Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

Pull request

v2:
 * Fix C11 typedef redefinitions in ahci and libqos malloc [Peter]
 * Fix lx -> PRIx64 format specifiers in ahci [Peter]

# gpg: Signature made Mon Feb 16 15:45:53 2015 GMT using RSA key ID 81AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"

* remotes/stefanha/tags/block-pull-request: (65 commits)
  block: Keep bdrv_check*_request()'s return value
  block: Remove "growable" from BDS
  block: Clamp BlockBackend requests
  qemu-io: Use BlockBackend
  qemu-io: Remove "growable" option
  qemu-io: Use blk_new_open() in openfile()
  qemu-nbd: Use blk_new_open() in main()
  qemu-img: Use BlockBackend as far as possible
  qemu-img: Use blk_new_open() in img_rebase()
  qemu-img: Use blk_new_open() in img_open()
  block/xen: Use blk_new_open() in blk_connect()
  blockdev: Use blk_new_open() in blockdev_init()
  iotests: Add test for driver=qcow2, format=qcow2
  block: Add Error parameter to bdrv_find_protocol()
  block: Add blk_new_open()
  block: Lift some BDS functions to the BlockBackend
  iotests: Add test for qemu-img convert to NBD
  qemu-img: Fix qemu-img convert -n
  qemu-iotests: Add 093 for IO throttling
  qemu-iotests: Allow caller to disable underscore convertion for qmp
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

block.c

@@ -508,9 +508,8 @@ int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp)
     Error *local_err = NULL;
     int ret;
 
-    drv = bdrv_find_protocol(filename, true);
+    drv = bdrv_find_protocol(filename, true, errp);
     if (drv == NULL) {
-        error_setg(errp, "Could not find protocol for file '%s'", filename);
         return -ENOENT;
     }
 
@@ -628,7 +627,8 @@ static BlockDriver *find_hdev_driver(const char *filename)
 }
 
 BlockDriver *bdrv_find_protocol(const char *filename,
-                                bool allow_protocol_prefix)
+                                bool allow_protocol_prefix,
+                                Error **errp)
 {
     BlockDriver *drv1;
     char protocol[128];
@@ -666,6 +666,8 @@ BlockDriver *bdrv_find_protocol(const char *filename,
             return drv1;
         }
     }
+
+    error_setg(errp, "Unknown protocol '%s'", protocol);
     return NULL;
 }
 
@@ -970,7 +972,6 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
     bs->zero_beyond_eof = true;
     open_flags = bdrv_open_flags(bs, flags);
     bs->read_only = !(open_flags & BDRV_O_RDWR);
-    bs->growable = !!(flags & BDRV_O_PROTOCOL);
 
     if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
         error_setg(errp,
@@ -1136,9 +1137,8 @@ static int bdrv_fill_options(QDict **options, const char **pfilename, int flags,
     } else {
         if (!drvname && protocol) {
             if (filename) {
-                drv = bdrv_find_protocol(filename, parse_filename);
+                drv = bdrv_find_protocol(filename, parse_filename, errp);
                 if (!drv) {
-                    error_setg(errp, "Unknown protocol");
                     return -EINVAL;
                 }
 
@@ -1885,7 +1885,6 @@ void bdrv_close(BlockDriverState *bs)
         bs->encrypted = 0;
         bs->valid_key = 0;
         bs->sg = 0;
-        bs->growable = 0;
         bs->zero_beyond_eof = false;
         QDECREF(bs->options);
         bs->options = NULL;
@@ -2645,25 +2644,17 @@ exit:
 static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
                                    size_t size)
 {
-    int64_t len;
-
     if (size > BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS) {
         return -EIO;
     }
 
-    if (!bdrv_is_inserted(bs))
+    if (!bdrv_is_inserted(bs)) {
         return -ENOMEDIUM;
+    }
 
-    if (bs->growable)
-        return 0;
-
-    len = bdrv_getlength(bs);
-
-    if (offset < 0)
-        return -EIO;
-
-    if ((offset > len) || (len - offset < size))
+    if (offset < 0) {
         return -EIO;
+    }
 
     return 0;
 }
@@ -3042,10 +3033,10 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
     }
 
     /* Forward the request to the BlockDriver */
-    if (!(bs->zero_beyond_eof && bs->growable)) {
+    if (!bs->zero_beyond_eof) {
         ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
     } else {
-        /* Read zeros after EOF of growable BDSes */
+        /* Read zeros after EOF */
         int64_t total_sectors, max_nb_sectors;
 
         total_sectors = bdrv_nb_sectors(bs);
@@ -3107,8 +3098,10 @@ static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
     if (!drv) {
         return -ENOMEDIUM;
     }
-    if (bdrv_check_byte_request(bs, offset, bytes)) {
-        return -EIO;
+
+    ret = bdrv_check_byte_request(bs, offset, bytes);
+    if (ret < 0) {
+        return ret;
     }
 
     if (bs->copy_on_read) {
@@ -3322,7 +3315,7 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
 
     block_acct_highest_sector(&bs->stats, sector_num, nb_sectors);
 
-    if (bs->growable && ret >= 0) {
+    if (ret >= 0) {
         bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
     }
 
@@ -3351,8 +3344,10 @@ static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
     if (bs->read_only) {
         return -EACCES;
     }
-    if (bdrv_check_byte_request(bs, offset, bytes)) {
-        return -EIO;
+
+    ret = bdrv_check_byte_request(bs, offset, bytes);
+    if (ret < 0) {
+        return ret;
     }
 
