Skip to contentSkip to conversation

virtio-net: disable delayed refill when pausing rx

PATCH Superseded Bui Quang Minh 2 participants 5 messages Apr 14, 2025

Subsystems (6)

v2 of 6 Superseded Latest is v6 →

lore
Share & tools
lore
#0 lore raw

v2 cover virtio-net: disable delayed refill when pausing rx

Hi everyone,

This series tries to fix a deadlock in virtio-net when binding/unbinding XDP program, XDP socket or resizing the rx queue.

When pausing rx (e.g. set up xdp, xsk pool, rx resize), we call napi_disable() on the receive queue's napi. In delayed refill_work, it also calls napi_disable() on the receive queue's napi. When napi_disable() is called on an already disabled napi, it will sleep in napi_disable_locked while still holding the netdev_lock. As a result, later napi_enable gets stuck too as it cannot acquire the netdev_lock. This leads to refill_work and the pause-then-resume tx are stuck altogether.

This scenario can be reproducible by binding a XDP socket to virtio-net interface without setting up the fill ring. As a result, try_fill_recv will fail until the fill ring is set up and refill_work is scheduled.

This fix adds virtnet_rx_(pause/resume)_all helpers and fixes up the virtnet_rx_resume to disable future and cancel all inflights delayed refill_work before calling napi_disable() to pause the rx.

Version 2 changes:
- Add selftest for deadlock scenario

Thanks,
Quang Minh.

Bui Quang Minh (3):
virtio-net: disable delayed refill when pausing rx
selftests: net: move xdp_helper to net/lib
selftests: net: add a virtio_net deadlock selftest

 drivers/net/virtio_net.c                      | 60 ++++++++++++++++---
 tools/testing/selftests/Makefile              |  2 +-
 tools/testing/selftests/drivers/net/Makefile  |  2 -
 tools/testing/selftests/drivers/net/queues.py |  4 +-
 .../selftests/drivers/net/virtio_net/Makefile |  2 +
 .../selftests/drivers/net/virtio_net/config   |  1 +
 .../drivers/net/virtio_net/lib/py/__init__.py | 16 +++++
 .../drivers/net/virtio_net/xsk_pool.py        | 52 ++++++++++++++++
 tools/testing/selftests/net/lib/.gitignore    |  1 +
 tools/testing/selftests/net/lib/Makefile      |  1 +
 .../{drivers/net => net/lib}/xdp_helper.c     |  0
 11 files changed, 127 insertions(+), 14 deletions(-)
 create mode 100644 tools/testing/selftests/drivers/net/virtio_net/lib/py/__init__.py
 create mode 100755 tools/testing/selftests/drivers/net/virtio_net/xsk_pool.py
 rename tools/testing/selftests/{drivers/net => net/lib}/xdp_helper.c (100%)
Signature · 1 line
2.43.0
#1 lore raw

PATCH v2 1/3 virtio-net: disable delayed refill when pausing rx

When pausing rx (e.g. set up xdp, xsk pool, rx resize), we call napi_disable() on the receive queue's napi. In delayed refill_work, it also calls napi_disable() on the receive queue's napi. When napi_disable() is called on an already disabled napi, it will sleep in napi_disable_locked while still holding the netdev_lock. As a result, later napi_enable gets stuck too as it cannot acquire the netdev_lock. This leads to refill_work and the pause-then-resume tx are stuck altogether.

This scenario can be reproducible by binding a XDP socket to virtio-net interface without setting up the fill ring. As a result, try_fill_recv will fail until the fill ring is set up and refill_work is scheduled.

This commit adds virtnet_rx_(pause/resume)_all helpers and fixes up the virtnet_rx_resume to disable future and cancel all inflights delayed refill_work before calling napi_disable() to pause the rx.

