netdev - [Patch v1 net-next 05/10] net: ena: add jiffies of last napi call to stats

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20210608160118.3767932-6-shayagr@amazon.com>
Date:   Tue, 8 Jun 2021 19:01:13 +0300
From:   Shay Agroskin <shayagr@...zon.com>
To:     David Miller <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>, <netdev@...r.kernel.org>
CC:     Shay Agroskin <shayagr@...zon.com>,
        "Woodhouse, David" <dwmw@...zon.com>,
        "Machulsky, Zorik" <zorik@...zon.com>,
        "Matushevsky, Alexander" <matua@...zon.com>,
        Saeed Bshara <saeedb@...zon.com>,
        "Wilson, Matt" <msw@...zon.com>,
        "Liguori, Anthony" <aliguori@...zon.com>,
        "Bshara, Nafea" <nafea@...zon.com>,
        "Belgazal, Netanel" <netanel@...zon.com>,
        "Saidi, Ali" <alisaidi@...zon.com>,
        "Herrenschmidt, Benjamin" <benh@...zon.com>,
        "Kiyanovski, Arthur" <akiyano@...zon.com>,
        "Dagan, Noam" <ndagan@...zon.com>,
        Sameeh Jubran <sameehj@...zon.com>
Subject: [Patch v1 net-next 05/10] net: ena: add jiffies of last napi call to stats

There are instances when we want to know when the last napi was
called for debugging.

On stuck / heavy loaded CPUs, the ena napi handler might not be
called for a long period of time. This stat can help us to
determine how much time passed since the last execution of napi.

Signed-off-by: Sameeh Jubran <sameehj@...zon.com>
Signed-off-by: Shay Agroskin <shayagr@...zon.com>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 28 ++++++++++++++------
 drivers/net/ethernet/amazon/ena/ena_netdev.h |  1 +
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index d7bc4f45e5df..f013fa312937 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -228,6 +228,7 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget)
 	xdp_ring->tx_stats.napi_comp += napi_comp_call;
 	xdp_ring->tx_stats.tx_poll++;
 	u64_stats_update_end(&xdp_ring->syncp);
+	xdp_ring->tx_stats.last_napi_jiffies = jiffies;
 
 	return ret;
 }
@@ -1989,6 +1990,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	tx_ring->tx_stats.tx_poll++;
 	u64_stats_update_end(&tx_ring->syncp);
 
+	tx_ring->tx_stats.last_napi_jiffies = jiffies;
+
 	return ret;
 }
 
@@ -3695,6 +3698,9 @@ 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);
+	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;
 	u32 missed_tx = 0;
@@ -3708,9 +3714,10 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 			/* no pending Tx at this location */
 			continue;
 
-		if (unlikely(!READ_ONCE(ena_napi->first_interrupt) &&
-			time_is_before_jiffies(last_jiffies + 2 *
-				adapter->missing_tx_completion_to))) {
+		is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies +
+			 2 * adapter->missing_tx_completion_to);
+
+		if (unlikely(!READ_ONCE(ena_napi->first_interrupt) && is_tx_comp_time_expired)) {
 			/* If after graceful period interrupt is still not
 			 * received, we schedule a reset
 			 */
@@ -3723,12 +3730,17 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 			return -EIO;
 		}
 
-		if (unlikely(time_is_before_jiffies(last_jiffies +
-				adapter->missing_tx_completion_to))) {
-			if (!tx_buf->print_once)
+		is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies +
+			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.\n",
-					     tx_ring->qid, i);
+					     "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);
+			}
 
 			tx_buf->print_once = 1;
 			missed_tx++;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 834348fcdf3c..0c39fc2fa345 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -206,6 +206,7 @@ struct ena_stats_tx {
 	u64 llq_buffer_copy;
 	u64 missed_tx;
 	u64 unmask_interrupt;
+	u64 last_napi_jiffies;
 };
 
 struct ena_stats_rx {
-- 
2.25.1