Generally speaking I think this is a wrong approach for our needs. This patch really overengineers the whole situation: - we should not build write requests if the device does not support zeroing. The correct way is to never advertise zeroes for such device. We can't do that in kernel because feature negotiation happens before backend is set. So we should check the limits in QEMU (which also should correctly set max_write_zeroes_sectors in config anyway, so the plumbing will be there) - vhost_blk_retry_zeroes() is probably nice but again not our case. This is a workaround when the device resets limits. We plan to use it with dm-qcow2 and we can just never reset the limit there (why would we
if writing zeroes is just a few bits in cluster tables)

So the whole patch shape should be
- When we get zero request we just construct a simple bio with REQ_OP_WRITE_ZEROES and queue it. (maybe a little check to match bdev_write_zeroes_sectors)

That's it. Let's not add some convoluted code we will never use.
So first I would expect a QEMU patch that reads device zero support and sets max_write_zeroes_sectors limit. Then the simplified version of this patch.

On 11/17/26 11:09, Alexander Ivanov wrote:
Handle VIRTIO_BLK_T_WRITE_ZEROES for parity with virtio-blk. The range
is zeroed with __blkdev_issue_zeroout(), which uses WRITE ZEROES of the
backend or falls back to writing zero pages. The UNMAP flag maps to
the absence of BLKDEV_ZERO_NOUNMAP. The range is issued in chunks of
at most 16 WRITE ZEROES bios and 1 GiB, or 4 MiB ones when zero pages
are written, since each chunk is built in the vhost worker.

The VMM must advertise blk_size equal to the backend logical block
size, max_write_zeroes_sectors aligned to it and at most 8388607, and
max_write_zeroes_seg = 1. A request is zeroed one chunk at a time and
holds vhost_blk_flush() until its last chunk, so a small
max_write_zeroes_sectors keeps vhost ioctls short on backends without
WRITE ZEROES. Our QEMU does not advertise the feature yet.

The guest gets VIRTIO_BLK_S_UNSUPP when VIRTIO_BLK_F_WRITE_ZEROES was
not negotiated, for a payload other than exactly one segment or an
unknown flag, and VIRTIO_BLK_S_IOERR for a read-only backend and for a
range that is unaligned, beyond the capacity or above 8388607 sectors.

