net: ena: add detection and recovery mechanism for handling missed/misrouted MSI-X

BugLink: http://bugs.launchpad.net/bugs/1792044
A mechanism for detection of stuck Rx/Tx rings due to missed or
misrouted interrupts.
Check if there are unhandled completion descriptors before the first
MSI-X interrupt arrived.
The check is per queue and per interrupt vector.
Once such condition is detected, driver and device reset is scheduled.

Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 8510e1a3d16c7e4e2b47c9675b18725407c616b7)
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Acked-by: Acked-by: Stefan Bader <stefan.bader@canonical.com>
Acked-by: Brad Figg <brad.figg@canonical.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>

diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index b11e573ad57a9a1d37f6e1f96b493e3795080d1a..ea149c134e1538d6c888db712d9b6cdc2b01412f 100644 (file)
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -504,3 +504,14 @@ int ena_com_tx_comp_req_id_get(struct ena_com_io_cq *io_cq, u16 *req_id)
 
        return 0;
 }
+
+bool ena_com_cq_empty(struct ena_com_io_cq *io_cq)
+{
+       struct ena_eth_io_rx_cdesc_base *cdesc;
+
+       cdesc = ena_com_get_next_rx_cdesc(io_cq);
+       if (cdesc)
+               return false;
+       else
+               return true;
+}

diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
index bb53c3a4f8e98366d9f3ffec311838a5275a9313..2f7657227cfe9c60d77482c98df22fdb2f89e3c9 100644 (file)
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
@@ -88,6 +88,8 @@ int ena_com_add_single_rx_desc(struct ena_com_io_sq *io_sq,
 
 int ena_com_tx_comp_req_id_get(struct ena_com_io_cq *io_cq, u16 *req_id);
 
+bool ena_com_cq_empty(struct ena_com_io_cq *io_cq);
+
 static inline void ena_com_unmask_intr(struct ena_com_io_cq *io_cq,
                                       struct ena_eth_io_intr_reg *intr_reg)
 {

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index fbe21a817bd8a2c9ca01a2be6e8c6948b704ef87..6975150d144e5ec8726d30cfe888b6888bb7a8b4 100644 (file)
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -161,6 +161,8 @@ static void ena_init_io_rings_common(struct ena_adapter *adapter,
        ring->per_napi_packets = 0;
        ring->per_napi_bytes = 0;
        ring->cpu = 0;
+       ring->first_interrupt = false;
+       ring->no_interrupt_event_cnt = 0;
        u64_stats_init(&ring->syncp);
 }
 
@@ -1277,6 +1279,9 @@ static irqreturn_t ena_intr_msix_io(int irq, void *data)
 {
        struct ena_napi *ena_napi = data;
 
+       ena_napi->tx_ring->first_interrupt = true;
+       ena_napi->rx_ring->first_interrupt = true;
+
        napi_schedule_irqoff(&ena_napi->napi);
 
        return IRQ_HANDLED;
@@ -2663,8 +2668,32 @@ static void ena_fw_reset_device(struct work_struct *work)
        rtnl_unlock();
 }
 
