From 764dcebb033764633700a036c7351a7c6350eec6 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 9 Sep 2026 23:31:23 +0000 Subject: [PATCH 1/4] neighbour: Add missing RCU annotation for neightbl_dump_info(). neightbl_dump_info() fetches the first non-default neigh_parms with list_next_entry(&tbl->parms, ...) and iterates through the list with list_for_each_entry_from_rcu(). However, list_next_entry() does not use RCU helper. Let's use list_for_each_entry_rcu() and skip the default parms. Fixes: 4ae34be50064 ("neighbour: Convert RTM_GETNEIGHTBL to RCU.") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260909233143.2401847-2-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/core/neighbour.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 1349c0eedb64..49dd7df149ef 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2611,11 +2611,14 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) break; nidx = 0; - p = list_next_entry(&tbl->parms, list); - list_for_each_entry_from_rcu(p, &tbl->parms_list, list) { + + list_for_each_entry_rcu(p, &tbl->parms_list, list) { if (!net_eq(neigh_parms_net(p), net)) continue; + if (!p->dev) + continue; + if (nidx < neigh_skip) goto next; From 6d79b223ec44ada58ad37db42f539b60985a7722 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 9 Sep 2026 23:31:24 +0000 Subject: [PATCH 2/4] neighbour: Enforce min/max to NDTPA_INTERVAL_PROBE_TIME_MS. NDTPA_INTERVAL_PROBE_TIME_MS sets .type and .min but misses .validation_type, so no validation is applied: # ynl --family rt-neigh --do setneightbl \ --json '{"name": "arp_cache", "parms": {"interval-probe-time-ms": 0}}' # ynl --family rt-neigh --dump getneightbl --output-json | \ jq '.[] | select(.name == "arp_cache" and has("config")) | .parms["interval-probe-time-ms"]' 0 Moreover, nla_get_msecs() uses msecs_to_jiffies(), and u64 is silently cast to u32, so a larger value can bypass the min check: e.g. 4294967296 == 0x100000000 # ynl --family rt-neigh --do setneightbl \ --json '{"name": "arp_cache", "parms": {"interval-probe-time-ms": 4294967296}}' # ynl --family rt-neigh --dump getneightbl --output-json | \ jq '.[] | select(.name == "arp_cache" and has("config")) | .parms["interval-probe-time-ms"]' 0 msecs_to_jiffies() returns MAX_JIFFY_OFFSET if the value is larger than INT_MAX. Also, INT_MAX ms overflows int NEIGH_VAR() when HZ > 1000 (Alpha, MIPS), and passing a negative integer to queue_delayed_work(unsigned long delay) causes sign extension, which wraps around the expiry time to the past, resulting in it being handled as 0 delay in the timer wheel. Let's use NLA_POLICY_FULL_RANGE() and limit the max to 1 day. The same max check is applied to sysctl as well. Note that this controls the probe interval for NTF_MANAGED entries, so the max of 1 day is unlikely to break any deployments. Fixes: 211da42eaa45 ("net, neigh: introduce interval_probe_time_ms for periodic probe") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260909233143.2401847-3-kuniyu@google.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/rt-neigh.yaml | 3 +++ Documentation/networking/ip-sysctl.rst | 2 +- net/core/neighbour.c | 17 +++++++++++++---- 3 files changed, 17 insertions(+), 5 deletions(-) diff --git a/Documentation/netlink/specs/rt-neigh.yaml b/Documentation/netlink/specs/rt-neigh.yaml index 0f46ef313590..c8e55c98d564 100644 --- a/Documentation/netlink/specs/rt-neigh.yaml +++ b/Documentation/netlink/specs/rt-neigh.yaml @@ -341,6 +341,9 @@ attribute-sets: - name: interval-probe-time-ms type: u64 + checks: + min: 1 + max: 86400000 operations: enum-model: directional diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 208f46967ee5..b05829e44d8f 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -248,7 +248,7 @@ neigh/default/unres_qlen - INTEGER neigh/default/interval_probe_time_ms - INTEGER The probe interval for neighbor entries with NTF_MANAGED flag, - the min value is 1. + the min value is 1, and the max value is 86400000 (1 day). Default: 5000 diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 49dd7df149ef..0db78a0dfb51 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2359,6 +2359,13 @@ static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = { [NDTA_PARMS] = { .type = NLA_NESTED }, }; +#define NTBL_PARM_MS_MAX (24 * 60 * 60 * MSEC_PER_SEC) + +static const struct netlink_range_validation nl_ntbl_parm_ms_range = { + .min = 1, + .max = NTBL_PARM_MS_MAX, +}; + static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_IFINDEX] = { .type = NLA_U32 }, [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, @@ -2375,7 +2382,8 