FAILED: patch "[PATCH] nvdimm: virtio_pmem: refcount requests for token lifetime" failed to apply to 6.6-stable tree

FAILED: patch "[PATCH] nvdimm: virtio_pmem: refcount requests for token lifetime" failed to apply to 6.6-stable tree

[gregkh]

The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x e57140944b5a47a7fd5a142faab29a02af040bc8
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026090939-disdain-corridor-626c@gregkh' --subject-prefix 'PATCH 6.6.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From e57140944b5a47a7fd5a142faab29a02af040bc8 Mon Sep 17 00:00:00 2001
From: Li Chen <me@linux.beauty>
Date: Tue, 30 Jun 2026 17:23:33 +0800
Subject: [PATCH] nvdimm: virtio_pmem: refcount requests for token lifetime

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>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <20260630092338.2094628-9-me@linux.beauty>

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index 8c0d4347938a..1cf53f75b128 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) {
+	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;
+		}
 
-		dev_info(&vdev->dev, "failed to send command to virtio pmem device, no free slots in the virtqueue\n");
+		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 e6dfc10ce076..3af92588bd9d 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;
 

[PATCH 6.6.y 1/6] nvdimm: preserve flush callback -ENOMEM

[Sasha Levin]

From: Li Chen <me@linux.beauty>

[ Upstream commit 6b7108712a4b1c37cac69815aede1dde202b3187 ]

nvdimm_flush() maps provider flush failures to -EIO. Keep that default
because provider callbacks can report host-side or backend failures that
should remain generic I/O errors to the guest.

Guest-side allocation failures should not be reported as I/O errors. In the
virtio-pmem path, the flush request allocation can fail with -ENOMEM before
any request is submitted to the host. Mapping that to -EIO makes resource
pressure look like media failure.

Preserve -ENOMEM from provider callbacks and continue to map other non-zero
provider failures to -EIO. The generic flush path still returns 0, and
pmem_submit_bio() already converts errno values to block status for bio
completion.

Suggested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Signed-off-by: Li Chen <me@linux.beauty>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <20260630092338.2094628-2-me@linux.beauty>
Stable-dep-of: e57140944b5a ("nvdimm: virtio_pmem: refcount requests for token lifetime")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvdimm/region_devs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index c13264c7b0deb..f6d14dd7b387c 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -1112,7 +1112,8 @@ int nvdimm_flush(struct nd_region *nd_region, struct bio *bio)
 	if (!nd_region->flush)
 		rc = generic_nvdimm_flush(nd_region);
 	else {
-		if (nd_region->flush(nd_region, bio))
+		rc = nd_region->flush(nd_region, bio);
+		if (rc && rc != -ENOMEM)
 			rc = -EIO;
 	}
 
-- 
2.53.0

[PATCH 6.6.y 2/6] nvdimm: pmem: keep PREFLUSH before data writes

[Sasha Levin]

From: Li Chen <me@linux.beauty>

[ Upstream commit c644a2f8fef5618fcf453c591177700fd07dd024 ]

pmem_submit_bio() records a REQ_PREFLUSH error, but continues to copy the
bio data and can later overwrite the error with a successful REQ_FUA flush.
That lets data writes run after a failed preflush and can complete the bio
successfully despite the failed ordering barrier.

Run the REQ_PREFLUSH flush synchronously before touching the bio data and
complete the bio with the flush error if it fails. Keep asynchronous flush
chaining for REQ_FUA. At that point, data copy has completed and the parent
bio can wait for the chained flush bio.

Signed-off-by: Li Chen <me@linux.beauty>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <20260630092338.2094628-3-me@linux.beauty>
Stable-dep-of: e57140944b5a ("nvdimm: virtio_pmem: refcount requests for token lifetime")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvdimm/pmem.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4e8fdcb3f1c82..e82c8e7ec3720 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -209,8 +209,14 @@ static void pmem_submit_bio(struct bio *bio)
 	struct pmem_device *pmem = bio->bi_bdev->bd_disk->private_data;
 	struct nd_region *nd_region = to_region(pmem);
 
