All of lore.kernel.org
 help / color / mirror / Atom feed
From: Saeed Mahameed <saeedm@mellanox.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	Aya Levin <ayal@mellanox.com>, Tariq Toukan <tariqt@mellanox.com>,
	Jiri Pirko <jiri@mellanox.com>,
	Saeed Mahameed <saeedm@mellanox.com>
Subject: [net-next v2 03/16] net/mlx5e: Generalize tx reporter's functionality
Date: Tue, 20 Aug 2019 20:24:16 +0000	[thread overview]
Message-ID: <20190820202352.2995-4-saeedm@mellanox.com> (raw)
In-Reply-To: <20190820202352.2995-1-saeedm@mellanox.com>

From: Aya Levin <ayal@mellanox.com>

Prepare for code sharing with rx reporter, which is added in the
following patches in the set. Introduce a generic error_ctx for
agnostic recovery despatch.

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>
---
 .../net/ethernet/mellanox/mlx5/core/Makefile  |   5 +-
 .../ethernet/mellanox/mlx5/core/en/health.c   |  82 ++++++++++
 .../ethernet/mellanox/mlx5/core/en/health.h   |  14 ++
 .../mellanox/mlx5/core/en/reporter_tx.c       | 140 +++++-------------
 4 files changed, 137 insertions(+), 104 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/health.c

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 57d2cc666fe3..23d566a45a30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -23,8 +23,9 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 #
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \
-		en/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o
+		en_selftest.o en/port.o en/monitor_stats.o en/health.o \
+		en/reporter_tx.o en/params.o en/xsk/umem.o en/xsk/setup.o \
+		en/xsk/rx.o en/xsk/tx.o
 
 #
 # Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
new file mode 100644
index 000000000000..fc3112921bd3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include "health.h"
+#include "lib/eq.h"
+
+int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn)
+{
+	struct mlx5_core_dev *mdev = channel->mdev;
+	struct net_device *dev = channel->netdev;
+	struct mlx5e_modify_sq_param msp = {};
+	int err;
+
+	msp.curr_state = MLX5_SQC_STATE_ERR;
+	msp.next_state = MLX5_SQC_STATE_RST;
+
+	err = mlx5e_modify_sq(mdev, sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sqn);
+		return err;
+	}
+
+	memset(&msp, 0, sizeof(msp));
+	msp.curr_state = MLX5_SQC_STATE_RST;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+
+	err = mlx5e_modify_sq(mdev, sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sqn);
+		return err;
+	}
+
+	return 0;
+}
+
+int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
+{
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
+	err = mlx5e_safe_reopen_channels(priv);
+
+out:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+
+	return err;
+}
+
+int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel)
+{
+	u32 eqe_count;
+
+	netdev_err(channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
+		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
+
+	eqe_count = mlx5_eq_poll_irq_disabled(eq);
+	if (!eqe_count)
+		return -EIO;
+
+	netdev_err(channel->netdev, "Recovered %d eqes on EQ 0x%x\n",
+		   eqe_count, eq->core.eqn);
+
+	channel->stats->eq_rearm++;
+	return 0;
+}
+
+int mlx5e_health_report(struct mlx5e_priv *priv,
+			struct devlink_health_reporter *reporter, char *err_str,
+			struct mlx5e_err_ctx *err_ctx)
+{
+	if (!reporter) {
+		netdev_err(priv->netdev, err_str);
+		return err_ctx->recover(&err_ctx->ctx);
+	}
+	return devlink_health_report(reporter, err_str, err_ctx);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index c7a5a149011e..386bda6104aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -11,4 +11,18 @@ void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv);
 void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
 int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq);
 
+#define MLX5E_REPORTER_PER_Q_MAX_LEN 256
+
+struct mlx5e_err_ctx {
+	int (*recover)(void *ctx);
+	void *ctx;
+};
+
+int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn);
+int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel);
+int mlx5e_health_recover_channels(struct mlx5e_priv *priv);
+int mlx5e_health_report(struct mlx5e_priv *priv,
+			struct devlink_health_reporter *reporter, char *err_str,
+			struct mlx5e_err_ctx *err_ctx);
+
 #endif
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 62b95f62e4dc..6f9f42ab3005 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -2,14 +2,6 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include "health.h"
-#include "lib/eq.h"
-
-#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256
-
-struct mlx5e_tx_err_ctx {
-	int (*recover)(struct mlx5e_txqsq *sq);
-	struct mlx5e_txqsq *sq;
-};
 
 static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
 {
@@ -39,41 +31,20 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
 	sq->pc = 0;
 }
 
-static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
+static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 {
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	struct mlx5e_modify_sq_param msp = {0};
+	struct mlx5_core_dev *mdev;
+	struct net_device *dev;
+	struct mlx5e_txqsq *sq;
+	u8 state;
 	int err;
 
-	msp.curr_state = curr_state;
-	msp.next_state = MLX5_SQC_STATE_RST;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
-		return err;
-	}
-
-	memset(&msp, 0, sizeof(msp));
-	msp.curr_state = MLX5_SQC_STATE_RST;
-	msp.next_state = MLX5_SQC_STATE_RDY;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
-		return err;
-	}
-
-	return 0;
-}
+	sq = ctx;
+	mdev = sq->channel->mdev;
+	dev = sq->channel->netdev;
 
-static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
-{
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	u8 state;
-	int err;
+	if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+		return 0;
 
 	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
 	if (err) {
@@ -96,7 +67,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
 	 * pending WQEs. SQ can safely reset the SQ.
 	 */
 
