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

Block layer patches:

- Fix crashes and hangs related to iothreads, bdrv_drain and block jobs:
    - Fix some AIO context locking in jobs
    - Fix blk->in_flight during blk_wait_while_drained()
- vpc: Don't round up already aligned BAT sizes

# gpg: Signature made Tue 07 Apr 2020 15:25:24 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:
  vpc: Don't round up already aligned BAT sizes
  block: Fix blk->in_flight during blk_wait_while_drained()
  block: Increase BB.in_flight for coroutine and sync interfaces
  block-backend: Reorder flush/pdiscard function definitions
  backup: don't acquire aio_context in backup_clean
  replication: assert we own context before job_cancel_sync
  job: take each job's lock individually in job_txn_apply

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

9 files changed, 193 insertions, 95 deletions

diff --git a/block/backup.c b/block/backup.c
index 7430ca5883..a7a7dcaf4c 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -126,11 +126,7 @@ static void backup_abort(Job *job)
 static void backup_clean(Job *job)
 {
     BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
-    AioContext *aio_context = bdrv_get_aio_context(s->backup_top);
-
-    aio_context_acquire(aio_context);
     bdrv_backup_top_drop(s->backup_top);
-    aio_context_release(aio_context);
 }
 
 void backup_do_checkpoint(BlockJob *job, Error **errp)
diff --git a/block/block-backend.c b/block/block-backend.c
index 8b8f2a80a0..38ae413826 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1140,16 +1140,22 @@ static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
     return 0;
 }
 
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
 static void coroutine_fn blk_wait_while_drained(BlockBackend *blk)
 {
+    assert(blk->in_flight > 0);
+
     if (blk->quiesce_counter && !blk->disable_request_queuing) {
+        blk_dec_in_flight(blk);
         qemu_co_queue_wait(&blk->queued_requests, NULL);
+        blk_inc_in_flight(blk);
     }
 }
 
-int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
-                               unsigned int bytes, QEMUIOVector *qiov,
-                               BdrvRequestFlags flags)
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_do_preadv(BlockBackend *blk, int64_t offset, unsigned int bytes,
+              QEMUIOVector *qiov, BdrvRequestFlags flags)
 {
     int ret;
     BlockDriverState *bs;
@@ -1178,10 +1184,24 @@ int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
     return ret;
 }
 
-int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
-                                     unsigned int bytes,
-                                     QEMUIOVector *qiov, size_t qiov_offset,
-                                     BdrvRequestFlags flags)
+int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
+                               unsigned int bytes, QEMUIOVector *qiov,
+                               BdrvRequestFlags flags)
+{
+    int ret;
+
+    blk_inc_in_flight(blk);
+    ret = blk_do_preadv(blk, offset, bytes, qiov, flags);
+    blk_dec_in_flight(blk);
+
+    return ret;
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_do_pwritev_part(BlockBackend *blk, int64_t offset, unsigned int bytes,
+                    QEMUIOVector *qiov, size_t qiov_offset,
+                    BdrvRequestFlags flags)
 {
     int ret;
     BlockDriverState *bs;
@@ -1214,6 +1234,20 @@ int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
     return ret;
 }
 
+int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
+                                     unsigned int bytes,
+                                     QEMUIOVector *qiov, size_t qiov_offset,
+                                     BdrvRequestFlags flags)
+{
+    int ret;
+
+    blk_inc_in_flight(blk);
+    ret = blk_do_pwritev_part(blk, offset, bytes, qiov, qiov_offset, flags);
+    blk_dec_in_flight(blk);
+
+    return ret;
+}
+
 int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
                                 unsigned int bytes, QEMUIOVector *qiov,
                                 BdrvRequestFlags flags)
@@ -1234,7 +1268,7 @@ static void blk_read_entry(void *opaque)
     BlkRwCo *rwco = opaque;
     QEMUIOVector *qiov = rwco->iobuf;
 
-    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, qiov->size,
+    rwco->ret = blk_do_preadv(rwco->blk, rwco->offset, qiov->size,
                               qiov, rwco->flags);
     aio_wait_kick();
 }
@@ -1244,8 +1278,8 @@ static void blk_write_entry(void *opaque)
     BlkRwCo *rwco = opaque;
     QEMUIOVector *qiov = rwco->iobuf;
 
-    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, qiov->size,
-                               qiov, rwco->flags);
+    rwco->ret = blk_do_pwritev_part(rwco->blk, rwco->offset, qiov->size,
+                                    qiov, 0, rwco->flags);
     aio_wait_kick();
 }
 
@@ -1262,6 +1296,7 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
         .ret    = NOT_DONE,
     };
 