     /* throttling disk I/O */
@@ -4206,12 +4201,18 @@ int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
                           const uint8_t *buf, int nb_sectors)
 {
     BlockDriver *drv = bs->drv;
-    if (!drv)
+    int ret;
+
+    if (!drv) {
         return -ENOMEDIUM;
-    if (!drv->bdrv_write_compressed)
+    }
+    if (!drv->bdrv_write_compressed) {
         return -ENOTSUP;
-    if (bdrv_check_request(bs, sector_num, nb_sectors))
-        return -EIO;
+    }
+    ret = bdrv_check_request(bs, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
 
     assert(QLIST_EMPTY(&bs->dirty_bitmaps));
 
@@ -5126,12 +5127,15 @@ static void coroutine_fn bdrv_discard_co_entry(void *opaque)
 int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
                                  int nb_sectors)
 {
-    int max_discard;
+    int max_discard, ret;
 
     if (!bs->drv) {
         return -ENOMEDIUM;
-    } else if (bdrv_check_request(bs, sector_num, nb_sectors)) {
-        return -EIO;
+    }
+
+    ret = bdrv_check_request(bs, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
     } else if (bs->read_only) {
         return -EROFS;
     }
@@ -5623,9 +5627,8 @@ void bdrv_img_create(const char *filename, const char *fmt,
         return;
     }
 
-    proto_drv = bdrv_find_protocol(filename, true);
+    proto_drv = bdrv_find_protocol(filename, true, errp);
     if (!proto_drv) {
-        error_setg(errp, "Unknown protocol '%s'", filename);
         return;
     }
 

block/block-backend.c

@@ -31,6 +31,16 @@ struct BlockBackend {
     void *dev_opaque;
 };
 
+typedef struct BlockBackendAIOCB {
+    BlockAIOCB common;
+    QEMUBH *bh;
+    int ret;
+} BlockBackendAIOCB;
+
+static const AIOCBInfo block_backend_aiocb_info = {
+    .aiocb_size = sizeof(BlockBackendAIOCB),
+};
+
 static void drive_info_del(DriveInfo *dinfo);
 
 /* All the BlockBackends (except for hidden ones) */
@@ -91,6 +101,40 @@ BlockBackend *blk_new_with_bs(const char *name, Error **errp)
     return blk;
 }
 
+/*
+ * Calls blk_new_with_bs() and then calls bdrv_open() on the BlockDriverState.
+ *
+ * Just as with bdrv_open(), after having called this function the reference to
+ * @options belongs to the block layer (even on failure).
+ *
+ * TODO: Remove @filename and @flags; it should be possible to specify a whole
+ * BDS tree just by specifying the @options QDict (or @reference,
+ * alternatively). At the time of adding this function, this is not possible,
+ * though, so callers of this function have to be able to specify @filename and
+ * @flags.
+ */
+BlockBackend *blk_new_open(const char *name, const char *filename,
+                           const char *reference, QDict *options, int flags,
+                           Error **errp)
+{
+    BlockBackend *blk;
+    int ret;
+
+    blk = blk_new_with_bs(name, errp);
+    if (!blk) {
+        QDECREF(options);
+        return NULL;
+    }
+
+    ret = bdrv_open(&blk->bs, filename, reference, options, flags, NULL, errp);
+    if (ret < 0) {
+        blk_unref(blk);
+        return NULL;
+    }
+
+    return blk;
+}
+
 static void blk_delete(BlockBackend *blk)
 {
     assert(!blk->refcnt);
@@ -394,39 +438,137 @@ void blk_iostatus_enable(BlockBackend *blk)
     bdrv_iostatus_enable(blk->bs);
 }
 
+static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
+                                  size_t size)
+{
+    int64_t len;
+
+    if (size > INT_MAX) {
+        return -EIO;
+    }
+
+    if (!blk_is_inserted(blk)) {
+        return -ENOMEDIUM;
+    }
+
+    len = blk_getlength(blk);
+    if (len < 0) {
+        return len;
+    }
+
+    if (offset < 0) {
+        return -EIO;
+    }
+
+    if (offset > len || len - offset < size) {
+        return -EIO;
+    }
+
+    return 0;
+}
+
+static int blk_check_request(BlockBackend *blk, int64_t sector_num,
+                             int nb_sectors)
+{
+    if (sector_num < 0 || sector_num > INT64_MAX / BDRV_SECTOR_SIZE) {
+        return -EIO;
+    }
+
+    if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+        return -EIO;
+    }
+
+    return blk_check_byte_request(blk, sector_num * BDRV_SECTOR_SIZE,
+                                  nb_sectors * BDRV_SECTOR_SIZE);
+}
+
 int blk_read(BlockBackend *blk, int64_t sector_num, uint8_t *buf,
              int nb_sectors)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
+
     return bdrv_read(blk->bs, sector_num, buf, nb_sectors);
 }
 
 int blk_read_unthrottled(BlockBackend *blk, int64_t sector_num, uint8_t *buf,
                          int nb_sectors)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
+
     return bdrv_read_unthrottled(blk->bs, sector_num, buf, nb_sectors);
 }
 
 int blk_write(BlockBackend *blk, int64_t sector_num, const uint8_t *buf,
               int nb_sectors)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
+
     return bdrv_write(blk->bs, sector_num, buf, nb_sectors);
 }
 
