* [PATCH net-next v3 1/5] veth: refactor NAPI enable paths
2026-11-15 19:35 [PATCH net-next v3 0/5] veth: link RX queues to their NAPI instances Tianyi Gao
@ 2026-11-15 19:35 ` Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 2/5] veth: link RX queues to their NAPI instances Tianyi Gao
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Tianyi Gao @ 2026-11-15 19:35 UTC (permalink / raw)
To: netdev
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, toke, lorenzo,
horms, shuah, ast, daniel, hawk, john.fastabend, sdf, joe,
linux-kselftest, bpf, kernel-team, tianyi.gao, Tianyi Gao
veth_enable_xdp_range() adds the NAPI instances itself, only to pass
rq->xdp_napi.napi_id as the napi_id argument of xdp_rxq_info_reg(). That
argument is unused in __xdp_rxq_info_reg() since commit 5ef44b3cb43b
("xsk: Bring back busy polling support"). Pass 0 instead, as ena, bnxt
and fec already do.
veth_enable_xdp_range() then no longer needs the NAPI instances. Move
netif_napi_add() from it and from veth_napi_enable_range() into
__veth_napi_enable_range(). Add the instances after the allocations
that can fail, and before the loop that enables them. Drop the
napi_already_on and delete_napi arguments.
veth_napi_enable_range() and veth_napi_enable() are then trivial
wrappers. Remove them, and rename __veth_napi_enable_range() and
__veth_napi_enable() to veth_napi_enable_range() and veth_napi_enable().
Signed-off-by: Tianyi Gao <tianyi@cloudflare.com>
---
Sashiko [1] pointed out that v2 added and enabled each NAPI instance in
the same loop, so a failed kthread creation could leave earlier instances
threaded and later ones not. v3 adds all instances before it enables any,
as the old code did, so such a failure turns off threaded mode for all.
[1] https://lore.kernel.org/all/179470883254.2199510.15270739408094114749@kernel.org/
---
drivers/net/veth.c | 82 +++++++++++-----------------------------------
1 file changed, 20 insertions(+), 62 deletions(-)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 0539b3661793..3cbedb8bad53 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1037,7 +1037,7 @@ static int veth_create_page_pool(struct veth_rq *rq)
return 0;
}
-static int __veth_napi_enable_range(struct net_device *dev, int start, int end)
+static int veth_napi_enable_range(struct net_device *dev, int start, int end)
{
struct veth_priv *priv = netdev_priv(dev);
int err, i;
@@ -1056,6 +1056,9 @@ static int __veth_napi_enable_range(struct net_device *dev, int start, int end)
goto err_xdp_ring;
}
+ for (i = start; i < end; i++)
+ netif_napi_add(dev, &priv->rq[i].xdp_napi, veth_poll);
+
for (i = start; i < end; i++) {
struct veth_rq *rq = &priv->rq[i];
@@ -1079,9 +1082,9 @@ static int __veth_napi_enable_range(struct net_device *dev, int start, int end)
return err;
}
-static int __veth_napi_enable(struct net_device *dev)
+static int veth_napi_enable(struct net_device *dev)
{
- return __veth_napi_enable_range(dev, 0, dev->real_num_rx_queues);
+ return veth_napi_enable_range(dev, 0, dev->real_num_rx_queues);
}
static void veth_napi_del_range(struct net_device *dev, int start, int end)
@@ -1122,8 +1125,7 @@ static bool veth_gro_requested(const struct net_device *dev)
return !!(dev->wanted_features & NETIF_F_GRO);
}
-static int veth_enable_xdp_range(struct net_device *dev, int start, int end,
- bool napi_already_on)
+static int veth_enable_xdp_range(struct net_device *dev, int start, int end)
{
struct veth_priv *priv = netdev_priv(dev);
int err, i;
@@ -1131,9 +1133,7 @@ static int veth_enable_xdp_range(struct net_device *dev, int start, int end,
for (i = start; i < end; i++) {
struct veth_rq *rq = &priv->rq[i];
- if (!napi_already_on)
- netif_napi_add(dev, &rq->xdp_napi, veth_poll);
- err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id);
+ err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, 0);
if (err < 0)
goto err_rxq_reg;
@@ -1151,21 +1151,13 @@ static int veth_enable_xdp_range(struct net_device *dev, int start, int end,
err_reg_mem:
xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
err_rxq_reg:
- if (!napi_already_on)
- netif_napi_del(&priv->rq[i].xdp_napi);
- for (i--; i >= start; i--) {
- struct veth_rq *rq = &priv->rq[i];
-
- xdp_rxq_info_unreg(&rq->xdp_rxq);
- if (!napi_already_on)
- netif_napi_del(&rq->xdp_napi);
- }
+ for (i--; i >= start; i--)
+ xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
return err;
}
-static void veth_disable_xdp_range(struct net_device *dev, int start, int end,
- bool delete_napi)
+static void veth_disable_xdp_range(struct net_device *dev, int start, int end)
{
struct veth_priv *priv = netdev_priv(dev);
int i;
@@ -1175,9 +1167,6 @@ static void veth_disable_xdp_range(struct net_device *dev, int start, int end,
rq->xdp_rxq.mem = rq->xdp_mem;
xdp_rxq_info_unreg(&rq->xdp_rxq);
-
- if (delete_napi)
- netif_napi_del(&rq->xdp_napi);
}
}
@@ -1188,14 +1177,15 @@ static int veth_enable_xdp(struct net_device *dev)
int err, i;
if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) {
- err = veth_enable_xdp_range(dev, 0, dev->real_num_rx_queues, napi_already_on);
+ err = veth_enable_xdp_range(dev, 0, dev->real_num_rx_queues);
if (err)
return err;
if (!napi_already_on) {
- err = __veth_napi_enable(dev);
+ err = veth_napi_enable(dev);
if (err) {
- veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true);
+ veth_disable_xdp_range(dev, 0,
+ dev->real_num_rx_queues);
return err;
}
}
@@ -1220,35 +1210,7 @@ static void veth_disable_xdp(struct net_device *dev)
if (!netif_running(dev) || !veth_gro_requested(dev))
veth_napi_del(dev);
- veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false);
-}
-
-static int veth_napi_enable_range(struct net_device *dev, int start, int end)
-{
- struct veth_priv *priv = netdev_priv(dev);
- int err, i;
-
- for (i = start; i < end; i++) {
- struct veth_rq *rq = &priv->rq[i];
-
- netif_napi_add(dev, &rq->xdp_napi, veth_poll);
- }
-
- err = __veth_napi_enable_range(dev, start, end);
- if (err) {
- for (i = start; i < end; i++) {
- struct veth_rq *rq = &priv->rq[i];
-
- netif_napi_del(&rq->xdp_napi);
- }
- return err;
- }
- return err;
-}
-
-static int veth_napi_enable(struct net_device *dev)
-{
- return veth_napi_enable_range(dev, 0, dev->real_num_rx_queues);
+ veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues);
}
static void veth_disable_range_safe(struct net_device *dev, int start, int end)
@@ -1260,7 +1222,7 @@ static void veth_disable_range_safe(struct net_device *dev, int start, int end)
if (priv->_xdp_prog) {
veth_napi_del_range(dev, start, end);
- veth_disable_xdp_range(dev, start, end, false);
+ veth_disable_xdp_range(dev, start, end);
} else if (veth_gro_requested(dev)) {
veth_napi_del_range(dev, start, end);
}
@@ -1275,17 +1237,13 @@ static int veth_enable_range_safe(struct net_device *dev, int start, int end)
return 0;
if (priv->_xdp_prog) {
- /* these channels are freshly initialized, napi is not on there even
- * when GRO is requeste
- */
- err = veth_enable_xdp_range(dev, start, end, false);
+ err = veth_enable_xdp_range(dev, start, end);
if (err)
return err;
- err = __veth_napi_enable_range(dev, start, end);
+ err = veth_napi_enable_range(dev, start, end);
if (err) {
- /* on error always delete the newly added napis */
- veth_disable_xdp_range(dev, start, end, true);
+ veth_disable_xdp_range(dev, start, end);
return err;
}
} else if (veth_gro_requested(dev)) {
--
2.56.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH net-next v3 2/5] veth: link RX queues to their NAPI instances
2026-11-15 19:35 [PATCH net-next v3 0/5] veth: link RX queues to their NAPI instances Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 1/5] veth: refactor NAPI enable paths Tianyi Gao
@ 2026-11-15 19:35 ` Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 3/5] selftests: net: veth: test RX queue NAPI links Tianyi Gao
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Tianyi Gao @ 2026-11-15 19:35 UTC (permalink / raw)
To: netdev
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, toke, lorenzo,
horms, shuah, ast, daniel, hawk, john.fastabend, sdf, joe,
linux-kselftest, bpf, kernel-team, tianyi.gao, Tianyi Gao
veth does not link its RX queues to their NAPI instances. queue-get
therefore reports no napi-id for them. napi-get lists the NAPI instances
of a veth, and their thread PIDs when NAPI is threaded. It does not show
which RX queue each instance polls. Userspace cannot tell which NAPI
thread to pin for a given queue, or which NAPI to change with napi-set.
There is also no way to busy poll an AF_XDP socket bound to a veth
queue. Since commit b95ed5517354 ("xsk: Bring back busy polling support
in XDP_COPY"), xsk_bind() takes the NAPI ID of a copy-mode socket from
rxq->napi. veth never sets rxq->napi, so the socket gets no NAPI ID.