https://virtuozzo.atlassian.net/browse/VSTOR-141684
Feature: vhost-blk: in-kernel accelerator for virtio-blk guests
Signed-off-by: Alexander Ivanov <[email protected]>
---
  drivers/vhost/blk.c | 178 +++++++++++++++++++++++++++++++++++++++++++-
  1 file changed, 176 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/blk.c b/drivers/vhost/blk.c
index eea8cca59cac..e27320651469 100644
--- a/drivers/vhost/blk.c
+++ b/drivers/vhost/blk.c
@@ -29,7 +29,8 @@ enum {
                             (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
                             (1ULL << VIRTIO_RING_F_EVENT_IDX) |
                             (1ULL << VIRTIO_BLK_F_MQ) |
-                            (1ULL << VIRTIO_BLK_F_FLUSH),
+                            (1ULL << VIRTIO_BLK_F_FLUSH) |
+                            (1ULL << VIRTIO_BLK_F_WRITE_ZEROES),
  };
/*
@@ -75,6 +76,10 @@ struct vhost_blk_req {
        struct iovec status[VHOST_MAX_METADATA_IOV];
sector_t sector;
+       sector_t nr_sects;
+       sector_t chunk_sects;
+       struct block_device *bdev;
Do we really need bdev? As far as I can see in the only place we use it, it can be derived from req->blk->backend. In general we allocate a lot of vhost_blk_req beforehand and I would prefer to keeps this struct as tight as possible.
+       unsigned int zeroout_flags;
        int bi_opf;
        u16 head;
        size_t len;
@@ -271,6 +276,63 @@ static int vhost_blk_move_bb_to_req(struct vhost_blk_req 
*req)
        return 0;
  }
+/*
+ * The range is zeroed in the vhost worker with vq->mutex held, so it is
+ * split into chunks of a few bios each, much smaller ones when zero pages
+ * are written. The chunk sizes are multiples of any logical block size.
+ */
+#define VHOST_BLK_MAX_WRITE_ZEROES_BIOS                16
+#define VHOST_BLK_MAX_WRITE_ZEROES_SECTORS     (SZ_1G >> SECTOR_SHIFT)
+#define VHOST_BLK_MAX_ZERO_PAGES_SECTORS       (SZ_4M >> SECTOR_SHIFT)
+
+/*
+ * A request holds vhost_blk_flush() until its last chunk completes, so the
+ * whole range is bounded too. No Linux guest sends more, a bio cannot carry
+ * it.
+ */
+#define VHOST_BLK_MAX_WRITE_ZEROES_REQ_SECTORS (UINT_MAX >> SECTOR_SHIFT)
+
+static int vhost_blk_bio_make_zeroes(struct vhost_blk_req *req,
+                                    struct block_device *bdev)
+{
+       sector_t bs_mask = (bdev_logical_block_size(bdev) >> SECTOR_SHIFT) - 1;
+       sector_t max_sects = (sector_t)bdev_write_zeroes_sectors(bdev) *
+                            VHOST_BLK_MAX_WRITE_ZEROES_BIOS & ~bs_mask;
+       struct bio *bio = NULL;
+       int ret = -EOPNOTSUPP;
+
+       req->chunk_sects = min3(req->nr_sects, max_sects,
+                               (sector_t)VHOST_BLK_MAX_WRITE_ZEROES_SECTORS);
+       /* The limit may appear after it was read, and no bio is built then */
+       if (req->chunk_sects)
+               ret = __blkdev_issue_zeroout(bdev, req->sector,
+                                            req->chunk_sects, GFP_KERNEL, &bio,
+                                            req->zeroout_flags |
+                                            BLKDEV_ZERO_NOFALLBACK);
+       if (ret == -EOPNOTSUPP) {
+               req->chunk_sects = min_t(sector_t, req->nr_sects,
+                                        VHOST_BLK_MAX_ZERO_PAGES_SECTORS);
+               ret = __blkdev_issue_zeroout(bdev, req->sector,
+                                            req->chunk_sects, GFP_KERNEL, &bio,
+                                            req->zeroout_flags);
+       }
+       if (ret)
+               return ret;
+
+       bio->bi_private = req;
+       bio->bi_end_io  = vhost_blk_req_done;
+       req->bio = req->inline_bio;
+       req->bio[0] = bio;
+
+       /* Zero pages are plain writes, a failure of them is not retried */
+       if (bio_op(bio) != REQ_OP_WRITE_ZEROES)
+               req->bi_opf = REQ_OP_WRITE;
+
+       atomic_set(&req->bio_nr, 1);
+
+       return 0;
+}
+
  static int vhost_blk_bio_make(struct vhost_blk_req *req,
                              struct block_device *bdev)
  {
@@ -284,6 +346,9 @@ static int vhost_blk_bio_make(struct vhost_blk_req *req,
        if (unlikely(req->bi_opf & REQ_PREFLUSH))
                return vhost_blk_bio_make_simple(req, bdev);
+ if (req->bi_opf == REQ_OP_WRITE_ZEROES)
+               return vhost_blk_bio_make_zeroes(req, bdev);
+
        /*
         * Requests with unaligned io vectors are not supported by underlined
         * block device, let's use an aligned intermediary "bounce buffer" to
@@ -451,6 +516,50 @@ static bool vhost_blk_backend_ro(struct file *f)
               bdev_read_only(I_BDEV(f->f_mapping->host));
  }
+static int vhost_blk_parse_write_zeroes(struct vhost_blk_req *req, u8 *status)
+{
+       struct file *f = vhost_vq_get_backend(&req->blk_vq->vq);
+       struct block_device *bdev = I_BDEV(f->f_mapping->host);
+       sector_t bs_mask = (bdev_logical_block_size(bdev) >> SECTOR_SHIFT) - 1;
+       struct virtio_blk_discard_write_zeroes seg;
+       struct iov_iter iter;
+       u32 flags;
+
+       if (!vhost_has_feature(&req->blk_vq->vq, VIRTIO_BLK_F_WRITE_ZEROES) ||
+           req->len != sizeof(seg)) {
+               *status = VIRTIO_BLK_S_UNSUPP;