+    blk_inc_in_flight(blk);
     if (qemu_in_coroutine()) {
         /* Fast-path if already in coroutine context */
         co_entry(&rwco);
@@ -1270,6 +1305,7 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
         bdrv_coroutine_enter(blk_bs(blk), co);
         BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE);
     }
+    blk_dec_in_flight(blk);
 
     return rwco.ret;
 }
@@ -1387,14 +1423,8 @@ 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,
+    rwco->ret = blk_do_preadv(rwco->blk, rwco->offset, acb->bytes,
                               qiov, rwco->flags);
     blk_aio_complete(acb);
 }
@@ -1405,15 +1435,9 @@ 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);
+    rwco->ret = blk_do_pwritev_part(rwco->blk, rwco->offset, acb->bytes,
+                                    qiov, 0, rwco->flags);
     blk_aio_complete(acb);
 }
 
@@ -1488,38 +1512,6 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
                         blk_aio_write_entry, flags, cb, opaque);
 }
 
-static void blk_aio_flush_entry(void *opaque)
-{
-    BlkAioEmAIOCB *acb = opaque;
-    BlkRwCo *rwco = &acb->rwco;
-
-    rwco->ret = blk_co_flush(rwco->blk);
-    blk_aio_complete(acb);
-}
-
-BlockAIOCB *blk_aio_flush(BlockBackend *blk,
-                          BlockCompletionFunc *cb, void *opaque)
-{
-    return blk_aio_prwv(blk, 0, 0, NULL, blk_aio_flush_entry, 0, cb, opaque);
-}
-
-static void blk_aio_pdiscard_entry(void *opaque)
-{
-    BlkAioEmAIOCB *acb = opaque;
-    BlkRwCo *rwco = &acb->rwco;
-
-    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, acb->bytes);
-    blk_aio_complete(acb);
-}
-
-BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk,
-                             int64_t offset, int bytes,
-                             BlockCompletionFunc *cb, void *opaque)
-{
-    return blk_aio_prwv(blk, offset, bytes, NULL, blk_aio_pdiscard_entry, 0,
-                        cb, opaque);
-}
-
 void blk_aio_cancel(BlockAIOCB *acb)
 {
     bdrv_aio_cancel(acb);
@@ -1530,7 +1522,9 @@ void blk_aio_cancel_async(BlockAIOCB *acb)
     bdrv_aio_cancel_async(acb);
 }
 
-int blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
 {
     blk_wait_while_drained(blk);
 
@@ -1546,8 +1540,7 @@ static void blk_ioctl_entry(void *opaque)
     BlkRwCo *rwco = opaque;
     QEMUIOVector *qiov = rwco->iobuf;
 
-    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset,
-                             qiov->iov[0].iov_base);
+    rwco->ret = blk_do_ioctl(rwco->blk, rwco->offset, qiov->iov[0].iov_base);
     aio_wait_kick();
 }
 
@@ -1561,7 +1554,7 @@ static void blk_aio_ioctl_entry(void *opaque)
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
 
-    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset, rwco->iobuf);
+    rwco->ret = blk_do_ioctl(rwco->blk, rwco->offset, rwco->iobuf);
 
     blk_aio_complete(acb);
 }
@@ -1572,7 +1565,9 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
     return blk_aio_prwv(blk, req, 0, buf, blk_aio_ioctl_entry, 0, cb, opaque);
 }
 
-int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn
+blk_do_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
 {
     int ret;
 
@@ -1586,7 +1581,50 @@ int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
     return bdrv_co_pdiscard(blk->root, offset, bytes);
 }
 
-int blk_co_flush(BlockBackend *blk)
+static void blk_aio_pdiscard_entry(void *opaque)
+{
+    BlkAioEmAIOCB *acb = opaque;
+    BlkRwCo *rwco = &acb->rwco;
+
+    rwco->ret = blk_do_pdiscard(rwco->blk, rwco->offset, acb->bytes);
+    blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk,
+                             int64_t offset, int bytes,
+                             BlockCompletionFunc *cb, void *opaque)
+{
+    return blk_aio_prwv(blk, offset, bytes, NULL, blk_aio_pdiscard_entry, 0,
+                        cb, opaque);
+}
+
+int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+{
+    int ret;
+
+    blk_inc_in_flight(blk);
+    ret = blk_do_pdiscard(blk, offset, bytes);
+    blk_dec_in_flight(blk);
+
+    return ret;
+}
+
+static void blk_pdiscard_entry(void *opaque)
+{
+    BlkRwCo *rwco = opaque;
+    QEMUIOVector *qiov = rwco->iobuf;
+
+    rwco->ret = blk_do_pdiscard(rwco->blk, rwco->offset, qiov->size);
+    aio_wait_kick();
+}
+
+int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+{
+    return blk_prw(blk, offset, NULL, bytes, blk_pdiscard_entry, 0);
+}
+
+/* To be called between exactly one pair of blk_inc/dec_in_flight() */
+static int coroutine_fn blk_do_flush(BlockBackend *blk)
 {
     blk_wait_while_drained(blk);
 