+static void error_callback_bh(void *opaque)
+{
+    struct BlockBackendAIOCB *acb = opaque;
+    qemu_bh_delete(acb->bh);
+    acb->common.cb(acb->common.opaque, acb->ret);
+    qemu_aio_unref(acb);
+}
+
+static BlockAIOCB *abort_aio_request(BlockBackend *blk, BlockCompletionFunc *cb,
+                                     void *opaque, int ret)
+{
+    struct BlockBackendAIOCB *acb;
+    QEMUBH *bh;
+
+    acb = blk_aio_get(&block_backend_aiocb_info, blk, cb, opaque);
+    acb->ret = ret;
+
+    bh = aio_bh_new(blk_get_aio_context(blk), error_callback_bh, acb);
+    acb->bh = bh;
+    qemu_bh_schedule(bh);
+
+    return &acb->common;
+}
+
 BlockAIOCB *blk_aio_write_zeroes(BlockBackend *blk, int64_t sector_num,
                                  int nb_sectors, BdrvRequestFlags flags,
                                  BlockCompletionFunc *cb, void *opaque)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return abort_aio_request(blk, cb, opaque, ret);
+    }
+
     return bdrv_aio_write_zeroes(blk->bs, sector_num, nb_sectors, flags,
                                  cb, opaque);
 }
 
 int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count)
 {
+    int ret = blk_check_byte_request(blk, offset, count);
+    if (ret < 0) {
+        return ret;
+    }
+
     return bdrv_pread(blk->bs, offset, buf, count);
 }
 
 int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count)
 {
+    int ret = blk_check_byte_request(blk, offset, count);
+    if (ret < 0) {
+        return ret;
+    }
+
     return bdrv_pwrite(blk->bs, offset, buf, count);
 }
 
@@ -440,10 +582,20 @@ void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr)
     bdrv_get_geometry(blk->bs, nb_sectors_ptr);
 }
 
+int64_t blk_nb_sectors(BlockBackend *blk)
+{
+    return bdrv_nb_sectors(blk->bs);
+}
+
 BlockAIOCB *blk_aio_readv(BlockBackend *blk, int64_t sector_num,
                           QEMUIOVector *iov, int nb_sectors,
                           BlockCompletionFunc *cb, void *opaque)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return abort_aio_request(blk, cb, opaque, ret);
+    }
+
     return bdrv_aio_readv(blk->bs, sector_num, iov, nb_sectors, cb, opaque);
 }
 
@@ -451,6 +603,11 @@ BlockAIOCB *blk_aio_writev(BlockBackend *blk, int64_t sector_num,
                            QEMUIOVector *iov, int nb_sectors,
                            BlockCompletionFunc *cb, void *opaque)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return abort_aio_request(blk, cb, opaque, ret);
+    }
+
     return bdrv_aio_writev(blk->bs, sector_num, iov, nb_sectors, cb, opaque);
 }
 
@@ -464,6 +621,11 @@ BlockAIOCB *blk_aio_discard(BlockBackend *blk,
                             int64_t sector_num, int nb_sectors,
                             BlockCompletionFunc *cb, void *opaque)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return abort_aio_request(blk, cb, opaque, ret);
+    }
+
     return bdrv_aio_discard(blk->bs, sector_num, nb_sectors, cb, opaque);
 }
 
@@ -479,6 +641,15 @@ void blk_aio_cancel_async(BlockAIOCB *acb)
 
 int blk_aio_multiwrite(BlockBackend *blk, BlockRequest *reqs, int num_reqs)
 {
+    int i, ret;
+
+    for (i = 0; i < num_reqs; i++) {
+        ret = blk_check_request(blk, reqs[i].sector, reqs[i].nb_sectors);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
     return bdrv_aio_multiwrite(blk->bs, reqs, num_reqs);
 }
 
@@ -495,6 +666,11 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
 
 int blk_co_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors)
 {
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
+
     return bdrv_co_discard(blk->bs, sector_num, nb_sectors);
 }
 
@@ -668,3 +844,51 @@ void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
 {
     return qemu_aio_get(aiocb_info, blk_bs(blk), cb, opaque);
 }
+
+int coroutine_fn blk_co_write_zeroes(BlockBackend *blk, int64_t sector_num,
+                                     int nb_sectors, BdrvRequestFlags flags)
+{
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return bdrv_co_write_zeroes(blk->bs, sector_num, nb_sectors, flags);
+}
+
+int blk_write_compressed(BlockBackend *blk, int64_t sector_num,
+                         const uint8_t *buf, int nb_sectors)
+{
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return bdrv_write_compressed(blk->bs, sector_num, buf, nb_sectors);
+}
+
+int blk_truncate(BlockBackend *blk, int64_t offset)
+{
+    return bdrv_truncate(blk->bs, offset);
+}
+
+int blk_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors)
+{
+    int ret = blk_check_request(blk, sector_num, nb_sectors);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return bdrv_discard(blk->bs, sector_num, nb_sectors);
+}
+
+int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
+                     int64_t pos, int size)
+{
+    return bdrv_save_vmstate(blk->bs, buf, pos, size);
+}
+
+int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size)
+{
+    return bdrv_load_vmstate(blk->bs, buf, pos, size);
+}

block/nbd-client.c

@@ -43,20 +43,23 @@ static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
     }
 }
 
-static void nbd_teardown_connection(NbdClientSession *client)
+static void nbd_teardown_connection(BlockDriverState *bs)
 {
+    NbdClientSession *client = nbd_get_client_session(bs);
+
     /* finish any pending coroutines */
     shutdown(client->sock, 2);
     nbd_recv_coroutines_enter_all(client);
 
-    nbd_client_session_detach_aio_context(client);
+    nbd_client_detach_aio_context(bs);
     closesocket(client->sock);
     client->sock = -1;
 }
 
 static void nbd_reply_ready(void *opaque)
 {
-    NbdClientSession *s = opaque;
+    BlockDriverState *bs = opaque;
+    NbdClientSession *s = nbd_get_client_session(bs);
     uint64_t i;
     int ret;
 
@@ -89,28 +92,40 @@ static void nbd_reply_ready(void *opaque)
     }
 
 fail:
-    nbd_teardown_connection(s);
+    nbd_teardown_connection(bs);
 }
 
 static void nbd_restart_write(void *opaque)
 {
-    NbdClientSession *s = opaque;
+    BlockDriverState *bs = opaque;
 
-    qemu_coroutine_enter(s->send_coroutine, NULL);
+    qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine, NULL);
 }
 
-static int nbd_co_send_request(NbdClientSession *s,
+static int nbd_co_send_request(BlockDriverState *bs,
                                struct nbd_request *request,
                                QEMUIOVector *qiov, int offset)
 {
+    NbdClientSession *s = nbd_get_client_session(bs);
     AioContext *aio_context;
-    int rc, ret;
+    int rc, ret, i;
 
     qemu_co_mutex_lock(&s->send_mutex);
+
+    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
+        if (s->recv_coroutine[i] == NULL) {
+            s->recv_coroutine[i] = qemu_coroutine_self();
+            break;
+        }
+    }
+
+    assert(i < MAX_NBD_REQUESTS);
+    request->handle = INDEX_TO_HANDLE(s, i);
     s->send_coroutine = qemu_coroutine_self();
-    aio_context = bdrv_get_aio_context(s->bs);
+    aio_context = bdrv_get_aio_context(bs);
+
     aio_set_fd_handler(aio_context, s->sock,
-                       nbd_reply_ready, nbd_restart_write, s);
+                       nbd_reply_ready, nbd_restart_write, bs);
     if (qiov) {
         if (!s->is_unix) {
             socket_set_cork(s->sock, 1);
@@ -129,7 +144,7 @@ static int nbd_co_send_request(NbdClientSession *s,
     } else {
         rc = nbd_send_request(s->sock, request);
     }
-    aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, s);
+    aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, bs);
     s->send_coroutine = NULL;
     qemu_co_mutex_unlock(&s->send_mutex);
     return rc;
@@ -164,8 +179,6 @@ static void nbd_co_receive_reply(NbdClientSession *s,
 static void nbd_coroutine_start(NbdClientSession *s,
    struct nbd_request *request)
 {
-    int i;
-
     /* Poor man semaphore.  The free_sema is locked when no other request
      * can be accepted, and unlocked after receiving one reply.  */
     if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
@@ -174,15 +187,7 @@ static void nbd_coroutine_start(NbdClientSession *s,
     }
     s->in_flight++;
 
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i] == NULL) {
-            s->recv_coroutine[i] = qemu_coroutine_self();
-            break;
-        }
-    }
-
-    assert(i < MAX_NBD_REQUESTS);
-    request->handle = INDEX_TO_HANDLE(s, i);
+    /* s->recv_coroutine[i] is set as soon as we get the send_lock.  */
 }
 
 static void nbd_coroutine_end(NbdClientSession *s,
@@ -195,10 +200,11 @@ static void nbd_coroutine_end(NbdClientSession *s,
     }
 }
 
-static int nbd_co_readv_1(NbdClientSession *client, int64_t sector_num,
+static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors, QEMUIOVector *qiov,
                           int offset)
 {
+    NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = { .type = NBD_CMD_READ };
     struct nbd_reply reply;
     ssize_t ret;
@@ -207,7 +213,7 @@ static int nbd_co_readv_1(NbdClientSession *client, int64_t sector_num,
     request.len = nb_sectors * 512;
 
     nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
+    ret = nbd_co_send_request(bs, &request, NULL, 0);
     if (ret < 0) {
         reply.error = -ret;
     } else {
@@ -218,15 +224,16 @@ static int nbd_co_readv_1(NbdClientSession *client, int64_t sector_num,
 
 }
 
-static int nbd_co_writev_1(NbdClientSession *client, int64_t sector_num,
+static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
                            int nb_sectors, QEMUIOVector *qiov,
                            int offset)
 {
+    NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = { .type = NBD_CMD_WRITE };
     struct nbd_reply reply;
     ssize_t ret;
 
-    if (!bdrv_enable_write_cache(client->bs) &&
+    if (!bdrv_enable_write_cache(bs) &&
         (client->nbdflags & NBD_FLAG_SEND_FUA)) {
         request.type |= NBD_CMD_FLAG_FUA;
     }
@@ -235,7 +242,7 @@ static int nbd_co_writev_1(NbdClientSession *client, int64_t sector_num,
     request.len = nb_sectors * 512;
 
     nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, qiov, offset);
+    ret = nbd_co_send_request(bs, &request, qiov, offset);
     if (ret < 0) {
         reply.error = -ret;
     } else {
@@ -249,14 +256,13 @@ static int nbd_co_writev_1(NbdClientSession *client, int64_t sector_num,
  * remain aligned to 4K. */
 #define NBD_MAX_SECTORS 2040
 
-int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
+int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
     int offset = 0;
     int ret;
     while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_readv_1(client, sector_num,
-                             NBD_MAX_SECTORS, qiov, offset);
+        ret = nbd_co_readv_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
         if (ret < 0) {
             return ret;
         }
@@ -264,17 +270,16 @@ int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
         sector_num += NBD_MAX_SECTORS;
         nb_sectors -= NBD_MAX_SECTORS;
     }
-    return nbd_co_readv_1(client, sector_num, nb_sectors, qiov, offset);
+    return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
 }
 
-int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
+int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov)
 {
     int offset = 0;
     int ret;
     while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_writev_1(client, sector_num,
-                              NBD_MAX_SECTORS, qiov, offset);
+        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
         if (ret < 0) {
             return ret;
         }
@@ -282,11 +287,12 @@ int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
         sector_num += NBD_MAX_SECTORS;
         nb_sectors -= NBD_MAX_SECTORS;
     }
-    return nbd_co_writev_1(client, sector_num, nb_sectors, qiov, offset);
+    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset);
 }
 