-	if (bio->bi_opf & REQ_PREFLUSH)
-		ret = nvdimm_flush(nd_region, bio);
+	if (bio->bi_opf & REQ_PREFLUSH) {
+		ret = nvdimm_flush(nd_region, NULL);
+		if (ret) {
+			bio->bi_status = errno_to_blk_status(ret);
+			bio_endio(bio);
+			return;
+		}
+	}
 
 	do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue);
 	if (do_acct)
@@ -230,7 +236,7 @@ static void pmem_submit_bio(struct bio *bio)
 	if (do_acct)
 		bio_end_io_acct(bio, start);
 
-	if (bio->bi_opf & REQ_FUA)
+	if ((bio->bi_opf & REQ_FUA) && !bio->bi_status)
 		ret = nvdimm_flush(nd_region, bio);
 
 	if (ret)
-- 
2.53.0

[PATCH 6.6.y 3/6] nvdimm: virtio_pmem: stop allocating child flush bio

[Sasha Levin]

From: Li Chen <me@linux.beauty>

[ Upstream commit 40f356e610df95728074b1fc2e2ccb54ca1b5659 ]

pmem_submit_bio() passes the parent bio to nvdimm_flush() for
REQ_FUA. For virtio-pmem this makes async_pmem_flush() allocate
and submit a child PREFLUSH bio chained to the parent.

That child allocation is in the block submit path. Making it
blocking with GFP_NOIO can consume the same global bio mempool that
submit_bio() uses, while making it GFP_ATOMIC can fail under
pressure. A forced failure of the child allocation produced:

virtio_pmem: forcing child bio allocation failure for test
Buffer I/O error on dev pmem0, logical block 0, lost sync page write
EXT4-fs (pmem0): I/O error while writing superblock
EXT4-fs (pmem0): mount failed

Avoid the child bio without turning REQ_FUA into a synchronous
submit-path wait. Let provider flush callbacks return
NVDIMM_FLUSH_ASYNC after taking ownership of parent bio completion.
pmem_submit_bio() returns in that case, and virtio-pmem queues an
ordered WQ_MEM_RECLAIM work item that runs the existing host flush
path and completes the parent bio.

This keeps the asynchronous completion model of the child-bio path
while removing the child bio allocation from the submit path.

Signed-off-by: Li Chen <me@linux.beauty>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <20260630092338.2094628-5-me@linux.beauty>

Backport notes for 6.6:
Use kmalloc(sizeof(*flush), GFP_NOIO), as kmalloc_obj() is not
available in this tree. Omit the virtio_pmem_freeze() workqueue-drain
hunk because this driver has no freeze/restore callbacks or shared-memory
feature table. Keep workqueue allocation, probe-error cleanup and remove
teardown in the existing stable driver. Correct the host-response comment
so the remaining wait-flag prerequisite has matching patch context.

Retain only the functions introduced by this dependency upstream. The
GFP_NOIO request-allocation, waiter-wakeup and READ_ONCE()/WRITE_ONCE()
prerequisites still precede the target refcount fix; their additional
helper is not folded into this dependency.

Stable-dep-of: e57140944b5a ("nvdimm: virtio_pmem: refcount requests for token lifetime")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvdimm/nd_virtio.c   | 56 +++++++++++++++++++++++++-----------
 drivers/nvdimm/pmem.c        |  5 +++-
 drivers/nvdimm/region_devs.c |  2 ++
 drivers/nvdimm/virtio_pmem.c | 14 ++++++++-
 drivers/nvdimm/virtio_pmem.h |  4 +++
 include/linux/libnvdimm.h    |  9 ++++++
 6 files changed, 71 insertions(+), 19 deletions(-)

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index e5a7b031da2d6..63d420a7866f5 100644
--- a/drivers/nvdimm/nd_virtio.c
+++ b/drivers/nvdimm/nd_virtio.c
@@ -9,6 +9,12 @@
 #include "virtio_pmem.h"
 #include "nd.h"
 
+struct virtio_pmem_flush_work {
+	struct work_struct work;
+	struct nd_region *nd_region;
+	struct bio *bio;
+};
+
  /* The interrupt handler */
 void virtio_pmem_host_ack(struct virtqueue *vq)
 {
@@ -98,7 +104,7 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 		dev_info(&vdev->dev, "failed to send command to virtio pmem device\n");
 		err = -EIO;
 	} else {
-		/* A host repsonse results in "host_ack" getting called */
+		/* A host response results in "host_ack" getting called */
 		wait_event(req_data->host_acked, req_data->done);
 		err = le32_to_cpu(req_data->resp.ret);
 	}
@@ -107,30 +113,46 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 	return err;
 };
 
