From: saeed@kernel.org
To: "David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>
Cc: netdev@vger.kernel.org, Saeed Mahameed <saeedm@nvidia.com>,
Moshe Shemesh <moshe@nvidia.com>
Subject: [net 06/15] net/mlx5: cmdif, Avoid skipping reclaim pages if FW is not accessible
Date: Wed, 30 Sep 2020 19:05:07 -0700 [thread overview]
Message-ID: <20201001020516.41217-7-saeed@kernel.org> (raw)
In-Reply-To: <20201001020516.41217-1-saeed@kernel.org>
From: Saeed Mahameed <saeedm@nvidia.com>
In case of pci is offline reclaim_pages_cmd() will still try to call
the FW to release FW pages, cmd_exec() in this case will return a silent
success without actually calling the FW.
This is wrong and will cause page leaks, what we should do is to detect
pci offline or command interface un-available before tying to access the
FW and manually release the FW pages in the driver.
In this patch we share the code to check for FW command interface
availability and we call it in sensitive places e.g. reclaim_pages_cmd().
Alternative fix:
1. Remove MLX5_CMD_OP_MANAGE_PAGES form mlx5_internal_err_ret_value,
command success simulation list.
2. Always Release FW pages even if cmd_exec fails in reclaim_pages_cmd().
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 17 +++++++++--------
.../net/ethernet/mellanox/mlx5/core/pagealloc.c | 2 +-
include/linux/mlx5/driver.h | 1 +
3 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 4b54c9241fd7..f9c44166e210 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -902,6 +902,13 @@ static int cmd_alloc_index_retry(struct mlx5_cmd *cmd)
return idx;
}
+bool mlx5_cmd_is_down(struct mlx5_core_dev *dev)
+{
+ return pci_channel_offline(dev->pdev) ||
+ dev->cmd.state != MLX5_CMDIF_STATE_UP ||
+ dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR;
+}
+
static void cmd_work_handler(struct work_struct *work)
{
struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -967,10 +974,7 @@ static void cmd_work_handler(struct work_struct *work)
set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
/* Skip sending command to fw if internal error */
- if (pci_channel_offline(dev->pdev) ||
- dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
- cmd->state != MLX5_CMDIF_STATE_UP ||
- !opcode_allowed(&dev->cmd, ent->op)) {
+ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) {
u8 status = 0;
u32 drv_synd;
@@ -1800,10 +1804,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
u8 token;
opcode = MLX5_GET(mbox_in, in, opcode);
- if (pci_channel_offline(dev->pdev) ||
- dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
- dev->cmd.state != MLX5_CMDIF_STATE_UP ||
- !opcode_allowed(&dev->cmd, opcode)) {
+ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) {
err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status);
MLX5_SET(mbox_out, out, status, status);
MLX5_SET(mbox_out, out, syndrome, drv_synd);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index f9b798af6335..c0e18f2ade99 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -432,7 +432,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
u32 npages;
u32 i = 0;
- if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR)
+ if (!mlx5_cmd_is_down(dev))
return mlx5_cmd_exec(dev, in, in_size, out, out_size);
/* No hard feelings, we want our pages back! */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2437e8721b36..4a99d6ff1401 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -936,6 +936,7 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
void *out, int out_size);
void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
+bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
--
2.26.2
next prev parent reply other threads:[~2020-10-01 2:05 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-01 2:05 [pull request][net 00/15] mlx5 fixes 2020-09-30 saeed
2020-10-01 2:05 ` [net 01/15] net/mlx5: Don't allow health work when device is uninitialized saeed
2020-10-01 19:21 ` David Miller
2020-10-01 19:41 ` Saeed Mahameed
2020-10-01 2:05 ` [net 02/15] net/mlx5: Fix a race when moving command interface to polling mode saeed
2020-10-01 2:05 ` [net 03/15] net/mlx5: Avoid possible free of command entry while timeout comp handler saeed
2020-10-01 2:05 ` [net 04/15] net/mlx5: poll cmd EQ in case of command timeout saeed
2020-10-01 2:05 ` [net 05/15] net/mlx5: Add retry mechanism to the command entry index allocation saeed
2020-10-01 2:05 ` saeed [this message]
2020-10-01 2:05 ` [net 07/15] net/mlx5: Fix request_irqs error flow saeed
2020-10-01 2:05 ` [net 08/15] net/mlx5e: Fix error path for RQ alloc saeed
2020-10-01 2:05 ` [net 09/15] net/mlx5e: Add resiliency in Striding RQ mode for packets larger than MTU saeed
2020-10-01 2:05 ` [net 10/15] net/mlx5e: CT, Fix coverity issue saeed
2020-10-01 2:05 ` [net 11/15] net/mlx5e: Fix driver's declaration to support GRE offload saeed
2020-10-01 2:05 ` [net 12/15] net/mlx5e: Fix return status when setting unsupported FEC mode saeed
2020-10-01 2:05 ` [net 13/15] net/mlx5e: Fix VLAN cleanup flow saeed
2020-10-01 2:05 ` [net 14/15] net/mlx5e: Fix VLAN create flow saeed
2020-10-01 2:05 ` [net 15/15] net/mlx5e: Fix race condition on nhe->n pointer in neigh update saeed
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=20201001020516.41217-7-saeed@kernel.org \
--to=saeed@kernel.org \
--cc=davem@davemloft.net \
--cc=kuba@kernel.org \
--cc=moshe@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=saeedm@nvidia.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).