From 6b8b42585886c59a008015083282aae434349094 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Wed, 22 Dec 2021 06:54:53 +0000 Subject: [PATCH 01/12] net/mlx5: DR, Fix NULL vs IS_ERR checking in dr_domain_init_resources The mlx5_get_uars_page() function returns error pointers. Using IS_ERR() to check the return value to fix this. Fixes: 4ec9e7b02697 ("net/mlx5: DR, Expose steering domain functionality") Signed-off-by: Miaoqian Lin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 8cbd36c82b3b..f6e6d9209766 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include +#include #include "dr_types.h" #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type) \ @@ -72,9 +73,9 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn) } dmn->uar = mlx5_get_uars_page(dmn->mdev); - if (!dmn->uar) { + if (IS_ERR(dmn->uar)) { mlx5dr_err(dmn, "Couldn't allocate UAR\n"); - ret = -ENOMEM; + ret = PTR_ERR(dmn->uar); goto clean_pd; } From 624bf42c2e3930acca9fcfc340b2fa38e712da84 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Sun, 12 Dec 2021 16:19:58 +0200 Subject: [PATCH 02/12] net/mlx5: DR, Fix querying eswitch manager vport for ECPF On BlueField the E-Switch manager is the ECPF (vport 0xFFFE), but when querying capabilities of ECPF eswitch manager, need to query vport 0 with other_vport = 0. Fixes: 9091b821aaa4 ("net/mlx5: DR, Handle eswitch manager and uplink vports separately") Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index f6e6d9209766..c54cc45f63dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -164,9 +164,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn, static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn) { - return dr_domain_query_vport(dmn, - dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0, - false, + return dr_domain_query_vport(dmn, 0, false, &dmn->info.caps.vports.esw_manager_caps); } From 26a7993c93a74a3fee83a37b46e00e69e49e57c2 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 26 Oct 2021 08:25:19 +0300 Subject: [PATCH 03/12] net/mlx5: Use first online CPU instead of hard coded CPU Hard coded CPU (0 in our case) might be offline. Hence, use the first online CPU instead. Fixes: f891b7cdbdcd ("net/mlx5: Enable single IRQ for PCI Function") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 830444f927d4..0e84c005d160 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -398,7 +398,7 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx, cpumask_copy(irq->mask, affinity); if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max && cpumask_empty(irq->mask)) - cpumask_set_cpu(0, irq->mask); + cpumask_set_cpu(cpumask_first(cpu_online_mask), irq->mask); irq_set_affinity_hint(irq->irqn, irq->mask); unlock: mutex_unlock(&pool->lock); From aa968f922039706f6d13e8870b49e424d0a8d9ad Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 24 Nov 2021 23:10:57 +0200 Subject: [PATCH 04/12] net/mlx5: Fix error print in case of IRQ request failed In case IRQ layer failed to find or to request irq, the driver is printing the first cpu of the provided affinity as part of the error print. Empty affinity is a valid input for the IRQ layer, and it is an error to call cpumask_first() on empty affinity. Remove the first cpu print from the error message. Fixes: c36326d38d93 ("net/mlx5: Round-Robin EQs over IRQs") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 0e84c005d160..bcee30f5de0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -356,8 +356,8 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool, new_irq = irq_pool_create_irq(pool, affinity); if (IS_ERR(new_irq)) { if (!least_loaded_irq) { - mlx5_core_err(pool->dev, "Didn't find IRQ for cpu = %u\n", - cpumask_first(affinity)); + mlx5_core_err(pool->dev, "Didn't find a matching IRQ. err = %ld\n", + PTR_ERR(new_irq)); mutex_unlock(&pool->lock); return new_irq; } From 33de865f7bce3968676e43b0182af0a2dd359dae Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Tue, 23 Nov 2021 20:08:13 +0200 Subject: [PATCH 05/12] net/mlx5: Fix SF health recovery flow SF do not directly control the PCI device. During recovery