Merge tag 'pull-block-2023-11-06' of https://gitlab.com/hreitz/qemu into staging

Block patches:
- One patch to make qcow2's discard-no-unref option do better what it is
  supposed to do (i.e. prevent fragmentation)
- Two fixes for zoned requests

# -----BEGIN PGP SIGNATURE-----
#
# iQJGBAABCAAwFiEEy2LXoO44KeRfAE00ofpA0JgBnN8FAmVJHbgSHGhyZWl0ekBy
# ZWRoYXQuY29tAAoJEKH6QNCYAZzfLn4QAKxuUYZaXirv6K4U2tW4aAJtc5uESdwv
# WYhG7YU7MleBGCY0fRoih5thrPrzRLC8o1QhbRcA36+/PAZf4BYrJEfqLUdzuN5x
# 6Vb1n3NRUzPD1+VfL/B9hVZhFbtTOUZuxPGEqCoHAmqBaeKuYRT1bLZbtRtPVLSk
# 5eTMiyrpRMlBWc7O71eGKLqU4k0vAznwHBGf2Z93qWAsKcRZCwbAWYa7Q6rJ9jJ8
# 1jNsQuAk0p74/uGEpFhoEVrFEcV6pMbI4+jB9i0t9YYxT0tLIdIX1VUx+AHJfItk
# IF2stB6SFOaAy2W3Fn+0oJvz40aMLzg9VjEeTpGmdlKC67ZTYa6Obwzy5WNLPIap
# k7VUheUEe8qoKUtxQNxGLR/HKEJSFXyhU0lgAGxE1gl2xc1QFFFsrimpwFd3d37j
# 3PwfhjARHonf4ZXgsvtIjb7nG9seMZYO7Vht0OztJyW8c2XN5OFVPir9xLbd9VUg
# wZNGB8jAsHgj77+S/mRIwpP+laKL8wB7zYZ1mgFI98QJIYqL8tGdV/IiUhLljHzc
# XAmwekOhBMMbgHhliBy9zDuTy59+zZ0FoxZPn/JvBjqBAkEnz9EbhHxi2imQg+1d
# XSoLbx1X1yEbepWz8mCGiveLIPkt+3qMJuuQF76nURaA+nm3tCl/nKca6QLnVKzU
# 2QtPWS0qRmwd
# =5w7S
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 07 Nov 2023 01:09:12 HKT
# gpg:                using RSA key CB62D7A0EE3829E45F004D34A1FA40D098019CDF
# gpg:                issuer "hreitz@redhat.com"
# gpg: Good signature from "Hanna Reitz <hreitz@redhat.com>" [unknown]
# gpg: WARNING: The key's User ID is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: CB62 D7A0 EE38 29E4 5F00  4D34 A1FA 40D0 9801 9CDF

* tag 'pull-block-2023-11-06' of https://gitlab.com/hreitz/qemu:
  file-posix: fix over-writing of returning zone_append offset
  block/file-posix: fix update_zones_wp() caller
  qcow2: keep reference on zeroize with discard-no-unref enabled

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

block/file-posix.c

@@ -160,7 +160,6 @@ typedef struct BDRVRawState {
     bool has_write_zeroes:1;
     bool use_linux_aio:1;
     bool use_linux_io_uring:1;
-    int64_t *offset; /* offset of zone append operation */
     int page_cache_inconsistent; /* errno from fdatasync failure */
     bool has_fallocate;
     bool needs_alignment;
@@ -2445,12 +2444,13 @@ static bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
     return true;
 }
 