+               return 0;
+       }
+
+       iov_iter_init(&iter, ITER_SOURCE, req->iov, req->iov_nr, req->len);
+       if (copy_from_iter(&seg, sizeof(seg), &iter) != sizeof(seg))
+               return -EFAULT;
+
+       flags = le32_to_cpu(seg.flags);
+       if (flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
+               *status = VIRTIO_BLK_S_UNSUPP;
+               return 0;
+       }
+
+       req->sector = le64_to_cpu(seg.sector);
+       req->nr_sects = le32_to_cpu(seg.num_sectors);
+       req->bdev = bdev;
+       req->zeroout_flags = flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP ?
+                            0 : BLKDEV_ZERO_NOUNMAP;
+
+       if (vhost_blk_backend_ro(f) ||
+           (req->sector | req->nr_sects) & bs_mask ||
+           req->nr_sects > VHOST_BLK_MAX_WRITE_ZEROES_REQ_SECTORS ||
+           req->sector > bdev_nr_sectors(bdev) ||
+           req->nr_sects > bdev_nr_sectors(bdev) - req->sector) {
+               *status = VIRTIO_BLK_S_IOERR;
+               return 0;
+       }
+
+       *status = VIRTIO_BLK_S_OK;
+       return 0;
+}
+
  static int vhost_blk_req_handle(struct vhost_virtqueue *vq,
                                struct virtio_blk_outhdr *hdr,
                                u16 head, u16 out, u16 in)
@@ -475,6 +584,7 @@ static int vhost_blk_req_handle(struct vhost_virtqueue *vq,
        req->head    = head;
        req->blk     = blk;
        req->sector  = vhost64_to_cpu(vq, hdr->sector);
+       req->nr_sects        = 0;
        req->iov     = blk_vq->iov;
        req->bio_err = 0;
        in_len          = iov_length(vq->iov + out, in);
@@ -490,7 +600,7 @@ static int vhost_blk_req_handle(struct vhost_virtqueue *vq,
        req->status[0].iov_base = st->iov_base + st->iov_len;
        req->status[0].iov_len = sizeof(status);
- if (type == VIRTIO_BLK_T_OUT) {
+       if (type == VIRTIO_BLK_T_OUT || type == VIRTIO_BLK_T_WRITE_ZEROES) {
                data_iov = vq->iov;
                data_nr = out;
        } else {
@@ -538,6 +648,22 @@ static int vhost_blk_req_handle(struct vhost_virtqueue *vq,
                req->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
                ret = vhost_blk_req_submit(req);
                break;
+       case VIRTIO_BLK_T_WRITE_ZEROES:
+               ret = vhost_blk_parse_write_zeroes(req, &status);
+               if (ret)
+                       break;
+               if (status == VIRTIO_BLK_S_OK && req->nr_sects) {
+                       req->bi_opf = REQ_OP_WRITE_ZEROES;
+                       ret = vhost_blk_req_submit(req);
+                       if (ret != -EPERM)
+                               break;
+                       status = VIRTIO_BLK_S_IOERR;
+               }
+               ret = vhost_blk_set_status(req, status);
+               if (ret)
+                       break;
+               vhost_add_used_and_signal(&blk->dev, vq, head, sizeof(status));
+               break;
        case VIRTIO_BLK_T_GET_ID:
                len = min_t(size_t,
                            strnlen(blk->serial, VIRTIO_BLK_ID_BYTES) + 1,
@@ -561,6 +687,51 @@ static int vhost_blk_req_handle(struct vhost_virtqueue *vq,
        return ret;
  }
+/*
+ * Some devices clear their WRITE ZEROES limit only after a failed request,
+ * as blkdev_issue_write_zeroes() expects. Retry such a request with zero
+ * pages instead of failing it.
+ */
+static bool vhost_blk_retry_zeroes(struct vhost_blk_req *req)
+{
+       if (!req->bio_err || req->bi_opf != REQ_OP_WRITE_ZEROES)
+               return false;
+
+       if (bdev_write_zeroes_sectors(req->bdev))
+               return false;
+
+       /* The limit may come back before the bio is built, retry only once */
+       req->bi_opf = REQ_OP_WRITE;
+       if (vhost_blk_bio_make_zeroes(req, req->bdev))
+               return false;
+
+       req->bio_err = 0;
+       vhost_blk_bio_send(req);
+       return true;
+}
+
+/* Issue the next chunk of a write-zeroes range, if any is left */
+static bool vhost_blk_next_zeroes(struct vhost_blk_req *req)
+{
+       int ret;
+
+       if (req->bio_err || req->nr_sects <= req->chunk_sects)
+               return false;
+
+       req->sector += req->chunk_sects;
+       req->nr_sects -= req->chunk_sects;
+
+       req->bi_opf = REQ_OP_WRITE_ZEROES;
+       ret = vhost_blk_bio_make_zeroes(req, req->bdev);
+       if (ret) {
+               req->bio_err = ret;
+               return false;
+       }
+
+       vhost_blk_bio_send(req);
+       return true;
+}
+
  static void vhost_blk_handle_guest_kick(struct vhost_work *work)
  {
        struct virtio_blk_outhdr hdr;
@@ -661,6 +832,9 @@ static void vhost_blk_handle_host_kick(struct vhost_work 
*work)
                if (!blk)
                        blk = req->blk;
+ if (vhost_blk_retry_zeroes(req) || vhost_blk_next_zeroes(req))
+                       continue;
+
                if (!req->bio_err && req->bb && req->bi_opf == REQ_OP_READ) {
                        if (vhost_blk_move_bb_to_req(req))
                                req->bio_err = EINVAL;

_______________________________________________
Devel mailing list
[email protected]
https://lists.openvz.org/mailman/listinfo/devel

Reply via email to