flow SF should not be allowed to do pci disable or pci reset, its PF will do it. It fixes the following kernel trace: mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:387:(pid 40948): starting health recovery flow mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called mlx5_core 0000:03:00.0: wait vital counter value 0xab175 after 1 iterations mlx5_core.sf mlx5_core.sf.25: firmware version: 24.32.532 mlx5_core.sf mlx5_core.sf.23: mlx5_health_try_recover:387:(pid 40946): starting health recovery flow mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called mlx5_core 0000:03:00.0: wait vital counter value 0xab193 after 1 iterations mlx5_core.sf mlx5_core.sf.23: firmware version: 24.32.532 mlx5_core.sf mlx5_core.sf.25: mlx5_cmd_check:813:(pid 40948): ENABLE_HCA(0x104) op_mod(0x0) failed, status bad resource state(0x9), syndrome (0x658908) mlx5_core.sf mlx5_core.sf.25: mlx5_function_setup:1292:(pid 40948): enable hca failed mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:389:(pid 40948): health recovery failed Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver") Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 7df9c7f8d9c8..65083496f913 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1809,12 +1809,13 @@ void mlx5_disable_device(struct mlx5_core_dev *dev) int mlx5_recover_device(struct mlx5_core_dev *dev) { - int ret = -EIO; + if (!mlx5_core_is_sf(dev)) { + mlx5_pci_disable_device(dev); + if (mlx5_pci_slot_reset(dev->pdev) != PCI_ERS_RESULT_RECOVERED) + return -EIO; + } - mlx5_pci_disable_device(dev); - if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED) - ret = mlx5_load_one(dev); - return ret; + return mlx5_load_one(dev); } static struct pci_driver mlx5_core_driver = { From d671e109bd8548d067b27e39e183a484430bf102 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Tue, 14 Dec 2021 03:52:53 +0200 Subject: [PATCH 06/12] net/mlx5: Fix tc max supported prio for nic mode Only prio 1 is supported if firmware doesn't support ignore flow level for nic mode. The offending commit removed the check wrongly. Add it back. Fixes: 9a99c8f1253a ("net/mlx5e: E-Switch, Offload all chain 0 priorities when modify header and forward action is not supported") Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index 97e5845b4cfd..d5e47630e284 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -121,6 +121,9 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains) u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains) { + if (!mlx5_chains_prios_supported(chains)) + return 1; + if (mlx5_chains_ignore_flow_level_supported(chains)) return UINT_MAX; From 918fc3855a6507a200e9cf22c20be852c0982687 Mon Sep 17 00:00:00 2001 From: Amir Tzin Date: Tue, 30 Nov 2021 16:05:44 +0200 Subject: [PATCH 07/12] net/mlx5e: Wrap the tx reporter dump callback to extract the sq Function mlx5e_tx_reporter_dump_sq() casts its void * argument to struct mlx5e_txqsq *, but in TX-timeout-recovery flow the argument is actually of type struct mlx5e_tx_timeout_ctx *. mlx5_core 0000:08:00.1 enp8s0f1: TX timeout detected mlx5_core 0000:08:00.1 enp8s0f1: TX timeout on queue: 1, SQ: 0x11ec, CQ: 0x146d, SQ Cons: 0x0 SQ Prod: 0x1, usecs since last trans: 21565000 BUG: stack guard page was hit at 0000000093f1a2de (stack is 00000000b66ea0dc..000000004d932dae) kernel stack overflow (page fault): 0000 [#1] SMP NOPTI CPU: 5 PID: 95 Comm: kworker/u20:1 Tainted: G W OE 5.13.0_mlnx #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core] RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180 [mlx5_core] Call Trace: mlx5e_tx_reporter_dump+0x43/0x1c0 [mlx5_core] devlink_health_do_dump.part.91+0x71/0xd0 devlink_health_report+0x157/0x1b0 mlx5e_reporter_tx_timeout+0xb9/0xf0 [mlx5_core] ? mlx5e_tx_reporter_err_cqe_recover+0x1d0/0x1d0 [mlx5_core] ? mlx5e_health_queue_dump+0xd0/0xd0 [mlx5_core] ? update_load_avg+0x19b/0x550 ? set_next_entity+0x72/0x80 ? pick_next_task_fair+0x227/0x340 ? finish_task_switch+0xa2/0x280 mlx5e_tx_timeout_work+0x83/0xb0 [mlx5_core] process_one_work+0x1de/0x3a0 worker_thread+0x2d/0x3c0 ? process_one_work+0x3a0/0x3a0 kthread+0x115/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x1f/0x30 --[ end trace 51ccabea504edaff ]--- RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180 PKRU: 55555554 Kernel panic - not syncing: Fatal exception Kernel Offset: disabled end Kernel panic - not syncing: Fatal exception To fix this bug add a wrapper for mlx5e_tx_reporter_dump_sq() which extracts the sq from struct mlx5e_tx_timeout_ctx and set it as the TX-timeout-recovery flow dump callback. Fixes: 5f29458b77d5 ("net/mlx5e: Support dump callback in TX reporter") Signed-off-by: Aya Levin Signed-off-by: Amir Tzin Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 4f4bc8726ec4..614cd9477600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -466,6 +466,14 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms return mlx5e_health_fmsg_named_obj_nest_end(fmsg); } +static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + void *ctx) +{ + struct mlx5e_tx_timeout_ctx *to_ctx = ctx; + + return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq); +} + static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg) { @@ -561,7 +569,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) to_ctx.sq = sq; err_ctx.ctx = &to_ctx; err_ctx.recover = mlx5e_tx_reporter_timeout_recover; - err_ctx.dump = mlx5e_tx_reporter_dump_sq; + err_ctx.dump = mlx5e_tx_reporter_timeout_dump; snprintf(err_str, sizeof(err_str), "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u", sq->ch_ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, From a0cb909644c36230a3c48904d14b91732de79fc0 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 13 Dec 2021 11:05:11 +0200 Subject: [PATCH 08/12] net/mlx5e: Fix skb memory leak when TC classifier action offloads are disabled When TC classifier action offloads are disabled (CONFIG_MLX5_CLS_ACT in Kconfig), the mlx5e_rep_tc_receive() function which is responsible for passing the skb to the stack (or freeing it) is defined as a nop, and results in leaking the skb memory. Replace the nop with a call to napi_gro_receive() to resolve the leak. Fixes: 28e7606fa8f1 ("net/mlx5e: Refactor rx handler of represetor device") Signed-off-by: Gal Pressman Reviewed-by: Ariel Levkovich Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h index d6c7c81690eb..7c9dd3a75f8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h @@ -66,7 +66,7 @@ mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, static inline void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, - struct sk_buff *skb) {} + struct sk_buff *skb) { napi_gro_receive(rq->cq.napi, skb); } #endif /* CONFIG_MLX5_CLS_ACT */ From 17958d7cd731b977ae7d4af38d891c3a1235b5f1 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 12 Oct 2021 19:40:09 +0300 Subject: [PATCH 09/12] net/mlx5e: Fix interoperability between XSK and ICOSQ recovery flow Both regular RQ and XSKRQ use the same ICOSQ for UMRs. When doing recovery for the ICOSQ, don't forget to deactivate XSKRQ. XSK can be opened and closed while channels are active, so a new mutex prevents the ICOSQ recovery from running at the same time. The ICOSQ recovery deactivates and reactivates XSKRQ, so any parallel change in XSK state would break consistency. As the regular RQ is running, it's not enough to just flush the recovery work, because it can be rescheduled. Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 ++ .../ethernet/mellanox/mlx5/core/en/health.h | 2 ++ .../mellanox/mlx5/core/en/reporter_rx.c | 35 ++++++++++++++++++- .../mellanox/mlx5/core/en/xsk/setup.c | 16 ++++++++- .../net/ethernet/mellanox/mlx5/core/en_main.c | 7 ++-- 5 files changed, 58 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index f0ac6b0d9653..f42067adc79d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -783,6 +783,8 @@ struct mlx5e_channel { DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; int cpu; + /* Sync between icosq recovery and XSK enable/disable. */ + struct mutex icosq_recovery_lock; }; struct mlx5e_ptp; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index