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, [NDTPA_LOCKTIME] = { .type = NLA_U64 }, - [NDTPA_INTERVAL_PROBE_TIME_MS] = { .type = NLA_U64, .min = 1 }, + [NDTPA_INTERVAL_PROBE_TIME_MS] = NLA_POLICY_FULL_RANGE(NLA_U64, + &nl_ntbl_parm_ms_range), }; static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -3672,12 +3680,13 @@ static int neigh_proc_dointvec_ms_jiffies_positive(const struct ctl_table *ctl, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp = *ctl; - int ret; + int ret, min, max; - int min = msecs_to_jiffies(1); + min = msecs_to_jiffies(1); + max = msecs_to_jiffies(NTBL_PARM_MS_MAX); tmp.extra1 = &min; - tmp.extra2 = NULL; + tmp.extra2 = &max; ret = proc_dointvec_ms_jiffies_minmax(&tmp, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); From 7b430fcfc972f61b09cc19ca95997586af4a147d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 9 Sep 2026 23:31:25 +0000 Subject: [PATCH 3/4] neighbour: Don't render blackhole_netdev via RTM_GETNEIGHTBL. The cited commits started to initialise blackhole_netdev with neigh_parms_alloc(). This is visible in init_net as the ifindex==0 entries via RTM_GETNEIGHTBL: # ynl --family rt-neigh --dump getneightbl --output-json \ | jq '.[] | select(.parms.ifindex == 0) | {name: .name, ifindex: .parms.ifindex}' { "name": "arp_cache", "ifindex": 0 } { "name": "ndisc_cache", "ifindex": 0 } For RTM_SETNEIGHTBL, ifindex being 0 means wildcard. Let's skip blackhole_netdev's parms in neightbl_dump_info(). Note that lookup_neigh_parms() does not need the same change because the default parms is always the first entry and matches with ifindex == 0. Fixes: e5f80fcf869a ("ipv6: give an IPv6 dev to blackhole_netdev") Fixes: 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260909233143.2401847-4-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/core/neighbour.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0db78a0dfb51..02bf940ce00a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2624,7 +2624,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (!net_eq(neigh_parms_net(p), net)) continue; - if (!p->dev) + if (!p->dev || p->dev == blackhole_netdev) continue; if (nidx < neigh_skip) From 979aabdad8dd03394467ee484a1a70f3d40b19ba Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 9 Sep 2026 23:31:26 +0000 Subject: [PATCH 4/4] neighbour: Skip default parms when resumed in neightbl_dump_info(). neightbl_dump_info() calls neightbl_fill_info() in each loop to render the default parms. If there are many devices and neightbl_fill_param_info() failed, neightbl_fill_info() is called again when the dump resumes: # ynl --family rt-neigh --dump getneightbl --output-json | jq '.[] | {name: .name, ifindex: .parms.ifindex}' ... { "name": "ndisc_cache", "ifindex": null } ... { "name": "ndisc_cache", "ifindex": 6 } { "name": "ndisc_cache", "ifindex": null } { "name": "ndisc_cache", "ifindex": 5 } Let's skip neightbl_fill_info() if it is already called in neightbl_dump_info(). Note that we cannot use !neigh_skip instead of !default_skip because default_skip == 1 && neigh_skip == 0 could be true if the first neightbl_fill_param_info() fails. Also, nidx must be cleared at the end of each table loop; otherwise, if neightbl_fill_info() for a subsequent table fails, the leftover nidx from the previous table would be saved in cb->args[1], resulting in erroneously skipping parms of the subsequent table in the next dump. Fixes: c7fb64db001f ("[NETLINK]: Neighbour table configuration and statistics via rtnetlink") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260909233143.2401847-5-kuniyu@google.com Signed-off-by: Jakub Kicinski --- net/core/neighbour.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 02bf940ce00a..7448320f7ad5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2587,9 +2587,10 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); + int default_skip = cb->args[2]; + int neigh_skip = cb->args[1]; int family, tidx, nidx = 0; int tbl_skip = cb->args[0]; - int neigh_skip = cb->args[1]; struct neigh_table *tbl; if (cb->strict_check) { @@ -2613,12 +2614,13 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, + if (!default_skip && + neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) < 0) break; - nidx = 0; + default_skip = 1; list_for_each_entry_rcu(p, &tbl->parms_list, list) { if (!net_eq(neigh_parms_net(p), net)) @@ -2641,12 +2643,15 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) } neigh_skip = 0; + nidx = 0; + default_skip = 0; } out: rcu_read_unlock(); cb->args[0] = tidx; cb->args[1] = nidx; + cb->args[2] = default_skip; return skb->len; }