-static int check_missing_comp_in_queue(struct ena_adapter *adapter,
-                                      struct ena_ring *tx_ring)
+static int check_for_rx_interrupt_queue(struct ena_adapter *adapter,
+                                       struct ena_ring *rx_ring)
+{
+       if (likely(rx_ring->first_interrupt))
+               return 0;
+
+       if (ena_com_cq_empty(rx_ring->ena_com_io_cq))
+               return 0;
+
+       rx_ring->no_interrupt_event_cnt++;
+
+       if (rx_ring->no_interrupt_event_cnt == ENA_MAX_NO_INTERRUPT_ITERATIONS) {
+               netif_err(adapter, rx_err, adapter->netdev,
+                         "Potential MSIX issue on Rx side Queue = %d. Reset the device\n",
+                         rx_ring->qid);
+               adapter->reset_reason = ENA_REGS_RESET_MISS_INTERRUPT;
+               smp_mb__before_atomic();
+               set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+               return -EIO;
+       }
+
+       return 0;
+}
+
+static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
+                                         struct ena_ring *tx_ring)
 {
        struct ena_tx_buffer *tx_buf;
        unsigned long last_jiffies;
@@ -2674,8 +2703,27 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter,
        for (i = 0; i < tx_ring->ring_size; i++) {
                tx_buf = &tx_ring->tx_buffer_info[i];
                last_jiffies = tx_buf->last_jiffies;
-               if (unlikely(last_jiffies &&
-                            time_is_before_jiffies(last_jiffies + adapter->missing_tx_completion_to))) {
+
+               if (last_jiffies == 0)
+                       /* no pending Tx at this location */
+                       continue;
+
+               if (unlikely(!tx_ring->first_interrupt && time_is_before_jiffies(last_jiffies +
+                            2 * adapter->missing_tx_completion_to))) {
+                       /* If after graceful period interrupt is still not
+                        * received, we schedule a reset
+                        */
+                       netif_err(adapter, tx_err, adapter->netdev,
+                                 "Potential MSIX issue on Tx side Queue = %d. Reset the device\n",
+                                 tx_ring->qid);
+                       adapter->reset_reason = ENA_REGS_RESET_MISS_INTERRUPT;
+                       smp_mb__before_atomic();
+                       set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+                       return -EIO;
+               }
+
+               if (unlikely(time_is_before_jiffies(last_jiffies +
+                               adapter->missing_tx_completion_to))) {
                        if (!tx_buf->print_once)
                                netif_notice(adapter, tx_err, adapter->netdev,
                                             "Found a Tx that wasn't completed on time, qid %d, index %d.\n",
@@ -2704,9 +2752,10 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter,
        return rc;
 }
 
-static void check_for_missing_tx_completions(struct ena_adapter *adapter)
+static void check_for_missing_completions(struct ena_adapter *adapter)
 {
        struct ena_ring *tx_ring;
+       struct ena_ring *rx_ring;
        int i, budget, rc;
 
        /* Make sure the driver doesn't turn the device in other process */
@@ -2725,8 +2774,13 @@ static void check_for_missing_tx_completions(struct ena_adapter *adapter)
 
        for (i = adapter->last_monitored_tx_qid; i < adapter->num_queues; i++) {
                tx_ring = &adapter->tx_ring[i];
+               rx_ring = &adapter->rx_ring[i];
+
+               rc = check_missing_comp_in_tx_queue(adapter, tx_ring);
+               if (unlikely(rc))
+                       return;
 
-               rc = check_missing_comp_in_queue(adapter, tx_ring);
+               rc = check_for_rx_interrupt_queue(adapter, rx_ring);
                if (unlikely(rc))
                        return;
 
@@ -2885,7 +2939,7 @@ static void ena_timer_service(struct timer_list *t)
 
        check_for_admin_com_state(adapter);
 
-       check_for_missing_tx_completions(adapter);
+       check_for_missing_completions(adapter);
 
        check_for_empty_rx_ring(adapter);
 

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 3bbc003871de401baa30cc47439969b0f49d732b..734ff2e84494ad65d3893899bb466592ef7acdc7 100644 (file)
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -122,6 +122,7 @@
  * We wait for 6 sec just to be on the safe side.
  */
 #define ENA_DEVICE_KALIVE_TIMEOUT      (6 * HZ)
+#define ENA_MAX_NO_INTERRUPT_ITERATIONS 3
 
 #define ENA_MMIO_DISABLE_REG_READ      BIT(0)
 
@@ -236,6 +237,9 @@ struct ena_ring {
        /* The maximum header length the device can handle */
        u8 tx_max_header_size;
 
+       bool first_interrupt;
+       u16 no_interrupt_event_cnt;
+
        /* cpu for TPH */
        int cpu;
         /* number of tx/rx_buffer_info's entries */

diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
index 9aec43c5bba8b31bc04416198401499526e747d2..48ca97fbe7bc6b42f2fd70ab4cd4d4d481106cea 100644 (file)
--- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
@@ -60,6 +60,8 @@ enum ena_regs_reset_reason_types {
        ENA_REGS_RESET_USER_TRIGGER             = 12,
 
        ENA_REGS_RESET_GENERIC                  = 13,
+
+       ENA_REGS_RESET_MISS_INTERRUPT           = 14,
 };
 
 /* ena_registers offsets */