diff options
| author | Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com> | 2012-07-20 13:55:43 +0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2012-07-26 02:24:13 +0400 |
| commit | 57dbf29a54bda5773f9ed1d00e3cc633294259da (patch) | |
| tree | 311f1973354a10fa997db812299982b560dc821f /drivers/net/ethernet/mellanox/mlx4/catas.c | |
| parent | f94898ea6682977f15c5a8f9ffb293a14f95455a (diff) | |
| download | linux-57dbf29a54bda5773f9ed1d00e3cc633294259da.tar.xz | |
mlx4: Add support for EEH error recovery
Currently the mlx4 drivers don't have the necessary callbacks to
implement EEH errors detection and recovery, so the PCI layer uses the
probe and remove callbacks to try to recover the device after an error on
the bus. However, these callbacks have race conditions with the internal
catastrophic error recovery functions, which will also detect the error
and this can cause the system to crash if both EEH and catas functions
try to reset the device.
This patch adds the necessary error recovery callbacks and makes sure
that the internal catastrophic error functions will not try to reset the
device in such scenarios. It also adds some calls to
pci_channel_offline() to suppress reads/writes on the bus when the slot
cannot accept I/O operations so we prevent unnecessary accesses to the
bus and speed up the device removal.
Signed-off-by: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Acked-by: Shlomo Pongratz <shlomop@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/catas.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/catas.c | 25 |
1 files changed, 17 insertions, 8 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 915e947b422d..9c656fe4983d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -69,16 +69,21 @@ static void poll_catas(unsigned long dev_ptr) struct mlx4_priv *priv = mlx4_priv(dev); if (readl(priv->catas_err.map)) { - dump_err_buf(dev); - - mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0); + /* If the device is off-line, we cannot try to recover it */ + if (pci_channel_offline(dev->pdev)) + mod_timer(&priv->catas_err.timer, + round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL)); + else { + dump_err_buf(dev); + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0); - if (internal_err_reset) { - spin_lock(&catas_lock); - list_add(&priv->catas_err.list, &catas_list); - spin_unlock(&catas_lock); + if (internal_err_reset) { + spin_lock(&catas_lock); + list_add(&priv->catas_err.list, &catas_list); + spin_unlock(&catas_lock); - queue_work(mlx4_wq, &catas_work); + queue_work(mlx4_wq, &catas_work); + } } } else mod_timer(&priv->catas_err.timer, @@ -100,6 +105,10 @@ static void catas_reset(struct work_struct *work) list_for_each_entry_safe(priv, tmppriv, &tlist, catas_err.list) { struct pci_dev *pdev = priv->dev.pdev; + /* If the device is off-line, we cannot reset it */ + if (pci_channel_offline(pdev)) + continue; + ret = mlx4_restart_one(priv->dev.pdev); /* 'priv' now is not valid */ if (ret) |