-int nbd_client_session_co_flush(NbdClientSession *client)
+int nbd_client_co_flush(BlockDriverState *bs)
 {
+    NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = { .type = NBD_CMD_FLUSH };
     struct nbd_reply reply;
     ssize_t ret;
@@ -303,7 +309,7 @@ int nbd_client_session_co_flush(NbdClientSession *client)
     request.len = 0;
 
     nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
+    ret = nbd_co_send_request(bs, &request, NULL, 0);
     if (ret < 0) {
         reply.error = -ret;
     } else {
@@ -313,9 +319,10 @@ int nbd_client_session_co_flush(NbdClientSession *client)
     return -reply.error;
 }
 
-int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
+int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors)
 {
+    NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = { .type = NBD_CMD_TRIM };
     struct nbd_reply reply;
     ssize_t ret;
@@ -327,7 +334,7 @@ int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
     request.len = nb_sectors * 512;
 
     nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
+    ret = nbd_co_send_request(bs, &request, NULL, 0);
     if (ret < 0) {
         reply.error = -ret;
     } else {
@@ -338,43 +345,41 @@ int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
 
 }
 
-void nbd_client_session_detach_aio_context(NbdClientSession *client)
+void nbd_client_detach_aio_context(BlockDriverState *bs)
 {
-    aio_set_fd_handler(bdrv_get_aio_context(client->bs), client->sock,
-                       NULL, NULL, NULL);
+    aio_set_fd_handler(bdrv_get_aio_context(bs),
+                       nbd_get_client_session(bs)->sock, NULL, NULL, NULL);
 }
 
-void nbd_client_session_attach_aio_context(NbdClientSession *client,
+void nbd_client_attach_aio_context(BlockDriverState *bs,
                                    AioContext *new_context)
 {
-    aio_set_fd_handler(new_context, client->sock,
-                       nbd_reply_ready, NULL, client);
+    aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sock,
+                       nbd_reply_ready, NULL, bs);
 }
 
-void nbd_client_session_close(NbdClientSession *client)
+void nbd_client_close(BlockDriverState *bs)
 {
+    NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = {
         .type = NBD_CMD_DISC,
         .from = 0,
         .len = 0
     };
 
-    if (!client->bs) {
-        return;
-    }
     if (client->sock == -1) {
         return;
     }
 
     nbd_send_request(client->sock, &request);
 
-    nbd_teardown_connection(client);
-    client->bs = NULL;
+    nbd_teardown_connection(bs);
 }
 
-int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
-                            int sock, const char *export, Error **errp)
+int nbd_client_init(BlockDriverState *bs, int sock, const char *export,
+                    Error **errp)
 {
+    NbdClientSession *client = nbd_get_client_session(bs);
     int ret;
 
     /* NBD handshake */
@@ -391,13 +396,12 @@ int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
 
     qemu_co_mutex_init(&client->send_mutex);
     qemu_co_mutex_init(&client->free_sema);
-    client->bs = bs;
     client->sock = sock;
 
     /* Now that we're connected, set the socket to be non-blocking and
      * kick the reply mechanism.  */
     qemu_set_nonblock(sock);
-    nbd_client_session_attach_aio_context(client, bdrv_get_aio_context(bs));
+    nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
 
     logout("Established connection with NBD server\n");
     return 0;

block/nbd-client.h

@@ -31,24 +31,24 @@ typedef struct NbdClientSession {
     struct nbd_reply reply;
 
     bool is_unix;
-
-    BlockDriverState *bs;
 } NbdClientSession;
 
-int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
-                            int sock, const char *export_name, Error **errp);
-void nbd_client_session_close(NbdClientSession *client);
+NbdClientSession *nbd_get_client_session(BlockDriverState *bs);
+
+int nbd_client_init(BlockDriverState *bs, int sock, const char *export_name,
+                    Error **errp);
+void nbd_client_close(BlockDriverState *bs);
 
-int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
+int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors);
-int nbd_client_session_co_flush(NbdClientSession *client);
-int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
+int nbd_client_co_flush(BlockDriverState *bs);
+int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov);
-int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
+int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov);
 
-void nbd_client_session_detach_aio_context(NbdClientSession *client);
-void nbd_client_session_attach_aio_context(NbdClientSession *client,
+void nbd_client_detach_aio_context(BlockDriverState *bs);
+void nbd_client_attach_aio_context(BlockDriverState *bs,
                                    AioContext *new_context);
 
 #endif /* NBD_CLIENT_H */

block/nbd.c

@@ -224,6 +224,12 @@ static void nbd_config(BDRVNBDState *s, QDict *options, char **export,
     }
 }
 
+NbdClientSession *nbd_get_client_session(BlockDriverState *bs)
+{
+    BDRVNBDState *s = bs->opaque;
+    return &s->client;
+}
+
 static int nbd_establish_connection(BlockDriverState *bs, Error **errp)
 {
     BDRVNBDState *s = bs->opaque;
@@ -271,7 +277,7 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* NBD handshake */
-    result = nbd_client_session_init(&s->client, bs, sock, export, errp);
+    result = nbd_client_init(bs, sock, export, errp);
     g_free(export);
     return result;
 }
@@ -279,26 +285,18 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
 static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    return nbd_client_session_co_readv(&s->client, sector_num,
-                                       nb_sectors, qiov);
+    return nbd_client_co_readv(bs, sector_num, nb_sectors, qiov);
 }
 
 static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    return nbd_client_session_co_writev(&s->client, sector_num,
-                                        nb_sectors, qiov);
+    return nbd_client_co_writev(bs, sector_num, nb_sectors, qiov);
 }
 
