diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 4382ef85488c5b6e936424dc902fd590d8030294..840ec945ccbab466863fb6f43a29bbfd23d08c4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -64,7 +64,7 @@ static int mlx5e_test_health_info(struct mlx5e_priv *priv)
{
struct mlx5_core_health *health = &priv->mdev->priv.health;
- return health->sick ? 1 : 0;
+ return health->fatal_error ? 1 : 0;
}
static int mlx5e_test_link_state(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index a2656f4008d9162b87ff2fc1f5639fcf8d3d4dda..737e6d55077598565794bf8247f0af2f21f8e9f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -62,12 +62,18 @@ enum {
enum {
MLX5_DROP_NEW_HEALTH_WORK,
- MLX5_DROP_NEW_RECOVERY_WORK,
+};
+
+enum {
+ MLX5_SENSOR_NO_ERR = 0,
+ MLX5_SENSOR_PCI_COMM_ERR = 1,
+ MLX5_SENSOR_NIC_DISABLED = 2,
+ MLX5_SENSOR_NIC_SW_RESET = 3,
};
u8 mlx5_get_nic_state(struct mlx5_core_dev *dev)
{
- return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3;
+ return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 7;
}
void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state)
@@ -80,18 +86,25 @@ void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state)
&dev->iseg->cmdq_addr_l_sz);
}
-static int in_fatal(struct mlx5_core_dev *dev)
+static bool sensor_pci_not_working(struct mlx5_core_dev *dev)
{
struct mlx5_core_health *health = &dev->priv.health;
struct health_buffer __iomem *h = health->health;
- if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
- return 1;
+ /* Offline PCI reads return 0xffffffff */
+ return (ioread32be(&h->fw_ver) == 0xffffffff);
+}
- if (ioread32be(&h->fw_ver) == 0xffffffff)
- return 1;
+static u32 check_fatal_sensors(struct mlx5_core_dev *dev)
+{
+ if (sensor_pci_not_working(dev))
+ return MLX5_SENSOR_PCI_COMM_ERR;
+ if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
+ return MLX5_SENSOR_NIC_DISABLED;
+ if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_SW_RESET)
+ return MLX5_SENSOR_NIC_SW_RESET;
- return 0;
+ return MLX5_SENSOR_NO_ERR;
}
void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
@@ -101,7 +114,8 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
goto unlock;
mlx5_core_err(dev, "start\n");
- if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) {
+ if (pci_channel_offline(dev->pdev) ||
+ dev->priv.health.fatal_error != MLX5_SENSOR_NO_ERR || force) {
dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
mlx5_cmd_flush(dev);
}
@@ -137,38 +151,14 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
mlx5_disable_device(dev);
}
-static void health_recover(struct work_struct *work)
-{
- struct mlx5_core_health *health;
- struct delayed_work *dwork;
- struct mlx5_core_dev *dev;
- struct mlx5_priv *priv;
- u8 nic_state;
-
- dwork = container_of(work, struct delayed_work, work);
- health = container_of(dwork, struct mlx5_core_health, recover_work);
- priv = container_of(health, struct mlx5_priv, health);
- dev = container_of(priv, struct mlx5_core_dev, priv);
-
- nic_state = mlx5_get_nic_state(dev);
- if (nic_state == MLX5_NIC_IFC_INVALID) {
- mlx5_core_err(dev, "health recovery flow aborted since the nic state is invalid\n");
- return;
- }
-
- mlx5_core_err(dev, "starting health recovery flow\n");
- mlx5_recover_device(dev);
-}
-
/* How much time to wait until health resetting the driver (in msecs) */
-#define MLX5_RECOVERY_DELAY_MSECS 60000
+#define MLX5_RECOVERY_WAIT_MSECS 60000
static void health_care(struct work_struct *work)
{
- unsigned long recover_delay = msecs_to_jiffies(MLX5_RECOVERY_DELAY_MSECS);
struct mlx5_core_health *health;
struct mlx5_core_dev *dev;
struct mlx5_priv *priv;
- unsigned long flags;
+ unsigned long end;
health = container_of(work, struct mlx5_core_health, work);
priv = container_of(health, struct mlx5_priv, health);
@@ -176,13 +166,18 @@ static void health_care(struct work_struct *work)
mlx5_core_warn(dev, "handling bad device here\n");
mlx5_handle_bad_state(dev);
- spin_lock_irqsave(&health->wq_lock, flags);
- if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
- schedule_delayed_work(&health->recover_work, recover_delay);
- else
- mlx5_core_err(dev,
- "new health works are not permitted at this stage\n");
- spin_unlock_irqrestore(&health->wq_lock, flags);