Call netif_queue_set_napi() after napi_enable(), which assigns the NAPI
ID. Call it again with NULL before napi_disable(). veth is not ops
locked, so netif_queue_set_napi() requires RTNL. veth enables and
disables NAPI only in ndo_open, ndo_stop, ndo_bpf, ndo_set_features and
ethtool's set_channels. All of them are called under RTNL.
Suggested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Tianyi Gao <tianyi@cloudflare.com>
---
drivers/net/veth.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 3cbedb8bad53..470c4f95e4a1 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1064,6 +1064,8 @@ static int veth_napi_enable_range(struct net_device *dev, int start, int end)
rcu_assign_pointer(rq->xdp_prog, priv->_xdp_prog);
napi_enable(&rq->xdp_napi);
+ netif_queue_set_napi(dev, i, NETDEV_QUEUE_TYPE_RX,
+ &rq->xdp_napi);
rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi);
}
@@ -1096,6 +1098,7 @@ static void veth_napi_del_range(struct net_device *dev, int start, int end)
struct veth_rq *rq = &priv->rq[i];
rcu_assign_pointer(priv->rq[i].napi, NULL);
+ netif_queue_set_napi(dev, i, NETDEV_QUEUE_TYPE_RX, NULL);
napi_disable(&rq->xdp_napi);
rcu_assign_pointer(rq->xdp_prog, NULL);
__netif_napi_del(&rq->xdp_napi);
--
2.56.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH net-next v3 3/5] selftests: net: veth: test RX queue NAPI links
2026-11-15 19:35 [PATCH net-next v3 0/5] veth: link RX queues to their NAPI instances Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 1/5] veth: refactor NAPI enable paths Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 2/5] veth: link RX queues to their NAPI instances Tianyi Gao
@ 2026-11-15 19:35 ` Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 4/5] veth: use persistent NAPI config Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 5/5] selftests: net: veth: test that RX queues keep their NAPI IDs Tianyi Gao
4 siblings, 0 replies; 6+ messages in thread
From: Tianyi Gao @ 2026-11-15 19:35 UTC (permalink / raw)
To: netdev
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, toke, lorenzo,
horms, shuah, ast, daniel, hawk, john.fastabend, sdf, joe,
linux-kselftest, bpf, kernel-team, tianyi.gao, Tianyi Gao
Add checks that each RX queue is linked to a NAPI instance of the
device while NAPI is enabled, and is not linked otherwise.
chk_queue_napi() reads queue-get and napi-get with the ynl CLI, as the
ndo-xmit checks do. It checks with jq that the napi-ids of the RX queues
are the IDs of the NAPI instances, and that the expected number of
queues is linked. The checks run with GRO on and with XDP attached, and
across RX channel changes and link down/up. They are skipped if the ynl
CLI or jq is not found.
Signed-off-by: Tianyi Gao <tianyi@cloudflare.com>
---
tools/testing/selftests/net/veth.sh | 79 ++++++++++++++++++++++++++++-
1 file changed, 78 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 64c2a5a59821..685209995485 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -110,6 +110,44 @@ chk_xdp_feature() {
fi
}
+chk_queue_napi() {
+ local msg="$1"
+ local target=$2
+ local expected=$3
+ local ns=$BASE$target
+ local ifindex
+ local queues
+ local napis
+ local st
+ local linked
+
+ ifindex=`ip netns exec $ns cat /sys/class/net/veth$target/ifindex`
+ queues=`ip netns exec $ns "$YNL" --family netdev --dump queue-get \
+ --output-json --json "{\"ifindex\": $ifindex}" 2>&1`
+ st=$?
+ napis=`ip netns exec $ns "$YNL" --family netdev --dump napi-get \
+ --output-json --json "{\"ifindex\": $ifindex}" 2>&1` || st=$?
