net/mlx4_core: Fix deadlock when switching between polling and event fw commands

commit a7e1f04905e5b2b90251974dddde781301b6be37 upstream.

When switching from polling-based fw commands to event-based fw
commands, there is a race condition which could cause a fw command
in another task to hang: that task will keep waiting for the polling
sempahore, but may never be able to acquire it. This is due to
mlx4_cmd_use_events, which "down"s the sempahore back to 0.

During driver initialization, this is not a problem, since no other
tasks which invoke FW commands are active.

However, there is a problem if the driver switches to polling mode
and then back to event mode during normal operation.

The "test_interrupts" feature does exactly that.
Running "ethtool -t <eth device> offline" causes the PF driver to
temporarily switch to polling mode, and then back to event mode.
(Note that for VF drivers, such switching is not performed).

Fix this by adding a read-write semaphore for protection when
switching between modes.

Fixes: 225c7b1feef1 ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[bwh: Backported to 3.2: adjust context, indentation]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 78f5a1a..37f4995 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -313,12 +313,18 @@ int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
               int out_is_imm, u32 in_modifier, u8 op_modifier,
               u16 op, unsigned long timeout)
 {
+       int ret;
+
+       down_read(&mlx4_priv(dev)->cmd.switch_sem);
        if (mlx4_priv(dev)->cmd.use_events)
-               return mlx4_cmd_wait(dev, in_param, out_param, out_is_imm,
-                                    in_modifier, op_modifier, op, timeout);
+               ret = mlx4_cmd_wait(dev, in_param, out_param, out_is_imm,
+                                   in_modifier, op_modifier, op, timeout);
        else
-               return mlx4_cmd_poll(dev, in_param, out_param, out_is_imm,
-                                    in_modifier, op_modifier, op, timeout);
+               ret = mlx4_cmd_poll(dev, in_param, out_param, out_is_imm,
+                                   in_modifier, op_modifier, op, timeout);
+
+       up_read(&mlx4_priv(dev)->cmd.switch_sem);
+       return ret;
 }
 EXPORT_SYMBOL_GPL(__mlx4_cmd);
 
@@ -326,6 +332,7 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 {
        struct mlx4_priv *priv = mlx4_priv(dev);
 
+       init_rwsem(&priv->cmd.switch_sem);
        mutex_init(&priv->cmd.hcr_mutex);
        sema_init(&priv->cmd.poll_sem, 1);
        priv->cmd.use_events = 0;
@@ -372,6 +379,7 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
        if (!priv->cmd.context)
                return -ENOMEM;
 
+       down_write(&priv->cmd.switch_sem);
        for (i = 0; i < priv->cmd.max_cmds; ++i) {
                priv->cmd.context[i].token = i;
                priv->cmd.context[i].next  = i + 1;
@@ -390,6 +398,7 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
        --priv->cmd.token_mask;
 
        priv->cmd.use_events = 1;
+       up_write(&priv->cmd.switch_sem);
 
        down(&priv->cmd.poll_sem);
 
@@ -404,6 +413,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
        struct mlx4_priv *priv = mlx4_priv(dev);
        int i;
 
+       down_write(&priv->cmd.switch_sem);
        priv->cmd.use_events = 0;
 
        for (i = 0; i < priv->cmd.max_cmds; ++i)
@@ -412,6 +422,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
        kfree(priv->cmd.context);
 
        up(&priv->cmd.poll_sem);
+       up_write(&priv->cmd.switch_sem);
 }
 
 struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)

diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 169853d..1bf26ba 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -42,6 +42,7 @@
 #include <linux/timer.h>
 #include <linux/semaphore.h>
 #include <linux/workqueue.h>
+#include <linux/rwsem.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -190,6 +191,7 @@ struct mlx4_cmd {
        struct mutex            hcr_mutex;
        struct semaphore        poll_sem;
        struct semaphore        event_sem;
+       struct rw_semaphore     switch_sem;
        int                     max_cmds;
        spinlock_t              context_lock;
        int                     free_head;