+ end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS);
+ while (sensor_pci_not_working(dev)) {
+ if (time_after(jiffies, end)) {
+ mlx5_core_err(dev,
+ "health recovery flow aborted, PCI reads still not working\n");
+ return;
+ }
+ msleep(100);
+ }
+
+ mlx5_core_err(dev, "starting health recovery flow\n");
+ mlx5_recover_device(dev);
}
static const char *hsynd_str(u8 synd)
@@ -274,6 +269,7 @@ static void poll_health(struct timer_list *t)
{
struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
struct mlx5_core_health *health = &dev->priv.health;
+ u32 fatal_error;
u32 count;
if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
@@ -291,8 +287,11 @@ static void poll_health(struct timer_list *t)
print_health_info(dev);
}
- if (in_fatal(dev) && !health->sick) {
- health->sick = true;
+ fatal_error = check_fatal_sensors(dev);
+
+ if (fatal_error && !health->fatal_error) {
+ mlx5_core_err(dev, "Fatal error %u detected\n", fatal_error);
+ dev->priv.health.fatal_error = fatal_error;
print_health_info(dev);
mlx5_trigger_health_work(dev);
}
@@ -306,9 +305,8 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
struct mlx5_core_health *health = &dev->priv.health;
timer_setup(&health->timer, poll_health, 0);
- health->sick = 0;
+ health->fatal_error = MLX5_SENSOR_NO_ERR;
clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
- clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
health->health = &dev->iseg->health;
health->health_counter = &dev->iseg->health_counter;
@@ -324,7 +322,6 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
if (disable_health) {
spin_lock_irqsave(&health->wq_lock, flags);
set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
- set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
spin_unlock_irqrestore(&health->wq_lock, flags);
}
@@ -338,23 +335,10 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
spin_lock_irqsave(&health->wq_lock, flags);
set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
- set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
spin_unlock_irqrestore(&health->wq_lock, flags);
- cancel_delayed_work_sync(&health->recover_work);
cancel_work_sync(&health->work);
}
-void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
-{
- struct mlx5_core_health *health = &dev->priv.health;
- unsigned long flags;
-
- spin_lock_irqsave(&health->wq_lock, flags);
- set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
- spin_unlock_irqrestore(&health->wq_lock, flags);
- cancel_delayed_work_sync(&dev->priv.health.recover_work);
-}
-
void mlx5_health_flush(struct mlx5_core_dev *dev)
{
struct mlx5_core_health *health = &dev->priv.health;
@@ -387,7 +371,6 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
return -ENOMEM;
spin_lock_init(&health->wq_lock);
INIT_WORK(&health->work, health_care);
- INIT_DELAYED_WORK(&health->recover_work, health_recover);
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c70e97071b872e4afdbe9f8b004c3947d2f470dc..fd0e2949c4f2355047fc979b701348b66d36fad0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1191,7 +1191,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
int err = 0;
if (cleanup)
- mlx5_drain_health_recovery(dev);
+ mlx5_drain_health_wq(dev);
mutex_lock(&dev->intf_state_mutex);
if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index d4dd8c1ae55c668abb379ddadee350127165a5f3..97f8cf67ced091106bf1040074642f6855e67212 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -214,7 +214,7 @@ enum {
MLX5_NIC_IFC_FULL = 0,
MLX5_NIC_IFC_DISABLED = 1,
MLX5_NIC_IFC_NO_DRAM_NIC = 2,
- MLX5_NIC_IFC_INVALID = 3
+ MLX5_NIC_IFC_SW_RESET = 7
};
u8 mlx5_get_nic_state(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 4ae533b3da0748452a513feb65734f5aa6d86244..cc7fd8e62844376c10371a51f6bdb095c869ed9e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -435,6 +435,7 @@ struct mlx5_core_health {
u32 prev;
int miss_counter;
bool sick;
+ u32 fatal_error;
u32 crdump_size;
/* wq spinlock to synchronize draining */
spinlock_t wq_lock;
@@ -906,7 +907,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev);
void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
-void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
struct mlx5_frag_buf *buf, int node);
int mlx5_buf_alloc(struct mlx5_core_dev *dev,