diff mbox series

[SRU,F,1/1] net/mlx5: Avoid processing commands before cmdif is ready

Message ID 20220901165337.602338-2-frank.heimes@canonical.com
State New
Headers show
Series net/mlx5: Avoid processing commands before cmdif is ready (LP: 1987287) | expand

Commit Message

Frank Heimes Sept. 1, 2022, 4:53 p.m. UTC 
From: Eran Ben Elisha <eranbe@mellanox.com>

BugLink: https://bugs.launchpad.net/bugs/1987287

When driver is reloading during recovery flow, it can't get new commands
till command interface is up again. Otherwise we may get to null pointer
trying to access non initialized command structures.

Add cmdif state to avoid processing commands while cmdif is not ready.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
(backported from commit f7936ddd35d8b849daf0372770c7c9dbe7910fca)
[Frank Heimes: Backport needed to make it fit to different kernel 5.4 context.]
Signed-off-by: Frank Heimes <frank.heimes@canonical.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c  | 10 ++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c |  4 ++++
 include/linux/mlx5/driver.h                    |  9 +++++++++
 3 files changed, 23 insertions(+)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 6c7b364d0bf0..0a4e49a0e431 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -955,6 +955,7 @@  static void cmd_work_handler(struct work_struct *work)
 	/* 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)) {
 		u8 status = 0;
 		u32 drv_synd;
@@ -1780,6 +1781,7 @@  static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	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)) {
 		err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status);
 		MLX5_SET(mbox_out, out, status, status);
@@ -2045,6 +2047,7 @@  int mlx5_cmd_init(struct mlx5_core_dev *dev)
 		goto err_free_page;
 	}
 
+	cmd->state = MLX5_CMDIF_STATE_DOWN;
 	cmd->checksum_disabled = 1;
 	cmd->max_reg_cmds = (1 << cmd->log_sz) - 1;
 	cmd->bitmask = (1UL << cmd->max_reg_cmds) - 1;
@@ -2122,3 +2125,10 @@  void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 	dma_pool_destroy(cmd->pool);
 }
 EXPORT_SYMBOL(mlx5_cmd_cleanup);
+
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+			enum mlx5_cmdif_state cmdif_state)
+{
+	dev->cmd.state = cmdif_state;
+}
+EXPORT_SYMBOL(mlx5_cmd_set_state);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0ebf687bf178..6bfe7b9615df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -975,6 +975,8 @@  static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 		goto err_cmd_cleanup;
 	}
 
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
+
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
@@ -1036,6 +1038,7 @@  static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 err_disable_hca:
 	mlx5_core_disable_hca(dev, 0);
 err_cmd_cleanup:
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
 	return err;
@@ -1053,6 +1056,7 @@  static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 	}
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev, 0);
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
 	return 0;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f01eaab8ea81..fa13fd38ebdf 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -228,6 +228,12 @@  struct mlx5_bfreg_info {
 	u32			num_dyn_bfregs;
 };
 
+enum mlx5_cmdif_state {
+	MLX5_CMDIF_STATE_UNINITIALIZED,
+	MLX5_CMDIF_STATE_UP,
+	MLX5_CMDIF_STATE_DOWN,
+};
+
 struct mlx5_cmd_first {
 	__be32		data[4];
 };
@@ -273,6 +279,7 @@  struct mlx5_cmd_stats {
 struct mlx5_cmd {
 	struct mlx5_nb    nb;
 
+	enum mlx5_cmdif_state	state;
 	void	       *cmd_alloc_buf;
 	dma_addr_t	alloc_dma;
 	int		alloc_size;
@@ -897,6 +904,8 @@  enum {
 
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+			enum mlx5_cmdif_state cmdif_state);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
 void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode);