From 17d00e839d3b592da9659c1977d45f85b77f986a Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 27 Dec 2019 07:01:53 +0200 Subject: net/mlx5: Add command entry handling completion When FW response to commands is very slow and all command entries in use are waiting for completion we can have a race where commands can get timeout before they get out of the queue and handled. Timeout completion on uninitialized command will cause releasing command's buffers before accessing it for initialization and then we will get NULL pointer exception while trying access it. It may also cause releasing buffers of another command since we may have timeout completion before even allocating entry index for this command. Add entry handling completion to avoid this race. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Moshe Shemesh Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6f8f79ef829b..9b1f29f26c27 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -743,6 +743,7 @@ struct mlx5_cmd_work_ent { struct delayed_work cb_timeout_work; void *context; int idx; + struct completion handling; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; -- cgit v1.2.3 From d43b7007dbd1195a5b6b83213e49b1516aaf6f5e Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 18 Mar 2020 21:44:32 +0200 Subject: net/mlx5: Fix a race when moving command interface to events mode After driver creates (via FW command) an EQ for commands, the driver will be informed on new commands completion by EQE. However, due to a race in driver's internal command mode metadata update, some new commands will still be miss-handled by driver as if we are in polling mode. Such commands can get two non forced completion, leading to already freed command entry access. CREATE_EQ command, that maps EQ to the command queue must be posted to the command queue while it is empty and no other command should be posted. Add SW mechanism that once the CREATE_EQ command is about to be executed, all other commands will return error without being sent to the FW. Allow sending other commands only after successfully changing the driver's internal command mode metadata. We can safely return error to all other commands while creating the command EQ, as all other commands might be sent from the user/application during driver load. Application can rerun them later after driver's load was finished. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Eran Ben Elisha Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9b1f29f26c27..c03778c75dfa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -284,6 +284,7 @@ struct mlx5_cmd { struct semaphore sem; struct semaphore pages_sem; int mode; + u16 allowed_opcode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; struct dma_pool *pool; struct mlx5_cmd_debug dbg; @@ -875,10 +876,15 @@ mlx5_frag_buf_get_idx_last_contig_stride(struct mlx5_frag_buf_ctrl *fbc, u32 ix) return min_t(u32, last_frag_stride_idx - fbc->strides_offset, fbc->sz_m1); } +enum { + CMD_ALLOWED_OPCODE_ALL, +}; + int mlx5_cmd_init(struct mlx5_core_dev *dev); void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); 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); struct mlx5_async_ctx { struct mlx5_core_dev *dev; -- cgit v1.2.3 From f7936ddd35d8b849daf0372770c7c9dbe7910fca Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 19 Mar 2020 21:43:13 +0200 Subject: net/mlx5: Avoid processing commands before cmdif is ready 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 Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c03778c75dfa..8397b6558dc7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -213,6 +213,12 @@ enum mlx5_port_status { MLX5_PORT_DOWN = 2, }; +enum mlx5_cmdif_state { + MLX5_CMDIF_STATE_UNINITIALIZED, + MLX5_CMDIF_STATE_UP, + MLX5_CMDIF_STATE_DOWN, +}; + struct mlx5_cmd_first { __be32 data[4]; }; @@ -258,6 +264,7 @@ 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; @@ -882,6 +889,8 @@ 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); -- cgit v1.2.3