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

…taging

Block layer patches:

- block: Fix crash with qcow2 partial cluster COW with small cluster
  sizes (misaligned write requests with BDRV_REQ_NO_FALLBACK)
- qcow2: Fix integer overflow potentially causing corruption with huge
  requests
- vhdx: Detect truncated image files
- tools: Support help options for --object
- Various block-related replay improvements
- iotests/028: Fix for long $TEST_DIRs

# gpg: Signature made Mon 14 Oct 2019 17:02:54 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:
  iotests: Test large write request to qcow2 file
  qcow2: Limit total allocation range to INT_MAX
  qemu-nbd: Support help options for --object
  qemu-img: Support help options for --object
  qemu-io: Support help options for --object
  vl: Split off user_creatable_print_help()
  iotests/028: Fix for long $TEST_DIRs
  block: Reject misaligned write requests with BDRV_REQ_NO_FALLBACK
  replay: add BH oneshot event for block layer
  replay: finish record/replay before closing the disks
  replay: don't drain/flush bdrv queue while RR is working
  replay: update docs for record/replay with block devices
  replay: disable default snapshot for record/replay
  block: implement bdrv_snapshot_goto for blkreplay
  block/vhdx: add check for truncated image files

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

block/blkreplay.c

@@ -126,6 +126,12 @@ static int coroutine_fn blkreplay_co_flush(BlockDriverState *bs)
     return ret;
 }
 
+static int blkreplay_snapshot_goto(BlockDriverState *bs,
+                                   const char *snapshot_id)
+{
+    return bdrv_snapshot_goto(bs->file->bs, snapshot_id, NULL);
+}
+
 static BlockDriver bdrv_blkreplay = {
     .format_name            = "blkreplay",
     .instance_size          = 0,
@@ -140,6 +146,8 @@ static BlockDriver bdrv_blkreplay = {
     .bdrv_co_pwrite_zeroes  = blkreplay_co_pwrite_zeroes,
     .bdrv_co_pdiscard       = blkreplay_co_pdiscard,
     .bdrv_co_flush          = blkreplay_co_flush,
+
+    .bdrv_snapshot_goto     = blkreplay_snapshot_goto,
 };
 
 static void bdrv_blkreplay_init(void)

block/block-backend.c

@@ -18,6 +18,8 @@
 #include "hw/qdev-core.h"
 #include "sysemu/blockdev.h"
 #include "sysemu/runstate.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/replay.h"
 #include "qapi/error.h"
 #include "qapi/qapi-events-block.h"
 #include "qemu/id.h"
@@ -1306,7 +1308,8 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
     acb->blk = blk;
     acb->ret = ret;
 
-    aio_bh_schedule_oneshot(blk_get_aio_context(blk), error_callback_bh, acb);
+    replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+                                     error_callback_bh, acb);
     return &acb->common;
 }
 
@@ -1362,8 +1365,8 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        aio_bh_schedule_oneshot(blk_get_aio_context(blk),
-                                blk_aio_complete_bh, acb);
+        replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+                                         blk_aio_complete_bh, acb);
     }
 
     return &acb->common;

block/io.c

@@ -33,6 +33,7 @@
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
+#include "sysemu/replay.h"
 
 #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
 
@@ -368,8 +369,8 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
     if (bs) {
         bdrv_inc_in_flight(bs);
     }
-    aio_bh_schedule_oneshot(bdrv_get_aio_context(bs),
-                            bdrv_co_drain_bh_cb, &data);
+    replay_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
+                                     bdrv_co_drain_bh_cb, &data);
 
     qemu_coroutine_yield();
     /* If we are resumed from some other event (such as an aio completion or a
@@ -600,6 +601,15 @@ void bdrv_drain_all_begin(void)
         return;
     }
 
+    /*
+     * bdrv queue is managed by record/replay,
+     * waiting for finishing the I/O requests may
+     * be infinite
+     */
+    if (replay_events_enabled()) {
+        return;
+    }
+
     /* AIO_WAIT_WHILE() with a NULL context can only be called from the main
      * loop AioContext, so make sure we're in the main context. */
     assert(qemu_get_current_aio_context() == qemu_get_aio_context());
@@ -629,6 +639,15 @@ void bdrv_drain_all_end(void)
     BlockDriverState *bs = NULL;
     int drained_end_counter = 0;
 
+    /*
+     * bdrv queue is managed by record/replay,
+     * waiting for finishing the I/O requests may
+     * be endless
+     */
+    if (replay_events_enabled()) {
+        return;
+    }
+
     while ((bs = bdrv_next_all_states(bs))) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
@@ -2071,6 +2090,13 @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
         return ret;
     }
 
+    /* If the request is misaligned then we can't make it efficient */
+    if ((flags & BDRV_REQ_NO_FALLBACK) &&
+        !QEMU_IS_ALIGNED(offset | bytes, align))
+    {
+        return -ENOTSUP;
+    }
+
     bdrv_inc_in_flight(bs);
     /*
      * Align write if necessary by performing a read-modify-write cycle.
@@ -2124,6 +2150,15 @@ int bdrv_flush_all(void)
     BlockDriverState *bs = NULL;
     int result = 0;
 
+    /*
+     * bdrv queue is managed by record/replay,
+     * creating new flush request for stopping
+     * the VM may break the determinism
+     */
+    if (replay_events_enabled()) {
+        return result;
+    }
+
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
         int ret;

block/iscsi.c

@@ -40,6 +40,7 @@
 #include "qemu/module.h"
 #include "qemu/option.h"
 #include "qemu/uuid.h"
+#include "sysemu/replay.h"
 #include "qapi/error.h"
 #include "qapi/qapi-commands-misc.h"
 #include "qapi/qmp/qdict.h"
@@ -280,8 +281,8 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
     }
 
     if (iTask->co) {
-        aio_bh_schedule_oneshot(iTask->iscsilun->aio_context,
-                                 iscsi_co_generic_bh_cb, iTask);
+        replay_bh_schedule_oneshot_event(iTask->iscsilun->aio_context,
+                                         iscsi_co_generic_bh_cb, iTask);
     } else {
         iTask->complete = 1;
     }

block/nfs.c

@@ -37,6 +37,8 @@
 #include "qemu/option.h"
 #include "qemu/uri.h"
 #include "qemu/cutils.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/replay.h"
 #include "qapi/qapi-visit-block-core.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qstring.h"
@@ -257,8 +259,8 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
     if (task->ret < 0) {
         error_report("NFS Error: %s", nfs_get_error(nfs));
     }
-    aio_bh_schedule_oneshot(task->client->aio_context,
-                            nfs_co_generic_bh_cb, task);
+    replay_bh_schedule_oneshot_event(task->client->aio_context,
+                                     nfs_co_generic_bh_cb, task);
 }
 
 static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,

block/null.c

@@ -17,6 +17,7 @@
 #include "qemu/module.h"
 #include "qemu/option.h"
 #include "block/block_int.h"
+#include "sysemu/replay.h"
 
 #define NULL_OPT_LATENCY "latency-ns"
 #define NULL_OPT_ZEROES  "read-zeroes"
@@ -179,7 +180,8 @@ static inline BlockAIOCB *null_aio_common(BlockDriverState *bs,
         timer_mod_ns(&acb->timer,
                      qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + s->latency_ns);
     } else {
-        aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), null_bh_cb, acb);
+        replay_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
+                                         null_bh_cb, acb);
     }
     return &acb->common;
 }

block/nvme.c

@@ -23,6 +23,7 @@
 #include "qemu/option.h"
 #include "qemu/vfio-helpers.h"
 #include "block/block_int.h"
+#include "sysemu/replay.h"
 #include "trace.h"
 
 #include "block/nvme.h"
@@ -351,7 +352,8 @@ static bool nvme_process_completion(BDRVNVMeState *s, NVMeQueuePair *q)
         smp_mb_release();
         *q->cq.doorbell = cpu_to_le32(q->cq.head);
         if (!qemu_co_queue_empty(&q->free_req_queue)) {
-            aio_bh_schedule_oneshot(s->aio_context, nvme_free_req_queue_cb, q);
+            replay_bh_schedule_oneshot_event(s->aio_context,
+                                             nvme_free_req_queue_cb, q);
         }
     }
     q->busy = false;
@@ -935,7 +937,7 @@ static void nvme_rw_cb(void *opaque, int ret)
         /* The rw coroutine hasn't yielded, don't try to enter. */
         return;
     }
-    aio_bh_schedule_oneshot(data->ctx, nvme_rw_cb_bh, data);
+    replay_bh_schedule_oneshot_event(data->ctx, nvme_rw_cb_bh, data);
 }
 
 static coroutine_fn int nvme_co_prw_aligned(BlockDriverState *bs,

block/qcow2-cluster.c

@@ -1330,6 +1330,9 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
     nb_clusters = MIN(nb_clusters, s->l2_slice_size - l2_index);
     assert(nb_clusters <= INT_MAX);
 
+    /* Limit total allocation byte count to INT_MAX */
+    nb_clusters = MIN(nb_clusters, INT_MAX >> s->cluster_bits);
+
     /* Find L2 entry for the first involved cluster */
     ret = get_cluster_table(bs, guest_offset, &l2_slice, &l2_index);
     if (ret < 0) {
@@ -1412,7 +1415,7 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
      * request actually writes to (excluding COW at the end)
      */
     uint64_t requested_bytes = *bytes + offset_into_cluster(s, guest_offset);
-    int avail_bytes = MIN(INT_MAX, nb_clusters << s->cluster_bits);
+    int avail_bytes = nb_clusters << s->cluster_bits;
     int nb_bytes = MIN(requested_bytes, avail_bytes);
     QCowL2Meta *old_m = *m;
 

block/rbd.c

@@ -22,6 +22,7 @@
 #include "block/qdict.h"
 #include "crypto/secret.h"
 #include "qemu/cutils.h"
+#include "sysemu/replay.h"
 #include "qapi/qmp/qstring.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qjson.h"
@@ -884,8 +885,8 @@ static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
     rcb->ret = rbd_aio_get_return_value(c);
     rbd_aio_release(c);
 
-    aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
-                            rbd_finish_bh, rcb);
+    replay_bh_schedule_oneshot_event(bdrv_get_aio_context(acb->common.bs),
+                                     rbd_finish_bh, rcb);
 }
 
 static int rbd_aio_discard_wrapper(rbd_image_t image,