-static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
+static int coroutine_fn raw_co_prw(BlockDriverState *bs, int64_t *offset_ptr,
                                    uint64_t bytes, QEMUIOVector *qiov, int type)
 {
     BDRVRawState *s = bs->opaque;
     RawPosixAIOData acb;
     int ret;
+    uint64_t offset = *offset_ptr;
 
     if (fd_open(bs) < 0)
         return -EIO;
@@ -2513,8 +2513,8 @@ out:
             uint64_t *wp = &wps->wp[offset / bs->bl.zone_size];
             if (!BDRV_ZT_IS_CONV(*wp)) {
                 if (type & QEMU_AIO_ZONE_APPEND) {
-                    *s->offset = *wp;
-                    trace_zbd_zone_append_complete(bs, *s->offset
+                    *offset_ptr = *wp;
+                    trace_zbd_zone_append_complete(bs, *offset_ptr
                         >> BDRV_SECTOR_BITS);
                 }
                 /* Advance the wp if needed */
@@ -2523,7 +2523,10 @@ out:
                 }
             }
         } else {
-            update_zones_wp(bs, s->fd, 0, 1);
+            /*
+             * write and append write are not allowed to cross zone boundaries
+             */
+            update_zones_wp(bs, s->fd, offset, 1);
         }
 
         qemu_co_mutex_unlock(&wps->colock);
@@ -2536,14 +2539,14 @@ static int coroutine_fn raw_co_preadv(BlockDriverState *bs, int64_t offset,
                                       int64_t bytes, QEMUIOVector *qiov,
                                       BdrvRequestFlags flags)
 {
-    return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_READ);
+    return raw_co_prw(bs, &offset, bytes, qiov, QEMU_AIO_READ);
 }
 
 static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, int64_t offset,
                                        int64_t bytes, QEMUIOVector *qiov,
                                        BdrvRequestFlags flags)
 {
-    return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_WRITE);
+    return raw_co_prw(bs, &offset, bytes, qiov, QEMU_AIO_WRITE);
 }
 
 static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs)
@@ -3470,7 +3473,7 @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
                         len >> BDRV_SECTOR_BITS);
     ret = raw_thread_pool_submit(handle_aiocb_zone_mgmt, &acb);
     if (ret != 0) {
-        update_zones_wp(bs, s->fd, offset, i);
+        update_zones_wp(bs, s->fd, offset, nrz);
         error_report("ioctl %s failed %d", op_name, ret);
         return ret;
     }
@@ -3506,8 +3509,6 @@ static int coroutine_fn raw_co_zone_append(BlockDriverState *bs,
     int64_t zone_size_mask = bs->bl.zone_size - 1;
     int64_t iov_len = 0;
     int64_t len = 0;
-    BDRVRawState *s = bs->opaque;
-    s->offset = offset;
 
     if (*offset & zone_size_mask) {
         error_report("sector offset %" PRId64 " is not aligned to zone size "
@@ -3528,7 +3529,7 @@ static int coroutine_fn raw_co_zone_append(BlockDriverState *bs,
     }
 
     trace_zbd_zone_append(bs, *offset >> BDRV_SECTOR_BITS);
-    return raw_co_prw(bs, *offset, len, qiov, QEMU_AIO_ZONE_APPEND);
+    return raw_co_prw(bs, offset, len, qiov, QEMU_AIO_ZONE_APPEND);
 }
 #endif
 

block/qcow2-cluster.c

@@ -1983,7 +1983,7 @@ discard_in_l2_slice(BlockDriverState *bs, uint64_t offset, uint64_t nb_clusters,
             /* If we keep the reference, pass on the discard still */
             bdrv_pdiscard(s->data_file, old_l2_entry & L2E_OFFSET_MASK,
                           s->cluster_size);
-       }
+        }
     }
 
     qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice);
@@ -2061,9 +2061,15 @@ zero_in_l2_slice(BlockDriverState *bs, uint64_t offset,
         QCow2ClusterType type = qcow2_get_cluster_type(bs, old_l2_entry);
         bool unmap = (type == QCOW2_CLUSTER_COMPRESSED) ||
             ((flags & BDRV_REQ_MAY_UNMAP) && qcow2_cluster_is_allocated(type));
-        uint64_t new_l2_entry = unmap ? 0 : old_l2_entry;
+        bool keep_reference =
+            (s->discard_no_unref && type != QCOW2_CLUSTER_COMPRESSED);
+        uint64_t new_l2_entry = old_l2_entry;
         uint64_t new_l2_bitmap = old_l2_bitmap;
 
