From 0483a16bc493075bb9f6483497786fed41d27b94 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Wed, 22 Feb 2023 10:29:44 +0800 Subject: [PATCH 1/7] net/mlx5: Remove NULL check before dev_{put, hold} MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The call netdev_{put, hold} of dev_{put, hold} will check NULL, so there is no need to check before using dev_{put, hold}, remove it to silence the warning： ./drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c:714:2-9: WARNING: NULL check before dev_{put, hold} functions is not needed. Reported-by: Abaci Robot Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=4174 Signed-off-by: Yang Li Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index e24b46953542..8f7452dc00ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -710,8 +710,7 @@ void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, else napi_gro_receive(rq->cq.napi, skb); - if (tc_priv.fwd_dev) - dev_put(tc_priv.fwd_dev); + dev_put(tc_priv.fwd_dev); return; From bfeda9683dcd697dc84bbd5ce375f659e9590bf5 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 17 Feb 2023 11:13:01 +0800 Subject: [PATCH 2/7] net/mlx5e: TC, fix return value check in mlx5e_tc_act_stats_create() kvzalloc() returns NULL pointer not PTR_ERR() when it fails, so replace the IS_ERR() check with NULL pointer check. Fixes: d13674b1d14c ("net/mlx5e: TC, map tc action cookie to a hw counter") Signed-off-by: Yang Yingliang Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c index f71766dca660..626cb7470fa5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c @@ -37,7 +37,7 @@ mlx5e_tc_act_stats_create(void) int err; handle = kvzalloc(sizeof(*handle), GFP_KERNEL); - if (IS_ERR(handle)) + if (!handle) return ERR_PTR(-ENOMEM); err = rhashtable_init(&handle->ht, &act_counters_ht_params); From e435941b1da1a0be4ff8a7ae425774c76a5ac514 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Thu, 2 Feb 2023 09:13:54 -0800 Subject: [PATCH 3/7] mlx5: fix skb leak while fifo resync and push During ptp resync operation SKBs were poped from the fifo but were never freed neither by napi_consume nor by dev_kfree_skb_any. Add call to napi_consume_skb to properly free SKBs. Another leak was happening because mlx5e_skb_fifo_has_room() had an error in the check. Comparing free running counters works well unless C promotes the types to something wider than the counter. In this case counters are u16 but the result of the substraction is promouted to int and it causes wrong result (negative value) of the check when producer have already overlapped but consumer haven't yet. Explicit cast to u16 fixes the issue. Fixes: 58a518948f60 ("net/mlx5e: Add resiliency for PTP TX port timestamp") Reviewed-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Vadim Fedorenko Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c | 6 ++++-- drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 9a1bc93b7dc6..392db8d5e9c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -86,7 +86,8 @@ static bool mlx5e_ptp_ts_cqe_drop(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb return (ptpsq->ts_cqe_ctr_mask && (skb_cc != skb_id)); } -static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb_id) +static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, + u16 skb_id, int budget) { struct skb_shared_hwtstamps hwts = {}; struct sk_buff *skb; @@ -98,6 +99,7 @@ static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_ hwts.hwtstamp = mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp; skb_tstamp_tx(skb, &hwts); ptpsq->cq_stats->resync_cqe++; + napi_consume_skb(skb, budget); skb_cc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc); } } @@ -119,7 +121,7 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, } if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id)) - mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id); + mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id, budget); skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo); hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index c067d2efab51..2c10adbf1849 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -86,7 +86,7 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq); static inline bool mlx5e_skb_fifo_has_room(struct mlx5e_skb_fifo *fifo) { - return (*fifo->pc - *fifo->cc) < fifo->mask; + return (u16)(*fifo->pc - *fifo->cc) < fifo->mask; } static inline bool From 3a50cf1e8e5157b82268eee7e330dbe5736a0948 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Thu, 2 Feb 2023 09:13:55 -0800 Subject: [PATCH 4/7] mlx5: fix possible ptp queue fifo use-after-free Fifo indexes are not checked during pop operations and it leads to potential use-after-free when poping from empty queue. Such case was possible during re-sync action. WARN_ON_ONCE covers future cases. There were out-of-order cqe spotted which lead to drain of the queue and use-after-free because of lack of fifo pointers check. Special check and counter are added to avoid resync operation if SKB could not exist in the fifo because of OOO cqe (skb_id must be between consumer and producer index). Fixes: 58a518948f60 ("net/mlx5e: Add resiliency for PTP TX port timestamp") Signed-off-by: Vadim Fedorenko Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/ptp.c | 19 ++++++++++++++++++- .../net/ethernet/mellanox/mlx5/core/en/txrx.h | 2 ++ .../ethernet/mellanox/mlx5/core/en_stats.c | 1 + .../ethernet/mellanox/mlx5/core/en_stats.h | 1 + 4 files changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 392db8d5e9c7..eb5aeba3addf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -86,6 +86,17 @@ static bool mlx5e_ptp_ts_cqe_drop(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb return (ptpsq->ts_cqe_ctr_mask && (skb_cc != skb_id)); } +static bool mlx5e_ptp_ts_cqe_ooo(struct