block: apply COR-filter to block-stream jobs

This patch completes the series with the COR-filter applied to
block-stream operations.

Adding the filter makes it possible in future implement discarding
copied regions in backing files during the block-stream job, to reduce
the disk overuse (we need control on permissions).

Also, the filter now is smart enough to do copy-on-read with specified
base, so we have benefit on guest reads even when doing block-stream of
the part of the backing chain.

Several iotests are slightly modified due to filter insertion.

Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20201216061703.70908-14-vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>

1 files changed, 62 insertions, 43 deletions

diff --git a/block/stream.c b/block/stream.c
index 626dfa2b22..1fa742b0db 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -17,8 +17,10 @@
 #include "block/blockjob_int.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
+#include "qapi/qmp/qdict.h"
 #include "qemu/ratelimit.h"
 #include "sysemu/block-backend.h"
+#include "block/copy-on-read.h"
 
 enum {
     /*
@@ -33,11 +35,11 @@ typedef struct StreamBlockJob {
     BlockJob common;
     BlockDriverState *base_overlay; /* COW overlay (stream from this) */
     BlockDriverState *above_base;   /* Node directly above the base */
+    BlockDriverState *cor_filter_bs;
     BlockDriverState *target_bs;
     BlockdevOnError on_error;
     char *backing_file_str;
     bool bs_read_only;
-    bool chain_frozen;
 } StreamBlockJob;
 
 static int coroutine_fn stream_populate(BlockBackend *blk,
@@ -45,17 +47,7 @@ static int coroutine_fn stream_populate(BlockBackend *blk,
 {
     assert(bytes < SIZE_MAX);
 
-    return blk_co_preadv(blk, offset, bytes, NULL,
-                         BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH);
-}
-
-static void stream_abort(Job *job)
-{
-    StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
-
-    if (s->chain_frozen) {
-        bdrv_unfreeze_backing_chain(s->target_bs, s->above_base);
-    }
+    return blk_co_preadv(blk, offset, bytes, NULL, BDRV_REQ_PREFETCH);
 }
 
 static int stream_prepare(Job *job)
@@ -67,8 +59,9 @@ static int stream_prepare(Job *job)
     Error *local_err = NULL;
     int ret = 0;
 
-    bdrv_unfreeze_backing_chain(s->target_bs, s->above_base);
-    s->chain_frozen = false;
+    /* We should drop filter at this point, as filter hold the backing chain */
+    bdrv_cor_filter_drop(s->cor_filter_bs);
+    s->cor_filter_bs = NULL;
 
     if (bdrv_cow_child(unfiltered_bs)) {
         const char *base_id = NULL, *base_fmt = NULL;
@@ -94,6 +87,11 @@ static void stream_clean(Job *job)
     StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
     BlockJob *bjob = &s->common;
 
+    if (s->cor_filter_bs) {
+        bdrv_cor_filter_drop(s->cor_filter_bs);
+        s->cor_filter_bs = NULL;
+    }
+
     /* Reopen the image back in read-only mode if necessary */
     if (s->bs_read_only) {
         /* Give up write permissions before making it read-only */
@@ -109,7 +107,6 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
     StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
     BlockBackend *blk = s->common.blk;
     BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs);
-    bool enable_cor = !bdrv_cow_child(s->base_overlay);
     int64_t len;
     int64_t offset = 0;
     uint64_t delay_ns = 0;
@@ -127,15 +124,6 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
     }
     job_progress_set_remaining(&s->common.job, len);
 
-    /* Turn on copy-on-read for the whole block device so that guest read
-     * requests help us make progress.  Only do this when copying the entire
-     * backing chain since the copy-on-read operation does not take base into
-     * account.
-     */
-    if (enable_cor) {
-        bdrv_enable_copy_on_read(s->target_bs);
-    }
-
     for ( ; offset < len; offset += n) {
         bool copy;
         int ret;
@@ -194,10 +182,6 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
         }
     }
 
-    if (enable_cor) {
-        bdrv_disable_copy_on_read(s->target_bs);
-    }
-
     /* Do not remove the backing file if an error was there but ignored. */
     return error;
 }
@@ -209,7 +193,6 @@ static const BlockJobDriver stream_job_driver = {
         .free          = block_job_free,
         .run           = stream_run,
         .prepare       = stream_prepare,
-        .abort         = stream_abort,
         .clean         = stream_clean,
         .user_resume   = block_job_user_resume,
     },
@@ -228,7 +211,9 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     bool bs_read_only;
     int basic_flags = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED;
     BlockDriverState *base_overlay;
+    BlockDriverState *cor_filter_bs = NULL;
     BlockDriverState *above_base;
+    QDict *opts;
 
     assert(!(base && bottom));
     assert(!(backing_file_str && bottom));
@@ -266,30 +251,62 @@ void stream_start(const char *job_id, BlockDriverState *bs,
         }
     }
 
-    if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) {
-        return;
-    }
-
     /* Make sure that the image is opened in read-write mode */
     bs_read_only = bdrv_is_read_only(bs);
     if (bs_read_only) {
-        if (bdrv_reopen_set_read_only(bs, false, errp) != 0) {
-            bs_read_only = false;
-            goto fail;
+        int ret;
+        /* Hold the chain during reopen */
+        if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) {
+            return;
+        }
+
+        ret = bdrv_reopen_set_read_only(bs, false, errp);
+
+        /* failure, or cor-filter will hold the chain */
+        bdrv_unfreeze_backing_chain(bs, above_base);
+
+        if (ret < 0) {
+            return;
         }
     }
 
-    /* Prevent concurrent jobs trying to modify the graph structure here, we
-     * already have our own plans. Also don't allow resize as the image size is
-     * queried only at the job start and then cached. */
-    s = block_job_create(job_id, &stream_job_driver, NULL, bs,
-                         basic_flags | BLK_PERM_GRAPH_MOD,
+    opts = qdict_new();
+
+    qdict_put_str(opts, "driver", "copy-on-read");
+    qdict_put_str(opts, "file", bdrv_get_node_name(bs));
+    /* Pass the base_overlay node name as 'bottom' to COR driver */
+    qdict_put_str(opts, "bottom", base_overlay->node_name);
+    if (filter_node_name) {
+        qdict_put_str(opts, "node-name", filter_node_name);
+    }
+
+    cor_filter_bs = bdrv_insert_node(bs, opts, BDRV_O_RDWR, errp);
+    if (!cor_filter_bs) {
+        goto fail;
+    }
+
+    if (!filter_node_name) {
+        cor_filter_bs->implicit = true;
+    }
+
+    s = block_job_create(job_id, &stream_job_driver, NULL, cor_filter_bs,
+                         BLK_PERM_CONSISTENT_READ,
                          basic_flags | BLK_PERM_WRITE,
                          speed, creation_flags, NULL, NULL, errp);
     if (!s) {
         goto fail;
     }
 
+    /*
+     * Prevent concurrent jobs trying to modify the graph structure here, we
+     * already have our own plans. Also don't allow resize as the image size is
+     * queried only at the job start and then cached.
+     */
+    if (block_job_add_bdrv(&s->common, "active node", bs, 0,
+                           basic_flags | BLK_PERM_WRITE, &error_abort)) {
+        goto fail;
+    }
+
     /* Block all intermediate nodes between bs and base, because they will
      * disappear from the chain after this operation. The streaming job reads
      * every block only once, assuming that it doesn't change, so forbid writes
@@ -310,9 +327,9 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     s->base_overlay = base_overlay;
     s->above_base = above_base;
     s->backing_file_str = g_strdup(backing_file_str);
+    s->cor_filter_bs = cor_filter_bs;
     s->target_bs = bs;
     s->bs_read_only = bs_read_only;
-    s->chain_frozen = true;
 
     s->on_error = on_error;
     trace_stream_start(bs, base, s);
@@ -320,8 +337,10 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     return;
 
 fail:
+    if (cor_filter_bs) {
+        bdrv_cor_filter_drop(cor_filter_bs);
+    }
     if (bs_read_only) {
         bdrv_reopen_set_read_only(bs, true, NULL);
     }
-    bdrv_unfreeze_backing_chain(bs, above_base);
 }