Merge remote-tracking branch 'remotes/maxreitz/tags/pull-block-2019-11-04' into staging

Block patches for 4.2-rc0:
- Work around XFS write-zeroes bug in file-posix block driver
- Fix backup job with compression
- Fix to the NVMe block driver header

# gpg: Signature made Mon 04 Nov 2019 09:01:16 GMT
# gpg:                using RSA key 91BEB60A30DB3E8857D11829F407DB0061D5CF40
# gpg:                issuer "mreitz@redhat.com"
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>" [full]
# Primary key fingerprint: 91BE B60A 30DB 3E88 57D1  1829 F407 DB00 61D5 CF40

* remotes/maxreitz/tags/pull-block-2019-11-04:
  block/file-posix: Let post-EOF fallocate serialize
  block: Add bdrv_co_get_self_request()
  block: Make wait/mark serialising requests public
  block/block-copy: fix s->copy_size for compressed cluster
  nvme: fix NSSRS offset in CAP register

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 73 insertions, 15 deletions

diff --git a/block/block-copy.c b/block/block-copy.c
index c39cc9cffe4..79798a1567b 100644
--- a/block/block-copy.c
+++ b/block/block-copy.c
@@ -109,9 +109,9 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
         s->use_copy_range = false;
         s->copy_size = cluster_size;
     } else if (write_flags & BDRV_REQ_WRITE_COMPRESSED) {
-        /* Compression is not supported for copy_range */
+        /* Compression supports only cluster-size writes and no copy-range. */
         s->use_copy_range = false;
-        s->copy_size = MAX(cluster_size, BLOCK_COPY_MAX_BUFFER);
+        s->copy_size = cluster_size;
     } else {
         /*
          * copy_range does not respect max_transfer (it's a TODO), so we factor
diff --git a/block/file-posix.c b/block/file-posix.c
index 0b7e904d484..1f0f61a02b1 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -2721,6 +2721,42 @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
     RawPosixAIOData acb;
     ThreadPoolFunc *handler;
 
+#ifdef CONFIG_FALLOCATE
+    if (offset + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) {
+        BdrvTrackedRequest *req;
+        uint64_t end;
+
+        /*
+         * This is a workaround for a bug in the Linux XFS driver,
+         * where writes submitted through the AIO interface will be
+         * discarded if they happen beyond a concurrently running
+         * fallocate() that increases the file length (i.e., both the
+         * write and the fallocate() happen beyond the EOF).
+         *
+         * To work around it, we extend the tracked request for this
+         * zero write until INT64_MAX (effectively infinity), and mark
+         * it as serializing.
+         *
+         * We have to enable this workaround for all filesystems and
+         * AIO modes (not just XFS with aio=native), because for
+         * remote filesystems we do not know the host configuration.
+         */
+
+        req = bdrv_co_get_self_request(bs);
+        assert(req);
+        assert(req->type == BDRV_TRACKED_WRITE);
+        assert(req->offset <= offset);
+        assert(req->offset + req->bytes >= offset + bytes);
+
+        end = INT64_MAX & -(uint64_t)bs->bl.request_alignment;
+        req->bytes = end - req->offset;
+        req->overlap_bytes = req->bytes;
+
+        bdrv_mark_request_serialising(req, bs->bl.request_alignment);
+        bdrv_wait_serialising_requests(req);
+    }
+#endif
+
     acb = (RawPosixAIOData) {
         .bs             = bs,
         .aio_fildes     = s->fd,
diff --git a/block/io.c b/block/io.c
index 02659f994d0..f75777f5ea7 100644
--- a/block/io.c
+++ b/block/io.c
@@ -715,7 +715,7 @@ static void tracked_request_begin(BdrvTrackedRequest *req,
     qemu_co_mutex_unlock(&bs->reqs_lock);
 }
 
-static void mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
+void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
 {
     int64_t overlap_offset = req->offset & ~(align - 1);
     uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
@@ -743,6 +743,24 @@ static bool is_request_serialising_and_aligned(BdrvTrackedRequest *req)
 }
 
