[PATCH net 0/4] gve: Fixes for issues discovered via net selftests

[PATCH net 0/4] gve: Fixes for issues discovered via net selftests

[Harshitha Ramamurthy]

From: Pin-yen Lin <treapking@google.com>

This patch series addresses several issues in the gve driver. All four of these
fixes were uncovered by running the net selftests.

The series includes the following changes:

- Patch 1 adds NULL pointer checks for the per-queue statistics code to
  prevent crashes when the rings are queried while the link is down. This
  was discovered by the drivers/net/stats.py selftest.
- Patch 2 fixes an issue where interface stats would go backwards when the
  interface was brought down or its configuration was adjusted. This was
  also discovered by the drivers/net/stats.py selftest.
- Patch 3 ensures the driver falls back to the default minimum ring size if
  the corresponding device option values are exposed as 0. This prevents
  userspace from configuring unexpectedly small ring sizes. This was
  discovered by the drivers/net/ring_reconfig.py selftest.
- Patch 4 makes sure ethtool configuration modifications are done
  synchronously before returning to the userspace. This was discovered by
  the drivers/net/ping.py selftest.

Debarghya Kundu (2):
  gve: Add NULL pointer checks for per-queue statistics
  gve: Fix backward stats when interface goes down or configuration is
    adjusted

Pin-yen Lin (2):
  gve: Use default min ring size when device option values are 0
  gve: Make ethtool config changes synchronous

 drivers/net/ethernet/google/gve/gve.h        |   6 +
 drivers/net/ethernet/google/gve/gve_adminq.c |   4 +-
 drivers/net/ethernet/google/gve/gve_main.c   | 128 +++++++++++++------
 3 files changed, 100 insertions(+), 38 deletions(-)

-- 
2.54.0.rc0.605.g598a273b03-goog

base-commit: 2dddb34dd0d07b01fa770eca89480a4da4f13153
branch: gve-misc-fixes

[PATCH net 1/4] gve: Add NULL pointer checks for per-queue statistics

[Harshitha Ramamurthy]

From: Debarghya Kundu <debarghyak@google.com>

gve_get_[tx/rx]_queue_stats references the [tx/rx] null rings when the
link is down. Add NULL pointer checks to guard this.

This was discovered by drivers/net/stats.py selftest.

Cc: stable@vger.kernel.org
Fixes: 2e5e0932dff5 ("gve: add support for basic queue stats")
Signed-off-by: Debarghya Kundu <debarghyak@google.com>
Signed-off-by: Pin-yen Lin <treapking@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
---
 drivers/net/ethernet/google/gve/gve_main.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 0ee864b0afe0..675382e9756c 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -2705,9 +2705,13 @@ static void gve_get_rx_queue_stats(struct net_device *dev, int idx,
 				   struct netdev_queue_stats_rx *rx_stats)
 {
 	struct gve_priv *priv = netdev_priv(dev);
-	struct gve_rx_ring *rx = &priv->rx[idx];
+	struct gve_rx_ring *rx;
 	unsigned int start;
 
+	if (!priv->rx)
+		return;
+	rx = &priv->rx[idx];
+
 	do {
 		start = u64_stats_fetch_begin(&rx->statss);
 		rx_stats->packets = rx->rpackets;
@@ -2721,9 +2725,13 @@ static void gve_get_tx_queue_stats(struct net_device *dev, int idx,
 				   struct netdev_queue_stats_tx *tx_stats)
 {
 	struct gve_priv *priv = netdev_priv(dev);
-	struct gve_tx_ring *tx = &priv->tx[idx];
+	struct gve_tx_ring *tx;
 	unsigned int start;
 
+	if (!priv->tx)
+		return;
+	tx = &priv->tx[idx];
+
 	do {
 		start = u64_stats_fetch_begin(&tx->statss);
 		tx_stats->packets = tx->pkt_done;
-- 
2.54.0.rc0.605.g598a273b03-goog

[PATCH net 2/4] gve: Fix backward stats when interface goes down or configuration is adjusted

[Harshitha Ramamurthy]

From: Debarghya Kundu <debarghyak@google.com>

gve_get_base_stats() sets all the stats to 0, so the stats go backwards
when interface goes down or configuration is adjusted.

Fix this by persisting baseline stats across interface down.

This was discovered by drivers/net/stats.py selftest.