+
+ printf "%-60s" "$msg"
+ if [ $st -ne 0 ]; then
+ echo " fail - ynl cli error: $queues $napis"
+ ret=1
+ return
+ fi
+
+ queues=`echo "$queues" | \
+ jq -c 'map(select(.type == "rx") | ."napi-id" // empty) | sort'`
+ napis=`echo "$napis" | jq -c 'map(.id) | sort'`
+ linked=`echo "$queues" | jq length`
+
+ if [ "$queues" = "$napis" ] && [ "$linked" = "$expected" ]; then
+ echo " ok "
+ else
+ echo " fail - expected $expected found $queues napis $napis"
+ ret=1
+ fi
+}
+
chk_channels() {
local msg="$1"
local target=$2
@@ -330,7 +368,8 @@ fi
[ $CPUS -lt 2 ] && echo "Only one CPU available, some tests will be skipped"
[ $STRESS -gt 0 -a $CPUS -lt 3 ] && echo " stress test will be skipped, too"
-[ ! -f "$YNL" ] && echo "ynl cli not found, ndo-xmit tests will be skipped"
+[ ! -f "$YNL" ] && echo "ynl cli not found, ndo-xmit/napi tests will be skipped"
+[ ! -x "$(command -v jq)" ] && echo "jq not found, napi tests will be skipped"
chk_channels_carrier up up || ret=1
chk_channels_carrier up down || ret=1
@@ -443,6 +482,44 @@ else
fi
cleanup
+if [ -f "$YNL" ] && [ -x "$(command -v jq)" ]; then
+ create_ns
+ RXQ=1
+ if [ $CPUS -gt 1 ]; then
+ ip netns exec $NS_DST ethtool -L veth$DST rx 2
+ RXQ=2
+ fi
+ chk_queue_napi "queue napi - default" $DST 0
+ ip netns exec $NS_DST ethtool -K veth$DST gro on
+ chk_queue_napi " - with gro on" $DST $RXQ
+ if [ $CPUS -gt 1 ]; then
+ ip netns exec $NS_DST ethtool -L veth$DST rx 1
+ chk_queue_napi " - fewer rx channels with gro" $DST 1
+ ip netns exec $NS_DST ethtool -L veth$DST rx 2
+ chk_queue_napi " - more rx channels with gro" $DST 2
+ fi
+ ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp
+ chk_queue_napi " - with gro and xdp on" $DST $RXQ
+ ip -n $NS_DST link set dev veth$DST xdp off
+ chk_queue_napi " - after xdp off with gro on" $DST $RXQ
+ ip netns exec $NS_DST ethtool -K veth$DST gro off
+ chk_queue_napi " - after gro off" $DST 0
+ ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp
+ chk_queue_napi " - with xdp on" $DST $RXQ
+ if [ $CPUS -gt 1 ]; then
+ ip netns exec $NS_DST ethtool -L veth$DST rx 1
+ chk_queue_napi " - fewer rx channels with xdp" $DST 1
+ ip netns exec $NS_DST ethtool -L veth$DST rx 2
+ chk_queue_napi " - more rx channels with xdp" $DST 2
+ fi
+ ip -n $NS_DST link set dev veth$DST down
+ ip -n $NS_DST link set dev veth$DST up
+ chk_queue_napi " - after down and up" $DST $RXQ
+ ip -n $NS_DST link set dev veth$DST xdp off
+ chk_queue_napi " - after xdp off" $DST 0
+ cleanup
+fi
+
create_ns
CUR_TX=1
--
2.56.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH net-next v3 4/5] veth: use persistent NAPI config
2026-11-15 19:35 [PATCH net-next v3 0/5] veth: link RX queues to their NAPI instances Tianyi Gao
` (2 preceding siblings ...)
2026-11-15 19:35 ` [PATCH net-next v3 3/5] selftests: net: veth: test RX queue NAPI links Tianyi Gao
@ 2026-11-15 19:35 ` Tianyi Gao
2026-11-15 19:35 ` [PATCH net-next v3 5/5] selftests: net: veth: test that RX queues keep their NAPI IDs Tianyi Gao
4 siblings, 0 replies; 6+ messages in thread
From: Tianyi Gao @ 2026-11-15 19:35 UTC (permalink / raw)
To: netdev
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, toke, lorenzo,
horms, shuah, ast, daniel, hawk, john.fastabend, sdf, joe,
linux-kselftest, bpf, kernel-team, tianyi.gao, Tianyi Gao
veth deletes the NAPI instances on link down, when NAPI is no longer
needed for GRO or XDP, and when ethtool -L reduces the number of RX
queues. When veth adds them again, each queue gets a new NAPI ID and
loses its per-NAPI settings. An AF_XDP socket bound to the queue keeps
the old NAPI ID, so its busy polling stops.
Use netif_napi_add_config(), as Documentation/networking/napi.rst asks
drivers to do whenever possible. The queue then keeps its NAPI ID and
its settings. virtio_net made the same change in commit d5d715207e29
("virtio_net: Use persistent NAPI config").
Signed-off-by: Tianyi Gao <tianyi@cloudflare.com>
---
New in v3, as Sashiko suggested on v2 [1].
[1] https://lore.kernel.org/all/179470883411.2199510.13825316417997386083@kernel.org/
---
drivers/net/veth.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 470c4f95e4a1..1c7ee3bf65f0 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1057,7 +1057,7 @@ static int veth_napi_enable_range(struct net_device *dev, int start, int end)
}
for (i = start; i < end; i++)
- netif_napi_add(dev, &priv->rq[i].xdp_napi, veth_poll);
+ netif_napi_add_config(dev, &priv->rq[i].xdp_napi, veth_poll, i);
for (i = start; i < end; i++) {
struct veth_rq *rq = &priv->rq[i];
--
2.56.0
^ permalink raw reply related [flat|nested] 6+ messages in thread