-	err = mlx5e_sq_to_ready(sq, state);
+	err = mlx5e_health_sq_to_ready(sq->channel, sq->sqn);
 	if (err)
 		goto out;
 
@@ -111,102 +82,66 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
 	return err;
 }
 
-static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
-				 char *err_str,
-				 struct mlx5e_tx_err_ctx *err_ctx)
-{
-	if (!tx_reporter) {
-		netdev_err(err_ctx->sq->channel->netdev, err_str);
-		return err_ctx->recover(err_ctx->sq);
-	}
-
-	return devlink_health_report(tx_reporter, err_str, err_ctx);
-}
-
 void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq)
 {
-	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
-	struct mlx5e_tx_err_ctx err_ctx = {0};
+	struct mlx5e_priv *priv = sq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx = {0};
 
-	err_ctx.sq       = sq;
-	err_ctx.recover  = mlx5e_tx_reporter_err_cqe_recover;
+	err_ctx.ctx = sq;
+	err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover;
 	sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn);
 
-	mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
-			      &err_ctx);
+	mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx);
 }
 
-static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
+static int mlx5e_tx_reporter_timeout_recover(void *ctx)
 {
-	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
-	u32 eqe_count;
-
-	netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
+	struct mlx5_eq_comp *eq;
+	struct mlx5e_txqsq *sq;
+	int err;
 
-	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	if (!eqe_count) {
+	sq = ctx;
+	eq = sq->cq.mcq.eq;
+	err = mlx5e_health_channel_eq_recover(eq, sq->channel);
+	if (err)
 		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-		return -EIO;
-	}
 
-	netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n",
-		   eqe_count, eq->core.eqn);
-	sq->channel->stats->eq_rearm++;
-	return 0;
+	return err;
 }
 
 int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
 {
-	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
-	struct mlx5e_tx_err_ctx err_ctx;
+	struct mlx5e_priv *priv = sq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx;
 
-	err_ctx.sq       = sq;
-	err_ctx.recover  = mlx5e_tx_reporter_timeout_recover;
+	err_ctx.ctx = sq;
+	err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
 	sprintf(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\n",
 		sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
 		jiffies_to_usecs(jiffies - sq->txq->trans_start));
 
-	return mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
-				     &err_ctx);
+	return mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx);
 }
 
 /* state lock cannot be grabbed within this function.
  * It can cause a dead lock or a read-after-free.
  */
-static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
-{
-	return err_ctx->recover(err_ctx->sq);
-}
-
-static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
+static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
 {
-	int err = 0;
-
-	rtnl_lock();
-	mutex_lock(&priv->state_lock);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto out;
-
-	err = mlx5e_safe_reopen_channels(priv);
-
-out:
-	mutex_unlock(&priv->state_lock);
-	rtnl_unlock();
-
-	return err;
+	return err_ctx->recover(err_ctx->ctx);
 }
 
 static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
 				     void *context)
 {
 	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
-	struct mlx5e_tx_err_ctx *err_ctx = context;
+	struct mlx5e_err_ctx *err_ctx = context;
 
 	return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) :
-			 mlx5e_tx_reporter_recover_all(priv);
+			 mlx5e_health_recover_channels(priv);
 }
 
 static int
@@ -289,8 +224,9 @@ int mlx5e_reporter_tx_create(struct mlx5e_priv *priv)
 {
 	struct devlink_health_reporter *reporter;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct devlink *devlink = priv_to_devlink(mdev);
+	struct devlink *devlink;
 
+	devlink = priv_to_devlink(mdev);
 	reporter =
 		devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
 					       MLX5_REPORTER_TX_GRACEFUL_PERIOD,
-- 
2.21.0


  parent reply	other threads:[~2019-08-20 20:26 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-20 20:24 [pull request][net-next v2 00/16] Mellanox, mlx5 devlink RX health reporters Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 01/16] net/mlx5e: Rename reporter header file Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 02/16] net/mlx5e: Change naming convention for reporter's functions Saeed Mahameed
2019-08-20 20:24 ` Saeed Mahameed [this message]
2019-08-20 20:24 ` [net-next v2 04/16] net/mlx5e: Extend tx diagnose function Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 05/16] net/mlx5e: Extend tx reporter diagnostics output Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 06/16] net/mlx5e: Add cq info to tx reporter diagnose Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 07/16] net/mlx5e: Add helper functions for reporter's basics Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 08/16] net/mlx5e: Add support to rx reporter diagnose Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 09/16] net/mlx5e: Split open/close ICOSQ into stages Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 10/16] net/mlx5e: Report and recover from CQE error on ICOSQ Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 11/16] net/mlx5e: Report and recover from rx timeout Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 12/16] net/mlx5e: RX, Handle CQE with error at the earliest stage Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 13/16] net/mlx5e: Report and recover from CQE with error on RQ Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 14/16] Documentation: net: mlx5: Devlink health documentation updates Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 15/16] net/mlx5e: Fix deallocation of non-fully init encap entries Saeed Mahameed
2019-08-20 20:24 ` [net-next v2 16/16] net/mlx5: Fix the order of fc_stats cleanup Saeed Mahameed
2019-08-21  3:36 ` [pull request][net-next v2 00/16] Mellanox, mlx5 devlink RX health reporters Jakub Kicinski
2019-08-21  6:36 ` David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190820202352.2995-4-saeedm@mellanox.com \
    --to=saeedm@mellanox.com \
    --cc=ayal@mellanox.com \
    --cc=davem@davemloft.net \
    --cc=jiri@mellanox.com \
    --cc=netdev@vger.kernel.org \
    --cc=tariqt@mellanox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.