+static void virtio_pmem_flush_work(struct work_struct *work)
+{
+	struct virtio_pmem_flush_work *flush;
+	int err;
+
+	flush = container_of(work, struct virtio_pmem_flush_work, work);
+	err = virtio_pmem_flush(flush->nd_region);
+	if (err > 0)
+		err = -EIO;
+	if (err)
+		flush->bio->bi_status = errno_to_blk_status(err);
+	bio_endio(flush->bio);
+	kfree(flush);
+}
+
 /* The asynchronous flush callback function */
 int async_pmem_flush(struct nd_region *nd_region, struct bio *bio)
 {
-	/*
-	 * Create child bio for asynchronous flush and chain with
-	 * parent bio. Otherwise directly call nd_region flush.
-	 */
-	if (bio && bio->bi_iter.bi_sector != -1) {
-		struct bio *child = bio_alloc(bio->bi_bdev, 0,
-					      REQ_OP_WRITE | REQ_PREFLUSH,
-					      GFP_ATOMIC);
+	struct virtio_device *vdev = nd_region->provider_data;
+	struct virtio_pmem *vpmem = vdev->priv;
+	struct virtio_pmem_flush_work *flush;
+	int err;
 
-		if (!child)
+	if (bio && bio->bi_iter.bi_sector != -1) {
+		flush = kmalloc(sizeof(*flush), GFP_NOIO);
+		if (!flush)
 			return -ENOMEM;
-		bio_clone_blkg_association(child, bio);
-		child->bi_iter.bi_sector = -1;
-		bio_chain(child, bio);
-		submit_bio(child);
-		return 0;
+
+		INIT_WORK(&flush->work, virtio_pmem_flush_work);
+		flush->nd_region = nd_region;
+		flush->bio = bio;
+		queue_work(vpmem->flush_wq, &flush->work);
+		return NVDIMM_FLUSH_ASYNC;
 	}
-	if (virtio_pmem_flush(nd_region))
+
+	err = virtio_pmem_flush(nd_region);
+	if (err > 0)
 		return -EIO;
 
-	return 0;
+	return err;
 };
 EXPORT_SYMBOL_GPL(async_pmem_flush);
 MODULE_LICENSE("GPL");
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index e82c8e7ec3720..f2a3270e8f17c 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -236,8 +236,11 @@ static void pmem_submit_bio(struct bio *bio)
 	if (do_acct)
 		bio_end_io_acct(bio, start);
 
-	if ((bio->bi_opf & REQ_FUA) && !bio->bi_status)
+	if ((bio->bi_opf & REQ_FUA) && !bio->bi_status) {
 		ret = nvdimm_flush(nd_region, bio);
+		if (ret == NVDIMM_FLUSH_ASYNC)
+			return;
+	}
 
 	if (ret)
 		bio->bi_status = errno_to_blk_status(ret);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index f6d14dd7b387c..ca53aaf7f5724 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -1113,6 +1113,8 @@ int nvdimm_flush(struct nd_region *nd_region, struct bio *bio)
 		rc = generic_nvdimm_flush(nd_region);
 	else {
 		rc = nd_region->flush(nd_region, bio);
+		if (rc > 0)
+			return rc;
 		if (rc && rc != -ENOMEM)
 			rc = -EIO;
 	}
diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index 4eebb2ec3cf97..4a8e7a2f81459 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -52,10 +52,17 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 	mutex_init(&vpmem->flush_lock);
 	vpmem->vdev = vdev;
 	vdev->priv = vpmem;
+	vpmem->flush_wq = alloc_ordered_workqueue("virtio-pmem-flush",
+						  WQ_MEM_RECLAIM);
+	if (!vpmem->flush_wq) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
 	err = init_vq(vpmem);
 	if (err) {
 		dev_err(&vdev->dev, "failed to initialize virtio pmem vq's\n");
-		goto out_err;
+		goto out_wq;
 	}
 
