net/mlx4_core: Avoid delays during VF driver device shutdown

[ Upstream commit 4cbe4dac82e423ecc9a0ba46af24a860853259f4 ]

Some Hypervisors detach VFs from VMs by instantly causing an FLR event
to be generated for a VF.

In the mlx4 case, this will cause that VF's comm channel to be disabled
before the VM has an opportunity to invoke the VF device's "shutdown"
method.

For such Hypervisors, there is a race condition between the VF's
shutdown method and its internal-error detection/reset thread.

The internal-error detection/reset thread (which runs every 5 seconds) also
detects a disabled comm channel. If the internal-error detection/reset
flow wins the race, we still get delays (while that flow tries repeatedly
to detect comm-channel recovery).

The cited commit fixed the command timeout problem when the
internal-error detection/reset flow loses the race.

This commit avoids the unneeded delays when the internal-error
detection/reset flow wins.

Fixes: d585df1c5ccf ("net/mlx4_core: Avoid command timeouts during VF driver device shutdown")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reported-by: Simon Xiao <sixiao@microsoft.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index d48d5793407d9ec729fe8548a049a2506d02a934..fc222df47aa9971dc53b8112142c8ec1367ba8d0 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2278,6 +2278,17 @@ static int sync_toggles(struct mlx4_dev *dev)
                rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read));
                if (wr_toggle == 0xffffffff || rd_toggle == 0xffffffff) {
                        /* PCI might be offline */
+
+                       /* If device removal has been requested,
+                        * do not continue retrying.
+                        */
+                       if (dev->persist->interface_state &
+                           MLX4_INTERFACE_STATE_NOWAIT) {
+                               mlx4_warn(dev,
+                                         "communication channel is offline\n");
+                               return -EIO;
+                       }
+
                        msleep(100);
                        wr_toggle = swab32(readl(&priv->mfunc.comm->
                                           slave_write));

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 99361352ed0d09f728011c66a4d2582a419ca3d0..a7d3144c238837abfac4fa4e76a512c9c48ab0a0 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1763,6 +1763,14 @@ static int mlx4_comm_check_offline(struct mlx4_dev *dev)
                               (u32)(1 << COMM_CHAN_OFFLINE_OFFSET));
                if (!offline_bit)
                        return 0;
+
+               /* If device removal has been requested,
+                * do not continue retrying.
+                */
+               if (dev->persist->interface_state &
+                   MLX4_INTERFACE_STATE_NOWAIT)
+                       break;
+
                /* There are cases as part of AER/Reset flow that PF needs
                 * around 100 msec to load. We therefore sleep for 100 msec
                 * to allow other tasks to make use of that CPU during this
@@ -3690,6 +3698,9 @@ static void mlx4_remove_one(struct pci_dev *pdev)
        struct mlx4_priv *priv = mlx4_priv(dev);
        int active_vfs = 0;
 
+       if (mlx4_is_slave(dev))
+               persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT;
+
        mutex_lock(&persist->interface_state_mutex);
        persist->interface_state |= MLX4_INTERFACE_STATE_DELETION;
        mutex_unlock(&persist->interface_state_mutex);

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d3133be12d922521e24528480edbdb31659a7007..7fde8af9b87eadefdd27f87f6eb59ea14907a59f 100644 (file)
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -460,6 +460,7 @@ enum {
 enum {
        MLX4_INTERFACE_STATE_UP         = 1 << 0,
        MLX4_INTERFACE_STATE_DELETION   = 1 << 1,
+       MLX4_INTERFACE_STATE_NOWAIT     = 1 << 2,
 };
 
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \