* [PATCH net-next 1/2] net: ena: add detection and recovery mechanism for handling missed/misrouted MSI-X
2017-12-28 21:31 [PATCH net-next 1/2] update ENA driver to version 1.5.0 netanel
@ 2017-12-28 21:31 ` netanel
2017-12-28 21:31 ` [PATCH net-next 2/2] net: ena: increase ena driver version to 1.5.0 netanel
2018-01-02 19:35 ` [PATCH net-next 1/2] update ENA driver to version 1.5.0 David Miller
2 siblings, 0 replies; 4+ messages in thread
From: netanel @ 2017-12-28 21:31 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys, gtzalik
From: Netanel Belgazal <netanel@amazon.com>
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>
---
drivers/net/ethernet/amazon/ena/ena_eth_com.c | 12 +++++
drivers/net/ethernet/amazon/ena/ena_eth_com.h | 2 +
drivers/net/ethernet/amazon/ena/ena_netdev.c | 68 ++++++++++++++++++++++---
drivers/net/ethernet/amazon/ena/ena_netdev.h | 4 ++
drivers/net/ethernet/amazon/ena/ena_regs_defs.h | 2 +
5 files changed, 81 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index b11e573ad57a..04ed2b57ff20 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -504,3 +504,15 @@ 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 bb53c3a4f8e9..2f7657227cfe 100644
--- 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 97c5a89a9cf7..a6f283232cb7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -158,6 +158,8 @@ 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);
}
@@ -1274,6 +1276,9 @@ 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;
@@ -2648,8 +2653,32 @@ 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;
@@ -2659,8 +2688,27 @@ 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",
@@ -2689,9 +2737,10 @@ 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 */
@@ -2710,8 +2759,13 @@ 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;
@@ -2870,7 +2924,7 @@ 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 3bbc003871de..734ff2e84494 100644
--- 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 9aec43c5bba8..48ca97fbe7bc 100644
--- 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 */
--
2.7.3.AMZN
^ permalink raw reply related [flat|nested] 4+ messages in thread