Cc: stable@vger.kernel.org
Fixes: 2e5e0932dff5 ("gve: add support for basic queue stats")
Signed-off-by: Debarghya Kundu <debarghyak@google.com>
Signed-off-by: Pin-yen Lin <treapking@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
---
 drivers/net/ethernet/google/gve/gve.h      |  6 ++
 drivers/net/ethernet/google/gve/gve_main.c | 64 +++++++++++++++++++---
 2 files changed, 63 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index cbdf3a842cfe..ff7797043908 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -794,6 +794,10 @@ struct gve_ptp {
 	struct gve_priv *priv;
 };
 
+struct gve_ring_err_stats {
+	u64 rx_alloc_fails;
+};
+
 struct gve_priv {
 	struct net_device *dev;
 	struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */
@@ -882,6 +886,8 @@ struct gve_priv {
 	unsigned long service_task_flags;
 	unsigned long state_flags;
 
+	struct gve_ring_err_stats base_ring_err_stats;
+	struct rtnl_link_stats64 base_net_stats;
 	struct gve_stats_report *stats_report;
 	u64 stats_report_len;
 	dma_addr_t stats_report_bus; /* dma address for the stats report */
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 675382e9756c..8617782791e0 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -105,9 +105,22 @@ static netdev_tx_t gve_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return gve_tx_dqo(skb, dev);
 }
 
-static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
+static void gve_add_base_stats(struct gve_priv *priv,
+			       struct rtnl_link_stats64 *s)
+{
+	struct rtnl_link_stats64 *base_stats = &priv->base_net_stats;
+
+	s->rx_packets += base_stats->rx_packets;
+	s->rx_bytes += base_stats->rx_bytes;
+	s->rx_dropped += base_stats->rx_dropped;
+	s->tx_packets += base_stats->tx_packets;
+	s->tx_bytes += base_stats->tx_bytes;
+	s->tx_dropped += base_stats->tx_dropped;
+}
+
+static void gve_get_ring_stats(struct gve_priv *priv,
+			       struct rtnl_link_stats64 *s)
 {
-	struct gve_priv *priv = netdev_priv(dev);
 	unsigned int start;
 	u64 packets, bytes;
 	int num_tx_queues;
@@ -142,6 +155,14 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 	}
 }
 
+static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+
+	gve_get_ring_stats(priv, s);
+	gve_add_base_stats(priv, s);
+}
+
 static int gve_alloc_flow_rule_caches(struct gve_priv *priv)
 {
 	struct gve_flow_rules_cache *flow_rules_cache = &priv->flow_rules_cache;
@@ -1493,6 +1514,23 @@ static int gve_queues_stop(struct gve_priv *priv)
 	return gve_reset_recovery(priv, false);
 }
 
+static void gve_get_ring_err_stats(struct gve_priv *priv,
+				   struct gve_ring_err_stats *err_stats)
+{
+	int ring;
+
+	for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
+		unsigned int start;
+		struct gve_rx_ring *rx = &priv->rx[ring];
+
+		do {
+			start = u64_stats_fetch_begin(&rx->statss);
+			err_stats->rx_alloc_fails +=
+				rx->rx_skb_alloc_fail + rx->rx_buf_alloc_fail;
+		} while (u64_stats_fetch_retry(&rx->statss, start));
+	}
+}
+
 static int gve_close(struct net_device *dev)
 {
 	struct gve_priv *priv = netdev_priv(dev);
@@ -1502,6 +1540,10 @@ static int gve_close(struct net_device *dev)
 	if (err)
 		return err;
 
+	/* Save ring queue and err stats before closing the interface */
+	gve_get_ring_stats(priv, &priv->base_net_stats);
+	gve_get_ring_err_stats(priv, &priv->base_ring_err_stats);
+
 	gve_queues_mem_remove(priv);
 	return 0;
 }
@@ -2743,12 +2785,20 @@ static void gve_get_base_stats(struct net_device *dev,
 			       struct netdev_queue_stats_rx *rx,
 			       struct netdev_queue_stats_tx *tx)
 {
-	rx->packets = 0;
-	rx->bytes = 0;
-	rx->alloc_fail = 0;
+	const struct gve_ring_err_stats *base_err_stats;
+	const struct rtnl_link_stats64 *base_stats;
+	struct gve_priv *priv;
+
+	priv = netdev_priv(dev);
+	base_stats = &priv->base_net_stats;
+	base_err_stats = &priv->base_ring_err_stats;
+
+	rx->packets = base_stats->rx_packets;
+	rx->bytes = base_stats->rx_bytes;
+	rx->alloc_fail = base_err_stats->rx_alloc_fails;
 
-	tx->packets = 0;
-	tx->bytes = 0;
+	tx->packets = base_stats->tx_packets;
+	tx->bytes = base_stats->tx_bytes;
 }
 
 static const struct netdev_stat_ops gve_stat_ops = {
-- 
2.54.0.rc0.605.g598a273b03-goog

[PATCH net 3/4] gve: Use default min ring size when device option values are 0

[Harshitha Ramamurthy]

From: Pin-yen Lin <treapking@google.com>

On gvnic devices that support reporting minimum ring sizes, the device
option always includes the min_(rx|tx)_ring_size fields, and the values
will be 0 if they are not configured to be exposed. This makes the
driver allow unexpected small ring size configurations from the
userspace.

Use the default ring size in the driver if the min ring sizes from the
device option are 0.

This was discovered by drivers/net/ring_reconfig.py selftest.

