diff mbox series

[net-next,v2,8/9] net/mlx5: Lock mlx5 devlink health recovery callback

Message ID 1659023630-32006-9-git-send-email-moshe@nvidia.com (mailing list archive)
State Accepted
Commit d3dbdc9f8ddce46ae2646b2257106d8cdb3d5887
Delegated to: Netdev Maintainers
Headers show
Series Take devlink lock on mlx4 and mlx5 callbacks | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 1 maintainers not CCed: linux-rdma@vger.kernel.org
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 51 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Moshe Shemesh July 28, 2022, 3:53 p.m. UTC 
Change devlink instance locks in mlx5 driver to have devlink health
recovery callback locked, while keeping all driver paths which lead to
devl_ API functions called by the driver locked.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 12 +++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |  4 ++--
 2 files changed, 13 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 659021c31cbd..6e154b5c2bc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -622,8 +622,14 @@  mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
 			       struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+	struct devlink *devlink = priv_to_devlink(dev);
+	int ret;
 
-	return mlx5_health_try_recover(dev);
+	devl_lock(devlink);
+	ret = mlx5_health_try_recover(dev);
+	devl_unlock(devlink);
+
+	return ret;
 }
 
 static int
@@ -666,16 +672,20 @@  static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
 	struct mlx5_fw_reporter_ctx fw_reporter_ctx;
 	struct mlx5_core_health *health;
 	struct mlx5_core_dev *dev;
+	struct devlink *devlink;
 	struct mlx5_priv *priv;
 
 	health = container_of(work, struct mlx5_core_health, fatal_report_work);
 	priv = container_of(health, struct mlx5_priv, health);
 	dev = container_of(priv, struct mlx5_core_dev, priv);
+	devlink = priv_to_devlink(dev);
 
 	enter_error_state(dev, false);
 	if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
+		devl_lock(devlink);
 		if (mlx5_health_try_recover(dev))
 			mlx5_core_err(dev, "health recovery failed\n");
+		devl_unlock(devlink);
 		return;
 	}
 	fw_reporter_ctx.err_synd = health->synd;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 01fcb23eb69a..1de9b39a6359 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1932,7 +1932,7 @@  MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);
 void mlx5_disable_device(struct mlx5_core_dev *dev)
 {
 	mlx5_error_sw_reset(dev);
-	mlx5_unload_one(dev);
+	mlx5_unload_one_devl_locked(dev);
 }
 
 int mlx5_recover_device(struct mlx5_core_dev *dev)
@@ -1943,7 +1943,7 @@  int mlx5_recover_device(struct mlx5_core_dev *dev)
 			return -EIO;
 	}
 
-	return mlx5_load_one(dev, true);
+	return mlx5_load_one_devl_locked(dev, true);
 }
 
 static struct pci_driver mlx5_core_driver = {