Fixes 413f0271f396 ("net: protect NAPI enablement with netdev_lock()")
---
 drivers/net/virtio_net.c | 60 ++++++++++++++++++++++++++++++++++------
 1 file changed, 51 insertions(+), 9 deletions(-)
drivers/net/virtio_net.c +51 -9
index 7e4617216a4b..4361b91ccc64 100644
@@ -3342,10 +3342,53 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static void virtnet_rx_pause_all(struct virtnet_info *vi)
+{
+	bool running = netif_running(vi->dev);
+
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	if (running) {
+		int i;
+
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			virtnet_napi_disable(&vi->rq[i]);
+			virtnet_cancel_dim(vi, &vi->rq[i].dim);
+		}
+	}
+}
+
+static void virtnet_rx_resume_all(struct virtnet_info *vi)
+{
+	bool running = netif_running(vi->dev);
+	int i;
+
+	enable_delayed_refill(vi);
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (i < vi->curr_queue_pairs) {
+			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
+				schedule_delayed_work(&vi->refill, 0);
+		}
+
+		if (running)
+			virtnet_napi_enable(&vi->rq[i]);
+	}
+}
+
 static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 {
 	bool running = netif_running(vi->dev);
 
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
 	if (running) {
 		virtnet_napi_disable(rq);
 		virtnet_cancel_dim(vi, &rq->dim);
@@ -3356,6 +3399,7 @@ static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
 {
 	bool running = netif_running(vi->dev);
 
+	enable_delayed_refill(vi);
 	if (!try_fill_recv(vi, rq, GFP_KERNEL))
 		schedule_delayed_work(&vi->refill, 0);
 
@@ -5959,12 +6003,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	if (prog)
 		bpf_prog_add(prog, vi->max_queue_pairs - 1);
 
+	virtnet_rx_pause_all(vi);
+
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_disable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_disable(&vi->sq[i]);
-		}
 	}
 
 	if (!prog) {
@@ -5996,13 +6040,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		vi->xdp_enabled = false;
 	}
 
+	virtnet_rx_resume_all(vi);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev)) {
-			virtnet_napi_enable(&vi->rq[i]);
+		if (netif_running(dev))
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 
 	return 0;
@@ -6014,11 +6057,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
 	}
 
+	virtnet_rx_resume_all(vi);
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
Signature · 1 line
2.43.0
#2 lore raw
Quoted 17 lines · Bui Quang Minh

When pausing rx (e.g. set up xdp, xsk pool, rx resize), we call napi_disable() on the receive queue's napi. In delayed refill_work, it also calls napi_disable() on the receive queue's napi. When napi_disable() is called on an already disabled napi, it will sleep in napi_disable_locked while still holding the netdev_lock. As a result, later napi_enable gets stuck too as it cannot acquire the netdev_lock. This leads to refill_work and the pause-then-resume tx are stuck altogether.

This scenario can be reproducible by binding a XDP socket to virtio-net interface without setting up the fill ring. As a result, try_fill_recv will fail until the fill ring is set up and refill_work is scheduled.

This commit adds virtnet_rx_(pause/resume)_all helpers and fixes up the virtnet_rx_resume to disable future and cancel all inflights delayed refill_work before calling napi_disable() to pause the rx.

Quoted 5 lines
Fixes 413f0271f396 ("net: protect NAPI enablement with netdev_lock()")
---
 drivers/net/virtio_net.c | 60 ++++++++++++++++++++++++++++++++++------
 1 file changed, 51 insertions(+), 9 deletions(-)

Thans for the patch! Yes something to improve:

Quoted 14 lines
drivers/net/virtio_net.c +6 -0
index 7e4617216a4b..4361b91ccc64 100644
@@ -3342,10 +3342,53 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static void virtnet_rx_pause_all(struct virtnet_info *vi)
+{
+	bool running = netif_running(vi->dev);
+
+	/*
+	 * Make sure refill_work does not run concurrently to

drivers/net/virtio_net.c static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) · line 3360

Quoted 10 lines
drivers/net/virtio_net.c +10 -0
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	if (running) {
+		int i;
+
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			virtnet_napi_disable(&vi->rq[i]);
+			virtnet_cancel_dim(vi, &vi->rq[i].dim);

duplicates a bit of code from virtnet_rx_pause_all.

Quoted 21 lines
drivers/net/virtio_net.c +21 -0
+		}
+	}
+}
+
+static void virtnet_rx_resume_all(struct virtnet_info *vi)
+{
+	bool running = netif_running(vi->dev);
+	int i;
+
+	enable_delayed_refill(vi);
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (i < vi->curr_queue_pairs) {
+			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
+				schedule_delayed_work(&vi->refill, 0);
+		}
+
+		if (running)
+			virtnet_napi_enable(&vi->rq[i]);
+	}
+}
+

drivers/net/virtio_net.c static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) · line 3391

Quoted 10 lines
drivers/net/virtio_net.c +6 -0
 static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 {
 	bool running = netif_running(vi->dev);
 
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);

Maybe rename this e.g. __virtnet_rx_pause ?

Quoted 59 lines
drivers/net/virtio_net.c +8 -9
 	if (running) {
 		virtnet_napi_disable(rq);
 		virtnet_cancel_dim(vi, &rq->dim);
@@ -3356,6 +3399,7 @@ static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
 {
 	bool running = netif_running(vi->dev);
 
+	enable_delayed_refill(vi);
 	if (!try_fill_recv(vi, rq, GFP_KERNEL))
 		schedule_delayed_work(&vi->refill, 0);
 
@@ -5959,12 +6003,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	if (prog)
 		bpf_prog_add(prog, vi->max_queue_pairs - 1);
 
+	virtnet_rx_pause_all(vi);
+
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_disable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_disable(&vi->sq[i]);
-		}
 	}
 
 	if (!prog) {
@@ -5996,13 +6040,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		vi->xdp_enabled = false;
 	}
 
+	virtnet_rx_resume_all(vi);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev)) {
-			virtnet_napi_enable(&vi->rq[i]);
+		if (netif_running(dev))
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 
 	return 0;
@@ -6014,11 +6057,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
 	}
 
+	virtnet_rx_resume_all(vi);
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
Signature · 1 line
2.43.0
#3 lore raw

PATCH v2 2/3 selftests: net: move xdp_helper to net/lib

In reply to Bui Quang Minh

Move xdp_helper to net/lib to make it easier for other selftests to use the helper.

---
 tools/testing/selftests/drivers/net/Makefile                  | 2 --
 tools/testing/selftests/drivers/net/queues.py                 | 4 ++--
 tools/testing/selftests/net/lib/.gitignore                    | 1 +
 tools/testing/selftests/net/lib/Makefile                      | 1 +
 tools/testing/selftests/{drivers/net => net/lib}/xdp_helper.c | 0
 5 files changed, 4 insertions(+), 4 deletions(-)
 rename tools/testing/selftests/{drivers/net => net/lib}/xdp_helper.c (100%)
tools/testing/selftests/drivers/net/Makefile +0 -2
index 0c95bd944d56..cd74f1eb3193 100644
@@ -6,8 +6,6 @@ TEST_INCLUDES := $(wildcard lib/py/*.py) \
 		 ../../net/net_helper.sh \
 		 ../../net/lib.sh \
 
-TEST_GEN_FILES := xdp_helper
-
 TEST_PROGS := \
 	netcons_basic.sh \
 	netcons_fragmented_msg.sh \
tools/testing/selftests/drivers/net/queues.py +2 -2
index 06abd3f233e1..236005290a33 100755
@@ -26,13 +26,13 @@ def nl_get_queues(cfg, nl, qtype='rx'):
 
 def check_xsk(cfg, nl, xdp_queue_id=0) -> None:
     # Probe for support
-    xdp = cmd(f'{cfg.test_dir / "xdp_helper"} - -', fail=False)
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
     if xdp.ret == 255:
         raise KsftSkipEx('AF_XDP unsupported')
     elif xdp.ret > 0:
         raise KsftFailEx('unable to create AF_XDP socket')
 
-    with bkg(f'{cfg.test_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
+    with bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
              ksft_wait=3):
 
         rx = tx = False
tools/testing/selftests/net/lib/.gitignore +1 -0
index 1ebc6187f421..bbc97d6bf556 100644
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 csum
+xdp_helper
tools/testing/selftests/net/lib/Makefile +1 -0
index c22623b9a2a5..88c4bc461459 100644
@@ -10,6 +10,7 @@ TEST_FILES += ../../../../net/ynl
 
 TEST_GEN_FILES += csum
 TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
+TEST_GEN_FILES += xdp_helper
 
 TEST_INCLUDES := $(wildcard py/*.py sh/*.sh)
 
tools/testing/selftests/net/lib/xdp_helper.c renamed from tools/testing/selftests/drivers/net/xdp_helper.c +0 -0
similarity index 100%
rename from tools/testing/selftests/drivers/net/xdp_helper.c
rename to tools/testing/selftests/net/lib/xdp_helper.c
Signature · 1 line
2.43.0
#4 lore raw

PATCH v2 3/3 selftests: net: add a virtio_net deadlock selftest

In reply to Bui Quang Minh

The selftest reproduces the deadlock scenario when binding/unbinding XDP program, XDP socket, rx ring resize on virtio_net interface.

---
 tools/testing/selftests/Makefile              |  2 +-
 .../selftests/drivers/net/virtio_net/Makefile |  2 +
 .../selftests/drivers/net/virtio_net/config   |  1 +
 .../drivers/net/virtio_net/lib/py/__init__.py | 16 ++++++
 .../drivers/net/virtio_net/xsk_pool.py        | 52 +++++++++++++++++++
 5 files changed, 72 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/drivers/net/virtio_net/lib/py/__init__.py
 create mode 100755 tools/testing/selftests/drivers/net/virtio_net/xsk_pool.py
tools/testing/selftests/Makefile +1 -1
index c77c8c8e3d9b..0a6b096f98b7 100644
@@ -130,7 +130,7 @@ TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
 # Networking tests want the net/lib target, include it automatically
-ifneq ($(filter net drivers/net drivers/net/hw,$(TARGETS)),)
+ifneq ($(filter net drivers/net drivers/net/hw drivers/net/virtio_net,$(TARGETS)),)
 ifeq ($(filter net/lib,$(TARGETS)),)
 	INSTALL_DEP_TARGETS := net/lib
 endif
tools/testing/selftests/drivers/net/virtio_net/Makefile +2 -0
index 7ec7cd3ab2cc..82adda96ef15 100644
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0+ OR MIT
 
 TEST_PROGS = basic_features.sh \
+        xsk_pool.py \
         #
 
 TEST_FILES = \
@@ -8,6 +9,7 @@ TEST_FILES = \
         #
 
 TEST_INCLUDES = \
+        $(wildcard lib/py/*.py ../lib/py/*.py) \
         ../../../net/forwarding/lib.sh \
         ../../../net/lib.sh \
         #
tools/testing/selftests/drivers/net/virtio_net/config +1 -0
index bcf7555eaffe..12e8caa22613 100644
@@ -6,3 +6,4 @@ CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_NET_VRF=m
 CONFIG_VIRTIO_DEBUG=y
 CONFIG_VIRTIO_NET=y
+CONFIG_XDP_SOCKETS=y
tools/testing/selftests/drivers/net/virtio_net/lib/py/__init__.py new file +16 -0
new file mode 100644
index 000000000000..b582885786f5
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import sys
+from pathlib import Path
+
+KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve()
+
+try:
+    sys.path.append(KSFT_DIR.as_posix())
+    from net.lib.py import *
+    from drivers.net.lib.py import *
+except ModuleNotFoundError as e:
+    ksft_pr("Failed importing `net` library from kernel sources")
+    ksft_pr(str(e))
+    ktap_result(True, comment="SKIP")
+    sys.exit(4)
tools/testing/selftests/drivers/net/virtio_net/xsk_pool.py new file +52 -0

52 lines not on this page · raw message

Signature · 1 line
2.43.0