replay: introduce block devices record/replay

This patch introduces block driver that implement recording
and replaying of block devices' operations.
All block completion operations are added to the queue.
Queue is flushed at checkpoints and information about processed requests
is recorded to the log. In replay phase the queue is matched with
events read from the log. Therefore block devices requests are processed
deterministically.

Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
[ kwolf: Rebased onto modified and already applied part of the series ]
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

block/Makefile.objs

@@ -4,7 +4,7 @@ block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
 block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
 block-obj-y += quorum.o
-block-obj-y += parallels.o blkdebug.o blkverify.o
+block-obj-y += parallels.o blkdebug.o blkverify.o blkreplay.o
 block-obj-y += block-backend.o snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
 block-obj-$(CONFIG_POSIX) += raw-posix.o

block/blkreplay.c

@@ -0,0 +1,160 @@
+/*
+ * Block protocol for record/replay
+ *
+ * Copyright (c) 2010-2016 Institute for System Programming
+ *                         of the Russian Academy of Sciences.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "sysemu/replay.h"
+#include "qapi/error.h"
+
+typedef struct Request {
+    Coroutine *co;
+    QEMUBH *bh;
+} Request;
+
+/* Next request id.
+   This counter is global, because requests from different
+   block devices should not get overlapping ids. */
+static uint64_t request_id;
+
+static int blkreplay_open(BlockDriverState *bs, QDict *options, int flags,
+                          Error **errp)
+{
+    Error *local_err = NULL;
+    int ret;
+
+    /* Open the image file */
+    bs->file = bdrv_open_child(NULL, options, "image",
+                               bs, &child_file, false, &local_err);
+    if (local_err) {
+        ret = -EINVAL;
+        error_propagate(errp, local_err);
+        goto fail;
+    }
+
+    ret = 0;
+fail:
+    if (ret < 0) {
+        bdrv_unref_child(bs, bs->file);
+    }
+    return ret;
+}
+
+static void blkreplay_close(BlockDriverState *bs)
+{
+}
+
+static int64_t blkreplay_getlength(BlockDriverState *bs)
+{
+    return bdrv_getlength(bs->file->bs);
+}
+
+/* This bh is used for synchronization of return from coroutines.
+   It continues yielded coroutine which then finishes its execution.
+   BH is called adjusted to some replay checkpoint, therefore
+   record and replay will always finish coroutines deterministically.
+*/
+static void blkreplay_bh_cb(void *opaque)
+{
+    Request *req = opaque;
+    qemu_coroutine_enter(req->co, NULL);
+    qemu_bh_delete(req->bh);
+    g_free(req);
+}
+
+static void block_request_create(uint64_t reqid, BlockDriverState *bs,
+                                 Coroutine *co)
+{
+    Request *req = g_new(Request, 1);
+    *req = (Request) {
+        .co = co,
+        .bh = aio_bh_new(bdrv_get_aio_context(bs), blkreplay_bh_cb, req),
+    };
+    replay_block_event(req->bh, reqid);
+}
+
+static int coroutine_fn blkreplay_co_readv(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_readv(bs->file->bs, sector_num, nb_sectors, qiov);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_writev(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_writev(bs->file->bs, sector_num, nb_sectors, qiov);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_write_zeroes(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_write_zeroes(bs->file->bs, sector_num, nb_sectors, flags);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_discard(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_discard(bs->file->bs, sector_num, nb_sectors);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_flush(BlockDriverState *bs)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_flush(bs->file->bs);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static BlockDriver bdrv_blkreplay = {
+    .format_name            = "blkreplay",
+    .protocol_name          = "blkreplay",
+    .instance_size          = 0,
+
+    .bdrv_file_open         = blkreplay_open,
+    .bdrv_close             = blkreplay_close,
+    .bdrv_getlength         = blkreplay_getlength,
+
+    .bdrv_co_readv          = blkreplay_co_readv,
+    .bdrv_co_writev         = blkreplay_co_writev,
+
+    .bdrv_co_write_zeroes   = blkreplay_co_write_zeroes,
+    .bdrv_co_discard        = blkreplay_co_discard,
+    .bdrv_co_flush          = blkreplay_co_flush,
+};
+
+static void bdrv_blkreplay_init(void)
+{
+    bdrv_register(&bdrv_blkreplay);
+}
+
+block_init(bdrv_blkreplay_init);

