QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Alberto Garcia <berto@igalia.com>
To: qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>,
	Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>,
	Alberto Garcia <berto@igalia.com>,
	qemu-block@nongnu.org, Derek Su <dereksu@qnap.com>,
	Max Reitz <mreitz@redhat.com>
Subject: [PATCH v9 28/34] qcow2: Add subcluster support to qcow2_co_pwrite_zeroes()
Date: Sun, 28 Jun 2020 13:02:37 +0200
Message-ID: <3c6140626c443f1eb443881eddcfb65b6107aff2.1593342067.git.berto@igalia.com> (raw)
In-Reply-To: <cover.1593342067.git.berto@igalia.com>

This works now at the subcluster level and pwrite_zeroes_alignment is
updated accordingly.

qcow2_cluster_zeroize() is turned into qcow2_subcluster_zeroize() with
the following changes:

   - The request can now be subcluster-aligned.

   - The cluster-aligned body of the request is still zeroized using
     zero_in_l2_slice() as before.

   - The subcluster-aligned head and tail of the request are zeroized
     with the new zero_l2_subclusters() function.

There is just one thing to take into account for a possible future
improvement: compressed clusters cannot be partially zeroized so
zero_l2_subclusters() on the head or the tail can return -ENOTSUP.
This makes the caller repeat the *complete* request and write actual
zeroes to disk. This is sub-optimal because

   1) if the head area was compressed we would still be able to use
      the fast path for the body and possibly the tail.

   2) if the tail area was compressed we are writing zeroes to the
      head and the body areas, which are already zeroized.

Signed-off-by: Alberto Garcia <berto@igalia.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
---
 block/qcow2.h         |  4 +--
 block/qcow2-cluster.c | 80 +++++++++++++++++++++++++++++++++++++++----
 block/qcow2.c         | 27 ++++++++-------
 3 files changed, 90 insertions(+), 21 deletions(-)

diff --git a/block/qcow2.h b/block/qcow2.h
index 4fad40b96b..4ef4ae4ab0 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -898,8 +898,8 @@ void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m);
 int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset,
                           uint64_t bytes, enum qcow2_discard_type type,
                           bool full_discard);
-int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, int flags);
+int qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset,
+                             uint64_t bytes, int flags);
 
 int qcow2_expand_zero_clusters(BlockDriverState *bs,
                                BlockDriverAmendStatusCB *status_cb,
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index deff838fe8..1641976028 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -2015,12 +2015,58 @@ static int zero_in_l2_slice(BlockDriverState *bs, uint64_t offset,
     return nb_clusters;
 }
 
-int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, int flags)
+static int zero_l2_subclusters(BlockDriverState *bs, uint64_t offset,
+                               unsigned nb_subclusters)
+{
+    BDRVQcow2State *s = bs->opaque;
+    uint64_t *l2_slice;
+    uint64_t old_l2_bitmap, l2_bitmap;
+    int l2_index, ret, sc = offset_to_sc_index(s, offset);
+
+    /* For full clusters use zero_in_l2_slice() instead */
+    assert(nb_subclusters > 0 && nb_subclusters < s->subclusters_per_cluster);
+    assert(sc + nb_subclusters <= s->subclusters_per_cluster);
+
+    ret = get_cluster_table(bs, offset, &l2_slice, &l2_index);
+    if (ret < 0) {
+        return ret;
+    }
+
+    switch (qcow2_get_cluster_type(bs, get_l2_entry(s, l2_slice, l2_index))) {
+    case QCOW2_CLUSTER_COMPRESSED:
+        ret = -ENOTSUP; /* We cannot partially zeroize compressed clusters */
+        goto out;
+    case QCOW2_CLUSTER_NORMAL:
+    case QCOW2_CLUSTER_UNALLOCATED:
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    old_l2_bitmap = l2_bitmap = get_l2_bitmap(s, l2_slice, l2_index);
+
+    l2_bitmap |=  QCOW_OFLAG_SUB_ZERO_RANGE(sc, sc + nb_subclusters);
+    l2_bitmap &= ~QCOW_OFLAG_SUB_ALLOC_RANGE(sc, sc + nb_subclusters);
+
+    if (old_l2_bitmap != l2_bitmap) {
+        set_l2_bitmap(s, l2_slice, l2_index, l2_bitmap);
+        qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice);
+    }
+
+    ret = 0;
+out:
+    qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice);
+
+    return ret;
+}
+
+int qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset,
+                             uint64_t bytes, int flags)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t end_offset = offset + bytes;
     uint64_t nb_clusters;
+    unsigned head, tail;
     int64_t cleared;
     int ret;
 
@@ -2035,8 +2081,8 @@ int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
     }
 
     /* Caller must pass aligned values, except at image end */
-    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
-    assert(QEMU_IS_ALIGNED(end_offset, s->cluster_size) ||
+    assert(offset_into_subcluster(s, offset) == 0);
+    assert(offset_into_subcluster(s, end_offset) == 0 ||
            end_offset >= bs->total_sectors << BDRV_SECTOR_BITS);
 