 static int nbd_co_flush(BlockDriverState *bs)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    return nbd_client_session_co_flush(&s->client);
+    return nbd_client_co_flush(bs);
 }
 
 static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
@@ -310,10 +308,7 @@ static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
 static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    return nbd_client_session_co_discard(&s->client, sector_num,
-                                         nb_sectors);
+    return nbd_client_co_discard(bs, sector_num, nb_sectors);
 }
 
 static void nbd_close(BlockDriverState *bs)
@@ -321,7 +316,7 @@ static void nbd_close(BlockDriverState *bs)
     BDRVNBDState *s = bs->opaque;
 
     qemu_opts_del(s->socket_opts);
-    nbd_client_session_close(&s->client);
+    nbd_client_close(bs);
 }
 
 static int64_t nbd_getlength(BlockDriverState *bs)
@@ -333,17 +328,13 @@ static int64_t nbd_getlength(BlockDriverState *bs)
 
 static void nbd_detach_aio_context(BlockDriverState *bs)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    nbd_client_session_detach_aio_context(&s->client);
+    nbd_client_detach_aio_context(bs);
 }
 
 static void nbd_attach_aio_context(BlockDriverState *bs,
                                    AioContext *new_context)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    nbd_client_session_attach_aio_context(&s->client, new_context);
+    nbd_client_attach_aio_context(bs, new_context);
 }
 
 static void nbd_refresh_filename(BlockDriverState *bs)

block/qcow2.c

@@ -2521,15 +2521,12 @@ static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
 {
     BDRVQcowState *s = bs->opaque;
     int64_t total_sectors = bs->total_sectors;
-    int growable = bs->growable;
     bool zero_beyond_eof = bs->zero_beyond_eof;
     int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_SAVE);
-    bs->growable = 1;
     bs->zero_beyond_eof = false;
     ret = bdrv_pwritev(bs, qcow2_vm_state_offset(s) + pos, qiov);
-    bs->growable = growable;
     bs->zero_beyond_eof = zero_beyond_eof;
 
     /* bdrv_co_do_writev will have increased the total_sectors value to include
@@ -2544,15 +2541,12 @@ static int qcow2_load_vmstate(BlockDriverState *bs, uint8_t *buf,
                               int64_t pos, int size)
 {
     BDRVQcowState *s = bs->opaque;
-    int growable = bs->growable;
     bool zero_beyond_eof = bs->zero_beyond_eof;
     int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_LOAD);
-    bs->growable = 1;
     bs->zero_beyond_eof = false;
     ret = bdrv_pread(bs, qcow2_vm_state_offset(s) + pos, buf, size);
-    bs->growable = growable;
     bs->zero_beyond_eof = zero_beyond_eof;
 
     return ret;

block/raw-posix.c

@@ -1047,7 +1047,7 @@ static int aio_worker(void *arg)
     switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
     case QEMU_AIO_READ:
         ret = handle_aiocb_rw(aiocb);
-        if (ret >= 0 && ret < aiocb->aio_nbytes && aiocb->bs->growable) {
+        if (ret >= 0 && ret < aiocb->aio_nbytes) {
             iov_memset(aiocb->aio_iov, aiocb->aio_niov, ret,
                       0, aiocb->aio_nbytes - ret);
 

block/raw-win32.c

@@ -101,7 +101,7 @@ static int aio_worker(void *arg)
     switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
     case QEMU_AIO_READ:
         count = handle_aiocb_rw(aiocb);
-        if (count < aiocb->aio_nbytes && aiocb->bs->growable) {
+        if (count < aiocb->aio_nbytes) {
             /* A short read means that we have reached EOF. Pad the buffer
              * with zeros for bytes after EOF. */
             iov_memset(aiocb->aio_iov, aiocb->aio_niov, count,

block/sheepdog.c

@@ -1730,7 +1730,7 @@ static int sd_create(const char *filename, QemuOpts *opts,
         BlockDriver *drv;
 
         /* Currently, only Sheepdog backing image is supported. */
-        drv = bdrv_find_protocol(backing_file, true);
+        drv = bdrv_find_protocol(backing_file, true, NULL);
         if (!drv || strcmp(drv->protocol_name, "sheepdog") != 0) {
             error_setg(errp, "backing_file must be a sheepdog image");
             ret = -EINVAL;
@@ -2117,7 +2117,7 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
     int64_t offset = (sector_num + nb_sectors) * BDRV_SECTOR_SIZE;
     BDRVSheepdogState *s = bs->opaque;
 
-    if (bs->growable && offset > s->inode.vdi_size) {
+    if (offset > s->inode.vdi_size) {
         ret = sd_truncate(bs, offset);
         if (ret < 0) {
             return ret;

block/vmdk.c

@@ -843,8 +843,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
         }
 
         extent_path = g_malloc0(PATH_MAX);
-        path_combine(extent_path, sizeof(extent_path),
-                desc_file_path, fname);
+        path_combine(extent_path, PATH_MAX, desc_file_path, fname);
         extent_file = NULL;
         ret = bdrv_open(&extent_file, extent_path, NULL, NULL,
                         bs->open_flags | BDRV_O_PROTOCOL, NULL, errp);

blockdev.c

@@ -354,13 +354,11 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     ThrottleConfig cfg;
     int snapshot = 0;
     bool copy_on_read;
-    int ret;
     Error *error = NULL;
     QemuOpts *opts;
     const char *id;
     bool has_driver_specific_opts;
     BlockdevDetectZeroesOptions detect_zeroes;
-    BlockDriver *drv = NULL;
 
