diff options
author | John Fraker <jfraker@google.com> | 2021-10-11 08:36:47 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2021-10-11 23:25:36 +0100 |
commit | 87a7f321bb6a45e54b7d6c90d032ee5636a6ad97 (patch) | |
tree | bde43329205c062d1ffb3cffc4c32feb20c08c77 /drivers/net/ethernet/google/gve/gve_main.c | |
parent | 61d72c7e486b63340f1fadcf3bed4cae98f03d9b (diff) |
gve: Recover from queue stall due to missed IRQ
Don't always reset the driver on a TX timeout. Attempt to
recover by kicking the queue in case an IRQ was missed.
Fixes: 9e5f7d26a4c08 ("gve: Add workqueue and reset support")
Signed-off-by: John Fraker <jfraker@google.com>
Signed-off-by: David Awogbemila <awogbemila@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/google/gve/gve_main.c')
-rw-r--r-- | drivers/net/ethernet/google/gve/gve_main.c | 48 |
1 files changed, 47 insertions, 1 deletions
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index b6805ad2011b..7647cd05b1d2 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -24,6 +24,9 @@ #define GVE_VERSION "1.0.0" #define GVE_VERSION_PREFIX "GVE-" +// Minimum amount of time between queue kicks in msec (10 seconds) +#define MIN_TX_TIMEOUT_GAP (1000 * 10) + const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; @@ -1121,9 +1124,47 @@ static void gve_turnup(struct gve_priv *priv) static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) { - struct gve_priv *priv = netdev_priv(dev); + struct gve_notify_block *block; + struct gve_tx_ring *tx = NULL; + struct gve_priv *priv; + u32 last_nic_done; + u32 current_time; + u32 ntfy_idx; + + netdev_info(dev, "Timeout on tx queue, %d", txqueue); + priv = netdev_priv(dev); + if (txqueue > priv->tx_cfg.num_queues) + goto reset; + + ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue); + if (ntfy_idx > priv->num_ntfy_blks) + goto reset; + + block = &priv->ntfy_blocks[ntfy_idx]; + tx = block->tx; + current_time = jiffies_to_msecs(jiffies); + if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) + goto reset; + + /* Check to see if there are missed completions, which will allow us to + * kick the queue. + */ + last_nic_done = gve_tx_load_event_counter(priv, tx); + if (last_nic_done - tx->done) { + netdev_info(dev, "Kicking queue %d", txqueue); + iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block)); + napi_schedule(&block->napi); + tx->last_kick_msec = current_time; + goto out; + } // Else reset. + +reset: gve_schedule_reset(priv); + +out: + if (tx) + tx->queue_timeout++; priv->tx_timeo_cnt++; } @@ -1252,6 +1293,11 @@ void gve_handle_report_stats(struct gve_priv *priv) .value = cpu_to_be64(last_completion), .queue_id = cpu_to_be32(idx), }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_TIMEOUT_CNT), + .value = cpu_to_be64(priv->tx[idx].queue_timeout), + .queue_id = cpu_to_be32(idx), + }; } } /* rx stats */ |