d5b7110a4265..0107e4e73bb0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -30,6 +30,8 @@ void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv); void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq); void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq); void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq); +void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c); +void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c); #define MLX5E_REPORTER_PER_Q_MAX_LEN 256 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 74086eb556ae..2684e9da9f41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -62,6 +62,7 @@ static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq) static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx) { + struct mlx5e_rq *xskrq = NULL; struct mlx5_core_dev *mdev; struct mlx5e_icosq *icosq; struct net_device *dev; @@ -70,7 +71,13 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx) int err; icosq = ctx; + + mutex_lock(&icosq->channel->icosq_recovery_lock); + + /* mlx5e_close_rq cancels this work before RQ and ICOSQ are killed. */ rq = &icosq->channel->rq; + if (test_bit(MLX5E_RQ_STATE_ENABLED, &icosq->channel->xskrq.state)) + xskrq = &icosq->channel->xskrq; mdev = icosq->channel->mdev; dev = icosq->channel->netdev; err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state); @@ -84,6 +91,9 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx) goto out; mlx5e_deactivate_rq(rq); + if (xskrq) + mlx5e_deactivate_rq(xskrq); + err = mlx5e_wait_for_icosq_flush(icosq); if (err) goto out; @@ -97,15 +107,28 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx) goto out; mlx5e_reset_icosq_cc_pc(icosq); + mlx5e_free_rx_in_progress_descs(rq); + if (xskrq) + mlx5e_free_rx_in_progress_descs(xskrq); + clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state); mlx5e_activate_icosq(icosq); - mlx5e_activate_rq(rq); + mlx5e_activate_rq(rq); rq->stats->recover++; + + if (xskrq) { + mlx5e_activate_rq(xskrq); + xskrq->stats->recover++; + } + + mutex_unlock(&icosq->channel->icosq_recovery_lock); + return 0; out: clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state); + mutex_unlock(&icosq->channel->icosq_recovery_lock); return err; } @@ -706,6 +729,16 @@ void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq) mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); } +void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c) +{ + mutex_lock(&c->icosq_recovery_lock); +} + +void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c) +{ + mutex_unlock(&c->icosq_recovery_lock); +} + static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = { .name = "rx", .recover = mlx5e_rx_reporter_recover, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 538bc2419bd8..8526a5fbbf0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -4,6 +4,7 @@ #include "setup.h" #include "en/params.h" #include "en/txrx.h" +#include "en/health.h" /* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may * change unexpectedly, and mlx5e has a minimum valid stride size for striding @@ -170,7 +171,13 @@ void mlx5e_close_xsk(struct mlx5e_channel *c) void mlx5e_activate_xsk(struct mlx5e_channel *c) { + /* ICOSQ recovery deactivates RQs. Suspend the recovery to avoid + * activating XSKRQ in the middle of recovery. + */ + mlx5e_reporter_icosq_suspend_recovery(c); set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); + mlx5e_reporter_icosq_resume_recovery(c); + /* TX queue is created active. */ spin_lock_bh(&c->async_icosq_lock); @@ -180,6 +187,13 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c) void mlx5e_deactivate_xsk(struct mlx5e_channel *c) { - mlx5e_deactivate_rq(&c->xskrq); + /* ICOSQ recovery may reactivate XSKRQ if clear_bit is called in the + * middle of recovery. Suspend the recovery to avoid it. + */ + mlx5e_reporter_icosq_suspend_recovery(c); + clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); + mlx5e_reporter_icosq_resume_recovery(c); + synchronize_net(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */ + /* TX queue is disabled on close. */ } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 65571593ec5c..a572fc9690ed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1087,8 +1087,6 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq) void mlx5e_close_rq(struct mlx5e_rq *rq) { cancel_work_sync(&rq->dim.work); - if (rq->icosq) - cancel_work_sync(&rq->icosq->recover_work); cancel_work_sync(&rq->recover_work); mlx5e_destroy_rq(rq); mlx5e_free_rx_descs(rq); @@ -2088,6 +2086,8 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, if (err) goto err_close_xdpsq_cq; + mutex_init(&c->icosq_recovery_lock); + err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq); if (err) goto err_close_async_icosq; @@ -2156,9 +2156,12 @@ static void mlx5e_close_queues(struct mlx5e_channel *c) mlx5e_close_xdpsq(&c->xdpsq); if (c->xdp) mlx5e_close_xdpsq(&c->rq_xdpsq); + /* The same ICOSQ is used for UMRs for both RQ and XSKRQ. */ + cancel_work_sync(&c->icosq.recover_work); mlx5e_close_rq(&c->rq); mlx5e_close_sqs(c); mlx5e_close_icosq(&c->icosq); + mutex_destroy(&c->icosq_recovery_lock); mlx5e_close_icosq(&c->async_icosq); if (c->xdp) mlx5e_close_cq(&c->rq_xdpsq.cq); From 19c4aba2d4e23997061fb11aed8a3e41334bfa14 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 22 Jul 2020 16:32:44 +0300 Subject: [PATCH 10/12] net/mlx5e: Fix ICOSQ recovery flow for XSK There are two ICOSQs per channel: one is needed for RX, and the other for async operations (XSK TX, kTLS offload). Currently, the recovery flow for both is the same, and async ICOSQ is mistakenly treated like the regular ICOSQ. This patch prevents running the regular ICOSQ recovery on async ICOSQ. The purpose of async ICOSQ is to handle XSK wakeup requests and post kTLS offload RX parameters, it has nothing to do with RQ and XSKRQ UMRs, so the regular recovery sequence is not applicable here. Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 -- .../net/ethernet/mellanox/mlx5/core/en_main.c | 30 ++++++++++++++----- 2 files changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index f42067adc79d..b47a0d3ef22f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1016,9 +1016,6 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param); void mlx5e_destroy_rq(struct mlx5e_rq *rq); struct mlx5e_sq_param; -int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct mlx5e_sq_param *param, struct mlx5e_icosq *sq); -void mlx5e_close_icosq(struct mlx5e_icosq *sq); int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool, struct mlx5e_xdpsq *sq, bool is_redirect); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a572fc9690ed..3b0f3a831216 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1214,9 +1214,20 @@ static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work) mlx5e_reporter_icosq_cqe_err(sq); } +static void mlx5e_async_icosq_err_cqe_work(struct work_struct *recover_work) +{ + struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq, + recover_work); + + /* Not implemented yet. */ + + netdev_warn(sq->channel->netdev, "async_icosq recovery is not implemented\n"); +} + static int mlx5e_alloc_icosq(struct mlx5e_channel *c, struct mlx5e_sq_param *param, - struct mlx5e_icosq *sq) + struct mlx5e_icosq *sq, + work_func_t recover_work_func) { void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq); struct mlx5_core_dev *mdev = c->mdev; @@ -1237,7 +1248,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, if (err) goto err_sq_wq_destroy; - INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work); + INIT_WORK(&sq->recover_work, recover_work_func); return 0; @@ -1573,13 +1584,14 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) mlx5e_reporter_tx_err_cqe(sq); } -int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct mlx5e_sq_param *param, struct mlx5e_icosq *sq) +static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_sq_param *param, struct mlx5e_icosq *sq, + work_func_t recover_work_func) { struct mlx5e_create_sq_param csp = {}; int err; - err = mlx5e_alloc_icosq(c, param, sq); + err = mlx5e_alloc_icosq(c, param, sq, recover_work_func); if (err) return err; @@ -1618,7 +1630,7 @@ void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq) synchronize_net(); /* Sync with NAPI. */ } -void mlx5e_close_icosq(struct mlx5e_icosq *sq) +static void mlx5e_close_icosq(struct mlx5e_icosq *sq) { struct mlx5e_channel *c = sq->channel; @@ -2082,13 +2094,15 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, spin_lock_init(&c->async_icosq_lock); - err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq); + err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq, + mlx5e_async_icosq_err_cqe_work); if (err) goto err_close_xdpsq_cq; mutex_init(&c->icosq_recovery_lock); - err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq); + err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq, + mlx5e_icosq_err_cqe_work); if (err) goto err_close_async_icosq; From 2820110d945923ab2f4901753e4ccbb2a506fa8e Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Thu, 2 Dec 2021 11:18:02 +0800 Subject: [PATCH 11/12] net/mlx5e: Delete forward rule for ct or sample action When there is ct or sample action, the ct or sample rule will be deleted and return. But if there is an extra mirror action, the forward rule can't be deleted because of the return. Fix it by removing the return. Fixes: 69e2916ebce4 ("net/mlx5: CT: Add support for mirroring") Fixes: f94d6389f6a8 ("net/mlx5e: TC, Add support to offload sample action") Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3d45f4ae80c0..f633448c3cc7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1196,21 +1196,16 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) goto offload_rule_0; - if (flow_flag_test(flow, CT)) { - mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); - return; - } - - if (flow_flag_test(flow, SAMPLE)) { - mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); - return; - } - if (attr->esw_attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); + if (flow_flag_test(flow, CT)) + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); + else if (flow_flag_test(flow, SAMPLE)) + mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); + else offload_rule_0: - mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); + mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); } struct mlx5_flow_handle * From 4390c6edc0fb390e699d0f886f45575dfeafeb4b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 6 Nov 2021 18:08:11 +0100 Subject: [PATCH 12/12] net/mlx5: Fix some error handling paths in 'mlx5e_tc_add_fdb_flow()' All the error handling paths of 'mlx5e_tc_add_fdb_flow()' end to 'err_out' where 'flow_flag_set(flow, FAILED);' is called. All but the new error handling paths added by the commits given in the Fixes tag below. Fix these error handling paths and branch to 'err_out'. Fixes: 166f431ec6be ("net/mlx5e: Add indirect tc offload of ovs internal port") Fixes: b16eb3c81fe2 ("net/mlx5: Support internal port as decap route device") Signed-off-by: Christophe JAILLET Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed (cherry picked from commit 31108d142f3632970f6f3e0224bd1c6781c9f87d) --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f633448c3cc7..a60c7680fd2b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1440,7 +1440,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, MLX5_FLOW_NAMESPACE_FDB, VPORT_TO_REG, metadata); if (err) - return err; + goto err_out; } } @@ -1456,13 +1456,15 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (attr->chain) { NL_SET_ERR_MSG_MOD(extack, "Internal port rule is only supported on chain 0"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_out; } if (attr->dest_chain) { NL_SET_ERR_MSG_MOD(extack, "Internal port rule offload doesn't support goto action"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_out; } int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv), @@ -1470,8 +1472,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, flow_flag_test(flow, EGRESS) ? MLX5E_TC_INT_PORT_EGRESS : MLX5E_TC_INT_PORT_INGRESS); - if (IS_ERR(int_port)) - return PTR_ERR(int_port); + if (IS_ERR(int_port)) { + err = PTR_ERR(int_port); + goto err_out; + } esw_attr->int_port = int_port; }