[Qemu-devel] [PATCH 29/32] mirror: add support for on-source-error/on-target-error

[Kevin Wolf <kwolf@redhat.com>]

From: Paolo Bonzini <pbonzini@redhat.com>

Error management is important for mirroring; otherwise, an error on the
target (even something as "innocent" as ENOSPC) requires to start again
with a full copy.  Similar to on_read_error/on_write_error, two separate
knobs are provided for on_source_error (reads) and on_target_error (writes).
The default is 'report' for both.

The 'ignore' policy will leave the sector dirty, so that it will be
retried later.  Thus, it will not cause corruption.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block/mirror.c   |   94 ++++++++++++++++++++++++++++++++++++++++++------------
 block_int.h      |    4 ++
 blockdev.c       |   14 +++++++-
 hmp.c            |    3 +-
 qapi-schema.json |   11 ++++++-
 qmp-commands.hx  |    8 ++++-
 6 files changed, 108 insertions(+), 26 deletions(-)

diff --git a/block/mirror.c b/block/mirror.c
index 6320f6a..d6618a4 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -32,13 +32,28 @@ typedef struct MirrorBlockJob {
     RateLimit limit;
     BlockDriverState *target;
     MirrorSyncMode mode;
+    BlockdevOnError on_source_error, on_target_error;
     bool synced;
     bool should_complete;
     int64_t sector_num;
     uint8_t *buf;
 } MirrorBlockJob;
 
-static int coroutine_fn mirror_iteration(MirrorBlockJob *s)
+static BlockErrorAction mirror_error_action(MirrorBlockJob *s, bool read,
+                                            int error)
+{
+    s->synced = false;
+    if (read) {
+        return block_job_error_action(&s->common, s->common.bs,
+                                      s->on_source_error, true, error);
+    } else {
+        return block_job_error_action(&s->common, s->target,
+                                      s->on_target_error, false, error);
+    }
+}
+
+static int coroutine_fn mirror_iteration(MirrorBlockJob *s,
+                                         BlockErrorAction *p_action)
 {
     BlockDriverState *source = s->common.bs;
     BlockDriverState *target = s->target;
@@ -60,9 +75,21 @@ static int coroutine_fn mirror_iteration(MirrorBlockJob *s)
     trace_mirror_one_iteration(s, s->sector_num, nb_sectors);
     ret = bdrv_co_readv(source, s->sector_num, nb_sectors, &qiov);
     if (ret < 0) {
-        return ret;
+        *p_action = mirror_error_action(s, true, -ret);
+        goto fail;
+    }
+    ret = bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
+    if (ret < 0) {
+        *p_action = mirror_error_action(s, false, -ret);
+        s->synced = false;
+        goto fail;
     }
-    return bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
+    return 0;
+
+fail:
+    /* Try again later.  */
+    bdrv_set_dirty(source, s->sector_num, nb_sectors);
+    return ret;
 }
 
 static void coroutine_fn mirror_run(void *opaque)
@@ -117,8 +144,9 @@ static void coroutine_fn mirror_run(void *opaque)
 
