kmod-redhat-mlx5_core/SOURCES/0030-netdrv-net-mlx5e-Report-and-recover-from-CQE-error-o.patch

From beae62dd1772b395964f8e73f82c202f1ad346d9 Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <ahleihel@redhat.com>
Date: Sun, 10 May 2020 14:51:54 -0400
Subject: [PATCH 030/312] [netdrv] net/mlx5e: Report and recover from CQE error
 on ICOSQ

Message-id: <20200510145245.10054-32-ahleihel@redhat.com>
Patchwork-id: 306571
Patchwork-instance: patchwork
O-Subject: [RHEL8.3 BZ 1789378 v2 31/82] net/mlx5e: Report and recover from CQE error on ICOSQ
Bugzilla: 1790198 1789378
RH-Acked-by: Kamal Heib <kheib@redhat.com>
RH-Acked-by: Jarod Wilson <jarod@redhat.com>
RH-Acked-by: Tony Camuso <tcamuso@redhat.com>
RH-Acked-by: Jonathan Toppins <jtoppins@redhat.com>

Bugzilla: http://bugzilla.redhat.com/1789378
Bugzilla: http://bugzilla.redhat.com/1790198
Upstream: v5.4-rc1
Conflicts:
 - drivers/net/ethernet/mellanox/mlx5/core/en_main.c
 - drivers/net/ethernet/mellanox/mlx5/core/en.h
   Dropped hunks that were previously applied for fixing incremental build.

 - drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
   Adapt mlx5e_rx_reporter_recover parameters to current API due to already
   backported commit:
   e7a981050a7f ("devlink: propagate extack down to health reporter ops")
   ---> .recover callback now expects to get extact as well.

commit be5323c8379f488f1de53206edeaf80fc20d7686
Author: Aya Levin <ayal@mellanox.com>
Date:   Tue Jun 25 17:44:28 2019 +0300

    net/mlx5e: Report and recover from CQE error on ICOSQ

    Add support for report and recovery from error on completion on ICOSQ.
    Deactivate RQ and flush, then deactivate ICOSQ. Set the queue back to
    ready state (firmware) and reset the ICOSQ and the RQ (software
    resources). Finally, activate the ICOSQ and the RQ.

    Signed-off-by: Aya Levin <ayal@mellanox.com>
    Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
    Acked-by: Jiri Pirko <jiri@mellanox.com>
    Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Signed-off-by: Alaa Hleihel <ahleihel@redhat.com>
Signed-off-by: Frantisek Hrbata <fhrbata@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   6 ++
 .../net/ethernet/mellanox/mlx5/core/en/health.h    |   1 +
 .../ethernet/mellanox/mlx5/core/en/reporter_rx.c   | 110 ++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  18 +++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |   2 +
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |   2 +
 7 files changed, 137 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 21926cb209f9..f0ba350579ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -559,6 +559,8 @@ struct mlx5e_icosq {
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
 	struct mlx5e_channel      *channel;
+
+	struct work_struct         recover_work;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_wqe_frag_info {
@@ -1037,6 +1039,10 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params);
+int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
+void mlx5e_activate_rq(struct mlx5e_rq *rq);
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 void mlx5e_activate_icosq(struct mlx5e_icosq *icosq);
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index a751c5316baf..8acd9dc520cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -18,6 +18,7 @@ int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg);
 
 int mlx5e_reporter_rx_create(struct mlx5e_priv *priv);
 void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv);
+void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq);
 
 #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 7cd767f0b8c7..661de567ca6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -27,6 +27,110 @@ static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state)
 	return err;
 }
 
