This is a note to let you know that I've just added the patch titled
net/mlx5: Cleanup IRQs in case of unload failure
to the 4.14-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
net-mlx5-cleanup-irqs-in-case-of-unload-failure.patch
and it can be found in the queue-4.14 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From foo@baz Wed Feb 28 16:23:28 CET 2018
From: Moshe Shemesh <moshe@xxxxxxxxxxxx>
Date: Tue, 21 Nov 2017 15:15:51 +0200
Subject: net/mlx5: Cleanup IRQs in case of unload failure
From: Moshe Shemesh <moshe@xxxxxxxxxxxx>
[ Upstream commit d6b2785cd55ee72e9608762650b3ef299f801b1b ]
When mlx5_stop_eqs fails to destroy any of the eqs it returns with an error.
In such failure flow the function will return without
releasing all EQs irqs and then pci_free_irq_vectors will fail.
Fix by only warn on destroy EQ failure and continue to release other
EQs and their irqs.
It fixes the following kernel trace:
kernel: kernel BUG at drivers/pci/msi.c:352!
...
...
kernel: Call Trace:
kernel: pci_disable_msix+0xd3/0x100
kernel: pci_free_irq_vectors+0xe/0x20
kernel: mlx5_load_one.isra.17+0x9f5/0xec0 [mlx5_core]
Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Moshe Shemesh <moshe@xxxxxxxxxxxx>
Signed-off-by: Saeed Mahameed <saeedm@xxxxxxxxxxxx>
Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 20 +++++++++++++-------
include/linux/mlx5/driver.h | 2 +-
2 files changed, 14 insertions(+), 8 deletions(-)
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -776,7 +776,7 @@ err1:
return err;
}
-int mlx5_stop_eqs(struct mlx5_core_dev *dev)
+void mlx5_stop_eqs(struct mlx5_core_dev *dev)
{
struct mlx5_eq_table *table = &dev->priv.eq_table;
int err;
@@ -785,22 +785,28 @@ int mlx5_stop_eqs(struct mlx5_core_dev *
if (MLX5_CAP_GEN(dev, pg)) {
err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq);
if (err)
- return err;
+ mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n",
+ err);
}
#endif
err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
if (err)
- return err;
+ mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
+ err);
- mlx5_destroy_unmap_eq(dev, &table->async_eq);
+ err = mlx5_destroy_unmap_eq(dev, &table->async_eq);
+ if (err)
+ mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
+ err);
mlx5_cmd_use_polling(dev);
err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
- if (err)
+ if (err) {
+ mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
+ err);
mlx5_cmd_use_events(dev);
-
- return err;
+ }
}
int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1017,7 +1017,7 @@ int mlx5_create_map_eq(struct mlx5_core_
enum mlx5_eq_type type);
int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
int mlx5_start_eqs(struct mlx5_core_dev *dev);
-int mlx5_stop_eqs(struct mlx5_core_dev *dev);
+void mlx5_stop_eqs(struct mlx5_core_dev *dev);
int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
unsigned int *irqn);
int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
Patches currently in stable-queue which might be from moshe@xxxxxxxxxxxx are
queue-4.14/net-mlx5e-fix-ets-bw-check.patch
queue-4.14/net-mlx5-stay-in-polling-mode-when-command-eq-destroy-fails.patch
queue-4.14/net-mlx5-cleanup-irqs-in-case-of-unload-failure.patch