static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt) +static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan) { - int i; + u32 chan; - for (i = 0; i < DMA_CHANNEL_NB_MAX; i++) - writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(i)); + for (chan = 0; chan < number_chan; chan++) + writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(chan)); } static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 61b9369a041e..16808e48ca1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -730,6 +730,7 @@ static int stmmac_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_cnt = priv->plat->rx_queues_to_use; unsigned int rx_riwt; /* Check not supported parameters */ @@ -768,7 +769,7 @@ static int stmmac_set_coalesce(struct net_device *dev, priv->tx_coal_frames = ec->tx_max_coalesced_frames; priv->tx_coal_timer = ec->tx_coalesce_usecs; priv->rx_riwt = rx_riwt; - priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt); + priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt, rx_cnt); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 79a792a0c12e..00d0f5ea7682 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1915,6 +1915,7 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) { struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_cnt = priv->plat->rx_queues_to_use; int ret; /* DMA initialization and SW reset */ @@ -1988,7 +1989,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) { priv->rx_riwt = MAX_DMA_RIWT; - priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT); + priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT, rx_cnt); } if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane) From 4854ab9966e10ca002e4cc7a12e34c1444357d3d Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:51 +0000 Subject: [PATCH 278/399] net: stmmac: rx and tx ring length prepared for multiple queues This patch prepares tx and rx ring length configuration for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 4 +-- .../net/ethernet/stmicro/stmmac/dwmac4_dma.h | 4 +-- .../net/ethernet/stmicro/stmmac/dwmac4_lib.c | 8 ++--- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 32 ++++++++++++++----- 4 files changed, 32 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 5fa23b13d3cd..bef1fc6a6756 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -444,8 +444,8 @@ struct stmmac_dma_ops { struct dma_features *dma_cap); /* Program the HW RX Watchdog */ void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan); - void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len); - void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len); + void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); + void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index 946dc14fe77f..8474bf961dd0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -194,8 +194,8 @@ void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan); void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan); int dwmac4_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x, u32 chan); -void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len); -void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len); +void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan); +void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan); void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index fcd8ec8a240b..da54c0b0bdf5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -94,14 +94,14 @@ void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan) writel(value, ioaddr + GMAC_CONFIG); } -void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len) +void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan) { - writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(STMMAC_CHAN0)); + writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(chan)); } -void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len) +void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan) { - writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(STMMAC_CHAN0)); + writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(chan)); } void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 00d0f5ea7682..26695d9a3283 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1802,6 +1802,27 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv) add_timer(&priv->txtimer); } +static void stmmac_set_rings_length(struct stmmac_priv *priv) +{ + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 chan; + + /* set TX ring length */ + if (priv->hw->dma->set_tx_ring_len) { + for (chan = 0; chan < tx_channels_count; chan++) + priv->hw->dma->set_tx_ring_len(priv->ioaddr, + (DMA_TX_SIZE - 1), chan); + } + + /* set RX ring length */ + if (priv->hw->dma->set_rx_ring_len) { + for (chan = 0; chan < rx_channels_count; chan++) + priv->hw->dma->set_rx_ring_len(priv->ioaddr, + (DMA_RX_SIZE - 1), chan); + } +} + /** * stmmac_set_tx_queue_weight - Set TX queue weight * @priv: driver private structure @@ -1995,14 +2016,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane) priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0); - /* set TX ring length */ - if (priv->hw->dma->set_tx_ring_len) - priv->hw->dma->set_tx_ring_len(priv->ioaddr, - (DMA_TX_SIZE - 1)); - /* set RX ring length */ - if (priv->hw->dma->set_rx_ring_len) - priv->hw->dma->set_rx_ring_len(priv->ioaddr, - (DMA_RX_SIZE - 1)); + /* set TX and RX rings length */ + stmmac_set_rings_length(priv); + /* Enable TSO */ if (priv->tso) priv->hw->dma->enable_tso(priv->ioaddr, 1, STMMAC_CHAN0); From 89cc57c55c1a7627b5dc912184da7e68d0d193bd Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:52 +0000 Subject: [PATCH 279/399] net: stmmac: prepare rx/tx set tail function for multiple queues This patch prepares RX and TX set tail functions for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index da54c0b0bdf5..49f5687879df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -37,12 +37,12 @@ int dwmac4_dma_reset(void __iomem *ioaddr) void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) { - writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(0)); + writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(chan)); } void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) { - writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(0)); + writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(chan)); } void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan) From 47f2a9ce527addf8a2c384efc47f0c812dc1a162 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:53 +0000 Subject: [PATCH 280/399] net: stmmac: dma channel init prepared for multiple queues This patch prepares the DMA initialization process for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 8 +++ .../net/ethernet/stmicro/stmmac/dwmac4_dma.c | 68 +++++++++++-------- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 51 +++++++++++--- 3 files changed, 89 insertions(+), 38 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index bef1fc6a6756..badc4414d67b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -416,6 +416,14 @@ struct stmmac_dma_ops { int (*reset)(void __iomem *ioaddr); void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, u32 dma_tx, u32 dma_rx, int atds); + void (*init_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, u32 chan); + void (*init_rx_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_rx_phy, u32 chan); + void (*init_tx_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_tx_phy, u32 chan); /* Configure the AXI Bus Mode Register */ void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi); /* Dump DMA registers */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 74177f9d640b..eec8463057fd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -71,36 +71,48 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) writel(value, ioaddr + DMA_SYS_BUS_MODE); } -static void dwmac4_dma_init_channel(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, - u32 dma_tx_phy, u32 dma_rx_phy, - u32 channel) +void dwmac4_dma_init_rx_chan(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_rx_phy, u32 chan) { u32 value; - int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; - int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; + u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; - /* set PBL for each channels. Currently we affect same configuration - * on each channel - */ - value = readl(ioaddr + DMA_CHAN_CONTROL(channel)); + value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); + value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT); + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); + + writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan)); +} + +void dwmac4_dma_init_tx_chan(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_tx_phy, u32 chan) +{ + u32 value; + u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; + + value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan)); + value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT); + writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan)); + + writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan)); +} + +void dwmac4_dma_init_channel(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, u32 chan) +{ + u32 value; + + /* common channel control register config */ + value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); if (dma_cfg->pblx8) value = value | DMA_BUS_MODE_PBL; - writel(value, ioaddr + DMA_CHAN_CONTROL(channel)); - - value = readl(ioaddr + DMA_CHAN_TX_CONTROL(channel)); - value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT); - writel(value, ioaddr + DMA_CHAN_TX_CONTROL(channel)); - - value = readl(ioaddr + DMA_CHAN_RX_CONTROL(channel)); - value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT); - writel(value, ioaddr + DMA_CHAN_RX_CONTROL(channel)); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); /* Mask interrupts by writing to CSR7 */ - writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(channel)); - - writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(channel)); - writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(channel)); + writel(DMA_CHAN_INTR_DEFAULT_MASK, + ioaddr + DMA_CHAN_INTR_ENA(chan)); } static void dwmac4_dma_init(void __iomem *ioaddr, @@ -108,7 +120,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr, u32 dma_tx, u32 dma_rx, int atds) { u32 value = readl(ioaddr + DMA_SYS_BUS_MODE); - int i; /* Set the Fixed burst mode */ if (dma_cfg->fixed_burst) @@ -122,9 +133,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr, value |= DMA_SYS_BUS_AAL; writel(value, ioaddr + DMA_SYS_BUS_MODE); - - for (i = 0; i < DMA_CHANNEL_NB_MAX; i++) - dwmac4_dma_init_channel(ioaddr, dma_cfg, dma_tx, dma_rx, i); } static void _dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 channel, @@ -379,6 +387,9 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan) const struct stmmac_dma_ops dwmac4_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, + .init_chan = dwmac4_dma_init_channel, + .init_rx_chan = dwmac4_dma_init_rx_chan, + .init_tx_chan = dwmac4_dma_init_tx_chan, .axi = dwmac4_dma_axi, .dump_regs = dwmac4_dump_dma_regs, .dma_rx_mode = dwmac4_dma_rx_chan_op_mode, @@ -402,6 +413,9 @@ const struct stmmac_dma_ops dwmac4_dma_ops = { const struct stmmac_dma_ops dwmac410_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, + .init_chan = dwmac4_dma_init_channel, + .init_rx_chan = dwmac4_dma_init_rx_chan, + .init_tx_chan = dwmac4_dma_init_tx_chan, .axi = dwmac4_dma_axi, .dump_regs = dwmac4_dump_dma_regs, .dma_rx_mode = dwmac4_dma_rx_chan_op_mode, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 26695d9a3283..2868391de0fb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1732,6 +1732,11 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv) */ static int stmmac_init_dma_engine(struct stmmac_priv *priv) { + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 dummy_dma_rx_phy = 0; + u32 dummy_dma_tx_phy = 0; + u32 chan = 0; int atds = 0; int ret = 0; @@ -1749,19 +1754,43 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) return ret; } - priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_tx_phy, priv->dma_rx_phy, atds); - if (priv->synopsys_id >= DWMAC_CORE_4_00) { - priv->rx_tail_addr = priv->dma_rx_phy + - (DMA_RX_SIZE * sizeof(struct dma_desc)); - priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, priv->rx_tail_addr, - STMMAC_CHAN0); + /* DMA Configuration */ + priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, + dummy_dma_tx_phy, dummy_dma_rx_phy, atds); - priv->tx_tail_addr = priv->dma_tx_phy + - (DMA_TX_SIZE * sizeof(struct dma_desc)); - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr, - STMMAC_CHAN0); + /* DMA RX Channel Configuration */ + for (chan = 0; chan < rx_channels_count; chan++) { + priv->hw->dma->init_rx_chan(priv->ioaddr, + priv->plat->dma_cfg, + priv->dma_rx_phy, chan); + + priv->rx_tail_addr = priv->dma_rx_phy + + (DMA_RX_SIZE * sizeof(struct dma_desc)); + priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, + priv->rx_tail_addr, + chan); + } + + /* DMA TX Channel Configuration */ + for (chan = 0; chan < tx_channels_count; chan++) { + priv->hw->dma->init_chan(priv->ioaddr, + priv->plat->dma_cfg, + chan); + + priv->hw->dma->init_tx_chan(priv->ioaddr, + priv->plat->dma_cfg, + priv->dma_tx_phy, chan); + + priv->tx_tail_addr = priv->dma_tx_phy + + (DMA_TX_SIZE * sizeof(struct dma_desc)); + priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, + priv->tx_tail_addr, + chan); + } + } else { + priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, + priv->dma_tx_phy, priv->dma_rx_phy, atds); } if (priv->plat->axi && priv->hw->dma->axi) From 146617b88b86c3d1f1309604d5d4cb38d5b24f1a Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:54 +0000 Subject: [PATCH 281/399] net: stmmac: tso init prepared for multiple queues This patch configures TSO for all available tx queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2868391de0fb..c802286380dc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1966,6 +1966,8 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) { struct stmmac_priv *priv = netdev_priv(dev); u32 rx_cnt = priv->plat->rx_queues_to_use; + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 chan; int ret; /* DMA initialization and SW reset */ @@ -2049,8 +2051,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_set_rings_length(priv); /* Enable TSO */ - if (priv->tso) - priv->hw->dma->enable_tso(priv->ioaddr, 1, STMMAC_CHAN0); + if (priv->tso) { + for (chan = 0; chan < tx_cnt; chan++) + priv->hw->dma->enable_tso(priv->ioaddr, 1, chan); + } return 0; } From 7bac4e1ec3ca2342929a39638d615c6b672c27a0 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Wed, 15 Mar 2017 11:04:55 +0000 Subject: [PATCH 282/399] net: stmmac: stmmac interrupt treatment prepared for multiple queues This patch prepares the main ISR for multiple queues. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 28 +++++++++++++------ 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c802286380dc..d3a21519e4c0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3115,6 +3115,12 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) { struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_cnt = priv->plat->rx_queues_to_use; + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 queues_count; + u32 queue; + + queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt; if (priv->irq_wake) pm_wakeup_event(priv->device, 0); @@ -3129,20 +3135,26 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) int status = priv->hw->mac->host_irq_status(priv->hw, &priv->xstats); - if (priv->synopsys_id >= DWMAC_CORE_4_00) - status |= priv->hw->mac->host_mtl_irq_status(priv->hw, - STMMAC_CHAN0); - if (unlikely(status)) { /* For LPI we need to save the tx status */ if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE) priv->tx_path_in_lpi_mode = true; if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE) priv->tx_path_in_lpi_mode = false; - if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr) - priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - priv->rx_tail_addr, - STMMAC_CHAN0); + } + + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + for (queue = 0; queue < queues_count; queue++) { + status |= + priv->hw->mac->host_mtl_irq_status(priv->hw, + queue); + + if (status & CORE_IRQ_MTL_RX_OVERFLOW && + priv->hw->dma->set_rx_tail_ptr) + priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, + priv->rx_tail_addr, + queue); + } } /* PCS link status */ From 5b7696499c68a6b84127018d063649597e31627a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 15 Mar 2017 15:31:58 +0000 Subject: [PATCH 283/399] netxen_nic: remove redundant check if retries is zero At the end of the timeout loop, retries will always be zero so the check for zero is redundant so remove it. Also replace printk with pr_err as recommended by checkpatch. Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c index 7b43a3b4abdc..3dd973475125 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c @@ -1375,13 +1375,8 @@ netxen_receive_peg_ready(struct netxen_adapter *adapter) } while (--retries); - if (!retries) { - printk(KERN_ERR "Receive Peg initialization not " - "complete, state: 0x%x.\n", val); - return -EIO; - } - - return 0; + pr_err("Receive Peg initialization not complete, state: 0x%x.\n", val); + return -EIO; } int netxen_init_firmware(struct netxen_adapter *adapter) From 2026fecf516bc04df20cb50874957cd8c364fb4e Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 15 Mar 2017 10:39:18 -0700 Subject: [PATCH 284/399] mqprio: Change handling of hw u8 to allow for multiple hardware offload modes This patch is meant to allow for support of multiple hardware offload type for a single device. There is currently no bounds checking for the hw member of the mqprio_qopt structure. This results in us being able to pass values from 1 to 255 with all being treated the same. On retreiving the value it is returned as 1 for anything 1 or greater being set. With this change we are currently adding limited bounds checking by defining an enum and using those values to limit the reported hardware offloads. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 8 ++++++++ net/sched/sch_mqprio.c | 26 ++++++++++++++++---------- 2 files changed, 24 insertions(+), 10 deletions(-) diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index df7451d35131..099bf5528fed 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -617,6 +617,14 @@ struct tc_drr_stats { #define TC_QOPT_BITMASK 15 #define TC_QOPT_MAX_QUEUE 16 +enum { + TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */ + TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */ + __TC_MQPRIO_HW_OFFLOAD_MAX +}; + +#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) + struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index b851e209da4d..5f55bf149d9f 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -21,7 +21,7 @@ struct mqprio_sched { struct Qdisc **qdiscs; - int hw_owned; + int hw_offload; }; static void mqprio_destroy(struct Qdisc *sch) @@ -39,7 +39,7 @@ static void mqprio_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } - if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); else netdev_set_num_tc(dev, 0); @@ -59,15 +59,20 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return -EINVAL; } - /* net_device does not support requested operation */ - if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) - return -EINVAL; + /* Limit qopt->hw to maximum supported offload value. Drivers have + * the option of overriding this later if they don't support the a + * given offload type. + */ + if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX) + qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX; - /* if hw owned qcount and qoffset are taken from LLD so - * no reason to verify them here + /* If hardware offload is requested we will leave it to the device + * to either populate the queue counts itself or to validate the + * provided queue counts. If ndo_setup_tc is not present then + * hardware doesn't support offload and we should return an error. */ if (qopt->hw) - return 0; + return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL; for (i = 0; i < qopt->num_tc; i++) { unsigned int last = qopt->offset[i] + qopt->count[i]; @@ -142,10 +147,11 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO, { .tc = qopt->num_tc }}; - priv->hw_owned = 1; err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); if (err) return err; + + priv->hw_offload = qopt->hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -243,7 +249,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.num_tc = netdev_get_num_tc(dev); memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); - opt.hw = priv->hw_owned; + opt.hw = priv->hw_offload; for (i = 0; i < netdev_get_num_tc(dev); i++) { opt.count[i] = dev->tc_to_txq[i].count; From 56f36acd215cf7c28372b2fdb4f33f6900e97e05 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Wed, 15 Mar 2017 10:39:25 -0700 Subject: [PATCH 285/399] mqprio: Modify mqprio to pass user parameters via ndo_setup_tc. The configurable priority to traffic class mapping and the user specified queue ranges are used to configure the traffic class, overriding the hardware defaults when the 'hw' option is set to 0. However, when the 'hw' option is non-zero, the hardware QOS defaults are used. This patch makes it so that we can pass the data the user provided to ndo_setup_tc. This allows us to pull in the queue configuration if the user requested it as well as any additional hardware offload type requested by using a value other than 1 for the hw value. Finally it also provides a means for the device driver to return the level supported for the offload type via the qopt->hw value. Previously we were just always assuming the value to be 1, in the future values beyond just 1 may be supported. Signed-off-by: Amritha Nambiar Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 3 ++- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 5 ++++- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 +++- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 16 ++++++++++------ drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 4 +++- drivers/net/ethernet/intel/i40e/i40e_main.c | 7 +++++-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 +++- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 4 +++- .../net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++- drivers/net/ethernet/sfc/falcon/tx.c | 4 +++- drivers/net/ethernet/sfc/tx.c | 4 +++- drivers/net/ethernet/ti/netcp_core.c | 12 ++++++++---- include/linux/netdevice.h | 2 +- net/sched/sch_mqprio.c | 17 +++++++++++------ 14 files changed, 62 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index ffea9859f5a7..7ec2c9717cf1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1854,7 +1854,8 @@ static int xgbe_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, if (tc_to_netdev->type != TC_SETUP_MQPRIO) return -EINVAL; - tc = tc_to_netdev->tc; + tc_to_netdev->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + tc = tc_to_netdev->mqprio->num_tc; if (tc > pdata->hw_feat.tc_cnt) return -EINVAL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 9e8c06130c09..ad3e0631877e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -4277,7 +4277,10 @@ int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto, { if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return bnx2x_setup_tc(dev, tc->tc); + + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return bnx2x_setup_tc(dev, tc->mqprio->num_tc); } /* called with rtnl_lock */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 32de4589d16a..174ec8f84637 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6905,7 +6905,9 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (ntc->type != TC_SETUP_MQPRIO) return -EINVAL; - return bnxt_setup_mq_tc(dev, ntc->tc); + ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return bnxt_setup_mq_tc(dev, ntc->mqprio->num_tc); } #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index aa769cbc7425..d4bb8bf86a45 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -346,33 +346,37 @@ static int dpaa_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, struct tc_to_netdev *tc) { struct dpaa_priv *priv = netdev_priv(net_dev); + u8 num_tc; int i; if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - if (tc->tc == priv->num_tc) + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + num_tc = tc->mqprio->num_tc; + + if (num_tc == priv->num_tc) return 0; - if (!tc->tc) { + if (!num_tc) { netdev_reset_tc(net_dev); goto out; } - if (tc->tc > DPAA_TC_NUM) { + if (num_tc > DPAA_TC_NUM) { netdev_err(net_dev, "Too many traffic classes: max %d supported.\n", DPAA_TC_NUM); return -EINVAL; } - netdev_set_num_tc(net_dev, tc->tc); + netdev_set_num_tc(net_dev, num_tc); - for (i = 0; i < tc->tc; i++) + for (i = 0; i < num_tc; i++) netdev_set_tc_queue(net_dev, i, DPAA_TC_TXQ_NUM, i * DPAA_TC_TXQ_NUM); out: - priv->num_tc = tc->tc ? tc->tc : 1; + priv->num_tc = num_tc ? : 1; netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM); return 0; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 01db688cf539..72481670478c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1226,7 +1226,9 @@ static int __fm10k_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return fm10k_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return fm10k_setup_tc(dev, tc->mqprio->num_tc); } static void fm10k_assign_l2_accel(struct fm10k_intfc *interface, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 113b32911f1b..9df0d86812e7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5611,9 +5611,12 @@ static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, struct tc_to_netdev *tc) #endif { - if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) + if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return i40e_setup_tc(netdev, tc->tc); + + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return i40e_setup_tc(netdev, tc->mqprio->num_tc); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index a7a430a7be2c..d45477db0227 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8948,7 +8948,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return ixgbe_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return ixgbe_setup_tc(dev, tc->mqprio->num_tc); } #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 61420473fe5f..94fab20ef146 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -92,7 +92,9 @@ static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return mlx4_en_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return mlx4_en_setup_tc(dev, tc->mqprio->num_tc); } #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8ef64c4db2c2..f96a73ea8e0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2737,7 +2737,9 @@ static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return mlx5e_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return mlx5e_setup_tc(dev, tc->mqprio->num_tc); } static void diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c index 104fb15a73f2..f6daf09b8627 100644 --- a/drivers/net/ethernet/sfc/falcon/tx.c +++ b/drivers/net/ethernet/sfc/falcon/tx.c @@ -437,11 +437,13 @@ int ef4_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, if (ntc->type != TC_SETUP_MQPRIO) return -EINVAL; - num_tc = ntc->tc; + num_tc = ntc->mqprio->num_tc; if (ef4_nic_rev(efx) < EF4_REV_FALCON_B0 || num_tc > EF4_MAX_TX_TC) return -EINVAL; + ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (num_tc == net_dev->num_tc) return 0; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index ff88d60aa6d5..3bdf87f31087 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -665,11 +665,13 @@ int efx_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, if (ntc->type != TC_SETUP_MQPRIO) return -EINVAL; - num_tc = ntc->tc; + num_tc = ntc->mqprio->num_tc; if (num_tc > EFX_MAX_TX_TC) return -EINVAL; + ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (num_tc == net_dev->num_tc) return 0; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 7c7ae0890e90..9027c9c509b5 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1882,6 +1882,7 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb, static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto, struct tc_to_netdev *tc) { + u8 num_tc; int i; /* setup tc must be called under rtnl lock */ @@ -1890,15 +1891,18 @@ static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + num_tc = tc->mqprio->num_tc; + /* Sanity-check the number of traffic classes requested */ if ((dev->real_num_tx_queues <= 1) || - (dev->real_num_tx_queues < tc->tc)) + (dev->real_num_tx_queues < num_tc)) return -EINVAL; /* Configure traffic class to queue mappings */ - if (tc->tc) { - netdev_set_num_tc(dev, tc->tc); - for (i = 0; i < tc->tc; i++) + if (num_tc) { + netdev_set_num_tc(dev, num_tc); + for (i = 0; i < num_tc; i++) netdev_set_tc_queue(dev, i, 1, i); } else { netdev_reset_tc(dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 97456b2539e4..b7365b587818 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -786,11 +786,11 @@ struct tc_cls_u32_offload; struct tc_to_netdev { unsigned int type; union { - u8 tc; struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; struct tc_cls_matchall_offload *cls_mall; struct tc_cls_bpf_offload *cls_bpf; + struct tc_mqprio_qopt *mqprio; }; bool egress_dev; }; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 5f55bf149d9f..0a4cf27ea54b 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -28,7 +28,6 @@ static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO}; unsigned int ntx; if (priv->qdiscs) { @@ -39,10 +38,15 @@ static void mqprio_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } - if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { + struct tc_mqprio_qopt offload = { 0 }; + struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, + { .mqprio = &offload } }; + dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); - else + } else { netdev_set_num_tc(dev, 0); + } } static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) @@ -144,14 +148,15 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO, - { .tc = qopt->num_tc }}; + struct tc_mqprio_qopt offload = *qopt; + struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, + { .mqprio = &offload } }; err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); if (err) return err; - priv->hw_offload = qopt->hw; + priv->hw_offload = offload.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) From e893de1ba1d39e78750ffadf7191aef8133c8fe8 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 15 Mar 2017 15:53:48 -0400 Subject: [PATCH 286/399] net: dsa: dsa_fastest_ageing_time return unsigned The ageing time is defined as unsigned int, so make dsa_fastest_ageing_time return an unsigned int instead of int. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index c34872e1febc..cec47e843570 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -419,8 +419,8 @@ static int dsa_slave_vlan_filtering(struct net_device *dev, return 0; } -static int dsa_fastest_ageing_time(struct dsa_switch *ds, - unsigned int ageing_time) +static unsigned int dsa_fastest_ageing_time(struct dsa_switch *ds, + unsigned int ageing_time) { int i; From 0f3da6afeef1f63c7254965253f7e6535dc7910c Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 15 Mar 2017 15:53:49 -0400 Subject: [PATCH 287/399] net: dsa: check out-of-range ageing time value If a DSA switch driver cannot program an ageing time value due to it being out-of-range, switchdev will raise a stack trace before failing. To fix this, add ageing_time_min and ageing_time_max members to the dsa_switch in order for the switch drivers to optionally specify their supported ageing time limits. The DSA core will now check for provided ageing time limits and return -ERANGE from the switchdev prepare phase if the value is out-of-range. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 4 ++++ net/dsa/slave.c | 8 ++++++-- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index bf0e42c2a6f7..e42897fd7a96 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -233,6 +233,10 @@ struct dsa_switch { u32 phys_mii_mask; struct mii_bus *slave_mii_bus; + /* Ageing Time limits in msecs */ + unsigned int ageing_time_min; + unsigned int ageing_time_max; + /* Dynamically allocated ports, keep last */ size_t num_ports; struct dsa_port ports[]; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index cec47e843570..78128acfbf63 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -443,9 +443,13 @@ static int dsa_slave_ageing_time(struct net_device *dev, unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time); unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); - /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ - if (switchdev_trans_ph_prepare(trans)) + if (switchdev_trans_ph_prepare(trans)) { + if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) + return -ERANGE; + if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) + return -ERANGE; return 0; + } /* Keep the fastest ageing time in case of multiple bridges */ p->dp->ageing_time = ageing_time; From 9ff74f249db8c80f13568460e26d168f5c6d55cd Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 15 Mar 2017 15:53:50 -0400 Subject: [PATCH 288/399] net: dsa: mv88e6xxx: specify ageing time limits Now that DSA has ageing time limits, specify them when registering a switch so that out-of-range values are handled correctly by the core. Signed-off-by: Vivien Didelot Reported-by: Jason Cobham Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 3354f99df378..2bca297d9296 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -4253,6 +4253,8 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip) ds->priv = chip; ds->ops = &mv88e6xxx_switch_ops; + ds->ageing_time_min = chip->info->age_time_coeff; + ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX; dev_set_drvdata(dev, ds); From 4b72436dc3dd2457056b22d6f147777368c869fa Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Wed, 15 Mar 2017 13:27:15 -0700 Subject: [PATCH 289/399] drivers: net: phy: xgene: Fix mdio write This patches fixes a typo in the argument to xgene_enet_wr_mdio_csr(). Signed-off-by: Quan Nguyen Signed-off-by: Iyappan Subramanian Signed-off-by: David S. Miller --- drivers/net/phy/mdio-xgene.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c index f095051beb54..3e2ac07b6e37 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/phy/mdio-xgene.c @@ -229,7 +229,7 @@ static int xgene_xfi_mdio_write(struct mii_bus *bus, int phy_id, val = SET_VAL(HSTPHYADX, phy_id) | SET_VAL(HSTREGADX, reg) | SET_VAL(HSTMIIMWRDAT, data); - xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, data); + xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, val); val = HSTLDCMD | SET_VAL(HSTMIIMCMD, MIIM_CMD_LEGACY_WRITE); xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, val); From e026e700d940a1ea3d3bc84d92ac668b1f015462 Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Wed, 15 Mar 2017 13:27:16 -0700 Subject: [PATCH 290/399] drivers: net: xgene: Fix hardware checksum setting This patch fixes the hardware checksum settings by properly program the classifier. Otherwise, packet may be received with checksum error on X-Gene1 SoC. Signed-off-by: Quan Nguyen Signed-off-by: Iyappan Subramanian Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_hw.c | 1 + drivers/net/ethernet/apm/xgene/xgene_enet_hw.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 06e681697c17..c72a17e98f13 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -623,6 +623,7 @@ static void xgene_enet_cle_bypass(struct xgene_enet_pdata *pdata, xgene_enet_rd_csr(pdata, CLE_BYPASS_REG0_0_ADDR, &cb); cb |= CFG_CLE_BYPASS_EN0; CFG_CLE_IP_PROTOCOL0_SET(&cb, 3); + CFG_CLE_IP_HDR_LEN_SET(&cb, 0); xgene_enet_wr_csr(pdata, CLE_BYPASS_REG0_0_ADDR, cb); xgene_enet_rd_csr(pdata, CLE_BYPASS_REG1_0_ADDR, &cb); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h index 5f83037bb96b..b6cd625fad84 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h @@ -163,6 +163,7 @@ enum xgene_enet_rm { #define CFG_RXCLK_MUXSEL0_SET(dst, val) xgene_set_bits(dst, val, 26, 3) #define CFG_CLE_IP_PROTOCOL0_SET(dst, val) xgene_set_bits(dst, val, 16, 2) +#define CFG_CLE_IP_HDR_LEN_SET(dst, val) xgene_set_bits(dst, val, 8, 5) #define CFG_CLE_DSTQID0_SET(dst, val) xgene_set_bits(dst, val, 0, 12) #define CFG_CLE_FPSEL0_SET(dst, val) xgene_set_bits(dst, val, 16, 4) #define CFG_CLE_NXTFPSEL0_SET(dst, val) xgene_set_bits(dst, val, 20, 4) From 11623fce0f9afef30c45e3f2120b063de3809a8f Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Wed, 15 Mar 2017 13:27:17 -0700 Subject: [PATCH 291/399] drivers: net: xgene: Fix wrong logical operation This patch fixes the wrong logical OR operation by changing it to bit-wise OR operation. Fixes: 3bb502f83080 ("drivers: net: xgene: fix statistics counters race condition") Signed-off-by: Iyappan Subramanian Signed-off-by: Quan Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index b3568c453b14..ec43278d4b93 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -677,9 +677,9 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, buf_pool->rx_skb[skb_index] = NULL; /* checking for error */ - status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) || + status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) | GET_VAL(LERR, le64_to_cpu(raw_desc->m0)); - if (unlikely(status > 2)) { + if (unlikely(status)) { dev_kfree_skb_any(skb); xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc); xgene_enet_parse_error(rx_ring, netdev_priv(rx_ring->ndev), From 0a0400c3094b5d5cedd479ddbf1329de74c09c4b Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Wed, 15 Mar 2017 13:27:18 -0700 Subject: [PATCH 292/399] drivers: net: xgene: Fix Rx checksum validation logic This patch fixes Rx checksum validation logic and adds NETIF_F_RXCSUM flag. Signed-off-by: Iyappan Subramanian Signed-off-by: David S. Miller --- .../net/ethernet/apm/xgene/xgene_enet_main.c | 27 ++++++++++++------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index ec43278d4b93..e881365160e4 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -601,14 +601,24 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } -static void xgene_enet_skip_csum(struct sk_buff *skb) +static void xgene_enet_rx_csum(struct sk_buff *skb) { + struct net_device *ndev = skb->dev; struct iphdr *iph = ip_hdr(skb); - if (!ip_is_fragment(iph) || - (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - } + if (!(ndev->features & NETIF_F_RXCSUM)) + return; + + if (skb->protocol != htons(ETH_P_IP)) + return; + + if (ip_is_fragment(iph)) + return; + + if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP) + return; + + skb->ip_summed = CHECKSUM_UNNECESSARY; } static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool, @@ -729,10 +739,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, skip_jumbo: skb_checksum_none_assert(skb); skb->protocol = eth_type_trans(skb, ndev); - if (likely((ndev->features & NETIF_F_IP_CSUM) && - skb->protocol == htons(ETH_P_IP))) { - xgene_enet_skip_csum(skb); - } + xgene_enet_rx_csum(skb); rx_ring->rx_packets++; rx_ring->rx_bytes += datalen; @@ -2039,7 +2046,7 @@ static int xgene_enet_probe(struct platform_device *pdev) xgene_enet_setup_ops(pdata); if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) { - ndev->features |= NETIF_F_TSO; + ndev->features |= NETIF_F_TSO | NETIF_F_RXCSUM; spin_lock_init(&pdata->mss_lock); } ndev->hw_features = ndev->features; From 7eac928c19d7cb2dee9339a321c3f1abbb81358d Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Wed, 15 Mar 2017 13:27:19 -0700 Subject: [PATCH 293/399] drivers: net: xgene: Add workaround for errata 10GE_1 This patch implements workaround for errata 10GE_1: 10Gb Ethernet port FIFO threshold default values are incorrect. Signed-off-by: Quan Nguyen Signed-off-by: Toan Le Signed-off-by: Iyappan Subramanian Tested-by: Fushen Chen Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c | 7 +++++++ drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h | 5 +++++ 2 files changed, 12 insertions(+) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c index ece19e6d68e3..423240c97d39 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c @@ -341,8 +341,15 @@ static void xgene_xgmac_init(struct xgene_enet_pdata *pdata) xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, &data); data |= CFG_RSIF_FPBUFF_TIMEOUT_EN; + /* Errata 10GE_1 - FIFO threshold default value incorrect */ + RSIF_CLE_BUFF_THRESH_SET(&data, XG_RSIF_CLE_BUFF_THRESH); xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, data); + /* Errata 10GE_1 - FIFO threshold default value incorrect */ + xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, &data); + RSIF_PLC_CLE_BUFF_THRESH_SET(&data, XG_RSIF_PLC_CLE_BUFF_THRESH); + xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, data); + xgene_enet_rd_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, &data); data |= BIT(12); xgene_enet_wr_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, data); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h index 03b847ad8937..e644a429ebf4 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h @@ -65,6 +65,11 @@ #define XG_DEF_PAUSE_THRES 0x390 #define XG_DEF_PAUSE_OFF_THRES 0x2c0 #define XG_RSIF_CONFIG_REG_ADDR 0x00a0 +#define XG_RSIF_CLE_BUFF_THRESH 0x3 +#define RSIF_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 3) +#define XG_RSIF_CONFIG1_REG_ADDR 0x00b8 +#define XG_RSIF_PLC_CLE_BUFF_THRESH 0x1 +#define RSIF_PLC_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 2) #define XCLE_BYPASS_REG0_ADDR 0x0160 #define XCLE_BYPASS_REG1_ADDR 0x0164 #define XG_CFG_BYPASS_ADDR 0x0204 From 4902a92270fb2abec57a215d237a74f5ca16c9c7 Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Wed, 15 Mar 2017 13:27:20 -0700 Subject: [PATCH 294/399] drivers: net: xgene: Add workaround for errata 10GE_8/ENET_11 This patch implements workaround for errata 10GE_8 and ENET_11: "HW reports length error for valid 64 byte frames with len <46 bytes" by recovering them from error. Signed-off-by: Iyappan Subramanian Signed-off-by: Quan Nguyen Signed-off-by: Toan Le Tested-by: Fushen Chen Signed-off-by: David S. Miller --- .../net/ethernet/apm/xgene/xgene_enet_hw.c | 2 +- .../net/ethernet/apm/xgene/xgene_enet_hw.h | 1 + .../net/ethernet/apm/xgene/xgene_enet_main.c | 43 ++++++++++++------- .../net/ethernet/apm/xgene/xgene_enet_main.h | 1 + 4 files changed, 30 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index c72a17e98f13..2a835e07adfb 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -494,7 +494,7 @@ static void xgene_gmac_set_speed(struct xgene_enet_pdata *pdata) break; } - mc2 |= FULL_DUPLEX2 | PAD_CRC; + mc2 |= FULL_DUPLEX2 | PAD_CRC | LENGTH_CHK; xgene_enet_wr_mcx_mac(pdata, MAC_CONFIG_2_ADDR, mc2); xgene_enet_wr_mcx_mac(pdata, INTERFACE_CONTROL_ADDR, intf_ctl); xgene_enet_wr_csr(pdata, RGMII_REG_0_ADDR, rgmii); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h index b6cd625fad84..d250bfe94d24 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h @@ -216,6 +216,7 @@ enum xgene_enet_rm { #define ENET_GHD_MODE BIT(26) #define FULL_DUPLEX2 BIT(0) #define PAD_CRC BIT(2) +#define LENGTH_CHK BIT(4) #define SCAN_AUTO_INCR BIT(5) #define TBYT_ADDR 0x38 #define TPKT_ADDR 0x39 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index e881365160e4..5f37ed3506d5 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -658,12 +658,24 @@ static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool, buf_pool->head = head; } +/* Errata 10GE_8 and ENET_11 - allow packet with length <=64B */ +static bool xgene_enet_errata_10GE_8(struct sk_buff *skb, u32 len, u8 status) +{ + if (status == INGRESS_PKT_LEN && len == ETHER_MIN_PACKET) { + if (ntohs(eth_hdr(skb)->h_proto) < 46) + return true; + } + + return false; +} + static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, struct xgene_enet_raw_desc *raw_desc, struct xgene_enet_raw_desc *exp_desc) { struct xgene_enet_desc_ring *buf_pool, *page_pool; u32 datalen, frag_size, skb_index; + struct xgene_enet_pdata *pdata; struct net_device *ndev; dma_addr_t dma_addr; struct sk_buff *skb; @@ -676,6 +688,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, bool nv; ndev = rx_ring->ndev; + pdata = netdev_priv(ndev); dev = ndev_to_dev(rx_ring->ndev); buf_pool = rx_ring->buf_pool; page_pool = rx_ring->page_pool; @@ -686,30 +699,29 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, skb = buf_pool->rx_skb[skb_index]; buf_pool->rx_skb[skb_index] = NULL; + datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1)); + skb_put(skb, datalen); + prefetch(skb->data - NET_IP_ALIGN); + skb->protocol = eth_type_trans(skb, ndev); + /* checking for error */ status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) | GET_VAL(LERR, le64_to_cpu(raw_desc->m0)); if (unlikely(status)) { - dev_kfree_skb_any(skb); - xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc); - xgene_enet_parse_error(rx_ring, netdev_priv(rx_ring->ndev), - status); - ret = -EIO; - goto out; + if (!xgene_enet_errata_10GE_8(skb, datalen, status)) { + dev_kfree_skb_any(skb); + xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc); + xgene_enet_parse_error(rx_ring, pdata, status); + goto out; + } } - /* strip off CRC as HW isn't doing this */ - datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1)); - nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0)); - if (!nv) + if (!nv) { + /* strip off CRC as HW isn't doing this */ datalen -= 4; - - skb_put(skb, datalen); - prefetch(skb->data - NET_IP_ALIGN); - - if (!nv) goto skip_jumbo; + } slots = page_pool->slots - 1; head = page_pool->head; @@ -738,7 +750,6 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, skip_jumbo: skb_checksum_none_assert(skb); - skb->protocol = eth_type_trans(skb, ndev); xgene_enet_rx_csum(skb); rx_ring->rx_packets++; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 52571741da9f..0d4be2425ebc 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -41,6 +41,7 @@ #include "../../../phy/mdio-xgene.h" #define XGENE_DRV_VERSION "v1.0" +#define ETHER_MIN_PACKET 64 #define XGENE_ENET_STD_MTU 1536 #define XGENE_ENET_MAX_MTU 9600 #define SKB_BUFFER_SIZE (XGENE_ENET_STD_MTU - NET_IP_ALIGN) From b3fd38d27320c2bf2dfe5de495ffa57f366d0bce Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Wed, 15 Mar 2017 13:27:21 -0700 Subject: [PATCH 295/399] MAINTAINERS: Update X-Gene SoC ethernet maintainer Signed-off-by: Iyappan Subramanian Signed-off-by: Keyur Chudgar Signed-off-by: Quan Nguyen Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index cefda30ed704..632e76223cc5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -896,6 +896,7 @@ F: arch/arm64/boot/dts/apm/ APPLIED MICRO (APM) X-GENE SOC ETHERNET DRIVER M: Iyappan Subramanian M: Keyur Chudgar +M: Quan Nguyen S: Supported F: drivers/net/ethernet/apm/xgene/ F: drivers/net/phy/mdio-xgene.c From 864e91ca981ea1d18f05a8f5063520d103373266 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 9 Dec 2016 21:09:59 -0800 Subject: [PATCH 296/399] ipvs: remove an annoying printk in netns init At most it is used for debugging purpose, but I don't think it is even useful for debugging, just remove it. Signed-off-by: Cong Wang Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index db40050f8785..9aaa49025cdc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2231,8 +2231,6 @@ static int __net_init __ip_vs_init(struct net *net) if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; - printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", - sizeof(struct netns_ipvs), ipvs->gen); return 0; /* * Error handling From a2f346d82bcab1927a199f475dc299c00413ec39 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 20 Feb 2017 16:31:35 +0800 Subject: [PATCH 297/399] ipvs: fix sync_threshold description and add sync_refresh_period, sync_retries Fix sync_threshold description which should have two values. Also add sync_refresh_period and sync_retries based on commit 749c42b620a9 ("ipvs: reduce sync rate with time thresholds"). Signed-off-by: Hangbin Liu Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 38 +++++++++++++++++++----- 1 file changed, 30 insertions(+), 8 deletions(-) diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index e6b1c025fdd8..7acaaa65451e 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -185,15 +185,37 @@ secure_tcp - INTEGER The value definition is the same as that of drop_entry and drop_packet. -sync_threshold - INTEGER - default 3 +sync_threshold - vector of 2 INTEGERs: sync_threshold, sync_period + default 3 50 - It sets synchronization threshold, which is the minimum number - of incoming packets that a connection needs to receive before - the connection will be synchronized. A connection will be - synchronized, every time the number of its incoming packets - modulus 50 equals the threshold. The range of the threshold is - from 0 to 49. + It sets synchronization threshold, which is the minimum number + of incoming packets that a connection needs to receive before + the connection will be synchronized. A connection will be + synchronized, every time the number of its incoming packets + modulus sync_period equals the threshold. The range of the + threshold is from 0 to sync_period. + + When sync_period and sync_refresh_period are 0, send sync only + for state changes or only once when pkts matches sync_threshold + +sync_refresh_period - UNSIGNED INTEGER + default 0 + + In seconds, difference in reported connection timer that triggers + new sync message. It can be used to avoid sync messages for the + specified period (or half of the connection timeout if it is lower) + if connection state is not changed since last sync. + + This is useful for normal connections with high traffic to reduce + sync rate. Additionally, retry sync_retries times with period of + sync_refresh_period/8. + +sync_retries - INTEGER + default 0 + + Defines sync retries with period of sync_refresh_period/8. Useful + to protect against loss of sync messages. The range of the + sync_retries is from 0 to 3. snat_reroute - BOOLEAN 0 - disabled From 237e5722bc615c3440d8476a694448074380fa01 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 20 Feb 2017 16:31:36 +0800 Subject: [PATCH 298/399] ipvs: Document sysctl sync_qlen_max and sync_sock_size Document sysctl sync_qlen_max and sync_sock_size based on commit 1c003b1580e2 ("ipvs: wakeup master thread"). Signed-off-by: Hangbin Liu Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 7acaaa65451e..159d70b6dff3 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -217,6 +217,20 @@ sync_retries - INTEGER to protect against loss of sync messages. The range of the sync_retries is from 0 to 3. +sync_qlen_max - UNSIGNED LONG + + Hard limit for queued sync messages that are not sent yet. It + defaults to 1/32 of the memory pages but actually represents + number of messages. It will protect us from allocating large + parts of memory when the sending rate is lower than the queuing + rate. + +sync_sock_size - INTEGER + default 0 + + Configuration of SNDBUF (master) or RCVBUF (slave) socket limit. + Default value is 0 (preserve system defaults). + snat_reroute - BOOLEAN 0 - disabled not 0 - enabled (default) From 24b444155b1e237accb2571ac656cf40c941a2a7 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 20 Feb 2017 16:31:37 +0800 Subject: [PATCH 299/399] ipvs: Document sysctl sync_ports Document sysctl sync_ports based on commit f73181c8288f ("ipvs: add support for sync threads"). Signed-off-by: Hangbin Liu Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 159d70b6dff3..a6feecd467cd 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -231,6 +231,14 @@ sync_sock_size - INTEGER Configuration of SNDBUF (master) or RCVBUF (slave) socket limit. Default value is 0 (preserve system defaults). +sync_ports - INTEGER + default 1 + + The number of threads that master and backup servers can use for + sync traffic. Every thread will use single UDP port, thread 0 will + use the default port 8848 while last thread will use port + 8848+sync_ports-1. + snat_reroute - BOOLEAN 0 - disabled not 0 - enabled (default) From 3c679cba588a46ba81a264673e192bbd3c92455b Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 20 Feb 2017 16:31:38 +0800 Subject: [PATCH 300/399] ipvs: Document sysctl pmtu_disc Document sysctl pmtu_disc based on commit 3654e61137db ("ipvs: add pmtu_disc option to disable IP DF for TUN packets"). Signed-off-by: Hangbin Liu Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index a6feecd467cd..056898685d40 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -175,6 +175,14 @@ nat_icmp_send - BOOLEAN for VS/NAT when the load balancer receives packets from real servers but the connection entries don't exist. +pmtu_disc - BOOLEAN + 0 - disabled + not 0 - enabled (default) + + By default, reject with FRAG_NEEDED all DF packets that exceed + the PMTU, irrespective of the forwarding method. For TUN method + the flag can be disabled to fragment such packets. + secure_tcp - INTEGER 0 - disabled (default) From ce594e9824ab6ed41ac86f672203f1832b87de79 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Thu, 16 Mar 2017 14:32:22 +0800 Subject: [PATCH 301/399] r8152: simply the arguments Replace &tp->napi with napi and tp->netdev with netdev. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 43 +++++++++++++++++++++++++---------------- 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 227e1fdd9228..4b85e95ab754 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1761,6 +1761,7 @@ static int rx_bottom(struct r8152 *tp, int budget) unsigned long flags; struct list_head *cursor, *next, rx_queue; int ret = 0, work_done = 0; + struct napi_struct *napi = &tp->napi; if (!skb_queue_empty(&tp->rx_queue)) { while (work_done < budget) { @@ -1773,7 +1774,7 @@ static int rx_bottom(struct r8152 *tp, int budget) break; pkt_len = skb->len; - napi_gro_receive(&tp->napi, skb); + napi_gro_receive(napi, skb); work_done++; stats->rx_packets++; stats->rx_bytes += pkt_len; @@ -1823,7 +1824,7 @@ static int rx_bottom(struct r8152 *tp, int budget) pkt_len -= CRC_SIZE; rx_data += sizeof(struct rx_desc); - skb = napi_alloc_skb(&tp->napi, pkt_len); + skb = napi_alloc_skb(napi, pkt_len); if (!skb) { stats->rx_dropped++; goto find_next_rx; @@ -1835,7 +1836,7 @@ static int rx_bottom(struct r8152 *tp, int budget) skb->protocol = eth_type_trans(skb, netdev); rtl_rx_vlan_tag(rx_desc, skb); if (work_done < budget) { - napi_gro_receive(&tp->napi, skb); + napi_gro_receive(napi, skb); work_done++; stats->rx_packets++; stats->rx_bytes += pkt_len; @@ -3150,6 +3151,7 @@ static bool rtl8153_in_nway(struct r8152 *tp) static void set_carrier(struct r8152 *tp) { struct net_device *netdev = tp->netdev; + struct napi_struct *napi = &tp->napi; u8 speed; speed = rtl8152_get_speed(tp); @@ -3159,7 +3161,7 @@ static void set_carrier(struct r8152 *tp) tp->rtl_ops.enable(tp); set_bit(RTL8152_SET_RX_MODE, &tp->flags); netif_stop_queue(netdev); - napi_disable(&tp->napi); + napi_disable(napi); netif_carrier_on(netdev); rtl_start_rx(tp); napi_enable(&tp->napi); @@ -3169,9 +3171,9 @@ static void set_carrier(struct r8152 *tp) } else { if (netif_carrier_ok(netdev)) { netif_carrier_off(netdev); - napi_disable(&tp->napi); + napi_disable(napi); tp->rtl_ops.disable(tp); - napi_enable(&tp->napi); + napi_enable(napi); netif_info(tp, link, netdev, "carrier off\n"); } } @@ -3633,11 +3635,13 @@ static int rtl8152_runtime_suspend(struct r8152 *tp) tp->rtl_ops.autosuspend_en(tp, true); if (netif_carrier_ok(netdev)) { - napi_disable(&tp->napi); + struct napi_struct *napi = &tp->napi; + + napi_disable(napi); rtl_stop_rx(tp); rxdy_gated_en(tp, false); ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr); - napi_enable(&tp->napi); + napi_enable(napi); } } @@ -3653,12 +3657,14 @@ static int rtl8152_system_suspend(struct r8152 *tp) netif_device_detach(netdev); if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) { + struct napi_struct *napi = &tp->napi; + clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); - napi_disable(&tp->napi); + napi_disable(napi); cancel_delayed_work_sync(&tp->schedule); tp->rtl_ops.down(tp); - napi_enable(&tp->napi); + napi_enable(napi); } return ret; @@ -3684,35 +3690,38 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) static int rtl8152_resume(struct usb_interface *intf) { struct r8152 *tp = usb_get_intfdata(intf); + struct net_device *netdev = tp->netdev; mutex_lock(&tp->control); if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) { tp->rtl_ops.init(tp); queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0); - netif_device_attach(tp->netdev); + netif_device_attach(netdev); } - if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) { + if (netif_running(netdev) && netdev->flags & IFF_UP) { if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + struct napi_struct *napi = &tp->napi; + tp->rtl_ops.autosuspend_en(tp, false); - napi_disable(&tp->napi); + napi_disable(napi); set_bit(WORK_ENABLE, &tp->flags); - if (netif_carrier_ok(tp->netdev)) + if (netif_carrier_ok(netdev)) rtl_start_rx(tp); - napi_enable(&tp->napi); + napi_enable(napi); clear_bit(SELECTIVE_SUSPEND, &tp->flags); smp_mb__after_atomic(); if (!list_empty(&tp->rx_done)) napi_schedule(&tp->napi); } else { tp->rtl_ops.up(tp); - netif_carrier_off(tp->netdev); + netif_carrier_off(netdev); set_bit(WORK_ENABLE, &tp->flags); } usb_submit_urb(tp->intr_urb, GFP_KERNEL); } else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { - if (tp->netdev->flags & IFF_UP) + if (netdev->flags & IFF_UP) tp->rtl_ops.autosuspend_en(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); } From 3c71006d15fd3a99071a2b20d01de3edabc85767 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:12 +0100 Subject: [PATCH 302/399] ipv4: fib_rules: Check if rule is a default rule Currently, when non-default (custom) FIB rules are used, devices capable of layer 3 offloading flush their tables and let the kernel do the forwarding instead. When these devices' drivers are loaded they register to the FIB notification chain, which lets them know about the existence of any custom FIB rules. This is done by sending a RULE_ADD notification based on the value of 'net->ipv4.fib_has_custom_rules'. This approach is problematic when VRF offload is taken into account, as upon the creation of the first VRF netdev, a l3mdev rule is programmed to direct skbs to the VRF's table. Instead of merely reading the above value and sending a single RULE_ADD notification, we should iterate over all the FIB rules and send a detailed notification for each, thereby allowing offloading drivers to sanitize the rules they don't support and potentially flush their tables. While l3mdev rules are uniquely marked, the default rules are not. Therefore, when they are being notified they might invoke offloading drivers to unnecessarily flush their tables. Solve this by adding an helper to check if a FIB rule is a default rule. Namely, its selector should match all packets and its action should point to the local, main or default tables. As noted by David Ahern, uniquely marking the default rules is insufficient. When using VRFs, it's common to avoid false hits by moving the rule for the local table to just before the main table: Default configuration: $ ip rule show 0: from all lookup local 32766: from all lookup main 32767: from all lookup default Common configuration with VRFs: $ ip rule show 1000: from all lookup [l3mdev-table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/fib_rules.h | 1 + include/net/ip_fib.h | 7 +++++++ net/core/fib_rules.c | 14 ++++++++++++++ net/ipv4/fib_rules.c | 21 +++++++++++++++++++++ 4 files changed, 43 insertions(+) diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 8dbfdf728cd8..1243b9c7694e 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -141,6 +141,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, struct fib_lookup_arg *); int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); +bool fib_rule_matchall(const struct fib_rule *rule); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index d9cee9659978..da6fa7b15558 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -311,6 +311,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp, return err; } +static inline bool fib4_rule_default(const struct fib_rule *rule) +{ + return true; +} + #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); @@ -355,6 +360,8 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, return err; } +bool fib4_rule_default(const struct fib_rule *rule); + #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index b6791d94841d..816e3ccb0ec9 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(~0), }; +bool fib_rule_matchall(const struct fib_rule *rule) +{ + if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || + rule->flags) + return false; + if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) + return false; + if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || + !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) + return false; + return true; +} +EXPORT_SYMBOL_GPL(fib_rule_matchall); + int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) { diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 289210903d58..d531bc94b15e 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -47,6 +47,27 @@ struct fib4_rule { #endif }; +static bool fib4_rule_matchall(const struct fib_rule *rule) +{ + struct fib4_rule *r = container_of(rule, struct fib4_rule, common); + + if (r->dst_len || r->src_len || r->tos) + return false; + return fib_rule_matchall(rule); +} + +bool fib4_rule_default(const struct fib_rule *rule) +{ + if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || + rule->l3mdev) + return false; + if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN && + rule->table != RT_TABLE_DEFAULT) + return false; + return true; +} +EXPORT_SYMBOL_GPL(fib4_rule_default); + int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { From 6a003a5ff29499a94373110202631743663569c6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:13 +0100 Subject: [PATCH 303/399] ipv4: fib_rules: Add notifier info to FIB rules notifications Whenever a FIB rule is added or removed, a notification is sent in the FIB notification chain. However, listeners don't have a way to tell which rule was added or removed. This is problematic as we would like to give listeners the ability to decide which action to execute based on the notified rule. Specifically, offloading drivers should be able to determine if they support the reflection of the notified FIB rule and flush their LPM tables in case they don't. Do that by adding a notifier info to these notifications and embed the common FIB rule struct in it. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/ip_fib.h | 5 +++++ net/ipv4/fib_rules.c | 13 ++++++++----- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index da6fa7b15558..272e62e139e0 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -213,6 +213,11 @@ struct fib_entry_notifier_info { u32 tb_id; }; +struct fib_rule_notifier_info { + struct fib_notifier_info info; /* must be first */ + struct fib_rule *rule; +}; + struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index d531bc94b15e..310d24a2e097 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -186,11 +186,14 @@ static struct fib_table *fib_empty_table(struct net *net) } static int call_fib_rule_notifiers(struct net *net, - enum fib_event_type event_type) + enum fib_event_type event_type, + struct fib_rule *rule) { - struct fib_notifier_info info; + struct fib_rule_notifier_info info = { + .rule = rule, + }; - return call_fib_notifiers(net, event_type, &info); + return call_fib_notifiers(net, event_type, &info.info); } void fib_rules_notify(struct net *net, struct notifier_block *nb) @@ -257,7 +260,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule); err = 0; errout: @@ -279,7 +282,7 @@ static int fib4_rule_delete(struct fib_rule *rule) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule); errout: return err; } From 5d7bfd141924a5ece21eb612ad3c56612f041c1e Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:14 +0100 Subject: [PATCH 304/399] ipv4: fib_rules: Dump FIB rules when registering FIB notifier In commit c3852ef7f2f8 ("ipv4: fib: Replay events when registering FIB notifier") we dumped the FIB tables and replayed the events to the passed notification block. However, we merely sent a RULE_ADD notification in case custom rules were in use. As explained in previous patches, this approach won't work anymore. Instead, we should notify the caller about all the FIB rules and let it act accordingly. Upon registration to the FIB notification chain, replay a RULE_ADD notification for each programmed FIB rule, custom or not. The integrity of the dump is ensured by the mechanism introduced in the above mentioned commit. Prevent regressions by making sure current listeners correctly sanitize the notified rules. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 13 ++++++++++++- drivers/net/ethernet/rocker/rocker_main.c | 17 +++++++++++++++-- net/ipv4/fib_rules.c | 19 ++++++++++++++++--- 3 files changed, 43 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 80345a1ddf17..9ab41c47c263 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -45,6 +45,7 @@ #include #include #include +#include #include "spectrum.h" #include "core.h" @@ -2514,6 +2515,7 @@ struct mlxsw_sp_fib_event_work { struct work_struct work; union { struct fib_entry_notifier_info fen_info; + struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; }; struct mlxsw_sp *mlxsw_sp; @@ -2525,6 +2527,7 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) struct mlxsw_sp_fib_event_work *fib_work = container_of(work, struct mlxsw_sp_fib_event_work, work); struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; + struct fib_rule *rule; bool replace, append; int err; @@ -2548,7 +2551,10 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) break; case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - mlxsw_sp_router_fib4_abort(mlxsw_sp); + rule = fib_work->fr_info.rule; + if (!fib4_rule_default(rule)) + mlxsw_sp_router_fib4_abort(mlxsw_sp); + fib_rule_put(rule); break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: @@ -2591,6 +2597,11 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, */ fib_info_hold(fib_work->fen_info.fi); break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info)); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index b712ec23075b..bab13613b138 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -2175,7 +2176,10 @@ static const struct switchdev_ops rocker_port_switchdev_ops = { struct rocker_fib_event_work { struct work_struct work; - struct fib_entry_notifier_info fen_info; + union { + struct fib_entry_notifier_info fen_info; + struct fib_rule_notifier_info fr_info; + }; struct rocker *rocker; unsigned long event; }; @@ -2185,6 +2189,7 @@ static void rocker_router_fib_event_work(struct work_struct *work) struct rocker_fib_event_work *fib_work = container_of(work, struct rocker_fib_event_work, work); struct rocker *rocker = fib_work->rocker; + struct fib_rule *rule; int err; /* Protect internal structures from changes */ @@ -2202,7 +2207,10 @@ static void rocker_router_fib_event_work(struct work_struct *work) break; case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - rocker_world_fib4_abort(rocker); + rule = fib_work->fr_info.rule; + if (!fib4_rule_default(rule)) + rocker_world_fib4_abort(rocker); + fib_rule_put(rule); break; } rtnl_unlock(); @@ -2233,6 +2241,11 @@ static int rocker_router_fib_event(struct notifier_block *nb, */ fib_info_hold(fib_work->fen_info.fi); break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; } queue_work(rocker->rocker_owq, &fib_work->work); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 310d24a2e097..778ecf977eb2 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -185,6 +185,17 @@ static struct fib_table *fib_empty_table(struct net *net) return NULL; } +static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_rule *rule) +{ + struct fib_rule_notifier_info info = { + .rule = rule, + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + static int call_fib_rule_notifiers(struct net *net, enum fib_event_type event_type, struct fib_rule *rule) @@ -196,12 +207,14 @@ static int call_fib_rule_notifiers(struct net *net, return call_fib_notifiers(net, event_type, &info.info); } +/* Called with rcu_read_lock() */ void fib_rules_notify(struct net *net, struct notifier_block *nb) { - struct fib_notifier_info info; + struct fib_rules_ops *ops = net->ipv4.rules_ops; + struct fib_rule *rule; - if (net->ipv4.fib_has_custom_rules) - call_fib_notifier(nb, net, FIB_EVENT_RULE_ADD, &info); + list_for_each_entry_rcu(rule, &ops->rules_list, list) + call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule); } static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { From fdeea7be88b12742bfd50d9e19a06c0d2e702400 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:15 +0100 Subject: [PATCH 305/399] net: vrf: Set slave's private flag before linking Allow listeners of the subsequent CHANGEUPPER notification to retrieve the VRF's table ID by calling l3mdev_fib_table() with the slave netdev. Without this change, the netdev won't be considered an L3 slave and the function would return 0. This is consistent with other master device such as bridge and bond that set the slave's private flag before linking. It also makes do_vrf_{add,del}_slave() symmetric. Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/vrf.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index fea687f35b5a..7f28021d9d93 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -747,14 +747,18 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) { int ret; + port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL); if (ret < 0) - return ret; + goto err; - port_dev->priv_flags |= IFF_L3MDEV_SLAVE; cycle_netdev(port_dev); return 0; + +err: + port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) From 57837885e3c74e42596a8d8c3e6831be1c0a7974 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:16 +0100 Subject: [PATCH 306/399] mlxsw: spectrum_router: Associate RIFs with correct VR When a router interface (RIF) is created due to a netdev being enslaved to a VRF master, then it should be associated with the appropriate virtual router (VR) and not the default one. If netdev is a VRF slave, lookup the VR based on the VRF's table ID. Otherwise default to the MAIN table. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 9ab41c47c263..5aad0aef1ed3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -46,6 +46,7 @@ #include #include #include +#include #include "spectrum.h" #include "core.h" @@ -2762,6 +2763,7 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, struct net_device *l3_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + u32 tb_id = l3mdev_fib_table(l3_dev); struct mlxsw_sp_vr *vr; struct mlxsw_sp_fid *f; struct mlxsw_sp_rif *r; @@ -2772,7 +2774,7 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, if (rif == MLXSW_SP_INVALID_RIF) return ERR_PTR(-ERANGE); - vr = mlxsw_sp_vr_get(mlxsw_sp, RT_TABLE_MAIN); + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); if (IS_ERR(vr)) return ERR_CAST(vr); @@ -3010,6 +3012,7 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, struct net_device *l3_dev, struct mlxsw_sp_fid *f) { + u32 tb_id = l3mdev_fib_table(l3_dev); struct mlxsw_sp_vr *vr; struct mlxsw_sp_rif *r; u16 rif; @@ -3019,7 +3022,7 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, if (rif == MLXSW_SP_INVALID_RIF) return -ERANGE; - vr = mlxsw_sp_vr_get(mlxsw_sp, RT_TABLE_MAIN); + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); if (IS_ERR(vr)) return PTR_ERR(vr); From 9db032bb1e8eed0721884c01a6c87f55f3d400fa Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:17 +0100 Subject: [PATCH 307/399] mlxsw: spectrum_router: Don't destroy RIF if L3 slave We usually destroy the netdev's router interface (RIF) when the last IP address is removed from it. However, we shouldn't do that if it's enslaved to an L3 master device. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 5aad0aef1ed3..91ec62a2db48 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -2660,7 +2661,7 @@ static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, return true; return false; case NETDEV_DOWN: - if (r && !in_dev->ifa_list) + if (r && !in_dev->ifa_list && !netif_is_l3_slave(r->dev)) return true; /* It is possible we already removed the RIF ourselves * if it was assigned to a netdev that is now a bridge From 7179eb5acd59d64cb8bef2d8788af8e9647f6986 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:18 +0100 Subject: [PATCH 308/399] mlxsw: spectrum_router: Add support for VRFs Allow port netdevs, LAG and VLAN devices stacked on top of these to be enslaved to a VRF master device. Upon enslavement, create a router interface (RIF) for the enslaved netdev and associate it with a virtual router (VR) based on the VRF's table ID. If a RIF already exists for the netdev (f.e., due to the existence of an IP address), then it's deleted and a new one is created with the appropriate VR binding. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 19 +++++++-- .../net/ethernet/mellanox/mlxsw/spectrum.h | 4 ++ .../ethernet/mellanox/mlxsw/spectrum_router.c | 41 +++++++++++++++++++ 3 files changed, 61 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 475499b6c989..659df3225a24 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3951,7 +3951,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, upper_dev = info->upper_dev; if (!is_vlan_dev(upper_dev) && !netif_is_lag_master(upper_dev) && - !netif_is_bridge_master(upper_dev)) + !netif_is_bridge_master(upper_dev) && + !netif_is_l3_master(upper_dev)) return -EINVAL; if (!info->linking) break; @@ -3991,6 +3992,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, else mlxsw_sp_port_lag_leave(mlxsw_sp_port, upper_dev); + } else if (netif_is_l3_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_port_vrf_join(mlxsw_sp_port); + else + mlxsw_sp_port_vrf_leave(mlxsw_sp_port); } else { err = -EINVAL; WARN_ON(1); @@ -4353,14 +4359,16 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, switch (event) { case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; - if (!netif_is_bridge_master(upper_dev)) + if (!netif_is_bridge_master(upper_dev) && + !netif_is_l3_master(upper_dev)) return -EINVAL; if (!info->linking) break; /* We can't have multiple VLAN interfaces configured on * the same port and being members in the same bridge. */ - if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port, + if (netif_is_bridge_master(upper_dev) && + !mlxsw_sp_port_master_bridge_check(mlxsw_sp_port, upper_dev)) return -EINVAL; break; @@ -4372,6 +4380,11 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, upper_dev); else mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport); + } else if (netif_is_l3_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_vport_vrf_join(mlxsw_sp_vport); + else + mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport); } else { err = -EINVAL; WARN_ON(1); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 5502232b06cf..60004d97e631 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -578,6 +578,10 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused, unsigned long event, void *ptr); void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *r); +int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport); +void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport); +int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port); +void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port); int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count); void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 91ec62a2db48..e26268805fcc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3226,6 +3226,47 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) return err; } +int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + struct net_device *dev = mlxsw_sp_vport->dev; + + /* In case vPort already has a RIF, then we need to drop it. + * A new one will be created using the VRF's VR. + */ + if (f && f->r) + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); + + return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, dev); +} + +void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); +} + +int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1); + if (WARN_ON(!mlxsw_sp_vport)) + return -EINVAL; + + return mlxsw_sp_vport_vrf_join(mlxsw_sp_vport); +} + +void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1); + if (WARN_ON(!mlxsw_sp_vport)) + return; + + mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport); +} + static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) { struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb); From 3d70e458be3af878216f8c97fb4c0926cc003e31 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:19 +0100 Subject: [PATCH 309/399] mlxsw: spectrum_router: Add support for VRFs on top of bridges In a similar fashion to the previous patch, allow bridges and VLAN devices on top of bridges to be enslaved to a VRF master device. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 52 ++++++++++++++++++- .../net/ethernet/mellanox/mlxsw/spectrum.h | 4 ++ .../ethernet/mellanox/mlxsw/spectrum_router.c | 26 ++++++++++ 3 files changed, 81 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 659df3225a24..28019f8b70f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4111,7 +4111,7 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, switch (event) { case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; - if (!is_vlan_dev(upper_dev)) + if (!is_vlan_dev(upper_dev) && !netif_is_l3_master(upper_dev)) return -EINVAL; if (is_vlan_dev(upper_dev) && br_dev != mlxsw_sp->master_bridge.dev) @@ -4126,6 +4126,12 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, else mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev); + } else if (netif_is_l3_master(upper_dev)) { + if (info->linking) + err = mlxsw_sp_bridge_vrf_join(mlxsw_sp, + br_dev); + else + mlxsw_sp_bridge_vrf_leave(mlxsw_sp, br_dev); } else { err = -EINVAL; WARN_ON(1); @@ -4415,6 +4421,47 @@ static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev, return 0; } +static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev, + unsigned long event, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct mlxsw_sp *mlxsw_sp; + int err = 0; + + mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); + if (!mlxsw_sp) + return 0; + + info = ptr; + + switch (event) { + case NETDEV_PRECHANGEUPPER: + /* VLAN devices are only allowed on top of the + * VLAN-aware bridge. + */ + if (WARN_ON(vlan_dev_real_dev(vlan_dev) != + mlxsw_sp->master_bridge.dev)) + return -EINVAL; + if (!netif_is_l3_master(info->upper_dev)) + return -EINVAL; + break; + case NETDEV_CHANGEUPPER: + if (netif_is_l3_master(info->upper_dev)) { + if (info->linking) + err = mlxsw_sp_bridge_vrf_join(mlxsw_sp, + vlan_dev); + else + mlxsw_sp_bridge_vrf_leave(mlxsw_sp, vlan_dev); + } else { + err = -EINVAL; + WARN_ON(1); + } + break; + } + + return err; +} + static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev, unsigned long event, void *ptr) { @@ -4427,6 +4474,9 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev, else if (netif_is_lag_master(real_dev)) return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr, vid); + else if (netif_is_bridge_master(real_dev)) + return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, event, + ptr); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 60004d97e631..0e223f6983c5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -582,6 +582,10 @@ int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport); void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport); int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port); void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port); +int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev); +void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev); int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count); void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index e26268805fcc..c89f4b4d70b1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3267,6 +3267,32 @@ void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port) mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport); } +int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return -EINVAL; + + if (f->r) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + + return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); +} + +void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return; + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); +} + static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) { struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb); From c7f6e6658b771c64a07b69852ac4362a8e781ab6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 16 Mar 2017 09:08:20 +0100 Subject: [PATCH 310/399] mlxsw: spectrum_router: Don't abort on l3mdev rules Now that port netdevs can be enslaved to a VRF master we need to make sure the device's routing tables won't be flushed upon the insertion of a l3mdev rule. Note that we assume the notified l3mdev rule is a simple rule as used by the VRF master. We don't check for the presence of other selectors such as 'iif' and 'oif'. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c89f4b4d70b1..488bc1fd7868 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2554,7 +2554,7 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: rule = fib_work->fr_info.rule; - if (!fib4_rule_default(rule)) + if (!fib4_rule_default(rule) && !rule->l3mdev) mlxsw_sp_router_fib4_abort(mlxsw_sp); fib_rule_put(rule); break; From 9768b45ceb0bc7bdee61837afad331dd6bf7977f Mon Sep 17 00:00:00 2001 From: Jane Li Date: Thu, 16 Mar 2017 16:22:28 +0800 Subject: [PATCH 311/399] net: mvneta: support suspend and resume Add basic support for handling suspend and resume. Signed-off-by: Jane Li Reviewed-by: Jisheng Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 61 +++++++++++++++++++++++++-- 1 file changed, 57 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 61dd4462411c..aebbc5399a06 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -431,6 +431,7 @@ struct mvneta_port { /* Flags for special SoC configurations */ bool neta_armada3700; u16 rx_offset_correction; + const struct mbus_dram_target_info *dram_target_info; }; /* The mvneta_tx_desc and mvneta_rx_desc structures describe the @@ -4118,7 +4119,6 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) /* Device initialization routine */ static int mvneta_probe(struct platform_device *pdev) { - const struct mbus_dram_target_info *dram_target_info; struct resource *res; struct device_node *dn = pdev->dev.of_node; struct device_node *phy_node; @@ -4267,13 +4267,13 @@ static int mvneta_probe(struct platform_device *pdev) pp->tx_csum_limit = tx_csum_limit; - dram_target_info = mv_mbus_dram_info(); + pp->dram_target_info = mv_mbus_dram_info(); /* Armada3700 requires setting default configuration of Mbus * windows, however without using filled mbus_dram_target_info * structure. */ - if (dram_target_info || pp->neta_armada3700) - mvneta_conf_mbus_windows(pp, dram_target_info); + if (pp->dram_target_info || pp->neta_armada3700) + mvneta_conf_mbus_windows(pp, pp->dram_target_info); pp->tx_ring_size = MVNETA_MAX_TXD; pp->rx_ring_size = MVNETA_MAX_RXD; @@ -4405,6 +4405,58 @@ static int mvneta_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int mvneta_suspend(struct device *device) +{ + struct net_device *dev = dev_get_drvdata(device); + struct mvneta_port *pp = netdev_priv(dev); + + if (netif_running(dev)) + mvneta_stop(dev); + netif_device_detach(dev); + clk_disable_unprepare(pp->clk_bus); + clk_disable_unprepare(pp->clk); + return 0; +} + +static int mvneta_resume(struct device *device) +{ + struct platform_device *pdev = to_platform_device(device); + struct net_device *dev = dev_get_drvdata(device); + struct mvneta_port *pp = netdev_priv(dev); + int err; + + clk_prepare_enable(pp->clk); + if (!IS_ERR(pp->clk_bus)) + clk_prepare_enable(pp->clk_bus); + if (pp->dram_target_info || pp->neta_armada3700) + mvneta_conf_mbus_windows(pp, pp->dram_target_info); + if (pp->bm_priv) { + err = mvneta_bm_port_init(pdev, pp); + if (err < 0) { + dev_info(&pdev->dev, "use SW buffer management\n"); + pp->bm_priv = NULL; + } + } + mvneta_defaults_set(pp); + err = mvneta_port_power_up(pp, pp->phy_interface); + if (err < 0) { + dev_err(device, "can't power up port\n"); + return err; + } + + if (pp->use_inband_status) + mvneta_fixed_link_update(pp, dev->phydev); + + netif_device_attach(dev); + if (netif_running(dev)) + mvneta_open(dev); + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(mvneta_pm_ops, mvneta_suspend, mvneta_resume); + static const struct of_device_id mvneta_match[] = { { .compatible = "marvell,armada-370-neta" }, { .compatible = "marvell,armada-xp-neta" }, @@ -4419,6 +4471,7 @@ static struct platform_driver mvneta_driver = { .driver = { .name = MVNETA_DRIVER_NAME, .of_match_table = mvneta_match, + .pm = &mvneta_pm_ops, }, }; From b79df0fc60c5b459ac7ba60c03467d672745954b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 16 Mar 2017 10:18:02 +0100 Subject: [PATCH 312/399] isdn: hardware: mISDN: Remove reference to CONFIG_8xx CONFIG_8xx is deprecated and should soon be removed in favor of CONFIG_PPC_8xx. Anyway, hfc_multi_8xx.h only uses 8xx I/O ports which are linked to the CPM1 communication processor included in the 8xx rather than the 8xx itself. This patch therefore makes it dependent on CONFIG_CPM1 instead, like several other drivers. Signed-off-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/isdn/hardware/mISDN/Kconfig | 6 +++--- drivers/isdn/hardware/mISDN/hfc_multi_8xx.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/Kconfig b/drivers/isdn/hardware/mISDN/Kconfig index 09df54fc1fef..fda912b0833f 100644 --- a/drivers/isdn/hardware/mISDN/Kconfig +++ b/drivers/isdn/hardware/mISDN/Kconfig @@ -13,7 +13,7 @@ config MISDN_HFCPCI config MISDN_HFCMULTI tristate "Support for HFC multiport cards (HFC-4S/8S/E1)" - depends on PCI || 8xx + depends on PCI || CPM1 depends on MISDN help Enable support for cards with Cologne Chip AG's HFC multiport @@ -27,8 +27,8 @@ config MISDN_HFCMULTI_8xx bool "Support for XHFC embedded board in HFC multiport driver" depends on MISDN depends on MISDN_HFCMULTI - depends on 8xx - default 8xx + depends on CPM1 + default CPM1 help Enable support for the XHFC embedded solution from Speech Design. diff --git a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h index 0eafe9f04fca..8a254747768e 100644 --- a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h +++ b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h @@ -6,7 +6,7 @@ * */ -#include +#include /* Change this to the value used by your board */ #ifndef IMAP_ADDR From 01ac2994c0d566f2e816ef0c88ab8e4f8b1b3ed1 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 16 Mar 2017 10:18:04 +0100 Subject: [PATCH 313/399] net: ethernet: fs_enet: Remove useless includes CONFIG_8xx is being deprecated. Since the includes dependent on CONFIG_8xx are useless, just drop them. Signed-off-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fs_enet/mac-fec.c | 6 ------ drivers/net/ethernet/freescale/fs_enet/mac-scc.c | 6 ------ 2 files changed, 12 deletions(-) diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index db9c0bcf54cd..1fc27c97e3b2 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -38,12 +38,6 @@ #include #include -#ifdef CONFIG_8xx -#include -#include -#include -#endif - #include "fs_enet.h" #include "fec.h" diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c index 96d44cf44fe0..64300ac13e02 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c @@ -37,12 +37,6 @@ #include #include -#ifdef CONFIG_8xx -#include -#include -#include -#endif - #include "fs_enet.h" /*************************************************/ From 2f771399a3a2c371c140ff33544a583c6fbc5fd9 Mon Sep 17 00:00:00 2001 From: Steve Lin Date: Thu, 16 Mar 2017 11:48:58 -0400 Subject: [PATCH 314/399] net: ethernet: bgmac: Allow MAC address to be specified in DTB Allows the BCMA version of the bgmac driver to obtain MAC address from the device tree. If no MAC address is specified there, then the previous behavior (obtaining MAC address from SPROM) is used. Signed-off-by: Steve Lin Reviewed-by: Florian Fainelli Acked-by: Jon Mason Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bgmac-bcma.c | 39 +++++++++++++--------- 1 file changed, 23 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index cf15b7e2929c..6322594ab260 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "bgmac.h" static inline bool bgmac_is_bcm4707_family(struct bcma_device *core) @@ -114,7 +115,7 @@ static int bgmac_probe(struct bcma_device *core) struct ssb_sprom *sprom = &core->bus->sprom; struct mii_bus *mii_bus; struct bgmac *bgmac; - u8 *mac; + const u8 *mac = NULL; int err; bgmac = bgmac_alloc(&core->dev); @@ -127,21 +128,27 @@ static int bgmac_probe(struct bcma_device *core) bcma_set_drvdata(core, bgmac); - switch (core->core_unit) { - case 0: - mac = sprom->et0mac; - break; - case 1: - mac = sprom->et1mac; - break; - case 2: - mac = sprom->et2mac; - break; - default: - dev_err(bgmac->dev, "Unsupported core_unit %d\n", - core->core_unit); - err = -ENOTSUPP; - goto err; + if (bgmac->dev->of_node) + mac = of_get_mac_address(bgmac->dev->of_node); + + /* If no MAC address assigned via device tree, check SPROM */ + if (!mac) { + switch (core->core_unit) { + case 0: + mac = sprom->et0mac; + break; + case 1: + mac = sprom->et1mac; + break; + case 2: + mac = sprom->et2mac; + break; + default: + dev_err(bgmac->dev, "Unsupported core_unit %d\n", + core->core_unit); + err = -ENOTSUPP; + goto err; + } } ether_addr_copy(bgmac->net_dev->dev_addr, mac); From 4dba87b07394ebf9fa4693d90f4074bda977449b Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 16 Mar 2017 12:53:41 +0200 Subject: [PATCH 315/399] net/sched: act_ife: Staticfy find_decode_metaid() As it's used only on that file. Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- net/sched/act_ife.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 71e7ff22f7c9..c75ea5c9102c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -603,8 +603,8 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, return -1; } -int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, - u16 metaid, u16 mlen, void *mdata) +static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, + u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; From a5e6a3b0222fb19eaae424226533eadb0be20e93 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 16 Mar 2017 12:53:42 +0200 Subject: [PATCH 316/399] net/sched: fq_codel: Avoid set-but-unused variable The code introduced by commit 2ccccf5fb43f ("net_sched: update hierarchical backlog too") only sets prev_backlog in fq_codel_dequeue() but not using that anywhere, remove that setting. Cc: Cong Wang Signed-off-by: Or Gerlitz Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/sch_fq_codel.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9f3a884d1590..097bbe9857a5 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -288,7 +288,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct fq_codel_flow *flow; struct list_head *head; u32 prev_drop_count, prev_ecn_mark; - unsigned int prev_backlog; begin: head = &q->new_flows; @@ -307,7 +306,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) prev_drop_count = q->cstats.drop_count; prev_ecn_mark = q->cstats.ecn_mark; - prev_backlog = sch->qstats.backlog; skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, From 5080f39e8c72e01cf37e8359023e7018e2a4901e Mon Sep 17 00:00:00 2001 From: Nik Unger Date: Mon, 13 Mar 2017 10:16:58 -0700 Subject: [PATCH 317/399] netem: apply correct delay when rate throttling I recently reported on the netem list that iperf network benchmarks show unexpected results when a bandwidth throttling rate has been configured for netem. Specifically: 1) The measured link bandwidth *increases* when a higher delay is added 2) The measured link bandwidth appears higher than the specified limit 3) The measured link bandwidth for the same very slow settings varies significantly across machines The issue can be reproduced by using tc to configure netem with a 512kbit rate and various (none, 1us, 50ms, 100ms, 200ms) delays on a veth pair between network namespaces, and then using iperf (or any other network benchmarking tool) to test throughput. Complete detailed instructions are in the original email chain here: https://lists.linuxfoundation.org/pipermail/netem/2017-February/001672.html There appear to be two underlying bugs causing these effects: - The first issue causes long delays when the rate is slow and no delay is configured (e.g., "rate 512kbit"). This is because SKBs are not orphaned when no delay is configured, so orphaning does not occur until *after* the rate-induced delay has been applied. For this reason, adding a tiny delay (e.g., "rate 512kbit delay 1us") dramatically increases the measured bandwidth. - The second issue is that rate-induced delays are not correctly applied, allowing SKB delays to occur in parallel. The indended approach is to compute the delay for an SKB and to add this delay to the end of the current queue. However, the code does not detect existing SKBs in the queue due to improperly testing sch->q.qlen, which is nonzero even when packets exist only in the rbtree. Consequently, new SKBs do not wait for the current queue to empty. When packet delays vary significantly (e.g., if packet sizes are different), then this also causes unintended reordering. I modified the code to expect a delay (and orphan the SKB) when a rate is configured. I also added some defensive tests that correctly find the latest scheduled delivery time, even if it is (unexpectedly) for a packet in sch->q. I have tested these changes on the latest kernel (4.11.0-rc1+) and the iperf / ping test results are as expected. Signed-off-by: Nik Unger Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/sched/sch_netem.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index c8bb62a1e744..94b4928ad413 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -462,7 +462,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) */ - if (q->latency || q->jitter) + if (q->latency || q->jitter || q->rate) skb_orphan_partial(skb); /* @@ -530,21 +530,31 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, now = psched_get_time(); if (q->rate) { - struct sk_buff *last; + struct netem_skb_cb *last = NULL; + + if (sch->q.tail) + last = netem_skb_cb(sch->q.tail); + if (q->t_root.rb_node) { + struct sk_buff *t_skb; + struct netem_skb_cb *t_last; + + t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + t_last = netem_skb_cb(t_skb); + if (!last || + t_last->time_to_send > last->time_to_send) { + last = t_last; + } + } - if (sch->q.qlen) - last = sch->q.tail; - else - last = netem_rb_to_skb(rb_last(&q->t_root)); if (last) { /* * Last packet in queue is reference point (now), * calculate this time bonus and subtract * from delay. */ - delay -= netem_skb_cb(last)->time_to_send - now; + delay -= last->time_to_send - now; delay = max_t(psched_tdiff_t, 0, delay); - now = netem_skb_cb(last)->time_to_send; + now = last->time_to_send; } delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); From b229487b36a418c755eab6485aae74582d52d4a4 Mon Sep 17 00:00:00 2001 From: Rick Farrington Date: Mon, 13 Mar 2017 12:07:32 -0700 Subject: [PATCH 318/399] liquidio: remove/replace invalid code Remove invalid call to dma_sync_single_for_cpu() because previous DMA allocation was coherent--not streaming. Remove code that references fields in struct list_head; replace it with calls to list_empty() and list_first_entry(). Also, add comment to clarify complicated if statement. Signed-off-by: Rick Farrington Signed-off-by: Felix Manlunas Signed-off-by: Derek Chickles Signed-off-by: David S. Miller --- .../cavium/liquidio/response_manager.c | 26 +++++++------------ 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c index 2fbaae96b505..1d987d7cd7bd 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c @@ -69,41 +69,35 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev, int resp_to_process = MAX_ORD_REQS_TO_PROCESS; u32 status; u64 status64; - struct octeon_instr_rdp *rdp; - u64 rptr; ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST]; do { spin_lock_bh(&ordered_sc_list->lock); - if (ordered_sc_list->head.next == &ordered_sc_list->head) { + if (list_empty(&ordered_sc_list->head)) { spin_unlock_bh(&ordered_sc_list->lock); return 1; } - sc = (struct octeon_soft_command *)ordered_sc_list-> - head.next; - if (OCTEON_CN23XX_PF(octeon_dev) || - OCTEON_CN23XX_VF(octeon_dev)) { - rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd3.rdp; - rptr = sc->cmd.cmd3.rptr; - } else { - rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp; - rptr = sc->cmd.cmd2.rptr; - } + sc = list_first_entry(&ordered_sc_list->head, + struct octeon_soft_command, node); status = OCTEON_REQUEST_PENDING; /* check if octeon has finished DMA'ing a response * to where rptr is pointing to */ - dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev, - rptr, rdp->rlen, - DMA_FROM_DEVICE); status64 = *sc->status_word; if (status64 != COMPLETION_WORD_INIT) { + /* This logic ensures that all 64b have been written. + * 1. check byte 0 for non-FF + * 2. if non-FF, then swap result from BE to host order + * 3. check byte 7 (swapped to 0) for non-FF + * 4. if non-FF, use the low 32-bit status code + * 5. if either byte 0 or byte 7 is FF, don't use status + */ if ((status64 & 0xff) != 0xff) { octeon_swap_8B_data(&status64, 1); if (((status64 & 0xff) != 0xff)) { From 0c88a76148432097aa9859bcd08ad07c05507725 Mon Sep 17 00:00:00 2001 From: Rick Farrington Date: Mon, 13 Mar 2017 12:58:04 -0700 Subject: [PATCH 319/399] liquidio: use meaningful names for IRQs All IRQs owned by the PF and VF drivers share the same nondescript name "octeon"; this makes it difficult to setup interrupt affinity. Change the IRQ names to reflect their specific purpose: LiquidIO--- Examples: LiquidIO0-pf0-rxtx-3 LiquidIO1-vf1-rxtx-0 LiquidIO0-pf0-aux We cannot use netdev->name for naming the IRQs because: 1. Early during init, the PF and VF drivers require interrupts to send/receive control data from the NIC firmware; so the PF and VF must request IRQs long before the netdev struct is registered. 2. The IRQ name can only be specified at the time it is requested. It cannot be changed after that. Signed-off-by: Rick Farrington Signed-off-by: Felix Manlunas Signed-off-by: Satanand Burla Signed-off-by: David S. Miller --- .../net/ethernet/cavium/liquidio/lio_main.c | 72 ++++++++++++++++--- .../ethernet/cavium/liquidio/lio_vf_main.c | 37 ++++++++-- .../cavium/liquidio/liquidio_common.h | 5 ++ .../ethernet/cavium/liquidio/octeon_device.h | 3 + 4 files changed, 101 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index ca529a78bca7..761061b96948 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1084,16 +1084,35 @@ static int octeon_setup_interrupt(struct octeon_device *oct) int i; int num_ioq_vectors; int num_alloc_ioq_vectors; + char *queue_irq_names = NULL; + char *aux_irq_name = NULL; if (OCTEON_CN23XX_PF(oct) && oct->msix_on) { oct->num_msix_irqs = oct->sriov_info.num_pf_rings; /* one non ioq interrupt for handling sli_mac_pf_int_sum */ oct->num_msix_irqs += 1; + /* allocate storage for the names assigned to each irq */ + oct->irq_name_storage = + kcalloc((MAX_IOQ_INTERRUPTS_PER_PF + 1), INTRNAMSIZ, + GFP_KERNEL); + if (!oct->irq_name_storage) { + dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n"); + return -ENOMEM; + } + + queue_irq_names = oct->irq_name_storage; + aux_irq_name = &queue_irq_names + [IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)]; + oct->msix_entries = kcalloc( oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL); - if (!oct->msix_entries) - return 1; + if (!oct->msix_entries) { + dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n"); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return -ENOMEM; + } msix_entries = (struct msix_entry *)oct->msix_entries; /*Assumption is that pf msix vectors start from pf srn to pf to @@ -1111,7 +1130,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct) dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n"); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return num_alloc_ioq_vectors; } dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n"); @@ -1119,9 +1140,12 @@ static int octeon_setup_interrupt(struct octeon_device *oct) /** For PF, there is one non-ioq interrupt handler */ num_ioq_vectors -= 1; + + snprintf(aux_irq_name, INTRNAMSIZ, + "LiquidIO%u-pf%u-aux", oct->octeon_id, oct->pf_num); irqret = request_irq(msix_entries[num_ioq_vectors].vector, - liquidio_legacy_intr_handler, 0, "octeon", - oct); + liquidio_legacy_intr_handler, 0, + aux_irq_name, oct); if (irqret) { dev_err(&oct->pci_dev->dev, "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", @@ -1129,13 +1153,20 @@ static int octeon_setup_interrupt(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } for (i = 0; i < num_ioq_vectors; i++) { + snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ, + "LiquidIO%u-pf%u-rxtx-%u", + oct->octeon_id, oct->pf_num, i); + irqret = request_irq(msix_entries[i].vector, liquidio_msix_intr_handler, 0, - "octeon", &oct->ioq_vector[i]); + &queue_irq_names[IRQ_NAME_OFF(i)], + &oct->ioq_vector[i]); if (irqret) { dev_err(&oct->pci_dev->dev, "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", @@ -1155,7 +1186,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } oct->ioq_vector[i].vector = msix_entries[i].vector; /* assign the cpu mask for this msix interrupt vector */ @@ -1173,15 +1206,29 @@ static int octeon_setup_interrupt(struct octeon_device *oct) else oct->flags |= LIO_FLAG_MSI_ENABLED; + /* allocate storage for the names assigned to the irq */ + oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL); + if (!oct->irq_name_storage) + return -ENOMEM; + + queue_irq_names = oct->irq_name_storage; + + snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ, + "LiquidIO%u-pf%u-rxtx-%u", + oct->octeon_id, oct->pf_num, 0); + irqret = request_irq(oct->pci_dev->irq, - liquidio_legacy_intr_handler, IRQF_SHARED, - "octeon", oct); + liquidio_legacy_intr_handler, + IRQF_SHARED, + &queue_irq_names[IRQ_NAME_OFF(0)], oct); if (irqret) { if (oct->flags & LIO_FLAG_MSI_ENABLED) pci_disable_msi(oct->pci_dev); dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n", irqret); - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } } return 0; @@ -1449,6 +1496,9 @@ static void octeon_destroy_resources(struct octeon_device *oct) pci_disable_msi(oct->pci_dev); } + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + /* fallthrough */ case OCT_DEV_MSIX_ALLOC_VECTOR_DONE: if (OCTEON_CN23XX_PF(oct)) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 7b83be4ce1fe..5ec5c24cee5d 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -780,6 +780,7 @@ liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev) static int octeon_setup_interrupt(struct octeon_device *oct) { struct msix_entry *msix_entries; + char *queue_irq_names = NULL; int num_alloc_ioq_vectors; int num_ioq_vectors; int irqret; @@ -788,10 +789,25 @@ static int octeon_setup_interrupt(struct octeon_device *oct) if (oct->msix_on) { oct->num_msix_irqs = oct->sriov_info.rings_per_vf; + /* allocate storage for the names assigned to each irq */ + oct->irq_name_storage = + kcalloc(MAX_IOQ_INTERRUPTS_PER_VF, INTRNAMSIZ, + GFP_KERNEL); + if (!oct->irq_name_storage) { + dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n"); + return -ENOMEM; + } + + queue_irq_names = oct->irq_name_storage; + oct->msix_entries = kcalloc( oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL); - if (!oct->msix_entries) - return 1; + if (!oct->msix_entries) { + dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n"); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return -ENOMEM; + } msix_entries = (struct msix_entry *)oct->msix_entries; @@ -805,16 +821,23 @@ static int octeon_setup_interrupt(struct octeon_device *oct) dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n"); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return num_alloc_ioq_vectors; } dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n"); num_ioq_vectors = oct->num_msix_irqs; for (i = 0; i < num_ioq_vectors; i++) { + snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ, + "LiquidIO%u-vf%u-rxtx-%u", + oct->octeon_id, oct->vf_num, i); + irqret = request_irq(msix_entries[i].vector, liquidio_msix_intr_handler, 0, - "octeon", &oct->ioq_vector[i]); + &queue_irq_names[IRQ_NAME_OFF(i)], + &oct->ioq_vector[i]); if (irqret) { dev_err(&oct->pci_dev->dev, "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", @@ -830,7 +853,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; - return 1; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; } oct->ioq_vector[i].vector = msix_entries[i].vector; /* assign the cpu mask for this msix interrupt vector */ @@ -975,6 +1000,8 @@ static void octeon_destroy_resources(struct octeon_device *oct) pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); oct->msix_entries = NULL; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; } /* Soft reset the octeon device before exiting */ if (oct->pci_dev->reset_fn) diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h index 294c6f3c6b48..4a07c0ac9fab 100644 --- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h +++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h @@ -100,6 +100,11 @@ enum octeon_tag_type { #define BYTES_PER_DHLEN_UNIT 8 #define MAX_REG_CNT 2000000U +#define INTRNAMSIZ 32 +#define IRQ_NAME_OFF(i) ((i) * INTRNAMSIZ) +#define MAX_IOQ_INTERRUPTS_PER_PF (64 * 2) +#define MAX_IOQ_INTERRUPTS_PER_VF (8 * 2) + static inline u32 incr_index(u32 index, u32 count, u32 max) { diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index c301a3852482..8c5d33e53cfa 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -517,6 +517,9 @@ struct octeon_device { void *msix_entries; + /* when requesting IRQs, the names are stored here */ + void *irq_name_storage; + struct octeon_sriov_info sriov_info; struct octeon_pf_vf_hs_word pfvf_hsword; From be7164cd579edab53edd184382b0bcd35f3bcc0a Mon Sep 17 00:00:00 2001 From: chun Long Date: Tue, 14 Mar 2017 15:26:24 +0800 Subject: [PATCH 320/399] tcp_westwood: fix tcp_westwood_info() style mistakes replace comma to semi colons in tcp_westwood_info(). Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/tcp_westwood.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index fed66dc0e0f5..9775453b8d17 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -265,8 +265,8 @@ static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr, if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = 0; - info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt), - info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min), + info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt); + info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min); *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); From 19ddde1eeca1ee81f4add5e04da66055e09281ac Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Tue, 14 Mar 2017 11:48:32 -0400 Subject: [PATCH 321/399] bonding: add 802.3ad support for 25G speeds Cut-n-paste enablement of 802.3ad bonding on 25G NICs, which currently report 0 as their bandwidth. CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Acked-by: Andy Gospodarek Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 431926bba9f4..508713b4e533 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -92,6 +92,7 @@ enum ad_link_speed_type { AD_LINK_SPEED_2500MBPS, AD_LINK_SPEED_10000MBPS, AD_LINK_SPEED_20000MBPS, + AD_LINK_SPEED_25000MBPS, AD_LINK_SPEED_40000MBPS, AD_LINK_SPEED_56000MBPS, AD_LINK_SPEED_100000MBPS, @@ -260,6 +261,7 @@ static inline int __check_agg_selection_timer(struct port *port) * %AD_LINK_SPEED_2500MBPS, * %AD_LINK_SPEED_10000MBPS * %AD_LINK_SPEED_20000MBPS + * %AD_LINK_SPEED_25000MBPS * %AD_LINK_SPEED_40000MBPS * %AD_LINK_SPEED_56000MBPS * %AD_LINK_SPEED_100000MBPS @@ -302,6 +304,10 @@ static u16 __get_link_speed(struct port *port) speed = AD_LINK_SPEED_20000MBPS; break; + case SPEED_25000: + speed = AD_LINK_SPEED_25000MBPS; + break; + case SPEED_40000: speed = AD_LINK_SPEED_40000MBPS; break; @@ -707,6 +713,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) case AD_LINK_SPEED_20000MBPS: bandwidth = nports * 20000; break; + case AD_LINK_SPEED_25000MBPS: + bandwidth = nports * 25000; + break; case AD_LINK_SPEED_40000MBPS: bandwidth = nports * 40000; break; From 867fa150f8f7ee6e9e5a9ab768e2d0dc675a968b Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 14 Mar 2017 10:24:39 -0700 Subject: [PATCH 322/399] ldmvsw: better use of link up and down on ldom vswitch When an ldom VM is bound, the network vswitch infrastructure is set up for it, but was being forced 'UP' by the userland switch configuration script. When 'UP' but not actually connected to a running VM, the ipv6 neighbor probes fail (not a horrible thing) and start cluttering up the kernel logs. Funny thing: these are debug messages that never actually show up, but we do see the net_ratelimited messages that say N callbacks were suppressed. This patch defers the netif_carrier_on() until an actual link has been established with the VM, as indicated by receiving an LDC_EVENT_UP from the underlying LDC protocol. Similarly, we take the link down when we see the LDC_EVENT_RESET. Now when we see the ndo_open(), we reset the link to get things talking again. Orabug: 25525312 Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/ldmvsw.c | 27 +++++++++++++++++++---- drivers/net/ethernet/sun/sunvnet_common.c | 20 ++++++++++++++--- drivers/net/ethernet/sun/sunvnet_common.h | 1 + 3 files changed, 41 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 89952deae47f..5a90fed06260 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -1,6 +1,6 @@ /* ldmvsw.c: Sun4v LDOM Virtual Switch Driver. * - * Copyright (C) 2016 Oracle. All rights reserved. + * Copyright (C) 2016-2017 Oracle. All rights reserved. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -41,8 +41,8 @@ static u8 vsw_port_hwaddr[ETH_ALEN] = {0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF}; #define DRV_MODULE_NAME "ldmvsw" -#define DRV_MODULE_VERSION "1.1" -#define DRV_MODULE_RELDATE "February 3, 2017" +#define DRV_MODULE_VERSION "1.2" +#define DRV_MODULE_RELDATE "March 4, 2017" static char version[] = DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")"; @@ -123,6 +123,20 @@ static void vsw_set_rx_mode(struct net_device *dev) return sunvnet_set_rx_mode_common(dev, port->vp); } +int ldmvsw_open(struct net_device *dev) +{ + struct vnet_port *port = netdev_priv(dev); + struct vio_driver_state *vio = &port->vio; + + /* reset the channel */ + vio_link_state_change(vio, LDC_EVENT_RESET); + vnet_port_reset(port); + vio_port_up(vio); + + return 0; +} +EXPORT_SYMBOL_GPL(ldmvsw_open); + #ifdef CONFIG_NET_POLL_CONTROLLER static void vsw_poll_controller(struct net_device *dev) { @@ -133,7 +147,7 @@ static void vsw_poll_controller(struct net_device *dev) #endif static const struct net_device_ops vsw_ops = { - .ndo_open = sunvnet_open_common, + .ndo_open = ldmvsw_open, .ndo_stop = sunvnet_close_common, .ndo_set_rx_mode = vsw_set_rx_mode, .ndo_set_mac_address = sunvnet_set_mac_addr_common, @@ -365,6 +379,11 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) napi_enable(&port->napi); vio_port_up(&port->vio); + /* assure no carrier until we receive an LDC_EVENT_UP, + * even if the vsw config script tries to force us up + */ + netif_carrier_off(dev); + netdev_info(dev, "LDOM vsw-port %pM\n", dev->dev_addr); pr_info("%s: PORT ( remote-mac %pM%s )\n", dev->name, diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index fa2d11ca9b81..fbd0f1e5210e 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1,7 +1,7 @@ /* sunvnet.c: Sun LDOM Virtual Network Driver. * * Copyright (C) 2007, 2008 David S. Miller - * Copyright (C) 2016 Oracle. All rights reserved. + * Copyright (C) 2016-2017 Oracle. All rights reserved. */ #include @@ -43,7 +43,6 @@ MODULE_LICENSE("GPL"); MODULE_VERSION("1.1"); static int __vnet_tx_trigger(struct vnet_port *port, u32 start); -static void vnet_port_reset(struct vnet_port *port); static inline u32 vnet_tx_dring_avail(struct vio_dring_state *dr) { @@ -747,6 +746,13 @@ static int vnet_event_napi(struct vnet_port *port, int budget) /* RESET takes precedent over any other event */ if (port->rx_event & LDC_EVENT_RESET) { + /* a link went down */ + + if (port->vsw == 1) { + netif_tx_stop_all_queues(dev); + netif_carrier_off(dev); + } + vio_link_state_change(vio, LDC_EVENT_RESET); vnet_port_reset(port); vio_port_up(vio); @@ -766,6 +772,13 @@ static int vnet_event_napi(struct vnet_port *port, int budget) } if (port->rx_event & LDC_EVENT_UP) { + /* a link came up */ + + if (port->vsw == 1) { + netif_carrier_on(port->dev); + netif_tx_start_all_queues(port->dev); + } + vio_link_state_change(vio, LDC_EVENT_UP); port->rx_event = 0; return 0; @@ -1631,7 +1644,7 @@ void sunvnet_port_free_tx_bufs_common(struct vnet_port *port) } EXPORT_SYMBOL_GPL(sunvnet_port_free_tx_bufs_common); -static void vnet_port_reset(struct vnet_port *port) +void vnet_port_reset(struct vnet_port *port) { del_timer(&port->clean_timer); sunvnet_port_free_tx_bufs_common(port); @@ -1639,6 +1652,7 @@ static void vnet_port_reset(struct vnet_port *port) port->tso = (port->vsw == 0); /* no tso in vsw, misbehaves in bridge */ port->tsolen = 0; } +EXPORT_SYMBOL_GPL(vnet_port_reset); static int vnet_port_alloc_tx_ring(struct vnet_port *port) { diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h index ce5c824128a3..b21ef4704bd1 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.h +++ b/drivers/net/ethernet/sun/sunvnet_common.h @@ -139,6 +139,7 @@ int sunvnet_handle_attr_common(struct vio_driver_state *vio, void *arg); void sunvnet_handshake_complete_common(struct vio_driver_state *vio); int sunvnet_poll_common(struct napi_struct *napi, int budget); void sunvnet_port_free_tx_bufs_common(struct vnet_port *port); +void vnet_port_reset(struct vnet_port *port); bool sunvnet_port_is_up_common(struct vnet_port *vnet); void sunvnet_port_add_txq_common(struct vnet_port *port); void sunvnet_port_rm_txq_common(struct vnet_port *port); From 0f512c84544b9a8f8de53b6f4bc0c372c45d8693 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 14 Mar 2017 10:24:40 -0700 Subject: [PATCH 323/399] sunvnet: add stats to track ldom to ldom packets and bytes In this driver, there is a "port" created for the connection to each of the other ldoms; a netdev queue is mapped to each port, and they are collected under a single netdev. The generic netdev statistics show us all the traffic in and out of our network device, but don't show individual queue/port stats. This patch breaks out the traffic counts for the individual ports and gives us a little view into the state of those connections. Orabug: 25190537 Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunvnet.c | 116 +++++++++++++++++++++- drivers/net/ethernet/sun/sunvnet_common.c | 6 ++ drivers/net/ethernet/sun/sunvnet_common.h | 15 +++ 3 files changed, 136 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 4cc2571f71c6..0b95105f7060 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -1,7 +1,7 @@ /* sunvnet.c: Sun LDOM Virtual Network Driver. * * Copyright (C) 2007, 2008 David S. Miller - * Copyright (C) 2016 Oracle. All rights reserved. + * Copyright (C) 2016-2017 Oracle. All rights reserved. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -77,11 +77,125 @@ static void vnet_set_msglevel(struct net_device *dev, u32 value) vp->msg_enable = value; } +static const struct { + const char string[ETH_GSTRING_LEN]; +} ethtool_stats_keys[] = { + { "rx_packets" }, + { "tx_packets" }, + { "rx_bytes" }, + { "tx_bytes" }, + { "rx_errors" }, + { "tx_errors" }, + { "rx_dropped" }, + { "tx_dropped" }, + { "multicast" }, + { "rx_length_errors" }, + { "rx_frame_errors" }, + { "rx_missed_errors" }, + { "tx_carrier_errors" }, + { "nports" }, +}; + +static int vnet_get_sset_count(struct net_device *dev, int sset) +{ + struct vnet *vp = (struct vnet *)netdev_priv(dev); + + switch (sset) { + case ETH_SS_STATS: + return ARRAY_SIZE(ethtool_stats_keys) + + (NUM_VNET_PORT_STATS * vp->nports); + default: + return -EOPNOTSUPP; + } +} + +static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf) +{ + struct vnet *vp = (struct vnet *)netdev_priv(dev); + struct vnet_port *port; + char *p = (char *)buf; + + switch (stringset) { + case ETH_SS_STATS: + memcpy(buf, ðtool_stats_keys, sizeof(ethtool_stats_keys)); + p += sizeof(ethtool_stats_keys); + + rcu_read_lock(); + list_for_each_entry_rcu(port, &vp->port_list, list) { + snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM", + port->q_index, port->switch_port ? "s" : "q", + port->raddr); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.event_up", + port->q_index); + p += ETH_GSTRING_LEN; + snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset", + port->q_index); + p += ETH_GSTRING_LEN; + } + rcu_read_unlock(); + break; + default: + WARN_ON(1); + break; + } +} + +static void vnet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *estats, u64 *data) +{ + struct vnet *vp = (struct vnet *)netdev_priv(dev); + struct vnet_port *port; + int i = 0; + + data[i++] = dev->stats.rx_packets; + data[i++] = dev->stats.tx_packets; + data[i++] = dev->stats.rx_bytes; + data[i++] = dev->stats.tx_bytes; + data[i++] = dev->stats.rx_errors; + data[i++] = dev->stats.tx_errors; + data[i++] = dev->stats.rx_dropped; + data[i++] = dev->stats.tx_dropped; + data[i++] = dev->stats.multicast; + data[i++] = dev->stats.rx_length_errors; + data[i++] = dev->stats.rx_frame_errors; + data[i++] = dev->stats.rx_missed_errors; + data[i++] = dev->stats.tx_carrier_errors; + data[i++] = vp->nports; + + rcu_read_lock(); + list_for_each_entry_rcu(port, &vp->port_list, list) { + data[i++] = port->q_index; + data[i++] = port->stats.rx_packets; + data[i++] = port->stats.tx_packets; + data[i++] = port->stats.rx_bytes; + data[i++] = port->stats.tx_bytes; + data[i++] = port->stats.event_up; + data[i++] = port->stats.event_reset; + } + rcu_read_unlock(); +} + static const struct ethtool_ops vnet_ethtool_ops = { .get_drvinfo = vnet_get_drvinfo, .get_msglevel = vnet_get_msglevel, .set_msglevel = vnet_set_msglevel, .get_link = ethtool_op_get_link, + .get_sset_count = vnet_get_sset_count, + .get_strings = vnet_get_strings, + .get_ethtool_stats = vnet_get_ethtool_stats, }; static LIST_HEAD(vnet_list); diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index fbd0f1e5210e..7e95808f8227 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -411,6 +411,8 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc) dev->stats.rx_packets++; dev->stats.rx_bytes += len; + port->stats.rx_packets++; + port->stats.rx_bytes += len; napi_gro_receive(&port->napi, skb); return 0; @@ -768,6 +770,7 @@ static int vnet_event_napi(struct vnet_port *port, int budget) maybe_tx_wakeup(port); port->rx_event = 0; + port->stats.event_reset++; return 0; } @@ -781,6 +784,7 @@ static int vnet_event_napi(struct vnet_port *port, int budget) vio_link_state_change(vio, LDC_EVENT_UP); port->rx_event = 0; + port->stats.event_up++; return 0; } @@ -1430,6 +1434,8 @@ int sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev, dev->stats.tx_packets++; dev->stats.tx_bytes += port->tx_bufs[txi].skb->len; + port->stats.tx_packets++; + port->stats.tx_bytes += port->tx_bufs[txi].skb->len; dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1); if (unlikely(vnet_tx_dring_avail(dr) < 1)) { diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h index b21ef4704bd1..c0fac03cb87a 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.h +++ b/drivers/net/ethernet/sun/sunvnet_common.h @@ -35,6 +35,19 @@ struct vnet_tx_entry { struct vnet; +struct vnet_port_stats { + /* keep them all the same size */ + u32 rx_bytes; + u32 tx_bytes; + u32 rx_packets; + u32 tx_packets; + u32 event_up; + u32 event_reset; + u32 q_placeholder; +}; + +#define NUM_VNET_PORT_STATS (sizeof(struct vnet_port_stats) / sizeof(u32)) + /* Structure to describe a vnet-port or vsw-port in the MD. * If the vsw bit is set, this structure represents a vswitch * port, and the net_device can be found from ->dev. If the @@ -44,6 +57,8 @@ struct vnet; struct vnet_port { struct vio_driver_state vio; + struct vnet_port_stats stats; + struct hlist_node hash; u8 raddr[ETH_ALEN]; unsigned switch_port:1; From e1f1e5f711265ee9d881afd12ff252b2d01e1174 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 14 Mar 2017 10:24:41 -0700 Subject: [PATCH 324/399] sunvnet: track port queues correctly Track our used and unused queue indexies correctly. Otherwise, as ports dropped out and returned, they all eventually ended up with the same queue index. Orabug: 25190537 Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunvnet_common.c | 24 +++++++++++++++++++---- drivers/net/ethernet/sun/sunvnet_common.h | 11 ++--------- 2 files changed, 22 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index 7e95808f8227..f8d1cc7e4977 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1728,11 +1728,25 @@ EXPORT_SYMBOL_GPL(sunvnet_poll_controller_common); void sunvnet_port_add_txq_common(struct vnet_port *port) { struct vnet *vp = port->vp; - int n; + int smallest = 0; + int i; - n = vp->nports++; - n = n & (VNET_MAX_TXQS - 1); - port->q_index = n; + /* find the first least-used q + * When there are more ldoms than q's, we start to + * double up on ports per queue. + */ + for (i = 0; i < VNET_MAX_TXQS; i++) { + if (vp->q_used[i] == 0) { + smallest = i; + break; + } + if (vp->q_used[i] < vp->q_used[smallest]) + smallest = i; + } + + vp->nports++; + vp->q_used[smallest]++; + port->q_index = smallest; netif_tx_wake_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port), port->q_index)); } @@ -1743,5 +1757,7 @@ void sunvnet_port_rm_txq_common(struct vnet_port *port) port->vp->nports--; netif_tx_stop_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port), port->q_index)); + port->vp->q_used[port->q_index]--; + port->q_index = 0; } EXPORT_SYMBOL_GPL(sunvnet_port_rm_txq_common); diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h index c0fac03cb87a..b20d6fa7ef25 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.h +++ b/drivers/net/ethernet/sun/sunvnet_common.h @@ -112,22 +112,15 @@ struct vnet_mcast_entry { }; struct vnet { - /* Protects port_list and port_hash. */ - spinlock_t lock; - + spinlock_t lock; /* Protects port_list and port_hash. */ struct net_device *dev; - u32 msg_enable; - + u8 q_used[VNET_MAX_TXQS]; struct list_head port_list; - struct hlist_head port_hash[VNET_PORT_HASH_SIZE]; - struct vnet_mcast_entry *mcast_list; - struct list_head list; u64 local_mac; - int nports; }; From b12a96f5cd04583f45a1b6554b8f3786b26db913 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 14 Mar 2017 10:24:42 -0700 Subject: [PATCH 325/399] sunvnet: count multicast packets Make sure multicast packets get counted in the device. Orabug: 25190537 Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunvnet_common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index f8d1cc7e4977..bf7e0fbe5a9d 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -409,6 +409,8 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc) skb->ip_summed = port->switch_port ? CHECKSUM_NONE : CHECKSUM_PARTIAL; + if (unlikely(is_multicast_ether_addr(eth_hdr(skb)->h_dest))) + dev->stats.multicast++; dev->stats.rx_packets++; dev->stats.rx_bytes += len; port->stats.rx_packets++; From 9c5a3a1f9388100d4b03e85faf0cce8264985302 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 14 Mar 2017 10:24:43 -0700 Subject: [PATCH 326/399] sunvnet: xoff not needed when removing port link The sunvnet netdev is connected to the controlling ldom's vswitch for network bridging. However, for higher performance between ldoms, there also is a channel between each client ldom. These connections are represented in the sunvnet driver by a queue for each ldom. The driver uses select_queue to tell the stack which queue to use by tracking the mac addresses on the other end of each port. When a connected ldom shuts down, the driver receives an LDC_EVENT_RESET and the port is removed from the driver, thus a queue with no ldom on the other end will never be selected for Tx. The driver was trying to reinforce the "don't use this queue" notion with netif_tx_stop_queue() and netif_tx_wake_queue(), which really should only be used to signal a Tx queue is full (aka XOFF). This misuse of queue state resulted in NETDEV WATCHDOG messages and lots of unnecessary calls into the driver's tx_timeout handler. Simply removing these takes care of the problem. Orabug: 25190537 Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunvnet_common.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index bf7e0fbe5a9d..9e86833249d4 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1749,16 +1749,12 @@ void sunvnet_port_add_txq_common(struct vnet_port *port) vp->nports++; vp->q_used[smallest]++; port->q_index = smallest; - netif_tx_wake_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port), - port->q_index)); } EXPORT_SYMBOL_GPL(sunvnet_port_add_txq_common); void sunvnet_port_rm_txq_common(struct vnet_port *port) { port->vp->nports--; - netif_tx_stop_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port), - port->q_index)); port->vp->q_used[port->q_index]--; port->q_index = 0; } From d82bae12dc38d79a2b77473f5eb0612a3d69c55b Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Wed, 15 Mar 2017 16:30:45 -0400 Subject: [PATCH 327/399] tcp: remove per-destination timestamp cache Commit 8a5bd45f6616 (tcp: randomize tcp timestamp offsets for each connection) randomizes TCP timestamps per connection. After this commit, there is no guarantee that the timestamps received from the same destination are monotonically increasing. As a result, the per-destination timestamp cache in TCP metrics (i.e., tcpm_ts in struct tcp_metrics_block) is broken and cannot be relied upon. Remove the per-destination timestamp cache and all related code paths. Note that this cache was already broken for caching timestamps of multiple machines behind a NAT sharing the same address. Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Cc: Lutz Vieweg Cc: Florian Westphal Signed-off-by: David S. Miller --- include/net/tcp.h | 6 +- net/ipv4/tcp_input.c | 6 +- net/ipv4/tcp_ipv4.c | 4 -- net/ipv4/tcp_metrics.c | 147 ++------------------------------------- net/ipv4/tcp_minisocks.c | 22 ++---- net/ipv6/tcp_ipv6.c | 5 -- 6 files changed, 11 insertions(+), 179 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index bede8f7fa742..c81f3b958d44 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -406,11 +406,7 @@ void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); -bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, - bool paws_check, bool timestamps); -bool tcp_remember_stamp(struct sock *sk); -bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw); -void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst); +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_disable_fack(struct tcp_sock *tp); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 96b67a8b18c3..aafec0676d3e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6342,8 +6342,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, dst = af_ops->route_req(sk, &fl, req, &strict); if (dst && strict && - !tcp_peer_is_proven(req, dst, true, - tmp_opt.saw_tstamp)) { + !tcp_peer_is_proven(req, dst)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); goto drop_and_release; } @@ -6352,8 +6351,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, else if (!net->ipv4.sysctl_tcp_syncookies && (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (net->ipv4.sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false, - tmp_opt.saw_tstamp)) { + !tcp_peer_is_proven(req, dst)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 08d870e45658..d8b401fff9fe 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -198,10 +198,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->write_seq = 0; } - if (tcp_death_row->sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) - tcp_fetch_timewait_stamp(sk, &rt->dst); - inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 0f46e5fe31ad..9d0d4f39e42b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -45,8 +45,6 @@ struct tcp_metrics_block { struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; - u32 tcpm_ts; - u32 tcpm_ts_stamp; u32 tcpm_lock; u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1]; struct tcp_fastopen_metrics tcpm_fastopen; @@ -123,8 +121,6 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); - tm->tcpm_ts = 0; - tm->tcpm_ts_stamp = 0; if (fastopen_clear) { tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; @@ -273,48 +269,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, return tm; } -static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw) -{ - struct tcp_metrics_block *tm; - struct inetpeer_addr saddr, daddr; - unsigned int hash; - struct net *net; - - if (tw->tw_family == AF_INET) { - inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); - inetpeer_set_addr_v4(&daddr, tw->tw_daddr); - hash = ipv4_addr_hash(tw->tw_daddr); - } -#if IS_ENABLED(CONFIG_IPV6) - else if (tw->tw_family == AF_INET6) { - if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) { - inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); - inetpeer_set_addr_v4(&daddr, tw->tw_daddr); - hash = ipv4_addr_hash(tw->tw_daddr); - } else { - inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr); - inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr); - hash = ipv6_addr_hash(&tw->tw_v6_daddr); - } - } -#endif - else - return NULL; - - net = twsk_net(tw); - hash ^= net_hash_mix(net); - hash = hash_32(hash, tcp_metrics_hash_log); - - for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm; - tm = rcu_dereference(tm->tcpm_next)) { - if (addr_same(&tm->tcpm_saddr, &saddr) && - addr_same(&tm->tcpm_daddr, &daddr) && - net_eq(tm_net(tm), net)) - break; - } - return tm; -} - static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, struct dst_entry *dst, bool create) @@ -573,8 +527,7 @@ void tcp_init_metrics(struct sock *sk) tp->snd_cwnd_stamp = tcp_time_stamp; } -bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, - bool paws_check, bool timestamps) +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) { struct tcp_metrics_block *tm; bool ret; @@ -584,94 +537,10 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, rcu_read_lock(); tm = __tcp_get_metrics_req(req, dst); - if (paws_check) { - if (tm && - (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL && - ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW || - !timestamps)) - ret = false; - else - ret = true; - } else { - if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp) - ret = true; - else - ret = false; - } - rcu_read_unlock(); - - return ret; -} - -void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst) -{ - struct tcp_metrics_block *tm; - - rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); - if (tm) { - struct tcp_sock *tp = tcp_sk(sk); - - if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) { - tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp; - tp->rx_opt.ts_recent = tm->tcpm_ts; - } - } - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp); - -/* VJ's idea. Save last timestamp seen from this destination and hold - * it at least for normal timewait interval to use for duplicate - * segment detection in subsequent connections, before they enter - * synchronized state. - */ -bool tcp_remember_stamp(struct sock *sk) -{ - struct dst_entry *dst = __sk_dst_get(sk); - bool ret = false; - - if (dst) { - struct tcp_metrics_block *tm; - - rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); - if (tm) { - struct tcp_sock *tp = tcp_sk(sk); - - if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 || - ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && - tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { - tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; - tm->tcpm_ts = tp->rx_opt.ts_recent; - } - ret = true; - } - rcu_read_unlock(); - } - return ret; -} - -bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) -{ - struct tcp_metrics_block *tm; - bool ret = false; - - rcu_read_lock(); - tm = __tcp_get_metrics_tw(tw); - if (tm) { - const struct tcp_timewait_sock *tcptw; - struct sock *sk = (struct sock *) tw; - - tcptw = tcp_twsk(sk); - if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 || - ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && - tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { - tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; - tm->tcpm_ts = tcptw->tw_ts_recent; - } + if (tm && tcp_metric_get(tm, TCP_METRIC_RTT)) ret = true; - } + else + ret = false; rcu_read_unlock(); return ret; @@ -791,14 +660,6 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, jiffies - tm->tcpm_stamp, TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; - if (tm->tcpm_ts_stamp) { - if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP, - (s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0) - goto nla_put_failure; - if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL, - tm->tcpm_ts) < 0) - goto nla_put_failure; - } { int n = 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7e16243cdb58..692f974e5abe 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -94,7 +94,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_options_received tmp_opt; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); bool paws_reject = false; - struct inet_timewait_death_row *tcp_death_row = &sock_net((struct sock*)tw)->ipv4.tcp_death_row; tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { @@ -149,12 +148,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tcptw->tw_ts_recent = tmp_opt.rcv_tsval; } - if (tcp_death_row->sysctl_tw_recycle && - tcptw->tw_ts_recent_stamp && - tcp_tw_remember_stamp(tw)) - inet_twsk_reschedule(tw, tw->tw_timeout); - else - inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -259,12 +253,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct inet_timewait_sock *tw; - bool recycle_ok = false; struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; - if (tcp_death_row->sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) - recycle_ok = tcp_remember_stamp(sk); - tw = inet_twsk_alloc(sk, tcp_death_row, state); if (tw) { @@ -317,13 +307,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (timeo < rto) timeo = rto; - if (recycle_ok) { - tw->tw_timeout = rto; - } else { - tw->tw_timeout = TCP_TIMEWAIT_LEN; - if (state == TCP_TIME_WAIT) - timeo = TCP_TIMEWAIT_LEN; - } + tw->tw_timeout = TCP_TIMEWAIT_LEN; + if (state == TCP_TIME_WAIT) + timeo = TCP_TIMEWAIT_LEN; inet_twsk_schedule(tw, timeo); /* Linkage updates. */ diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c73a431fd06f..853cb43e3e3c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -265,11 +265,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, NULL, NULL); - if (tcp_death_row->sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr)) - tcp_fetch_timewait_stamp(sk, dst); - icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + From 4396e46187ca5070219b81773c4e65088dac50cc Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Wed, 15 Mar 2017 16:30:46 -0400 Subject: [PATCH 328/399] tcp: remove tcp_tw_recycle The tcp_tw_recycle was already broken for connections behind NAT, since the per-destination timestamp is not monotonically increasing for multiple machines behind a single destination address. After the randomization of TCP timestamp offsets in commit 8a5bd45f6616 (tcp: randomize tcp timestamp offsets for each connection), the tcp_tw_recycle is broken for all types of connections for the same reason: the timestamps received from a single machine is not monotonically increasing, anymore. Remove tcp_tw_recycle, since it is not functional. Also, remove the PAWSPassive SNMP counter since it is only used for tcp_tw_recycle, and simplify tcp_v4_route_req and tcp_v6_route_req since the strict argument is only set when tcp_tw_recycle is enabled. Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Cc: Lutz Vieweg Cc: Florian Westphal Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 5 ----- include/net/netns/ipv4.h | 1 - include/net/tcp.h | 3 +-- include/uapi/linux/snmp.h | 1 - net/ipv4/proc.c | 1 - net/ipv4/sysctl_net_ipv4.c | 7 ------ net/ipv4/tcp_input.c | 30 +++++--------------------- net/ipv4/tcp_ipv4.c | 15 ++----------- net/ipv6/tcp_ipv6.c | 5 +---- 9 files changed, 9 insertions(+), 59 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ab0230461377..ed3d0791eb27 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -640,11 +640,6 @@ tcp_tso_win_divisor - INTEGER building larger TSO frames. Default: 3 -tcp_tw_recycle - BOOLEAN - Enable fast recycling TIME-WAIT sockets. Default value is 0. - It should not be changed without advice/request of technical - experts. - tcp_tw_reuse - BOOLEAN Allow to reuse TIME-WAIT sockets for new connections when it is safe from protocol viewpoint. Default value is 0. diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 622d2da27135..2e9d649ba169 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -33,7 +33,6 @@ struct inet_timewait_death_row { atomic_t tw_count; struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; - int sysctl_tw_recycle; int sysctl_max_tw_buckets; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index c81f3b958d44..e614ad4d613e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1810,8 +1810,7 @@ struct tcp_request_sock_ops { __u16 *mss); #endif struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict); + const struct request_sock *req); __u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 3b2bed7ca9a4..cec0e171d20c 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -177,7 +177,6 @@ enum LINUX_MIB_TIMEWAITED, /* TimeWaited */ LINUX_MIB_TIMEWAITRECYCLED, /* TimeWaitRecycled */ LINUX_MIB_TIMEWAITKILLED, /* TimeWaitKilled */ - LINUX_MIB_PAWSPASSIVEREJECTED, /* PAWSPassiveRejected */ LINUX_MIB_PAWSACTIVEREJECTED, /* PAWSActiveRejected */ LINUX_MIB_PAWSESTABREJECTED, /* PAWSEstabRejected */ LINUX_MIB_DELAYEDACKS, /* DelayedACKs */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 69cf49e8356d..4ccbf464d1ac 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -199,7 +199,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED), SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED), SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED), - SNMP_MIB_ITEM("PAWSPassive", LINUX_MIB_PAWSPASSIVEREJECTED), SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED), SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED), SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS), diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d6880a6149ee..11aaef0939b2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -980,13 +980,6 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_tw_recycle", - .data = &init_net.ipv4.tcp_death_row.sysctl_tw_recycle, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index aafec0676d3e..bb09c7095988 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6327,31 +6327,11 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); if (!want_cookie && !isn) { - /* VJ's idea. We save last timestamp seen - * from the destination in peer table, when entering - * state TIME-WAIT, and check against it before - * accepting new connection request. - * - * If "isn" is not zero, this request hit alive - * timewait bucket, so that all the necessary checks - * are made in the function processing timewait state. - */ - if (net->ipv4.tcp_death_row.sysctl_tw_recycle) { - bool strict; - - dst = af_ops->route_req(sk, &fl, req, &strict); - - if (dst && strict && - !tcp_peer_is_proven(req, dst)) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); - goto drop_and_release; - } - } /* Kill the following clause, if you dislike this way. */ - else if (!net->ipv4.sysctl_tcp_syncookies && - (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (net->ipv4.sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst)) { + if (!net->ipv4.sysctl_tcp_syncookies && + (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (net->ipv4.sysctl_max_syn_backlog >> 2)) && + !tcp_peer_is_proven(req, dst)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. @@ -6367,7 +6347,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); } if (!dst) { - dst = af_ops->route_req(sk, &fl, req, NULL); + dst = af_ops->route_req(sk, &fl, req); if (!dst) goto drop_and_free; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d8b401fff9fe..7482b5d11861 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1213,19 +1213,9 @@ static void tcp_v4_init_req(struct request_sock *req, static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict) + const struct request_sock *req) { - struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req); - - if (strict) { - if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr) - *strict = true; - else - *strict = false; - } - - return dst; + return inet_csk_route_req(sk, &fl->u.ip4, req); } struct request_sock_ops tcp_request_sock_ops __read_mostly = { @@ -2462,7 +2452,6 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 0; cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row.sysctl_tw_recycle = 0; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 853cb43e3e3c..0f08d718a002 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -722,11 +722,8 @@ static void tcp_v6_init_req(struct request_sock *req, static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict) + const struct request_sock *req) { - if (strict) - *strict = true; return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } From e245c5c6a5656e4d61aa7bb08e9694fd6e5b2b9d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Mar 2017 18:26:39 -0700 Subject: [PATCH 329/399] bpf: move fixup_bpf_calls() function no functional change. move fixup_bpf_calls() to verifier.c it's being refactored in the next patch Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 56 ------------------------------------------ kernel/bpf/verifier.c | 57 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+), 56 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7af0dcc5d755..48c914b983bd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -586,59 +586,6 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl) list_add(&tl->list_node, &bpf_prog_types); } -/* fixup insn->imm field of bpf_call instructions: - * if (insn->imm == BPF_FUNC_map_lookup_elem) - * insn->imm = bpf_map_lookup_elem - __bpf_call_base; - * else if (insn->imm == BPF_FUNC_map_update_elem) - * insn->imm = bpf_map_update_elem - __bpf_call_base; - * else ... - * - * this function is called after eBPF program passed verification - */ -static void fixup_bpf_calls(struct bpf_prog *prog) -{ - const struct bpf_func_proto *fn; - int i; - - for (i = 0; i < prog->len; i++) { - struct bpf_insn *insn = &prog->insnsi[i]; - - if (insn->code == (BPF_JMP | BPF_CALL)) { - /* we reach here when program has bpf_call instructions - * and it passed bpf_check(), means that - * ops->get_func_proto must have been supplied, check it - */ - BUG_ON(!prog->aux->ops->get_func_proto); - - if (insn->imm == BPF_FUNC_get_route_realm) - prog->dst_needed = 1; - if (insn->imm == BPF_FUNC_get_prandom_u32) - bpf_user_rnd_init_once(); - if (insn->imm == BPF_FUNC_xdp_adjust_head) - prog->xdp_adjust_head = 1; - if (insn->imm == BPF_FUNC_tail_call) { - /* mark bpf_tail_call as different opcode - * to avoid conditional branch in - * interpeter for every normal call - * and to prevent accidental JITing by - * JIT compiler that doesn't support - * bpf_tail_call yet - */ - insn->imm = 0; - insn->code |= BPF_X; - continue; - } - - fn = prog->aux->ops->get_func_proto(insn->imm); - /* all functions that have prototype and verifier allowed - * programs to call them, must be real in-kernel functions - */ - BUG_ON(!fn->func); - insn->imm = fn->func - __bpf_call_base; - } - } -} - /* drop refcnt on maps used by eBPF program and free auxilary data */ static void free_used_maps(struct bpf_prog_aux *aux) { @@ -892,9 +839,6 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - /* fixup BPF_CALL->imm field */ - fixup_bpf_calls(prog); - /* eBPF program is ready to be JITed */ prog = bpf_prog_select_runtime(prog, &err); if (err < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 796b68d00119..e41da6c57053 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3233,6 +3233,60 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return 0; } +/* fixup insn->imm field of bpf_call instructions: + * if (insn->imm == BPF_FUNC_map_lookup_elem) + * insn->imm = bpf_map_lookup_elem - __bpf_call_base; + * else if (insn->imm == BPF_FUNC_map_update_elem) + * insn->imm = bpf_map_update_elem - __bpf_call_base; + * else ... + * + * this function is called after eBPF program passed verification + */ +static void fixup_bpf_calls(struct bpf_prog *prog) +{ + const struct bpf_func_proto *fn; + int i; + + for (i = 0; i < prog->len; i++) { + struct bpf_insn *insn = &prog->insnsi[i]; + + if (insn->code == (BPF_JMP | BPF_CALL)) { + /* we reach here when program has bpf_call instructions + * and it passed bpf_check(), means that + * ops->get_func_proto must have been supplied, check it + */ + BUG_ON(!prog->aux->ops->get_func_proto); + + if (insn->imm == BPF_FUNC_get_route_realm) + prog->dst_needed = 1; + if (insn->imm == BPF_FUNC_get_prandom_u32) + bpf_user_rnd_init_once(); + if (insn->imm == BPF_FUNC_xdp_adjust_head) + prog->xdp_adjust_head = 1; + if (insn->imm == BPF_FUNC_tail_call) { + /* mark bpf_tail_call as different opcode + * to avoid conditional branch in + * interpeter for every normal call + * and to prevent accidental JITing by + * JIT compiler that doesn't support + * bpf_tail_call yet + */ + insn->imm = 0; + insn->code |= BPF_X; + continue; + } + + fn = prog->aux->ops->get_func_proto(insn->imm); + /* all functions that have prototype and verifier allowed + * programs to call them, must be real in-kernel functions + */ + BUG_ON(!fn->func); + insn->imm = fn->func - __bpf_call_base; + } + } +} + + static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl, *sln; @@ -3328,6 +3382,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); + if (ret == 0) + fixup_bpf_calls(env->prog); + if (log_level && log_len >= log_size - 1) { BUG_ON(log_len >= log_size); /* verifier log exceeded user supplied buffer */ From 79741b3bdec01a8628368fbcfccc7d189ed606cb Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Mar 2017 18:26:40 -0700 Subject: [PATCH 330/399] bpf: refactor fixup_bpf_calls() reduce indent and make it iterate over instructions similar to convert_ctx_accesses(). Also convert hard BUG_ON into soft verifier error. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 80 ++++++++++++++++++++----------------------- 1 file changed, 37 insertions(+), 43 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e41da6c57053..5dfa9b8111da 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3233,59 +3233,53 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return 0; } -/* fixup insn->imm field of bpf_call instructions: - * if (insn->imm == BPF_FUNC_map_lookup_elem) - * insn->imm = bpf_map_lookup_elem - __bpf_call_base; - * else if (insn->imm == BPF_FUNC_map_update_elem) - * insn->imm = bpf_map_update_elem - __bpf_call_base; - * else ... +/* fixup insn->imm field of bpf_call instructions * * this function is called after eBPF program passed verification */ -static void fixup_bpf_calls(struct bpf_prog *prog) +static int fixup_bpf_calls(struct bpf_verifier_env *env) { + struct bpf_prog *prog = env->prog; + struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; + const int insn_cnt = prog->len; int i; - for (i = 0; i < prog->len; i++) { - struct bpf_insn *insn = &prog->insnsi[i]; + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL)) + continue; - if (insn->code == (BPF_JMP | BPF_CALL)) { - /* we reach here when program has bpf_call instructions - * and it passed bpf_check(), means that - * ops->get_func_proto must have been supplied, check it + if (insn->imm == BPF_FUNC_get_route_realm) + prog->dst_needed = 1; + if (insn->imm == BPF_FUNC_get_prandom_u32) + bpf_user_rnd_init_once(); + if (insn->imm == BPF_FUNC_xdp_adjust_head) + prog->xdp_adjust_head = 1; + if (insn->imm == BPF_FUNC_tail_call) { + /* mark bpf_tail_call as different opcode to avoid + * conditional branch in the interpeter for every normal + * call and to prevent accidental JITing by JIT compiler + * that doesn't support bpf_tail_call yet */ - BUG_ON(!prog->aux->ops->get_func_proto); - - if (insn->imm == BPF_FUNC_get_route_realm) - prog->dst_needed = 1; - if (insn->imm == BPF_FUNC_get_prandom_u32) - bpf_user_rnd_init_once(); - if (insn->imm == BPF_FUNC_xdp_adjust_head) - prog->xdp_adjust_head = 1; - if (insn->imm == BPF_FUNC_tail_call) { - /* mark bpf_tail_call as different opcode - * to avoid conditional branch in - * interpeter for every normal call - * and to prevent accidental JITing by - * JIT compiler that doesn't support - * bpf_tail_call yet - */ - insn->imm = 0; - insn->code |= BPF_X; - continue; - } - - fn = prog->aux->ops->get_func_proto(insn->imm); - /* all functions that have prototype and verifier allowed - * programs to call them, must be real in-kernel functions - */ - BUG_ON(!fn->func); - insn->imm = fn->func - __bpf_call_base; + insn->imm = 0; + insn->code |= BPF_X; + continue; } - } -} + fn = prog->aux->ops->get_func_proto(insn->imm); + /* all functions that have prototype and verifier allowed + * programs to call them, must be real in-kernel functions + */ + if (!fn->func) { + verbose("kernel subsystem misconfigured func %s#%d\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } + insn->imm = fn->func - __bpf_call_base; + } + + return 0; +} static void free_states(struct bpf_verifier_env *env) { @@ -3383,7 +3377,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) ret = convert_ctx_accesses(env); if (ret == 0) - fixup_bpf_calls(env->prog); + ret = fixup_bpf_calls(env); if (log_level && log_len >= log_size - 1) { BUG_ON(log_len >= log_size); From 8041902dae5299c1f194ba42d14383f734631009 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Mar 2017 18:26:41 -0700 Subject: [PATCH 331/399] bpf: adjust insn_aux_data when patching insns convert_ctx_accesses() replaces single bpf instruction with a set of instructions. Adjust corresponding insn_aux_data while patching. It's needed to make sure subsequent 'for(all insn)' loops have matching insn and insn_aux_data. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 44 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 39 insertions(+), 5 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5dfa9b8111da..2990fda1c6a5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3162,6 +3162,41 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) insn->src_reg = 0; } +/* single env->prog->insni[off] instruction was replaced with the range + * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying + * [0, off) and [off, end) to new locations, so the patched range stays zero + */ +static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, + u32 off, u32 cnt) +{ + struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; + + if (cnt == 1) + return 0; + new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len); + if (!new_data) + return -ENOMEM; + memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); + memcpy(new_data + off + cnt - 1, old_data + off, + sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); + env->insn_aux_data = new_data; + vfree(old_data); + return 0; +} + +static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, + const struct bpf_insn *patch, u32 len) +{ + struct bpf_prog *new_prog; + + new_prog = bpf_patch_insn_single(env->prog, off, patch, len); + if (!new_prog) + return NULL; + if (adjust_insn_aux_data(env, new_prog->len, off, len)) + return NULL; + return new_prog; +} + /* convert load instructions that access fields of 'struct __sk_buff' * into sequence of instructions that access fields of 'struct sk_buff' */ @@ -3181,10 +3216,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) verbose("bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { - new_prog = bpf_patch_insn_single(env->prog, 0, - insn_buf, cnt); + new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) return -ENOMEM; + env->prog = new_prog; delta += cnt - 1; } @@ -3209,7 +3244,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) else continue; - if (env->insn_aux_data[i].ptr_type != PTR_TO_CTX) + if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) continue; cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog); @@ -3218,8 +3253,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return -EINVAL; } - new_prog = bpf_patch_insn_single(env->prog, i + delta, insn_buf, - cnt); + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; From 81ed18ab3098b6519274545e80a29caacb77d160 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Mar 2017 18:26:42 -0700 Subject: [PATCH 332/399] bpf: add helper inlining infra and optimize map_array lookup Optimize bpf_call -> bpf_map_lookup_elem() -> array_map_lookup_elem() into a sequence of bpf instructions. When JIT is on the sequence of bpf instructions is the sequence of native cpu instructions with significantly faster performance than indirect call and two function's prologue/epilogue. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 5 ++++- include/linux/filter.h | 10 ++++++++++ kernel/bpf/arraymap.c | 29 +++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 36 +++++++++++++++++++++++++++++++++--- 5 files changed, 77 insertions(+), 4 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 909fc033173a..da8c64ca8dc9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -35,6 +35,7 @@ struct bpf_map_ops { void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); void (*map_fd_put_ptr)(void *ptr); + u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); }; struct bpf_map { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a13b031dc6b8..5efb4db44e1e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -66,7 +66,10 @@ struct bpf_verifier_state_list { }; struct bpf_insn_aux_data { - enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + union { + enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ + }; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/include/linux/filter.h b/include/linux/filter.h index fbf7b39e8103..dffa072b7b79 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -693,6 +693,11 @@ static inline bool bpf_jit_is_ebpf(void) # endif } +static inline bool ebpf_jit_enabled(void) +{ + return bpf_jit_enable && bpf_jit_is_ebpf(); +} + static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); @@ -753,6 +758,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ +static inline bool ebpf_jit_enabled(void) +{ + return false; +} + static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 6b6f41f0b211..bcf9955fac95 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1,4 +1,5 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016,2017 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -113,6 +114,33 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) return array->value + array->elem_size * index; } +/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ +static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_insn *insn = insn_buf; + u32 elem_size = array->elem_size; + const int ret = BPF_REG_0; + const int map_ptr = BPF_REG_1; + const int index = BPF_REG_2; + + *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); + *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, array->map.max_entries, + elem_size == 1 ? 2 : 3); + if (elem_size == 1) { + /* nop */ + } else if (is_power_of_2(elem_size)) { + *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); + } else { + *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); + } + *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *insn++ = BPF_MOV64_IMM(ret, 0); + return insn - insn_buf; +} + /* Called from eBPF program */ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) { @@ -267,6 +295,7 @@ static const struct bpf_map_ops array_ops = { .map_lookup_elem = array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_gen_lookup = array_map_gen_lookup, }; static struct bpf_map_type_list array_type __ro_after_init = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2990fda1c6a5..90bf46787603 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1273,7 +1273,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) } } -static int check_call(struct bpf_verifier_env *env, int func_id) +static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { struct bpf_verifier_state *state = &env->cur_state; const struct bpf_func_proto *fn = NULL; @@ -1369,6 +1369,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id) } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; + env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr; } else { verbose("unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -2940,7 +2941,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - err = check_call(env, insn->imm); + err = check_call(env, insn->imm, insn_idx); if (err) return err; @@ -3268,6 +3269,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } /* fixup insn->imm field of bpf_call instructions + * and inline eligible helpers as explicit sequence of BPF instructions * * this function is called after eBPF program passed verification */ @@ -3277,7 +3279,10 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; - int i; + struct bpf_insn insn_buf[16]; + struct bpf_prog *new_prog; + struct bpf_map *map_ptr; + int i, cnt, delta = 0; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL)) @@ -3300,6 +3305,31 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + if (ebpf_jit_enabled() && insn->imm == BPF_FUNC_map_lookup_elem) { + map_ptr = env->insn_aux_data[i + delta].map_ptr; + if (!map_ptr->ops->map_gen_lookup) + goto patch_call_imm; + + cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose("bpf verifier is misconfigured\n"); + return -EINVAL; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, + cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + + /* keep walking new program and skip insns we just inserted */ + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + +patch_call_imm: fn = prog->aux->ops->get_func_proto(insn->imm); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions From 9015d2f5953590e8273392b44c2b0f864350b427 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Mar 2017 18:26:43 -0700 Subject: [PATCH 333/399] bpf: inline htab_map_lookup_elem() Optimize: bpf_call bpf_map_lookup_elem map->ops->map_lookup_elem htab_map_lookup_elem __htab_map_lookup_elem into: bpf_call __htab_map_lookup_elem to improve performance of JITed programs. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/hashtab.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index afe5bab376c9..000153acb6d5 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -419,7 +419,11 @@ static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head, return NULL; } -/* Called from syscall or from eBPF program */ +/* Called from syscall or from eBPF program directly, so + * arguments have to match bpf_map_lookup_elem() exactly. + * The return value is adjusted by BPF instructions + * in htab_map_gen_lookup(). + */ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); @@ -451,6 +455,30 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +/* inline bpf_map_lookup_elem() call. + * Instead of: + * bpf_prog + * bpf_map_lookup_elem + * map->ops->map_lookup_elem + * htab_map_lookup_elem + * __htab_map_lookup_elem + * do: + * bpf_prog + * __htab_map_lookup_elem + */ +static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + + *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); + *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, + offsetof(struct htab_elem, key) + + round_up(map->key_size, 8)); + return insn - insn_buf; +} + static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); @@ -1062,6 +1090,7 @@ static const struct bpf_map_ops htab_ops = { .map_lookup_elem = htab_map_lookup_elem, .map_update_elem = htab_map_update_elem, .map_delete_elem = htab_map_delete_elem, + .map_gen_lookup = htab_map_gen_lookup, }; static struct bpf_map_type_list htab_type __ro_after_init = { From 95ff141e52f84f476fcde50560f42d4f118539c0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Mar 2017 18:26:44 -0700 Subject: [PATCH 334/399] samples/bpf: add map_lookup microbenchmark $ map_perf_test 128 speed of HASH bpf_map_lookup_elem() in lookups per second w/o JIT w/JIT before 46M 58M after 42M 74M perf report before: 54.23% map_perf_test [kernel.kallsyms] [k] __htab_map_lookup_elem 14.24% map_perf_test [kernel.kallsyms] [k] lookup_elem_raw 8.84% map_perf_test [kernel.kallsyms] [k] htab_map_lookup_elem 5.93% map_perf_test [kernel.kallsyms] [k] bpf_map_lookup_elem 2.30% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 1.49% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler after: 60.03% map_perf_test [kernel.kallsyms] [k] __htab_map_lookup_elem 18.07% map_perf_test [kernel.kallsyms] [k] lookup_elem_raw 2.91% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 1.94% map_perf_test [kernel.kallsyms] [k] _einittext 1.90% map_perf_test [kernel.kallsyms] [k] __audit_syscall_exit 1.72% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler Notice that bpf_map_lookup_elem() and htab_map_lookup_elem() are trivial functions, yet they take sizeable amount of cpu time. htab_map_gen_lookup() removes bpf_map_lookup_elem() and converts htab_map_lookup_elem() into three BPF insns which causing cpu time for bpf_prog_da4fc6a3f41761a2() slightly increase. $ map_perf_test 256 speed of ARRAY bpf_map_lookup_elem() in lookups per second w/o JIT w/JIT before 97M 174M after 64M 280M before: 37.33% map_perf_test [kernel.kallsyms] [k] array_map_lookup_elem 13.95% map_perf_test [kernel.kallsyms] [k] bpf_map_lookup_elem 6.54% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 4.57% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler after: 32.86% map_perf_test [kernel.kallsyms] [k] bpf_prog_da4fc6a3f41761a2 6.54% map_perf_test [kernel.kallsyms] [k] kprobe_ftrace_handler array_map_gen_lookup() removes calls to array_map_lookup_elem() and bpf_map_lookup_elem() and replaces them with 7 bpf insns. The performance without JIT is slower, since executing extra insns in the interpreter is slower than running native C code, but with JIT the performance gains are obvious, since native C->x86 code is replaced with fewer bpf->x86 instructions. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- samples/bpf/map_perf_test_kern.c | 33 ++++++++++++++++++++++++++++++++ samples/bpf/map_perf_test_user.c | 32 +++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c index a91872a97742..9da2a3441b0a 100644 --- a/samples/bpf/map_perf_test_kern.c +++ b/samples/bpf/map_perf_test_kern.c @@ -65,6 +65,13 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = { .map_flags = BPF_F_NO_PREALLOC, }; +struct bpf_map_def SEC("maps") array_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, +}; + SEC("kprobe/sys_getuid") int stress_hmap(struct pt_regs *ctx) { @@ -165,5 +172,31 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx) return 0; } +SEC("kprobe/sys_getpgid") +int stress_hash_map_lookup(struct pt_regs *ctx) +{ + u32 key = 1, i; + long *value; + +#pragma clang loop unroll(full) + for (i = 0; i < 64; ++i) + value = bpf_map_lookup_elem(&hash_map, &key); + + return 0; +} + +SEC("kprobe/sys_getpgrp") +int stress_array_map_lookup(struct pt_regs *ctx) +{ + u32 key = 1, i; + long *value; + +#pragma clang loop unroll(full) + for (i = 0; i < 64; ++i) + value = bpf_map_lookup_elem(&array_map, &key); + + return 0; +} + char _license[] SEC("license") = "GPL"; u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index 680260a91f50..e29ff318a793 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -38,6 +38,8 @@ static __u64 time_get_ns(void) #define LRU_HASH_PREALLOC (1 << 4) #define PERCPU_LRU_HASH_PREALLOC (1 << 5) #define LPM_KMALLOC (1 << 6) +#define HASH_LOOKUP (1 << 7) +#define ARRAY_LOOKUP (1 << 8) static int test_flags = ~0; @@ -125,6 +127,30 @@ static void test_lpm_kmalloc(int cpu) cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); } +static void test_hash_lookup(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getpgid, 0); + printf("%d:hash_lookup %lld lookups per sec\n", + cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time)); +} + +static void test_array_lookup(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getpgrp, 0); + printf("%d:array_lookup %lld lookups per sec\n", + cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time)); +} + static void loop(int cpu) { cpu_set_t cpuset; @@ -153,6 +179,12 @@ static void loop(int cpu) if (test_flags & LPM_KMALLOC) test_lpm_kmalloc(cpu); + + if (test_flags & HASH_LOOKUP) + test_hash_lookup(cpu); + + if (test_flags & ARRAY_LOOKUP) + test_array_lookup(cpu); } static void run_perf_test(int tasks) From 6de38af611ca81a970965c06231cd2d5f30b2566 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 16 Mar 2017 16:12:37 -0700 Subject: [PATCH 335/399] netvsc: avoid race with callback Change the argument to channel callback from the channel pointer to the internal data structure containing per-channel info. This avoids any possible races when callback happens during initialization and makes IRQ code simpler. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc.c | 18 +++++------------- drivers/net/hyperv/rndis_filter.c | 15 ++++++++++----- 2 files changed, 15 insertions(+), 18 deletions(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 0e71164849dd..0a2e9bd98d2c 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1250,21 +1250,12 @@ int netvsc_poll(struct napi_struct *napi, int budget) void netvsc_channel_cb(void *context) { - struct vmbus_channel *channel = context; - struct hv_device *device = netvsc_channel_to_device(channel); - u16 q_idx = channel->offermsg.offer.sub_channel_index; - struct netvsc_device *net_device; - struct net_device *ndev; - - ndev = hv_get_drvdata(device); - if (unlikely(!ndev)) - return; + struct netvsc_channel *nvchan = context; /* disable interupts from host */ - hv_begin_read(&channel->inbound); + hv_begin_read(&nvchan->channel->inbound); - net_device = net_device_to_netvsc_device(ndev); - napi_schedule(&net_device->chan_table[q_idx].napi); + napi_schedule(&nvchan->napi); } /* @@ -1294,7 +1285,8 @@ int netvsc_device_add(struct hv_device *device, /* Open the channel */ ret = vmbus_open(device->channel, ring_size * PAGE_SIZE, ring_size * PAGE_SIZE, NULL, 0, - netvsc_channel_cb, device->channel); + netvsc_channel_cb, + net_device->chan_table); if (ret != 0) { netdev_err(ndev, "unable to open channel: %d\n", ret); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index d7b6311e6c19..382b9a62e3c4 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -996,23 +996,28 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) hv_get_drvdata(new_sc->primary_channel->device_obj); struct netvsc_device *nvscdev = net_device_to_netvsc_device(ndev); u16 chn_index = new_sc->offermsg.offer.sub_channel_index; - int ret; + struct netvsc_channel *nvchan; unsigned long flags; + int ret; if (chn_index >= nvscdev->num_chn) return; - nvscdev->chan_table[chn_index].mrc.buf + nvchan = nvscdev->chan_table + chn_index; + nvchan->mrc.buf = vzalloc(NETVSC_RECVSLOT_MAX * sizeof(struct recv_comp_data)); + if (!nvchan->mrc.buf) + return; + ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE, nvscdev->ring_size * PAGE_SIZE, NULL, 0, - netvsc_channel_cb, new_sc); + netvsc_channel_cb, nvchan); if (ret == 0) - nvscdev->chan_table[chn_index].channel = new_sc; + nvchan->channel = new_sc; - napi_enable(&nvscdev->chan_table[chn_index].napi); + napi_enable(&nvchan->napi); spin_lock_irqsave(&nvscdev->sc_lock, flags); nvscdev->num_sc_offered--; From 262b7f142a50badde4032e925902a0d0ad89eb7f Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 16 Mar 2017 16:12:38 -0700 Subject: [PATCH 336/399] netvsc: add comments about callback's and NAPI Add some short description of how callback's and NAPI interoperate. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 0a2e9bd98d2c..989b7cd99380 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1209,6 +1209,10 @@ static struct hv_device *netvsc_channel_to_device(struct vmbus_channel *channel) return primary ? primary->device_obj : channel->device_obj; } +/* Network processing softirq + * Process data in incoming ring buffer from host + * Stops when ring is empty or budget is met or exceeded. + */ int netvsc_poll(struct napi_struct *napi, int budget) { struct netvsc_channel *nvchan @@ -1238,7 +1242,11 @@ int netvsc_poll(struct napi_struct *napi, int budget) } hv_pkt_iter_close(channel); - /* If ring is empty and NAPI is not doing polling */ + /* If budget was not exhausted and + * not doing busy poll + * then re-enable host interrupts + * and reschedule if ring is not empty. + */ if (work_done < budget && napi_complete_done(napi, work_done) && hv_end_read(&channel->inbound) != 0) @@ -1248,6 +1256,9 @@ int netvsc_poll(struct napi_struct *napi, int budget) return work_done; } +/* Call back when data is available in host ring buffer. + * Processing is deferred until network softirq (NAPI) + */ void netvsc_channel_cb(void *context) { struct netvsc_channel *nvchan = context; From 76f5ed881c8de0264283c5b934deb33bf87209a8 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 16 Mar 2017 16:12:39 -0700 Subject: [PATCH 337/399] netvsc: remove unused #define Not used anywhere. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/hyperv_net.