diff mbox series

[v2] xen/netfront: destroy queues before real_num_tx_queues is zeroed

Message ID 20220223211954.2506824-1-marmarek@invisiblethingslab.com (mailing list archive)
State Accepted
Commit dcf4ff7a48e7598e6b10126cc02177abb8ae4f3f
Delegated to: Netdev Maintainers
Headers show
Series [v2] xen/netfront: destroy queues before real_num_tx_queues is zeroed | expand

Checks

Context Check Description
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix warning Target tree name not specified in the subject
netdev/cover_letter success Single patches do not need cover letters
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers success CCed 8 of 8 maintainers
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: Missing a blank line after declarations
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/tree_selection success Guessing tree name failed - patch did not apply

Commit Message

Marek Marczykowski-Górecki Feb. 23, 2022, 9:19 p.m. UTC
xennet_destroy_queues() relies on info->netdev->real_num_tx_queues to
delete queues. Since d7dac083414eb5bb99a6d2ed53dc2c1b405224e5
("net-sysfs: update the queue counts in the unregistration path"),
unregister_netdev() indirectly sets real_num_tx_queues to 0. Those two
facts together means, that xennet_destroy_queues() called from
xennet_remove() cannot do its job, because it's called after
unregister_netdev(). This results in kfree-ing queues that are still
linked in napi, which ultimately crashes:

    BUG: kernel NULL pointer dereference, address: 0000000000000000
    #PF: supervisor read access in kernel mode
    #PF: error_code(0x0000) - not-present page
    PGD 0 P4D 0
    Oops: 0000 [#1] PREEMPT SMP PTI
    CPU: 1 PID: 52 Comm: xenwatch Tainted: G        W         5.16.10-1.32.fc32.qubes.x86_64+ #226
    RIP: 0010:free_netdev+0xa3/0x1a0
    Code: ff 48 89 df e8 2e e9 00 00 48 8b 43 50 48 8b 08 48 8d b8 a0 fe ff ff 48 8d a9 a0 fe ff ff 49 39 c4 75 26 eb 47 e8 ed c1 66 ff <48> 8b 85 60 01 00 00 48 8d 95 60 01 00 00 48 89 ef 48 2d 60 01 00
    RSP: 0000:ffffc90000bcfd00 EFLAGS: 00010286
    RAX: 0000000000000000 RBX: ffff88800edad000 RCX: 0000000000000000
    RDX: 0000000000000001 RSI: ffffc90000bcfc30 RDI: 00000000ffffffff
    RBP: fffffffffffffea0 R08: 0000000000000000 R09: 0000000000000000
    R10: 0000000000000000 R11: 0000000000000001 R12: ffff88800edad050
    R13: ffff8880065f8f88 R14: 0000000000000000 R15: ffff8880066c6680
    FS:  0000000000000000(0000) GS:ffff8880f3300000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 0000000000000000 CR3: 00000000e998c006 CR4: 00000000003706e0
    Call Trace:
     <TASK>
     xennet_remove+0x13d/0x300 [xen_netfront]
     xenbus_dev_remove+0x6d/0xf0
     __device_release_driver+0x17a/0x240
     device_release_driver+0x24/0x30
     bus_remove_device+0xd8/0x140
     device_del+0x18b/0x410
     ? _raw_spin_unlock+0x16/0x30
     ? klist_iter_exit+0x14/0x20
     ? xenbus_dev_request_and_reply+0x80/0x80
     device_unregister+0x13/0x60
     xenbus_dev_changed+0x18e/0x1f0
     xenwatch_thread+0xc0/0x1a0
     ? do_wait_intr_irq+0xa0/0xa0
     kthread+0x16b/0x190
     ? set_kthread_struct+0x40/0x40
     ret_from_fork+0x22/0x30
     </TASK>

Fix this by calling xennet_destroy_queues() from xennet_uninit(),
when real_num_tx_queues is still available. This ensures that queues are
destroyed when real_num_tx_queues is set to 0, regardless of how
unregister_netdev() was called.

Originally reported at
https://github.com/QubesOS/qubes-issues/issues/7257

Fixes: d7dac083414eb5bb9 ("net-sysfs: update the queue counts in the unregistration path")
Cc: stable@vger.kernel.org
Signed-off-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>

---
Changes in v2:
 - use xennet_uninit, as suggested by Jakub Kicinski
---
 drivers/net/xen-netfront.c | 39 ++++++++++++++++++++++----------------
 1 file changed, 23 insertions(+), 16 deletions(-)

Comments

patchwork-bot+netdevbpf@kernel.org Feb. 25, 2022, 10:40 a.m. UTC | #1
Hello:

This patch was applied to netdev/net.git (master)
by David S. Miller <davem@davemloft.net>:

On Wed, 23 Feb 2022 22:19:54 +0100 you wrote:
> xennet_destroy_queues() relies on info->netdev->real_num_tx_queues to
> delete queues. Since d7dac083414eb5bb99a6d2ed53dc2c1b405224e5
> ("net-sysfs: update the queue counts in the unregistration path"),
> unregister_netdev() indirectly sets real_num_tx_queues to 0. Those two
> facts together means, that xennet_destroy_queues() called from
> xennet_remove() cannot do its job, because it's called after
> unregister_netdev(). This results in kfree-ing queues that are still
> linked in napi, which ultimately crashes:
> 
> [...]

Here is the summary with links:
  - [v2] xen/netfront: destroy queues before real_num_tx_queues is zeroed
    https://git.kernel.org/netdev/net/c/dcf4ff7a48e7

You are awesome, thank you!
diff mbox series

Patch

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index d514d96027a6..039ca902c5bf 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -842,6 +842,28 @@  static int xennet_close(struct net_device *dev)
 	return 0;
 }
 
+static void xennet_destroy_queues(struct netfront_info *info)
+{
+	unsigned int i;
+
+	for (i = 0; i < info->netdev->real_num_tx_queues; i++) {
+		struct netfront_queue *queue = &info->queues[i];
+
+		if (netif_running(info->netdev))
+			napi_disable(&queue->napi);
+		netif_napi_del(&queue->napi);
+	}
+
+	kfree(info->queues);
+	info->queues = NULL;
+}
+
+static void xennet_uninit(struct net_device *dev)
+{
+	struct netfront_info *np = netdev_priv(dev);
+	xennet_destroy_queues(np);
+}
+
 static void xennet_set_rx_rsp_cons(struct netfront_queue *queue, RING_IDX val)
 {
 	unsigned long flags;
@@ -1611,6 +1633,7 @@  static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 }
 
 static const struct net_device_ops xennet_netdev_ops = {
+	.ndo_uninit          = xennet_uninit,
 	.ndo_open            = xennet_open,
 	.ndo_stop            = xennet_close,
 	.ndo_start_xmit      = xennet_start_xmit,
@@ -2103,22 +2126,6 @@  static int write_queue_xenstore_keys(struct netfront_queue *queue,
 	return err;
 }
 
-static void xennet_destroy_queues(struct netfront_info *info)
-{
-	unsigned int i;
-
-	for (i = 0; i < info->netdev->real_num_tx_queues; i++) {
-		struct netfront_queue *queue = &info->queues[i];
-
-		if (netif_running(info->netdev))
-			napi_disable(&queue->napi);
-		netif_napi_del(&queue->napi);
-	}
-
-	kfree(info->queues);
-	info->queues = NULL;
-}
-
 
 
 static int xennet_create_page_pool(struct netfront_queue *queue)