summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/amazon/ena/ena_netdev.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/amazon/ena/ena_netdev.c')
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_netdev.c77
1 files changed, 63 insertions, 14 deletions
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 18acb764e446..ae9291b61be2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -47,19 +47,44 @@ static int ena_restore_device(struct ena_adapter *adapter);
static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue)
{
+ enum ena_regs_reset_reason_types reset_reason = ENA_REGS_RESET_OS_NETDEV_WD;
struct ena_adapter *adapter = netdev_priv(dev);
+ unsigned int time_since_last_napi, threshold;
+ struct ena_ring *tx_ring;
+ int napi_scheduled;
+
+ if (txqueue >= adapter->num_io_queues) {
+ netdev_err(dev, "TX timeout on invalid queue %u\n", txqueue);
+ goto schedule_reset;
+ }
+
+ threshold = jiffies_to_usecs(dev->watchdog_timeo);
+ tx_ring = &adapter->tx_ring[txqueue];
+
+ time_since_last_napi = jiffies_to_usecs(jiffies - tx_ring->tx_stats.last_napi_jiffies);
+ napi_scheduled = !!(tx_ring->napi->state & NAPIF_STATE_SCHED);
+ netdev_err(dev,
+ "TX q %d is paused for too long (threshold %u). Time since last napi %u usec. napi scheduled: %d\n",
+ txqueue,
+ threshold,
+ time_since_last_napi,
+ napi_scheduled);
+
+ if (threshold < time_since_last_napi && napi_scheduled) {
+ netdev_err(dev,
+ "napi handler hasn't been called for a long time but is scheduled\n");
+ reset_reason = ENA_REGS_RESET_SUSPECTED_POLL_STARVATION;
+ }
+schedule_reset:
/* Change the state of the device to trigger reset
* Check that we are not in the middle or a trigger already
*/
-
if (test_and_set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
return;
- ena_reset_device(adapter, ENA_REGS_RESET_OS_NETDEV_WD);
+ ena_reset_device(adapter, reset_reason);
ena_increase_stat(&adapter->dev_stats.tx_timeout, 1, &adapter->syncp);
-
- netif_err(adapter, tx_err, dev, "Transmit time out\n");
}
static void update_rx_ring_mtu(struct ena_adapter *adapter, int mtu)
@@ -3374,14 +3399,18 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
struct ena_ring *tx_ring)
{
struct ena_napi *ena_napi = container_of(tx_ring->napi, struct ena_napi, napi);
+ enum ena_regs_reset_reason_types reset_reason = ENA_REGS_RESET_MISS_TX_CMPL;
unsigned int time_since_last_napi;
unsigned int missing_tx_comp_to;
bool is_tx_comp_time_expired;
struct ena_tx_buffer *tx_buf;
unsigned long last_jiffies;
+ int napi_scheduled;
u32 missed_tx = 0;
int i, rc = 0;
+ missing_tx_comp_to = jiffies_to_msecs(adapter->missing_tx_completion_to);
+
for (i = 0; i < tx_ring->ring_size; i++) {
tx_buf = &tx_ring->tx_buffer_info[i];
last_jiffies = tx_buf->last_jiffies;
@@ -3408,25 +3437,45 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
adapter->missing_tx_completion_to);
if (unlikely(is_tx_comp_time_expired)) {
- if (!tx_buf->print_once) {
- time_since_last_napi = jiffies_to_usecs(jiffies - tx_ring->tx_stats.last_napi_jiffies);
- missing_tx_comp_to = jiffies_to_msecs(adapter->missing_tx_completion_to);
- netif_notice(adapter, tx_err, adapter->netdev,
- "Found a Tx that wasn't completed on time, qid %d, index %d. %u usecs have passed since last napi execution. Missing Tx timeout value %u msecs\n",
- tx_ring->qid, i, time_since_last_napi, missing_tx_comp_to);
+ time_since_last_napi =
+ jiffies_to_usecs(jiffies - tx_ring->tx_stats.last_napi_jiffies);
+ napi_scheduled = !!(ena_napi->napi.state & NAPIF_STATE_SCHED);
+
+ if (missing_tx_comp_to < time_since_last_napi && napi_scheduled) {
+ /* We suspect napi isn't called because the
+ * bottom half is not run. Require a bigger
+ * timeout for these cases
+ */
+ if (!time_is_before_jiffies(last_jiffies +
+ 2 * adapter->missing_tx_completion_to))
+ continue;
+
+ reset_reason = ENA_REGS_RESET_SUSPECTED_POLL_STARVATION;
}
- tx_buf->print_once = 1;
missed_tx++;
+
+ if (tx_buf->print_once)
+ continue;
+
+ netif_notice(adapter, tx_err, adapter->netdev,
+ "TX hasn't completed, qid %d, index %d. %u usecs from last napi execution, napi scheduled: %d\n",
+ tx_ring->qid, i, time_since_last_napi, napi_scheduled);
+
+ tx_buf->print_once = 1;
}
}
if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) {
netif_err(adapter, tx_err, adapter->netdev,
- "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
+ "Lost TX completions are above the threshold (%d > %d). Completion transmission timeout: %u.\n",
missed_tx,
- adapter->missing_tx_completion_threshold);
- ena_reset_device(adapter, ENA_REGS_RESET_MISS_TX_CMPL);
+ adapter->missing_tx_completion_threshold,
+ missing_tx_comp_to);
+ netif_err(adapter, tx_err, adapter->netdev,
+ "Resetting the device\n");
+
+ ena_reset_device(adapter, reset_reason);
rc = -EIO;
}