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index b09c4fca1805..6b5f75217694 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1427,9 +1427,6 @@ struct rndis_message { ((void *) rndis_msg) -#define __struct_bcount(x) - - #define RNDIS_HEADER_SIZE (sizeof(struct rndis_message) - \ sizeof(union rndis_message_container)) From fe723dff0fa4181ddb8116e72bc67d00d4239cb6 Mon Sep 17 00:00:00 2001 From: Manish Awasthi Date: Thu, 16 Mar 2017 16:16:17 -0700 Subject: [PATCH 338/399] liquidio: fix wrong information about link modes reported to ethtool Information reported to ethtool about link modes is wrong for 25G NIC. Fix it by checking for presence of 25G NIC, checking the link speed reported by NIC firmware, and then assigning proper values to the ethtool_link_ksettings struct. Signed-off-by: Manish Awasthi Signed-off-by: Felix Manlunas Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 50384cede8be..6eef3b999130 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -213,17 +213,23 @@ static int lio_get_link_ksettings(struct net_device *netdev, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct oct_link_info *linfo; - u32 supported, advertising; + u32 supported = 0, advertising = 0; linfo = &lio->linfo; if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI || linfo->link.s.if_mode == INTERFACE_MODE_RXAUI || + linfo->link.s.if_mode == INTERFACE_MODE_XLAUI || linfo->link.s.if_mode == INTERFACE_MODE_XFI) { ecmd->base.port = PORT_FIBRE; - supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE | - SUPPORTED_Pause); - advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Pause); + + if (linfo->link.s.speed == SPEED_10000) { + supported = SUPPORTED_10000baseT_Full; + advertising = ADVERTISED_10000baseT_Full; + } + + supported |= SUPPORTED_FIBRE | SUPPORTED_Pause; + advertising |= ADVERTISED_Pause; ethtool_convert_legacy_u32_to_link_mode( ecmd->link_modes.supported, supported); ethtool_convert_legacy_u32_to_link_mode( From b54ab92b84b6161f91b1ad9160199422b3699009 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Thu, 16 Mar 2017 10:03:34 +0200 Subject: [PATCH 339/399] netfilter: refcounter conversions refcount_t type and corresponding API (see include/linux/refcount.h) should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 16 +++++++------ include/net/netfilter/nf_conntrack_expect.h | 4 +++- include/net/netfilter/nf_conntrack_timeout.h | 3 ++- net/ipv4/netfilter/ipt_CLUSTERIP.c | 19 ++++++++-------- net/netfilter/ipvs/ip_vs_conn.c | 24 ++++++++++---------- net/netfilter/ipvs/ip_vs_core.c | 4 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 12 +++++----- net/netfilter/ipvs/ip_vs_lblc.c | 2 +- net/netfilter/ipvs/ip_vs_lblcr.c | 6 ++--- net/netfilter/ipvs/ip_vs_nq.c | 2 +- net/netfilter/ipvs/ip_vs_proto_sctp.c | 2 +- net/netfilter/ipvs/ip_vs_proto_tcp.c | 2 +- net/netfilter/ipvs/ip_vs_rr.c | 2 +- net/netfilter/ipvs/ip_vs_sed.c | 2 +- net/netfilter/ipvs/ip_vs_wlc.c | 2 +- net/netfilter/ipvs/ip_vs_wrr.c | 2 +- net/netfilter/nf_conntrack_expect.c | 10 ++++---- net/netfilter/nf_conntrack_netlink.c | 4 ++-- net/netfilter/nfnetlink_acct.c | 16 +++++++------ net/netfilter/nfnetlink_cttimeout.c | 12 +++++----- net/netfilter/nfnetlink_log.c | 14 +++++++----- 21 files changed, 85 insertions(+), 75 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 7bdfa7d78363..8a4a57b887fb 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -12,6 +12,8 @@ #include /* for struct list_head */ #include /* for struct rwlock_t */ #include /* for struct atomic_t */ +#include /* for struct refcount_t */ + #include #include #include @@ -525,7 +527,7 @@ struct ip_vs_conn { struct netns_ipvs *ipvs; /* counter and timer */ - atomic_t refcnt; /* reference count */ + refcount_t refcnt; /* reference count */ struct timer_list timer; /* Expiration timer */ volatile unsigned long timeout; /* timeout */ @@ -667,7 +669,7 @@ struct ip_vs_dest { atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ - atomic_t refcnt; /* reference counter */ + refcount_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ unsigned long idle_start; /* start time, jiffies */ @@ -1211,14 +1213,14 @@ struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, */ static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp) { - return atomic_inc_not_zero(&cp->refcnt); + return refcount_inc_not_zero(&cp->refcnt); } /* put back the conn without restarting its timer */ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp) { smp_mb__before_atomic(); - atomic_dec(&cp->refcnt); + refcount_dec(&cp->refcnt); } void ip_vs_conn_put(struct ip_vs_conn *cp); void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); @@ -1410,18 +1412,18 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp); static inline void ip_vs_dest_hold(struct ip_vs_dest *dest) { - atomic_inc(&dest->refcnt); + refcount_inc(&dest->refcnt); } static inline void ip_vs_dest_put(struct ip_vs_dest *dest) { smp_mb__before_atomic(); - atomic_dec(&dest->refcnt); + refcount_dec(&dest->refcnt); } static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) { - if (atomic_dec_and_test(&dest->refcnt)) + if (refcount_dec_and_test(&dest->refcnt)) kfree(dest); } diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 5ed33ea4718e..65cc2cb005d9 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -5,6 +5,8 @@ #ifndef _NF_CONNTRACK_EXPECT_H #define _NF_CONNTRACK_EXPECT_H +#include + #include #include @@ -37,7 +39,7 @@ struct nf_conntrack_expect { struct timer_list timeout; /* Usage count. */ - atomic_t use; + refcount_t use; /* Flags */ unsigned int flags; diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 5cc5e9e6171a..d40b89355fdd 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -4,6 +4,7 @@ #include #include #include +#include #include #include @@ -12,7 +13,7 @@ struct ctnl_timeout { struct list_head head; struct rcu_head rcu_head; - atomic_t refcnt; + refcount_t refcnt; char name[CTNL_TIMEOUT_NAME_MAX]; __u16 l3num; struct nf_conntrack_l4proto *l4proto; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 52f26459efc3..fcbdc0c49b0e 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -40,8 +41,8 @@ MODULE_DESCRIPTION("Xtables: CLUSTERIP target"); struct clusterip_config { struct list_head list; /* list of all configs */ - atomic_t refcount; /* reference count */ - atomic_t entries; /* number of entries/rules + refcount_t refcount; /* reference count */ + refcount_t entries; /* number of entries/rules * referencing us */ __be32 clusterip; /* the IP address */ @@ -77,7 +78,7 @@ struct clusterip_net { static inline void clusterip_config_get(struct clusterip_config *c) { - atomic_inc(&c->refcount); + refcount_inc(&c->refcount); } @@ -89,7 +90,7 @@ static void clusterip_config_rcu_free(struct rcu_head *head) static inline void clusterip_config_put(struct clusterip_config *c) { - if (atomic_dec_and_test(&c->refcount)) + if (refcount_dec_and_test(&c->refcount)) call_rcu_bh(&c->rcu, clusterip_config_rcu_free); } @@ -103,7 +104,7 @@ clusterip_config_entry_put(struct clusterip_config *c) struct clusterip_net *cn = net_generic(net, clusterip_net_id); local_bh_disable(); - if (atomic_dec_and_lock(&c->entries, &cn->lock)) { + if (refcount_dec_and_lock(&c->entries, &cn->lock)) { list_del_rcu(&c->list); spin_unlock(&cn->lock); local_bh_enable(); @@ -149,10 +150,10 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry) c = NULL; else #endif - if (unlikely(!atomic_inc_not_zero(&c->refcount))) + if (unlikely(!refcount_inc_not_zero(&c->refcount))) c = NULL; else if (entry) - atomic_inc(&c->entries); + refcount_inc(&c->entries); } rcu_read_unlock_bh(); @@ -188,8 +189,8 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, clusterip_config_init_nodelist(c, i); c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; - atomic_set(&c->refcount, 1); - atomic_set(&c->entries, 1); + refcount_set(&c->refcount, 1); + refcount_set(&c->entries, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index e6a2753dff9e..3d2ac71a83ec 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -181,7 +181,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) if (!(cp->flags & IP_VS_CONN_F_HASHED)) { cp->flags |= IP_VS_CONN_F_HASHED; - atomic_inc(&cp->refcnt); + refcount_inc(&cp->refcnt); hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]); ret = 1; } else { @@ -215,7 +215,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) if (cp->flags & IP_VS_CONN_F_HASHED) { hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; - atomic_dec(&cp->refcnt); + refcount_dec(&cp->refcnt); ret = 1; } else ret = 0; @@ -242,13 +242,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) if (cp->flags & IP_VS_CONN_F_HASHED) { ret = false; /* Decrease refcnt and unlink conn only if we are last user */ - if (atomic_cmpxchg(&cp->refcnt, 1, 0) == 1) { + if (refcount_dec_if_one(&cp->refcnt)) { hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; ret = true; } } else - ret = atomic_read(&cp->refcnt) ? false : true; + ret = refcount_read(&cp->refcnt) ? false : true; spin_unlock(&cp->lock); ct_write_unlock_bh(hash); @@ -475,7 +475,7 @@ static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp) void ip_vs_conn_put(struct ip_vs_conn *cp) { if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && - (atomic_read(&cp->refcnt) == 1) && + (refcount_read(&cp->refcnt) == 1) && !timer_pending(&cp->timer)) /* expire connection immediately */ __ip_vs_conn_put_notimer(cp); @@ -617,8 +617,8 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), ip_vs_fwd_tag(cp), cp->state, - cp->flags, atomic_read(&cp->refcnt), - atomic_read(&dest->refcnt)); + cp->flags, refcount_read(&cp->refcnt), + refcount_read(&dest->refcnt)); /* Update the connection counters */ if (!(flags & IP_VS_CONN_F_TEMPLATE)) { @@ -714,8 +714,8 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), ip_vs_fwd_tag(cp), cp->state, - cp->flags, atomic_read(&cp->refcnt), - atomic_read(&dest->refcnt)); + cp->flags, refcount_read(&cp->refcnt), + refcount_read(&dest->refcnt)); /* Update the connection counters */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { @@ -863,10 +863,10 @@ static void ip_vs_conn_expire(unsigned long data) expire_later: IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n", - atomic_read(&cp->refcnt), + refcount_read(&cp->refcnt), atomic_read(&cp->n_control)); - atomic_inc(&cp->refcnt); + refcount_inc(&cp->refcnt); cp->timeout = 60*HZ; if (ipvs->sync_state & IP_VS_STATE_MASTER) @@ -941,7 +941,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, * it in the table, so that other thread run ip_vs_random_dropentry * but cannot drop this entry. */ - atomic_set(&cp->refcnt, 1); + refcount_set(&cp->refcnt, 1); cp->control = NULL; atomic_set(&cp->n_control, 0); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 9aaa49025cdc..b4a746d0e39b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -542,7 +542,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), - cp->flags, atomic_read(&cp->refcnt)); + cp->flags, refcount_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; @@ -1193,7 +1193,7 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), - cp->flags, atomic_read(&cp->refcnt)); + cp->flags, refcount_read(&cp->refcnt)); LeaveFunction(12); return cp; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5aeb0dde6ccc..541aa7694775 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -699,7 +699,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af, dest->vfwmark, IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); + refcount_read(&dest->refcnt)); if (dest->af == dest_af && ip_vs_addr_equal(dest_af, &dest->addr, daddr) && dest->port == dport && @@ -934,7 +934,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atomic_set(&dest->activeconns, 0); atomic_set(&dest->inactconns, 0); atomic_set(&dest->persistconns, 0); - atomic_set(&dest->refcnt, 1); + refcount_set(&dest->refcnt, 1); INIT_HLIST_NODE(&dest->d_list); spin_lock_init(&dest->dst_lock); @@ -998,7 +998,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, " "dest->refcnt=%d, service %u/%s:%u\n", IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport), - atomic_read(&dest->refcnt), + refcount_read(&dest->refcnt), dest->vfwmark, IP_VS_DBG_ADDR(svc->af, &dest->vaddr), ntohs(dest->vport)); @@ -1074,7 +1074,7 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, spin_lock_bh(&ipvs->dest_trash_lock); IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); + refcount_read(&dest->refcnt)); if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); @@ -1157,7 +1157,7 @@ static void ip_vs_dest_trash_expire(unsigned long data) spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { - if (atomic_read(&dest->refcnt) > 1) + if (refcount_read(&dest->refcnt) > 1) continue; if (dest->idle_start) { if (time_before(now, dest->idle_start + @@ -1545,7 +1545,7 @@ ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev) dev->name, IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); + refcount_read(&dest->refcnt)); __ip_vs_dst_cache_reset(dest); } spin_unlock_bh(&dest->dst_lock); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 5824927cf8e0..b6aa4a970c6e 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -448,7 +448,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc) IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 703f11877bee..c13ff575f9f7 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -204,7 +204,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; } @@ -249,7 +249,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) __func__, IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port), atomic_read(&most->activeconns), - atomic_read(&most->refcnt), + refcount_read(&most->refcnt), atomic_read(&most->weight), moh); return most; } @@ -612,7 +612,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc) IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index a8b63401e773..7d9d4ac596ca 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -110,7 +110,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index d952d67f904d..56f8e4b204ff 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -447,7 +447,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, ntohs(cp->cport), sctp_state_name(cp->state), sctp_state_name(next_state), - atomic_read(&cp->refcnt)); + refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state != IP_VS_SCTP_S_ESTABLISHED)) { diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 5117bcb7d2f0..12dc8d5bc37d 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -557,7 +557,7 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, ntohs(cp->cport), tcp_state_name(cp->state), tcp_state_name(new_state), - atomic_read(&cp->refcnt)); + refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c index 58bacfc461ee..ee0530d14c5f 100644 --- a/net/netfilter/ipvs/ip_vs_rr.c +++ b/net/netfilter/ipvs/ip_vs_rr.c @@ -97,7 +97,7 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, "activeconns %d refcnt %d weight %d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->activeconns), - atomic_read(&dest->refcnt), atomic_read(&dest->weight)); + refcount_read(&dest->refcnt), atomic_read(&dest->weight)); return dest; } diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index f8e2d00f528b..ab23cf203437 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -111,7 +111,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 6b366fd90554..6add39e0ec20 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -83,7 +83,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index 17e6d4406ca7..62258dd457ac 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -218,7 +218,7 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, "activeconns %d refcnt %d weight %d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->activeconns), - atomic_read(&dest->refcnt), + refcount_read(&dest->refcnt), atomic_read(&dest->weight)); mark->cl = dest; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 4b2e1fb28bb4..cb29e598605f 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -133,7 +133,7 @@ nf_ct_expect_find_get(struct net *net, rcu_read_lock(); i = __nf_ct_expect_find(net, zone, tuple); - if (i && !atomic_inc_not_zero(&i->use)) + if (i && !refcount_inc_not_zero(&i->use)) i = NULL; rcu_read_unlock(); @@ -186,7 +186,7 @@ nf_ct_find_expectation(struct net *net, return NULL; if (exp->flags & NF_CT_EXPECT_PERMANENT) { - atomic_inc(&exp->use); + refcount_inc(&exp->use); return exp; } else if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); @@ -275,7 +275,7 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me) return NULL; new->master = me; - atomic_set(&new->use, 1); + refcount_set(&new->use, 1); return new; } EXPORT_SYMBOL_GPL(nf_ct_expect_alloc); @@ -348,7 +348,7 @@ static void nf_ct_expect_free_rcu(struct rcu_head *head) void nf_ct_expect_put(struct nf_conntrack_expect *exp) { - if (atomic_dec_and_test(&exp->use)) + if (refcount_dec_and_test(&exp->use)) call_rcu(&exp->rcu, nf_ct_expect_free_rcu); } EXPORT_SYMBOL_GPL(nf_ct_expect_put); @@ -361,7 +361,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple); /* two references : one for hash insert, one for the timer */ - atomic_add(2, &exp->use); + refcount_add(2, &exp->use); hlist_add_head(&exp->lnode, &master_help->expectations); master_help->expecting[exp->class]++; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6806b5e73567..d49cc1e03c5b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2693,7 +2693,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!atomic_inc_not_zero(&exp->use)) + if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; @@ -2739,7 +2739,7 @@ ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!atomic_inc_not_zero(&exp->use)) + if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index d44d89b56127..f44cbd35357f 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -32,7 +33,7 @@ struct nf_acct { atomic64_t bytes; unsigned long flags; struct list_head head; - atomic_t refcnt; + refcount_t refcnt; char name[NFACCT_NAME_MAX]; struct rcu_head rcu_head; char data[0]; @@ -123,7 +124,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl, atomic64_set(&nfacct->pkts, be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS]))); } - atomic_set(&nfacct->refcnt, 1); + refcount_set(&nfacct->refcnt, 1); list_add_tail_rcu(&nfacct->head, &net->nfnl_acct_list); return 0; } @@ -166,7 +167,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, NFACCT_PAD) || nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes), NFACCT_PAD) || - nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt)))) + nla_put_be32(skb, NFACCT_USE, htonl(refcount_read(&acct->refcnt)))) goto nla_put_failure; if (acct->flags & NFACCT_F_QUOTA) { u64 *quota = (u64 *)acct->data; @@ -325,11 +326,12 @@ static int nfnl_acct_get(struct net *net, struct sock *nfnl, static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; + unsigned int refcount; /* We want to avoid races with nfnl_acct_put. So only when the current * refcnt is 1, we decrease it to 0. */ - if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) { + if (refcount_dec_if_one(&cur->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); @@ -413,7 +415,7 @@ struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name) if (!try_module_get(THIS_MODULE)) goto err; - if (!atomic_inc_not_zero(&cur->refcnt)) { + if (!refcount_inc_not_zero(&cur->refcnt)) { module_put(THIS_MODULE); goto err; } @@ -429,7 +431,7 @@ EXPORT_SYMBOL_GPL(nfnl_acct_find_get); void nfnl_acct_put(struct nf_acct *acct) { - if (atomic_dec_and_test(&acct->refcnt)) + if (refcount_dec_and_test(&acct->refcnt)) kfree_rcu(acct, rcu_head); module_put(THIS_MODULE); @@ -502,7 +504,7 @@ static void __net_exit nfnl_acct_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) { list_del_rcu(&cur->head); - if (atomic_dec_and_test(&cur->refcnt)) + if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 139e0867e56e..baa75f3ab7e7 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -138,7 +138,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME])); timeout->l3num = l3num; timeout->l4proto = l4proto; - atomic_set(&timeout->refcnt, 1); + refcount_set(&timeout->refcnt, 1); list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list); return 0; @@ -172,7 +172,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) || nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) || nla_put_be32(skb, CTA_TIMEOUT_USE, - htonl(atomic_read(&timeout->refcnt)))) + htonl(refcount_read(&timeout->refcnt)))) goto nla_put_failure; if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) { @@ -339,7 +339,7 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) /* We want to avoid races with ctnl_timeout_put. So only when the * current refcnt is 1, we decrease it to 0. */ - if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) { + if (refcount_dec_if_one(&timeout->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); @@ -536,7 +536,7 @@ ctnl_timeout_find_get(struct net *net, const char *name) if (!try_module_get(THIS_MODULE)) goto err; - if (!atomic_inc_not_zero(&timeout->refcnt)) { + if (!refcount_inc_not_zero(&timeout->refcnt)) { module_put(THIS_MODULE); goto err; } @@ -550,7 +550,7 @@ ctnl_timeout_find_get(struct net *net, const char *name) static void ctnl_timeout_put(struct ctnl_timeout *timeout) { - if (atomic_dec_and_test(&timeout->refcnt)) + if (refcount_dec_and_test(&timeout->refcnt)) kfree_rcu(timeout, rcu_head); module_put(THIS_MODULE); @@ -601,7 +601,7 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_del_rcu(&cur->head); nf_ct_l4proto_put(cur->l4proto); - if (atomic_dec_and_test(&cur->refcnt)) + if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 08247bf7d7b8..ecd857b75ffe 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -40,6 +40,8 @@ #include #include +#include + #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" @@ -57,7 +59,7 @@ struct nfulnl_instance { struct hlist_node hlist; /* global list of instances */ spinlock_t lock; - atomic_t use; /* use count */ + refcount_t use; /* use count */ unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ @@ -115,7 +117,7 @@ __instance_lookup(struct nfnl_log_net *log, u_int16_t group_num) static inline void instance_get(struct nfulnl_instance *inst) { - atomic_inc(&inst->use); + refcount_inc(&inst->use); } static struct nfulnl_instance * @@ -125,7 +127,7 @@ instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num) rcu_read_lock_bh(); inst = __instance_lookup(log, group_num); - if (inst && !atomic_inc_not_zero(&inst->use)) + if (inst && !refcount_inc_not_zero(&inst->use)) inst = NULL; rcu_read_unlock_bh(); @@ -145,7 +147,7 @@ static void nfulnl_instance_free_rcu(struct rcu_head *head) static void instance_put(struct nfulnl_instance *inst) { - if (inst && atomic_dec_and_test(&inst->use)) + if (inst && refcount_dec_and_test(&inst->use)) call_rcu_bh(&inst->rcu, nfulnl_instance_free_rcu); } @@ -180,7 +182,7 @@ instance_create(struct net *net, u_int16_t group_num, INIT_HLIST_NODE(&inst->hlist); spin_lock_init(&inst->lock); /* needs to be two, since we _put() after creation */ - atomic_set(&inst->use, 2); + refcount_set(&inst->use, 2); setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst); @@ -1031,7 +1033,7 @@ static int seq_show(struct seq_file *s, void *v) inst->group_num, inst->peer_portid, inst->qlen, inst->copy_mode, inst->copy_range, - inst->flushtimeout, atomic_read(&inst->use)); + inst->flushtimeout, refcount_read(&inst->use)); return 0; } From 7bd175928280c3e5d741cb9948cffaa61b7cc7c6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:25:26 -0800 Subject: [PATCH 340/399] igb: Add support for DMA_ATTR_WEAK_ORDERING Since we are already using DMA attributes in igb for Rx there is no reason why we can't also apply DMA_ATTR_WEAK_ORDERING which is needed on some platforms to improve performance. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 3 +++ drivers/net/ethernet/intel/igb/igb_main.c | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index acbc3abe2ddd..87c9fe9d6f18 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -148,6 +148,9 @@ struct vf_data_storage { /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IGB_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + #define AUTO_ALL_MODES 0 #define IGB_EEPROM_APME 0x0400 diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index be456bae8169..cf7ee9cdac6f 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3963,7 +3963,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) buffer_info->dma, PAGE_SIZE, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); + IGB_RX_DMA_ATTR); __page_frag_cache_drain(buffer_info->page, buffer_info->pagecnt_bias); @@ -6990,7 +6990,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); + IGB_RX_DMA_ATTR); __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); } @@ -7250,7 +7250,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, /* map page for use */ dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, - DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); + DMA_FROM_DEVICE, IGB_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use From 7ec0116c9131a8cd58dc456ae2bd5bc9976460d1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:25:41 -0800 Subject: [PATCH 341/399] igb: Use length to determine if descriptor is done This change makes it so that we use the length of the packet instead of the DD status bit to determine if a new descriptor is ready to be processed. The obvious advantage is that it cuts down on reads as we don't really even need the DD bit if going from a 0 to a non-zero value on size is enough to inform us that the packet has been completed. In addition I have updated the code so that we only reset the Rx descriptor length for descriptor zero when resetting a ring instead of having to do a memset with 0 over the entire ring. By doing this we can save some time on initialization. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ethtool.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 14 ++++++++------ 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 737b664d004c..3f5f7744c90f 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1811,7 +1811,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IGB_RX_DESC(rx_ring, rx_ntc); - while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) { + while (rx_desc->wb.upper.length) { /* check Rx buffer */ rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc]; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index cf7ee9cdac6f..1d76d3a90a17 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3720,6 +3720,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, struct igb_ring *ring) { struct e1000_hw *hw = &adapter->hw; + union e1000_adv_rx_desc *rx_desc; u64 rdba = ring->dma; int reg_idx = ring->reg_idx; u32 srrctl = 0, rxdctl = 0; @@ -3758,6 +3759,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; + /* initialize Rx descriptor 0 */ + rx_desc = IGB_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + /* enable receive descriptor fetching */ rxdctl |= E1000_RXDCTL_QUEUE_ENABLE; wr32(E1000_RXDCTL(reg_idx), rxdctl); @@ -3973,9 +3978,6 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) size = sizeof(struct igb_rx_buffer) * rx_ring->count; memset(rx_ring->rx_buffer_info, 0, size); - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -7172,7 +7174,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean); - if (!rx_desc->wb.upper.status_error) + if (!rx_desc->wb.upper.length) break; /* This memory barrier is needed to keep us from reading @@ -7312,8 +7314,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.upper.status_error = 0; + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; cleaned_count--; } while (cleaned_count); From d2bead576e67c34fe9ea174bb245254d0fe237b5 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:25:50 -0800 Subject: [PATCH 342/399] igb: Clear Rx buffer_info in configure instead of clean This change makes it so that instead of going through the entire ring on Rx cleanup we only go through the region that was designated to be cleaned up and stop when we reach the region where new allocations should start. In addition we can avoid having to perform a memset on the Rx buffer_info structures until we are about to start using the ring again. By deferring this we can avoid dirtying the cache any more than we have to which can help to improve the time needed to bring the interface down and then back up again in a reset or suspend/resume cycle. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 24 ++++++++++------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 1d76d3a90a17..680f0d3d9b72 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3435,7 +3435,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) size = sizeof(struct igb_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc(size); + rx_ring->rx_buffer_info = vmalloc(size); if (!rx_ring->rx_buffer_info) goto err; @@ -3759,6 +3759,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct igb_rx_buffer) * ring->count); + /* initialize Rx descriptor 0 */ rx_desc = IGB_RX_DESC(ring, 0); rx_desc->wb.upper.length = 0; @@ -3937,23 +3941,16 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) **/ static void igb_clean_rx_ring(struct igb_ring *rx_ring) { - unsigned long size; - u16 i; + u16 i = rx_ring->next_to_clean; if (rx_ring->skb) dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; - if (!rx_ring->rx_buffer_info) - return; - /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { + while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; - if (!buffer_info->page) - continue; - /* Invalidate cache lines that may have been written to by * device so that we avoid corrupting memory. */ @@ -3972,12 +3969,11 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) __page_frag_cache_drain(buffer_info->page, buffer_info->pagecnt_bias); - buffer_info->page = NULL; + i++; + if (i == rx_ring->count) + i = 0; } - size = sizeof(struct igb_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_buffer_info, 0, size); - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; From 7cc6fd4c60f267e17b0baef1580d7a6258c0a6f0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:26:02 -0800 Subject: [PATCH 343/399] igb: Don't bother clearing Tx buffer_info in igb_clean_tx_ring In the case of the Tx rings we need to only clear the Tx buffer_info when we are resetting the rings. Ideally we do this when we configure the ring to bring it back up instead of when we are taking it down in order to avoid dirtying pages we don't need to. In addition we don't need to clear the Tx descriptor ring since we will fully repopulate it when we begin transmitting frames and next_to_watch can be cleared to prevent the ring from being cleaned beyond that point instead of needing to touch anything in the Tx descriptor ring. Finally with these changes we can avoid having to reset the skb member of the Tx buffer_info structure in the cleanup path since the skb will always be associated with the first buffer which has next_to_watch set. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 1 - drivers/net/ethernet/intel/igb/igb_ethtool.c | 11 +- drivers/net/ethernet/intel/igb/igb_main.c | 120 +++++++++++-------- 3 files changed, 83 insertions(+), 49 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 87c9fe9d6f18..a638254f4e06 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -594,7 +594,6 @@ void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); -void igb_unmap_and_free_tx_resource(struct igb_ring *, struct igb_tx_buffer *); void igb_alloc_rx_buffers(struct igb_ring *, u16); void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *); bool igb_has_link(struct igb_adapter *adapter); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 3f5f7744c90f..612cf13b7a3a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1833,7 +1833,16 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, /* unmap buffer on Tx side */ tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer_info->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer_info, dma), + dma_unmap_len(tx_buffer_info, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer_info, len, 0); /* increment Rx/Tx next to clean counters */ rx_ntc++; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 680f0d3d9b72..e541cccaae1b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3293,7 +3293,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) size = sizeof(struct igb_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc(size); + tx_ring->tx_buffer_info = vmalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -3404,6 +3404,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, txdctl |= IGB_TX_HTHRESH << 8; txdctl |= IGB_TX_WTHRESH << 16; + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct igb_tx_buffer) * ring->count); + txdctl |= E1000_TXDCTL_QUEUE_ENABLE; wr32(E1000_TXDCTL(reg_idx), txdctl); } @@ -3831,55 +3835,63 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) igb_free_tx_resources(adapter->tx_ring[i]); } -void igb_unmap_and_free_tx_resource(struct igb_ring *ring, - struct igb_tx_buffer *tx_buffer) -{ - if (tx_buffer->skb) { - dev_kfree_skb_any(tx_buffer->skb); - if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } else if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } - tx_buffer->next_to_watch = NULL; - tx_buffer->skb = NULL; - dma_unmap_len_set(tx_buffer, len, 0); - /* buffer_info must be completely set up in the transmit path */ -} - /** * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ static void igb_clean_tx_ring(struct igb_ring *tx_ring) { - struct igb_tx_buffer *buffer_info; - unsigned long size; - u16 i; + u16 i = tx_ring->next_to_clean; + struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (!tx_ring->tx_buffer_info) - return; - /* Free all the Tx ring sk_buffs */ + while (i != tx_ring->next_to_use) { + union e1000_adv_tx_desc *eop_desc, *tx_desc; - for (i = 0; i < tx_ring->count; i++) { - buffer_info = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, buffer_info); + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IGB_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } } + /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); - size = sizeof(struct igb_tx_buffer) * tx_ring->count; - memset(tx_ring->tx_buffer_info, 0, size); - - /* Zero out the descriptor ring */ - memset(tx_ring->desc, 0, tx_ring->size); - + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; } @@ -5254,18 +5266,32 @@ static void igb_tx_map(struct igb_ring *tx_ring, dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; /* clear dma mappings for failed tx_buffer_info map */ - for (;;) { + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i--) + i += tx_ring->count; tx_buffer = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer); - if (tx_buffer == first) - break; - if (i == 0) - i = tx_ring->count; - i--; } + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + tx_ring->next_to_use = i; } @@ -5337,7 +5363,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: - igb_unmap_and_free_tx_resource(tx_ring, first); + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } @@ -6684,7 +6711,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) DMA_TO_DEVICE); /* clear tx_buffer data */ - tx_buffer->skb = NULL; dma_unmap_len_set(tx_buffer, len, 0); /* clear last DMA location and unmap remaining buffers */ From cfbc871c2174f352542053d25659920d6841ed41 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:26:15 -0800 Subject: [PATCH 344/399] igb: Limit maximum frame Rx based on MTU In order to support the use of build_skb going forward it will be necessary to place a maximum limit on the amount of data we can receive when jumbo frames is not enabled. In order to do this I am adding a new upper limit for receive based on the size of a 2K buffer minus padding. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 10 +++++++++- drivers/net/ethernet/intel/igb/igb_main.c | 21 +++++++++++++++++---- 2 files changed, 26 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index a638254f4e06..a74928cc0e58 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -143,8 +143,17 @@ struct vf_data_storage { #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_2048 2048 #define IGB_RX_HDR_LEN IGB_RXBUFFER_256 +#define IGB_TS_HDR_LEN 16 #define IGB_RX_BUFSZ IGB_RXBUFFER_2048 +#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IGB_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN) +#else +#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN) +#endif + /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */ @@ -561,7 +570,6 @@ struct igb_adapter { #define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */ #define IGB_82576_TSYNC_SHIFT 19 -#define IGB_TS_HDR_LEN 16 enum e1000_state_t { __IGB_TESTING, __IGB_RESETTING, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index e541cccaae1b..1bf31224dfac 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4250,7 +4250,7 @@ static void igb_set_rx_mode(struct net_device *netdev) struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; unsigned int vfn = adapter->vfs_allocated_count; - u32 rctl = 0, vmolr = 0; + u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE; int count; /* Check for Promiscuous and All Multicast modes */ @@ -4308,6 +4308,14 @@ static void igb_set_rx_mode(struct net_device *netdev) E1000_RCTL_VFE); wr32(E1000_RCTL, rctl); +#if (PAGE_SIZE < 8192) + if (!adapter->vfs_allocated_count) { + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + rlpml = IGB_MAX_FRAME_BUILD_SKB; + } +#endif + wr32(E1000_RLPML, rlpml); + /* In order to support SR-IOV and eventually VMDq it is necessary to set * the VMOLR to enable the appropriate modes. Without this workaround * we will have issues with VLAN tag stripping not being done for frames @@ -4322,12 +4330,17 @@ static void igb_set_rx_mode(struct net_device *netdev) vmolr |= rd32(E1000_VMOLR(vfn)) & ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); - /* enable Rx jumbo frames, no need for restriction */ + /* enable Rx jumbo frames, restrict as needed to support build_skb */ vmolr &= ~E1000_VMOLR_RLPML_MASK; - vmolr |= MAX_JUMBO_FRAME_SIZE | E1000_VMOLR_LPE; +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + vmolr |= IGB_MAX_FRAME_BUILD_SKB; + else +#endif + vmolr |= MAX_JUMBO_FRAME_SIZE; + vmolr |= E1000_VMOLR_LPE; wr32(E1000_VMOLR(vfn), vmolr); - wr32(E1000_RLPML, MAX_JUMBO_FRAME_SIZE); igb_restore_vf_multicasts(adapter); } From cb0ef1d1dc8739e307f70493b7eb1184685dbbde Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:26:26 -0800 Subject: [PATCH 345/399] igb: Only sync size of expected frame in ethtool testing We only need to sync the size of the frame that is read to test. We don't need to sync the entire Rx buffer. This way the testing is more consistent with how we handle things in the receive path. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 612cf13b7a3a..d5966feb7b96 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1818,7 +1818,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, /* sync Rx buffer for CPU read */ dma_sync_single_for_cpu(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* verify contents of skb */ @@ -1828,7 +1828,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, /* sync Rx buffer for device write */ dma_sync_single_for_device(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* unmap buffer on Tx side */ From 3456fd53421e7f499395542d6c2e76e0b46ab4d3 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:26:40 -0800 Subject: [PATCH 346/399] igb: Use page_address offset from page instead of masking virtual address Update the handling of page addresses so that we always refer to them using a void pointer, and try to use the consistent name of va indicating we are working with a virtual address. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 11 +++++------ drivers/net/ethernet/intel/igb/igb_ptp.c | 3 +-- 3 files changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index a74928cc0e58..6a88a08c021c 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -614,7 +614,7 @@ void igb_ptp_reset(struct igb_adapter *adapter); void igb_ptp_suspend(struct igb_adapter *adapter); void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 1bf31224dfac..44c590c5d5b7 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6927,7 +6927,7 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, struct sk_buff *skb) { struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; + void *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = IGB_RX_BUFSZ; #else @@ -6969,7 +6969,7 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, add_tail_frag: skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - (unsigned long)va & ~PAGE_MASK, size, truesize); + va - page_address(page), size, truesize); return igb_can_reuse_rx_page(rx_buffer, page, truesize); } @@ -6994,13 +6994,12 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, DMA_FROM_DEVICE); if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; + void *va = page_address(page) + rx_buffer->page_offset; /* prefetch first cache line of first page */ - prefetch(page_addr); + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif /* allocate a skb to store the frags */ diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index c4477552ce9e..7a3fd4d74592 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) * incoming frame. The value is stored in little endian format starting on * byte 8. **/ -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, - unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb) { __le64 *regval = (__le64 *)va; From e08912985b296b33b18a563cc126e3e2f018c2e1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:26:52 -0800 Subject: [PATCH 347/399] igb: Add support for ethtool private flag to allow use of legacy Rx Since there are potential drawbacks to the new Rx allocation approach I thought it best to add a "chicken bit" so that we can turn the feature off if in the event that a problem is found. It also provides a means of validating the legacy Rx path in the event that we are forced to fall back. At some point in the future when we are convinced we don't need it anymore we might be able to drop the legacy-rx flag. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 1 + drivers/net/ethernet/intel/igb/igb_ethtool.c | 48 ++++++++++++++++++++ 2 files changed, 49 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 6a88a08c021c..bffdfe65a0b6 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -557,6 +557,7 @@ struct igb_adapter { #define IGB_FLAG_HAS_MSIX BIT(13) #define IGB_FLAG_EEE BIT(14) #define IGB_FLAG_VLAN_PROMISC BIT(15) +#define IGB_FLAG_RX_LEGACY BIT(16) /* Media Auto Sense */ #define IGB_MAS_ENABLE_0 0X0001 diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index d5966feb7b96..797b9daba224 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -144,6 +144,13 @@ static const char igb_gstrings_test[][ETH_GSTRING_LEN] = { }; #define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN) +static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IGB_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings) + static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) { struct igb_adapter *adapter = netdev_priv(netdev); @@ -852,6 +859,8 @@ static void igb_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IGB_PRIV_FLAGS_STR_LEN; } static void igb_get_ringparam(struct net_device *netdev, @@ -2280,6 +2289,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset) return IGB_STATS_LEN; case ETH_SS_TEST: return IGB_TEST_LEN; + case ETH_SS_PRIV_FLAGS: + return IGB_PRIV_FLAGS_STR_LEN; default: return -ENOTSUPP; } @@ -2385,6 +2396,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } /* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */ break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, igb_priv_flags_strings, + IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; } } @@ -3397,6 +3412,37 @@ static int igb_set_channels(struct net_device *netdev, return 0; } +static u32 igb_get_priv_flags(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IGB_FLAG_RX_LEGACY; + if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX) + flags |= IGB_FLAG_RX_LEGACY; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + igb_reinit_locked(adapter); + } + + return 0; +} + static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -3435,6 +3481,8 @@ static const struct ethtool_ops igb_ethtool_ops = { .set_rxfh = igb_set_rxfh, .get_channels = igb_get_channels, .set_channels = igb_set_channels, + .get_priv_flags = igb_get_priv_flags, + .set_priv_flags = igb_set_priv_flags, .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, }; From 8649aaef4044681257ed38cf8706aea88430f2c4 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:27:03 -0800 Subject: [PATCH 348/399] igb: Add support for using order 1 pages to receive large frames This patch adds support for using 3K buffers in order 1 pages the same way we were using 2K buffers in 4K pages. We are reserving 1K of room for now to have space available for future headroom and tailroom when we enable build_skb support. One side effect of this patch is that we can end up using a larger buffer if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo frames is enabled as the truesize of frames will be larger. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 30 ++++++++++- drivers/net/ethernet/intel/igb/igb_main.c | 64 +++++++++++++++++------ 2 files changed, 76 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index bffdfe65a0b6..eb91c87e0c1d 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -142,9 +142,9 @@ struct vf_data_storage { /* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_2048 2048 +#define IGB_RXBUFFER_3072 3072 #define IGB_RX_HDR_LEN IGB_RXBUFFER_256 #define IGB_TS_HDR_LEN 16 -#define IGB_RX_BUFSZ IGB_RXBUFFER_2048 #define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) #if (PAGE_SIZE < 8192) @@ -313,12 +313,40 @@ struct igb_q_vector { }; enum e1000_ring_flags_t { + IGB_RING_FLAG_RX_3K_BUFFER, IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, IGB_RING_FLAG_TX_DETECT_HANG }; +#define ring_uses_large_buffer(ring) \ + test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define set_ring_uses_large_buffer(ring) \ + set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) + +static inline unsigned int igb_rx_bufsz(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IGB_RXBUFFER_3072; +#endif + return IGB_RXBUFFER_2048; +} + +static inline unsigned int igb_rx_pg_order(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring)) + #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS) #define IGB_RX_DESC(R, i) \ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 44c590c5d5b7..24c20d401240 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -554,7 +554,7 @@ static void igb_dump(struct igb_adapter *adapter) 16, 1, page_address(buffer_info->page) + buffer_info->page_offset, - IGB_RX_BUFSZ, true); + igb_rx_bufsz(rx_ring), true); } } } @@ -3746,7 +3746,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, /* set descriptor configuration */ srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -3776,6 +3779,23 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, wr32(E1000_RXDCTL(reg_idx), rxdctl); } +static void igb_set_rx_buffer_len(struct igb_adapter *adapter, + struct igb_ring *rx_ring) +{ + /* set build_skb and buffer size flags */ + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + return; + +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + return; + + set_ring_uses_large_buffer(rx_ring); +#endif +} + /** * igb_configure_rx - Configure receive Unit after Reset * @adapter: board private structure @@ -3793,8 +3813,12 @@ static void igb_configure_rx(struct igb_adapter *adapter) /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) - igb_configure_rx_ring(adapter, adapter->rx_ring[i]); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *rx_ring = adapter->rx_ring[i]; + + igb_set_rx_buffer_len(adapter, rx_ring); + igb_configure_rx_ring(adapter, rx_ring); + } } /** @@ -3969,13 +3993,13 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) dma_sync_single_range_for_cpu(rx_ring->dev, buffer_info->dma, buffer_info->page_offset, - IGB_RX_BUFSZ, + igb_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, buffer_info->dma, - PAGE_SIZE, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IGB_RX_DMA_ATTR); __page_frag_cache_drain(buffer_info->page, @@ -6870,7 +6894,7 @@ static inline bool igb_page_is_reserved(struct page *page) static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, struct page *page, - unsigned int truesize) + const unsigned int truesize) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; @@ -6884,12 +6908,14 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, return false; /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IGB_RX_BUFSZ; + rx_buffer->page_offset ^= truesize; #else /* move offset up to the next cache line */ rx_buffer->page_offset += truesize; +#define IGB_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048) - if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) + if (rx_buffer->page_offset > IGB_LAST_OFFSET) return false; #endif @@ -6929,7 +6955,7 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, struct page *page = rx_buffer->page; void *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = IGB_RX_BUFSZ; + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif @@ -7025,7 +7051,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, * any references we are holding to it */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IGB_RX_DMA_ATTR); __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); } @@ -7278,21 +7304,23 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, return true; /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(igb_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; return false; } /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, - DMA_FROM_DEVICE, IGB_RX_DMA_ATTR); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + igb_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_page(page); + __free_pages(page, igb_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_failed++; return false; @@ -7315,6 +7343,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) union e1000_adv_rx_desc *rx_desc; struct igb_rx_buffer *bi; u16 i = rx_ring->next_to_use; + u16 bufsz; /* nothing to do */ if (!cleaned_count) @@ -7324,14 +7353,15 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) bi = &rx_ring->rx_buffer_info[i]; i -= rx_ring->count; + bufsz = igb_rx_bufsz(rx_ring); + do { if (!igb_alloc_mapped_page(rx_ring, bi)) break; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - IGB_RX_BUFSZ, + bi->page_offset, bufsz, DMA_FROM_DEVICE); /* Refresh the desc even if buffer_addrs didn't change From e3cdf68d4a861d91ef62ed615483e673f07fccfe Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:27:14 -0800 Subject: [PATCH 349/399] igb: Add support for padding packet With the size of the frame limited we can now write to an offset within the buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 11 +++++++++++ drivers/net/ethernet/intel/igb/igb_main.c | 14 ++++++++++++-- 2 files changed, 23 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index eb91c87e0c1d..dc6e2980718f 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -314,6 +314,7 @@ struct igb_q_vector { enum e1000_ring_flags_t { IGB_RING_FLAG_RX_3K_BUFFER, + IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, @@ -327,11 +328,21 @@ enum e1000_ring_flags_t { #define clear_ring_uses_large_buffer(ring) \ clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define ring_uses_build_skb(ring) \ + test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define set_ring_build_skb_enabled(ring) \ + set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) + static inline unsigned int igb_rx_bufsz(struct igb_ring *ring) { #if (PAGE_SIZE < 8192) if (ring_uses_large_buffer(ring)) return IGB_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN; #endif return IGB_RXBUFFER_2048; } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 24c20d401240..3ef66577872b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3783,11 +3783,14 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, struct igb_ring *rx_ring) { /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); clear_ring_uses_large_buffer(rx_ring); if (adapter->flags & IGB_FLAG_RX_LEGACY) return; + set_ring_build_skb_enabled(rx_ring); + #if (PAGE_SIZE < 8192) if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) return; @@ -6957,7 +6960,9 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size); + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGB_SKB_PAD + size) : + SKB_DATA_ALIGN(size); #endif unsigned int pull_len; @@ -7293,6 +7298,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) return total_packets; } +static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0; +} + static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, struct igb_rx_buffer *bi) { @@ -7328,7 +7338,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = igb_rx_offset(rx_ring); bi->pagecnt_bias = 1; return true; From e014272672b964471608a2624e4cdf1d5e7c22ea Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:27:26 -0800 Subject: [PATCH 350/399] igb: Break out Rx buffer page management At this point we have 2 to 3 paths that can be taken depending on what Rx modes are enabled. In order to better support that and improve the maintainability I am breaking out the common bits from those paths and making them into their own functions. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 235 +++++++++++----------- 1 file changed, 121 insertions(+), 114 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 3ef66577872b..dfae641647d3 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6886,8 +6886,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, nta++; rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - /* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; + /* Transfer page from old buffer to new buffer. + * Move each member individually to avoid possible store + * forwarding stalls. + */ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } static inline bool igb_page_is_reserved(struct page *page) @@ -6895,11 +6901,10 @@ static inline bool igb_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, - struct page *page, - const unsigned int truesize) +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) { - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* avoid re-using remote pages */ if (unlikely(igb_page_is_reserved(page))) @@ -6907,14 +6912,9 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_ref_count(page) != pagecnt_bias)) + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= truesize; #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; #define IGB_LAST_OFFSET \ (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048) @@ -6926,7 +6926,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(pagecnt_bias == 1)) { + if (unlikely(!pagecnt_bias)) { page_ref_add(page, USHRT_MAX); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -6938,25 +6938,16 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * igb_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into + * @size: size of buffer to be added * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. - * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. **/ -static bool igb_add_rx_frag(struct igb_ring *rx_ring, +static void igb_add_rx_frag(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, - unsigned int size, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - void *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else @@ -6964,10 +6955,39 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, SKB_DATA_ALIGN(IGB_SKB_PAD + size) : SKB_DATA_ALIGN(size); #endif - unsigned int pull_len; + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} - if (unlikely(skb_is_nonlinear(skb))) - goto add_tail_frag; +static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + unsigned int headlen; + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); + if (unlikely(!skb)) + return NULL; if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); @@ -6975,95 +6995,29 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, size -= IGB_TS_HDR_LEN; } - if (likely(size <= IGB_RX_HDR_LEN)) { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!igb_page_is_reserved(page))) - return true; - - /* this page cannot be reused so discard it */ - return false; - } - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN); + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IGB_RX_HDR_LEN) + headlen = eth_get_headlen(va, IGB_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); /* update all of the pointers */ - va += pull_len; - size -= pull_len; - -add_tail_frag: - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - va - page_address(page), size, truesize); - - return igb_can_reuse_rx_page(rx_buffer, page, truesize); -} - -static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) -{ - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); - struct igb_rx_buffer *rx_buffer; - struct page *page; - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - if (likely(!skb)) { - void *va = page_address(page) + rx_buffer->page_offset; - - /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (va + headlen) - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; #endif - - /* allocate a skb to store the frags */ - skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_failed++; - return NULL; - } - - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } - - /* pull page into skb */ - if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { - /* hand second half of page back to the ring */ - igb_reuse_rx_page(rx_ring, rx_buffer); } else { - /* We are not reusing the buffer so unmap it and free - * any references we are holding to it - */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - IGB_RX_DMA_ATTR); - __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); + rx_buffer->pagecnt_bias++; } - /* clear contents of rx_buffer */ - rx_buffer->page = NULL; - return skb; } @@ -7221,6 +7175,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, + const unsigned int size) +{ + struct igb_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void igb_put_rx_buffer(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer) +{ + if (igb_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + igb_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { struct igb_ring *rx_ring = q_vector->rx.ring; @@ -7230,6 +7225,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *rx_buffer; + unsigned int size; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { @@ -7238,8 +7235,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) } rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean); - - if (!rx_desc->wb.upper.length) + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) break; /* This memory barrier is needed to keep us from reading @@ -7248,13 +7245,23 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) */ dma_rmb(); + rx_buffer = igb_get_rx_buffer(rx_ring, size); + /* retrieve a buffer from the ring */ - skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); + if (skb) + igb_add_rx_frag(rx_ring, rx_buffer, skb, size); + else + skb = igb_construct_skb(rx_ring, rx_buffer, + rx_desc, size); /* exit if we failed to retrieve a buffer */ - if (!skb) + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + rx_buffer->pagecnt_bias++; break; + } + igb_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; /* fetch next buffer in frame if non-eop */ From b1bb2eb0a0deb03e9847d8e29eb1e75ce141e4d9 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 6 Feb 2017 18:27:36 -0800 Subject: [PATCH 351/399] igb: Re-add support for build_skb in igb This reverts commit f9d40f6a9921 ("igb: Revert support for build_skb in igb") and adds a few changes to update it to work with the latest version of igb. We are now able to revert the removal of this due to the fact that with the recent changes to the page count and the use of DMA_ATTR_SKIP_CPU_SYNC we can make the pages writable so we should not be invalidating the additional data added when we call build_skb. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 47 +++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index dfae641647d3..79f39a785dca 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7021,6 +7021,51 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, return skb; } +static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IGB_SKB_PAD + size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* build an skb to around the page buffer */ + skb = build_skb(va - IGB_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, IGB_SKB_PAD); + __skb_put(skb, size); + + /* pull timestamp out of packet data */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); + __skb_pull(skb, IGB_TS_HDR_LEN); + } + + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + static inline void igb_rx_checksum(struct igb_ring *ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -7250,6 +7295,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* retrieve a buffer from the ring */ if (skb) igb_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size); else skb = igb_construct_skb(rx_ring, rx_buffer, rx_desc, size); From 3a1eb6d10c9350fa7adce850a752693460ac62d6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 15 Feb 2017 09:15:59 -0800 Subject: [PATCH 352/399] igb/ixgbe: Fix typo in igb_build_skb and/or ixgbe_build_skb code comment There was a typo that I had left in the code comments for the igb and ixgbe functions that enabled build_skb support. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 79f39a785dca..26a821fcd220 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7041,7 +7041,7 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, prefetch(va + L1_CACHE_BYTES); #endif - /* build an skb to around the page buffer */ + /* build an skb around the page buffer */ skb = build_skb(va - IGB_SKB_PAD, truesize); if (unlikely(!skb)) return NULL; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d45477db0227..852a2e7e25ed 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2122,7 +2122,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, prefetch(va + L1_CACHE_BYTES); #endif - /* build an skb to around the page buffer */ + /* build an skb around the page buffer */ skb = build_skb(va - IXGBE_SKB_PAD, truesize); if (unlikely(!skb)) return NULL; From a7f909405bf9bd3a737a39d3a433a4eae4d7eb21 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sat, 4 Feb 2017 22:05:06 +0100 Subject: [PATCH 353/399] i40e: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/i40e/i40e_ethtool.c | 266 ++++++++++-------- 1 file changed, 154 insertions(+), 112 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index a933c6c2aff8..ceb57ad59e8f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -387,7 +387,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, * **/ static void i40e_get_settings_link_up(struct i40e_hw *hw, - struct ethtool_cmd *ecmd, + struct ethtool_link_ksettings *cmd, struct net_device *netdev, struct i40e_pf *pf) { @@ -395,90 +395,96 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, u32 link_speed = hw_link_info->link_speed; u32 e_advertising = 0x0; u32 e_supported = 0x0; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); /* Initialize supported and advertised settings based on phy settings */ switch (hw_link_info->phy_type) { case I40E_PHY_TYPE_40GBASE_CR4: case I40E_PHY_TYPE_40GBASE_CR4_CU: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_40000baseCR4_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_40000baseCR4_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_40000baseCR4_Full; + advertising = ADVERTISED_Autoneg | + ADVERTISED_40000baseCR4_Full; break; case I40E_PHY_TYPE_XLAUI: case I40E_PHY_TYPE_XLPPI: case I40E_PHY_TYPE_40GBASE_AOC: - ecmd->supported = SUPPORTED_40000baseCR4_Full; + supported = SUPPORTED_40000baseCR4_Full; break; case I40E_PHY_TYPE_40GBASE_SR4: - ecmd->supported = SUPPORTED_40000baseSR4_Full; + supported = SUPPORTED_40000baseSR4_Full; break; case I40E_PHY_TYPE_40GBASE_LR4: - ecmd->supported = SUPPORTED_40000baseLR4_Full; + supported = SUPPORTED_40000baseLR4_Full; break; case I40E_PHY_TYPE_10GBASE_SR: case I40E_PHY_TYPE_10GBASE_LR: case I40E_PHY_TYPE_1000BASE_SX: case I40E_PHY_TYPE_1000BASE_LX: - ecmd->supported = SUPPORTED_10000baseT_Full; + supported = SUPPORTED_10000baseT_Full; if (hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_SX || hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_LX) { - ecmd->supported |= SUPPORTED_1000baseT_Full; + supported |= SUPPORTED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; } if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - ecmd->advertising |= ADVERTISED_10000baseT_Full; + advertising |= ADVERTISED_10000baseT_Full; break; case I40E_PHY_TYPE_10GBASE_T: case I40E_PHY_TYPE_1000BASE_T: case I40E_PHY_TYPE_100BASE_TX: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full; - ecmd->advertising = ADVERTISED_Autoneg; + supported = SUPPORTED_Autoneg | + SUPPORTED_10000baseT_Full | + SUPPORTED_1000baseT_Full | + SUPPORTED_100baseT_Full; + advertising = ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - ecmd->advertising |= ADVERTISED_10000baseT_Full; + advertising |= ADVERTISED_10000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - ecmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; break; case I40E_PHY_TYPE_1000BASE_T_OPTICAL: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_1000baseT_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_1000baseT_Full; + advertising = ADVERTISED_Autoneg | + ADVERTISED_1000baseT_Full; break; case I40E_PHY_TYPE_10GBASE_CR1_CU: case I40E_PHY_TYPE_10GBASE_CR1: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_10000baseT_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_10000baseT_Full; + advertising = ADVERTISED_Autoneg | + ADVERTISED_10000baseT_Full; break; case I40E_PHY_TYPE_XAUI: case I40E_PHY_TYPE_XFI: case I40E_PHY_TYPE_SFI: case I40E_PHY_TYPE_10GBASE_SFPP_CU: case I40E_PHY_TYPE_10GBASE_AOC: - ecmd->supported = SUPPORTED_10000baseT_Full; - ecmd->advertising = SUPPORTED_10000baseT_Full; + supported = SUPPORTED_10000baseT_Full; + advertising = SUPPORTED_10000baseT_Full; break; case I40E_PHY_TYPE_SGMII: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) { - ecmd->supported |= SUPPORTED_100baseT_Full; + supported |= SUPPORTED_100baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - ecmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; } break; case I40E_PHY_TYPE_40GBASE_KR4: @@ -486,25 +492,25 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, case I40E_PHY_TYPE_10GBASE_KR: case I40E_PHY_TYPE_10GBASE_KX4: case I40E_PHY_TYPE_1000BASE_KX: - ecmd->supported |= SUPPORTED_40000baseKR4_Full | - SUPPORTED_20000baseKR2_Full | - SUPPORTED_10000baseKR_Full | - SUPPORTED_10000baseKX4_Full | - SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg; - ecmd->advertising |= ADVERTISED_40000baseKR4_Full | - ADVERTISED_20000baseKR2_Full | - ADVERTISED_10000baseKR_Full | - ADVERTISED_10000baseKX4_Full | - ADVERTISED_1000baseKX_Full | - ADVERTISED_Autoneg; + supported |= SUPPORTED_40000baseKR4_Full | + SUPPORTED_20000baseKR2_Full | + SUPPORTED_10000baseKR_Full | + SUPPORTED_10000baseKX4_Full | + SUPPORTED_1000baseKX_Full | + SUPPORTED_Autoneg; + advertising |= ADVERTISED_40000baseKR4_Full | + ADVERTISED_20000baseKR2_Full | + ADVERTISED_10000baseKR_Full | + ADVERTISED_10000baseKX4_Full | + ADVERTISED_1000baseKX_Full | + ADVERTISED_Autoneg; break; case I40E_PHY_TYPE_25GBASE_KR: case I40E_PHY_TYPE_25GBASE_CR: case I40E_PHY_TYPE_25GBASE_SR: case I40E_PHY_TYPE_25GBASE_LR: - ecmd->supported = SUPPORTED_Autoneg; - ecmd->advertising = ADVERTISED_Autoneg; + supported = SUPPORTED_Autoneg; + advertising = ADVERTISED_Autoneg; /* TODO: add speeds when ethtool is ready to support*/ break; default: @@ -520,38 +526,43 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, i40e_phy_type_to_ethtool(pf, &e_supported, &e_advertising); - ecmd->supported = ecmd->supported & e_supported; - ecmd->advertising = ecmd->advertising & e_advertising; + supported = supported & e_supported; + advertising = advertising & e_advertising; /* Set speed and duplex */ switch (link_speed) { case I40E_LINK_SPEED_40GB: - ethtool_cmd_speed_set(ecmd, SPEED_40000); + cmd->base.speed = SPEED_40000; break; case I40E_LINK_SPEED_25GB: #ifdef SPEED_25000 - ethtool_cmd_speed_set(ecmd, SPEED_25000); + cmd->base.speed = SPEED_25000; #else netdev_info(netdev, "Speed is 25G, display not supported by this version of ethtool.\n"); #endif break; case I40E_LINK_SPEED_20GB: - ethtool_cmd_speed_set(ecmd, SPEED_20000); + cmd->base.speed = SPEED_20000; break; case I40E_LINK_SPEED_10GB: - ethtool_cmd_speed_set(ecmd, SPEED_10000); + cmd->base.speed = SPEED_10000; break; case I40E_LINK_SPEED_1GB: - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; case I40E_LINK_SPEED_100MB: - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; break; default: break; } - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); } /** @@ -562,18 +573,24 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, * Reports link settings that can be determined when link is down **/ static void i40e_get_settings_link_down(struct i40e_hw *hw, - struct ethtool_cmd *ecmd, + struct ethtool_link_ksettings *cmd, struct i40e_pf *pf) { + u32 supported, advertising; + /* link is down and the driver needs to fall back on * supported phy types to figure out what info to display */ - i40e_phy_type_to_ethtool(pf, &ecmd->supported, - &ecmd->advertising); + i40e_phy_type_to_ethtool(pf, &supported, &advertising); + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); /* With no link speed and duplex are unknown */ - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } /** @@ -583,74 +600,85 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw, * * Reports speed/duplex settings based on media_type **/ -static int i40e_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int i40e_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_link_status *hw_link_info = &hw->phy.link_info; bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP; + u32 advertising; if (link_up) - i40e_get_settings_link_up(hw, ecmd, netdev, pf); + i40e_get_settings_link_up(hw, cmd, netdev, pf); else - i40e_get_settings_link_down(hw, ecmd, pf); + i40e_get_settings_link_down(hw, cmd, pf); /* Now set the settings that don't rely on link being up/down */ /* Set autoneg settings */ - ecmd->autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? + cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? AUTONEG_ENABLE : AUTONEG_DISABLE); switch (hw->phy.media_type) { case I40E_MEDIA_TYPE_BACKPLANE: - ecmd->supported |= SUPPORTED_Autoneg | - SUPPORTED_Backplane; - ecmd->advertising |= ADVERTISED_Autoneg | - ADVERTISED_Backplane; - ecmd->port = PORT_NONE; + ethtool_link_ksettings_add_link_mode(cmd, supported, + Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, supported, + Backplane); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Backplane); + cmd->base.port = PORT_NONE; break; case I40E_MEDIA_TYPE_BASET: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); + cmd->base.port = PORT_TP; break; case I40E_MEDIA_TYPE_DA: case I40E_MEDIA_TYPE_CX4: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_DA; + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); + cmd->base.port = PORT_DA; break; case I40E_MEDIA_TYPE_FIBER: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->port = PORT_FIBRE; + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + cmd->base.port = PORT_FIBRE; break; case I40E_MEDIA_TYPE_UNKNOWN: default: - ecmd->port = PORT_OTHER; + cmd->base.port = PORT_OTHER; break; } - /* Set transceiver */ - ecmd->transceiver = XCVR_EXTERNAL; - /* Set flow control settings */ - ecmd->supported |= SUPPORTED_Pause; + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); switch (hw->fc.requested_mode) { case I40E_FC_FULL: - ecmd->advertising |= ADVERTISED_Pause; + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Pause); break; case I40E_FC_TX_PAUSE: - ecmd->advertising |= ADVERTISED_Asym_Pause; + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); break; case I40E_FC_RX_PAUSE: - ecmd->advertising |= (ADVERTISED_Pause | - ADVERTISED_Asym_Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); break; default: - ecmd->advertising &= ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); + ethtool_convert_link_mode_to_legacy_u32( + &advertising, cmd->link_modes.advertising); + + advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); + + ethtool_convert_legacy_u32_to_link_mode( + cmd->link_modes.advertising, advertising); break; } @@ -664,8 +692,8 @@ static int i40e_get_settings(struct net_device *netdev, * * Set speed/duplex per media_types advertised/forced **/ -static int i40e_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int i40e_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp abilities; @@ -673,12 +701,14 @@ static int i40e_set_settings(struct net_device *netdev, struct i40e_pf *pf = np->vsi->back; struct i40e_vsi *vsi = np->vsi; struct i40e_hw *hw = &pf->hw; - struct ethtool_cmd safe_ecmd; + struct ethtool_link_ksettings safe_cmd; + struct ethtool_link_ksettings copy_cmd; i40e_status status = 0; bool change = false; int err = 0; - u8 autoneg; + u32 autoneg; u32 advertise; + u32 tmp; /* Changing port settings is not supported if this isn't the * port's controlling PF @@ -706,23 +736,31 @@ static int i40e_set_settings(struct net_device *netdev, return -EOPNOTSUPP; } - /* get our own copy of the bits to check against */ - memset(&safe_ecmd, 0, sizeof(struct ethtool_cmd)); - i40e_get_settings(netdev, &safe_ecmd); + /* copy the cmd to copy_cmd to avoid modifying the origin */ + memcpy(©_cmd, cmd, sizeof(struct ethtool_link_ksettings)); - /* save autoneg and speed out of ecmd */ - autoneg = ecmd->autoneg; - advertise = ecmd->advertising; + /* get our own copy of the bits to check against */ + memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings)); + i40e_get_link_ksettings(netdev, &safe_cmd); + + /* save autoneg and speed out of cmd */ + autoneg = cmd->base.autoneg; + ethtool_convert_link_mode_to_legacy_u32(&advertise, + cmd->link_modes.advertising); /* set autoneg and speed back to what they currently are */ - ecmd->autoneg = safe_ecmd.autoneg; - ecmd->advertising = safe_ecmd.advertising; + copy_cmd.base.autoneg = safe_cmd.base.autoneg; + ethtool_convert_link_mode_to_legacy_u32( + &tmp, safe_cmd.link_modes.advertising); + ethtool_convert_legacy_u32_to_link_mode( + copy_cmd.link_modes.advertising, tmp); - ecmd->cmd = safe_ecmd.cmd; - /* If ecmd and safe_ecmd are not the same now, then they are + copy_cmd.base.cmd = safe_cmd.base.cmd; + + /* If copy_cmd and safe_cmd are not the same now, then they are * trying to set something that we do not support */ - if (memcmp(ecmd, &safe_ecmd, sizeof(struct ethtool_cmd))) + if (memcmp(©_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings))) return -EOPNOTSUPP; while (test_bit(__I40E_CONFIG_BUSY, &vsi->state)) @@ -745,7 +783,8 @@ static int i40e_set_settings(struct net_device *netdev, /* If autoneg was not already enabled */ if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) { /* If autoneg is not supported, return error */ - if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) { + if (!ethtool_link_ksettings_test_link_mode( + &safe_cmd, supported, Autoneg)) { netdev_info(netdev, "Autoneg not supported on this phy\n"); return -EINVAL; } @@ -760,7 +799,8 @@ static int i40e_set_settings(struct net_device *netdev, /* If autoneg is supported 10GBASE_T is the only PHY * that can disable it, so otherwise return error */ - if (safe_ecmd.supported & SUPPORTED_Autoneg && + if (ethtool_link_ksettings_test_link_mode( + &safe_cmd, supported, Autoneg) && hw->phy.link_info.phy_type != I40E_PHY_TYPE_10GBASE_T) { netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); @@ -773,7 +813,9 @@ static int i40e_set_settings(struct net_device *netdev, } } - if (advertise & ~safe_ecmd.supported) + ethtool_convert_link_mode_to_legacy_u32(&tmp, + safe_cmd.link_modes.supported); + if (advertise & ~tmp) return -EINVAL; if (advertise & ADVERTISED_100baseT_Full) @@ -3156,8 +3198,6 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) } static const struct ethtool_ops i40e_ethtool_ops = { - .get_settings = i40e_get_settings, - .set_settings = i40e_set_settings, .get_drvinfo = i40e_get_drvinfo, .get_regs_len = i40e_get_regs_len, .get_regs = i40e_get_regs, @@ -3194,6 +3234,8 @@ static const struct ethtool_ops i40e_ethtool_ops = { .set_priv_flags = i40e_set_priv_flags, .get_per_queue_coalesce = i40e_get_per_queue_coalesce, .set_per_queue_coalesce = i40e_set_per_queue_coalesce, + .get_link_ksettings = i40e_get_link_ksettings, + .set_link_ksettings = i40e_set_link_ksettings, }; void i40e_set_ethtool_ops(struct net_device *netdev) From 4485a841be171dbd8d3f0701b00f59d389e94ce6 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Mon, 20 Mar 2017 11:43:28 +0200 Subject: [PATCH 354/399] netfilter: fix the warning on unused refcount variable net/netfilter/nfnetlink_acct.c: In function 'nfnl_acct_try_del': net/netfilter/nfnetlink_acct.c:329:15: warning: unused variable 'refcount' [-Wunused-variable] unsigned int refcount; ^ Fixes: b54ab92b84b6 ("netfilter: refcounter conversions") Signed-off-by: Elena Reshetova Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_acct.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index f44cbd35357f..c86da174a5fc 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -326,7 +326,6 @@ static int nfnl_acct_get(struct net *net, struct sock *nfnl, static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; - unsigned int refcount; /* We want to avoid races with nfnl_acct_put. So only when the current * refcnt is 1, we decrease it to 0. From 48ce88022dbc28eebddc524d1fc2b913f03f64ba Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sat, 4 Feb 2017 23:49:03 +0100 Subject: [PATCH 355/399] i40evf: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../ethernet/intel/i40evf/i40evf_ethtool.c | 31 +++++++++---------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index 272d600c1ed0..122efbd29a19 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -64,51 +64,50 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = { (I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev)) /** - * i40evf_get_settings - Get Link Speed and Duplex settings + * i40evf_get_link_ksettings - Get Link Speed and Duplex settings * @netdev: network interface device structure - * @ecmd: ethtool command + * @cmd: ethtool command * * Reports speed/duplex settings. Because this is a VF, we don't know what * kind of link we really have, so we fake it. **/ -static int i40evf_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int i40evf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct i40evf_adapter *adapter = netdev_priv(netdev); - ecmd->supported = 0; - ecmd->autoneg = AUTONEG_DISABLE; - ecmd->transceiver = XCVR_DUMMY1; - ecmd->port = PORT_NONE; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = PORT_NONE; /* Set speed and duplex */ switch (adapter->link_speed) { case I40E_LINK_SPEED_40GB: - ethtool_cmd_speed_set(ecmd, SPEED_40000); + cmd->base.speed = SPEED_40000; break; case I40E_LINK_SPEED_25GB: #ifdef SPEED_25000 - ethtool_cmd_speed_set(ecmd, SPEED_25000); + cmd->base.speed = SPEED_25000; #else netdev_info(netdev, "Speed is 25G, display not supported by this version of ethtool.\n"); #endif break; case I40E_LINK_SPEED_20GB: - ethtool_cmd_speed_set(ecmd, SPEED_20000); + cmd->base.speed = SPEED_20000; break; case I40E_LINK_SPEED_10GB: - ethtool_cmd_speed_set(ecmd, SPEED_10000); + cmd->base.speed = SPEED_10000; break; case I40E_LINK_SPEED_1GB: - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; case I40E_LINK_SPEED_100MB: - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; break; default: break; } - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; return 0; } @@ -643,7 +642,6 @@ static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir, } static const struct ethtool_ops i40evf_ethtool_ops = { - .get_settings = i40evf_get_settings, .get_drvinfo = i40evf_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = i40evf_get_ringparam, @@ -663,6 +661,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = { .set_rxfh = i40evf_set_rxfh, .get_channels = i40evf_get_channels, .get_rxfh_key_size = i40evf_get_rxfh_key_size, + .get_link_ksettings = i40evf_get_link_ksettings, }; /** From fe0b0cd97b4f210ecd1693edba6eec10820e11f2 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:38 -0800 Subject: [PATCH 356/399] i40e: send correct port number to AdminQ when enabling UDP tunnels The firmware expects the port numbers for offloaded UDP tunnels in Little Endian format. We accidentally sent the value in Big Endian format which obviously will cause the wrong port number to be put into the UDP tunnels list. This results in VxLAN and Geneve tunnel Rx offloads being essentially disabled, unless the port number happens to be identical after byte swapping. Note that i40e_aq_add_udp_tunnel() will byteswap the parameter from host order into Little Endian so we don't need worry about passing strictly a __le16 value to the command. This patch essentially reverts b3f5c7bc88ba ("i40e: Fix for extra byte swap in tunnel setup", 2016-08-24), but in a way that makes the result much more clear to the reader. Fixes: b3f5c7bc88ba ("i40e: Fix for extra byte swap in tunnel setup", 2016-08-24) Signed-off-by: Jacob Keller Reviewed-by: Williams, Mitch A Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 3 ++- drivers/net/ethernet/intel/i40e/i40e_main.c | 17 ++++++++--------- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index a5cf5d11d0e7..fba8495a8787 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -244,7 +244,8 @@ struct i40e_tc_configuration { }; struct i40e_udp_port_config { - __be16 index; + /* AdminQ command interface expects port number in Host byte order */ + u16 index; u8 type; }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 9df0d86812e7..6e63459ceb65 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7353,7 +7353,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; i40e_status ret; - __be16 port; + u16 port; int i; if (!(pf->flags & I40E_FLAG_UDP_FILTER_SYNC)) @@ -7377,7 +7377,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) "%s %s port %d, index %d failed, err %s aq_err %s\n", pf->udp_ports[i].type ? "vxlan" : "geneve", port ? "add" : "delete", - ntohs(port), i, + port, i, i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); @@ -9014,7 +9014,7 @@ static int i40e_set_features(struct net_device *netdev, * * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found **/ -static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port) +static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port) { u8 i; @@ -9037,7 +9037,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - __be16 port = ti->port; + u16 port = ntohs(ti->port); u8 next_idx; u8 idx; @@ -9045,8 +9045,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, /* Check if port already exists */ if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) { - netdev_info(netdev, "port %d already offloaded\n", - ntohs(port)); + netdev_info(netdev, "port %d already offloaded\n", port); return; } @@ -9055,7 +9054,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) { netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n", - ntohs(port)); + port); return; } @@ -9089,7 +9088,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - __be16 port = ti->port; + u16 port = ntohs(ti->port); u8 idx; idx = i40e_get_udp_port_idx(pf, port); @@ -9121,7 +9120,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev, return; not_found: netdev_warn(netdev, "UDP port %d was not found, not deleting\n", - ntohs(port)); + port); } static int i40e_get_phys_port_id(struct net_device *netdev, From 8ce43dce6f272202dcd127e0e288b37277ca87dd Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:39 -0800 Subject: [PATCH 357/399] i40e: don't use arrays for (src|dst)_ip The code originally included src_ip and dst_ip with enough space to support ipv6 filters. However, no actual support for ipv6 filters has been implemented. Thus, remove the arrays and just use __be32 values. Should ipv6 support be added in the future, we can replace these with a union that has sizes for both values. Change-Id: I1bc04032244a80eb6ebc8a4e6c723a4a665c1dd5 Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 12 ++++++------ drivers/net/ethernet/intel/i40e/i40e_txrx.c | 12 ++++++------ 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index fba8495a8787..55ea1c0221e6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -208,8 +208,8 @@ struct i40e_fdir_filter { u8 flow_type; u8 ip4_proto; /* TX packet view of src and dst */ - __be32 dst_ip[4]; - __be32 src_ip[4]; + __be32 dst_ip; + __be32 src_ip; __be16 src_port; __be16 dst_port; __be32 sctp_v_tag; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index ceb57ad59e8f..7a22b473dbdd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2406,8 +2406,8 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf, */ fsp->h_u.tcp_ip4_spec.psrc = rule->dst_port; fsp->h_u.tcp_ip4_spec.pdst = rule->src_port; - fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip[0]; - fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip[0]; + fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip; + fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip; if (rule->dest_ctl == I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET) fsp->ring_cookie = RX_CLS_FLOW_DISC; @@ -2630,8 +2630,8 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) static bool i40e_match_fdir_input_set(struct i40e_fdir_filter *rule, struct i40e_fdir_filter *input) { - if ((rule->dst_ip[0] != input->dst_ip[0]) || - (rule->src_ip[0] != input->src_ip[0]) || + if ((rule->dst_ip != input->dst_ip) || + (rule->src_ip != input->src_ip) || (rule->dst_port != input->dst_port) || (rule->src_port != input->src_port)) return false; @@ -2807,8 +2807,8 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, */ input->dst_port = fsp->h_u.tcp_ip4_spec.psrc; input->src_port = fsp->h_u.tcp_ip4_spec.pdst; - input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; - input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; + input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src; + input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst; if (ntohl(fsp->m_ext.data[1])) { vf_id = ntohl(fsp->h_ext.data[1]); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 6eb5dc4168f3..c4d3a40a3f10 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -219,9 +219,9 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, udp = (struct udphdr *)(raw_packet + IP_HEADER_OFFSET + sizeof(struct iphdr)); - ip->daddr = fd_data->dst_ip[0]; + ip->daddr = fd_data->dst_ip; udp->dest = fd_data->dst_port; - ip->saddr = fd_data->src_ip[0]; + ip->saddr = fd_data->src_ip; udp->source = fd_data->src_port; fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP; @@ -281,9 +281,9 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, tcp = (struct tcphdr *)(raw_packet + IP_HEADER_OFFSET + sizeof(struct iphdr)); - ip->daddr = fd_data->dst_ip[0]; + ip->daddr = fd_data->dst_ip; tcp->dest = fd_data->dst_port; - ip->saddr = fd_data->src_ip[0]; + ip->saddr = fd_data->src_ip; tcp->source = fd_data->src_port; if (add) { @@ -359,8 +359,8 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, memcpy(raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN); ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET); - ip->saddr = fd_data->src_ip[0]; - ip->daddr = fd_data->dst_ip[0]; + ip->saddr = fd_data->src_ip; + ip->daddr = fd_data->dst_ip; ip->protocol = 0; fd_data->pctype = i; From 01016da1e58136518252822738fe833c662df916 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:40 -0800 Subject: [PATCH 358/399] i40e: rework exit flow of i40e_add_fdir_ethtool Refactor the exit flow of the i40e_add_fdir_ethtool function. Move the input_label to the end of the function, removing the dependency on having a non-zero return value. Add a comment explaining why it is ok not to free the fdir data structure, because the structure is now stored in the fdir_filter_list. Change-Id: I723342181d59cd0c9f3b31140c37961ba37bb242 Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 7a22b473dbdd..d16a5a6b24fc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2828,12 +2828,19 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, } ret = i40e_add_del_fdir(vsi, input, true); -free_input: if (ret) - kfree(input); - else - i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL); + goto free_input; + /* Add the input filter to the fdir_input_list, possibly replacing + * a previous filter. Do not free the input structure after adding it + * to the list as this would cause a use-after-free bug. + */ + i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL); + + return 0; + +free_input: + kfree(input); return ret; } From e5187ee3ee9a95b1aa32a9a3daf4f07a9f89c20c Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:41 -0800 Subject: [PATCH 359/399] i40e: return immediately when failing to add fdir filter Instead of setting err=true and checking this to determine when to free the raw_packet near the end of the function, simply kfree and return immediately. The resulting code is a bit cleaner and has one less variable. This also resolves a subtle bug in the ipv4 case which could fail to add the first filter and then never free the memory, resulting in a small memory leak. Change-ID: I7583aac033481dc794b4acaa14445059c8930ff1 Signed-off-by: Jacob Keller Reviewed-by: Avinash Dayanand Reviewed-by: Alan Brady Reviewed-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 33 +++++++++------------ 1 file changed, 14 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index c4d3a40a3f10..005257b4f218 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -203,7 +203,6 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; struct udphdr *udp; struct iphdr *ip; - bool err = false; u8 *raw_packet; int ret; static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, @@ -230,7 +229,9 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, dev_info(&pf->pdev->dev, "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n", fd_data->pctype, fd_data->fd_id, ret); - err = true; + /* Free the packet buffer since it wasn't added to the ring */ + kfree(raw_packet); + return -EOPNOTSUPP; } else if (I40E_DEBUG_FD & pf->hw.debug_mask) { if (add) dev_info(&pf->pdev->dev, @@ -241,10 +242,8 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, "Filter deleted for PCTYPE %d loc = %d\n", fd_data->pctype, fd_data->fd_id); } - if (err) - kfree(raw_packet); - return err ? -EOPNOTSUPP : 0; + return 0; } #define I40E_TCPIP_DUMMY_PACKET_LEN 54 @@ -263,7 +262,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; struct tcphdr *tcp; struct iphdr *ip; - bool err = false; u8 *raw_packet; int ret; /* Dummy packet */ @@ -305,12 +303,13 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); - if (ret) { dev_info(&pf->pdev->dev, "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n", fd_data->pctype, fd_data->fd_id, ret); - err = true; + /* Free the packet buffer since it wasn't added to the ring */ + kfree(raw_packet); + return -EOPNOTSUPP; } else if (I40E_DEBUG_FD & pf->hw.debug_mask) { if (add) dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n", @@ -321,10 +320,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, fd_data->pctype, fd_data->fd_id); } - if (err) - kfree(raw_packet); - - return err ? -EOPNOTSUPP : 0; + return 0; } #define I40E_IP_DUMMY_PACKET_LEN 34 @@ -343,7 +339,6 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, { struct i40e_pf *pf = vsi->back; struct iphdr *ip; - bool err = false; u8 *raw_packet; int ret; int i; @@ -365,12 +360,15 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, fd_data->pctype = i; ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); - if (ret) { dev_info(&pf->pdev->dev, "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n", fd_data->pctype, fd_data->fd_id, ret); - err = true; + /* The packet buffer wasn't added to the ring so we + * need to free it now. + */ + kfree(raw_packet); + return -EOPNOTSUPP; } else if (I40E_DEBUG_FD & pf->hw.debug_mask) { if (add) dev_info(&pf->pdev->dev, @@ -383,10 +381,7 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, } } - if (err) - kfree(raw_packet); - - return err ? -EOPNOTSUPP : 0; + return 0; } /** From 377cc24980588d03abf3a2a843b8c53dfc8b5a1b Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:42 -0800 Subject: [PATCH 360/399] i40e: exit ATR mode only when adding TCP/IPv4 filter succeeds Move ATR exit check after we have sent the TCP/IPv4 filter to the ring successfully. This avoids an issue where we potentially update the filter count without actually succeeding in adding the filter. Now, we only increment the fd_tcp_rule after we've succeeded. Additionally, we will re-enable ATR mode only after deletion of the filter is actually posted to the FDIR ring. Change-ID: If5c1dea422081cc5e2de65618b01b4c3bf6bd586 Signed-off-by: Jacob Keller Reviewed-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 34 ++++++++++----------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 005257b4f218..05f3d0d5a004 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -284,23 +284,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, ip->saddr = fd_data->src_ip; tcp->source = fd_data->src_port; - if (add) { - pf->fd_tcp_rule++; - if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - I40E_DEBUG_FD & pf->hw.debug_mask) - dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); - pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; - } else { - pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ? - (pf->fd_tcp_rule - 1) : 0; - if (pf->fd_tcp_rule == 0) { - if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - I40E_DEBUG_FD & pf->hw.debug_mask) - dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); - pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; - } - } - fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); if (ret) { @@ -320,6 +303,23 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, fd_data->pctype, fd_data->fd_id); } + if (add) { + pf->fd_tcp_rule++; + if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && + I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); + pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; + } else { + pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ? + (pf->fd_tcp_rule - 1) : 0; + if (pf->fd_tcp_rule == 0) { + if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && + I40E_DEBUG_FD & pf->hw.debug_mask) + dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); + pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; + } + } + return 0; } From e122eb7482d4af67bec77055ca2a9009867491e9 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:43 -0800 Subject: [PATCH 361/399] i40e: remove redundant check for fd_tcp_rule when restoring filters i40e_fdir_filter_restore re-adds all existing filters, which already checks when adding a TCPv4 filter to disable ATR. We don't need to make the check twice, so remove this redundant code. Change-ID: Ia0b0690e23523915199d601494557def135c9d7f Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6e63459ceb65..221e1705c031 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5466,12 +5466,6 @@ static int i40e_up_complete(struct i40e_vsi *vsi) if (vsi->type == I40E_VSI_FDIR) { /* reset fd counters */ pf->fd_add_err = pf->fd_atr_cnt = 0; - if (pf->fd_tcp_rule > 0) { - pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; - if (I40E_DEBUG_FD & pf->hw.debug_mask) - dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n"); - pf->fd_tcp_rule = 0; - } i40e_fdir_filter_restore(vsi); } From 6d069425f0fcafff5bfdd292e5f345ce55d46a43 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:44 -0800 Subject: [PATCH 362/399] i40e: reset fd_tcp_rule count when restoring filters Since we're about to reprogram the filters, we need to ensure that the fd_tcp_rule count is correctly reset to 0. Otherwise, we will keep a stale count that does not accurately reflect the number of programmed TCPv4 filters. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 221e1705c031..437b79eeb8b5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3283,6 +3283,9 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi) if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED)) return; + /* Reset FDir counters as we're replaying all existing filters */ + pf->fd_tcp_rule = 0; + hlist_for_each_entry_safe(filter, node, &pf->fdir_filter_list, fdir_node) { i40e_add_del_fdir(vsi, filter, true); From 510dd4609f581329a421fa20e1b802b629bb7ee2 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:45 -0800 Subject: [PATCH 363/399] i40e: don't re-enable ATR when flushing filters if SB has TCP4/IPv4 rules When flushing and replaying FDIR filters, it is possible we would disable ATR, and then re-enable it even though we should have kept it disabled due to existing TCP/IPv4 filters. Fix this by checking whether we have TCP4/IPv4 filters before re-enabling. Alternatively, we could instead restore ATR and then replay filters, however, this would cause us to rapidly enable and then disable ATR in some cases. Change-ID: I076e4cc1e4409bce7f98f3c213295433a4ff43d8 Signed-off-by: Jacob Keller Reviewed-by: Avinash Dayanand Reviewed-by: Alan Brady Reviewed-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 437b79eeb8b5..cc33ac835181 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6228,7 +6228,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } else { /* replay sideband filters */ i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]); - if (!disable_atr) + if (!disable_atr && !pf->fd_tcp_rule) pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); if (I40E_DEBUG_FD & pf->hw.debug_mask) From 097dbf52505962d06f9b707a3984d48d4f25fbe9 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:38:46 -0800 Subject: [PATCH 364/399] i40e: add counters for UDP/IPv4 and IPv4 filters In preparation for adding code to properly check the mask values, we will need to know the number of active filters for each type. Add counters for each filter type. Rename the already existing fd_tcp_rule to fd_tcp4_filter_cnt to match the style of other names. To avoid style warnings, avoid assigning multiple parameters at once, and fix up one other case where we did so previously. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 9 ++++++++- drivers/net/ethernet/intel/i40e/i40e_main.c | 19 +++++++++++++------ drivers/net/ethernet/intel/i40e/i40e_txrx.c | 17 +++++++++++++---- 3 files changed, 34 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 55ea1c0221e6..c0f2286c2b72 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -286,7 +286,14 @@ struct i40e_pf { u32 fd_flush_cnt; u32 fd_add_err; u32 fd_atr_cnt; - u32 fd_tcp_rule; + + /* Book-keeping of side-band filter count per flow-type. + * This is used to detect and handle input set changes for + * respective flow-type. + */ + u16 fd_tcp4_filter_cnt; + u16 fd_udp4_filter_cnt; + u16 fd_ip4_filter_cnt; struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS]; u16 pending_udp_bitmap; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index cc33ac835181..caccb8e97f1b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3284,7 +3284,9 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi) return; /* Reset FDir counters as we're replaying all existing filters */ - pf->fd_tcp_rule = 0; + pf->fd_tcp4_filter_cnt = 0; + pf->fd_udp4_filter_cnt = 0; + pf->fd_ip4_filter_cnt = 0; hlist_for_each_entry_safe(filter, node, &pf->fdir_filter_list, fdir_node) { @@ -5468,7 +5470,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi) /* replay FDIR SB filters */ if (vsi->type == I40E_VSI_FDIR) { /* reset fd counters */ - pf->fd_add_err = pf->fd_atr_cnt = 0; + pf->fd_add_err = 0; + pf->fd_atr_cnt = 0; i40e_fdir_filter_restore(vsi); } @@ -5751,7 +5754,11 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf) hlist_del(&filter->fdir_node); kfree(filter); } + pf->fdir_pf_active_filters = 0; + pf->fd_tcp4_filter_cnt = 0; + pf->fd_udp4_filter_cnt = 0; + pf->fd_ip4_filter_cnt = 0; } /** @@ -6156,7 +6163,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) { if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->fd_tcp_rule == 0)) { + (pf->fd_tcp4_filter_cnt == 0)) { pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n"); @@ -6228,7 +6235,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } else { /* replay sideband filters */ i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]); - if (!disable_atr && !pf->fd_tcp_rule) + if (!disable_atr && !pf->fd_tcp4_filter_cnt) pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED; clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); if (I40E_DEBUG_FD & pf->hw.debug_mask) @@ -8937,8 +8944,8 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features) pf->flags &= ~I40E_FLAG_FD_SB_ENABLED; pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED; /* reset fd counters */ - pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0; - pf->fdir_pf_active_filters = 0; + pf->fd_add_err = 0; + pf->fd_atr_cnt = 0; /* if ATR was auto disabled it can be re-enabled. */ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 05f3d0d5a004..3880e417f167 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -243,6 +243,11 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, fd_data->pctype, fd_data->fd_id); } + if (add) + pf->fd_udp4_filter_cnt++; + else + pf->fd_udp4_filter_cnt--; + return 0; } @@ -304,15 +309,14 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, } if (add) { - pf->fd_tcp_rule++; + pf->fd_tcp4_filter_cnt++; if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED; } else { - pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ? - (pf->fd_tcp_rule - 1) : 0; - if (pf->fd_tcp_rule == 0) { + pf->fd_tcp4_filter_cnt--; + if (pf->fd_tcp4_filter_cnt == 0) { if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); @@ -381,6 +385,11 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, } } + if (add) + pf->fd_ip4_filter_cnt++; + else + pf->fd_ip4_filter_cnt--; + return 0; } From 1ec8deac8c63505194e773b9657824ed3c2fbdd8 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:39:12 -0800 Subject: [PATCH 365/399] i40e: explicitly fail on extended MAC field for ethtool_rx_flow_spec Although we will fail the filter later due to checking flow_type which will have a bogus invalid type, it is possible future refactoring will remove this hidden failure case. Avoid a possible issue in the future by explicitly checking the flow type at the start. Change-Id: Ia98eb26f7b93ccbe38c7141e8f203ef496fc6598 Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index d16a5a6b24fc..905d66e87247 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2771,6 +2771,10 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + /* Extended MAC field is not supported */ + if (fsp->flow_type & FLOW_MAC_EXT) + return -EINVAL; + if (fsp->location >= (pf->hw.func_caps.fd_filters_best_effort + pf->hw.func_caps.fd_filters_guaranteed)) { return -EINVAL; From c6da525de724e3fbe439b8dad385395bb4fd2211 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 6 Feb 2017 14:39:13 -0800 Subject: [PATCH 366/399] i40e: always remove old filter when adding new FDir filter The previous code relied on i40e_match_fdir_input_set to determine when determining whether to free the old filter. Change this code so that we simply unconditionally delete the old filter, even if it's identical to the new filter. This ensures that we don't leak any memory, and that we always update the filters as expected. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/i40e/i40e_ethtool.c | 32 ++++--------------- 1 file changed, 7 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 905d66e87247..1c3805b4fcf3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2620,24 +2620,6 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) return 0; } -/** - * i40e_match_fdir_input_set - Match a new filter against an existing one - * @rule: The filter already added - * @input: The new filter to comapre against - * - * Returns true if the two input set match - **/ -static bool i40e_match_fdir_input_set(struct i40e_fdir_filter *rule, - struct i40e_fdir_filter *input) -{ - if ((rule->dst_ip != input->dst_ip) || - (rule->src_ip != input->src_ip) || - (rule->dst_port != input->dst_port) || - (rule->src_port != input->src_port)) - return false; - return true; -} - /** * i40e_update_ethtool_fdir_entry - Updates the fdir filter entry * @vsi: Pointer to the targeted VSI @@ -2673,22 +2655,22 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi, /* if there is an old rule occupying our place remove it */ if (rule && (rule->fd_id == sw_idx)) { - if (input && !i40e_match_fdir_input_set(rule, input)) - err = i40e_add_del_fdir(vsi, rule, false); - else if (!input) - err = i40e_add_del_fdir(vsi, rule, false); + /* Remove this rule, since we're either deleting it, or + * replacing it. + */ + err = i40e_add_del_fdir(vsi, rule, false); hlist_del(&rule->fdir_node); kfree(rule); pf->fdir_pf_active_filters--; } - /* If no input this was a delete, err should be 0 if a rule was - * successfully found and removed from the list else -EINVAL + /* If we weren't given an input, this is a delete, so just return the + * error code indicating if there was an entry at the requested slot */ if (!input) return err; - /* initialize node and set software index */ + /* Otherwise, install the new rule as requested */ INIT_HLIST_NODE(&input->fdir_node); /* add filter to the list */ From 6df014cffbe335ea7f41ee5324d8ba2047d3f0d0 Mon Sep 17 00:00:00 2001 From: Ezequiel Lara Gomez Date: Sat, 11 Mar 2017 20:06:54 +0000 Subject: [PATCH 367/399] Enable tx timestamping on loopback and dummy This enables developing code that uses SOF_TIMESTAMPING_TX_SOFTWARE by using localhost addresses (without needing to send packets outside), as well as enabling unit and functional testing of TX timestamping code without needing hardware support or network access. It also fulfills the expectation of software network devices supporting software-based timestamping. Tested on qemu using txtimestamping.c from the kernel selftests, and ethtool -T. Signed-off-by: Ezequiel Lara Gomez Signed-off-by: David S. Miller --- drivers/net/dummy.c | 15 +++++++++++++++ drivers/net/loopback.c | 15 +++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 2c80611b94ae..149244aac20a 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include @@ -125,6 +126,7 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev) dstats->tx_bytes += skb->len; u64_stats_update_end(&dstats->syncp); + skb_tx_timestamp(skb); dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -304,8 +306,21 @@ static void dummy_get_drvinfo(struct net_device *dev, strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } +static int dummy_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *ts_info) +{ + ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + ts_info->phc_index = -1; + + return 0; +}; + static const struct ethtool_ops dummy_ethtool_ops = { .get_drvinfo = dummy_get_drvinfo, + .get_ts_info = dummy_get_ts_info, }; static void dummy_free_netdev(struct net_device *dev) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index b23b71981fd5..8d179d616993 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -55,6 +55,7 @@ #include #include #include +#include #include #include @@ -74,6 +75,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, struct pcpu_lstats *lb_stats; int len; + skb_tx_timestamp(skb); skb_orphan(skb); /* Before queueing this packet to netif_rx(), @@ -129,8 +131,21 @@ static u32 always_on(struct net_device *dev) return 1; } +static int loopback_get_ts_info(struct net_device *netdev, + struct ethtool_ts_info *ts_info) +{ + ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + ts_info->phc_index = -1; + + return 0; +}; + static const struct ethtool_ops loopback_ethtool_ops = { .get_link = always_on, + .get_ts_info = loopback_get_ts_info, }; static int loopback_dev_init(struct net_device *dev) From b3407c8e5eb78e4e0b57a97a4dd2e411354b60cd Mon Sep 17 00:00:00 2001 From: Ezequiel Lara Gomez Date: Sat, 11 Mar 2017 20:06:01 +0000 Subject: [PATCH 368/399] Cleanup some warning from timestamping code. Following checkpatch.pl recommendations (which include replacing with the , since linux/io.h includes it). Signed-off-by: Ezequiel Lara Gomez Signed-off-by: David S. Miller --- drivers/net/loopback.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 8d179d616993..224f65cb576b 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -13,7 +13,7 @@ * * Alan Cox : Fixed oddments for NET3.014 * Alan Cox : Rejig for NET3.029 snap #3 - * Alan Cox : Fixed NET3.029 bugs and sped up + * Alan Cox : Fixed NET3.029 bugs and sped up * Larry McVoy : Tiny tweak to double performance * Alan Cox : Backed out LMV's tweak - the linux mm * can't take it... @@ -41,7 +41,7 @@ #include #include -#include +#include #include #include @@ -65,8 +65,7 @@ struct pcpu_lstats { struct u64_stats_sync syncp; }; -/* - * The higher levels take care of making this non-reentrant (it's +/* The higher levels take care of making this non-reentrant (it's * called with bh's disabled). */ static netdev_tx_t loopback_xmit(struct sk_buff *skb, @@ -164,14 +163,13 @@ static void loopback_dev_free(struct net_device *dev) } static const struct net_device_ops loopback_ops = { - .ndo_init = loopback_dev_init, - .ndo_start_xmit= loopback_xmit, + .ndo_init = loopback_dev_init, + .ndo_start_xmit = loopback_xmit, .ndo_get_stats64 = loopback_get_stats64, .ndo_set_mac_address = eth_mac_addr, }; -/* - * The loopback device is special. There is only one instance +/* The loopback device is special. There is only one instance * per network namespace. */ static void loopback_setup(struct net_device *dev) @@ -185,7 +183,7 @@ static void loopback_setup(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; netif_keep_dst(dev); dev->hw_features = NETIF_F_GSO_SOFTWARE; - dev->features = NETIF_F_SG | NETIF_F_FRAGLIST + dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | NETIF_F_HW_CSUM | NETIF_F_RXCSUM @@ -221,7 +219,6 @@ static __net_init int loopback_net_init(struct net *net) net->loopback_dev = dev; return 0; - out_free_netdev: free_netdev(dev); out: @@ -232,5 +229,5 @@ static __net_init int loopback_net_init(struct net *net) /* Registered in net/core/dev.c */ struct pernet_operations __net_initdata loopback_net_ops = { - .init = loopback_net_init, + .init = loopback_net_init, }; From 88997e4208aea117627898e5f6f9801cf3cd42d2 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Wed, 15 Mar 2017 17:41:14 -0700 Subject: [PATCH 369/399] net/8021q: create device with all possible features in wanted_features wanted_features is a set of features which have to be enabled if a hardware allows that. Currently when a vlan device is created, its wanted_features is set to current features of its base device. The problem is that the base device can get new features and they are not propagated to vlan-s of this device. If we look at bonding devices, they doesn't have this problem and this patch suggests to fix this issue by the same way how it works for bonding devices. We meet this problem, when we try to create a vlan device over a bonding device. When a system are booting, real devices require time to be initialized, so bonding devices created without slaves, then vlan devices are created and only then ethernet devices are added to the bonding device. As a result we have vlan devices with disabled scatter-gather. * create a bonding device $ ip link add bond0 type bond $ ethtool -k bond0 | grep scatter scatter-gather: off tx-scatter-gather: off [requested on] tx-scatter-gather-fraglist: off [requested on] * create a vlan device $ ip link add link bond0 name bond0.10 type vlan id 10 $ ethtool -k bond0.10 | grep scatter scatter-gather: off tx-scatter-gather: off tx-scatter-gather-fraglist: off * Add a slave device to bond0 $ ip link set dev eth0 master bond0 And now we can see that the bond0 device has got the scatter-gather feature, but the bond0.10 hasn't got it. [root@laptop linux-task-diag]# ethtool -k bond0 | grep scatter scatter-gather: on tx-scatter-gather: on tx-scatter-gather-fraglist: on [root@laptop linux-task-diag]# ethtool -k bond0.10 | grep scatter scatter-gather: off tx-scatter-gather: off tx-scatter-gather-fraglist: off With this patch the vlan device will get all new features from the bonding device. Here is a call trace how features which are set in this patch reach dev->wanted_features. register_netdevice vlan_dev_init ... dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | NETIF_F_ALL_FCOE; dev->features |= dev->hw_features; ... dev->wanted_features = dev->features & dev->hw_features; __netdev_update_features(dev); vlan_dev_fix_features ... Cc: Alexey Kuznetsov Cc: Patrick McHardy Cc: "David S. Miller" Signed-off-by: Andrei Vagin Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e97ab824e368..9ee5787634e5 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -562,8 +562,7 @@ static int vlan_dev_init(struct net_device *dev) NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | NETIF_F_ALL_FCOE; - dev->features |= real_dev->vlan_features | NETIF_F_LLTX | - NETIF_F_GSO_SOFTWARE; + dev->features |= dev->hw_features | NETIF_F_LLTX; dev->gso_max_size = real_dev->gso_max_size; dev->gso_max_segs = real_dev->gso_max_segs; if (dev->features & NETIF_F_VLAN_FEATURES) From bf4e0a3db97eb882368fd82980b3b1fa0b5b9778 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 16 Mar 2017 15:28:00 +0200 Subject: [PATCH 370/399] net: ipv4: add support for ECMP hash policy choice This patch adds support for ECMP hash policy choice via a new sysctl called fib_multipath_hash_policy and also adds support for L4 hashes. The current values for fib_multipath_hash_policy are: 0 - layer 3 (default) 1 - layer 4 If there's an skb hash already set and it matches the chosen policy then it will be used instead of being calculated (currently only for L4). In L3 mode we always calculate the hash due to the ICMP error special case, the flow dissector's field consistentification should handle the address order thus we can remove the address reversals. If the skb is provided we always use it for the hash calculation, otherwise we fallback to fl4, that is if skb is NULL fl4 has to be set. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 8 +++ include/net/ip_fib.h | 14 ++-- include/net/netns/ipv4.h | 1 + include/net/route.h | 6 +- net/ipv4/fib_semantics.c | 11 +-- net/ipv4/icmp.c | 19 +----- net/ipv4/route.c | 94 +++++++++++++++++++------- net/ipv4/sysctl_net_ipv4.c | 9 +++ 8 files changed, 101 insertions(+), 61 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ed3d0791eb27..b57308e76b1d 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -73,6 +73,14 @@ fib_multipath_use_neigh - BOOLEAN 0 - disabled 1 - enabled +fib_multipath_hash_policy - INTEGER + Controls which hash policy to use for multipath routes. Only valid + for kernels built with CONFIG_IP_ROUTE_MULTIPATH enabled. + Default: 0 (Layer 3) + Possible values: + 0 - Layer 3 + 1 - Layer 4 + route/max_size - INTEGER Maximum number of routes allowed in the kernel. Increase this when using large numbers of interfaces and/or routes. diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 272e62e139e0..6692c5758b33 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -395,17 +395,13 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned int nh_flags); -extern u32 fib_multipath_secret __read_mostly; - -static inline int fib_multipath_hash(__be32 saddr, __be32 daddr) -{ - return jhash_2words((__force u32)saddr, (__force u32)daddr, - fib_multipath_secret) >> 1; -} - +#ifdef CONFIG_IP_ROUTE_MULTIPATH +int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, + const struct sk_buff *skb); +#endif void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, - struct flowi4 *fl4, int mp_hash); + struct flowi4 *fl4, const struct sk_buff *skb); /* Exported by fib_trie.c */ void fib_trie_init(void); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2e9d649ba169..a0e89190a3e9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -151,6 +151,7 @@ struct netns_ipv4 { #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH int sysctl_fib_multipath_use_neigh; + int sysctl_fib_multipath_hash_policy; #endif unsigned int fib_seq; /* protected by rtnl_mutex */ diff --git a/include/net/route.h b/include/net/route.h index c0874c87c173..2cc0e14c6359 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -113,13 +113,13 @@ struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); -struct rtable *__ip_route_output_key_hash(struct net *, struct flowi4 *flp, - int mp_hash); +struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp, + const struct sk_buff *skb); static inline struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp) { - return __ip_route_output_key_hash(net, flp, -1); + return __ip_route_output_key_hash(net, flp, NULL); } struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 317026a39cfa..da449ddb8cc1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -57,7 +57,6 @@ static unsigned int fib_info_cnt; static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE]; #ifdef CONFIG_IP_ROUTE_MULTIPATH -u32 fib_multipath_secret __read_mostly; #define for_nexthops(fi) { \ int nhsel; const struct fib_nh *nh; \ @@ -576,9 +575,6 @@ static void fib_rebalance(struct fib_info *fi) atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); } endfor_nexthops(fi); - - net_get_random_once(&fib_multipath_secret, - sizeof(fib_multipath_secret)); } static inline void fib_add_weight(struct fib_info *fi, @@ -1641,7 +1637,7 @@ void fib_select_multipath(struct fib_result *res, int hash) #endif void fib_select_path(struct net *net, struct fib_result *res, - struct flowi4 *fl4, int mp_hash) + struct flowi4 *fl4, const struct sk_buff *skb) { bool oif_check; @@ -1650,10 +1646,9 @@ void fib_select_path(struct net *net, struct fib_result *res, #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi->fib_nhs > 1 && oif_check) { - if (mp_hash < 0) - mp_hash = get_hash_from_flowi4(fl4) >> 1; + int h = fib_multipath_hash(res->fi, fl4, skb); - fib_select_multipath(res, mp_hash); + fib_select_multipath(res, h); } else #endif diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index fc310db2708b..43318b5f5647 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -464,22 +464,6 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) local_bh_enable(); } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - -/* Source and destination is swapped. See ip_multipath_icmp_hash */ -static int icmp_multipath_hash_skb(const struct sk_buff *skb) -{ - const struct iphdr *iph = ip_hdr(skb); - - return fib_multipath_hash(iph->daddr, iph->saddr); -} - -#else - -#define icmp_multipath_hash_skb(skb) (-1) - -#endif - static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, @@ -505,8 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key_hash(net, fl4, - icmp_multipath_hash_skb(skb_in)); + rt = __ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8471dd116771..5dda1ef81c7e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1734,45 +1734,97 @@ static int __mkroute_input(struct sk_buff *skb, } #ifdef CONFIG_IP_ROUTE_MULTIPATH - /* To make ICMP packets follow the right flow, the multipath hash is - * calculated from the inner IP addresses in reverse order. + * calculated from the inner IP addresses. */ -static int ip_multipath_icmp_hash(struct sk_buff *skb) +static void ip_multipath_l3_keys(const struct sk_buff *skb, + struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); - struct icmphdr _icmph; + const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; - const struct iphdr *inner_iph; + struct icmphdr _icmph; + + hash_keys->addrs.v4addrs.src = outer_iph->saddr; + hash_keys->addrs.v4addrs.dst = outer_iph->daddr; + if (likely(outer_iph->protocol != IPPROTO_ICMP)) + return; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) - goto standard_hash; + return; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) - goto standard_hash; + return; if (icmph->type != ICMP_DEST_UNREACH && icmph->type != ICMP_REDIRECT && icmph->type != ICMP_TIME_EXCEEDED && - icmph->type != ICMP_PARAMETERPROB) { - goto standard_hash; - } + icmph->type != ICMP_PARAMETERPROB) + return; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) - goto standard_hash; - - return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr); - -standard_hash: - return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr); + return; + hash_keys->addrs.v4addrs.src = inner_iph->saddr; + hash_keys->addrs.v4addrs.dst = inner_iph->daddr; } +/* if skb is set it will be used and fl4 can be NULL */ +int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, + const struct sk_buff *skb) +{ + struct net *net = fi->fib_net; + struct flow_keys hash_keys; + u32 mhash; + + switch (net->ipv4.sysctl_fib_multipath_hash_policy) { + case 0: + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (skb) { + ip_multipath_l3_keys(skb, &hash_keys); + } else { + hash_keys.addrs.v4addrs.src = fl4->saddr; + hash_keys.addrs.v4addrs.dst = fl4->daddr; + } + break; + case 1: + /* skb is currently provided only when forwarding */ + if (skb) { + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + struct flow_keys keys; + + /* short-circuit if we already have L4 hash present */ + if (skb->l4_hash) + return skb_get_hash_raw(skb) >> 1; + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, flag); + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + hash_keys.ports.src = keys.ports.src; + hash_keys.ports.dst = keys.ports.dst; + hash_keys.basic.ip_proto = keys.basic.ip_proto; + } else { + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + hash_keys.addrs.v4addrs.src = fl4->saddr; + hash_keys.addrs.v4addrs.dst = fl4->daddr; + hash_keys.ports.src = fl4->fl4_sport; + hash_keys.ports.dst = fl4->fl4_dport; + hash_keys.basic.ip_proto = fl4->flowi4_proto; + } + break; + } + mhash = flow_hash_from_keys(&hash_keys); + + return mhash >> 1; +} +EXPORT_SYMBOL_GPL(fib_multipath_hash); #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, @@ -1782,12 +1834,8 @@ static int ip_mkroute_input(struct sk_buff *skb, { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) { - int h; + int h = fib_multipath_hash(res->fi, NULL, skb); - if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP)) - h = ip_multipath_icmp_hash(skb); - else - h = fib_multipath_hash(saddr, daddr); fib_select_multipath(res, h); } #endif @@ -2203,7 +2251,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, */ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, - int mp_hash) + const struct sk_buff *skb) { struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); @@ -2365,7 +2413,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, goto make_route; } - fib_select_path(net, &res, fl4, mp_hash); + fib_select_path(net, &res, fl4, skb); dev_out = FIB_RES_DEV(res); fl4->flowi4_oif = dev_out->ifindex; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 11aaef0939b2..711c3e2e17b1 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -997,6 +997,15 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "fib_multipath_hash_policy", + .data = &init_net.ipv4.sysctl_fib_multipath_hash_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, #endif { .procname = "ip_unprivileged_port_start", From 37a30b435b92a6b577795c642b6326fd0ea96e3f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 16 Mar 2017 10:27:08 -0700 Subject: [PATCH 371/399] net: bcmgenet: Track per TX/RX rings statistics __bcmgenet_tx_reclaim() is currently summing TX bytes/packets in a way that is not SMP friendly, mutliples CPUs could run __bcmgenet_tx_reclaim() independently and still update stats->tx_bytes and stats->tx_packets, cloberring the other CPUs statistics. Fix this by tracking per RX and TX rings the number of bytes, packets, dropped and errors statistics, and provide a bcmgenet_get_stats() function which aggregates everything and returns a consistent output. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/genet/bcmgenet.c | 77 +++++++++++++++++-- .../net/ethernet/broadcom/genet/bcmgenet.h | 6 ++ 2 files changed, 75 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 44f9c0a1f85d..f493276d432a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -707,6 +707,19 @@ struct bcmgenet_stats { .reg_offset = offset, \ } +#define STAT_GENET_Q(num) \ + STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \ + tx_rings[num].packets), \ + STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \ + tx_rings[num].bytes), \ + STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \ + rx_rings[num].bytes), \ + STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \ + rx_rings[num].packets), \ + STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \ + rx_rings[num].errors), \ + STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \ + rx_rings[num].dropped) /* There is a 0xC gap between the end of RX and beginning of TX stats and then * between the end of TX stats and the beginning of the RX RUNT @@ -801,6 +814,12 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = { STAT_GENET_SOFT_MIB("alloc_rx_buff_failed", mib.alloc_rx_buff_failed), STAT_GENET_SOFT_MIB("rx_dma_failed", mib.rx_dma_failed), STAT_GENET_SOFT_MIB("tx_dma_failed", mib.tx_dma_failed), + /* Per TX queues */ + STAT_GENET_Q(0), + STAT_GENET_Q(1), + STAT_GENET_Q(2), + STAT_GENET_Q(3), + STAT_GENET_Q(16), }; #define BCMGENET_STATS_LEN ARRAY_SIZE(bcmgenet_gstrings_stats) @@ -1298,8 +1317,8 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, ring->free_bds += txbds_processed; ring->c_index = c_index; - dev->stats.tx_packets += pkts_compl; - dev->stats.tx_bytes += bytes_compl; + ring->packets += pkts_compl; + ring->bytes += bytes_compl; netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue), pkts_compl, bytes_compl); @@ -1694,8 +1713,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, DMA_P_INDEX_DISCARD_CNT_MASK; if (discards > ring->old_discards) { discards = discards - ring->old_discards; - dev->stats.rx_missed_errors += discards; - dev->stats.rx_errors += discards; + ring->errors += discards; ring->old_discards += discards; /* Clear HW register when we reach 75% of maximum 0xFFFF */ @@ -1718,7 +1736,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, skb = bcmgenet_rx_refill(priv, cb); if (unlikely(!skb)) { - dev->stats.rx_dropped++; + ring->dropped++; goto next; } @@ -1746,7 +1764,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) { netif_err(priv, rx_status, dev, "dropping fragmented packet!\n"); - dev->stats.rx_errors++; + ring->errors++; dev_kfree_skb_any(skb); goto next; } @@ -1795,8 +1813,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, /*Finish setting up the received SKB and send it to the kernel*/ skb->protocol = eth_type_trans(skb, priv->dev); - dev->stats.rx_packets++; - dev->stats.rx_bytes += len; + ring->packets++; + ring->bytes += len; if (dma_flag & DMA_RX_MULT) dev->stats.multicast++; @@ -3134,6 +3152,48 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p) return 0; } +static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + unsigned long tx_bytes = 0, tx_packets = 0; + unsigned long rx_bytes = 0, rx_packets = 0; + unsigned long rx_errors = 0, rx_dropped = 0; + struct bcmgenet_tx_ring *tx_ring; + struct bcmgenet_rx_ring *rx_ring; + unsigned int q; + + for (q = 0; q < priv->hw_params->tx_queues; q++) { + tx_ring = &priv->tx_rings[q]; + tx_bytes += tx_ring->bytes; + tx_packets += tx_ring->packets; + } + tx_ring = &priv->tx_rings[DESC_INDEX]; + tx_bytes += tx_ring->bytes; + tx_packets += tx_ring->packets; + + for (q = 0; q < priv->hw_params->rx_queues; q++) { + rx_ring = &priv->rx_rings[q]; + + rx_bytes += rx_ring->bytes; + rx_packets += rx_ring->packets; + rx_errors += rx_ring->errors; + rx_dropped += rx_ring->dropped; + } + rx_ring = &priv->rx_rings[DESC_INDEX]; + rx_bytes += rx_ring->bytes; + rx_packets += rx_ring->packets; + rx_errors += rx_ring->errors; + rx_dropped += rx_ring->dropped; + + dev->stats.tx_bytes = tx_bytes; + dev->stats.tx_packets = tx_packets; + dev->stats.rx_bytes = rx_bytes; + dev->stats.rx_packets = rx_packets; + dev->stats.rx_errors = rx_errors; + dev->stats.rx_missed_errors = rx_errors; + return &dev->stats; +} + static const struct net_device_ops bcmgenet_netdev_ops = { .ndo_open = bcmgenet_open, .ndo_stop = bcmgenet_close, @@ -3146,6 +3206,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = bcmgenet_poll_controller, #endif + .ndo_get_stats = bcmgenet_get_stats, }; /* Array of GENET hardware parameters/characteristics */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 5692c0582434..efd07020b89f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -552,6 +552,8 @@ struct bcmgenet_skb_cb { struct bcmgenet_tx_ring { spinlock_t lock; /* ring lock */ struct napi_struct napi; /* NAPI per tx queue */ + unsigned long packets; + unsigned long bytes; unsigned int index; /* ring index */ unsigned int queue; /* queue index */ struct enet_cb *cbs; /* tx ring buffer control block*/ @@ -570,6 +572,10 @@ struct bcmgenet_tx_ring { struct bcmgenet_rx_ring { struct napi_struct napi; /* Rx NAPI struct */ + unsigned long bytes; + unsigned long packets; + unsigned long errors; + unsigned long dropped; unsigned int index; /* Rx ring index */ struct enet_cb *cbs; /* Rx ring buffer control block */ unsigned int size; /* Rx ring size */ From 8bae3551e93de4e8a5b959c495b06de9264be0d5 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:47 +0100 Subject: [PATCH 372/399] net: usb: usbnet: add new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We add the new api {get|set}_link_ksettings to this driver. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Acked-by: Oliver Neukum Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 36 ++++++++++++++++++++++++++++++++++++ include/linux/usb/usbnet.h | 4 ++++ 2 files changed, 40 insertions(+) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 3de65ea6531a..1b40b189435a 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -980,6 +980,40 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd) } EXPORT_SYMBOL_GPL(usbnet_set_settings); +int usbnet_get_link_ksettings(struct net_device *net, + struct ethtool_link_ksettings *cmd) +{ + struct usbnet *dev = netdev_priv(net); + + if (!dev->mii.mdio_read) + return -EOPNOTSUPP; + + return mii_ethtool_get_link_ksettings(&dev->mii, cmd); +} +EXPORT_SYMBOL_GPL(usbnet_get_link_ksettings); + +int usbnet_set_link_ksettings(struct net_device *net, + const struct ethtool_link_ksettings *cmd) +{ + struct usbnet *dev = netdev_priv(net); + int retval; + + if (!dev->mii.mdio_write) + return -EOPNOTSUPP; + + retval = mii_ethtool_set_link_ksettings(&dev->mii, cmd); + + /* link speed/duplex might have changed */ + if (dev->driver_info->link_reset) + dev->driver_info->link_reset(dev); + + /* hard_mtu or rx_urb_size may change in link_reset() */ + usbnet_update_max_qlen(dev); + + return retval; +} +EXPORT_SYMBOL_GPL(usbnet_set_link_ksettings); + u32 usbnet_get_link (struct net_device *net) { struct usbnet *dev = netdev_priv(net); @@ -1046,6 +1080,8 @@ static const struct ethtool_ops usbnet_ethtool_ops = { .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_ts_info = ethtool_op_get_ts_info, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; /*-------------------------------------------------------------------------*/ diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 6e0ce8c7b8cb..5bd80078b7fe 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -265,6 +265,10 @@ extern int usbnet_get_settings(struct net_device *net, struct ethtool_cmd *cmd); extern int usbnet_set_settings(struct net_device *net, struct ethtool_cmd *cmd); +extern int usbnet_get_link_ksettings(struct net_device *net, + struct ethtool_link_ksettings *cmd); +extern int usbnet_set_link_ksettings(struct net_device *net, + const struct ethtool_link_ksettings *cmd); extern u32 usbnet_get_link(struct net_device *net); extern u32 usbnet_get_msglevel(struct net_device *); extern void usbnet_set_msglevel(struct net_device *, u32); From eaf9a32a448bf01468bee5737c9391110ec05725 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:48 +0100 Subject: [PATCH 373/399] net: usb: smsc95xx: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 831aa33d078a..4a8bf960cbb9 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -853,32 +853,32 @@ static void set_mdix_status(struct net_device *net, __u8 mdix_ctrl) pdata->mdix_ctrl = mdix_ctrl; } -static int smsc95xx_get_settings(struct net_device *net, - struct ethtool_cmd *cmd) +static int smsc95xx_get_link_ksettings(struct net_device *net, + struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); int retval; - retval = usbnet_get_settings(net, cmd); + retval = usbnet_get_link_ksettings(net, cmd); - cmd->eth_tp_mdix = pdata->mdix_ctrl; - cmd->eth_tp_mdix_ctrl = pdata->mdix_ctrl; + cmd->base.eth_tp_mdix = pdata->mdix_ctrl; + cmd->base.eth_tp_mdix_ctrl = pdata->mdix_ctrl; return retval; } -static int smsc95xx_set_settings(struct net_device *net, - struct ethtool_cmd *cmd) +static int smsc95xx_set_link_ksettings(struct net_device *net, + const struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); int retval; - if (pdata->mdix_ctrl != cmd->eth_tp_mdix_ctrl) - set_mdix_status(net, cmd->eth_tp_mdix_ctrl); + if (pdata->mdix_ctrl != cmd->base.eth_tp_mdix_ctrl) + set_mdix_status(net, cmd->base.eth_tp_mdix_ctrl); - retval = usbnet_set_settings(net, cmd); + retval = usbnet_set_link_ksettings(net, cmd); return retval; } @@ -889,8 +889,6 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .get_drvinfo = usbnet_get_drvinfo, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, - .get_settings = smsc95xx_get_settings, - .set_settings = smsc95xx_set_settings, .get_eeprom_len = smsc95xx_ethtool_get_eeprom_len, .get_eeprom = smsc95xx_ethtool_get_eeprom, .set_eeprom = smsc95xx_ethtool_set_eeprom, @@ -898,6 +896,8 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .get_regs = smsc95xx_ethtool_getregs, .get_wol = smsc95xx_ethtool_get_wol, .set_wol = smsc95xx_ethtool_set_wol, + .get_link_ksettings = smsc95xx_get_link_ksettings, + .set_link_ksettings = smsc95xx_set_link_ksettings, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) From d8c3de2e8603f31de502f63e6997e55e7439eab9 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:49 +0100 Subject: [PATCH 374/399] net: usb: sr9800: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/sr9800.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index a50df0d8fb9a..a696b628782c 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -524,9 +524,9 @@ static const struct ethtool_ops sr9800_ethtool_ops = { .set_wol = sr_set_wol, .get_eeprom_len = sr_get_eeprom_len, .get_eeprom = sr_get_eeprom, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static int sr9800_link_reset(struct usbnet *dev) From d0b3ab309fd896f80fefa4b1d1a7e45de1fa8a36 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:50 +0100 Subject: [PATCH 375/399] net: usb: cdc_ncm: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ncm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index f317984f7536..b6c1d3abad96 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -131,8 +131,6 @@ static void cdc_ncm_get_strings(struct net_device __always_unused *netdev, u32 s static void cdc_ncm_update_rxtx_max(struct usbnet *dev, u32 new_rx, u32 new_tx); static const struct ethtool_ops cdc_ncm_ethtool_ops = { - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .get_link = usbnet_get_link, .nway_reset = usbnet_nway_reset, .get_drvinfo = usbnet_get_drvinfo, @@ -142,6 +140,8 @@ static const struct ethtool_ops cdc_ncm_ethtool_ops = { .get_sset_count = cdc_ncm_get_sset_count, .get_strings = cdc_ncm_get_strings, .get_ethtool_stats = cdc_ncm_get_ethtool_stats, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static u32 cdc_ncm_check_rx_max(struct usbnet *dev, u32 new_rx) From bcb58f777eb1b7030fbe525477530cbf0ac6480d Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:51 +0100 Subject: [PATCH 376/399] net: usb: dm9601: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/dm9601.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 0b4bdd39106b..fea1b64ca26a 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -281,9 +281,9 @@ static const struct ethtool_ops dm9601_ethtool_ops = { .set_msglevel = usbnet_set_msglevel, .get_eeprom_len = dm9601_get_eeprom_len, .get_eeprom = dm9601_get_eeprom, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static void dm9601_set_multicast(struct net_device *net) From 17400f77b87cd2cf29fde358a05d5efc7b0eabab Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:52 +0100 Subject: [PATCH 377/399] net: usb: mcs7830: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Tested-by: poma Signed-off-by: David S. Miller --- drivers/net/usb/mcs7830.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index 4f345bd4e6e2..5771ff261fa8 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -464,9 +464,9 @@ static const struct ethtool_ops mcs7830_ethtool_ops = { .get_link = usbnet_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static const struct net_device_ops mcs7830_netdev_ops = { From 90a8e95e87720eaf202fb40cc420da02d9072b23 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:53 +0100 Subject: [PATCH 378/399] net: usb: sierra_net: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/sierra_net.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index ac69f28d92d2..c8f60b887c22 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -648,9 +648,9 @@ static const struct ethtool_ops sierra_net_ethtool_ops = { .get_link = sierra_net_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static int sierra_net_get_fw_attr(struct usbnet *dev, u16 *datap) From a44017a504b4d9161eeefbae067af3ef0147526d Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:54 +0100 Subject: [PATCH 379/399] net: usb: smsc75xx: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/smsc75xx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 0b17b40d7a4f..1ab0ff43c6a2 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -743,13 +743,13 @@ static const struct ethtool_ops smsc75xx_ethtool_ops = { .get_drvinfo = usbnet_get_drvinfo, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .get_eeprom_len = smsc75xx_ethtool_get_eeprom_len, .get_eeprom = smsc75xx_ethtool_get_eeprom, .set_eeprom = smsc75xx_ethtool_set_eeprom, .get_wol = smsc75xx_ethtool_get_wol, .set_wol = smsc75xx_ethtool_set_wol, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) From 39f49eadc3e56609dc50c4abfeba0e4d77a590a3 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:55 +0100 Subject: [PATCH 380/399] net: usb: sr9700: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/sr9700.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 4a1e9c489f1f..950a3a9466bd 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -249,9 +249,9 @@ static const struct ethtool_ops sr9700_ethtool_ops = { .set_msglevel = usbnet_set_msglevel, .get_eeprom_len = sr9700_get_eeprom_len, .get_eeprom = sr9700_get_eeprom, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static void sr9700_set_multicast(struct net_device *netdev) From fd4f0a75f5f3c722a84cea999b0e9b00853ef3bd Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:56 +0100 Subject: [PATCH 381/399] net: usb: asix: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/usb/asix_devices.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 0dd510604118..38456d0bcfd2 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -136,9 +136,9 @@ static const struct ethtool_ops ax88172_ethtool_ops = { .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static void ax88172_set_multicast(struct net_device *net) @@ -301,9 +301,9 @@ static const struct ethtool_ops ax88772_ethtool_ops = { .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static int ax88772_link_reset(struct usbnet *dev) @@ -775,9 +775,9 @@ static const struct ethtool_ops ax88178_ethtool_ops = { .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .nway_reset = usbnet_nway_reset, + .get_link_ksettings = usbnet_get_link_ksettings, + .set_link_ksettings = usbnet_set_link_ksettings, }; static int marvell_phy_init(struct usbnet *dev) From bde87ad64c4cee7a1d5b41d217b440e21050813e Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 16 Mar 2017 23:18:57 +0100 Subject: [PATCH 382/399] net: usb: usb: remove old api ethtool_{get|set}_settings The function usbnet_{get|set}_settings is no longer used, so we remove it. Signed-off-by: Philippe Reynes Acked-by: Oliver Neukum Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 35 ----------------------------------- include/linux/usb/usbnet.h | 4 ---- 2 files changed, 39 deletions(-) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 1b40b189435a..13d4ec5f6f34 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -947,39 +947,6 @@ EXPORT_SYMBOL_GPL(usbnet_open); * they'll probably want to use this base set. */ -int usbnet_get_settings (struct net_device *net, struct ethtool_cmd *cmd) -{ - struct usbnet *dev = netdev_priv(net); - - if (!dev->mii.mdio_read) - return -EOPNOTSUPP; - - return mii_ethtool_gset(&dev->mii, cmd); -} -EXPORT_SYMBOL_GPL(usbnet_get_settings); - -int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd) -{ - struct usbnet *dev = netdev_priv(net); - int retval; - - if (!dev->mii.mdio_write) - return -EOPNOTSUPP; - - retval = mii_ethtool_sset(&dev->mii, cmd); - - /* link speed/duplex might have changed */ - if (dev->driver_info->link_reset) - dev->driver_info->link_reset(dev); - - /* hard_mtu or rx_urb_size may change in link_reset() */ - usbnet_update_max_qlen(dev); - - return retval; - -} -EXPORT_SYMBOL_GPL(usbnet_set_settings); - int usbnet_get_link_ksettings(struct net_device *net, struct ethtool_link_ksettings *cmd) { @@ -1072,8 +1039,6 @@ EXPORT_SYMBOL_GPL(usbnet_set_msglevel); /* drivers may override default ethtool_ops in their bind() routine */ static const struct ethtool_ops usbnet_ethtool_ops = { - .get_settings = usbnet_get_settings, - .set_settings = usbnet_set_settings, .get_link = usbnet_get_link, .nway_reset = usbnet_nway_reset, .get_drvinfo = usbnet_get_drvinfo, diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 5bd80078b7fe..e2b56917450f 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -261,10 +261,6 @@ extern void usbnet_pause_rx(struct usbnet *); extern void usbnet_resume_rx(struct usbnet *); extern void usbnet_purge_paused_rxq(struct usbnet *); -extern int usbnet_get_settings(struct net_device *net, - struct ethtool_cmd *cmd); -extern int usbnet_set_settings(struct net_device *net, - struct ethtool_cmd *cmd); extern int usbnet_get_link_ksettings(struct net_device *net, struct ethtool_link_ksettings *cmd); extern int usbnet_set_link_ksettings(struct net_device *net, From 33928eed8d934bb912d8168cd5e57fa80f9122c4 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Fri, 17 Mar 2017 11:20:13 +0800 Subject: [PATCH 383/399] r8152: check hw version first Check hw version first in probe(). Do nothing if the driver doesn't support the chip. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 102 +++++++++++++++++++++++++--------------- 1 file changed, 63 insertions(+), 39 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 4b85e95ab754..3262a326aae6 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4236,44 +4236,6 @@ static const struct net_device_ops rtl8152_netdev_ops = { .ndo_features_check = rtl8152_features_check, }; -static void r8152b_get_version(struct r8152 *tp) -{ - u32 ocp_data; - u16 version; - - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR1); - version = (u16)(ocp_data & VERSION_MASK); - - switch (version) { - case 0x4c00: - tp->version = RTL_VER_01; - break; - case 0x4c10: - tp->version = RTL_VER_02; - break; - case 0x5c00: - tp->version = RTL_VER_03; - tp->mii.supports_gmii = 1; - break; - case 0x5c10: - tp->version = RTL_VER_04; - tp->mii.supports_gmii = 1; - break; - case 0x5c20: - tp->version = RTL_VER_05; - tp->mii.supports_gmii = 1; - break; - case 0x5c30: - tp->version = RTL_VER_06; - tp->mii.supports_gmii = 1; - break; - default: - netif_info(tp, probe, tp->netdev, - "Unknown version 0x%04x\n", version); - break; - } -} - static void rtl8152_unload(struct r8152 *tp) { if (test_bit(RTL8152_UNPLUG, &tp->flags)) @@ -4338,14 +4300,66 @@ static int rtl_ops_init(struct r8152 *tp) return ret; } +static u8 rtl_get_version(struct usb_interface *intf) +{ + struct usb_device *udev = interface_to_usbdev(intf); + u32 ocp_data = 0; + __le32 *tmp; + u8 version; + int ret; + + tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return 0; + + ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), + RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, + PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500); + if (ret > 0) + ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK; + + kfree(tmp); + + switch (ocp_data) { + case 0x4c00: + version = RTL_VER_01; + break; + case 0x4c10: + version = RTL_VER_02; + break; + case 0x5c00: + version = RTL_VER_03; + break; + case 0x5c10: + version = RTL_VER_04; + break; + case 0x5c20: + version = RTL_VER_05; + break; + case 0x5c30: + version = RTL_VER_06; + break; + default: + version = RTL_VER_UNKNOWN; + dev_info(&intf->dev, "Unknown version 0x%04x\n", ocp_data); + break; + } + + return version; +} + static int rtl8152_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(intf); + u8 version = rtl_get_version(intf); struct r8152 *tp; struct net_device *netdev; int ret; + if (version == RTL_VER_UNKNOWN) + return -ENODEV; + if (udev->actconfig->desc.bConfigurationValue != 1) { usb_driver_set_configuration(udev, 1); return -ENODEV; @@ -4365,8 +4379,18 @@ static int rtl8152_probe(struct usb_interface *intf, tp->udev = udev; tp->netdev = netdev; tp->intf = intf; + tp->version = version; + + switch (version) { + case RTL_VER_01: + case RTL_VER_02: + tp->mii.supports_gmii = 0; + break; + default: + tp->mii.supports_gmii = 1; + break; + } - r8152b_get_version(tp); ret = rtl_ops_init(tp); if (ret) goto out; From bf95233e206983d5a05a2e27700d2678ffdef62c Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Fri, 17 Mar 2017 09:38:00 +0100 Subject: [PATCH 384/399] mlxsw: spectrum: Cosmetic naming change Currently the struct representing router interface "mlxsw_sp_rif" is reffered as "r" in various places in the driver. Furthermore it contains a member which specify the index which is called "rif". This patch change "r" to "rif" and "rif" to "rif_index". Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 8 +- .../net/ethernet/mellanox/mlxsw/spectrum.h | 4 +- .../ethernet/mellanox/mlxsw/spectrum_router.c | 282 +++++++++--------- .../mellanox/mlxsw/spectrum_switchdev.c | 4 +- 4 files changed, 152 insertions(+), 146 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 28019f8b70f7..cbc1646ee1d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4088,8 +4088,8 @@ static void mlxsw_sp_master_bridge_vlan_unlink(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f; f = mlxsw_sp_fid_find(mlxsw_sp, fid); - if (f && f->r) - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + if (f && f->rif) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif); if (f && --f->ref_count == 0) mlxsw_sp_fid_destroy(mlxsw_sp, f); } @@ -4206,8 +4206,8 @@ static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, clear_bit(vfid, mlxsw_sp->vfids.mapped); list_del(&f->list); - if (f->r) - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + if (f->rif) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif); kfree(f); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 0e223f6983c5..bffd9e698eff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -103,7 +103,7 @@ struct mlxsw_sp_fid { struct list_head list; unsigned int ref_count; struct net_device *dev; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; u16 fid; }; @@ -577,7 +577,7 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev); int mlxsw_sp_inetaddr_event(struct notifier_block *unused, unsigned long event, void *ptr); void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r); + struct mlxsw_sp_rif *rif); int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport); void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport); int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 488bc1fd7868..fe4a55e3272b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -60,7 +60,7 @@ struct mlxsw_sp_rif { struct mlxsw_sp_fid *f; unsigned char addr[ETH_ALEN]; int mtu; - u16 rif; + u16 rif_index; u16 vr_id; }; @@ -600,14 +600,14 @@ static struct mlxsw_sp_neigh_entry * mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) { struct mlxsw_sp_neigh_entry *neigh_entry; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; int err; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); - if (!r) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); + if (!rif) return ERR_PTR(-EINVAL); - neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, r->rif); + neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, rif->rif_index); if (!neigh_entry) return ERR_PTR(-ENOMEM); @@ -615,7 +615,7 @@ mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) if (err) goto err_neigh_entry_insert; - list_add(&neigh_entry->rif_list_node, &r->neigh_list); + list_add(&neigh_entry->rif_list_node, &rif->neigh_list); return neigh_entry; @@ -1023,22 +1023,22 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp) } static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif *r) + const struct mlxsw_sp_rif *rif) { char rauht_pl[MLXSW_REG_RAUHT_LEN]; mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL, - r->rif, r->addr); + rif->rif_index, rif->addr); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); } static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { struct mlxsw_sp_neigh_entry *neigh_entry, *tmp; - mlxsw_sp_neigh_rif_flush(mlxsw_sp, r); - list_for_each_entry_safe(neigh_entry, tmp, &r->neigh_list, + mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif); + list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list, rif_list_node) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); } @@ -1055,7 +1055,7 @@ struct mlxsw_sp_nexthop { */ struct rhash_head ht_node; struct mlxsw_sp_nexthop_key key; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; u8 should_offload:1, /* set indicates this neigh is connected and * should be put to KVD linear area of this group. */ @@ -1082,7 +1082,7 @@ struct mlxsw_sp_nexthop_group { u16 ecmp_size; u16 count; struct mlxsw_sp_nexthop nexthops[0]; -#define nh_rif nexthops[0].r +#define nh_rif nexthops[0].rif }; static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = { @@ -1372,22 +1372,22 @@ mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, } static void mlxsw_sp_nexthop_rif_init(struct mlxsw_sp_nexthop *nh, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { - if (nh->r) + if (nh->rif) return; - nh->r = r; - list_add(&nh->rif_list_node, &r->nexthop_list); + nh->rif = rif; + list_add(&nh->rif_list_node, &rif->nexthop_list); } static void mlxsw_sp_nexthop_rif_fini(struct mlxsw_sp_nexthop *nh) { - if (!nh->r) + if (!nh->rif) return; list_del(&nh->rif_list_node); - nh->r = NULL; + nh->rif = NULL; } static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, @@ -1478,7 +1478,7 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, { struct net_device *dev = fib_nh->nh_dev; struct in_device *in_dev; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; int err; nh->nh_grp = nh_grp; @@ -1495,10 +1495,10 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, fib_nh->nh_flags & RTNH_F_LINKDOWN) return 0; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!r) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) return 0; - mlxsw_sp_nexthop_rif_init(nh, r); + mlxsw_sp_nexthop_rif_init(nh, rif); err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); if (err) @@ -1524,7 +1524,7 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_nexthop_key key; struct mlxsw_sp_nexthop *nh; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; if (mlxsw_sp->router.aborted) return; @@ -1534,13 +1534,13 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, if (WARN_ON_ONCE(!nh)) return; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev); - if (!r) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev); + if (!rif) return; switch (event) { case FIB_EVENT_NH_ADD: - mlxsw_sp_nexthop_rif_init(nh, r); + mlxsw_sp_nexthop_rif_init(nh, rif); mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); break; case FIB_EVENT_NH_DEL: @@ -1553,11 +1553,11 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, } static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { struct mlxsw_sp_nexthop *nh, *tmp; - list_for_each_entry_safe(nh, tmp, &r->nexthop_list, rif_list_node) { + list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) { mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh); mlxsw_sp_nexthop_rif_fini(nh); mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); @@ -1760,17 +1760,17 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { - struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif; + struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif; struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; enum mlxsw_reg_ralue_trap_action trap_action; char ralue_pl[MLXSW_REG_RALUE_LEN]; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; u16 trap_id = 0; - u16 rif = 0; + u16 rif_index = 0; if (mlxsw_sp_fib_entry_should_offload(fib_entry)) { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; - rif = r->rif; + rif_index = rif->rif_index; } else { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; @@ -1780,7 +1780,8 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, (enum mlxsw_reg_ralxx_protocol) fib->proto, op, fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); - mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, + rif_index); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } @@ -2644,24 +2645,25 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) } static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { - mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif); - mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r); - mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r); + mlxsw_sp_router_rif_disable(mlxsw_sp, rif->rif_index); + mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, rif); + mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif); } -static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, +static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, const struct in_device *in_dev, unsigned long event) { switch (event) { case NETDEV_UP: - if (!r) + if (!rif) return true; return false; case NETDEV_DOWN: - if (r && !in_dev->ifa_list && !netif_is_l3_slave(r->dev)) + if (rif && !in_dev->ifa_list && + !netif_is_l3_slave(rif->dev)) return true; /* It is possible we already removed the RIF ourselves * if it was assigned to a netdev that is now a bridge @@ -2673,7 +2675,7 @@ static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r, return false; } -#define MLXSW_SP_INVALID_RIF 0xffff +#define MLXSW_SP_INVALID_INDEX_RIF 0xffff static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) { int i; @@ -2682,7 +2684,7 @@ static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) if (!mlxsw_sp->rifs[i]) return i; - return MLXSW_SP_INVALID_RIF; + return MLXSW_SP_INVALID_INDEX_RIF; } static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, @@ -2696,15 +2698,15 @@ static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vr_id, struct net_device *l3_dev, - u16 rif, bool create) + u16 rif_index, bool create) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; bool lagged = mlxsw_sp_vport->lagged; char ritr_pl[MLXSW_REG_RITR_LEN]; u16 system_port; - mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif, vr_id, - l3_dev->mtu, l3_dev->dev_addr); + mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif_index, + vr_id, l3_dev->mtu, l3_dev->dev_addr); mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port, @@ -2715,9 +2717,9 @@ static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport); -static u16 mlxsw_sp_rif_sp_to_fid(u16 rif) +static u16 mlxsw_sp_rif_sp_to_fid(u16 rif_index) { - return MLXSW_SP_RFID_BASE + rif; + return MLXSW_SP_RFID_BASE + rif_index; } static struct mlxsw_sp_fid * @@ -2738,25 +2740,25 @@ mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) } static struct mlxsw_sp_rif * -mlxsw_sp_rif_alloc(u16 rif, u16 vr_id, struct net_device *l3_dev, +mlxsw_sp_rif_alloc(u16 rif_index, u16 vr_id, struct net_device *l3_dev, struct mlxsw_sp_fid *f) { - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) + rif = kzalloc(sizeof(*rif), GFP_KERNEL); + if (!rif) return NULL; - INIT_LIST_HEAD(&r->nexthop_list); - INIT_LIST_HEAD(&r->neigh_list); - ether_addr_copy(r->addr, l3_dev->dev_addr); - r->mtu = l3_dev->mtu; - r->vr_id = vr_id; - r->dev = l3_dev; - r->rif = rif; - r->f = f; + INIT_LIST_HEAD(&rif->nexthop_list); + INIT_LIST_HEAD(&rif->neigh_list); + ether_addr_copy(rif->addr, l3_dev->dev_addr); + rif->mtu = l3_dev->mtu; + rif->vr_id = vr_id; + rif->dev = l3_dev; + rif->rif_index = rif_index; + rif->f = f; - return r; + return rif; } static struct mlxsw_sp_rif * @@ -2767,24 +2769,24 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, u32 tb_id = l3mdev_fib_table(l3_dev); struct mlxsw_sp_vr *vr; struct mlxsw_sp_fid *f; - struct mlxsw_sp_rif *r; - u16 fid, rif; + struct mlxsw_sp_rif *rif; + u16 fid, rif_index; int err; - rif = mlxsw_sp_avail_rif_get(mlxsw_sp); - if (rif == MLXSW_SP_INVALID_RIF) + rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif_index == MLXSW_SP_INVALID_INDEX_RIF) return ERR_PTR(-ERANGE); vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); if (IS_ERR(vr)) return ERR_CAST(vr); - err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, - true); + err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, + rif_index, true); if (err) goto err_vport_rif_sp_op; - fid = mlxsw_sp_rif_sp_to_fid(rif); + fid = mlxsw_sp_rif_sp_to_fid(rif_index); err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); if (err) goto err_rif_fdb_op; @@ -2795,53 +2797,54 @@ mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, goto err_rfid_alloc; } - r = mlxsw_sp_rif_alloc(rif, vr->id, l3_dev, f); - if (!r) { + rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f); + if (!rif) { err = -ENOMEM; goto err_rif_alloc; } - f->r = r; - mlxsw_sp->rifs[rif] = r; + f->rif = rif; + mlxsw_sp->rifs[rif_index] = rif; vr->rif_count++; - return r; + return rif; err_rif_alloc: kfree(f); err_rfid_alloc: mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); err_rif_fdb_op: - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, false); + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index, + false); err_vport_rif_sp_op: mlxsw_sp_vr_put(vr); return ERR_PTR(err); } static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[r->vr_id]; - struct net_device *l3_dev = r->dev; - struct mlxsw_sp_fid *f = r->f; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id]; + struct net_device *l3_dev = rif->dev; + struct mlxsw_sp_fid *f = rif->f; + u16 rif_index = rif->rif_index; u16 fid = f->fid; - u16 rif = r->rif; - mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); vr->rif_count--; - mlxsw_sp->rifs[rif] = NULL; - f->r = NULL; + mlxsw_sp->rifs[rif_index] = NULL; + f->rif = NULL; - kfree(r); + kfree(rif); kfree(f); mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); - mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif, false); - + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index, + false); mlxsw_sp_vr_put(vr); } @@ -2849,19 +2852,19 @@ static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, struct net_device *l3_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); - if (!r) { - r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); - if (IS_ERR(r)) - return PTR_ERR(r); + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); + if (!rif) { + rif = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); + if (IS_ERR(rif)) + return PTR_ERR(rif); } - mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f); - r->f->ref_count++; + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, rif->f); + rif->f->ref_count++; - netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid); + netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", rif->f->fid); return 0; } @@ -2874,7 +2877,7 @@ static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport) mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); if (--f->ref_count == 0) - mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r); + mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->rif); } static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, @@ -3014,13 +3017,13 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f) { u32 tb_id = l3mdev_fib_table(l3_dev); + struct mlxsw_sp_rif *rif; struct mlxsw_sp_vr *vr; - struct mlxsw_sp_rif *r; - u16 rif; + u16 rif_index; int err; - rif = mlxsw_sp_avail_rif_get(mlxsw_sp); - if (rif == MLXSW_SP_INVALID_RIF) + rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif_index == MLXSW_SP_INVALID_INDEX_RIF) return -ERANGE; vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); @@ -3031,8 +3034,8 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_port_flood_set; - err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, - true); + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, + rif_index, true); if (err) goto err_rif_bridge_op; @@ -3040,24 +3043,25 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rif_fdb_op; - r = mlxsw_sp_rif_alloc(rif, vr->id, l3_dev, f); - if (!r) { + rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f); + if (!rif) { err = -ENOMEM; goto err_rif_alloc; } - f->r = r; - mlxsw_sp->rifs[rif] = r; + f->rif = rif; + mlxsw_sp->rifs[rif_index] = rif; vr->rif_count++; - netdev_dbg(l3_dev, "RIF=%d created\n", rif); + netdev_dbg(l3_dev, "RIF=%d created\n", rif_index); return 0; err_rif_alloc: mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); err_rif_fdb_op: - mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, false); + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index, + false); err_rif_bridge_op: mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); err_port_flood_set: @@ -3066,30 +3070,31 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, } void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { - struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[r->vr_id]; - struct net_device *l3_dev = r->dev; - struct mlxsw_sp_fid *f = r->f; - u16 rif = r->rif; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id]; + struct net_device *l3_dev = rif->dev; + struct mlxsw_sp_fid *f = rif->f; + u16 rif_index = rif->rif_index; - mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r); + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); vr->rif_count--; - mlxsw_sp->rifs[rif] = NULL; - f->r = NULL; + mlxsw_sp->rifs[rif_index] = NULL; + f->rif = NULL; - kfree(r); + kfree(rif); mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); - mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif, false); + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index, + false); mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); mlxsw_sp_vr_put(vr); - netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif_index); } static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, @@ -3111,7 +3116,7 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, case NETDEV_UP: return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); case NETDEV_DOWN: - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif); break; } @@ -3145,15 +3150,15 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused, struct in_ifaddr *ifa = (struct in_ifaddr *) ptr; struct net_device *dev = ifa->ifa_dev->dev; struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; int err = 0; mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) goto out; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!mlxsw_sp_rif_should_config(r, ifa->ifa_dev, event)) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(rif, ifa->ifa_dev, event)) goto out; if (mlxsw_sp_port_dev_check(dev)) @@ -3169,13 +3174,13 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused, return notifier_from_errno(err); } -static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif, +static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index, const char *mac, int mtu) { char ritr_pl[MLXSW_REG_RITR_LEN]; int err; - mlxsw_reg_ritr_rif_pack(ritr_pl, rif); + mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); if (err) return err; @@ -3189,40 +3194,41 @@ static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif, int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) { struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; int err; mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) return 0; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!r) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) return 0; - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false); + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, false); if (err) return err; - err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu); + err = mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, dev->dev_addr, + dev->mtu); if (err) goto err_rif_edit; - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true); + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, rif->f->fid, true); if (err) goto err_rif_fdb_op; - ether_addr_copy(r->addr, dev->dev_addr); - r->mtu = dev->mtu; + ether_addr_copy(rif->addr, dev->dev_addr); + rif->mtu = dev->mtu; - netdev_dbg(dev, "Updated RIF=%d\n", r->rif); + netdev_dbg(dev, "Updated RIF=%d\n", rif->rif_index); return 0; err_rif_fdb_op: - mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu); + mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, rif->addr, rif->mtu); err_rif_edit: - mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true); + mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, true); return err; } @@ -3234,7 +3240,7 @@ int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport) /* In case vPort already has a RIF, then we need to drop it. * A new one will be created using the VRF's VR. */ - if (f && f->r) + if (f && f->rif) mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, dev); @@ -3276,8 +3282,8 @@ int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(!f)) return -EINVAL; - if (f->r) - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + if (f->rif) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif); return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); } @@ -3290,7 +3296,7 @@ void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp, f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); if (WARN_ON(!f)) return; - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif); } static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 598727d578c1..d44d92fe7ff3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -568,8 +568,8 @@ void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f) list_del(&f->list); - if (f->r) - mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r); + if (f->rif) + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif); kfree(f); From abbdf4bd7dd0d814f1af2bd90112e74a2be2c573 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Fri, 17 Mar 2017 09:38:01 +0100 Subject: [PATCH 385/399] mlxsw: spectrum: Align the matchall default case returned value Align the default case for matchall offload with what's there for flower. Signed-off-by: Or Gerlitz Acked-by: Yotam Gigi Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index cbc1646ee1d9..3ed77e10b4d6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1423,7 +1423,7 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle, tc->cls_mall); return 0; default: - return -EINVAL; + return -EOPNOTSUPP; } case TC_SETUP_CLSFLOWER: switch (tc->cls_flower->command) { From de6b08fd82087778c579dc3f3c28bb1c878a993a Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 17 Mar 2017 11:52:15 +0100 Subject: [PATCH 386/399] net: ethoc: Use ether_addr_copy() Use ether_addr_copy() instead of memcpy() to set netdev->dev_addr (which is 2-byte aligned). Signed-off-by: Tobias Klauser Reviewed-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/ethoc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 23d82748f52b..e863ba74d005 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1148,14 +1148,14 @@ static int ethoc_probe(struct platform_device *pdev) /* Allow the platform setup code to pass in a MAC address. */ if (pdata) { - memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN); + ether_addr_copy(netdev->dev_addr, pdata->hwaddr); priv->phy_id = pdata->phy_id; } else { const void *mac; mac = of_get_mac_address(pdev->dev.of_node); if (mac) - memcpy(netdev->dev_addr, mac, IFHWADDRLEN); + ether_addr_copy(netdev->dev_addr, mac); priv->phy_id = -1; } From aff3d9eff84399e433c4aca65a9bb236581bc082 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 17 Mar 2017 16:11:05 +0000 Subject: [PATCH 387/399] net: stmmac: enable multiple buffers This patch creates 2 new structures (stmmac_tx_queue and stmmac_rx_queue) in include/linux/stmmac.h, enabling that each RX and TX queue has its own buffers and data. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/chain_mode.c | 45 +- .../net/ethernet/stmicro/stmmac/ring_mode.c | 46 +- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 49 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 1344 +++++++++++------ 4 files changed, 992 insertions(+), 492 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index 01a8c020d6db..37881f81319e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -26,12 +26,15 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) { - struct stmmac_priv *priv = (struct stmmac_priv *)p; - unsigned int entry = priv->cur_tx; - struct dma_desc *desc = priv->dma_tx + entry; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p; unsigned int nopaged_len = skb_headlen(skb); + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->cur_tx; unsigned int bmax, des2; unsigned int i = 1, len; + struct dma_desc *desc; + + desc = tx_q->dma_tx + entry; if (priv->plat->enh_desc) bmax = BUF_SIZE_8KiB; @@ -45,16 +48,16 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = bmax; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = bmax; /* do not close the descriptor and do not set own bit */ priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE, 0, false); while (len != 0) { - priv->tx_skbuff[entry] = NULL; + tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; if (len > bmax) { des2 = dma_map_single(priv->device, @@ -63,8 +66,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = bmax; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = bmax; priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, STMMAC_CHAIN_MODE, 1, false); @@ -77,8 +80,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = len; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = len; /* last descriptor can be set now */ priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, STMMAC_CHAIN_MODE, 1, @@ -87,7 +90,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) } } - priv->cur_tx = entry; + tx_q->cur_tx = entry; return entry; } @@ -136,32 +139,34 @@ static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr, static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; + struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)priv_ptr; + struct stmmac_priv *priv = rx_q->priv_data; if (priv->hwts_rx_en && !priv->extend_desc) /* NOTE: Device will overwrite des3 with timestamp value if * 1588-2002 time stamping is enabled, hence reinitialize it * to keep explicit chaining in the descriptor. */ - p->des3 = cpu_to_le32((unsigned int)(priv->dma_rx_phy + - (((priv->dirty_rx) + 1) % + p->des3 = cpu_to_le32((unsigned int)(rx_q->dma_rx_phy + + (((rx_q->dirty_rx) + 1) % DMA_RX_SIZE) * sizeof(struct dma_desc))); } static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; - unsigned int entry = priv->dirty_tx; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr; + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->dirty_tx; - if (priv->tx_skbuff_dma[entry].last_segment && !priv->extend_desc && + if (tx_q->tx_skbuff_dma[entry].last_segment && !priv->extend_desc && priv->hwts_tx_en) /* NOTE: Device will overwrite des3 with timestamp value if * 1588-2002 time stamping is enabled, hence reinitialize it * to keep explicit chaining in the descriptor. */ - p->des3 = cpu_to_le32((unsigned int)((priv->dma_tx_phy + - ((priv->dirty_tx + 1) % DMA_TX_SIZE)) + p->des3 = cpu_to_le32((unsigned int)((tx_q->dma_tx_phy + + ((tx_q->dirty_tx + 1) % DMA_TX_SIZE)) * sizeof(struct dma_desc))); } diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index 452f256ff03f..31213e64513d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -26,16 +26,17 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) { - struct stmmac_priv *priv = (struct stmmac_priv *)p; - unsigned int entry = priv->cur_tx; - struct dma_desc *desc; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p; unsigned int nopaged_len = skb_headlen(skb); + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->cur_tx; unsigned int bmax, len, des2; + struct dma_desc *desc; if (priv->extend_desc) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; if (priv->plat->enh_desc) bmax = BUF_SIZE_8KiB; @@ -52,29 +53,29 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = bmax; - priv->tx_skbuff_dma[entry].is_jumbo = true; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = bmax; + tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_RING_MODE, 0, false); - priv->tx_skbuff[entry] = NULL; + tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); if (priv->extend_desc) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; des2 = dma_map_single(priv->device, skb->data + bmax, len, DMA_TO_DEVICE); desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = len; - priv->tx_skbuff_dma[entry].is_jumbo = true; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = len; + tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, @@ -85,15 +86,15 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; - priv->tx_skbuff_dma[entry].buf = des2; - priv->tx_skbuff_dma[entry].len = nopaged_len; - priv->tx_skbuff_dma[entry].is_jumbo = true; + tx_q->tx_skbuff_dma[entry].buf = des2; + tx_q->tx_skbuff_dma[entry].len = nopaged_len; + tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, STMMAC_RING_MODE, 0, true); } - priv->cur_tx = entry; + tx_q->cur_tx = entry; return entry; } @@ -125,12 +126,13 @@ static void stmmac_init_desc3(struct dma_desc *p) static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; - unsigned int entry = priv->dirty_tx; + struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr; + struct stmmac_priv *priv = tx_q->priv_data; + unsigned int entry = tx_q->dirty_tx; /* des3 is only used for jumbo frames tx or time stamping */ - if (unlikely(priv->tx_skbuff_dma[entry].is_jumbo || - (priv->tx_skbuff_dma[entry].last_segment && + if (unlikely(tx_q->tx_skbuff_dma[entry].is_jumbo || + (tx_q->tx_skbuff_dma[entry].last_segment && !priv->extend_desc && priv->hwts_tx_en))) p->des3 = 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index cd8fb619b1e9..6ec671c9be84 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -46,6 +46,35 @@ struct stmmac_tx_info { bool is_jumbo; }; +/* Frequently used values are kept adjacent for cache effect */ +struct stmmac_tx_queue { + u32 queue_index; + struct stmmac_priv *priv_data; + struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp; + struct dma_desc *dma_tx; + struct sk_buff **tx_skbuff; + struct stmmac_tx_info *tx_skbuff_dma; + unsigned int cur_tx; + unsigned int dirty_tx; + dma_addr_t dma_tx_phy; + u32 tx_tail_addr; +}; + +struct stmmac_rx_queue { + u32 queue_index; + struct stmmac_priv *priv_data; + struct dma_extended_desc *dma_erx; + struct dma_desc *dma_rx ____cacheline_aligned_in_smp; + struct sk_buff **rx_skbuff; + dma_addr_t *rx_skbuff_dma; + struct napi_struct napi ____cacheline_aligned_in_smp; + unsigned int cur_rx; + unsigned int dirty_rx; + u32 rx_zeroc_thresh; + dma_addr_t dma_rx_phy; + u32 rx_tail_addr; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp; @@ -56,28 +85,22 @@ struct stmmac_priv { u32 tx_count_frames; u32 tx_coal_frames; u32 tx_coal_timer; - struct stmmac_tx_info *tx_skbuff_dma; - dma_addr_t dma_tx_phy; int tx_coalesce; int hwts_tx_en; bool tx_path_in_lpi_mode; struct timer_list txtimer; bool tso; - struct dma_desc *dma_rx ____cacheline_aligned_in_smp; - struct dma_extended_desc *dma_erx; - struct sk_buff **rx_skbuff; - unsigned int cur_rx; - unsigned int dirty_rx; + /* TX Queue */ + struct stmmac_tx_queue *tx_queue; + + /* RX Queue */ + struct stmmac_rx_queue *rx_queue; + unsigned int dma_buf_sz; unsigned int rx_copybreak; - unsigned int rx_zeroc_thresh; u32 rx_riwt; int hwts_rx_en; - dma_addr_t *rx_skbuff_dma; - dma_addr_t dma_rx_phy; - - struct napi_struct napi ____cacheline_aligned_in_smp; void __iomem *ioaddr; struct net_device *dev; @@ -119,8 +142,6 @@ struct stmmac_priv { spinlock_t ptp_lock; void __iomem *mmcaddr; void __iomem *ptpaddr; - u32 rx_tail_addr; - u32 tx_tail_addr; u32 mss; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d3a21519e4c0..a389dfbe630c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -185,26 +185,38 @@ static void print_pkt(unsigned char *buf, int len) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, buf, len); } -static inline u32 stmmac_tx_avail(struct stmmac_priv *priv) +/** + * stmmac_tx_avail - Get tx queue availability + * @priv: driver private structure + * @queue: TX queue index + */ +static inline u32 stmmac_tx_avail(struct stmmac_priv *priv, u32 queue) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; u32 avail; - if (priv->dirty_tx > priv->cur_tx) - avail = priv->dirty_tx - priv->cur_tx - 1; + if (tx_q->dirty_tx > tx_q->cur_tx) + avail = tx_q->dirty_tx - tx_q->cur_tx - 1; else - avail = DMA_TX_SIZE - priv->cur_tx + priv->dirty_tx - 1; + avail = DMA_TX_SIZE - tx_q->cur_tx + tx_q->dirty_tx - 1; return avail; } -static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv) +/** + * stmmac_rx_dirty - Get RX queue dirty + * @priv: driver private structure + * @queue: RX queue index + */ +static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; u32 dirty; - if (priv->dirty_rx <= priv->cur_rx) - dirty = priv->cur_rx - priv->dirty_rx; + if (rx_q->dirty_rx <= rx_q->cur_rx) + dirty = rx_q->cur_rx - rx_q->dirty_rx; else - dirty = DMA_RX_SIZE - priv->dirty_rx + priv->cur_rx; + dirty = DMA_RX_SIZE - rx_q->dirty_rx + rx_q->cur_rx; return dirty; } @@ -232,9 +244,19 @@ static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv) */ static void stmmac_enable_eee_mode(struct stmmac_priv *priv) { + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + /* check if all TX queues have the work finished */ + for (queue = 0; queue < tx_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + if (tx_q->dirty_tx != tx_q->cur_tx) + return; /* still unfinished work */ + } + /* Check and enter in LPI mode */ - if ((priv->dirty_tx == priv->cur_tx) && - (priv->tx_path_in_lpi_mode == false)) + if (!priv->tx_path_in_lpi_mode) priv->hw->mac->set_eee_mode(priv->hw, priv->plat->en_tx_lpi_clockgating); } @@ -891,20 +913,40 @@ static int stmmac_init_phy(struct net_device *dev) static void stmmac_display_rings(struct stmmac_priv *priv) { + u32 rx_cnt = priv->plat->rx_queues_to_use; + u32 tx_cnt = priv->plat->tx_queues_to_use; void *head_rx, *head_tx; + u32 queue; - if (priv->extend_desc) { - head_rx = (void *)priv->dma_erx; - head_tx = (void *)priv->dma_etx; - } else { - head_rx = (void *)priv->dma_rx; - head_tx = (void *)priv->dma_tx; + /* Display RX rings */ + for (queue = 0; queue < rx_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + pr_info("\tRX Queue %d rings\n", queue); + + if (priv->extend_desc) + head_rx = (void *)rx_q->dma_erx; + else + head_rx = (void *)rx_q->dma_rx; + + /* Display Rx ring */ + priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true); } - /* Display Rx ring */ - priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true); - /* Display Tx ring */ - priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false); + /* Display TX rings */ + for (queue = 0; queue < tx_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + pr_info("\tTX Queue %d rings\n", queue); + + if (priv->extend_desc) + head_tx = (void *)tx_q->dma_etx; + else + head_tx = (void *)tx_q->dma_tx; + + /* Display Tx ring */ + priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false); + } } static int stmmac_set_bfsize(int mtu, int bufsize) @@ -923,6 +965,54 @@ static int stmmac_set_bfsize(int mtu, int bufsize) return ret; } +/** + * stmmac_clear_rx_descriptors - clear the descriptors of a RX queue + * @priv: driver private structure + * @queue: RX queue index + * Description: this function is called to clear the RX descriptors + * in case of both basic and extended descriptors are used. + */ +static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue) +{ + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + u32 i = 0; + + /* Clear the RX descriptors */ + for (i = 0; i < DMA_RX_SIZE; i++) + if (priv->extend_desc) + priv->hw->desc->init_rx_desc(&rx_q->dma_erx[i].basic, + priv->use_riwt, priv->mode, + (i == DMA_RX_SIZE - 1)); + else + priv->hw->desc->init_rx_desc(&rx_q->dma_rx[i], + priv->use_riwt, priv->mode, + (i == DMA_RX_SIZE - 1)); +} + +/** + * stmmac_clear_tx_descriptors - clear the descriptors of a TX queue + * @priv: driver private structure + * @queue: TX queue index + * Description: this function is called to clear the TX descriptors + * in case of both basic and extended descriptors are used. + */ +static void stmmac_clear_tx_descriptors(struct stmmac_priv *priv, u32 queue) +{ + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + u32 i = 0; + + /* Clear the TX descriptors */ + for (i = 0; i < DMA_TX_SIZE; i++) + if (priv->extend_desc) + priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic, + priv->mode, + (i == DMA_TX_SIZE - 1)); + else + priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i], + priv->mode, + (i == DMA_TX_SIZE - 1)); +} + /** * stmmac_clear_descriptors - clear descriptors * @priv: driver private structure @@ -931,27 +1021,15 @@ static int stmmac_set_bfsize(int mtu, int bufsize) */ static void stmmac_clear_descriptors(struct stmmac_priv *priv) { - int i; + u32 rx_queue_cnt = priv->plat->rx_queues_to_use; + u32 tx_queue_cnt = priv->plat->tx_queues_to_use; + u32 queue; - /* Clear the Rx/Tx descriptors */ - for (i = 0; i < DMA_RX_SIZE; i++) - if (priv->extend_desc) - priv->hw->desc->init_rx_desc(&priv->dma_erx[i].basic, - priv->use_riwt, priv->mode, - (i == DMA_RX_SIZE - 1)); - else - priv->hw->desc->init_rx_desc(&priv->dma_rx[i], - priv->use_riwt, priv->mode, - (i == DMA_RX_SIZE - 1)); - for (i = 0; i < DMA_TX_SIZE; i++) - if (priv->extend_desc) - priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic, - priv->mode, - (i == DMA_TX_SIZE - 1)); - else - priv->hw->desc->init_tx_desc(&priv->dma_tx[i], - priv->mode, - (i == DMA_TX_SIZE - 1)); + for (queue = 0; queue < rx_queue_cnt; queue++) + stmmac_clear_rx_descriptors(priv, queue); + + for (queue = 0; queue < tx_queue_cnt; queue++) + stmmac_clear_tx_descriptors(priv, queue); } /** @@ -960,12 +1038,14 @@ static void stmmac_clear_descriptors(struct stmmac_priv *priv) * @p: descriptor pointer * @i: descriptor index * @flags: gfp flag. + * @queue: RX queue index * Description: this function is called to allocate a receive buffer, perform * the DMA mapping and init the descriptor. */ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, - int i, gfp_t flags) + int i, gfp_t flags, u32 queue) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct sk_buff *skb; skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags); @@ -974,20 +1054,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, "%s: Rx init fails; skb is NULL\n", __func__); return -ENOMEM; } - priv->rx_skbuff[i] = skb; - priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data, + rx_q->rx_skbuff[i] = skb; + rx_q->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data, priv->dma_buf_sz, DMA_FROM_DEVICE); - if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) { + if (dma_mapping_error(priv->device, rx_q->rx_skbuff_dma[i])) { netdev_err(priv->dev, "%s: DMA mapping error\n", __func__); dev_kfree_skb_any(skb); return -EINVAL; } if (priv->synopsys_id >= DWMAC_CORE_4_00) - p->des0 = cpu_to_le32(priv->rx_skbuff_dma[i]); + p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[i]); else - p->des2 = cpu_to_le32(priv->rx_skbuff_dma[i]); + p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]); if ((priv->hw->mode->init_desc3) && (priv->dma_buf_sz == BUF_SIZE_16KiB)) @@ -996,30 +1076,136 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, return 0; } -static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i) +/** + * stmmac_free_rx_buffers - free RX buffers. + * @priv: driver private structure + * @queue: RX queue index + * @i: buffer index + */ +static void stmmac_free_rx_buffers(struct stmmac_priv *priv, u32 queue, int i) { - if (priv->rx_skbuff[i]) { - dma_unmap_single(priv->device, priv->rx_skbuff_dma[i], + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + if (rx_q->rx_skbuff[i]) { + dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[i], priv->dma_buf_sz, DMA_FROM_DEVICE); - dev_kfree_skb_any(priv->rx_skbuff[i]); + dev_kfree_skb_any(rx_q->rx_skbuff[i]); } - priv->rx_skbuff[i] = NULL; + rx_q->rx_skbuff[i] = NULL; } /** - * init_dma_desc_rings - init the RX/TX descriptor rings + * stmmac_free_tx_buffers - free RX buffers. + * @priv: driver private structure + * @queue: RX queue index + * @i: buffer index + */ +static void stmmac_free_tx_buffers(struct stmmac_priv *priv, u32 queue, u32 i) +{ + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + if (tx_q->tx_skbuff_dma[i].buf) { + if (tx_q->tx_skbuff_dma[i].map_as_page) + dma_unmap_page(priv->device, + tx_q->tx_skbuff_dma[i].buf, + tx_q->tx_skbuff_dma[i].len, + DMA_TO_DEVICE); + else + dma_unmap_single(priv->device, + tx_q->tx_skbuff_dma[i].buf, + tx_q->tx_skbuff_dma[i].len, + DMA_TO_DEVICE); + } + + if (tx_q->tx_skbuff[i]) { + dev_kfree_skb_any(tx_q->tx_skbuff[i]); + tx_q->tx_skbuff[i] = NULL; + tx_q->tx_skbuff_dma[i].buf = 0; + tx_q->tx_skbuff_dma[i].map_as_page = false; + } +} + +/** + * init_tx_dma_desc_rings - init the TX descriptor rings * @dev: net device structure - * @flags: gfp flag. - * Description: this function initializes the DMA RX/TX descriptors - * and allocates the socket buffers. It supports the chained and ring + * Description: this function initializes the DMA TX descriptors + * and allocates the socket buffers. It suppors the chained and ring * modes. */ -static int init_dma_desc_rings(struct net_device *dev, gfp_t flags) +static int init_tx_dma_desc_rings(struct net_device *dev) { - int i; struct stmmac_priv *priv = netdev_priv(dev); + u32 tx_queue_cnt = priv->plat->tx_queues_to_use; + u32 queue; + int i = 0; + + for (queue = 0; queue < tx_queue_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + netif_dbg(priv, probe, priv->dev, + "(%s) dma_tx_phy=0x%08x\n", __func__, + (u32)tx_q->dma_tx_phy); + + /* Setup the chained descriptor addresses */ + if (priv->mode == STMMAC_CHAIN_MODE) { + if (priv->extend_desc) + priv->hw->mode->init(tx_q->dma_etx, + tx_q->dma_tx_phy, + DMA_TX_SIZE, 1); + else + priv->hw->mode->init(tx_q->dma_tx, + tx_q->dma_tx_phy, + DMA_TX_SIZE, 0); + } + + for (i = 0; i < DMA_TX_SIZE; i++) { + struct dma_desc *p; + + if (priv->extend_desc) + p = &((tx_q->dma_etx + i)->basic); + else + p = tx_q->dma_tx + i; + + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + p->des0 = 0; + p->des1 = 0; + p->des2 = 0; + p->des3 = 0; + } else { + p->des2 = 0; + } + + tx_q->tx_skbuff_dma[i].buf = 0; + tx_q->tx_skbuff_dma[i].map_as_page = false; + tx_q->tx_skbuff_dma[i].len = 0; + tx_q->tx_skbuff_dma[i].last_segment = false; + tx_q->tx_skbuff[i] = NULL; + } + + tx_q->dirty_tx = 0; + tx_q->cur_tx = 0; + netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue)); + } + + return 0; +} + +/** + * init_rx_dma_desc_rings - init the RX descriptor rings + * @dev: net device structure + * @flags: gfp flag. + * Description: this function initializes the DMA RX descriptors + * and allocates the socket buffers. It suppors the chained and ring + * modes. + */ +static int init_rx_dma_desc_rings(struct net_device *dev, gfp_t flags) +{ + struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_count = priv->plat->rx_queues_to_use; unsigned int bfsize = 0; int ret = -ENOMEM; + u32 queue; + int i; if (priv->hw->mode->set_16kib_bfsize) bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu); @@ -1029,121 +1215,329 @@ static int init_dma_desc_rings(struct net_device *dev, gfp_t flags) priv->dma_buf_sz = bfsize; - netif_dbg(priv, probe, priv->dev, - "(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n", - __func__, (u32)priv->dma_rx_phy, (u32)priv->dma_tx_phy); - /* RX INITIALIZATION */ netif_dbg(priv, probe, priv->dev, "SKB addresses:\nskb\t\tskb data\tdma data\n"); - for (i = 0; i < DMA_RX_SIZE; i++) { - struct dma_desc *p; - if (priv->extend_desc) - p = &((priv->dma_erx + i)->basic); - else - p = priv->dma_rx + i; + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; - ret = stmmac_init_rx_buffers(priv, p, i, flags); - if (ret) - goto err_init_rx_buffers; + netif_dbg(priv, probe, priv->dev, + "(%s) dma_rx_phy=0x%08x\n", __func__, + (u32)rx_q->dma_rx_phy); - netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n", - priv->rx_skbuff[i], priv->rx_skbuff[i]->data, - (unsigned int)priv->rx_skbuff_dma[i]); + for (i = 0; i < DMA_RX_SIZE; i++) { + struct dma_desc *p; + + if (priv->extend_desc) + p = &((rx_q->dma_erx + i)->basic); + else + p = rx_q->dma_rx + i; + + ret = stmmac_init_rx_buffers(priv, p, i, flags, queue); + if (ret) + goto err_init_rx_buffers; + + netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n", + rx_q->rx_skbuff[i], + rx_q->rx_skbuff[i]->data, + (unsigned int)rx_q->rx_skbuff_dma[i]); + } + + rx_q->cur_rx = 0; + rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE); + + stmmac_clear_rx_descriptors(priv, queue); + + if (priv->mode == STMMAC_CHAIN_MODE) { + if (priv->extend_desc) + priv->hw->mode->init(rx_q->dma_erx, + rx_q->dma_rx_phy, + DMA_RX_SIZE, 1); + else + priv->hw->mode->init(rx_q->dma_rx, + rx_q->dma_rx_phy, + DMA_RX_SIZE, 0); + } } - priv->cur_rx = 0; - priv->dirty_rx = (unsigned int)(i - DMA_RX_SIZE); + buf_sz = bfsize; - /* Setup the chained descriptor addresses */ - if (priv->mode == STMMAC_CHAIN_MODE) { - if (priv->extend_desc) { - priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy, - DMA_RX_SIZE, 1); - priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy, - DMA_TX_SIZE, 1); - } else { - priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy, - DMA_RX_SIZE, 0); - priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy, - DMA_TX_SIZE, 0); - } + return 0; + +err_init_rx_buffers: + while (queue-- >= 0) { + while (--i >= 0) + stmmac_free_rx_buffers(priv, queue, i); + + i = DMA_RX_SIZE; } - /* TX INITIALIZATION */ - for (i = 0; i < DMA_TX_SIZE; i++) { - struct dma_desc *p; - if (priv->extend_desc) - p = &((priv->dma_etx + i)->basic); - else - p = priv->dma_tx + i; + return ret; +} - if (priv->synopsys_id >= DWMAC_CORE_4_00) { - p->des0 = 0; - p->des1 = 0; - p->des2 = 0; - p->des3 = 0; - } else { - p->des2 = 0; - } +/** + * init_dma_desc_rings - init the RX/TX descriptor rings + * @dev: net device structure + * @flags: gfp flag. + * Description: this function initializes the DMA RX/TX descriptors + * and allocates the socket buffers. It suppors the chained and ring + * modes. + */ +static int init_dma_desc_rings(struct net_device *dev, gfp_t flags) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int ret = init_rx_dma_desc_rings(dev, flags); - priv->tx_skbuff_dma[i].buf = 0; - priv->tx_skbuff_dma[i].map_as_page = false; - priv->tx_skbuff_dma[i].len = 0; - priv->tx_skbuff_dma[i].last_segment = false; - priv->tx_skbuff[i] = NULL; - } + if (ret) + return ret; - priv->dirty_tx = 0; - priv->cur_tx = 0; - netdev_reset_queue(priv->dev); - - stmmac_clear_descriptors(priv); + ret = init_tx_dma_desc_rings(dev); if (netif_msg_hw(priv)) stmmac_display_rings(priv); - return 0; -err_init_rx_buffers: - while (--i >= 0) - stmmac_free_rx_buffers(priv, i); return ret; } -static void dma_free_rx_skbufs(struct stmmac_priv *priv) +static void dma_free_rx_skbufs(struct stmmac_priv *priv, u32 queue) { int i; for (i = 0; i < DMA_RX_SIZE; i++) - stmmac_free_rx_buffers(priv, i); + stmmac_free_rx_buffers(priv, queue, i); } -static void dma_free_tx_skbufs(struct stmmac_priv *priv) +static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue) { int i; - for (i = 0; i < DMA_TX_SIZE; i++) { - if (priv->tx_skbuff_dma[i].buf) { - if (priv->tx_skbuff_dma[i].map_as_page) - dma_unmap_page(priv->device, - priv->tx_skbuff_dma[i].buf, - priv->tx_skbuff_dma[i].len, - DMA_TO_DEVICE); - else - dma_unmap_single(priv->device, - priv->tx_skbuff_dma[i].buf, - priv->tx_skbuff_dma[i].len, - DMA_TO_DEVICE); - } + for (i = 0; i < DMA_TX_SIZE; i++) + stmmac_free_tx_buffers(priv, queue, i); +} - if (priv->tx_skbuff[i]) { - dev_kfree_skb_any(priv->tx_skbuff[i]); - priv->tx_skbuff[i] = NULL; - priv->tx_skbuff_dma[i].buf = 0; - priv->tx_skbuff_dma[i].map_as_page = false; +/** + * free_rx_dma_desc_resources - free RX DMA resources + * @priv: driver private structure + */ +static void free_rx_dma_desc_resources(struct stmmac_priv *priv) +{ + u32 rx_count = priv->plat->rx_queues_to_use; + u32 queue = 0; + + if (!priv->rx_queue) + return; + + /* Free RX queue resources */ + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + if (!rx_q) + break; + + /* Release the DMA RX socket buffers */ + dma_free_rx_skbufs(priv, queue); + + kfree(rx_q->rx_skbuff); + + kfree(rx_q->rx_skbuff_dma); + + if (!priv->extend_desc) + dma_free_coherent(priv->device, + DMA_RX_SIZE * sizeof(struct dma_desc), + rx_q->dma_rx, + rx_q->dma_rx_phy); + else + dma_free_coherent(priv->device, DMA_RX_SIZE * + sizeof(struct dma_extended_desc), + rx_q->dma_erx, + rx_q->dma_rx_phy); + } + + kfree(priv->rx_queue); +} + +/** + * free_tx_dma_desc_resources - free TX DMA resources + * @priv: driver private structure + */ +static void free_tx_dma_desc_resources(struct stmmac_priv *priv) +{ + u32 tx_count = priv->plat->tx_queues_to_use; + u32 queue = 0; + + if (!priv->tx_queue) + return; + + /* Free TX queue resources */ + for (queue = 0; queue < tx_count; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + if (!tx_q) + break; + + /* Release the DMA TX socket buffers */ + dma_free_tx_skbufs(priv, queue); + + kfree(tx_q->tx_skbuff); + + kfree(tx_q->tx_skbuff_dma); + + if (!priv->extend_desc) + dma_free_coherent(priv->device, + DMA_TX_SIZE * sizeof(struct dma_desc), + tx_q->dma_tx, + tx_q->dma_tx_phy); + else + dma_free_coherent(priv->device, DMA_TX_SIZE * + sizeof(struct dma_extended_desc), + tx_q->dma_etx, + tx_q->dma_tx_phy); + } + + kfree(priv->tx_queue); +} + +/** + * free_dma_desc_resources - free All DMA resources + * @priv: driver private structure + */ +static void free_dma_desc_resources(struct stmmac_priv *priv) +{ + free_rx_dma_desc_resources(priv); + free_tx_dma_desc_resources(priv); +} + +/** + * alloc_rx_dma_desc_resources - alloc RX resources. + * @priv: private structure + * Description: according to which descriptor can be used (extend or basic) + * this function allocates the resources for RX paths. It pre-allocates the + * RX socket buffer in order to allow zero-copy mechanism. + */ +static int alloc_rx_dma_desc_resources(struct stmmac_priv *priv) +{ + u32 rx_count = priv->plat->rx_queues_to_use; + int ret = -ENOMEM; + u32 queue = 0; + + /* Allocate RX queues array */ + priv->rx_queue = kmalloc_array(rx_count, + sizeof(struct stmmac_rx_queue), + GFP_KERNEL); + if (!priv->rx_queue) { + kfree(priv->rx_queue); + return -ENOMEM; + } + + /* RX queues buffers and DMA */ + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + rx_q->queue_index = queue; + rx_q->priv_data = priv; + + rx_q->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE, + sizeof(dma_addr_t), + GFP_KERNEL); + if (!rx_q->rx_skbuff_dma) + goto err_dma_buffers; + + rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE, + sizeof(struct sk_buff *), + GFP_KERNEL); + if (!rx_q->rx_skbuff) + goto err_dma_buffers; + + if (priv->extend_desc) { + rx_q->dma_erx = dma_zalloc_coherent(priv->device, + (DMA_RX_SIZE * sizeof(struct dma_extended_desc)), + &rx_q->dma_rx_phy, GFP_KERNEL); + + if (!rx_q->dma_erx) + goto err_dma_buffers; + } else { + rx_q->dma_rx = dma_zalloc_coherent(priv->device, + (DMA_RX_SIZE * sizeof(struct dma_desc)), + &rx_q->dma_rx_phy, GFP_KERNEL); + + if (!rx_q->dma_rx) + goto err_dma_buffers; } } + + return 0; + +err_dma_buffers: + free_rx_dma_desc_resources(priv); + + return ret; +} + +/** + * alloc_tx_dma_desc_resources - alloc TX resources. + * @priv: private structure + * Description: according to which descriptor can be used (extend or basic) + * this function allocates the resources for TX paths. + */ +static int alloc_tx_dma_desc_resources(struct stmmac_priv *priv) +{ + u32 tx_count = priv->plat->tx_queues_to_use; + int ret = -ENOMEM; + u32 queue = 0; + + /* Allocate TX queues array */ + priv->tx_queue = kmalloc_array(tx_count, + sizeof(struct stmmac_tx_queue), + GFP_KERNEL); + if (!priv->tx_queue) + return -ENOMEM; + + /* TX queues buffers and DMA */ + for (queue = 0; queue < tx_count; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + tx_q->queue_index = queue; + tx_q->priv_data = priv; + + tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE, + sizeof(struct stmmac_tx_info), + GFP_KERNEL); + + if (!tx_q->tx_skbuff_dma) + goto err_dma_buffers; + + tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE, + sizeof(struct sk_buff *), + GFP_KERNEL); + if (!tx_q->tx_skbuff) + goto err_dma_buffers; + + if (priv->extend_desc) { + tx_q->dma_etx = + dma_zalloc_coherent(priv->device, + (DMA_TX_SIZE * sizeof(struct dma_extended_desc)), + &tx_q->dma_tx_phy, GFP_KERNEL); + + if (!tx_q->dma_etx) + goto err_dma_buffers; + } else { + tx_q->dma_tx = + dma_zalloc_coherent(priv->device, + (DMA_TX_SIZE * sizeof(struct dma_desc)), + &tx_q->dma_tx_phy, GFP_KERNEL); + + if (!tx_q->dma_tx) + goto err_dma_buffers; + } + } + + return 0; + +err_dma_buffers: + free_tx_dma_desc_resources(priv); + + return ret; } /** @@ -1156,110 +1550,17 @@ static void dma_free_tx_skbufs(struct stmmac_priv *priv) */ static int alloc_dma_desc_resources(struct stmmac_priv *priv) { - int ret = -ENOMEM; + int ret = 0; - priv->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE, sizeof(dma_addr_t), - GFP_KERNEL); - if (!priv->rx_skbuff_dma) - return -ENOMEM; + ret = alloc_tx_dma_desc_resources(priv); + if (ret) + return ret; - priv->rx_skbuff = kmalloc_array(DMA_RX_SIZE, sizeof(struct sk_buff *), - GFP_KERNEL); - if (!priv->rx_skbuff) - goto err_rx_skbuff; + ret = alloc_rx_dma_desc_resources(priv); - priv->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE, - sizeof(*priv->tx_skbuff_dma), - GFP_KERNEL); - if (!priv->tx_skbuff_dma) - goto err_tx_skbuff_dma; - - priv->tx_skbuff = kmalloc_array(DMA_TX_SIZE, sizeof(struct sk_buff *), - GFP_KERNEL); - if (!priv->tx_skbuff) - goto err_tx_skbuff; - - if (priv->extend_desc) { - priv->dma_erx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct - dma_extended_desc), - &priv->dma_rx_phy, - GFP_KERNEL); - if (!priv->dma_erx) - goto err_dma; - - priv->dma_etx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE * - sizeof(struct - dma_extended_desc), - &priv->dma_tx_phy, - GFP_KERNEL); - if (!priv->dma_etx) { - dma_free_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_extended_desc), - priv->dma_erx, priv->dma_rx_phy); - goto err_dma; - } - } else { - priv->dma_rx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_desc), - &priv->dma_rx_phy, - GFP_KERNEL); - if (!priv->dma_rx) - goto err_dma; - - priv->dma_tx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE * - sizeof(struct dma_desc), - &priv->dma_tx_phy, - GFP_KERNEL); - if (!priv->dma_tx) { - dma_free_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_desc), - priv->dma_rx, priv->dma_rx_phy); - goto err_dma; - } - } - - return 0; - -err_dma: - kfree(priv->tx_skbuff); -err_tx_skbuff: - kfree(priv->tx_skbuff_dma); -err_tx_skbuff_dma: - kfree(priv->rx_skbuff); -err_rx_skbuff: - kfree(priv->rx_skbuff_dma); return ret; } -static void free_dma_desc_resources(struct stmmac_priv *priv) -{ - /* Release the DMA TX/RX socket buffers */ - dma_free_rx_skbufs(priv); - dma_free_tx_skbufs(priv); - - /* Free DMA regions of consistent memory previously allocated */ - if (!priv->extend_desc) { - dma_free_coherent(priv->device, - DMA_TX_SIZE * sizeof(struct dma_desc), - priv->dma_tx, priv->dma_tx_phy); - dma_free_coherent(priv->device, - DMA_RX_SIZE * sizeof(struct dma_desc), - priv->dma_rx, priv->dma_rx_phy); - } else { - dma_free_coherent(priv->device, DMA_TX_SIZE * - sizeof(struct dma_extended_desc), - priv->dma_etx, priv->dma_tx_phy); - dma_free_coherent(priv->device, DMA_RX_SIZE * - sizeof(struct dma_extended_desc), - priv->dma_erx, priv->dma_rx_phy); - } - kfree(priv->rx_skbuff_dma); - kfree(priv->rx_skbuff); - kfree(priv->tx_skbuff_dma); - kfree(priv->tx_skbuff); -} - /** * stmmac_mac_enable_rx_queues - Enable MAC rx queues * @priv: driver private structure @@ -1421,26 +1722,28 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) /** * stmmac_tx_clean - to manage the transmission completion * @priv: driver private structure + * @queue: TX queue index * Description: it reclaims the transmit resources after transmission completes. */ -static void stmmac_tx_clean(struct stmmac_priv *priv) +static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; unsigned int bytes_compl = 0, pkts_compl = 0; - unsigned int entry = priv->dirty_tx; + unsigned int entry = tx_q->dirty_tx; netif_tx_lock(priv->dev); priv->xstats.tx_clean++; - while (entry != priv->cur_tx) { - struct sk_buff *skb = priv->tx_skbuff[entry]; + while (entry != tx_q->cur_tx) { + struct sk_buff *skb = tx_q->tx_skbuff[entry]; struct dma_desc *p; int status; if (priv->extend_desc) - p = (struct dma_desc *)(priv->dma_etx + entry); + p = (struct dma_desc *)(tx_q->dma_etx + entry); else - p = priv->dma_tx + entry; + p = tx_q->dma_tx + entry; status = priv->hw->desc->tx_status(&priv->dev->stats, &priv->xstats, p, @@ -1461,48 +1764,50 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) stmmac_get_tx_hwtstamp(priv, p, skb); } - if (likely(priv->tx_skbuff_dma[entry].buf)) { - if (priv->tx_skbuff_dma[entry].map_as_page) + if (likely(tx_q->tx_skbuff_dma[entry].buf)) { + if (tx_q->tx_skbuff_dma[entry].map_as_page) dma_unmap_page(priv->device, - priv->tx_skbuff_dma[entry].buf, - priv->tx_skbuff_dma[entry].len, + tx_q->tx_skbuff_dma[entry].buf, + tx_q->tx_skbuff_dma[entry].len, DMA_TO_DEVICE); else dma_unmap_single(priv->device, - priv->tx_skbuff_dma[entry].buf, - priv->tx_skbuff_dma[entry].len, + tx_q->tx_skbuff_dma[entry].buf, + tx_q->tx_skbuff_dma[entry].len, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry].buf = 0; - priv->tx_skbuff_dma[entry].len = 0; - priv->tx_skbuff_dma[entry].map_as_page = false; + tx_q->tx_skbuff_dma[entry].buf = 0; + tx_q->tx_skbuff_dma[entry].len = 0; + tx_q->tx_skbuff_dma[entry].map_as_page = false; } if (priv->hw->mode->clean_desc3) - priv->hw->mode->clean_desc3(priv, p); + priv->hw->mode->clean_desc3(tx_q, p); - priv->tx_skbuff_dma[entry].last_segment = false; - priv->tx_skbuff_dma[entry].is_jumbo = false; + tx_q->tx_skbuff_dma[entry].last_segment = false; + tx_q->tx_skbuff_dma[entry].is_jumbo = false; if (likely(skb != NULL)) { pkts_compl++; bytes_compl += skb->len; dev_consume_skb_any(skb); - priv->tx_skbuff[entry] = NULL; + tx_q->tx_skbuff[entry] = NULL; } priv->hw->desc->release_tx_desc(p, priv->mode); entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); } - priv->dirty_tx = entry; + tx_q->dirty_tx = entry; - netdev_completed_queue(priv->dev, pkts_compl, bytes_compl); + netdev_tx_completed_queue(netdev_get_tx_queue(priv->dev, queue), + pkts_compl, bytes_compl); - if (unlikely(netif_queue_stopped(priv->dev) && - stmmac_tx_avail(priv) > STMMAC_TX_THRESH)) { + if (unlikely(netif_tx_queue_stopped(netdev_get_tx_queue(priv->dev, + queue))) && + stmmac_tx_avail(priv, queue) > STMMAC_TX_THRESH) { netif_dbg(priv, tx_done, priv->dev, "%s: restart transmit\n", __func__); - netif_wake_queue(priv->dev); + netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue)); } if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) { @@ -1525,33 +1830,36 @@ static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan) /** * stmmac_tx_err - to manage the tx error * @priv: driver private structure - * @chan: channel index + * @queue: queue index * Description: it cleans the descriptors and restarts the transmission * in case of transmission errors. */ -static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) +static void stmmac_tx_err(struct stmmac_priv *priv, u32 queue) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + u32 chan = queue; int i; - netif_stop_queue(priv->dev); + + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); stmmac_stop_tx_dma(priv, chan); - dma_free_tx_skbufs(priv); + dma_free_tx_skbufs(priv, queue); for (i = 0; i < DMA_TX_SIZE; i++) if (priv->extend_desc) - priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic, + priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic, priv->mode, (i == DMA_TX_SIZE - 1)); else - priv->hw->desc->init_tx_desc(&priv->dma_tx[i], + priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i], priv->mode, (i == DMA_TX_SIZE - 1)); - priv->dirty_tx = 0; - priv->cur_tx = 0; - netdev_reset_queue(priv->dev); + tx_q->dirty_tx = 0; + tx_q->cur_tx = 0; + netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue)); stmmac_start_tx_dma(priv, chan); priv->dev->stats.tx_errors++; - netif_wake_queue(priv->dev); + netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue)); } /** @@ -1596,12 +1904,14 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) u32 chan; for (chan = 0; chan < tx_channel_count; chan++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; + status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats, chan); if (likely((status & handle_rx)) || (status & handle_tx)) { - if (likely(napi_schedule_prep(&priv->napi))) { + if (likely(napi_schedule_prep(&rx_q->napi))) { stmmac_disable_dma_irq(priv, chan); - __napi_schedule(&priv->napi); + __napi_schedule(&rx_q->napi); } } @@ -1734,6 +2044,8 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) { u32 rx_channels_count = priv->plat->rx_queues_to_use; u32 tx_channels_count = priv->plat->tx_queues_to_use; + struct stmmac_rx_queue *rx_q; + struct stmmac_tx_queue *tx_q; u32 dummy_dma_rx_phy = 0; u32 dummy_dma_tx_phy = 0; u32 chan = 0; @@ -1761,36 +2073,43 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) /* DMA RX Channel Configuration */ for (chan = 0; chan < rx_channels_count; chan++) { + rx_q = &priv->rx_queue[chan]; + priv->hw->dma->init_rx_chan(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_rx_phy, chan); + rx_q->dma_rx_phy, chan); - priv->rx_tail_addr = priv->dma_rx_phy + + rx_q->rx_tail_addr = rx_q->dma_rx_phy + (DMA_RX_SIZE * sizeof(struct dma_desc)); priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - priv->rx_tail_addr, + rx_q->rx_tail_addr, chan); } /* DMA TX Channel Configuration */ for (chan = 0; chan < tx_channels_count; chan++) { + tx_q = &priv->tx_queue[chan]; + priv->hw->dma->init_chan(priv->ioaddr, - priv->plat->dma_cfg, - chan); + priv->plat->dma_cfg, + chan); priv->hw->dma->init_tx_chan(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_tx_phy, chan); + tx_q->dma_tx_phy, chan); - priv->tx_tail_addr = priv->dma_tx_phy + + tx_q->tx_tail_addr = tx_q->dma_tx_phy + (DMA_TX_SIZE * sizeof(struct dma_desc)); priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, - priv->tx_tail_addr, + tx_q->tx_tail_addr, chan); } } else { + rx_q = &priv->rx_queue[chan]; + tx_q = &priv->tx_queue[chan]; + priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, - priv->dma_tx_phy, priv->dma_rx_phy, atds); + tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds); } if (priv->plat->axi && priv->hw->dma->axi) @@ -1808,8 +2127,70 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) static void stmmac_tx_timer(unsigned long data) { struct stmmac_priv *priv = (struct stmmac_priv *)data; + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 queue; - stmmac_tx_clean(priv); + /* let's scan all the tx queues */ + for (queue = 0; queue < tx_queues_count; queue++) + stmmac_tx_clean(priv, queue); +} + +/** + * stmmac_stop_all_queues - Stop all queues + * @priv: driver private structure + */ +static void stmmac_stop_all_queues(struct stmmac_priv *priv) +{ + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < tx_queues_cnt; queue++) + netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); +} + +/** + * stmmac_start_all_queues - Start all queues + * @priv: driver private structure + */ +static void stmmac_start_all_queues(struct stmmac_priv *priv) +{ + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < tx_queues_cnt; queue++) + netif_tx_start_queue(netdev_get_tx_queue(priv->dev, queue)); +} + +/** + * stmmac_disable_all_queues - Disable all queues + * @priv: driver private structure + */ +static void stmmac_disable_all_queues(struct stmmac_priv *priv) +{ + u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 queue; + + for (queue = 0; queue < rx_queues_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + napi_disable(&rx_q->napi); + } +} + +/** + * stmmac_enable_all_queues - Enable all queues + * @priv: driver private structure + */ +static void stmmac_enable_all_queues(struct stmmac_priv *priv) +{ + u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 queue; + + for (queue = 0; queue < rx_queues_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + napi_enable(&rx_q->napi); + } } /** @@ -2098,23 +2479,8 @@ static int stmmac_open(struct net_device *dev) memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats)); priv->xstats.threshold = tc; - priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); priv->rx_copybreak = STMMAC_RX_COPYBREAK; - ret = alloc_dma_desc_resources(priv); - if (ret < 0) { - netdev_err(priv->dev, "%s: DMA descriptors allocation failed\n", - __func__); - goto dma_desc_error; - } - - ret = init_dma_desc_rings(dev, GFP_KERNEL); - if (ret < 0) { - netdev_err(priv->dev, "%s: DMA descriptors initialization failed\n", - __func__); - goto init_error; - } - ret = stmmac_hw_setup(dev, true); if (ret < 0) { netdev_err(priv->dev, "%s: Hw setup failed\n", __func__); @@ -2160,8 +2526,8 @@ static int stmmac_open(struct net_device *dev) } } - napi_enable(&priv->napi); - netif_start_queue(dev); + stmmac_enable_all_queues(priv); + stmmac_start_all_queues(priv); return 0; @@ -2178,7 +2544,7 @@ static int stmmac_open(struct net_device *dev) stmmac_hw_teardown(dev); init_error: free_dma_desc_resources(priv); -dma_desc_error: + if (dev->phydev) phy_disconnect(dev->phydev); @@ -2204,9 +2570,9 @@ static int stmmac_release(struct net_device *dev) phy_disconnect(dev->phydev); } - netif_stop_queue(dev); + stmmac_stop_all_queues(priv); - napi_disable(&priv->napi); + stmmac_disable_all_queues(priv); del_timer_sync(&priv->txtimer); @@ -2243,22 +2609,24 @@ static int stmmac_release(struct net_device *dev) * @des: buffer start address * @total_len: total length to fill in descriptors * @last_segmant: condition for the last descriptor + * @queue: TX queue index * Description: * This function fills descriptor and request new descriptors according to * buffer length to fill */ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des, - int total_len, bool last_segment) + int total_len, bool last_segment, u32 queue) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; struct dma_desc *desc; - int tmp_len; u32 buff_size; + int tmp_len; tmp_len = total_len; while (tmp_len > 0) { - priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE); - desc = priv->dma_tx + priv->cur_tx; + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + desc = tx_q->dma_tx + tx_q->cur_tx; desc->des0 = cpu_to_le32(des + (total_len - tmp_len)); buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ? @@ -2302,23 +2670,27 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des, */ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { - u32 pay_len, mss; - int tmp_pay_len = 0; + struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); + u32 queue = skb_get_queue_mapping(skb); int nfrags = skb_shinfo(skb)->nr_frags; unsigned int first_entry, des; - struct dma_desc *desc, *first, *mss_desc = NULL; + struct stmmac_tx_queue *tx_q; + int tmp_pay_len = 0; + u32 pay_len, mss; u8 proto_hdr_len; int i; + tx_q = &priv->tx_queue[queue]; + /* Compute header lengths */ proto_hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); /* Desc availability based on threshold should be enough safe */ - if (unlikely(stmmac_tx_avail(priv) < + if (unlikely(stmmac_tx_avail(priv, queue) < (((skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1)))) { - if (!netif_queue_stopped(dev)) { - netif_stop_queue(dev); + if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { + netif_tx_stop_queue(netdev_get_tx_queue(dev, queue)); /* This is a hard error, log it. */ netdev_err(priv->dev, "%s: Tx Ring full when queue awake\n", @@ -2333,10 +2705,10 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* set new MSS value if needed */ if (mss != priv->mss) { - mss_desc = priv->dma_tx + priv->cur_tx; + mss_desc = tx_q->dma_tx + tx_q->cur_tx; priv->hw->desc->set_mss(mss_desc, mss); priv->mss = mss; - priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE); + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); } if (netif_msg_tx_queued(priv)) { @@ -2346,9 +2718,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb->data_len); } - first_entry = priv->cur_tx; + first_entry = tx_q->cur_tx; - desc = priv->dma_tx + first_entry; + desc = tx_q->dma_tx + first_entry; first = desc; /* first descriptor: fill Headers on Buf1 */ @@ -2357,9 +2729,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; - priv->tx_skbuff_dma[first_entry].buf = des; - priv->tx_skbuff_dma[first_entry].len = skb_headlen(skb); - priv->tx_skbuff[first_entry] = skb; + tx_q->tx_skbuff_dma[first_entry].buf = des; + tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb); + tx_q->tx_skbuff[first_entry] = skb; first->des0 = cpu_to_le32(des); @@ -2370,7 +2742,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* If needed take extra descriptors to fill the remaining payload */ tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE; - stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0)); + stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue); /* Prepare fragments */ for (i = 0; i < nfrags; i++) { @@ -2383,22 +2755,22 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) goto dma_map_err; stmmac_tso_allocator(priv, des, skb_frag_size(frag), - (i == nfrags - 1)); + (i == nfrags - 1), queue); - priv->tx_skbuff_dma[priv->cur_tx].buf = des; - priv->tx_skbuff_dma[priv->cur_tx].len = skb_frag_size(frag); - priv->tx_skbuff[priv->cur_tx] = NULL; - priv->tx_skbuff_dma[priv->cur_tx].map_as_page = true; + tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des; + tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_frag_size(frag); + tx_q->tx_skbuff[tx_q->cur_tx] = NULL; + tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = true; } - priv->tx_skbuff_dma[priv->cur_tx].last_segment = true; + tx_q->tx_skbuff_dma[tx_q->cur_tx].last_segment = true; - priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE); + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); - if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) { + if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) { netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n", __func__); - netif_stop_queue(dev); + netif_tx_stop_queue(netdev_get_tx_queue(dev, queue)); } dev->stats.tx_bytes += skb->len; @@ -2430,7 +2802,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->hw->desc->prepare_tso_tx_desc(first, 1, proto_hdr_len, pay_len, - 1, priv->tx_skbuff_dma[first_entry].last_segment, + 1, tx_q->tx_skbuff_dma[first_entry].last_segment, tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len)); /* If context desc is used to change MSS */ @@ -2445,20 +2817,20 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) if (netif_msg_pktdata(priv)) { pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n", - __func__, priv->cur_tx, priv->dirty_tx, first_entry, - priv->cur_tx, first, nfrags); + __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry, + tx_q->cur_tx, first, nfrags); - priv->hw->desc->display_ring((void *)priv->dma_tx, DMA_TX_SIZE, + priv->hw->desc->display_ring((void *)tx_q->dma_tx, DMA_TX_SIZE, 0); pr_info(">>> frame to be transmitted: "); print_pkt(skb->data, skb_headlen(skb)); } - netdev_sent_queue(dev, skb->len); + netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr, - STMMAC_CHAN0); + priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr, + queue); return NETDEV_TX_OK; @@ -2482,21 +2854,25 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); unsigned int nopaged_len = skb_headlen(skb); int i, csum_insertion = 0, is_jumbo = 0; + u32 queue = skb_get_queue_mapping(skb); int nfrags = skb_shinfo(skb)->nr_frags; unsigned int entry, first_entry; struct dma_desc *desc, *first; + struct stmmac_tx_queue *tx_q; unsigned int enh_desc; unsigned int des; + tx_q = &priv->tx_queue[queue]; + /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { if (ip_hdr(skb)->protocol == IPPROTO_TCP) return stmmac_tso_xmit(skb, dev); } - if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) { - if (!netif_queue_stopped(dev)) { - netif_stop_queue(dev); + if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { + if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { + netif_tx_stop_queue(netdev_get_tx_queue(dev, queue)); /* This is a hard error, log it. */ netdev_err(priv->dev, "%s: Tx Ring full when queue awake\n", @@ -2508,19 +2884,19 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (priv->tx_path_in_lpi_mode) stmmac_disable_eee_mode(priv); - entry = priv->cur_tx; + entry = tx_q->cur_tx; first_entry = entry; csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL); if (likely(priv->extend_desc)) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; first = desc; - priv->tx_skbuff[first_entry] = skb; + tx_q->tx_skbuff[first_entry] = skb; enh_desc = priv->plat->enh_desc; /* To program the descriptors according to the size of the frame */ @@ -2529,7 +2905,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(is_jumbo) && likely(priv->synopsys_id < DWMAC_CORE_4_00)) { - entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion); + entry = priv->hw->mode->jumbo_frm(tx_q, skb, csum_insertion); if (unlikely(entry < 0)) goto dma_map_err; } @@ -2542,26 +2918,26 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); if (likely(priv->extend_desc)) - desc = (struct dma_desc *)(priv->dma_etx + entry); + desc = (struct dma_desc *)(tx_q->dma_etx + entry); else - desc = priv->dma_tx + entry; + desc = tx_q->dma_tx + entry; des = skb_frag_dma_map(priv->device, frag, 0, len, DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) goto dma_map_err; /* should reuse desc w/o issues */ - priv->tx_skbuff[entry] = NULL; + tx_q->tx_skbuff[entry] = NULL; - priv->tx_skbuff_dma[entry].buf = des; + tx_q->tx_skbuff_dma[entry].buf = des; if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) desc->des0 = cpu_to_le32(des); else desc->des2 = cpu_to_le32(des); - priv->tx_skbuff_dma[entry].map_as_page = true; - priv->tx_skbuff_dma[entry].len = len; - priv->tx_skbuff_dma[entry].last_segment = last_segment; + tx_q->tx_skbuff_dma[entry].map_as_page = true; + tx_q->tx_skbuff_dma[entry].len = len; + tx_q->tx_skbuff_dma[entry].last_segment = last_segment; /* Prepare the descriptor and set the own bit too */ priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, @@ -2570,20 +2946,20 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); - priv->cur_tx = entry; + tx_q->cur_tx = entry; if (netif_msg_pktdata(priv)) { void *tx_head; netdev_dbg(priv->dev, "%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d", - __func__, priv->cur_tx, priv->dirty_tx, first_entry, + __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry, entry, first, nfrags); if (priv->extend_desc) - tx_head = (void *)priv->dma_etx; + tx_head = (void *)tx_q->dma_etx; else - tx_head = (void *)priv->dma_tx; + tx_head = (void *)tx_q->dma_tx; priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false); @@ -2591,10 +2967,10 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) print_pkt(skb->data, skb->len); } - if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) { + if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) { netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n", __func__); - netif_stop_queue(dev); + netif_tx_stop_queue(netdev_get_tx_queue(dev, queue)); } dev->stats.tx_bytes += skb->len; @@ -2629,14 +3005,14 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; - priv->tx_skbuff_dma[first_entry].buf = des; + tx_q->tx_skbuff_dma[first_entry].buf = des; if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) first->des0 = cpu_to_le32(des); else first->des2 = cpu_to_le32(des); - priv->tx_skbuff_dma[first_entry].len = nopaged_len; - priv->tx_skbuff_dma[first_entry].last_segment = last_segment; + tx_q->tx_skbuff_dma[first_entry].len = nopaged_len; + tx_q->tx_skbuff_dma[first_entry].last_segment = last_segment; if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)) { @@ -2657,13 +3033,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) dma_wmb(); } - netdev_sent_queue(dev, skb->len); + netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); if (priv->synopsys_id < DWMAC_CORE_4_00) priv->hw->dma->enable_dma_transmission(priv->ioaddr); else - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr, - STMMAC_CHAN0); + priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr, + queue); return NETDEV_TX_OK; @@ -2691,9 +3067,9 @@ static void stmmac_rx_vlan(struct net_device *dev, struct sk_buff *skb) } -static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv) +static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q) { - if (priv->rx_zeroc_thresh < STMMAC_RX_THRESH) + if (rx_q->rx_zeroc_thresh < STMMAC_RX_THRESH) return 0; return 1; @@ -2702,30 +3078,32 @@ static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv) /** * stmmac_rx_refill - refill used skb preallocated buffers * @priv: driver private structure + * @queue: RX queue index * Description : this is to reallocate the skb for the reception process * that is based on zero-copy. */ -static inline void stmmac_rx_refill(struct stmmac_priv *priv) +static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + int dirty = stmmac_rx_dirty(priv, queue); + unsigned int entry = rx_q->dirty_rx; int bfsize = priv->dma_buf_sz; - unsigned int entry = priv->dirty_rx; - int dirty = stmmac_rx_dirty(priv); while (dirty-- > 0) { struct dma_desc *p; if (priv->extend_desc) - p = (struct dma_desc *)(priv->dma_erx + entry); + p = (struct dma_desc *)(rx_q->dma_erx + entry); else - p = priv->dma_rx + entry; + p = rx_q->dma_rx + entry; - if (likely(priv->rx_skbuff[entry] == NULL)) { + if (!rx_q->rx_skbuff[entry]) { struct sk_buff *skb; skb = netdev_alloc_skb_ip_align(priv->dev, bfsize); if (unlikely(!skb)) { /* so for a while no zero-copy! */ - priv->rx_zeroc_thresh = STMMAC_RX_THRESH; + rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH; if (unlikely(net_ratelimit())) dev_err(priv->device, "fail to alloc skb entry %d\n", @@ -2733,28 +3111,28 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) break; } - priv->rx_skbuff[entry] = skb; - priv->rx_skbuff_dma[entry] = + rx_q->rx_skbuff[entry] = skb; + rx_q->rx_skbuff_dma[entry] = dma_map_single(priv->device, skb->data, bfsize, DMA_FROM_DEVICE); if (dma_mapping_error(priv->device, - priv->rx_skbuff_dma[entry])) { + rx_q->rx_skbuff_dma[entry])) { netdev_err(priv->dev, "Rx DMA map failed\n"); dev_kfree_skb(skb); break; } if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) { - p->des0 = cpu_to_le32(priv->rx_skbuff_dma[entry]); + p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]); p->des1 = 0; } else { - p->des2 = cpu_to_le32(priv->rx_skbuff_dma[entry]); + p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]); } if (priv->hw->mode->refill_desc3) - priv->hw->mode->refill_desc3(priv, p); + priv->hw->mode->refill_desc3(rx_q, p); - if (priv->rx_zeroc_thresh > 0) - priv->rx_zeroc_thresh--; + if (rx_q->rx_zeroc_thresh > 0) + rx_q->rx_zeroc_thresh--; netif_dbg(priv, rx_status, priv->dev, "refill entry #%d\n", entry); @@ -2770,7 +3148,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE); } - priv->dirty_rx = entry; + rx_q->dirty_rx = entry; } /** @@ -2780,21 +3158,22 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) * Description : this the function called by the napi poll method. * It gets all the frames inside the ring. */ -static int stmmac_rx(struct stmmac_priv *priv, int limit) +static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { - unsigned int entry = priv->cur_rx; + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + unsigned int entry = rx_q->cur_rx; + int coe = priv->hw->rx_csum; unsigned int next_entry; unsigned int count = 0; - int coe = priv->hw->rx_csum; if (netif_msg_rx_status(priv)) { void *rx_head; netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__); if (priv->extend_desc) - rx_head = (void *)priv->dma_erx; + rx_head = (void *)rx_q->dma_erx; else - rx_head = (void *)priv->dma_rx; + rx_head = (void *)rx_q->dma_rx; priv->hw->desc->display_ring(rx_head, DMA_RX_SIZE, true); } @@ -2804,9 +3183,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) struct dma_desc *np; if (priv->extend_desc) - p = (struct dma_desc *)(priv->dma_erx + entry); + p = (struct dma_desc *)(rx_q->dma_erx + entry); else - p = priv->dma_rx + entry; + p = rx_q->dma_rx + entry; /* read the status of the incoming frame */ status = priv->hw->desc->rx_status(&priv->dev->stats, @@ -2817,20 +3196,20 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) count++; - priv->cur_rx = STMMAC_GET_ENTRY(priv->cur_rx, DMA_RX_SIZE); - next_entry = priv->cur_rx; + rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE); + next_entry = rx_q->cur_rx; if (priv->extend_desc) - np = (struct dma_desc *)(priv->dma_erx + next_entry); + np = (struct dma_desc *)(rx_q->dma_erx + next_entry); else - np = priv->dma_rx + next_entry; + np = rx_q->dma_rx + next_entry; prefetch(np); if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status)) priv->hw->desc->rx_extended_status(&priv->dev->stats, &priv->xstats, - priv->dma_erx + + rx_q->dma_erx + entry); if (unlikely(status == discard_frame)) { priv->dev->stats.rx_errors++; @@ -2840,9 +3219,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) * them in stmmac_rx_refill() function so that * device can reuse it. */ - priv->rx_skbuff[entry] = NULL; + rx_q->rx_skbuff[entry] = NULL; dma_unmap_single(priv->device, - priv->rx_skbuff_dma[entry], + rx_q->rx_skbuff_dma[entry], priv->dma_buf_sz, DMA_FROM_DEVICE); } @@ -2890,7 +3269,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) */ if (unlikely(!priv->plat->has_gmac4 && ((frame_len < priv->rx_copybreak) || - stmmac_rx_threshold_count(priv)))) { + stmmac_rx_threshold_count(rx_q)))) { skb = netdev_alloc_skb_ip_align(priv->dev, frame_len); if (unlikely(!skb)) { @@ -2902,21 +3281,21 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) } dma_sync_single_for_cpu(priv->device, - priv->rx_skbuff_dma + rx_q->rx_skbuff_dma [entry], frame_len, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, - priv-> + rx_q-> rx_skbuff[entry]->data, frame_len); skb_put(skb, frame_len); dma_sync_single_for_device(priv->device, - priv->rx_skbuff_dma + rx_q->rx_skbuff_dma [entry], frame_len, DMA_FROM_DEVICE); } else { - skb = priv->rx_skbuff[entry]; + skb = rx_q->rx_skbuff[entry]; if (unlikely(!skb)) { netdev_err(priv->dev, "%s: Inconsistent Rx chain\n", @@ -2925,12 +3304,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) break; } prefetch(skb->data - NET_IP_ALIGN); - priv->rx_skbuff[entry] = NULL; - priv->rx_zeroc_thresh++; + rx_q->rx_skbuff[entry] = NULL; + rx_q->rx_zeroc_thresh++; skb_put(skb, frame_len); dma_unmap_single(priv->device, - priv->rx_skbuff_dma[entry], + rx_q->rx_skbuff_dma[entry], priv->dma_buf_sz, DMA_FROM_DEVICE); } @@ -2952,7 +3331,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) else skb->ip_summed = CHECKSUM_UNNECESSARY; - napi_gro_receive(&priv->napi, skb); + napi_gro_receive(&rx_q->napi, skb); priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += frame_len; @@ -2960,7 +3339,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) entry = next_entry; } - stmmac_rx_refill(priv); + stmmac_rx_refill(priv, queue); priv->xstats.rx_pkt_n += count; @@ -2977,14 +3356,22 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) */ static int stmmac_poll(struct napi_struct *napi, int budget) { - struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi); - int work_done = 0; - u32 chan = STMMAC_CHAN0; + struct stmmac_rx_queue *rx_q = + container_of(napi, struct stmmac_rx_queue, napi); + struct stmmac_priv *priv = rx_q->priv_data; + u32 tx_count = priv->dma_cap.number_tx_queues; + u32 chan = rx_q->queue_index; + u32 work_done = 0; + u32 queue = 0; priv->xstats.napi_poll++; - stmmac_tx_clean(priv); + /* check all the queues */ + for (queue = 0; queue < tx_count; queue++) + stmmac_tx_clean(priv, queue); + + /* Process RX packets from this queue */ + work_done = stmmac_rx(priv, budget, rx_q->queue_index); - work_done = stmmac_rx(priv, budget); if (work_done < budget) { napi_complete_done(napi, work_done); stmmac_enable_dma_irq(priv, chan); @@ -3003,10 +3390,12 @@ static int stmmac_poll(struct napi_struct *napi, int budget) static void stmmac_tx_timeout(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - u32 chan = STMMAC_CHAN0; + u32 tx_count = priv->plat->tx_queues_to_use; + u32 chan; /* Clear Tx resources and restart transmitting again */ - stmmac_tx_err(priv, chan); + for (chan = 0; chan < tx_count; chan++) + stmmac_tx_err(priv, chan); } /** @@ -3145,6 +3534,9 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if (priv->synopsys_id >= DWMAC_CORE_4_00) { for (queue = 0; queue < queues_count; queue++) { + struct stmmac_rx_queue *rx_q = + &priv->rx_queue[queue]; + status |= priv->hw->mac->host_mtl_irq_status(priv->hw, queue); @@ -3152,7 +3544,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr) priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - priv->rx_tail_addr, + rx_q->rx_tail_addr, queue); } } @@ -3252,17 +3644,40 @@ static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v) { struct net_device *dev = seq->private; struct stmmac_priv *priv = netdev_priv(dev); + u32 rx_count = priv->plat->rx_queues_to_use; + u32 tx_count = priv->plat->tx_queues_to_use; + u32 queue; - if (priv->extend_desc) { - seq_printf(seq, "Extended RX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_erx, DMA_RX_SIZE, 1, seq); - seq_printf(seq, "Extended TX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_etx, DMA_TX_SIZE, 1, seq); - } else { - seq_printf(seq, "RX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_rx, DMA_RX_SIZE, 0, seq); - seq_printf(seq, "TX descriptor ring:\n"); - sysfs_display_ring((void *)priv->dma_tx, DMA_TX_SIZE, 0, seq); + for (queue = 0; queue < rx_count; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + seq_printf(seq, "RX Queue %d:\n", queue); + + if (priv->extend_desc) { + seq_printf(seq, "Extended descriptor ring:\n"); + sysfs_display_ring((void *)rx_q->dma_erx, + DMA_RX_SIZE, 1, seq); + } else { + seq_printf(seq, "Descriptor ring:\n"); + sysfs_display_ring((void *)rx_q->dma_rx, + DMA_RX_SIZE, 0, seq); + } + } + + for (queue = 0; queue < tx_count; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + seq_printf(seq, "TX Queue %d:\n", queue); + + if (priv->extend_desc) { + seq_printf(seq, "Extended descriptor ring:\n"); + sysfs_display_ring((void *)tx_q->dma_etx, + DMA_TX_SIZE, 1, seq); + } else { + seq_printf(seq, "Descriptor ring:\n"); + sysfs_display_ring((void *)tx_q->dma_tx, + DMA_TX_SIZE, 0, seq); + } } return 0; @@ -3545,11 +3960,14 @@ int stmmac_dvr_probe(struct device *device, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *res) { - int ret = 0; struct net_device *ndev = NULL; struct stmmac_priv *priv; + int ret = 0; + u32 queue; - ndev = alloc_etherdev(sizeof(struct stmmac_priv)); + ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv), + MTL_MAX_TX_QUEUES, + MTL_MAX_RX_QUEUES); if (!ndev) return -ENOMEM; @@ -3591,6 +4009,12 @@ int stmmac_dvr_probe(struct device *device, if (ret) goto error_hw_init; + /* Configure real RX and TX queues */ + ndev->real_num_rx_queues = priv->plat->rx_queues_to_use; + ndev->real_num_tx_queues = priv->plat->tx_queues_to_use; + + priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); + ndev->netdev_ops = &stmmac_netdev_ops; ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -3640,7 +4064,26 @@ int stmmac_dvr_probe(struct device *device, "Enable RX Mitigation via HW Watchdog Timer\n"); } - netif_napi_add(ndev, &priv->napi, stmmac_poll, 64); + ret = alloc_dma_desc_resources(priv); + if (ret < 0) { + netdev_err(priv->dev, "%s: DMA descriptors allocation failed\n", + __func__); + goto init_dma_error; + } + + ret = init_dma_desc_rings(priv->dev, GFP_KERNEL); + if (ret < 0) { + netdev_err(priv->dev, "%s: DMA descriptors initialization failed\n", + __func__); + goto init_dma_error; + } + + for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + netif_napi_add(ndev, &rx_q->napi, stmmac_poll, + (64 * priv->plat->rx_queues_to_use)); + } spin_lock_init(&priv->lock); @@ -3685,7 +4128,13 @@ int stmmac_dvr_probe(struct device *device, priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); error_mdio_register: - netif_napi_del(&priv->napi); + for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + netif_napi_del(&rx_q->napi); + } +init_dma_error: + free_dma_desc_resources(priv); error_hw_init: free_netdev(ndev); @@ -3747,9 +4196,9 @@ int stmmac_suspend(struct device *dev) spin_lock_irqsave(&priv->lock, flags); netif_device_detach(ndev); - netif_stop_queue(ndev); + stmmac_stop_all_queues(priv); - napi_disable(&priv->napi); + stmmac_disable_all_queues(priv); /* Stop TX/RX DMA */ stmmac_stop_all_dma(priv); @@ -3774,6 +4223,31 @@ int stmmac_suspend(struct device *dev) } EXPORT_SYMBOL_GPL(stmmac_suspend); +/** + * stmmac_reset_queues_param - reset queue parameters + * @dev: device pointer + */ +static void stmmac_reset_queues_param(struct stmmac_priv *priv) +{ + u32 rx_cnt = priv->plat->rx_queues_to_use; + u32 tx_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < rx_cnt; queue++) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + + rx_q->cur_rx = 0; + rx_q->dirty_rx = 0; + } + + for (queue = 0; queue < tx_cnt; queue++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + tx_q->cur_tx = 0; + tx_q->dirty_tx = 0; + } +} + /** * stmmac_resume - resume callback * @dev: device pointer @@ -3814,10 +4288,8 @@ int stmmac_resume(struct device *dev) spin_lock_irqsave(&priv->lock, flags); - priv->cur_rx = 0; - priv->dirty_rx = 0; - priv->dirty_tx = 0; - priv->cur_tx = 0; + stmmac_reset_queues_param(priv); + /* reset private mss value to force mss context settings at * next tso xmit (only used for gmac4). */ @@ -3829,9 +4301,9 @@ int stmmac_resume(struct device *dev) stmmac_init_tx_coalesce(priv); stmmac_set_rx_mode(ndev); - napi_enable(&priv->napi); + stmmac_enable_all_queues(priv); - netif_start_queue(ndev); + stmmac_start_all_queues(priv); spin_unlock_irqrestore(&priv->lock, flags); From a8f5102af2a7740a4b3200a27beddf27f23f921a Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 17 Mar 2017 16:11:06 +0000 Subject: [PATCH 388/399] net: stmmac: TX and RX queue priority configuration This patch adds the configuration of RX and TX queues' priority. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- .../devicetree/bindings/net/stmmac.txt | 5 ++ drivers/net/ethernet/stmicro/stmmac/common.h | 4 ++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 13 +++++ .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 37 ++++++++++++++ .../net/ethernet/stmicro/stmmac/stmmac_main.c | 48 +++++++++++++++++++ .../net/ethernet/stmicro/stmmac/stmmac_pci.c | 4 ++ .../ethernet/stmicro/stmmac/stmmac_platform.c | 16 +++++++ include/linux/stmmac.h | 4 ++ 8 files changed, 131 insertions(+) diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index a7b0e41cb264..d11bd09f4ba6 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -83,6 +83,7 @@ Optional properties: - snps,dcb-algorithm: Queue to be enabled as DCB - snps,avb-algorithm: Queue to be enabled as AVB - snps,map-to-dma-channel: Channel to map + - snps,priority: RX queue priority (Range: 0x0 to 0xF) - Multiple TX Queues parameters: below the list of all the parameters to configure the multiple TX queues: - snps,tx-queues-to-use: number of TX queues to be used in the driver @@ -101,6 +102,7 @@ Optional properties: - snps,idle_slope: unlock on WoL - snps,high_credit: max write outstanding req. limit - snps,low_credit: max read outstanding req. limit + - snps,priority: TX queue priority (Range: 0x0 to 0xF) Examples: stmmac_axi_setup: stmmac-axi-config { @@ -115,6 +117,7 @@ Examples: queue0 { snps,dcb-algorithm; snps,map-to-dma-channel = <0x0>; + snps,priority = <0x0>; }; }; @@ -124,6 +127,7 @@ Examples: queue0 { snps,weight = <0x10>; snps,dcb-algorithm; + snps,priority = <0x0>; }; queue1 { @@ -132,6 +136,7 @@ Examples: snps,idle_slope = <0x1000>; snps,high_credit = <0x3E800>; snps,low_credit = <0xFFC18000>; + snps,priority = <0x1>; }; }; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index badc4414d67b..e0b31e759c0e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -469,6 +469,10 @@ struct stmmac_ops { int (*rx_ipc)(struct mac_device_info *hw); /* Enable RX Queues */ void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue); + /* RX Queues Priority */ + void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); + /* TX Queues Priority */ + void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); /* Program RX Algorithms */ void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); /* Program TX Algorithms */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 54bcdb4d10db..a6c382d22ebf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -22,7 +22,12 @@ #define GMAC_HASH_TAB_32_63 0x00000014 #define GMAC_RX_FLOW_CTRL 0x00000090 #define GMAC_QX_TX_FLOW_CTRL(x) (0x70 + x * 4) +#define GMAC_TXQ_PRTY_MAP0 0x98 +#define GMAC_TXQ_PRTY_MAP1 0x9C #define GMAC_RXQ_CTRL0 0x000000a0 +#define GMAC_RXQ_CTRL1 0x000000a4 +#define GMAC_RXQ_CTRL2 0x000000a8 +#define GMAC_RXQ_CTRL3 0x000000ac #define GMAC_INT_STATUS 0x000000b0 #define GMAC_INT_EN 0x000000b4 #define GMAC_1US_TIC_COUNTER 0x000000dc @@ -54,6 +59,14 @@ /* MAC Flow Control RX */ #define GMAC_RX_FLOW_CTRL_RFE BIT(0) +/* RX Queues Priorities */ +#define GMAC_RXQCTRL_PSRQX_MASK(x) GENMASK(7 + ((x) * 8), 0 + ((x) * 8)) +#define GMAC_RXQCTRL_PSRQX_SHIFT(x) ((x) * 8) + +/* TX Queues Priorities */ +#define GMAC_TXQCTRL_PSTQX_MASK(x) GENMASK(7 + ((x) * 8), 0 + ((x) * 8)) +#define GMAC_TXQCTRL_PSTQX_SHIFT(x) ((x) * 8) + /* MAC Flow Control TX */ #define GMAC_TX_FLOW_CTRL_TFE BIT(1) #define GMAC_TX_FLOW_CTRL_PT_SHIFT 16 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 10599dbc232f..342f62abb9ca 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -74,6 +74,41 @@ static void dwmac4_rx_queue_enable(struct mac_device_info *hw, writel(value, ioaddr + GMAC_RXQ_CTRL0); } +static void dwmac4_rx_queue_priority(struct mac_device_info *hw, + u32 prio, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 base_register; + u32 value; + + base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; + + value = readl(ioaddr + base_register); + + value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue); + value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + GMAC_RXQCTRL_PSRQX_MASK(queue); + writel(value, ioaddr + base_register); +} + +static void dwmac4_tx_queue_priority(struct mac_device_info *hw, + u32 prio, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 base_register; + u32 value; + + base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1; + + value = readl(ioaddr + base_register); + + value &= ~GMAC_TXQCTRL_PSTQX_MASK(queue); + value |= (prio << GMAC_TXQCTRL_PSTQX_SHIFT(queue)) & + GMAC_TXQCTRL_PSTQX_MASK(queue); + + writel(value, ioaddr + base_register); +} + static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw, u32 rx_alg) { @@ -603,6 +638,8 @@ static const struct stmmac_ops dwmac4_ops = { .core_init = dwmac4_core_init, .rx_ipc = dwmac4_rx_ipc_enable, .rx_queue_enable = dwmac4_rx_queue_enable, + .rx_queue_prio = dwmac4_rx_queue_priority, + .tx_queue_prio = dwmac4_tx_queue_priority, .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a389dfbe630c..0f2c0d762e33 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2292,6 +2292,46 @@ static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv) } } +/** + * stmmac_mac_config_rx_queues_prio - Configure RX Queue priority + * @priv: driver private structure + * Description: It is used for configuring the RX Queue Priority + */ +static void stmmac_mac_config_rx_queues_prio(struct stmmac_priv *priv) +{ + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 queue; + u32 prio; + + for (queue = 0; queue < rx_queues_count; queue++) { + if (!priv->plat->rx_queues_cfg[queue].use_prio) + continue; + + prio = priv->plat->rx_queues_cfg[queue].prio; + priv->hw->mac->rx_queue_prio(priv->hw, prio, queue); + } +} + +/** + * stmmac_mac_config_tx_queues_prio - Configure TX Queue priority + * @priv: driver private structure + * Description: It is used for configuring the TX Queue Priority + */ +static void stmmac_mac_config_tx_queues_prio(struct stmmac_priv *priv) +{ + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 queue; + u32 prio; + + for (queue = 0; queue < tx_queues_count; queue++) { + if (!priv->plat->tx_queues_cfg[queue].use_prio) + continue; + + prio = priv->plat->tx_queues_cfg[queue].prio; + priv->hw->mac->tx_queue_prio(priv->hw, prio, queue); + } +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -2329,6 +2369,14 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) /* Set the HW DMA mode and the COE */ stmmac_dma_operation_mode(priv); + + /* Set RX priorities */ + if (rx_queues_count > 1 && priv->hw->mac->rx_queue_prio) + stmmac_mac_config_rx_queues_prio(priv); + + /* Set TX priorities */ + if (tx_queues_count > 1 && priv->hw->mac->tx_queue_prio) + stmmac_mac_config_tx_queues_prio(priv); } /** diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index cea472a7c335..ffe4fac22d3d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -92,6 +92,10 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat) /* Set default number of RX and TX queues to use */ plat->tx_queues_to_use = 1; plat->rx_queues_to_use = 1; + + /* Disable Priority config by default */ + plat->tx_queues_cfg[0].use_prio = false; + plat->rx_queues_cfg[0].use_prio = false; } static int quark_default_data(struct plat_stmmacenet_data *plat, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 37f550ae76a5..77b0468dd79f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -182,6 +182,14 @@ static void stmmac_mtl_setup(struct platform_device *pdev, plat->rx_queues_cfg[queue].chan = queue; /* TODO: Dynamic mapping to be included in the future */ + if (of_property_read_u32(q_node, "snps,priority", + &plat->rx_queues_cfg[queue].prio)) { + plat->rx_queues_cfg[queue].prio = 0; + plat->rx_queues_cfg[queue].use_prio = false; + } else { + plat->rx_queues_cfg[queue].use_prio = true; + } + queue++; } @@ -235,6 +243,14 @@ static void stmmac_mtl_setup(struct platform_device *pdev, plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; } + if (of_property_read_u32(q_node, "snps,priority", + &plat->tx_queues_cfg[queue].prio)) { + plat->tx_queues_cfg[queue].prio = 0; + plat->tx_queues_cfg[queue].use_prio = false; + } else { + plat->tx_queues_cfg[queue].use_prio = true; + } + queue++; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index be47b859e954..b7d5e7ae9591 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -127,6 +127,8 @@ struct stmmac_axi { struct stmmac_rxq_cfg { u8 mode_to_use; u8 chan; + bool use_prio; + u32 prio; }; struct stmmac_txq_cfg { @@ -137,6 +139,8 @@ struct stmmac_txq_cfg { u32 idle_slope; u32 high_credit; u32 low_credit; + bool use_prio; + u32 prio; }; struct plat_stmmacenet_data { From abe80fdc6ee664b2f8515f91b45e852b65dbb1a1 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Fri, 17 Mar 2017 16:11:07 +0000 Subject: [PATCH 389/399] net: stmmac: RX queue routing configuration This patch adds the configuration of RX queues' routing. Signed-off-by: Joao Pinto Signed-off-by: David S. Miller --- .../devicetree/bindings/net/stmmac.txt | 6 ++++ drivers/net/ethernet/stmicro/stmmac/common.h | 17 ++++++++++ drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 16 +++++++++ .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 34 +++++++++++++++++++ .../net/ethernet/stmicro/stmmac/stmmac_main.c | 25 ++++++++++++++ .../net/ethernet/stmicro/stmmac/stmmac_pci.c | 3 ++ .../ethernet/stmicro/stmmac/stmmac_platform.c | 14 ++++++++ include/linux/stmmac.h | 1 + 8 files changed, 116 insertions(+) diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index d11bd09f4ba6..784d98862b52 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -83,6 +83,12 @@ Optional properties: - snps,dcb-algorithm: Queue to be enabled as DCB - snps,avb-algorithm: Queue to be enabled as AVB - snps,map-to-dma-channel: Channel to map + - Specifiy specific packet routing: + - snps,route-avcp: AV Untagged Control packets + - snps,route-ptp: PTP Packets + - snps,route-dcbcp: DCB Control Packets + - snps,route-up: Untagged Packets + - snps,route-multi-broad: Multicast & Broadcast Packets - snps,priority: RX queue priority (Range: 0x0 to 0xF) - Multiple TX Queues parameters: below the list of all the parameters to configure the multiple TX queues: diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index e0b31e759c0e..572cf8b61707 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -246,6 +246,15 @@ struct stmmac_extra_stats { #define STMMAC_TX_MAX_FRAMES 256 #define STMMAC_TX_FRAMES 64 +/* Packets types */ +enum packets_types { + PACKET_AVCPQ = 0x1, /* AV Untagged Control packets */ + PACKET_PTPQ = 0x2, /* PTP Packets */ + PACKET_DCBCPQ = 0x3, /* DCB Control Packets */ + PACKET_UPQ = 0x4, /* Untagged Packets */ + PACKET_MCBCQ = 0x5, /* Multicast & Broadcast Packets */ +}; + /* Rx IPC status */ enum rx_frame_status { good_frame = 0x0, @@ -473,6 +482,9 @@ struct stmmac_ops { void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); /* TX Queues Priority */ void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); + /* RX Queues Routing */ + void (*rx_queue_routing)(struct mac_device_info *hw, u8 packet, + u32 queue); /* Program RX Algorithms */ void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); /* Program TX Algorithms */ @@ -581,6 +593,11 @@ struct mac_device_info { unsigned int ps; }; +struct stmmac_rx_routing { + u32 reg_mask; + u32 reg_shift; +}; + struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins, int perfect_uc_entries, int *synopsys_id); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index a6c382d22ebf..d74cedf2a397 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -44,6 +44,22 @@ #define GMAC_ADDR_HIGH(reg) (0x300 + reg * 8) #define GMAC_ADDR_LOW(reg) (0x304 + reg * 8) +/* RX Queues Routing */ +#define GMAC_RXQCTRL_AVCPQ_MASK GENMASK(2, 0) +#define GMAC_RXQCTRL_AVCPQ_SHIFT 0 +#define GMAC_RXQCTRL_PTPQ_MASK GENMASK(6, 4) +#define GMAC_RXQCTRL_PTPQ_SHIFT 4 +#define GMAC_RXQCTRL_DCBCPQ_MASK GENMASK(10, 8) +#define GMAC_RXQCTRL_DCBCPQ_SHIFT 8 +#define GMAC_RXQCTRL_UPQ_MASK GENMASK(14, 12) +#define GMAC_RXQCTRL_UPQ_SHIFT 12 +#define GMAC_RXQCTRL_MCBCQ_MASK GENMASK(18, 16) +#define GMAC_RXQCTRL_MCBCQ_SHIFT 16 +#define GMAC_RXQCTRL_MCBCQEN BIT(20) +#define GMAC_RXQCTRL_MCBCQEN_SHIFT 20 +#define GMAC_RXQCTRL_TACPQE BIT(21) +#define GMAC_RXQCTRL_TACPQE_SHIFT 21 + /* MAC Packet Filtering */ #define GMAC_PACKET_FILTER_PR BIT(0) #define GMAC_PACKET_FILTER_HMC BIT(2) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 342f62abb9ca..40ce20218402 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -109,6 +109,39 @@ static void dwmac4_tx_queue_priority(struct mac_device_info *hw, writel(value, ioaddr + base_register); } +static void dwmac4_tx_queue_routing(struct mac_device_info *hw, + u8 packet, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + const struct stmmac_rx_routing route_possibilities[] = { + { GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT }, + { GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT }, + { GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT }, + { GMAC_RXQCTRL_UPQ_MASK, GMAC_RXQCTRL_UPQ_SHIFT }, + { GMAC_RXQCTRL_MCBCQ_MASK, GMAC_RXQCTRL_MCBCQ_SHIFT }, + }; + + value = readl(ioaddr + GMAC_RXQ_CTRL1); + + /* routing configuration */ + value &= ~route_possibilities[packet - 1].reg_mask; + value |= (queue << route_possibilities[packet-1].reg_shift) & + route_possibilities[packet - 1].reg_mask; + + /* some packets require extra ops */ + if (packet == PACKET_AVCPQ) { + value &= ~GMAC_RXQCTRL_TACPQE; + value |= 0x1 << GMAC_RXQCTRL_TACPQE_SHIFT; + } else if (packet == PACKET_MCBCQ) { + value &= ~GMAC_RXQCTRL_MCBCQEN; + value |= 0x1 << GMAC_RXQCTRL_MCBCQEN_SHIFT; + } + + writel(value, ioaddr + GMAC_RXQ_CTRL1); +} + static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw, u32 rx_alg) { @@ -640,6 +673,7 @@ static const struct stmmac_ops dwmac4_ops = { .rx_queue_enable = dwmac4_rx_queue_enable, .rx_queue_prio = dwmac4_rx_queue_priority, .tx_queue_prio = dwmac4_tx_queue_priority, + .rx_queue_routing = dwmac4_tx_queue_routing, .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0f2c0d762e33..531bf1dc35cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2332,6 +2332,27 @@ static void stmmac_mac_config_tx_queues_prio(struct stmmac_priv *priv) } } +/** + * stmmac_mac_config_rx_queues_routing - Configure RX Queue Routing + * @priv: driver private structure + * Description: It is used for configuring the RX queue routing + */ +static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) +{ + u32 rx_queues_count = priv->plat->rx_queues_to_use; + u32 queue; + u8 packet; + + for (queue = 0; queue < rx_queues_count; queue++) { + /* no specific packet type routing specified for the queue */ + if (priv->plat->rx_queues_cfg[queue].pkt_route == 0x0) + continue; + + packet = priv->plat->rx_queues_cfg[queue].pkt_route; + priv->hw->mac->rx_queue_prio(priv->hw, packet, queue); + } +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -2377,6 +2398,10 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) /* Set TX priorities */ if (tx_queues_count > 1 && priv->hw->mac->tx_queue_prio) stmmac_mac_config_tx_queues_prio(priv); + + /* Set RX routing */ + if (rx_queues_count > 1 && priv->hw->mac->rx_queue_routing) + stmmac_mac_config_rx_queues_routing(priv); } /** diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index ffe4fac22d3d..a224d7bf1c1b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -96,6 +96,9 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat) /* Disable Priority config by default */ plat->tx_queues_cfg[0].use_prio = false; plat->rx_queues_cfg[0].use_prio = false; + + /* Disable RX queues routing by default */ + plat->rx_queues_cfg[0].pkt_route = 0x0; } static int quark_default_data(struct plat_stmmacenet_data *plat, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 77b0468dd79f..f5c8b1bca002 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -190,6 +190,20 @@ static void stmmac_mtl_setup(struct platform_device *pdev, plat->rx_queues_cfg[queue].use_prio = true; } + /* RX queue specific packet type routing */ + if (of_property_read_bool(q_node, "snps,route-avcp")) + plat->rx_queues_cfg[queue].pkt_route = PACKET_AVCPQ; + else if (of_property_read_bool(q_node, "snps,route-ptp")) + plat->rx_queues_cfg[queue].pkt_route = PACKET_PTPQ; + else if (of_property_read_bool(q_node, "snps,route-dcbcp")) + plat->rx_queues_cfg[queue].pkt_route = PACKET_DCBCPQ; + else if (of_property_read_bool(q_node, "snps,route-up")) + plat->rx_queues_cfg[queue].pkt_route = PACKET_UPQ; + else if (of_property_read_bool(q_node, "snps,route-multi-broad")) + plat->rx_queues_cfg[queue].pkt_route = PACKET_MCBCQ; + else + plat->rx_queues_cfg[queue].pkt_route = 0x0; + queue++; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index b7d5e7ae9591..cd98ee232ad1 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -127,6 +127,7 @@ struct stmmac_axi { struct stmmac_rxq_cfg { u8 mode_to_use; u8 chan; + u8 pkt_route; bool use_prio; u32 prio; }; From 1f697ab109d60392f14c5e79eb6caf96805e68e9 Mon Sep 17 00:00:00 2001 From: Satanand Burla Date: Fri, 17 Mar 2017 10:50:05 -0700 Subject: [PATCH 390/399] liquidio: remove duplicate code Remove code duplicated in PF and VF; define that code once only in a common header file included by PF and VF. Signed-off-by: Satanand Burla Signed-off-by: Felix Manlunas Signed-off-by: David S. Miller --- .../net/ethernet/cavium/liquidio/lio_main.c | 36 ------------------- .../ethernet/cavium/liquidio/lio_vf_main.c | 36 ------------------- .../ethernet/cavium/liquidio/octeon_network.h | 36 +++++++++++++++++++ 3 files changed, 36 insertions(+), 72 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 761061b96948..b2d6478ffbd9 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -60,12 +60,6 @@ MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\""); static int ptp_enable = 1; -/* Bit mask values for lio->ifstate */ -#define LIO_IFSTATE_DROQ_OPS 0x01 -#define LIO_IFSTATE_REGISTERED 0x02 -#define LIO_IFSTATE_RUNNING 0x04 -#define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08 - /* Polling interval for determining when NIC application is alive */ #define LIQUIDIO_STARTER_POLL_INTERVAL_MS 100 @@ -530,36 +524,6 @@ static void liquidio_deinit_pci(void) pci_unregister_driver(&liquidio_pci_driver); } -/** - * \brief check interface state - * @param lio per-network private data - * @param state_flag flag state to check - */ -static inline int ifstate_check(struct lio *lio, int state_flag) -{ - return atomic_read(&lio->ifstate) & state_flag; -} - -/** - * \brief set interface state - * @param lio per-network private data - * @param state_flag flag state to set - */ -static inline void ifstate_set(struct lio *lio, int state_flag) -{ - atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag)); -} - -/** - * \brief clear interface state - * @param lio per-network private data - * @param state_flag flag state to clear - */ -static inline void ifstate_reset(struct lio *lio, int state_flag) -{ - atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag))); -} - /** * \brief Stop Tx queues * @param netdev network device diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 5ec5c24cee5d..f72db33fcd3a 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -39,12 +39,6 @@ MODULE_PARM_DESC(debug, "NETIF_MSG debug bits"); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) -/* Bit mask values for lio->ifstate */ -#define LIO_IFSTATE_DROQ_OPS 0x01 -#define LIO_IFSTATE_REGISTERED 0x02 -#define LIO_IFSTATE_RUNNING 0x04 -#define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08 - struct liquidio_if_cfg_context { int octeon_id; @@ -335,36 +329,6 @@ static struct pci_driver liquidio_vf_pci_driver = { .err_handler = &liquidio_vf_err_handler, /* For AER */ }; -/** - * \brief check interface state - * @param lio per-network private data - * @param state_flag flag state to check - */ -static int ifstate_check(struct lio *lio, int state_flag) -{ - return atomic_read(&lio->ifstate) & state_flag; -} - -/** - * \brief set interface state - * @param lio per-network private data - * @param state_flag flag state to set - */ -static void ifstate_set(struct lio *lio, int state_flag) -{ - atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag)); -} - -/** - * \brief clear interface state - * @param lio per-network private data - * @param state_flag flag state to clear - */ -static void ifstate_reset(struct lio *lio, int state_flag) -{ - atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag))); -} - /** * \brief Stop Tx queues * @param netdev network device diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index eef2a1e8a7e3..ddb61bf25775 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -28,6 +28,12 @@ #define LIO_MAX_MTU_SIZE (OCTNET_MAX_FRM_SIZE - OCTNET_FRM_HEADER_SIZE) #define LIO_MIN_MTU_SIZE ETH_MIN_MTU +/* Bit mask values for lio->ifstate */ +#define LIO_IFSTATE_DROQ_OPS 0x01 +#define LIO_IFSTATE_REGISTERED 0x02 +#define LIO_IFSTATE_RUNNING 0x04 +#define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08 + struct oct_nic_stats_resp { u64 rh; struct oct_link_stats stats; @@ -438,4 +444,34 @@ static inline void octeon_fast_packet_next(struct octeon_droq *droq, get_rbd(droq->recv_buf_list[idx].buffer), copy_len); } +/** + * \brief check interface state + * @param lio per-network private data + * @param state_flag flag state to check + */ +static inline int ifstate_check(struct lio *lio, int state_flag) +{ + return atomic_read(&lio->ifstate) & state_flag; +} + +/** + * \brief set interface state + * @param lio per-network private data + * @param state_flag flag state to set + */ +static inline void ifstate_set(struct lio *lio, int state_flag) +{ + atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag)); +} + +/** + * \brief clear interface state + * @param lio per-network private data + * @param state_flag flag state to clear + */ +static inline void ifstate_reset(struct lio *lio, int state_flag) +{ + atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag))); +} + #endif From c5b71e633da381c299990341ec88694bd00ecad1 Mon Sep 17 00:00:00 2001 From: Rick Farrington Date: Fri, 17 Mar 2017 11:23:08 -0700 Subject: [PATCH 391/399] liquidio: add debug error messages to report command timeout Add timeout error message in lio_process_ordered_list(). Add host failure status in existing error message in if_cfg_callback(). Signed-off-by: Rick Farrington Signed-off-by: Felix Manlunas Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_main.c | 4 ++-- drivers/net/ethernet/cavium/liquidio/response_manager.c | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index b2d6478ffbd9..afa173de1042 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2225,8 +2225,8 @@ static void if_cfg_callback(struct octeon_device *oct, oct = lio_get_device(ctx->octeon_id); if (resp->status) - dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n", - CVM_CAST64(resp->status)); + dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: 0x%llx (0x%08x)\n", + CVM_CAST64(resp->status), status); WRITE_ONCE(ctx->cond, 1); snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s", diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c index 1d987d7cd7bd..945633339723 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c @@ -107,6 +107,8 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev, } } else if (force_quit || (sc->timeout && time_after(jiffies, (unsigned long)sc->timeout))) { + dev_err(&octeon_dev->pci_dev->dev, "%s: cmd failed, timeout (%ld, %ld)\n", + __func__, (long)jiffies, (long)sc->timeout); status = OCTEON_REQUEST_TIMEOUT; } From e74bad6b015b732d8269a8ddfb303c9b33092722 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Fri, 17 Mar 2017 22:54:04 +0100 Subject: [PATCH 392/399] net: sun: sungem: rix a possible null dereference The function gem_begin_auto_negotiation dereference the pointer ep before testing if it's null. This patch add a check on ep before dereferencing it. Fixes: 92552fdda557 ("net: sun: sungem: use new api ethtool_{get|set}_link_ksettings") Reported-by: Dan Carpenter Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sungem.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index dbfca0466760..fa607d062cb3 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1259,8 +1259,9 @@ static void gem_begin_auto_negotiation(struct gem *gp, int duplex; u32 advertising; - ethtool_convert_link_mode_to_legacy_u32(&advertising, - ep->link_modes.advertising); + if (ep) + ethtool_convert_link_mode_to_legacy_u32( + &advertising, ep->link_modes.advertising); if (gp->phy_type != phy_mii_mdio0 && gp->phy_type != phy_mii_mdio1) From bd0b6723139416fd22acd5849b93edbd32d561f3 Mon Sep 17 00:00:00 2001 From: John Allen Date: Fri, 17 Mar 2017 17:13:40 -0500 Subject: [PATCH 393/399] ibmvnic: Move login and queue negotiation into ibmvnic_open VNIC server expects LINK_STATE_UP to be sent within 30s of the login. If we exceed the timeout, VNIC server will attempt to fail over. Since time between probe and open of the device is indeterminate, move login and queue negotiation into ibmvnic open so we can guarantee that login and sending LINK_STATE_UP occur within the 30s window. Signed-off-by: John Allen Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 88 +++++++++++++++--------------- 1 file changed, 43 insertions(+), 45 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5f11b4dc95d2..61d9d4045b4c 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -110,6 +110,9 @@ static int ibmvnic_poll(struct napi_struct *napi, int data); static void send_map_query(struct ibmvnic_adapter *adapter); static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8); static void send_request_unmap(struct ibmvnic_adapter *, u8); +static void send_login(struct ibmvnic_adapter *adapter); +static void send_cap_queries(struct ibmvnic_adapter *adapter); +static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -371,14 +374,51 @@ static void free_rx_pool(struct ibmvnic_adapter *adapter, static int ibmvnic_open(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); + unsigned long timeout = msecs_to_jiffies(30000); struct device *dev = &adapter->vdev->dev; struct ibmvnic_tx_pool *tx_pool; union ibmvnic_crq crq; int rxadd_subcrqs; u64 *size_array; int tx_subcrqs; + int rc = 0; int i, j; + do { + if (adapter->renegotiate) { + adapter->renegotiate = false; + release_sub_crqs_no_irqs(adapter); + + reinit_completion(&adapter->init_done); + send_cap_queries(adapter); + if (!wait_for_completion_timeout(&adapter->init_done, + timeout)) { + dev_err(dev, "Capabilities query timeout\n"); + return -1; + } + } + + reinit_completion(&adapter->init_done); + send_login(adapter); + if (!wait_for_completion_timeout(&adapter->init_done, + timeout)) { + dev_err(dev, "Login timeout\n"); + return -1; + } + } while (adapter->renegotiate); + + rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues); + if (rc) { + dev_err(dev, "failed to set the number of tx queues\n"); + return -1; + } + + rc = init_sub_crq_irqs(adapter); + if (rc) { + dev_err(dev, "failed to initialize sub crq irqs\n"); + return -1; + } + rxadd_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); tx_subcrqs = @@ -508,6 +548,7 @@ static int ibmvnic_open(struct net_device *netdev) for (i = 0; i < adapter->req_rx_queues; i++) napi_disable(&adapter->napi[i]); alloc_napi_failed: + release_sub_crqs(adapter); return -ENOMEM; } @@ -3419,8 +3460,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, dma_unmap_single(dev, adapter->ip_offload_ctrl_tok, sizeof(adapter->ip_offload_ctrl), DMA_TO_DEVICE); - /* We're done with the queries, perform the login */ - send_login(adapter); + complete(&adapter->init_done); break; case REQUEST_RAS_COMP_NUM_RSP: netdev_dbg(netdev, "Got Request RAS Comp Num Response\n"); @@ -3700,26 +3740,6 @@ static void handle_crq_init_rsp(struct work_struct *work) goto task_failed; } - do { - if (adapter->renegotiate) { - adapter->renegotiate = false; - release_sub_crqs_no_irqs(adapter); - - reinit_completion(&adapter->init_done); - send_cap_queries(adapter); - if (!wait_for_completion_timeout(&adapter->init_done, - timeout)) { - dev_err(dev, "Passive init timeout\n"); - goto task_failed; - } - } - } while (adapter->renegotiate); - rc = init_sub_crq_irqs(adapter); - - if (rc) - goto task_failed; - - netdev->real_num_tx_queues = adapter->req_tx_queues; netdev->mtu = adapter->req_mtu - ETH_HLEN; if (adapter->failover) { @@ -3840,39 +3860,17 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) return 0; - do { - if (adapter->renegotiate) { - adapter->renegotiate = false; - release_sub_crqs_no_irqs(adapter); - - reinit_completion(&adapter->init_done); - send_cap_queries(adapter); - if (!wait_for_completion_timeout(&adapter->init_done, - timeout)) - return 0; - } - } while (adapter->renegotiate); - - rc = init_sub_crq_irqs(adapter); - if (rc) { - dev_err(&dev->dev, "failed to initialize sub crq irqs\n"); - goto free_debugfs; - } - - netdev->real_num_tx_queues = adapter->req_tx_queues; netdev->mtu = adapter->req_mtu - ETH_HLEN; rc = register_netdev(netdev); if (rc) { dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); - goto free_sub_crqs; + goto free_debugfs; } dev_info(&dev->dev, "ibmvnic registered\n"); return 0; -free_sub_crqs: - release_sub_crqs(adapter); free_debugfs: if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) debugfs_remove_recursive(adapter->debugfs_dir); From a57a5d25a56bd9625722d17fecacf21cbe9818d8 Mon Sep 17 00:00:00 2001 From: John Allen Date: Fri, 17 Mar 2017 17:13:41 -0500 Subject: [PATCH 394/399] ibmvnic: Move login to its own routine Move the code that handles login and renegotiation of ibmvnic capabilities to its own routine. Signed-off-by: Nathan Fontenot Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 61d9d4045b4c..04f8feb0f2a3 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -371,18 +371,11 @@ static void free_rx_pool(struct ibmvnic_adapter *adapter, pool->rx_buff = NULL; } -static int ibmvnic_open(struct net_device *netdev) +static int ibmvnic_login(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); unsigned long timeout = msecs_to_jiffies(30000); struct device *dev = &adapter->vdev->dev; - struct ibmvnic_tx_pool *tx_pool; - union ibmvnic_crq crq; - int rxadd_subcrqs; - u64 *size_array; - int tx_subcrqs; - int rc = 0; - int i, j; do { if (adapter->renegotiate) { @@ -407,6 +400,25 @@ static int ibmvnic_open(struct net_device *netdev) } } while (adapter->renegotiate); + return 0; +} + +static int ibmvnic_open(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_tx_pool *tx_pool; + union ibmvnic_crq crq; + int rxadd_subcrqs; + u64 *size_array; + int tx_subcrqs; + int rc = 0; + int i, j; + + rc = ibmvnic_login(netdev); + if (rc) + return rc; + rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues); if (rc) { dev_err(dev, "failed to set the number of tx queues\n"); From f6ef6408e840f6e1a7c016d6dd1b4341bc1023f6 Mon Sep 17 00:00:00 2001 From: John Allen Date: Fri, 17 Mar 2017 17:13:42 -0500 Subject: [PATCH 395/399] ibmvnic: Move ibmvnic adapter intialization to its own routine The intialization of the ibmvnic driver with respect to the virtual server it connects to should be moved to its own routine. This will alolow the driver to initiate this process from places outside of the drivers probe routine. Signed-off-by: Nathan Fontenot Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 110 ++++++++++++++++------------- 1 file changed, 60 insertions(+), 50 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 04f8feb0f2a3..42274bf4bc09 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3783,14 +3783,65 @@ static void handle_crq_init_rsp(struct work_struct *work) dev_err(dev, "Passive initialization was not successful\n"); } +static int ibmvnic_init(struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + unsigned long timeout = msecs_to_jiffies(30000); + struct dentry *ent; + char buf[17]; /* debugfs name buf */ + int rc; + + rc = ibmvnic_init_crq_queue(adapter); + if (rc) { + dev_err(dev, "Couldn't initialize crq. rc=%d\n", rc); + return rc; + } + + adapter->stats_token = dma_map_single(dev, &adapter->stats, + sizeof(struct ibmvnic_statistics), + DMA_FROM_DEVICE); + if (dma_mapping_error(dev, adapter->stats_token)) { + ibmvnic_release_crq_queue(adapter); + dev_err(dev, "Couldn't map stats buffer\n"); + return -ENOMEM; + } + + snprintf(buf, sizeof(buf), "ibmvnic_%x", adapter->vdev->unit_address); + ent = debugfs_create_dir(buf, NULL); + if (!ent || IS_ERR(ent)) { + dev_info(dev, "debugfs create directory failed\n"); + adapter->debugfs_dir = NULL; + } else { + adapter->debugfs_dir = ent; + ent = debugfs_create_file("dump", S_IRUGO, + adapter->debugfs_dir, + adapter->netdev, &ibmvnic_dump_ops); + if (!ent || IS_ERR(ent)) { + dev_info(dev, "debugfs create dump file failed\n"); + adapter->debugfs_dump = NULL; + } else { + adapter->debugfs_dump = ent; + } + } + + init_completion(&adapter->init_done); + ibmvnic_send_crq_init(adapter); + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { + dev_err(dev, "Initialization sequence timed out\n"); + if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) + debugfs_remove_recursive(adapter->debugfs_dir); + ibmvnic_release_crq_queue(adapter); + return -1; + } + + return 0; +} + static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) { - unsigned long timeout = msecs_to_jiffies(30000); struct ibmvnic_adapter *adapter; struct net_device *netdev; unsigned char *mac_addr_p; - struct dentry *ent; - char buf[17]; /* debugfs name buf */ int rc; dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n", @@ -3828,69 +3879,28 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) spin_lock_init(&adapter->stats_lock); - rc = ibmvnic_init_crq_queue(adapter); - if (rc) { - dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n", rc); - goto free_netdev; - } - INIT_LIST_HEAD(&adapter->errors); INIT_LIST_HEAD(&adapter->inflight); spin_lock_init(&adapter->error_list_lock); spin_lock_init(&adapter->inflight_lock); - adapter->stats_token = dma_map_single(&dev->dev, &adapter->stats, - sizeof(struct ibmvnic_statistics), - DMA_FROM_DEVICE); - if (dma_mapping_error(&dev->dev, adapter->stats_token)) { - if (!firmware_has_feature(FW_FEATURE_CMO)) - dev_err(&dev->dev, "Couldn't map stats buffer\n"); - rc = -ENOMEM; - goto free_crq; + rc = ibmvnic_init(adapter); + if (rc) { + free_netdev(netdev); + return rc; } - snprintf(buf, sizeof(buf), "ibmvnic_%x", dev->unit_address); - ent = debugfs_create_dir(buf, NULL); - if (!ent || IS_ERR(ent)) { - dev_info(&dev->dev, "debugfs create directory failed\n"); - adapter->debugfs_dir = NULL; - } else { - adapter->debugfs_dir = ent; - ent = debugfs_create_file("dump", S_IRUGO, adapter->debugfs_dir, - netdev, &ibmvnic_dump_ops); - if (!ent || IS_ERR(ent)) { - dev_info(&dev->dev, - "debugfs create dump file failed\n"); - adapter->debugfs_dump = NULL; - } else { - adapter->debugfs_dump = ent; - } - } - - init_completion(&adapter->init_done); - ibmvnic_send_crq_init(adapter); - if (!wait_for_completion_timeout(&adapter->init_done, timeout)) - return 0; - netdev->mtu = adapter->req_mtu - ETH_HLEN; rc = register_netdev(netdev); if (rc) { dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); - goto free_debugfs; + free_netdev(netdev); + return rc; } dev_info(&dev->dev, "ibmvnic registered\n"); return 0; - -free_debugfs: - if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) - debugfs_remove_recursive(adapter->debugfs_dir); -free_crq: - ibmvnic_release_crq_queue(adapter); -free_netdev: - free_netdev(netdev); - return rc; } static int ibmvnic_remove(struct vio_dev *dev) From ea5509f53ce81662eb409c514086734d1ce16207 Mon Sep 17 00:00:00 2001 From: John Allen Date: Fri, 17 Mar 2017 17:13:43 -0500 Subject: [PATCH 396/399] ibmvnic: Correct ibmvnic handling of device open/close When closing the ibmvnic device we need to release the resources used in communicating to the virtual I/O server. These need to be re-negotiated with the server at open time. This patch moves the releasing of resources a separate routine and updates the open and close handlers to release all resources at close and re-negotiate and allocate these resources at open. Signed-off-by: Nathan Fontenot Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 118 +++++++++++++++++------------ drivers/net/ethernet/ibm/ibmvnic.h | 1 + 2 files changed, 69 insertions(+), 50 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 42274bf4bc09..30e1699649b8 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -113,6 +113,8 @@ static void send_request_unmap(struct ibmvnic_adapter *, u8); static void send_login(struct ibmvnic_adapter *adapter); static void send_cap_queries(struct ibmvnic_adapter *adapter); static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter); +static int ibmvnic_init(struct ibmvnic_adapter *); +static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -415,6 +417,12 @@ static int ibmvnic_open(struct net_device *netdev) int rc = 0; int i, j; + if (adapter->is_closed) { + rc = ibmvnic_init(adapter); + if (rc) + return rc; + } + rc = ibmvnic_login(netdev); if (rc) return rc; @@ -525,6 +533,7 @@ static int ibmvnic_open(struct net_device *netdev) ibmvnic_send_crq(adapter, &crq); netif_tx_start_all_queues(netdev); + adapter->is_closed = false; return 0; @@ -564,21 +573,12 @@ static int ibmvnic_open(struct net_device *netdev) return -ENOMEM; } -static int ibmvnic_close(struct net_device *netdev) +static void ibmvnic_release_resources(struct ibmvnic_adapter *adapter) { - struct ibmvnic_adapter *adapter = netdev_priv(netdev); struct device *dev = &adapter->vdev->dev; - union ibmvnic_crq crq; + int tx_scrqs, rx_scrqs; int i; - adapter->closing = true; - - for (i = 0; i < adapter->req_rx_queues; i++) - napi_disable(&adapter->napi[i]); - - if (!adapter->failover) - netif_tx_stop_all_queues(netdev); - if (adapter->bounce_buffer) { if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) { dma_unmap_single(&adapter->vdev->dev, @@ -591,33 +591,70 @@ static int ibmvnic_close(struct net_device *netdev) adapter->bounce_buffer = NULL; } + tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + for (i = 0; i < tx_scrqs; i++) { + struct ibmvnic_tx_pool *tx_pool = &adapter->tx_pool[i]; + + kfree(tx_pool->tx_buff); + free_long_term_buff(adapter, &tx_pool->long_term_buff); + kfree(tx_pool->free_map); + } + kfree(adapter->tx_pool); + adapter->tx_pool = NULL; + + rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + for (i = 0; i < rx_scrqs; i++) { + struct ibmvnic_rx_pool *rx_pool = &adapter->rx_pool[i]; + + free_rx_pool(adapter, rx_pool); + free_long_term_buff(adapter, &rx_pool->long_term_buff); + } + kfree(adapter->rx_pool); + adapter->rx_pool = NULL; + + release_sub_crqs(adapter); + ibmvnic_release_crq_queue(adapter); + + if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) + debugfs_remove_recursive(adapter->debugfs_dir); + + if (adapter->stats_token) + dma_unmap_single(dev, adapter->stats_token, + sizeof(struct ibmvnic_statistics), + DMA_FROM_DEVICE); + + if (adapter->ras_comps) + dma_free_coherent(dev, adapter->ras_comp_num * + sizeof(struct ibmvnic_fw_component), + adapter->ras_comps, adapter->ras_comps_tok); + + kfree(adapter->ras_comp_int); +} + +static int ibmvnic_close(struct net_device *netdev) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + union ibmvnic_crq crq; + int i; + + adapter->closing = true; + + for (i = 0; i < adapter->req_rx_queues; i++) + napi_disable(&adapter->napi[i]); + + if (!adapter->failover) + netif_tx_stop_all_queues(netdev); + memset(&crq, 0, sizeof(crq)); crq.logical_link_state.first = IBMVNIC_CRQ_CMD; crq.logical_link_state.cmd = LOGICAL_LINK_STATE; crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_DN; ibmvnic_send_crq(adapter, &crq); - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); - i++) { - kfree(adapter->tx_pool[i].tx_buff); - free_long_term_buff(adapter, - &adapter->tx_pool[i].long_term_buff); - kfree(adapter->tx_pool[i].free_map); - } - kfree(adapter->tx_pool); - adapter->tx_pool = NULL; - - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - i++) { - free_rx_pool(adapter, &adapter->rx_pool[i]); - free_long_term_buff(adapter, - &adapter->rx_pool[i].long_term_buff); - } - kfree(adapter->rx_pool); - adapter->rx_pool = NULL; + ibmvnic_release_resources(adapter); + adapter->is_closed = true; adapter->closing = false; - return 0; } @@ -3891,6 +3928,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) } netdev->mtu = adapter->req_mtu - ETH_HLEN; + adapter->is_closed = false; rc = register_netdev(netdev); if (rc) { @@ -3906,28 +3944,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) static int ibmvnic_remove(struct vio_dev *dev) { struct net_device *netdev = dev_get_drvdata(&dev->dev); - struct ibmvnic_adapter *adapter = netdev_priv(netdev); unregister_netdev(netdev); - - release_sub_crqs(adapter); - - ibmvnic_release_crq_queue(adapter); - - if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) - debugfs_remove_recursive(adapter->debugfs_dir); - - dma_unmap_single(&dev->dev, adapter->stats_token, - sizeof(struct ibmvnic_statistics), DMA_FROM_DEVICE); - - if (adapter->ras_comps) - dma_free_coherent(&dev->dev, - adapter->ras_comp_num * - sizeof(struct ibmvnic_fw_component), - adapter->ras_comps, adapter->ras_comps_tok); - - kfree(adapter->ras_comp_int); - free_netdev(netdev); dev_set_drvdata(&dev->dev, NULL); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 1993b42666f7..10ad259208cb 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1052,4 +1052,5 @@ struct ibmvnic_adapter { struct work_struct ibmvnic_xport; struct tasklet_struct tasklet; bool failover; + bool is_closed; }; From 71dbc3414caaf68d1914f63864b65d2a4d0bc39c Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Fri, 17 Mar 2017 23:34:04 +0100 Subject: [PATCH 397/399] net: usb: pegasus: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by: Philippe Reynes Acked-by: Petko Manolov Signed-off-by: David S. Miller --- drivers/net/usb/pegasus.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 36674484c6fb..321e059e13ae 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -953,20 +953,22 @@ static inline void pegasus_reset_wol(struct net_device *dev) } static int -pegasus_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) +pegasus_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *ecmd) { pegasus_t *pegasus; pegasus = netdev_priv(dev); - mii_ethtool_gset(&pegasus->mii, ecmd); + mii_ethtool_get_link_ksettings(&pegasus->mii, ecmd); return 0; } static int -pegasus_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) +pegasus_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *ecmd) { pegasus_t *pegasus = netdev_priv(dev); - return mii_ethtool_sset(&pegasus->mii, ecmd); + return mii_ethtool_set_link_ksettings(&pegasus->mii, ecmd); } static int pegasus_nway_reset(struct net_device *dev) @@ -995,14 +997,14 @@ static void pegasus_set_msglevel(struct net_device *dev, u32 v) static const struct ethtool_ops ops = { .get_drvinfo = pegasus_get_drvinfo, - .get_settings = pegasus_get_settings, - .set_settings = pegasus_set_settings, .nway_reset = pegasus_nway_reset, .get_link = pegasus_get_link, .get_msglevel = pegasus_get_msglevel, .set_msglevel = pegasus_set_msglevel, .get_wol = pegasus_get_wol, .set_wol = pegasus_set_wol, + .get_link_ksettings = pegasus_get_link_ksettings, + .set_link_ksettings = pegasus_set_link_ksettings, }; static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd) From 9549c6c872beee08ddb5bb92715bfde3b7161a88 Mon Sep 17 00:00:00 2001 From: Rick Farrington Date: Fri, 17 Mar 2017 15:43:26 -0700 Subject: [PATCH 398/399] liquidio: fix for vf mac addr command sent to nic firmware Change to support host<->firmware command return value. Fix for vf mac addr state command. 1. Added support for firmware commands to return a value: - previously, the returned code overlapped with host codes, thus commands were only returning 0 (success) or -1 (interpreted as timeout) - per 'response_manager.h', the error codes are split into two fields (major/minor) now, firmware commands are grouped into their own 'major' group, separate from the host's 'major' group, which allow f/w commands to return any 16-bit value 2. The command to set vf mac addr was logging a success message even if command failed. Now command uses a callback function to log the status message. 3. The command to set vf mac addr was not logging a message when set via the host 'ip' command. Now, the callback function will log an appropriate message. Signed-off-by: Rick Farrington Signed-off-by: Felix Manlunas Signed-off-by: Derek Chickles Signed-off-by: Satanand Burla Signed-off-by: David S. Miller --- .../net/ethernet/cavium/liquidio/lio_core.c | 19 ++++++++++++++----- .../net/ethernet/cavium/liquidio/lio_main.c | 3 ++- .../cavium/liquidio/response_manager.c | 11 +++++++++-- .../cavium/liquidio/response_manager.h | 5 +++++ 4 files changed, 30 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index f629c2fe04a4..65a1a9e7a159 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -131,11 +131,20 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr) case OCTNET_CMD_CHANGE_MACADDR: mac = ((u8 *)&nctrl->udd[0]) + 2; - netif_info(lio, probe, lio->netdev, - "MACAddr changed to %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x\n", - mac[0], mac[1], - mac[2], mac[3], - mac[4], mac[5]); + if (nctrl->ncmd.s.param1) { + /* vfidx is 0 based, but vf_num (param1) is 1 based */ + int vfidx = nctrl->ncmd.s.param1 - 1; + bool mac_is_admin_assigned = nctrl->ncmd.s.param2; + + if (mac_is_admin_assigned) + netif_info(lio, probe, lio->netdev, + "MAC Address %pM is configured for VF %d\n", + mac, vfidx); + } else { + netif_info(lio, probe, lio->netdev, + " MACAddr changed to %pM\n", + mac); + } break; case OCTNET_CMD_CHANGE_MTU: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index afa173de1042..b23485c3af13 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3619,7 +3619,8 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx, nctrl.ncmd.s.param2 = (is_admin_assigned ? 1 : 0); nctrl.ncmd.s.more = 1; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.cb_fn = 0; + nctrl.netpndev = (u64)netdev; + nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; nctrl.wait_time = LIO_CMD_WAIT_TM; nctrl.udd[0] = 0; diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c index 945633339723..3d691c69f74d 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c @@ -101,8 +101,15 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev, if ((status64 & 0xff) != 0xff) { octeon_swap_8B_data(&status64, 1); if (((status64 & 0xff) != 0xff)) { - status = (u32)(status64 & - 0xffffffffULL); + /* retrieve 16-bit firmware status */ + status = (u32)(status64 & 0xffffULL); + if (status) { + status = + FIRMWARE_STATUS_CODE(status); + } else { + /* i.e. no error */ + status = OCTEON_REQUEST_DONE; + } } } } else if (force_quit || (sc->timeout && diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h index cbb2d84e8932..9169c2815dba 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.h +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h @@ -78,6 +78,8 @@ enum { /*------------ Error codes used by host driver -----------------*/ #define DRIVER_MAJOR_ERROR_CODE 0x0000 +/*------ Error codes used by firmware (bits 15..0 set by firmware */ +#define FIRMWARE_MAJOR_ERROR_CODE 0x0001 /** A value of 0x00000000 indicates no error i.e. success */ #define DRIVER_ERROR_NONE 0x00000000 @@ -116,6 +118,9 @@ enum { }; +#define FIRMWARE_STATUS_CODE(status) \ + ((FIRMWARE_MAJOR_ERROR_CODE << 16) | (status)) + /** Initialize the response lists. The number of response lists to create is * given by count. * @param octeon_dev - the octeon device structure. From f9fe1c12d126f9887441fa5bb165046f30ddd4b5 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sat, 18 Mar 2017 00:36:15 +0100 Subject: [PATCH 399/399] rhashtable: Add rhashtable_lookup_get_insert_fast Add rhashtable_lookup_get_insert_fast for fixed keys, similar to rhashtable_lookup_get_insert_key for explicit keys. Signed-off-by: Andreas Gruenbacher Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 092292b6675e..e507290cd2c7 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -915,6 +915,28 @@ static inline int rhashtable_lookup_insert_fast( return ret == NULL ? 0 : -EEXIST; } +/** + * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Just like rhashtable_lookup_insert_fast(), but this function returns the + * object if it exists, NULL if it did not and the insertion was successful, + * and an ERR_PTR otherwise. + */ +static inline void *rhashtable_lookup_get_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + const char *key = rht_obj(ht, obj); + + BUG_ON(ht->p.obj_hashfn); + + return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, + false); +} + /** * rhashtable_lookup_insert_key - search and insert object to hash table * with explicit key