Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches:

- file-posix: Fix O_DIRECT alignment detection
- Fixes for concurrent block jobs
- block-backend: Queue requests while drained (fix IDE vs. job crashes)
- qemu-img convert: Deprecate using -n and -o together
- iotests: Migration tests with filter nodes
- iotests: More media change tests

# gpg: Signature made Fri 16 Aug 2019 10:29:18 BST
# gpg:                using RSA key 7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream:
  file-posix: Handle undetectable alignment
  qemu-img convert: Deprecate using -n and -o together
  block-backend: Queue requests while drained
  mirror: Keep mirror_top_bs drained after dropping permissions
  block: Remove blk_pread_unthrottled()
  iotests: Add test for concurrent stream/commit
  tests: Test mid-drain bdrv_replace_child_noperm()
  tests: Test polling in bdrv_drop_intermediate()
  block: Reduce (un)drains when replacing a child
  block: Keep subtree drained in drop_intermediate
  block: Simplify bdrv_filter_default_perms()
  iotests: Test migration with all kinds of filter nodes
  iotests: Move migration helpers to iotests.py
  iotests/118: Add -blockdev based tests
  iotests/118: Create test classes dynamically
  iotests/118: Test media change for scsi-cd

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 84 insertions, 31 deletions

diff --git a/block/backup.c b/block/backup.c
index b26c22c..4743c8f 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -644,6 +644,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
     if (ret < 0) {
         goto error;
     }
+    blk_set_disable_request_queuing(job->target, true);
 
     job->on_source_error = on_source_error;
     job->on_target_error = on_target_error;
diff --git a/block/block-backend.c b/block/block-backend.c
index 84e76bf..1c605d5 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -81,6 +81,9 @@ struct BlockBackend {
     QLIST_HEAD(, BlockBackendAioNotifier) aio_notifiers;
 
     int quiesce_counter;
+    CoQueue queued_requests;
+    bool disable_request_queuing;
+
     VMChangeStateEntry *vmsh;
     bool force_allow_inactivate;
 
@@ -341,6 +344,7 @@ BlockBackend *blk_new(AioContext *ctx, uint64_t perm, uint64_t shared_perm)
 
     block_acct_init(&blk->stats);
 
+    qemu_co_queue_init(&blk->queued_requests);
     notifier_list_init(&blk->remove_bs_notifiers);
     notifier_list_init(&blk->insert_bs_notifiers);
     QLIST_INIT(&blk->aio_notifiers);
@@ -1098,6 +1102,11 @@ void blk_set_allow_aio_context_change(BlockBackend *blk, bool allow)
     blk->allow_aio_context_change = allow;
 }
 
+void blk_set_disable_request_queuing(BlockBackend *blk, bool disable)
+{
+    blk->disable_request_queuing = disable;
+}
+
 static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
                                   size_t size)
 {
@@ -1129,13 +1138,24 @@ static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
     return 0;
 }
 
+static void coroutine_fn blk_wait_while_drained(BlockBackend *blk)
+{
+    if (blk->quiesce_counter && !blk->disable_request_queuing) {
+        qemu_co_queue_wait(&blk->queued_requests, NULL);
+    }
+}
+
 int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
                                unsigned int bytes, QEMUIOVector *qiov,
                                BdrvRequestFlags flags)
 {
     int ret;
-    BlockDriverState *bs = blk_bs(blk);
+    BlockDriverState *bs;
+
+    blk_wait_while_drained(blk);
 
+    /* Call blk_bs() only after waiting, the graph may have changed */
+    bs = blk_bs(blk);
     trace_blk_co_preadv(blk, bs, offset, bytes, flags);
 
     ret = blk_check_byte_request(blk, offset, bytes);
@@ -1161,8 +1181,12 @@ int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
                                 BdrvRequestFlags flags)
 {
     int ret;
-    BlockDriverState *bs = blk_bs(blk);
+    BlockDriverState *bs;
+
+    blk_wait_while_drained(blk);
 
+    /* Call blk_bs() only after waiting, the graph may have changed */
+    bs = blk_bs(blk);
     trace_blk_co_pwritev(blk, bs, offset, bytes, flags);
 
     ret = blk_check_byte_request(blk, offset, bytes);
@@ -1239,22 +1263,6 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
     return rwco.ret;
 }
 
-int blk_pread_unthrottled(BlockBackend *blk, int64_t offset, uint8_t *buf,
-                          int count)
-{
-    int ret;
-
-    ret = blk_check_byte_request(blk, offset, count);
-    if (ret < 0) {
-        return ret;
-    }
-
-    blk_root_drained_begin(blk->root);
-    ret = blk_pread(blk, offset, buf, count);
-    blk_root_drained_end(blk->root, NULL);
-    return ret;
-}
-
 int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
                       int bytes, BdrvRequestFlags flags)
 {
@@ -1367,6 +1375,12 @@ static void blk_aio_read_entry(void *opaque)
     BlkRwCo *rwco = &acb->rwco;
     QEMUIOVector *qiov = rwco->iobuf;
 
+    if (rwco->blk->quiesce_counter) {
+        blk_dec_in_flight(rwco->blk);
+        blk_wait_while_drained(rwco->blk);
+        blk_inc_in_flight(rwco->blk);
+    }
+
     assert(qiov->size == acb->bytes);
     rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, acb->bytes,
                               qiov, rwco->flags);
@@ -1379,6 +1393,12 @@ static void blk_aio_write_entry(void *opaque)
     BlkRwCo *rwco = &acb->rwco;
     QEMUIOVector *qiov = rwco->iobuf;
 
