Merge branch 'virtio_net-correct-netdev_tx_reset_queue-invocation-points'

Koichiro Den says:

====================
virtio_net: correct netdev_tx_reset_queue() invocation points

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
scenarios 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.

This patch series resolves the issue and also addresses similar existing
problems:

(a). Drop netdev_tx_reset_queue() from open/close path. This eliminates the
     BQL crashes due to the problematic open/close path.

(b). As a result of (a), netdev_tx_reset_queue() is now explicitly required
     in freeze/restore path. Add netdev_tx_reset_queue() immediately after
     free_unused_bufs() invocation.

(c). Fix missing resetting in virtnet_tx_resize().
     virtnet_tx_resize() has lacked proper resetting since commit
     c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits").

(d). Fix missing resetting in the XDP_SETUP_XSK_POOL path.
     Similar to (c), this path lacked proper resetting. Call
     netdev_tx_reset_queue() when virtqueue_reset() has actually recycled
     unused buffers.

This patch series consists of six commits:
  [1/6]: Resolves (a) and (b).                      # also -stable 6.11.y
  [2/6]: Minor fix to make [4/6] streamlined.
  [3/6]: Prerequisite for (c).                      # also -stable 6.11.y
  [4/6]: Resolves (c) (incl. Prerequisite for (d))  # also -stable 6.11.y
  [5/6]: Preresuisite for (d).
  [6/6]: Resolves (d).

Changes for v4:
  - move netdev_tx_reset_queue() out of free_unused_bufs()
  - submit to net, not net-next
Changes for v3:
  - replace 'flushed' argument with 'recycle_done'
Changes for v2:
  - add tx queue resetting for (b) to (d) above

v3: https://lore.kernel.org/all/20241204050724.307544-1-koichiro.den@canonical.com/
v2: https://lore.kernel.org/all/20241203073025.67065-1-koichiro.den@canonical.com/
v1: https://lore.kernel.org/all/20241130181744.3772632-1-koichiro.den@canonical.com/

[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>
[...]
====================

Link: https://patch.msgid.link/20241206011047.923923-1-koichiro.den@canonical.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 39 insertions, 10 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 64c87bb48a41..7646ddd9bef7 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -503,6 +503,7 @@ struct virtio_net_common_hdr {
 static struct virtio_net_common_hdr xsk_hdr;
 
 static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
+static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq);
 static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
 			       struct net_device *dev,
 			       unsigned int *xdp_xmit,
@@ -3054,7 +3055,6 @@ 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);
 
@@ -3332,7 +3332,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 
 	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, NULL);
 	if (err)
 		netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err);
 
@@ -3395,7 +3395,8 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *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,
+			       virtnet_sq_free_unused_buf_done);
 	if (err)
 		netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err);
 
@@ -5710,7 +5711,7 @@ static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queu
 
 	virtnet_rx_pause(vi, rq);
 
-	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf);
+	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf, NULL);
 	if (err) {
 		netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err);
 
@@ -5739,7 +5740,8 @@ static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi,
 
 	virtnet_tx_pause(vi, sq);
 
-	err = virtqueue_reset(sq->vq, virtnet_sq_free_unused_buf);
+	err = virtqueue_reset(sq->vq, virtnet_sq_free_unused_buf,
+			      virtnet_sq_free_unused_buf_done);
 	if (err) {
 		netdev_err(vi->dev, "reset tx fail: tx queue index: %d err: %d\n", qindex, err);
 		pool = NULL;
@@ -6214,7 +6216,7 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
 {
 	struct virtnet_info *vi = vq->vdev->priv;
 	struct send_queue *sq;
-	int i = vq2rxq(vq);
+	int i = vq2txq(vq);
 
 	sq = &vi->sq[i];
 
@@ -6234,6 +6236,14 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
 	}
 }
 
+static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq)
+{
+	struct virtnet_info *vi = vq->vdev->priv;
+	int i = vq2txq(vq);
+
+	netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i));
+}
+
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -6966,11 +6976,20 @@ free:
 
 static void remove_vq_common(struct virtnet_info *vi)
 {
+	int i;
+
 	virtio_reset_device(vi->vdev);
 
 	/* Free unused buffers in both send and recv, if any. */
 	free_unused_bufs(vi);
 
+	/*
+	 * Rule of thumb is netdev_tx_reset_queue() should follow any
+	 * skb freeing not followed by netdev_tx_completed_queue()
+	 */
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i));
+
 	free_receive_bufs(vi);
 
 	free_receive_page_frags(vi);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 82a7d2cbc704..fdd2d2b07b5a 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
+ * @recycle_done: callback to be invoked when recycle for all unused buffers done
  *
  * 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
@@ -2792,7 +2793,8 @@ 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),
+		     void (*recycle_done)(struct virtqueue *vq))
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	int err;
@@ -2809,6 +2811,8 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num,
 	err = virtqueue_disable_and_recycle(_vq, recycle);
 	if (err)
 		return err;
+	if (recycle_done)
+		recycle_done(_vq);
 
 	if (vq->packed_ring)
 		err = virtqueue_resize_packed(_vq, num);
@@ -2823,6 +2827,7 @@ EXPORT_SYMBOL_GPL(virtqueue_resize);
  * virtqueue_reset - detach and recycle all unused buffers
  * @_vq: the struct virtqueue we're talking about.
  * @recycle: callback to recycle unused buffers
+ * @recycle_done: callback to be invoked when recycle for all unused buffers done
  *
  * Caller must ensure we don't call this with other virtqueue operations
  * at the same time (except where noted).
@@ -2834,7 +2839,8 @@ EXPORT_SYMBOL_GPL(virtqueue_resize);
  * -EPERM: Operation not permitted
  */
 int virtqueue_reset(struct virtqueue *_vq,
-		    void (*recycle)(struct virtqueue *vq, void *buf))
+		    void (*recycle)(struct virtqueue *vq, void *buf),
+		    void (*recycle_done)(struct virtqueue *vq))
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	int err;
@@ -2842,6 +2848,8 @@ int virtqueue_reset(struct virtqueue *_vq,
 	err = virtqueue_disable_and_recycle(_vq, recycle);
 	if (err)
 		return err;
+	if (recycle_done)
+		recycle_done(_vq);
 
 	if (vq->packed_ring)
 		virtqueue_reinit_packed(vq);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 57cc4b07fd17..dd88682e27e3 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -109,9 +109,11 @@ 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),
+		     void (*recycle_done)(struct virtqueue *vq));
 int virtqueue_reset(struct virtqueue *vq,
-		    void (*recycle)(struct virtqueue *vq, void *buf));
+		    void (*recycle)(struct virtqueue *vq, void *buf),
+		    void (*recycle_done)(struct virtqueue *vq));
 
 struct virtio_admin_cmd {
 	__le16 opcode;