@@ -1597,10 +1635,36 @@ int blk_co_flush(BlockBackend *blk)
     return bdrv_co_flush(blk_bs(blk));
 }
 
+static void blk_aio_flush_entry(void *opaque)
+{
+    BlkAioEmAIOCB *acb = opaque;
+    BlkRwCo *rwco = &acb->rwco;
+
+    rwco->ret = blk_do_flush(rwco->blk);
+    blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_flush(BlockBackend *blk,
+                          BlockCompletionFunc *cb, void *opaque)
+{
+    return blk_aio_prwv(blk, 0, 0, NULL, blk_aio_flush_entry, 0, cb, opaque);
+}
+
+int coroutine_fn blk_co_flush(BlockBackend *blk)
+{
+    int ret;
+
+    blk_inc_in_flight(blk);
+    ret = blk_do_flush(blk);
+    blk_dec_in_flight(blk);
+
+    return ret;
+}
+
 static void blk_flush_entry(void *opaque)
 {
     BlkRwCo *rwco = opaque;
-    rwco->ret = blk_co_flush(rwco->blk);
+    rwco->ret = blk_do_flush(rwco->blk);
     aio_wait_kick();
 }
 
@@ -2083,20 +2147,6 @@ int blk_truncate(BlockBackend *blk, int64_t offset, bool exact,
     return bdrv_truncate(blk->root, offset, exact, prealloc, errp);
 }
 
-static void blk_pdiscard_entry(void *opaque)
-{
-    BlkRwCo *rwco = opaque;
-    QEMUIOVector *qiov = rwco->iobuf;
-
-    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, qiov->size);
-    aio_wait_kick();
-}
-
-int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
-{
-    return blk_prw(blk, offset, NULL, bytes, blk_pdiscard_entry, 0);
-}
-
 int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
                      int64_t pos, int size)
 {
diff --git a/block/replication.c b/block/replication.c
index 413d95407d..da013c2041 100644
--- a/block/replication.c
+++ b/block/replication.c
@@ -144,12 +144,15 @@ fail:
 static void replication_close(BlockDriverState *bs)
 {
     BDRVReplicationState *s = bs->opaque;
+    Job *commit_job;
 
     if (s->stage == BLOCK_REPLICATION_RUNNING) {
         replication_stop(s->rs, false, NULL);
     }
     if (s->stage == BLOCK_REPLICATION_FAILOVER) {
-        job_cancel_sync(&s->commit_job->job);
+        commit_job = &s->commit_job->job;
+        assert(commit_job->aio_context == qemu_get_current_aio_context());
+        job_cancel_sync(commit_job);
     }
 
     if (s->mode == REPLICATION_MODE_SECONDARY) {
diff --git a/block/vpc.c b/block/vpc.c
index 6df75e22dc..d8141b52da 100644
--- a/block/vpc.c
+++ b/block/vpc.c
@@ -835,7 +835,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
 
     /* Write the footer (twice: at the beginning and at the end) */
     block_size = 0x200000;
-    num_bat_entries = (total_sectors + block_size / 512) / (block_size / 512);
+    num_bat_entries = DIV_ROUND_UP(total_sectors, block_size / 512);
 
     ret = blk_pwrite(blk, offset, buf, HEADER_SIZE, 0);
     if (ret < 0) {
diff --git a/blockdev.c b/blockdev.c
index fa8630cb41..5faddaa705 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -3612,7 +3612,16 @@ void qmp_block_job_finalize(const char *id, Error **errp)
     }
 
     trace_qmp_block_job_finalize(job);
+    job_ref(&job->job);
     job_finalize(&job->job, errp);
+
+    /*
+     * Job's context might have changed via job_finalize (and job_txn_apply
+     * automatically acquires the new one), so make sure we release the correct
+     * one.
+     */
+    aio_context = blk_get_aio_context(job->blk);
+    job_unref(&job->job);
     aio_context_release(aio_context);
 }
 