+    if (rwco->blk->quiesce_counter) {
+        blk_dec_in_flight(rwco->blk);
+        blk_wait_while_drained(rwco->blk);
+        blk_inc_in_flight(rwco->blk);
+    }
+
     assert(!qiov || qiov->size == acb->bytes);
     rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, acb->bytes,
                                qiov, rwco->flags);
@@ -1500,6 +1520,8 @@ void blk_aio_cancel_async(BlockAIOCB *acb)
 
 int blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
 {
+    blk_wait_while_drained(blk);
+
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
@@ -1540,7 +1562,11 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
 
 int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
 {
-    int ret = blk_check_byte_request(blk, offset, bytes);
+    int ret;
+
+    blk_wait_while_drained(blk);
+
+    ret = blk_check_byte_request(blk, offset, bytes);
     if (ret < 0) {
         return ret;
     }
@@ -1550,6 +1576,8 @@ int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
 
 int blk_co_flush(BlockBackend *blk)
 {
+    blk_wait_while_drained(blk);
+
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
@@ -2250,6 +2278,9 @@ static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter)
         if (blk->dev_ops && blk->dev_ops->drained_end) {
             blk->dev_ops->drained_end(blk->dev_opaque);
         }
+        while (qemu_co_enter_next(&blk->queued_requests, NULL)) {
+            /* Resume all queued requests */
+        }
     }
 }
 
diff --git a/block/commit.c b/block/commit.c
index 2c5a6d4..408ae15 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -350,6 +350,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     if (ret < 0) {
         goto fail;
     }
+    blk_set_disable_request_queuing(s->base, true);
     s->base_bs = base;
 
     /* Required permissions are already taken with block_job_add_bdrv() */
@@ -358,6 +359,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     if (ret < 0) {
         goto fail;
     }
+    blk_set_disable_request_queuing(s->top, true);
 
     s->backing_file_str = g_strdup(backing_file_str);
     s->on_error = on_error;
diff --git a/block/file-posix.c b/block/file-posix.c
index 4479cc7..b8b4dad 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -323,6 +323,7 @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp)
     BDRVRawState *s = bs->opaque;
     char *buf;
     size_t max_align = MAX(MAX_BLOCKSIZE, getpagesize());
+    size_t alignments[] = {1, 512, 1024, 2048, 4096};
 
     /* For SCSI generic devices the alignment is not really used.
        With buffered I/O, we don't have any restrictions. */
@@ -349,25 +350,38 @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp)
     }
 #endif
 
-    /* If we could not get the sizes so far, we can only guess them */
-    if (!s->buf_align) {
+    /*
+     * If we could not get the sizes so far, we can only guess them. First try
+     * to detect request alignment, since it is more likely to succeed. Then
+     * try to detect buf_align, which cannot be detected in some cases (e.g.
+     * Gluster). If buf_align cannot be detected, we fallback to the value of
+     * request_alignment.
+     */
+
+    if (!bs->bl.request_alignment) {
+        int i;
         size_t align;
-        buf = qemu_memalign(max_align, 2 * max_align);
-        for (align = 512; align <= max_align; align <<= 1) {
-            if (raw_is_io_aligned(fd, buf + align, max_align)) {
-                s->buf_align = align;
+        buf = qemu_memalign(max_align, max_align);
+        for (i = 0; i < ARRAY_SIZE(alignments); i++) {
+            align = alignments[i];
+            if (raw_is_io_aligned(fd, buf, align)) {
+                /* Fallback to safe value. */
+                bs->bl.request_alignment = (align != 1) ? align : max_align;
                 break;
             }
         }
         qemu_vfree(buf);
     }
 
-    if (!bs->bl.request_alignment) {
+    if (!s->buf_align) {
+        int i;
         size_t align;
-        buf = qemu_memalign(s->buf_align, max_align);
-        for (align = 512; align <= max_align; align <<= 1) {
-            if (raw_is_io_aligned(fd, buf, align)) {
-                bs->bl.request_alignment = align;
+        buf = qemu_memalign(max_align, 2 * max_align);
+        for (i = 0; i < ARRAY_SIZE(alignments); i++) {
+            align = alignments[i];
+            if (raw_is_io_aligned(fd, buf + align, max_align)) {
+                /* Fallback to request_aligment. */
+                s->buf_align = (align != 1) ? align : bs->bl.request_alignment;
                 break;
             }
         }
diff --git a/block/mirror.c b/block/mirror.c
index 9f5c59e..9b36391 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -656,7 +656,10 @@ static int mirror_exit_common(Job *job)
     s->target = NULL;
 
     /* We don't access the source any more. Dropping any WRITE/RESIZE is
-     * required before it could become a backing file of target_bs. */
+     * required before it could become a backing file of target_bs. Not having
+     * these permissions any more means that we can't allow any new requests on
+     * mirror_top_bs from now on, so keep it drained. */
+    bdrv_drained_begin(mirror_top_bs);
     bs_opaque->stop = true;
     bdrv_child_refresh_perms(mirror_top_bs, mirror_top_bs->backing,
                              &error_abort);
@@ -724,6 +727,7 @@ static int mirror_exit_common(Job *job)
     bs_opaque->job = NULL;
 
     bdrv_drained_end(src);
+    bdrv_drained_end(mirror_top_bs);
     s->in_drain = false;
     bdrv_unref(mirror_top_bs);
     bdrv_unref(src);
@@ -1632,6 +1636,7 @@ static BlockJob *mirror_start_job(
         blk_set_force_allow_inactivate(s->target);
     }
     blk_set_allow_aio_context_change(s->target, true);
+    blk_set_disable_request_queuing(s->target, true);
 
     s->replaces = g_strdup(replaces);
     s->on_source_error = on_source_error;