mlx5e_ptpsq *ptpsq, u16 skb_id) +{ + u16 skb_cc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc); + u16 skb_pc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_pc); + + if (PTP_WQE_CTR2IDX(skb_id - skb_cc) >= PTP_WQE_CTR2IDX(skb_pc - skb_cc)) + return true; + + return false; +} + static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb_id, int budget) { @@ -120,8 +131,14 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, goto out; } - if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id)) + if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id)) { + if (mlx5e_ptp_ts_cqe_ooo(ptpsq, skb_id)) { + /* already handled by a previous resync */ + ptpsq->cq_stats->ooo_cqe_drop++; + return; + } mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id, budget); + } skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo); hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 2c10adbf1849..b9c2f67d3794 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -302,6 +302,8 @@ void mlx5e_skb_fifo_push(struct mlx5e_skb_fifo *fifo, struct sk_buff *skb) static inline struct sk_buff *mlx5e_skb_fifo_pop(struct mlx5e_skb_fifo *fifo) { + WARN_ON_ONCE(*fifo->pc == *fifo->cc); + return *mlx5e_skb_fifo_get(fifo, (*fifo->cc)++); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 6687b8136e44..4478223c1720 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -2138,6 +2138,7 @@ static const struct counter_desc ptp_cq_stats_desc[] = { { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) }, { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_cqe) }, { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_event) }, + { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, ooo_cqe_drop) }, }; static const struct counter_desc ptp_rq_stats_desc[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 375752d6546d..b77100b60b50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -461,6 +461,7 @@ struct mlx5e_ptp_cq_stats { u64 abort_abs_diff_ns; u64 resync_cqe; u64 resync_event; + u64 ooo_cqe_drop; }; struct mlx5e_rep_stats { From e1ed30c8c09abc85a01c897845bdbd08c0333353 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Wed, 15 Feb 2023 20:12:05 +0200 Subject: [PATCH 5/7] net/mlx5: ECPF, wait for VF pages only after disabling host PFs Currently, during the early stages of their unloading, particularly during SRIOV disablement, PFs/ECPFs wait on the release of all of their VFs memory pages. Furthermore, ECPFs are considered the page supplier for host VFs, hence the host VFs memory pages are freed only during ECPF cleanup when host interfaces get disabled. Thus, disabling SRIOV early in unload timeline causes the DPU ECPF to stall on driver unload while waiting on the release of host VF pages that won't be freed before host interfaces get disabled later on. Therefore, for ECPFs, wait on the release of VFs pages only after the disablement of host PFs during ECPF cleanup flow. Then, host PFs and VFs are disabled and their memory shall be freed accordingly. Fixes: 143a41d7623d ("net/mlx5: Disable SRIOV before PF removal") Signed-off-by: Maher Sanalla Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/ecpf.c | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 9a3878f9e582..7c9c4e40c019 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -98,4 +98,8 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); if (err) mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err); + + err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF]); + if (err) + mlx5_core_warn(dev, "Timeout reclaiming external host VFs pages err(%d)\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 3008e9ce2bbf..20d7662c10fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,6 +147,10 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf); + /* For ECPFs, skip waiting for host VF pages until ECPF is destroyed */ + if (mlx5_core_is_ecpf(dev)) + return; + if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } From 1bf8b0dae8dde6f02520a5ea34fdaa3b39342e69 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Tue, 31 Jan 2023 12:04:30 +0200 Subject: [PATCH 6/7] net/mlx5e: Verify flow_source cap before using it When adding send to vport rule verify flow_source matching is supported by checking the flow_source cap. Fixes: d04442540372 ("net/mlx5: E-Switch, set flow source for send to uplink rule") Signed-off-by: Roi Dayan Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 2a98375a0abf..d766a64b1823 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -869,7 +869,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - if (rep->vport == MLX5_VPORT_UPLINK) + if (MLX5_CAP_ESW_FLOWTABLE(on_esw->dev, flow_source) && + rep->vport == MLX5_VPORT_UPLINK) spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(on_esw), From d28a06d7dbedc598a06bd1e53a28125f87ca5d0c Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Wed, 8 Feb 2023 17:44:06 +0200 Subject: [PATCH 7/7] net/mlx5: Geneve, Fix handling of Geneve object id as error code On success, mlx5_geneve_tlv_option_create returns non negative Geneve object id. In case the object id is positive value the caller functions will handle it as an error (non zero) and will fail to offload the Geneve rule. Fix this by changing caller function ,mlx5_geneve_tlv_option_add, to return 0 in case valid non negative object id was provided. Fixes: 0ccc171ea6a2 ("net/mlx5: Geneve, Manage Geneve TLV options") Signed-off-by: Maor Dickman Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c index 23361a9ae4fa..6dc83e871cd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c @@ -105,6 +105,7 @@ int mlx5_geneve_tlv_option_add(struct mlx5_geneve *geneve, struct geneve_opt *op geneve->opt_type = opt->type; geneve->obj_id = res; geneve->refcount++; + res = 0; } unlock: