When virtnet_close is followed by virtnet_open, some TX completions can possibly remain unconsumed, until they are finally processed during the first NAPI poll after the netdev_tx_reset_queue(), resulting in a crash [1]. Commit b96ed2c97c79 ("virtio_net: move netdev_tx_reset_queue() call before RX napi enable") was not sufficient to eliminate all BQL crash cases for virtio-net.

This issue can be reproduced with the latest net-next master by running: `while :; do ip l set DEV down; ip l set DEV up; done` under heavy network TX load from inside the machine.

netdev_tx_reset_queue() can actually be dropped from virtnet_open path; the device is not stopped in any case. For BQL core part, it's just like traffic nearly ceases to exist for some period. For stall detector added to BQL, even if virtnet_close could somehow lead to some TX completions delayed for long, followed by virtnet_open, we can just take it as stall as mentioned in commit 6025b9135f7a ("net: dqs: add NIC stall detector based on BQL"). Note also that users can still reset stall_max via sysfs.

So, drop netdev_tx_reset_queue() from virtnet_enable_queue_pair(). This eliminates the BQL crashes. Note that netdev_tx_reset_queue() is now explicitly required in freeze/restore path, so this patch adds it to free_unused_bufs().

[1]: ------------[ cut here ]------------ kernel BUG at lib/dynamic_queue_limits.c:99! Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 7 UID: 0 PID: 1598 Comm: ip Tainted: G N 6.12.0net-next_main+ #2 Tainted: [N]=TEST Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), \ BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:dql_completed+0x26b/0x290 Code: b7 c2 49 89 e9 44 89 da 89 c6 4c 89 d7 e8 ed 17 47 00 58 65 ff 0d 4d 27 90 7e 0f 85 fd fe ff ff e8 ea 53 8d ff e9 f3 fe ff ff <0f> 0b 01 d2 44 89 d1 29 d1 ba 00 00 00 00 0f 48 ca e9 28 ff ff ff RSP: 0018:ffffc900002b0d08 EFLAGS: 00010297 RAX: 0000000000000000 RBX: ffff888102398c80 RCX: 0000000080190009 RDX: 0000000000000000 RSI: 000000000000006a RDI: 0000000000000000 RBP: ffff888102398c00 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000000ca R11: 0000000000015681 R12: 0000000000000001 R13: ffffc900002b0d68 R14: ffff88811115e000 R15: ffff8881107aca40 FS: 00007f41ded69500(0000) GS:ffff888667dc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000556ccc2dc1a0 CR3: 0000000104fd8003 CR4: 0000000000772ef0 PKRU: 55555554 Call Trace: <IRQ> ? die+0x32/0x80 ? do_trap+0xd9/0x100 ? dql_completed+0x26b/0x290 ? dql_completed+0x26b/0x290 ? do_error_trap+0x6d/0xb0 ? dql_completed+0x26b/0x290 ? exc_invalid_op+0x4c/0x60 ? dql_completed+0x26b/0x290 ? asm_exc_invalid_op+0x16/0x20 ? dql_completed+0x26b/0x290 __free_old_xmit+0xff/0x170 [virtio_net] free_old_xmit+0x54/0xc0 [virtio_net] virtnet_poll+0xf4/0xe30 [virtio_net] ? __update_load_avg_cfs_rq+0x264/0x2d0 ? update_curr+0x35/0x260 ? reweight_entity+0x1be/0x260 __napi_poll.constprop.0+0x28/0x1c0 net_rx_action+0x329/0x420 ? enqueue_hrtimer+0x35/0x90 ? trace_hardirqs_on+0x1d/0x80 ? kvm_sched_clock_read+0xd/0x20 ? sched_clock+0xc/0x30 ? kvm_sched_clock_read+0xd/0x20 ? sched_clock+0xc/0x30 ? sched_clock_cpu+0xd/0x1a0 handle_softirqs+0x138/0x3e0 do_softirq.part.0+0x89/0xc0 </IRQ> <TASK> __local_bh_enable_ip+0xa7/0xb0 virtnet_open+0xc8/0x310 [virtio_net] __dev_open+0xfa/0x1b0 __dev_change_flags+0x1de/0x250 dev_change_flags+0x22/0x60 do_setlink.isra.0+0x2df/0x10b0 ? rtnetlink_rcv_msg+0x34f/0x3f0 ? netlink_rcv_skb+0x54/0x100 ? netlink_unicast+0x23e/0x390 ? netlink_sendmsg+0x21e/0x490 ? ____sys_sendmsg+0x31b/0x350 ? avc_has_perm_noaudit+0x67/0xf0 ? cred_has_capability.isra.0+0x75/0x110 ? __nla_validate_parse+0x5f/0xee0 ? __pfx___probestub_irq_enable+0x3/0x10 ? __create_object+0x5e/0x90 ? security_capable+0x3b/0x70 rtnl_newlink+0x784/0xaf0 ? avc_has_perm_noaudit+0x67/0xf0 ? cred_has_capability.isra.0+0x75/0x110 ? stack_depot_save_flags+0x24/0x6d0 ? __pfx_rtnl_newlink+0x10/0x10 rtnetlink_rcv_msg+0x34f/0x3f0 ? do_syscall_64+0x6c/0x180 ? entry_SYSCALL_64_after_hwframe+0x76/0x7e ? __pfx_rtnetlink_rcv_msg+0x10/0x10 netlink_rcv_skb+0x54/0x100 netlink_unicast+0x23e/0x390 netlink_sendmsg+0x21e/0x490 ____sys_sendmsg+0x31b/0x350 ? copy_msghdr_from_user+0x6d/0xa0 ___sys_sendmsg+0x86/0xd0 ? __pte_offset_map+0x17/0x160 ? preempt_count_add+0x69/0xa0 ? __call_rcu_common.constprop.0+0x147/0x610 ? preempt_count_add+0x69/0xa0 ? preempt_count_add+0x69/0xa0 ? _raw_spin_trylock+0x13/0x60 ? trace_hardirqs_on+0x1d/0x80 __sys_sendmsg+0x66/0xc0 do_syscall_64+0x6c/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f41defe5b34 Code: 15 e1 12 0f 00 f7 d8 64 89 02 b8 ff ff ff ff eb bf 0f 1f 44 00 00 f3 0f 1e fa 80 3d 35 95 0f 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 4c c3 0f 1f 00 55 48 89 e5 48 83 ec 20 89 55 RSP: 002b:00007ffe5336ecc8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f41defe5b34 RDX: 0000000000000000 RSI: 00007ffe5336ed30 RDI: 0000000000000003 RBP: 00007ffe5336eda0 R08: 0000000000000010 R09: 0000000000000001 R10: 00007ffe5336f6f9 R11: 0000000000000202 R12: 0000000000000003 R13: 0000000067452259 R14: 0000556ccc28b040 R15: 0000000000000000 </TASK> [...] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fixes: c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits") Cc: stable@vger.kernel.org # v6.11+ Signed-off-by: Koichiro Den koichiro.den@canonical.com --- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 64c87bb48a41..48ce8b3881b6 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3054,7 +3054,6 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model;

- netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);

@@ -6243,6 +6242,7 @@ static void free_unused_bufs(struct virtnet_info *vi) struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_sq_free_unused_buf(vq, buf); + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); cond_resched(); }

When virtqueue_resize() has actually recycled all unused buffers, additional work may be required in some cases. Relying solely on its return status is fragile, so introduce a new argument 'flushed' to explicitly indicate whether it has really occurred.

Signed-off-by: Koichiro Den koichiro.den@canonical.com --- drivers/net/virtio_net.c | 6 ++++-- drivers/virtio/virtio_ring.c | 7 ++++++- include/linux/virtio.h | 3 ++- 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 48ce8b3881b6..df9bfe31aa6d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3326,12 +3326,13 @@ static int virtnet_rx_resize(struct virtnet_info *vi, struct receive_queue *rq, u32 ring_num) { int err, qindex; + bool flushed;

qindex = rq - vi->rq;

virtnet_rx_pause(vi, rq);

- err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf); + err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf, &flushed); if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err);

@@ -3389,12 +3390,13 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, u32 ring_num) { int qindex, err; + bool flushed;

qindex = sq - vi->sq;

virtnet_tx_pause(vi, sq);

- err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf); + err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf, &flushed); if (err) netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err);

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 82a7d2cbc704..34a068d401ec 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2772,6 +2772,7 @@ EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); * @_vq: the struct virtqueue we're talking about. * @num: new ring num * @recycle: callback to recycle unused buffers + * @flushed: whether or not unused buffers are all flushed * * When it is really necessary to create a new vring, it will set the current vq * into the reset state. Then call the passed callback to recycle the buffer @@ -2792,11 +2793,14 @@ EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); * */ int virtqueue_resize(struct virtqueue *_vq, u32 num, - void (*recycle)(struct virtqueue *vq, void *buf)) + void (*recycle)(struct virtqueue *vq, void *buf), + bool *flushed) { struct vring_virtqueue *vq = to_vvq(_vq); int err;

+ *flushed = false; + if (num > vq->vq.num_max) return -E2BIG;

@@ -2809,6 +2813,7 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num, err = virtqueue_disable_and_recycle(_vq, recycle); if (err) return err; + *flushed = true;

if (vq->packed_ring) err = virtqueue_resize_packed(_vq, num); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 57cc4b07fd17..878feda08af9 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -109,7 +109,8 @@ dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq);

int virtqueue_resize(struct virtqueue *vq, u32 num, - void (*recycle)(struct virtqueue *vq, void *buf)); + void (*recycle)(struct virtqueue *vq, void *buf), + bool *flushed); int virtqueue_reset(struct virtqueue *vq, void (*recycle)(struct virtqueue *vq, void *buf));

virtnet_sq_bind_xsk_pool() flushes tx skbs and then resets tx queue, so DQL counters need to be reset.

Fixes: 21a4e3ce6dc7 ("virtio_net: xsk: bind/unbind xsk for tx") Signed-off-by: Koichiro Den koichiro.den@canonical.com --- drivers/net/virtio_net.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d5240a03b7d6..27d58fb47b07 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -5749,6 +5749,8 @@ static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi, netdev_err(vi->dev, "reset tx fail: tx queue index: %d err: %d\n", qindex, err); pool = NULL; } + if (flushed) + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qindex));

sq->xsk_pool = pool;