diff mbox series

[net-next,v2,08/10] gve: Account for stopped queues when reading NIC stats

Message ID 20240501232549.1327174-9-shailend@google.com (mailing list archive)
State Accepted
Commit af9bcf910b1f86244f39e15e701b2dc564b469a6
Delegated to: Netdev Maintainers
Headers show
Series gve: Implement queue api | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 926 this patch: 926
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 9 of 9 maintainers
netdev/build_clang success Errors and warnings before: 940 this patch: 940
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 937 this patch: 937
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 107 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-05-05--03-00 (tests: 1003)

Commit Message

Shailend Chand May 1, 2024, 11:25 p.m. UTC 
We now account for the fact that the NIC might send us stats for a
subset of queues. Without this change, gve_get_ethtool_stats might make
an invalid access on the priv->stats_report->stats array.

Tested-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Shailend Chand <shailend@google.com>
---
 drivers/net/ethernet/google/gve/gve_ethtool.c | 41 ++++++++++++++++---
 1 file changed, 35 insertions(+), 6 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index bd7632eed776..a606670a9a39 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -8,6 +8,7 @@ 
 #include "gve.h"
 #include "gve_adminq.h"
 #include "gve_dqo.h"
+#include "gve_utils.h"
 
 static void gve_get_drvinfo(struct net_device *netdev,
 			    struct ethtool_drvinfo *info)
@@ -165,6 +166,8 @@  gve_get_ethtool_stats(struct net_device *netdev,
 	struct stats *report_stats;
 	int *rx_qid_to_stats_idx;
 	int *tx_qid_to_stats_idx;
+	int num_stopped_rxqs = 0;
+	int num_stopped_txqs = 0;
 	struct gve_priv *priv;
 	bool skip_nic_stats;
 	unsigned int start;
@@ -181,12 +184,23 @@  gve_get_ethtool_stats(struct net_device *netdev,
 					    sizeof(int), GFP_KERNEL);
 	if (!rx_qid_to_stats_idx)
 		return;
+	for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
+		rx_qid_to_stats_idx[ring] = -1;
+		if (!gve_rx_was_added_to_block(priv, ring))
+			num_stopped_rxqs++;
+	}
 	tx_qid_to_stats_idx = kmalloc_array(num_tx_queues,
 					    sizeof(int), GFP_KERNEL);
 	if (!tx_qid_to_stats_idx) {
 		kfree(rx_qid_to_stats_idx);
 		return;
 	}
+	for (ring = 0; ring < num_tx_queues; ring++) {
+		tx_qid_to_stats_idx[ring] = -1;
+		if (!gve_tx_was_added_to_block(priv, ring))
+			num_stopped_txqs++;
+	}
+
 	for (rx_pkts = 0, rx_bytes = 0, rx_hsplit_pkt = 0,
 	     rx_skb_alloc_fail = 0, rx_buf_alloc_fail = 0,
 	     rx_desc_err_dropped_pkt = 0, rx_hsplit_unsplit_pkt = 0,
@@ -260,7 +274,13 @@  gve_get_ethtool_stats(struct net_device *netdev,
 	/* For rx cross-reporting stats, start from nic rx stats in report */
 	base_stats_idx = GVE_TX_STATS_REPORT_NUM * num_tx_queues +
 		GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues;
-	max_stats_idx = NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues +
+	/* The boundary between driver stats and NIC stats shifts if there are
+	 * stopped queues.
+	 */
+	base_stats_idx += NIC_RX_STATS_REPORT_NUM * num_stopped_rxqs +
+		NIC_TX_STATS_REPORT_NUM * num_stopped_txqs;
+	max_stats_idx = NIC_RX_STATS_REPORT_NUM *
+		(priv->rx_cfg.num_queues - num_stopped_rxqs) +
 		base_stats_idx;
 	/* Preprocess the stats report for rx, map queue id to start index */
 	skip_nic_stats = false;
@@ -274,6 +294,10 @@  gve_get_ethtool_stats(struct net_device *netdev,
 			skip_nic_stats = true;
 			break;
 		}
+		if (queue_id < 0 || queue_id >= priv->rx_cfg.num_queues) {
+			net_err_ratelimited("Invalid rxq id in NIC stats\n");
+			continue;
+		}
 		rx_qid_to_stats_idx[queue_id] = stats_idx;
 	}
 	/* walk RX rings */
@@ -308,11 +332,11 @@  gve_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = rx->rx_copybreak_pkt;
 			data[i++] = rx->rx_copied_pkt;
 			/* stats from NIC */
-			if (skip_nic_stats) {
+			stats_idx = rx_qid_to_stats_idx[ring];
+			if (skip_nic_stats || stats_idx < 0) {
 				/* skip NIC rx stats */
 				i += NIC_RX_STATS_REPORT_NUM;
 			} else {
-				stats_idx = rx_qid_to_stats_idx[ring];
 				for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) {
 					u64 value =
 						be64_to_cpu(report_stats[stats_idx + j].value);
@@ -338,7 +362,8 @@  gve_get_ethtool_stats(struct net_device *netdev,
 
 	/* For tx cross-reporting stats, start from nic tx stats in report */
 	base_stats_idx = max_stats_idx;
-	max_stats_idx = NIC_TX_STATS_REPORT_NUM * num_tx_queues +
+	max_stats_idx = NIC_TX_STATS_REPORT_NUM *
+		(num_tx_queues - num_stopped_txqs) +
 		max_stats_idx;
 	/* Preprocess the stats report for tx, map queue id to start index */
 	skip_nic_stats = false;
@@ -352,6 +377,10 @@  gve_get_ethtool_stats(struct net_device *netdev,
 			skip_nic_stats = true;
 			break;
 		}
+		if (queue_id < 0 || queue_id >= num_tx_queues) {
+			net_err_ratelimited("Invalid txq id in NIC stats\n");
+			continue;
+		}
 		tx_qid_to_stats_idx[queue_id] = stats_idx;
 	}
 	/* walk TX rings */
@@ -383,11 +412,11 @@  gve_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = gve_tx_load_event_counter(priv, tx);
 			data[i++] = tx->dma_mapping_error;
 			/* stats from NIC */
-			if (skip_nic_stats) {
+			stats_idx = tx_qid_to_stats_idx[ring];
+			if (skip_nic_stats || stats_idx < 0) {
 				/* skip NIC tx stats */
 				i += NIC_TX_STATS_REPORT_NUM;
 			} else {
-				stats_idx = tx_qid_to_stats_idx[ring];
 				for (j = 0; j < NIC_TX_STATS_REPORT_NUM; j++) {
 					u64 value =
 						be64_to_cpu(report_stats[stats_idx + j].value);