+static int mlx5e_wait_for_icosq_flush(struct mlx5e_icosq *icosq)
+{
+	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+
+	while (time_before(jiffies, exp_time)) {
+		if (icosq->cc == icosq->pc)
+			return 0;
+
+		msleep(20);
+	}
+
+	netdev_err(icosq->channel->netdev,
+		   "Wait for ICOSQ 0x%x flush timeout (cc = 0x%x, pc = 0x%x)\n",
+		   icosq->sqn, icosq->cc, icosq->pc);
+
+	return -ETIMEDOUT;
+}
+
+static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq)
+{
+	WARN_ONCE(icosq->cc != icosq->pc, "ICOSQ 0x%x: cc (0x%x) != pc (0x%x)\n",
+		  icosq->sqn, icosq->cc, icosq->pc);
+	icosq->cc = 0;
+	icosq->pc = 0;
+}
+
+static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
+{
+	struct mlx5_core_dev *mdev;
+	struct mlx5e_icosq *icosq;
+	struct net_device *dev;
+	struct mlx5e_rq *rq;
+	u8 state;
+	int err;
+
+	icosq = ctx;
+	rq = &icosq->channel->rq;
+	mdev = icosq->channel->mdev;
+	dev = icosq->channel->netdev;
+	err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state);
+	if (err) {
+		netdev_err(dev, "Failed to query ICOSQ 0x%x state. err = %d\n",
+			   icosq->sqn, err);
+		goto out;
+	}
+
+	if (state != MLX5_SQC_STATE_ERR)
+		goto out;
+
+	mlx5e_deactivate_rq(rq);
+	err = mlx5e_wait_for_icosq_flush(icosq);
+	if (err)
+		goto out;
+
+	mlx5e_deactivate_icosq(icosq);
+
+	/* At this point, both the rq and the icosq are disabled */
+
+	err = mlx5e_health_sq_to_ready(icosq->channel, icosq->sqn);
+	if (err)
+		goto out;
+
+	mlx5e_reset_icosq_cc_pc(icosq);
+	mlx5e_free_rx_descs(rq);
+	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+	mlx5e_activate_icosq(icosq);
+	mlx5e_activate_rq(rq);
+
+	rq->stats->recover++;
+	return 0;
+out:
+	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+	return err;
+}
+
+void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq)
+{
+	struct mlx5e_priv *priv = icosq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx = {};
+
+	err_ctx.ctx = icosq;
+	err_ctx.recover = mlx5e_rx_reporter_err_icosq_cqe_recover;
+	sprintf(err_str, "ERR CQE on ICOSQ: 0x%x", icosq->sqn);
+
+	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
+}
+
+static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
+{
+	return err_ctx->recover(err_ctx->ctx);
+}
+
+static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter,
+				     void *context,
+				     struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	struct mlx5e_err_ctx *err_ctx = context;
+
+	return err_ctx ? mlx5e_rx_reporter_recover_from_ctx(err_ctx) :
+			 mlx5e_health_recover_channels(priv);
+}
+
 static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq,
 						   struct devlink_fmsg *fmsg)
 {
@@ -168,9 +272,12 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
 
 static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = {
 	.name = "rx",
+	.recover = mlx5e_rx_reporter_recover,
 	.diagnose = mlx5e_rx_reporter_diagnose,
 };
 
+#define MLX5E_REPORTER_RX_GRACEFUL_PERIOD 500
+
 int mlx5e_reporter_rx_create(struct mlx5e_priv *priv)
 {
 	struct devlink *devlink = priv_to_devlink(priv->mdev);
@@ -178,7 +285,8 @@ int mlx5e_reporter_rx_create(struct mlx5e_priv *priv)
 
 	reporter = devlink_health_reporter_create(devlink,
 						  &mlx5_rx_reporter_ops,
-						  0, false, priv);
+						  MLX5E_REPORTER_RX_GRACEFUL_PERIOD,
+						  true, priv);
 	if (IS_ERR(reporter)) {
 		netdev_warn(priv->netdev, "Failed to create rx reporter, err = %ld\n",
 			    PTR_ERR(reporter));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7dde1be49f35..430fb04ea96f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -691,8 +691,7 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq,
 	return err;
 }
 
-static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
-				 int next_state)
+int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
 
@@ -803,7 +802,7 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 	return -ETIMEDOUT;
 }
 
-static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 {
 	__be16 wqe_ix_be;
 	u16 wqe_ix;
@@ -882,7 +881,7 @@ int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	return err;
 }
 
-static void mlx5e_activate_rq(struct mlx5e_rq *rq)
+void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	mlx5e_trigger_irq(&rq->channel->icosq);
@@ -897,6 +896,7 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
 	cancel_work_sync(&rq->dim.work);
+	cancel_work_sync(&rq->channel->icosq.recover_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
 	mlx5e_free_rq(rq);
@@ -1013,6 +1013,14 @@ static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 	return 0;
 }
 
+static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+					      recover_work);
+
+	mlx5e_reporter_icosq_cqe_err(sq);
+}
+
 static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 			     struct mlx5e_sq_param *param,
 			     struct mlx5e_icosq *sq)
@@ -1035,6 +1043,8 @@ 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);
+
 	return 0;
 
 err_sq_wq_destroy:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index a22b3a3db253..ce4d357188df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -616,6 +616,8 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
 			netdev_WARN_ONCE(cq->channel->netdev,
 					 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
+			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+				queue_work(cq->channel->priv->wq, &sq->recover_work);
 			break;
 		}
 		do {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 3d993e2e7bea..79b3ec005f43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -161,6 +161,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
@@ -272,6 +273,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 		s->rx_cache_waive += rq_stats->cache_waive;
 		s->rx_congst_umr  += rq_stats->congst_umr;
 		s->rx_arfs_err    += rq_stats->arfs_err;
+		s->rx_recover     += rq_stats->recover;
 		s->ch_events      += ch_stats->events;
 		s->ch_poll        += ch_stats->poll;
 		s->ch_arm         += ch_stats->arm;
@@ -1484,6 +1486,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
 };
 
 static const struct counter_desc sq_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 a4a43613d026..ab1c3366ff7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -167,6 +167,7 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_waive;
 	u64 rx_congst_umr;
 	u64 rx_arfs_err;
+	u64 rx_recover;
 	u64 ch_events;
 	u64 ch_poll;
 	u64 ch_arm;
@@ -302,6 +303,7 @@ struct mlx5e_rq_stats {
 	u64 cache_waive;
 	u64 congst_umr;
 	u64 arfs_err;
+	u64 recover;
 };
 
 struct mlx5e_sq_stats {
-- 
2.13.6