 	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
@@ -110,6 +117,8 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 	nvdimm_bus_unregister(vpmem->nvdimm_bus);
 out_vq:
 	vdev->config->del_vqs(vdev);
+out_wq:
+	destroy_workqueue(vpmem->flush_wq);
 out_err:
 	return err;
 }
@@ -117,10 +126,13 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 static void virtio_pmem_remove(struct virtio_device *vdev)
 {
 	struct nvdimm_bus *nvdimm_bus = dev_get_drvdata(&vdev->dev);
+	struct virtio_pmem *vpmem = vdev->priv;
 
 	nvdimm_bus_unregister(nvdimm_bus);
+	drain_workqueue(vpmem->flush_wq);
 	vdev->config->del_vqs(vdev);
 	virtio_reset_device(vdev);
+	destroy_workqueue(vpmem->flush_wq);
 }
 
 static struct virtio_driver virtio_pmem_driver = {
diff --git a/drivers/nvdimm/virtio_pmem.h b/drivers/nvdimm/virtio_pmem.h
index f72cf17f9518f..e6dfc10ce0762 100644
--- a/drivers/nvdimm/virtio_pmem.h
+++ b/drivers/nvdimm/virtio_pmem.h
@@ -15,6 +15,7 @@
 #include <linux/libnvdimm.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
+#include <linux/workqueue.h>
 
 struct virtio_pmem_request {
 	struct virtio_pmem_req req;
@@ -39,6 +40,9 @@ struct virtio_pmem {
 	/* Serialize flush requests to the device. */
 	struct mutex flush_lock;
 
+	/* Complete asynchronous FUA flushes outside the submit path. */
+	struct workqueue_struct *flush_wq;
+
 	/* nvdimm bus registers virtio pmem device */
 	struct nvdimm_bus *nvdimm_bus;
 	struct nvdimm_bus_descriptor nd_desc;
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index e772aae718431..04043b7d5712a 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -122,6 +122,15 @@ struct nd_mapping_desc {
 };
 
 struct nd_region;
+
+/*
+ * Provider flush callback return values:
+ *   0: flush completed synchronously
+ *  <0: flush failed
+ *  >0: flush completion was queued and @bio will be completed later
+ */
+#define NVDIMM_FLUSH_ASYNC 1
+
 struct nd_region_desc {
 	struct resource *res;
 	struct nd_mapping_desc *mapping;
-- 
2.53.0

[PATCH 6.6.y 4/6] nvdimm: virtio_pmem: always wake -ENOSPC waiters

[Sasha Levin]

From: Li Chen <me@linux.beauty>

[ Upstream commit 811808761e19fdea1c25b7c76734b8945f758f27 ]

virtio_pmem_host_ack() reclaims virtqueue descriptors with
virtqueue_get_buf(). The -ENOSPC waiter wakeup is tied to completing the
returned token. If token completion is skipped for any reason, reclaimed
descriptors may not wake a waiter and the submitter may sleep forever
waiting for a free slot. Always wake one -ENOSPC waiter for each virtqueue
completion before touching the returned token.

Signed-off-by: Li Chen <me@linux.beauty>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <20260630092338.2094628-7-me@linux.beauty>
Stable-dep-of: e57140944b5a ("nvdimm: virtio_pmem: refcount requests for token lifetime")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvdimm/nd_virtio.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index 63d420a7866f5..4b81544db4a61 100644
--- a/drivers/nvdimm/nd_virtio.c
+++ b/drivers/nvdimm/nd_virtio.c
@@ -15,26 +15,33 @@ struct virtio_pmem_flush_work {
 	struct bio *bio;
 };
 
+static void virtio_pmem_wake_one_waiter(struct virtio_pmem *vpmem)
+{
+	struct virtio_pmem_request *req_buf;
+
+	if (list_empty(&vpmem->req_list))
+		return;
+
+	req_buf = list_first_entry(&vpmem->req_list,
+				   struct virtio_pmem_request, list);
+	req_buf->wq_buf_avail = true;
+	wake_up(&req_buf->wq_buf);
+	list_del(&req_buf->list);
+}
+
  /* The interrupt handler */
 void virtio_pmem_host_ack(struct virtqueue *vq)
 {
 	struct virtio_pmem *vpmem = vq->vdev->priv;
-	struct virtio_pmem_request *req_data, *req_buf;
+	struct virtio_pmem_request *req_data;
 	unsigned long flags;
 	unsigned int len;
 
 	spin_lock_irqsave(&vpmem->pmem_lock, flags);
 	while ((req_data = virtqueue_get_buf(vq, &len)) != NULL) {
+		virtio_pmem_wake_one_waiter(vpmem);
 		req_data->done = true;
 		wake_up(&req_data->host_acked);
-
-		if (!list_empty(&vpmem->req_list)) {
-			req_buf = list_first_entry(&vpmem->req_list,
-					struct virtio_pmem_request, list);
-			req_buf->wq_buf_avail = true;
-			wake_up(&req_buf->wq_buf);
-			list_del(&req_buf->list);
-		}
 	}
 	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
 }
-- 
2.53.0

