[PATCH v2] nvdimm: virtio_pmem: serialize flush requests

[Li Chen]

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>
---
v2:
- Use guard(mutex)() for flush_lock (as suggested by Ira Weiny).
- Drop redundant might_sleep() next to guard(mutex)() (as suggested by Michael 
S. Tsirkin).

 drivers/nvdimm/nd_virtio.c   | 3 ++-
 drivers/nvdimm/virtio_pmem.c | 1 +
 drivers/nvdimm/virtio_pmem.h | 4 ++++
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
index c3f07be4aa22..af82385be7c6 100644
--- a/drivers/nvdimm/nd_virtio.c
+++ b/drivers/nvdimm/nd_virtio.c
@@ -44,6 +44,8 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
        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.
@@ -53,7 +55,6 @@ static int virtio_pmem_flush(struct nd_region *nd_region)
                return -EIO;
        }
 
-       might_sleep();
        req_data = kmalloc(sizeof(*req_data), GFP_KERNEL);
        if (!req_data)
                return -ENOMEM;
diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index 2396d19ce549..77b196661905 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -64,6 +64,7 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
                goto out_err;
        }
 
+       mutex_init(&vpmem->flush_lock);
        vpmem->vdev = vdev;
        vdev->priv = vpmem;
        err = init_vq(vpmem);
diff --git a/drivers/nvdimm/virtio_pmem.h b/drivers/nvdimm/virtio_pmem.h
index 0dddefe594c4..f72cf17f9518 100644
--- a/drivers/nvdimm/virtio_pmem.h
+++ b/drivers/nvdimm/virtio_pmem.h
@@ -13,6 +13,7 @@
 #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 {
@@ -35,6 +36,9 @@ struct virtio_pmem {
        /* 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;
-- 
2.52.0