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index b198deca0b..9bbdbd63d7 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -171,7 +171,6 @@ BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int bytes,
                              BlockCompletionFunc *cb, void *opaque);
 void blk_aio_cancel(BlockAIOCB *acb);
 void blk_aio_cancel_async(BlockAIOCB *acb);
-int blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
 int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
 BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
                           BlockCompletionFunc *cb, void *opaque);
diff --git a/job-qmp.c b/job-qmp.c
index fecc939ebd..f9a58832e1 100644
--- a/job-qmp.c
+++ b/job-qmp.c
@@ -114,7 +114,16 @@ void qmp_job_finalize(const char *id, Error **errp)
     }
 
     trace_qmp_job_finalize(job);
+    job_ref(job);
     job_finalize(job, errp);
+
+    /*
+     * Job's context might have changed via job_finalize (and job_txn_apply
+     * automatically acquires the new one), so make sure we release the correct
+     * one.
+     */
+    aio_context = job->aio_context;
+    job_unref(job);
     aio_context_release(aio_context);
 }
 
diff --git a/job.c b/job.c
index 134a07b92e..53be57a3a0 100644
--- a/job.c
+++ b/job.c
@@ -136,17 +136,38 @@ static void job_txn_del_job(Job *job)
     }
 }
 
-static int job_txn_apply(JobTxn *txn, int fn(Job *))
+static int job_txn_apply(Job *job, int fn(Job *))
 {
-    Job *job, *next;
+    AioContext *inner_ctx;
+    Job *other_job, *next;
+    JobTxn *txn = job->txn;
     int rc = 0;
 
-    QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) {
-        rc = fn(job);
+    /*
+     * Similar to job_completed_txn_abort, we take each job's lock before
+     * applying fn, but since we assume that outer_ctx is held by the caller,
+     * we need to release it here to avoid holding the lock twice - which would
+     * break AIO_WAIT_WHILE from within fn.
+     */
+    job_ref(job);
+    aio_context_release(job->aio_context);
+
+    QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) {
+        inner_ctx = other_job->aio_context;
+        aio_context_acquire(inner_ctx);
+        rc = fn(other_job);
+        aio_context_release(inner_ctx);
         if (rc) {
             break;
         }
     }
+
+    /*
+     * Note that job->aio_context might have been changed by calling fn, so we
+     * can't use a local variable to cache it.
+     */
+    aio_context_acquire(job->aio_context);
+    job_unref(job);
     return rc;
 }
 
@@ -774,11 +795,11 @@ static void job_do_finalize(Job *job)
     assert(job && job->txn);
 
     /* prepare the transaction to complete */
-    rc = job_txn_apply(job->txn, job_prepare);
+    rc = job_txn_apply(job, job_prepare);
     if (rc) {
         job_completed_txn_abort(job);
     } else {
-        job_txn_apply(job->txn, job_finalize_single);
+        job_txn_apply(job, job_finalize_single);
     }
 }
 
@@ -824,10 +845,10 @@ static void job_completed_txn_success(Job *job)
         assert(other_job->ret == 0);
     }
 
-    job_txn_apply(txn, job_transition_to_pending);
+    job_txn_apply(job, job_transition_to_pending);
 
     /* If no jobs need manual finalization, automatically do so */
-    if (job_txn_apply(txn, job_needs_finalize) == 0) {
+    if (job_txn_apply(job, job_needs_finalize) == 0) {
         job_do_finalize(job);
     }
 }
@@ -849,9 +870,10 @@ static void job_completed(Job *job)
 static void job_exit(void *opaque)
 {
     Job *job = (Job *)opaque;
-    AioContext *ctx = job->aio_context;
+    AioContext *ctx;
 
-    aio_context_acquire(ctx);
+    job_ref(job);
+    aio_context_acquire(job->aio_context);
 
     /* This is a lie, we're not quiescent, but still doing the completion
      * callbacks. However, completion callbacks tend to involve operations that
@@ -862,6 +884,14 @@ static void job_exit(void *opaque)
 
     job_completed(job);
 
+    /*
+     * Note that calling job_completed can move the job to a different
+     * aio_context, so we cannot cache from above. job_txn_apply takes care of
+     * acquiring the new lock, and we ref/unref to avoid job_completed freeing
+     * the job underneath us.
+     */
+    ctx = job->aio_context;
+    job_unref(job);
     aio_context_release(ctx);
 }
 
diff --git a/tests/test-blockjob.c b/tests/test-blockjob.c
index 4eeb184caf..7519847912 100644
--- a/tests/test-blockjob.c
+++ b/tests/test-blockjob.c
@@ -367,7 +367,9 @@ static void test_cancel_concluded(void)
     aio_poll(qemu_get_aio_context(), true);
     assert(job->status == JOB_STATUS_PENDING);
 
+    aio_context_acquire(job->aio_context);
     job_finalize(job, &error_abort);
+    aio_context_release(job->aio_context);
     assert(job->status == JOB_STATUS_CONCLUDED);
 
     cancel_common(s);