All of lore.kernel.org
 help / color / mirror / Atom feed
From: Li Chen <me@linux.beauty>
To: Pankaj Gupta <pankaj.gupta.linux@gmail.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	Dave Jiang <dave.jiang@intel.com>,
	Alison Schofield <alison.schofield@intel.com>,
	virtualization@lists.linux.dev, nvdimm@lists.linux.dev
Cc: linux-kernel@vger.kernel.org, stable@vger.kernel.org,
	Li Chen <me@linux.beauty>
Subject: [PATCH v7 08/12] nvdimm: virtio_pmem: refcount requests for token lifetime
Date: Tue, 30 Jun 2026 17:23:33 +0800	[thread overview]
Message-ID: <20260630092338.2094628-9-me@linux.beauty> (raw)
In-Reply-To: <20260630092338.2094628-1-me@linux.beauty>

KASAN reports slab-use-after-free in __wake_up_common():
BUG: KASAN: slab-use-after-free in __wake_up_common+0x114/0x160
Read of size 8 at addr ffff88810fdcb710 by task swapper/0/0

CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted
6.19.0-next-20260220-00006-g1eae5f204ec3 #4 PREEMPT(full)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux
1.17.0-2-2 04/01/2014
Call Trace:
 <IRQ>
 dump_stack_lvl+0x6d/0xb0
 print_report+0x170/0x4e2
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 ? __virt_addr_valid+0x1dc/0x380
 kasan_report+0xbc/0xf0
 ? __wake_up_common+0x114/0x160
 ? __wake_up_common+0x114/0x160
 __wake_up_common+0x114/0x160
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 __wake_up+0x36/0x60
 virtio_pmem_host_ack+0x11d/0x3b0
 ? sched_balance_domains+0x29f/0xb00
 ? __pfx_virtio_pmem_host_ack+0x10/0x10
 ? _raw_spin_lock_irqsave+0x98/0x100
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 vring_interrupt+0x1c9/0x5e0
 ? __pfx_vp_interrupt+0x10/0x10
 vp_vring_interrupt+0x87/0x100
 ? __pfx_vp_interrupt+0x10/0x10
 __handle_irq_event_percpu+0x17f/0x550
 ? __pfx__raw_spin_lock+0x10/0x10
 handle_irq_event+0xab/0x1c0
 handle_fasteoi_irq+0x276/0xae0
 __common_interrupt+0x65/0x130
 common_interrupt+0x78/0xa0
 </IRQ>

virtio_pmem_host_ack() wakes a request that has already been freed by the
submitter.

This happens when the request token is still reachable via the virtqueue,
but virtio_pmem_flush() returns and frees it.

Fix the token lifetime by refcounting struct virtio_pmem_request.
virtio_pmem_flush() holds a submitter reference, and the virtqueue holds an
extra reference once the request is queued. The completion path drops the
virtqueue reference, and the submitter drops its reference before
returning.

Fixes: 6e84200c0a29 ("virtio-pmem: Add virtio pmem driver")
Cc: stable@vger.kernel.org
Signed-off-by: Li Chen <me@linux.beauty>
---
v2->v3:
- Add raw KASAN report to the patch description.
- Drop timestamps from the embedded report.
v3->v4:
- Rebased onto v7.1-rc7 and renumbered after the flush error patches.

 drivers/nvdimm/nd_virtio.c   | 34 +++++++++++++++++++++++++++++-----
 drivers/nvdimm/virtio_pmem.h |  2 ++
 2 files changed, 31 insertions(+), 5 deletions(-)

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index 8c0d4347938a1..1cf53f75b1281 100644
--- a/drivers/nvdimm/nd_virtio.c
+++ b/drivers/nvdimm/nd_virtio.c
@@ -15,6 +15,14 @@ struct virtio_pmem_flush_work {
 	struct bio *bio;
 };
 
+static void virtio_pmem_req_release(struct kref *kref)
+{
+	struct virtio_pmem_request *req;
+
+	req = container_of(kref, struct virtio_pmem_request, kref);
+	kfree(req);
+}
+
 static void virtio_pmem_wake_one_waiter(struct virtio_pmem *vpmem)
 {
 	struct virtio_pmem_request *req_buf;
@@ -42,6 +50,7 @@ void virtio_pmem_host_ack(struct virtqueue *vq)
 		virtio_pmem_wake_one_waiter(vpmem);
 		WRITE_ONCE(req_data->done, true);
 		wake_up(&req_data->host_acked);
+		kref_put(&req_data->kref, virtio_pmem_req_release);
 	}
 	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
 }
@@ -72,6 +81,7 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 	if (!req_data)
 		return -ENOMEM;
 