[PATCH 6.6.y 5/6] nvdimm: virtio_pmem: use READ_ONCE()/WRITE_ONCE() for wait flags

[Sasha Levin]

From: Li Chen <me@linux.beauty>

[ Upstream commit 08e72a5ba1ab9dc0adf993ff0f4d606a1e3445a8 ]

Use READ_ONCE()/WRITE_ONCE() for the wait_event() flags (done and
wq_buf_avail). They are observed by waiters without pmem_lock, so make
the accesses explicit single loads/stores and avoid compiler
reordering/caching across the wait/wake paths.

Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Signed-off-by: Li Chen <me@linux.beauty>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <20260630092338.2094628-8-me@linux.beauty>
Stable-dep-of: e57140944b5a ("nvdimm: virtio_pmem: refcount requests for token lifetime")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvdimm/nd_virtio.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index 4b81544db4a61..ce3f14d99eac6 100644
--- a/drivers/nvdimm/nd_virtio.c
+++ b/drivers/nvdimm/nd_virtio.c
@@ -24,9 +24,9 @@ static void virtio_pmem_wake_one_waiter(struct virtio_pmem *vpmem)
 
 	req_buf = list_first_entry(&vpmem->req_list,
 				   struct virtio_pmem_request, list);
-	req_buf->wq_buf_avail = true;
+	list_del_init(&req_buf->list);
+	WRITE_ONCE(req_buf->wq_buf_avail, true);
 	wake_up(&req_buf->wq_buf);
-	list_del(&req_buf->list);
 }
 
  /* The interrupt handler */
@@ -40,7 +40,7 @@ void virtio_pmem_host_ack(struct virtqueue *vq)
 	spin_lock_irqsave(&vpmem->pmem_lock, flags);
 	while ((req_data = virtqueue_get_buf(vq, &len)) != NULL) {
 		virtio_pmem_wake_one_waiter(vpmem);
-		req_data->done = true;
+		WRITE_ONCE(req_data->done, true);
 		wake_up(&req_data->host_acked);
 	}
 	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
@@ -72,7 +72,7 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 	if (!req_data)
 		return -ENOMEM;
 
-	req_data->done = false;
+	WRITE_ONCE(req_data->done, false);
 	init_waitqueue_head(&req_data->host_acked);
 	init_waitqueue_head(&req_data->wq_buf);
 	INIT_LIST_HEAD(&req_data->list);
@@ -93,12 +93,12 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 					GFP_ATOMIC)) == -ENOSPC) {
 
 		dev_info(&vdev->dev, "failed to send command to virtio pmem device, no free slots in the virtqueue\n");
-		req_data->wq_buf_avail = false;
+		WRITE_ONCE(req_data->wq_buf_avail, false);
 		list_add_tail(&req_data->list, &vpmem->req_list);
 		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
 
 		/* A host response results in "host_ack" getting called */
-		wait_event(req_data->wq_buf, req_data->wq_buf_avail);
+		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);
@@ -112,7 +112,7 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
 		err = -EIO;
 	} else {
 		/* A host response results in "host_ack" getting called */
-		wait_event(req_data->host_acked, req_data->done);
+		wait_event(req_data->host_acked, READ_ONCE(req_data->done));
 		err = le32_to_cpu(req_data->resp.ret);
 	}
 
-- 
2.53.0

[PATCH 6.6.y 6/6] nvdimm: virtio_pmem: refcount requests for token lifetime

[Sasha Levin]

From: Li Chen <me@linux.beauty>

[ Upstream commit e57140944b5a47a7fd5a142faab29a02af040bc8 ]

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>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <20260630092338.2094628-9-me@linux.beauty>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 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 ce3f14d99eac6..ffe39529acbc8 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;
 
-- 
2.53.0