+        if (unmap && !keep_reference) {
+            new_l2_entry = 0;
+        }
+
         if (has_subclusters(s)) {
             new_l2_bitmap = QCOW_L2_BITMAP_ALL_ZEROES;
         } else {
@@ -2081,9 +2087,17 @@ zero_in_l2_slice(BlockDriverState *bs, uint64_t offset,
             set_l2_bitmap(s, l2_slice, l2_index + i, new_l2_bitmap);
         }
 
-        /* Then decrease the refcount */
         if (unmap) {
-            qcow2_free_any_cluster(bs, old_l2_entry, QCOW2_DISCARD_REQUEST);
+            if (!keep_reference) {
+                /* Then decrease the refcount */
+                qcow2_free_any_cluster(bs, old_l2_entry, QCOW2_DISCARD_REQUEST);
+            } else if (s->discard_passthrough[QCOW2_DISCARD_REQUEST] &&
+                       (type == QCOW2_CLUSTER_NORMAL ||
+                        type == QCOW2_CLUSTER_ZERO_ALLOC)) {
+                /* If we keep the reference, pass on the discard still */
+                bdrv_pdiscard(s->data_file, old_l2_entry & L2E_OFFSET_MASK,
+                            s->cluster_size);
+            }
         }
     }
 

qapi/block-core.json

@@ -3528,16 +3528,20 @@
 # @pass-discard-other: whether discard requests for the data source
 #     should be issued on other occasions where a cluster gets freed
 #
-# @discard-no-unref: when enabled, discards from the guest will not
-#     cause cluster allocations to be relinquished.  This prevents
-#     qcow2 fragmentation that would be caused by such discards.
-#     Besides potential performance degradation, such fragmentation
-#     can lead to increased allocation of clusters past the end of the
-#     image file, resulting in image files whose file length can grow
-#     much larger than their guest disk size would suggest.  If image
-#     file length is of concern (e.g. when storing qcow2 images
-#     directly on block devices), you should consider enabling this
-#     option.  (since 8.1)
+# @discard-no-unref: when enabled, data clusters will remain
+#     preallocated when they are no longer used, e.g. because they are
+#     discarded or converted to zero clusters.  As usual, whether the
+#     old data is discarded or kept on the protocol level (i.e. in the
+#     image file) depends on the setting of the pass-discard-request
+#     option.  Keeping the clusters preallocated prevents qcow2
+#     fragmentation that would otherwise be caused by freeing and
+#     re-allocating them later.  Besides potential performance
+#     degradation, such fragmentation can lead to increased allocation
+#     of clusters past the end of the image file, resulting in image
+#     files whose file length can grow much larger than their guest disk
+#     size would suggest.  If image file length is of concern (e.g. when
+#     storing qcow2 images directly on block devices), you should
+#     consider enabling this option.  (since 8.1)
 #
 # @overlap-check: which overlap checks to perform for writes to the
 #     image, defaults to 'cached' (since 2.2)

qemu-options.hx

@@ -1457,9 +1457,13 @@ SRST
             (on/off; default: off)
 
         ``discard-no-unref``
-            When enabled, discards from the guest will not cause cluster
-            allocations to be relinquished. This prevents qcow2 fragmentation
-            that would be caused by such discards. Besides potential
+            When enabled, data clusters will remain preallocated when they are
+            no longer used, e.g. because they are discarded or converted to
+            zero clusters. As usual, whether the old data is discarded or kept
+            on the protocol level (i.e. in the image file) depends on the
+            setting of the pass-discard-request option. Keeping the clusters
+            preallocated prevents qcow2 fragmentation that would otherwise be
+            caused by freeing and re-allocating them later. Besides potential
             performance degradation, such fragmentation can lead to increased
             allocation of clusters past the end of the image file,
             resulting in image files whose file length can grow much larger