All of lore.kernel.org
 help / color / mirror / Atom feed
From: Fam Zheng <famz@redhat.com>
To: qemu-devel@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Ronnie Sahlberg <ronniesahlberg@gmail.com>,
	qemu-block@nongnu.org, Peter Lieven <pl@kamp.de>,
	Fam Zheng <famz@redhat.com>, Kevin Wolf <kwolf@redhat.com>,
	Max Reitz <mreitz@redhat.com>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	eblake@redhat.com
Subject: [Qemu-devel] [PATCH v4 04/10] qcow2: Implement copy offloading
Date: Fri, 11 May 2018 20:08:17 +0800	[thread overview]
Message-ID: <20180511120823.7892-5-famz@redhat.com> (raw)
In-Reply-To: <20180511120823.7892-1-famz@redhat.com>

The two callbacks are implemented quite similarly to the read/write
functions: bdrv_co_copy_range_from maps for read and calls into bs->file
or bs->backing depending on the allocation status; bdrv_co_copy_range_to
maps for write and calls into bs->file.

Signed-off-by: Fam Zheng <famz@redhat.com>
---
 block/qcow2.c | 232 ++++++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 202 insertions(+), 30 deletions(-)

diff --git a/block/qcow2.c b/block/qcow2.c
index 2f36e632f9..b5a8b2c1f7 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1755,6 +1755,31 @@ static int coroutine_fn qcow2_co_block_status(BlockDriverState *bs,
     return status;
 }
 
+static int qcow2_handle_l2meta(BlockDriverState *bs, QCowL2Meta *l2meta)
+{
+    int ret = 0;
+
+    while (l2meta != NULL) {
+        QCowL2Meta *next;
+
+        if (!ret) {
+            ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
+        }
+
+        /* Take the request off the list of running requests */
+        if (l2meta->nb_clusters != 0) {
+            QLIST_REMOVE(l2meta, next_in_flight);
+        }
+
+        qemu_co_queue_restart_all(&l2meta->dependent_requests);
+
+        next = l2meta->next;
+        g_free(l2meta);
+        l2meta = next;
+    }
+    return ret;
+}
+
 static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
                                         uint64_t bytes, QEMUIOVector *qiov,
                                         int flags)
@@ -2041,24 +2066,10 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
             }
         }
 
-        while (l2meta != NULL) {
-            QCowL2Meta *next;
-
-            ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
-            if (ret < 0) {
-                goto fail;
-            }
-
-            /* Take the request off the list of running requests */
-            if (l2meta->nb_clusters != 0) {
-                QLIST_REMOVE(l2meta, next_in_flight);
-            }
-
-            qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
-            next = l2meta->next;
-            g_free(l2meta);
-            l2meta = next;
+        ret = qcow2_handle_l2meta(bs, l2meta);
+        l2meta = NULL;
+        if (ret) {
+            goto fail;
         }
 
         bytes -= cur_bytes;
@@ -2069,18 +2080,7 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
     ret = 0;
 
 fail:
-    while (l2meta != NULL) {
-        QCowL2Meta *next;
-
-        if (l2meta->nb_clusters != 0) {
-            QLIST_REMOVE(l2meta, next_in_flight);
-        }
-        qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
-        next = l2meta->next;
-        g_free(l2meta);
-        l2meta = next;
-    }
+    qcow2_handle_l2meta(bs, l2meta);
 
     qemu_co_mutex_unlock(&s->lock);
 
@@ -3267,6 +3267,176 @@ static coroutine_fn int qcow2_co_pdiscard(BlockDriverState *bs,
     return ret;
 }
 
+static int qcow2_co_copy_range_from(BlockDriverState *bs,
+                                    BdrvChild *src, uint64_t src_offset,
+                                    BdrvChild *dst, uint64_t dst_offset,
+                                    uint64_t bytes, BdrvRequestFlags flags)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int ret;
+    unsigned int cur_bytes; /* number of bytes in current iteration */
+    BdrvChild *child = NULL;
+
+    assert(!bs->encrypted);
+    qemu_co_mutex_lock(&s->lock);
+
+    while (bytes != 0) {
+        uint64_t copy_offset = 0;
+        /* prepare next request */
+        cur_bytes = MIN(bytes, INT_MAX);
+
+        ret = qcow2_get_cluster_offset(bs, src_offset, &cur_bytes, &copy_offset);
+        if (ret < 0) {
+            goto out;
+        }
+
+        switch (ret) {
+        case QCOW2_CLUSTER_UNALLOCATED:
+            if (bs->backing && bs->backing->bs) {
+                int64_t backing_length = bdrv_getlength(bs->backing->bs);
+                if (src_offset >= backing_length) {
+                    flags |= BDRV_REQ_ZERO_WRITE;
+                } else {
+                    child = bs->backing;
+                    cur_bytes = MIN(cur_bytes, backing_length - src_offset);
+                    copy_offset = src_offset;
+                }
+            } else {
+                flags |= BDRV_REQ_ZERO_WRITE;
+            }
+            break;
+
+        case QCOW2_CLUSTER_ZERO_PLAIN:
+        case QCOW2_CLUSTER_ZERO_ALLOC:
+            flags |= BDRV_REQ_ZERO_WRITE;
+            break;
+
+        case QCOW2_CLUSTER_COMPRESSED:
+            ret = -ENOTSUP;
+            goto out;
+            break;
+
+        case QCOW2_CLUSTER_NORMAL:
+            child = bs->file;
+            copy_offset += offset_into_cluster(s, src_offset);
+            if ((copy_offset & 511) != 0) {
+                ret = -EIO;
+                goto out;
+            }
+            break;
+
+        default:
+            abort();
+        }
+        qemu_co_mutex_unlock(&s->lock);
+        ret = bdrv_co_copy_range_from(child,
+                                      copy_offset,
+                                      dst, dst_offset,
+                                      cur_bytes, flags);
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0) {
+            goto out;
+        }
+
+        bytes -= cur_bytes;
+        src_offset += cur_bytes;
+    }
+    ret = 0;
+
+out:
+    qemu_co_mutex_unlock(&s->lock);
+    return ret;
+}
+
+static int qcow2_co_copy_range_to(BlockDriverState *bs,
+                                  BdrvChild *src, uint64_t src_offset,
+                                  BdrvChild *dst, uint64_t dst_offset,
+                                  uint64_t bytes, BdrvRequestFlags flags)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int offset_in_cluster;
+    int ret;
+    unsigned int cur_bytes; /* number of sectors in current iteration */
+    uint64_t cluster_offset;
+    uint8_t *cluster_data = NULL;
+    QCowL2Meta *l2meta = NULL;
+
+    assert(!bs->encrypted);
+    s->cluster_cache_offset = -1; /* disable compressed cache */
+
+    qemu_co_mutex_lock(&s->lock);
+
+    while (bytes != 0) {
+
+        l2meta = NULL;
+
+        offset_in_cluster = offset_into_cluster(s, dst_offset);
+        cur_bytes = MIN(bytes, INT_MAX);
+
+        /* TODO:
+         * If src->bs == dst->bs, we could simply copy by incrementing
+         * the refcnt, without copying user data.
+         * Or if src->bs == dst->bs->backing->bs, we could copy by discarding. */
+        ret = qcow2_alloc_cluster_offset(bs, dst_offset, &cur_bytes,
+                                         &cluster_offset, &l2meta);
+        if (ret < 0) {
+            goto fail;
+        }
+
+        assert((cluster_offset & 511) == 0);
+
+        ret = qcow2_pre_write_overlap_check(bs, 0,
+                cluster_offset + offset_in_cluster, cur_bytes);
+        if (ret < 0) {
+            goto fail;
+        }
+
+        qemu_co_mutex_unlock(&s->lock);
+        ret = bdrv_co_copy_range_to(src, src_offset,
+                                    bs->file,
+                                    cluster_offset + offset_in_cluster,
+                                    cur_bytes, flags);
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0) {
+            goto fail;
+        }
+
+        while (l2meta != NULL) {
+            QCowL2Meta *next;
+
+            ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
+            if (ret < 0) {
+                goto fail;
+            }
+
+            /* Take the request off the list of running requests */
+            if (l2meta->nb_clusters != 0) {
+                QLIST_REMOVE(l2meta, next_in_flight);
+            }
+
+            qemu_co_queue_restart_all(&l2meta->dependent_requests);
+
+            next = l2meta->next;
+            g_free(l2meta);
+            l2meta = next;
+        }
+
+        bytes -= cur_bytes;
+        dst_offset += cur_bytes;
+    }
+    ret = 0;
+
+fail:
+    qcow2_handle_l2meta(bs, l2meta);
+
+    qemu_co_mutex_unlock(&s->lock);
+
+    qemu_vfree(cluster_data);
+    trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
+
+    return ret;
+}
+
 static int qcow2_truncate(BlockDriverState *bs, int64_t offset,
                           PreallocMode prealloc, Error **errp)
 {
@@ -4515,6 +4685,8 @@ BlockDriver bdrv_qcow2 = {
 
     .bdrv_co_pwrite_zeroes  = qcow2_co_pwrite_zeroes,
     .bdrv_co_pdiscard       = qcow2_co_pdiscard,
+    .bdrv_co_copy_range_from = qcow2_co_copy_range_from,
+    .bdrv_co_copy_range_to  = qcow2_co_copy_range_to,
     .bdrv_truncate          = qcow2_truncate,
     .bdrv_co_pwritev_compressed = qcow2_co_pwritev_compressed,
     .bdrv_make_empty        = qcow2_make_empty,
-- 
2.14.3

  parent reply	other threads:[~2018-05-11 12:09 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-11 12:08 [Qemu-devel] [PATCH v4 00/10] qemu-img convert with copy offloading Fam Zheng
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 01/10] block: Introduce API for " Fam Zheng
2018-05-17  9:44   ` Stefan Hajnoczi
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 02/10] raw: Check byte range uniformly Fam Zheng
2018-05-11 13:59   ` Eric Blake
2018-05-14  1:57     ` Fam Zheng
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 03/10] raw: Implement copy offloading Fam Zheng
2018-05-11 12:08 ` Fam Zheng [this message]
2018-05-17 10:01   ` [Qemu-devel] [PATCH v4 04/10] qcow2: " Stefan Hajnoczi
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 05/10] file-posix: Implement bdrv_co_copy_range Fam Zheng
2018-05-17 10:02   ` Stefan Hajnoczi
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 06/10] iscsi: Query and save device designator when opening Fam Zheng
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 07/10] iscsi: Create and use iscsi_co_wait_for_task Fam Zheng
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 08/10] iscsi: Implement copy offloading Fam Zheng
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 09/10] block-backend: Add blk_co_copy_range Fam Zheng
2018-05-11 12:08 ` [Qemu-devel] [PATCH v4 10/10] qemu-img: Convert with copy offloading Fam Zheng

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=20180511120823.7892-5-famz@redhat.com \
    --to=famz@redhat.com \
    --cc=eblake@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=pl@kamp.de \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=ronniesahlberg@gmail.com \
    --cc=stefanha@redhat.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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.