Under heavy concurrent flush traffic, virtio-pmem can overflow its request
virtqueue (req_vq): virtqueue_add_sgs() starts returning -ENOSPC and the
driver logs "no free slots in the virtqueue". Shortly after that the
device enters VIRTIO_CONFIG_S_NEEDS_RESET and flush requests fail with
"virtio pmem device needs a reset".
Serialize virtio_pmem_flush() with a per-device mutex so only one flush
request is in-flight at a time. This prevents req_vq descriptor overflow
under high concurrency.
Reproducer (guest with virtio-pmem):
- mkfs.ext4 -F /dev/pmem0
- mount -t ext4 -o dax,noatime /dev/pmem0 /mnt/bench
- fio: ioengine=io_uring rw=randwrite bs=4k iodepth=64 numjobs=64
direct=1 fsync=1 runtime=30s time_based=1
- dmesg: "no free slots in the virtqueue"
"virtio pmem device needs a reset"
Fixes: 6e84200c0a29 ("virtio-pmem: Add virtio pmem driver")
Signed-off-by: Li Chen <me@linux.beauty>
Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://patch.msgid.link/20260203021353.121091-1-me@linux.beauty
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
unsigned long flags;
int err, err1;
+ guard(mutex)(&vpmem->flush_lock);
+
/*
* Don't bother to submit the request to the device if the device is
* not activated.
return -EIO;
}
- might_sleep();
req_data = kmalloc(sizeof(*req_data), GFP_KERNEL);
if (!req_data)
return -ENOMEM;
goto out_err;
}
+ mutex_init(&vpmem->flush_lock);
vpmem->vdev = vdev;
vdev->priv = vpmem;
err = init_vq(vpmem);
#include <linux/module.h>
#include <uapi/linux/virtio_pmem.h>
#include <linux/libnvdimm.h>
+#include <linux/mutex.h>
#include <linux/spinlock.h>
struct virtio_pmem_request {
/* Virtio pmem request queue */
struct virtqueue *req_vq;
+ /* Serialize flush requests to the device. */
+ struct mutex flush_lock;
+
/* nvdimm bus registers virtio pmem device */
struct nvdimm_bus *nvdimm_bus;
struct nvdimm_bus_descriptor nd_desc;