         cnt = bdrv_get_dirty_count(bs);
         if (cnt != 0) {
-            ret = mirror_iteration(s);
-            if (ret < 0) {
+            BlockErrorAction action = BDRV_ACTION_REPORT;
+            ret = mirror_iteration(s, &action);
+            if (ret < 0 && action == BDRV_ACTION_REPORT) {
                 goto immediate_exit;
             }
             cnt = bdrv_get_dirty_count(bs);
@@ -129,23 +157,25 @@ static void coroutine_fn mirror_run(void *opaque)
             trace_mirror_before_flush(s);
             ret = bdrv_flush(s->target);
             if (ret < 0) {
-                goto immediate_exit;
-            }
-
-            /* We're out of the streaming phase.  From now on, if the job
-             * is cancelled we will actually complete all pending I/O and
-             * report completion.  This way, block-job-cancel will leave
-             * the target in a consistent state.
-             */
-            s->common.offset = end * BDRV_SECTOR_SIZE;
-            if (!s->synced) {
-                block_job_ready(&s->common);
-                s->synced = true;
+                if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
+                    goto immediate_exit;
+                }
+            } else {
+                /* We're out of the streaming phase.  From now on, if the job
+                 * is cancelled we will actually complete all pending I/O and
+                 * report completion.  This way, block-job-cancel will leave
+                 * the target in a consistent state.
+                 */
+                s->common.offset = end * BDRV_SECTOR_SIZE;
+                if (!s->synced) {
+                    block_job_ready(&s->common);
+                    s->synced = true;
+                }
+
+                should_complete = s->should_complete ||
+                    block_job_is_cancelled(&s->common);
+                cnt = bdrv_get_dirty_count(bs);
             }
-
-            should_complete = s->should_complete ||
-                block_job_is_cancelled(&s->common);
-            cnt = bdrv_get_dirty_count(bs);
         }
 
         if (cnt == 0 && should_complete) {
@@ -197,6 +227,7 @@ static void coroutine_fn mirror_run(void *opaque)
 immediate_exit:
     g_free(s->buf);
     bdrv_set_dirty_tracking(bs, false);
+    bdrv_iostatus_disable(s->target);
     if (s->should_complete && ret == 0) {
         if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
             bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
@@ -219,6 +250,13 @@ static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
     ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
 }
 
+static void mirror_iostatus_reset(BlockJob *job)
+{
+    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
+
+    bdrv_iostatus_reset(s->target);
+}
+
 static void mirror_complete(BlockJob *job, Error **errp)
 {
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
@@ -245,25 +283,39 @@ static BlockJobType mirror_job_type = {
     .instance_size = sizeof(MirrorBlockJob),
     .job_type      = "mirror",
     .set_speed     = mirror_set_speed,
+    .iostatus_reset= mirror_iostatus_reset,
     .complete      = mirror_complete,
 };
 
 void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                   int64_t speed, MirrorSyncMode mode,
+                  BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp)
 {
     MirrorBlockJob *s;
 
+    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
+         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
+        !bdrv_iostatus_is_enabled(bs)) {
+        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
+        return;
+    }
+
     s = block_job_create(&mirror_job_type, bs, speed, cb, opaque, errp);
     if (!s) {
         return;
     }
 
+    s->on_source_error = on_source_error;
+    s->on_target_error = on_target_error;
     s->target = target;
     s->mode = mode;
     bdrv_set_dirty_tracking(bs, true);
     bdrv_set_enable_write_cache(s->target, true);
+    bdrv_set_on_error(s->target, on_target_error, on_target_error);
+    bdrv_iostatus_enable(s->target);
     s->common.co = qemu_coroutine_create(mirror_run);
     trace_mirror_start(bs, s, s->common.co, opaque);
     qemu_coroutine_enter(s->common.co, s);
diff --git a/block_int.h b/block_int.h
index aaa46a8..00204eb 100644
--- a/block_int.h
+++ b/block_int.h
@@ -337,6 +337,8 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
  * @target: Block device to write to.
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @mode: Whether to collapse all images in the chain to the target.
+ * @on_source_error: The action to take upon error reading from the source.
+ * @on_target_error: The action to take upon error writing to the target.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
  * @errp: Error object.
@@ -348,6 +350,8 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
  */
 void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                   int64_t speed, MirrorSyncMode mode,
+                  BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp);
 