Cc: stable@vger.kernel.org
Fixes: ed4fb326947d ("gve: add support to read ring size ranges from the device")
Reviewed-by: Joshua Washington <joshwash@google.com>
Reviewed-by: Jordan Rhee <jordanrhee@google.com>
Signed-off-by: Pin-yen Lin <treapking@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
---
 drivers/net/ethernet/google/gve/gve_adminq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index b72cc0fa2ba2..57d898f6fa82 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -189,7 +189,9 @@ void gve_parse_device_option(struct gve_priv *priv,
 		*dev_op_modify_ring = (void *)(option + 1);
 
 		/* device has not provided min ring size */
-		if (option_length == GVE_DEVICE_OPTION_NO_MIN_RING_SIZE)
+		if (option_length == GVE_DEVICE_OPTION_NO_MIN_RING_SIZE ||
+		    be16_to_cpu((*dev_op_modify_ring)->min_rx_ring_size) == 0 ||
+		    be16_to_cpu((*dev_op_modify_ring)->min_tx_ring_size) == 0)
 			priv->default_min_ring_size = true;
 		break;
 	case GVE_DEV_OPT_ID_FLOW_STEERING:
-- 
2.54.0.rc0.605.g598a273b03-goog

[PATCH net 4/4] gve: Make ethtool config changes synchronous

[Harshitha Ramamurthy]

From: Pin-yen Lin <treapking@google.com>

When modifying device features via ethtool, the driver queues the
carrier status update to its workqueue (gve_wq). This leads to a
short link-down state after running the ethtool command.

Use `gve_turnup_and_check_status()` instead of `gve_turnup()` in
`gve_queues_start()` to update the carrier status before returning to
the userspace.

This was discovered by drivers/net/ping.py selftest. The test calls
ping command right after an ethtool configuration, but the interface
could be down without this fix.

Cc: stable@vger.kernel.org
Fixes: 5f08cd3d6423 ("gve: Alloc before freeing when adjusting queues")
Reviewed-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Pin-yen Lin <treapking@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
---
 drivers/net/ethernet/google/gve/gve_main.c | 56 +++++++++++-----------
 1 file changed, 28 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 8617782791e0..d3b4bec38de5 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -1374,6 +1374,33 @@ static void gve_queues_mem_remove(struct gve_priv *priv)
 	priv->rx = NULL;
 }
 
+static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
+{
+	if (!gve_get_napi_enabled(priv))
+		return;
+
+	if (link_status == netif_carrier_ok(priv->dev))
+		return;
+
+	if (link_status) {
+		netdev_info(priv->dev, "Device link is up.\n");
+		netif_carrier_on(priv->dev);
+	} else {
+		netdev_info(priv->dev, "Device link is down.\n");
+		netif_carrier_off(priv->dev);
+	}
+}
+
+static void gve_turnup_and_check_status(struct gve_priv *priv)
+{
+	u32 status;
+
+	gve_turnup(priv);
+	status = ioread32be(&priv->reg_bar0->device_status);
+	gve_handle_link_status(priv,
+			       GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
+}
+
 /* The passed-in queue memory is stored into priv and the queues are made live.
  * No memory is allocated. Passed-in memory is freed on errors.
  */
@@ -1434,8 +1461,7 @@ static int gve_queues_start(struct gve_priv *priv,
 			  round_jiffies(jiffies +
 				msecs_to_jiffies(priv->stats_report_timer_period)));
 
-	gve_turnup(priv);
-	queue_work(priv->gve_wq, &priv->service_task);
+	gve_turnup_and_check_status(priv);
 	priv->interface_up_cnt++;
 	return 0;
 
@@ -1548,23 +1574,6 @@ static int gve_close(struct net_device *dev)
 	return 0;
 }
 
-static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
-{
-	if (!gve_get_napi_enabled(priv))
-		return;
-
-	if (link_status == netif_carrier_ok(priv->dev))
-		return;
-
-	if (link_status) {
-		netdev_info(priv->dev, "Device link is up.\n");
-		netif_carrier_on(priv->dev);
-	} else {
-		netdev_info(priv->dev, "Device link is down.\n");
-		netif_carrier_off(priv->dev);
-	}
-}
-
 static int gve_configure_rings_xdp(struct gve_priv *priv,
 				   u16 num_xdp_rings)
 {
@@ -2039,15 +2048,6 @@ static void gve_turnup(struct gve_priv *priv)
 	gve_set_napi_enabled(priv);
 }
 
-static void gve_turnup_and_check_status(struct gve_priv *priv)
-{
-	u32 status;
-
-	gve_turnup(priv);
-	status = ioread32be(&priv->reg_bar0->device_status);
-	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
-}
-
 static struct gve_notify_block *gve_get_tx_notify_block(struct gve_priv *priv,
 							unsigned int txqueue)
 {
-- 
2.54.0.rc0.605.g598a273b03-goog