net/mlx5: Add timeout handle to commands with callback

commit 65ee67084589c1783a74b4a4a5db38d7264ec8b5 upstream.

The current implementation does not handle timeout in case of command
with callback request, and this can lead to deadlock if the command
doesn't get fw response.
Add delayed callback timeout work before posting the command to fw.
In case of real fw command completion we will cancel the delayed work.
In case of fw command timeout the callback timeout handler will be
called and it will simulate fw completion with timeout error.

Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d2187d0d60eb9852709d9e079da57b4bbf9f79d2..cea4098b1d80f0b527847509d252de6b5245d7a9 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -509,11 +509,36 @@ static void dump_command(struct mlx5_core_dev *dev,
                pr_debug("\n");
 }
 
+static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
+{
+       struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
+
+       return be16_to_cpu(hdr->opcode);
+}
+
+static void cb_timeout_handler(struct work_struct *work)
+{
+       struct delayed_work *dwork = container_of(work, struct delayed_work,
+                                                 work);
+       struct mlx5_cmd_work_ent *ent = container_of(dwork,
+                                                    struct mlx5_cmd_work_ent,
+                                                    cb_timeout_work);
+       struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
+                                                cmd);
+
+       ent->ret = -ETIMEDOUT;
+       mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
+                      mlx5_command_str(msg_to_opcode(ent->in)),
+                      msg_to_opcode(ent->in));
+       mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
        struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
        struct mlx5_cmd *cmd = ent->cmd;
        struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd);
+       unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
        struct mlx5_cmd_layout *lay;
        struct semaphore *sem;
 
@@ -550,6 +575,9 @@ static void cmd_work_handler(struct work_struct *work)
        dump_command(dev, ent, 1);
        ktime_get_ts(&ent->ts1);
 
+       if (ent->callback)
+               schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+
        /* ring doorbell after the descriptor is valid */
        wmb();
        iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
@@ -593,13 +621,6 @@ static const char *deliv_status_to_str(u8 status)
        }
 }
 
-static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
-{
-       struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
-
-       return be16_to_cpu(hdr->opcode);
-}
-
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 {
        unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
@@ -654,6 +675,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
        if (!callback)
                init_completion(&ent->done);
 
+       INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler);
        INIT_WORK(&ent->work, cmd_work_handler);
        if (page_queue) {
                cmd_work_handler(&ent->work);
@@ -1132,6 +1154,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector)
                        struct semaphore *sem;
 
                        ent = cmd->ent_arr[i];
+                       if (ent->callback)
+                               cancel_delayed_work(&ent->cb_timeout_work);
                        if (ent->page_queue)
                                sem = &cmd->pages_sem;
                        else

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fd152032d7791921fe4578069d03902b7238cfdd..8ab4eac0292b0159f4296e21267d6e5e432db149 100644 (file)
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -594,6 +594,7 @@ struct mlx5_cmd_work_ent {
        void                   *uout;
        int                     uout_size;
        mlx5_cmd_cbk_t          callback;
+       struct delayed_work     cb_timeout_work;
        void                   *context;
        int                     idx;
        struct completion       done;