diff --git a/blockdev.c b/blockdev.c
index 431c678..a068a4b 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -1185,7 +1185,10 @@ void qmp_drive_mirror(const char *device, const char *target,
                       bool has_format, const char *format,
                       enum MirrorSyncMode sync,
                       bool has_mode, enum NewImageMode mode,
-                      bool has_speed, int64_t speed, Error **errp)
+                      bool has_speed, int64_t speed,
+                      bool has_on_source_error, BlockdevOnError on_source_error,
+                      bool has_on_target_error, BlockdevOnError on_target_error,
+                      Error **errp)
 {
     BlockDriverInfo bdi;
     BlockDriverState *bs;
@@ -1200,6 +1203,12 @@ void qmp_drive_mirror(const char *device, const char *target,
     if (!has_speed) {
         speed = 0;
     }
+    if (!has_on_source_error) {
+        on_source_error = BLOCKDEV_ON_ERROR_REPORT;
+    }
+    if (!has_on_target_error) {
+        on_target_error = BLOCKDEV_ON_ERROR_REPORT;
+    }
     if (!has_mode) {
         mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
     }
@@ -1292,7 +1301,8 @@ void qmp_drive_mirror(const char *device, const char *target,
         }
     }
 
-    mirror_start(bs, target_bs, speed, sync, block_job_cb, bs, &local_err);
+    mirror_start(bs, target_bs, speed, sync, on_source_error, on_target_error,
+                 block_job_cb, bs, &local_err);
     if (local_err != NULL) {
         bdrv_delete(target_bs);
         error_propagate(errp, local_err);
diff --git a/hmp.c b/hmp.c
index e530253..4a458ac 100644
--- a/hmp.c
+++ b/hmp.c
@@ -795,7 +795,8 @@ void hmp_drive_mirror(Monitor *mon, const QDict *qdict)
 
     qmp_drive_mirror(device, filename, !!format, format,
                      full ? MIRROR_SYNC_MODE_FULL : MIRROR_SYNC_MODE_TOP,
-                     true, mode, false, 0, &errp);
+                     true, mode, false, 0,
+                     false, 0, false, 0, &errp);
     hmp_handle_error(mon, &errp);
 }
 
diff --git a/qapi-schema.json b/qapi-schema.json
index a066cd5..6aa443e 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -1629,6 +1629,14 @@
 #        (all the disk, only the sectors allocated in the topmost image, or
 #        only new I/O).
 #
+# @on-source-error: #optional the action to take on an error on the source,
+#                   default 'report'.  'stop' and 'enospc' can only be used
+#                   if the block device supports io-status (see BlockInfo).
+#
+# @on-target-error: #optional the action to take on an error on the target,
+#                   default 'report' (no limitations, since this applies to
+#                   a different block device than @device).
+#
 # Returns: nothing on success
 #          If @device is not a valid block device, DeviceNotFound
 #
@@ -1637,7 +1645,8 @@
 { 'command': 'drive-mirror',
   'data': { 'device': 'str', 'target': 'str', '*format': 'str',
             'sync': 'MirrorSyncMode', '*mode': 'NewImageMode',
-            '*speed': 'int' } }
+            '*speed': 'int', '*on-source-error': 'BlockdevOnError',
+            '*on-target-error': 'BlockdevOnError' } }
 
 ##
 # @migrate_cancel
diff --git a/qmp-commands.hx b/qmp-commands.hx
index 614baea..c31312f 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -937,7 +937,8 @@ EQMP
 
     {
         .name       = "drive-mirror",
-        .args_type  = "sync:s,device:B,target:s,speed:i?,mode:s?,format:s?",
+        .args_type  = "sync:s,device:B,target:s,speed:i?,mode:s?,format:s?,"
+                      "on-source-error:s?,on-target-error:s?",
         .mhandler.cmd_new = qmp_marshal_input_drive_mirror,
     },
 
@@ -965,6 +966,11 @@ Arguments:
   possibilities include "full" for all the disk, "top" for only the sectors
   allocated in the topmost image, or "none" to only replicate new I/O
   (MirrorSyncMode).
+- "on-source-error": the action to take on an error on the source
+  (BlockdevOnError, default 'report')
+- "on-target-error": the action to take on an error on the target
+  (BlockdevOnError, default 'report')
+
 
 
 Example:
-- 
1.7.6.5