+	kref_init(&req_data->kref);
 	WRITE_ONCE(req_data->done, false);
 	init_waitqueue_head(&req_data->host_acked);
 	init_waitqueue_head(&req_data->wq_buf);
@@ -89,10 +99,23 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 	  * to req_list and wait for host_ack to wake us up when free
 	  * slots are available.
 	  */
-	while ((err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req_data,
-					GFP_ATOMIC)) == -ENOSPC) {
-
-		dev_info(&vdev->dev, "failed to send command to virtio pmem device, no free slots in the virtqueue\n");
+	for (;;) {
+		err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req_data,
+					GFP_ATOMIC);
+		if (!err) {
+			/*
+			 * Take the virtqueue reference while @pmem_lock is
+			 * held so completion cannot run concurrently.
+			 */
+			kref_get(&req_data->kref);
+			break;
+		}
+
+		if (err != -ENOSPC)
+			break;
+
+		dev_info_ratelimited(&vdev->dev,
+				     "failed to send command to virtio pmem device, no free slots in the virtqueue\n");
 		WRITE_ONCE(req_data->wq_buf_avail, false);
 		list_add_tail(&req_data->list, &vpmem->req_list);
 		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
@@ -101,6 +124,7 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 		wait_event(req_data->wq_buf, READ_ONCE(req_data->wq_buf_avail));
 		spin_lock_irqsave(&vpmem->pmem_lock, flags);
 	}
+
 	err1 = virtqueue_kick(vpmem->req_vq);
 	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
 	/*
@@ -116,7 +140,7 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 		err = le32_to_cpu(req_data->resp.ret);
 	}
 
-	kfree(req_data);
+	kref_put(&req_data->kref, virtio_pmem_req_release);
 	return err;
 };
 
diff --git a/drivers/nvdimm/virtio_pmem.h b/drivers/nvdimm/virtio_pmem.h
index e6dfc10ce0762..3af92588bd9d1 100644
--- a/drivers/nvdimm/virtio_pmem.h
+++ b/drivers/nvdimm/virtio_pmem.h
@@ -12,12 +12,14 @@
 
 #include <linux/module.h>
 #include <uapi/linux/virtio_pmem.h>
+#include <linux/kref.h>
 #include <linux/libnvdimm.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 
 struct virtio_pmem_request {
+	struct kref kref;
 	struct virtio_pmem_req req;
 	struct virtio_pmem_resp resp;
 
-- 
2.52.0

  parent reply	other threads:[~2026-06-30  9:24 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-30  9:23 [PATCH v7 00/12] nvdimm: virtio_pmem: fix flush/request failure paths Li Chen
2026-06-30  9:23 ` [PATCH v7 01/12] nvdimm: preserve flush callback -ENOMEM Li Chen
2026-06-30  9:23 ` [PATCH v7 02/12] nvdimm: pmem: keep PREFLUSH before data writes Li Chen
2026-06-30  9:23 ` [PATCH v7 03/12] nvdimm: pmem: guard data loop for dataless bios Li Chen
2026-06-30  9:23 ` [PATCH v7 04/12] nvdimm: virtio_pmem: stop allocating child flush bio Li Chen
2026-06-30 10:28   ` sashiko-bot
2026-06-30  9:23 ` [PATCH v7 05/12] nvdimm: virtio_pmem: use GFP_NOIO for flush requests Li Chen
2026-06-30 10:42   ` sashiko-bot
2026-06-30  9:23 ` [PATCH v7 06/12] nvdimm: virtio_pmem: always wake -ENOSPC waiters Li Chen
2026-06-30  9:23 ` [PATCH v7 07/12] nvdimm: virtio_pmem: use READ_ONCE()/WRITE_ONCE() for wait flags Li Chen
2026-06-30  9:23 ` Li Chen [this message]
2026-06-30  9:23 ` [PATCH v7 09/12] nvdimm: virtio_pmem: publish done with release/acquire Li Chen
2026-06-30  9:23 ` [PATCH v7 10/12] nvdimm: virtio_pmem: isolate DMA request buffers Li Chen
2026-06-30  9:23 ` [PATCH v7 11/12] nvdimm: virtio_pmem: converge broken virtqueue to -EIO Li Chen
2026-06-30 11:50   ` sashiko-bot
2026-06-30  9:23 ` [PATCH v7 12/12] nvdimm: virtio_pmem: drain requests in freeze Li Chen
2026-06-30  9:47 ` [PATCH v7 00/12] nvdimm: virtio_pmem: fix flush/request failure paths Pankaj Gupta

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260630092338.2094628-9-me@linux.beauty \
    --to=me@linux.beauty \
    --cc=alison.schofield@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nvdimm@lists.linux.dev \
    --cc=pankaj.gupta.linux@gmail.com \
    --cc=stable@vger.kernel.org \
    --cc=virtualization@lists.linux.dev \
    --cc=vishal.l.verma@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.