 /**
+ * Return the tracked request on @bs for the current coroutine, or
+ * NULL if there is none.
+ */
+BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs)
+{
+    BdrvTrackedRequest *req;
+    Coroutine *self = qemu_coroutine_self();
+
+    QLIST_FOREACH(req, &bs->tracked_requests, list) {
+        if (req->co == self) {
+            return req;
+        }
+    }
+
+    return NULL;
+}
+
+/**
  * Round a region to cluster boundaries
  */
 void bdrv_round_to_clusters(BlockDriverState *bs,
@@ -805,7 +823,7 @@ void bdrv_dec_in_flight(BlockDriverState *bs)
     bdrv_wakeup(bs);
 }
 
-static bool coroutine_fn wait_serialising_requests(BdrvTrackedRequest *self)
+bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self)
 {
     BlockDriverState *bs = self->bs;
     BdrvTrackedRequest *req;
@@ -1437,14 +1455,14 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
          * with each other for the same cluster.  For example, in copy-on-read
          * it ensures that the CoR read and write operations are atomic and
          * guest writes cannot interleave between them. */
-        mark_request_serialising(req, bdrv_get_cluster_size(bs));
+        bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
     }
 
     /* BDRV_REQ_SERIALISING is only for write operation */
     assert(!(flags & BDRV_REQ_SERIALISING));
 
     if (!(flags & BDRV_REQ_NO_SERIALISING)) {
-        wait_serialising_requests(req);
+        bdrv_wait_serialising_requests(req);
     }
 
     if (flags & BDRV_REQ_COPY_ON_READ) {
@@ -1841,10 +1859,10 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
     assert(!(flags & ~BDRV_REQ_MASK));
 
     if (flags & BDRV_REQ_SERIALISING) {
-        mark_request_serialising(req, bdrv_get_cluster_size(bs));
+        bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs));
     }
 
-    waited = wait_serialising_requests(req);
+    waited = bdrv_wait_serialising_requests(req);
 
     assert(!waited || !req->serialising ||
            is_request_serialising_and_aligned(req));
@@ -2008,8 +2026,8 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
 
     padding = bdrv_init_padding(bs, offset, bytes, &pad);
     if (padding) {
-        mark_request_serialising(req, align);
-        wait_serialising_requests(req);
+        bdrv_mark_request_serialising(req, align);
+        bdrv_wait_serialising_requests(req);
 
         bdrv_padding_rmw_read(child, req, &pad, true);
 
@@ -2111,8 +2129,8 @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
     }
 
     if (bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad)) {
-        mark_request_serialising(&req, align);
-        wait_serialising_requests(&req);
+        bdrv_mark_request_serialising(&req, align);
+        bdrv_wait_serialising_requests(&req);
         bdrv_padding_rmw_read(child, &req, &pad, false);
     }
 
@@ -3205,7 +3223,7 @@ static int coroutine_fn bdrv_co_copy_range_internal(
         /* BDRV_REQ_SERIALISING is only for write operation */
         assert(!(read_flags & BDRV_REQ_SERIALISING));
         if (!(read_flags & BDRV_REQ_NO_SERIALISING)) {
-            wait_serialising_requests(&req);
+            bdrv_wait_serialising_requests(&req);
         }
 
         ret = src->bs->drv->bdrv_co_copy_range_from(src->bs,
@@ -3336,7 +3354,7 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
      * new area, we need to make sure that no write requests are made to it
      * concurrently or they might be overwritten by preallocation. */
     if (new_bytes) {
-        mark_request_serialising(&req, 1);
+        bdrv_mark_request_serialising(&req, 1);
     }
     if (bs->read_only) {
         error_setg(errp, "Image is read-only");
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 02dc0034a2c..dd033d0b375 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -999,6 +999,10 @@ extern unsigned int bdrv_drain_all_count;
 void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
 void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
 
+bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self);
+void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align);
+BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs);
+
 int get_tmp_filename(char *filename, int size);
 BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
                             const char *filename);
diff --git a/include/block/nvme.h b/include/block/nvme.h
index ab5943b90aa..8fb941c6537 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -23,7 +23,7 @@ enum NvmeCapShift {
     CAP_AMS_SHIFT      = 17,
     CAP_TO_SHIFT       = 24,
     CAP_DSTRD_SHIFT    = 32,
-    CAP_NSSRS_SHIFT    = 33,
+    CAP_NSSRS_SHIFT    = 36,
     CAP_CSS_SHIFT      = 37,
     CAP_MPSMIN_SHIFT   = 48,
     CAP_MPSMAX_SHIFT   = 52,