     /* Check common options by copying from bs_opts to opts, all other options
      * stay in bs_opts for processing by bdrv_open(). */
@@ -426,11 +424,11 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
             goto early_err;
         }
 
-        drv = bdrv_find_format(buf);
-        if (!drv) {
-            error_setg(errp, "'%s' invalid format", buf);
+        if (qdict_haskey(bs_opts, "driver")) {
+            error_setg(errp, "Cannot specify both 'driver' and 'format'");
             goto early_err;
         }
+        qdict_put(bs_opts, "driver", qstring_from_str(buf));
     }
 
     /* disk I/O throttling */
@@ -505,32 +503,22 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     }
 
     /* init */
+    if ((!file || !*file) && !has_driver_specific_opts) {
         blk = blk_new_with_bs(qemu_opts_id(opts), errp);
         if (!blk) {
             goto early_err;
         }
+
         bs = blk_bs(blk);
         bs->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
         bs->read_only = ro;
-    bs->detect_zeroes = detect_zeroes;
 
-    bdrv_set_on_error(bs, on_read_error, on_write_error);
-
-    /* disk I/O throttling */
-    if (throttle_enabled(&cfg)) {
-        bdrv_io_limits_enable(bs);
-        bdrv_set_io_limits(bs, &cfg);
-    }
-
-    if (!file || !*file) {
-        if (has_driver_specific_opts) {
-            file = NULL;
-        } else {
         QDECREF(bs_opts);
-            qemu_opts_del(opts);
-            return blk;
-        }
+    } else {
+        if (file && !*file) {
+            file = NULL;
         }
+
         if (snapshot) {
             /* always use cache=unsafe with snapshot */
             bdrv_flags &= ~BDRV_O_CACHE_MASK;
@@ -547,28 +535,32 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
 
         bdrv_flags |= ro ? 0 : BDRV_O_RDWR;
 
-    QINCREF(bs_opts);
-    ret = bdrv_open(&bs, file, NULL, bs_opts, bdrv_flags, drv, &error);
-    assert(bs == blk_bs(blk));
+        blk = blk_new_open(qemu_opts_id(opts), file, NULL, bs_opts, bdrv_flags,
+                           errp);
+        if (!blk) {
+            goto err_no_bs_opts;
+        }
+        bs = blk_bs(blk);
+    }
 
-    if (ret < 0) {
-        error_setg(errp, "could not open disk image %s: %s",
-                   file ?: blk_name(blk), error_get_pretty(error));
-        error_free(error);
-        goto err;
+    bs->detect_zeroes = detect_zeroes;
+
+    bdrv_set_on_error(bs, on_read_error, on_write_error);
+
+    /* disk I/O throttling */
+    if (throttle_enabled(&cfg)) {
+        bdrv_io_limits_enable(bs);
+        bdrv_set_io_limits(bs, &cfg);
     }
 
     if (bdrv_key_required(bs)) {
         autostart = 0;
     }
 
-    QDECREF(bs_opts);
+err_no_bs_opts:
     qemu_opts_del(opts);
-
     return blk;
 
-err:
-    blk_unref(blk);
 early_err:
     qemu_opts_del(opts);
 err_no_opts:

cpus.c

@@ -361,15 +361,19 @@ static void icount_warp_rt(void *opaque)
 void qtest_clock_warp(int64_t dest)
 {
     int64_t clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    AioContext *aio_context;
     assert(qtest_enabled());
+    aio_context = qemu_get_aio_context();
     while (clock < dest) {
         int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
         int64_t warp = qemu_soonest_timeout(dest - clock, deadline);
+
         seqlock_write_lock(&timers_state.vm_clock_seqlock);
         timers_state.qemu_icount_bias += warp;
         seqlock_write_unlock(&timers_state.vm_clock_seqlock);
 
         qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
+        timerlist_run_timers(aio_context->tlg.tl[QEMU_CLOCK_VIRTUAL]);
         clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     }
     qemu_clock_notify(QEMU_CLOCK_VIRTUAL);

hmp.c

@@ -16,6 +16,7 @@
 #include "hmp.h"
 #include "net/net.h"
 #include "sysemu/char.h"
+#include "sysemu/block-backend.h"
 #include "qemu/option.h"
 #include "qemu/timer.h"
 #include "qmp-commands.h"
@@ -1720,14 +1721,14 @@ void hmp_chardev_remove(Monitor *mon, const QDict *qdict)
 
 void hmp_qemu_io(Monitor *mon, const QDict *qdict)
 {
-    BlockDriverState *bs;
+    BlockBackend *blk;
     const char* device = qdict_get_str(qdict, "device");
     const char* command = qdict_get_str(qdict, "command");
     Error *err = NULL;
 
-    bs = bdrv_find(device);
-    if (bs) {
-        qemuio_command(bs, command);
+    blk = blk_by_name(device);
+    if (blk) {
+        qemuio_command(blk, command);
     } else {
         error_set(&err, QERR_DEVICE_NOT_FOUND, device);
     }

hw/block/dataplane/virtio-blk.c

@@ -16,7 +16,9 @@
 #include "qemu/iov.h"
 #include "qemu/thread.h"
 #include "qemu/error-report.h"
+#include "hw/virtio/virtio-access.h"
 #include "hw/virtio/dataplane/vring.h"
+#include "hw/virtio/dataplane/vring-accessors.h"
 #include "sysemu/block-backend.h"
 #include "hw/virtio/virtio-blk.h"
 #include "virtio-blk.h"
@@ -75,7 +77,7 @@ static void complete_request_vring(VirtIOBlockReq *req, unsigned char status)
     VirtIOBlockDataPlane *s = req->dev->dataplane;
     stb_p(&req->in->status, status);
 