     /* The zero flag is only supported by version 3 and newer */
@@ -2044,11 +2090,26 @@ int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
         return -ENOTSUP;
     }
 
-    /* Each L2 slice is handled by its own loop iteration */
-    nb_clusters = size_to_clusters(s, bytes);
+    head = MIN(end_offset, ROUND_UP(offset, s->cluster_size)) - offset;
+    offset += head;
+
+    tail = (end_offset >= bs->total_sectors << BDRV_SECTOR_BITS) ? 0 :
+        end_offset - MAX(offset, start_of_cluster(s, end_offset));
+    end_offset -= tail;
 
     s->cache_discards = true;
 
+    if (head) {
+        ret = zero_l2_subclusters(bs, offset - head,
+                                  size_to_subclusters(s, head));
+        if (ret < 0) {
+            goto fail;
+        }
+    }
+
+    /* Each L2 slice is handled by its own loop iteration */
+    nb_clusters = size_to_clusters(s, end_offset - offset);
+
     while (nb_clusters > 0) {
         cleared = zero_in_l2_slice(bs, offset, nb_clusters, flags);
         if (cleared < 0) {
@@ -2060,6 +2121,13 @@ int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
         offset += (cleared * s->cluster_size);
     }
 
+    if (tail) {
+        ret = zero_l2_subclusters(bs, end_offset, size_to_subclusters(s, tail));
+        if (ret < 0) {
+            goto fail;
+        }
+    }
+
     ret = 0;
 fail:
     s->cache_discards = false;
diff --git a/block/qcow2.c b/block/qcow2.c
index 86258fbc22..4edc3c72b9 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1903,7 +1903,7 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
         /* Encryption works on a sector granularity */
         bs->bl.request_alignment = qcrypto_block_get_sector_size(s->crypto);
     }
-    bs->bl.pwrite_zeroes_alignment = s->cluster_size;
+    bs->bl.pwrite_zeroes_alignment = s->subcluster_size;
     bs->bl.pdiscard_alignment = s->cluster_size;
 }
 
@@ -3840,8 +3840,9 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
     int ret;
     BDRVQcow2State *s = bs->opaque;
 
-    uint32_t head = offset % s->cluster_size;
-    uint32_t tail = (offset + bytes) % s->cluster_size;
+    uint32_t head = offset_into_subcluster(s, offset);
+    uint32_t tail = ROUND_UP(offset + bytes, s->subcluster_size) -
+        (offset + bytes);
 
     trace_qcow2_pwrite_zeroes_start_req(qemu_coroutine_self(), offset, bytes);
     if (offset + bytes == bs->total_sectors * BDRV_SECTOR_SIZE) {
@@ -3853,20 +3854,19 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
         unsigned int nr;
         QCow2SubclusterType type;
 
-        assert(head + bytes <= s->cluster_size);
+        assert(head + bytes + tail <= s->subcluster_size);
 
         /* check whether remainder of cluster already reads as zero */
         if (!(is_zero(bs, offset - head, head) &&
-              is_zero(bs, offset + bytes,
-                      tail ? s->cluster_size - tail : 0))) {
+              is_zero(bs, offset + bytes, tail))) {
             return -ENOTSUP;
         }
 
         qemu_co_mutex_lock(&s->lock);
         /* We can have new write after previous check */
-        offset = QEMU_ALIGN_DOWN(offset, s->cluster_size);
-        bytes = s->cluster_size;
-        nr = s->cluster_size;
+        offset -= head;
+        bytes = s->subcluster_size;
+        nr = s->subcluster_size;
         ret = qcow2_get_host_offset(bs, offset, &nr, &off, &type);
         if (ret < 0 ||
             (type != QCOW2_SUBCLUSTER_UNALLOCATED_PLAIN &&
@@ -3882,8 +3882,8 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
 
     trace_qcow2_pwrite_zeroes(qemu_coroutine_self(), offset, bytes);
 
-    /* Whatever is left can use real zero clusters */
-    ret = qcow2_cluster_zeroize(bs, offset, bytes, flags);
+    /* Whatever is left can use real zero subclusters */
+    ret = qcow2_subcluster_zeroize(bs, offset, bytes, flags);
     qemu_co_mutex_unlock(&s->lock);
 
     return ret;
@@ -4367,12 +4367,13 @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset,
         uint64_t zero_start = QEMU_ALIGN_UP(old_length, s->cluster_size);
 
         /*
-         * Use zero clusters as much as we can. qcow2_cluster_zeroize()
+         * Use zero clusters as much as we can. qcow2_subcluster_zeroize()
          * requires a cluster-aligned start. The end may be unaligned if it is
          * at the end of the image (which it is here).
          */
         if (offset > zero_start) {
-            ret = qcow2_cluster_zeroize(bs, zero_start, offset - zero_start, 0);
+            ret = qcow2_subcluster_zeroize(bs, zero_start, offset - zero_start,
+                                           0);
             if (ret < 0) {
                 error_setg_errno(errp, -ret, "Failed to zero out new clusters");
                 goto fail;
-- 
2.20.1



  parent reply index

Thread overview: 71+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-28 11:02 [PATCH v9 00/34] Add subcluster allocation to qcow2 Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 01/34] qcow2: Make Qcow2AioTask store the full host offset Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 02/34] qcow2: Convert qcow2_get_cluster_offset() into qcow2_get_host_offset() Alberto Garcia
2020-06-30 10:19   ` Max Reitz
2020-06-30 10:27     ` Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 03/34] qcow2: Add calculate_l2_meta() Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 04/34] qcow2: Split cluster_needs_cow() out of count_cow_clusters() Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 05/34] qcow2: Process QCOW2_CLUSTER_ZERO_ALLOC clusters in handle_copied() Alberto Garcia
2020-06-30 10:38   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 06/34] qcow2: Add get_l2_entry() and set_l2_entry() Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 07/34] qcow2: Document the Extended L2 Entries feature Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 08/34] qcow2: Add dummy has_subclusters() function Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 09/34] qcow2: Add subcluster-related fields to BDRVQcow2State Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 10/34] qcow2: Add offset_to_sc_index() Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 11/34] qcow2: Add offset_into_subcluster() and size_to_subclusters() Alberto Garcia
2020-07-01 12:23   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 12/34] qcow2: Add l2_entry_size() Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 13/34] qcow2: Update get/set_l2_entry() and add get/set_l2_bitmap() Alberto Garcia
2020-07-01 12:28   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 14/34] qcow2: Add QCow2SubclusterType and qcow2_get_subcluster_type() Alberto Garcia
2020-07-01 12:52   ` Max Reitz
2020-07-01 16:26     ` Alberto Garcia
2020-07-02  9:57       ` Max Reitz
2020-07-02 22:00         ` Alberto Garcia
2020-07-03  7:17           ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 15/34] qcow2: Add qcow2_get_subcluster_range_type() Alberto Garcia
2020-07-01 13:37   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 16/34] qcow2: Add qcow2_cluster_is_allocated() Alberto Garcia
2020-07-01 13:55   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 17/34] qcow2: Add cluster type parameter to qcow2_get_host_offset() Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 18/34] qcow2: Replace QCOW2_CLUSTER_* with QCOW2_SUBCLUSTER_* Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 19/34] qcow2: Handle QCOW2_SUBCLUSTER_UNALLOCATED_ALLOC Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 20/34] qcow2: Add subcluster support to calculate_l2_meta() Alberto Garcia
2020-07-02 11:30   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 21/34] qcow2: Add subcluster support to qcow2_get_host_offset() Alberto Garcia
2020-07-02 12:46   ` Max Reitz
2020-07-02 22:04     ` Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 22/34] qcow2: Add subcluster support to zero_in_l2_slice() Alberto Garcia
2020-07-02 12:56   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 23/34] qcow2: Add subcluster support to discard_in_l2_slice() Alberto Garcia
2020-07-02 13:24   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 24/34] qcow2: Add subcluster support to check_refcounts_l2() Alberto Garcia
2020-07-02 13:32   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 25/34] qcow2: Update L2 bitmap in qcow2_alloc_cluster_link_l2() Alberto Garcia
2020-07-02 14:01   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 26/34] qcow2: Clear the L2 bitmap when allocating a compressed cluster Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 27/34] qcow2: Add subcluster support to handle_alloc_space() Alberto Garcia
2020-06-28 11:02 ` Alberto Garcia [this message]
2020-07-02 14:28   ` [PATCH v9 28/34] qcow2: Add subcluster support to qcow2_co_pwrite_zeroes() Max Reitz
2020-07-02 22:40     ` Alberto Garcia
2020-07-03  7:18       ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 29/34] qcow2: Add subcluster support to qcow2_measure() Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 30/34] qcow2: Add prealloc field to QCowL2Meta Alberto Garcia
2020-07-02 14:50   ` Max Reitz
2020-07-02 14:58     ` Eric Blake
2020-07-02 15:09       ` Max Reitz
2020-07-02 23:05         ` Alberto Garcia
2020-07-03  7:22           ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 31/34] qcow2: Add the 'extended_l2' option and the QCOW2_INCOMPAT_EXTL2 bit Alberto Garcia
2020-07-02 15:13   ` Max Reitz
2020-07-03 12:43     ` Alberto Garcia
2020-06-28 11:02 ` [PATCH v9 32/34] qcow2: Allow preallocation and backing files if extended_l2 is set Alberto Garcia
2020-07-03  7:45   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 33/34] qcow2: Assert that expand_zero_clusters_in_l1() does not support subclusters Alberto Garcia
2020-07-03  7:46   ` Max Reitz
2020-06-28 11:02 ` [PATCH v9 34/34] iotests: Add tests for qcow2 images with extended L2 entries Alberto Garcia
2020-07-03  9:49   ` Max Reitz
2020-07-03 13:06     ` Alberto Garcia
2020-07-03 13:47       ` Max Reitz
2020-07-03 15:20         ` Alberto Garcia
2020-07-06 13:57       ` Eric Blake

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=3c6140626c443f1eb443881eddcfb65b6107aff2.1593342067.git.berto@igalia.com \
    --to=berto@igalia.com \
    --cc=dereksu@qnap.com \
    --cc=kwolf@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=vsementsov@virtuozzo.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git