docs/replay.txt

@@ -175,3 +175,23 @@ Sometimes the block layer uses asynchronous callbacks for its internal purposes
 (like reading or writing VM snapshots or disk image cluster tables). In this
 case bottom halves are not marked as "replayable" and do not saved
 into the log.
+
+Block devices
+-------------
+
+Block devices record/replay module intercepts calls of
+bdrv coroutine functions at the top of block drivers stack.
+To record and replay block operations the drive must be configured
+as following:
+ -drive file=disk.qcow,if=none,id=img-direct
+ -drive driver=blkreplay,if=none,image=img-direct,id=img-blkreplay
+ -device ide-hd,drive=img-blkreplay
+
+blkreplay driver should be inserted between disk image and virtual driver
+controller. Therefore all disk requests may be recorded and replayed.
+
+All block completion operations are added to the queue in the coroutines.
+Queue is flushed at checkpoints and information about processed requests
+is recorded to the log. In replay phase the queue is matched with
+events read from the log. Therefore block devices requests are processed
+deterministically.

include/sysemu/replay.h

@@ -113,6 +113,8 @@ void replay_bh_schedule_event(QEMUBH *bh);
 void replay_input_event(QemuConsole *src, InputEvent *evt);
 /*! Adds input sync event to the queue */
 void replay_input_sync_event(void);
+/*! Adds block layer event to the queue */
+void replay_block_event(QEMUBH *bh, uint64_t id);
 
 /* Character device */
 

replay/replay-events.c

@@ -51,6 +51,9 @@ static void replay_run_event(Event *event)
     case REPLAY_ASYNC_EVENT_CHAR_READ:
         replay_event_char_read_run(event->opaque);
         break;
+    case REPLAY_ASYNC_EVENT_BLOCK:
+        aio_bh_call(event->opaque);
+        break;
     default:
         error_report("Replay: invalid async event ID (%d) in the queue",
                     event->event_kind);
@@ -153,6 +156,15 @@ void replay_add_input_sync_event(void)
     replay_add_event(REPLAY_ASYNC_EVENT_INPUT_SYNC, NULL, NULL, 0);
 }
 
+void replay_block_event(QEMUBH *bh, uint64_t id)
+{
+    if (replay_mode != REPLAY_MODE_NONE && events_enabled) {
+        replay_add_event(REPLAY_ASYNC_EVENT_BLOCK, bh, NULL, id);
+    } else {
+        qemu_bh_schedule(bh);
+    }
+}
+
 static void replay_save_event(Event *event, int checkpoint)
 {
     if (replay_mode != REPLAY_MODE_PLAY) {
@@ -174,6 +186,9 @@ static void replay_save_event(Event *event, int checkpoint)
         case REPLAY_ASYNC_EVENT_CHAR_READ:
             replay_event_char_read_save(event->opaque);
             break;
+        case REPLAY_ASYNC_EVENT_BLOCK:
+            replay_put_qword(event->id);
+            break;
         default:
             error_report("Unknown ID %" PRId64 " of replay event", event->id);
             exit(1);
@@ -232,6 +247,11 @@ static Event *replay_read_event(int checkpoint)
         event->event_kind = read_event_kind;
         event->opaque = replay_event_char_read_load();
         return event;
+    case REPLAY_ASYNC_EVENT_BLOCK:
+        if (read_id == -1) {
+            read_id = replay_get_qword();
+        }
+        break;
     default:
         error_report("Unknown ID %d of replay event", read_event_kind);
         exit(1);

replay/replay-internal.h

@@ -49,6 +49,7 @@ enum ReplayAsyncEventKind {
     REPLAY_ASYNC_EVENT_INPUT,
     REPLAY_ASYNC_EVENT_INPUT_SYNC,
     REPLAY_ASYNC_EVENT_CHAR_READ,
+    REPLAY_ASYNC_EVENT_BLOCK,
     REPLAY_ASYNC_COUNT
 };
 

replay/replay.c

@@ -21,7 +21,7 @@
 
 /* Current version of the replay mechanism.
    Increase it when file format changes. */
-#define REPLAY_VERSION              0xe02003
+#define REPLAY_VERSION              0xe02004
 /* Size of replay log header */
 #define HEADER_SIZE                 (sizeof(uint32_t) + sizeof(uint64_t))
 

stubs/replay.c

@@ -63,3 +63,7 @@ void replay_char_read_all_save_buf(uint8_t *buf, int offset)
 {
     abort();
 }
+
+void replay_block_event(QEMUBH *bh, uint64_t id)
+{
+}