net/mlx5: cmdif, Avoid skipping reclaim pages if FW is not accessible

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().

Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

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 2b597ac365f84..2d1f4b3be9bf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -902,6 +902,13 @@ retry:
 	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 f9b798af6335d..c0e18f2ade996 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 897156822f0de..372100c755e7f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -935,6 +935,7 @@ 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);