-    vring_push(&req->dev->dataplane->vring, &req->elem,
+    vring_push(s->vdev, &req->dev->dataplane->vring, &req->elem,
                req->qiov.size + sizeof(*req->in));
 
     /* Suppress notification to guest by BH and its scheduled

hw/block/xen_disk.c

@@ -40,6 +40,8 @@
 #include "xen_blkif.h"
 #include "sysemu/blockdev.h"
 #include "sysemu/block-backend.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qstring.h"
 
 /* ------------------------------------------------------------- */
 
@@ -897,30 +899,23 @@ static int blk_connect(struct XenDevice *xendev)
     blkdev->dinfo = drive_get(IF_XEN, 0, index);
     if (!blkdev->dinfo) {
         Error *local_err = NULL;
-        BlockBackend *blk;
-        BlockDriver *drv;
-        BlockDriverState *bs;
+        QDict *options = NULL;
 
-        /* setup via xenbus -> create new block driver instance */
-        xen_be_printf(&blkdev->xendev, 2, "create new bdrv (xenbus setup)\n");
-        blk = blk_new_with_bs(blkdev->dev, NULL);
-        if (!blk) {
-            return -1;
+        if (strcmp(blkdev->fileproto, "<unset>")) {
+            options = qdict_new();
+            qdict_put(options, "driver", qstring_from_str(blkdev->fileproto));
         }
-        blkdev->blk = blk;
 
-        bs = blk_bs(blk);
-        drv = bdrv_find_whitelisted_format(blkdev->fileproto, readonly);
-        if (bdrv_open(&bs, blkdev->filename, NULL, NULL, qflags,
-                      drv, &local_err) != 0) {
+        /* setup via xenbus -> create new block driver instance */
+        xen_be_printf(&blkdev->xendev, 2, "create new bdrv (xenbus setup)\n");
+        blkdev->blk = blk_new_open(blkdev->dev, blkdev->filename, NULL, options,
+                                   qflags, &local_err);
+        if (!blkdev->blk) {
             xen_be_printf(&blkdev->xendev, 0, "error: %s\n",
                           error_get_pretty(local_err));
             error_free(local_err);
-            blk_unref(blk);
-            blkdev->blk = NULL;
             return -1;
         }
-        assert(bs == blk_bs(blk));
     } else {
         /* setup via qemu cmdline -> already setup for us */
         xen_be_printf(&blkdev->xendev, 2, "get configured bdrv (cmdline setup)\n");

hw/scsi/virtio-scsi-dataplane.c

@@ -94,7 +94,7 @@ void virtio_scsi_vring_push_notify(VirtIOSCSIReq *req)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(req->vring->parent);
 
-    vring_push(&req->vring->vring, &req->elem,
+    vring_push(vdev, &req->vring->vring, &req->elem,
                req->qsgl.size + req->resp_iov.size);
 
     if (vring_should_notify(vdev, &req->vring->vring)) {

hw/virtio/Makefile.objs

@@ -2,7 +2,7 @@ common-obj-y += virtio-rng.o
 common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
 common-obj-y += virtio-bus.o
 common-obj-y += virtio-mmio.o
-common-obj-$(CONFIG_VIRTIO) += dataplane/
+obj-$(CONFIG_VIRTIO) += dataplane/
 
 obj-y += virtio.o virtio-balloon.o 
 obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o

hw/virtio/dataplane/Makefile.objs

-common-obj-y += vring.o
+obj-y += vring.o

hw/virtio/dataplane/vring.c

@@ -18,7 +18,9 @@
 #include "hw/hw.h"
 #include "exec/memory.h"
 #include "exec/address-spaces.h"
+#include "hw/virtio/virtio-access.h"
 #include "hw/virtio/dataplane/vring.h"
+#include "hw/virtio/dataplane/vring-accessors.h"
 #include "qemu/error-report.h"
 
 /* vring_map can be coupled with vring_unmap or (if you still have the
@@ -83,7 +85,7 @@ bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
     vring_init(&vring->vr, virtio_queue_get_num(vdev, n), vring_ptr, 4096);
 
     vring->last_avail_idx = virtio_queue_get_last_avail_idx(vdev, n);
-    vring->last_used_idx = vring->vr.used->idx;
+    vring->last_used_idx = vring_get_used_idx(vdev, vring);
     vring->signalled_used = 0;
     vring->signalled_used_valid = false;
 
@@ -104,7 +106,7 @@ void vring_teardown(Vring *vring, VirtIODevice *vdev, int n)
 void vring_disable_notification(VirtIODevice *vdev, Vring *vring)
 {
     if (!(vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX))) {
-        vring->vr.used->flags |= VRING_USED_F_NO_NOTIFY;
+        vring_set_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
     }
 }
 
@@ -117,10 +119,10 @@ bool vring_enable_notification(VirtIODevice *vdev, Vring *vring)
     if (vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
         vring_avail_event(&vring->vr) = vring->vr.avail->idx;
     } else {
-        vring->vr.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+        vring_clear_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
     }
     smp_mb(); /* ensure update is seen before reading avail_idx */
-    return !vring_more_avail(vring);
+    return !vring_more_avail(vdev, vring);
 }
 
 /* This is stolen from linux/drivers/vhost/vhost.c:vhost_notify() */
@@ -134,12 +136,13 @@ bool vring_should_notify(VirtIODevice *vdev, Vring *vring)
     smp_mb();
 
     if ((vdev->guest_features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY)) &&
-        unlikely(vring->vr.avail->idx == vring->last_avail_idx)) {
+        unlikely(!vring_more_avail(vdev, vring))) {
         return true;
     }
 
     if (!(vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX))) {
-        return !(vring->vr.avail->flags & VRING_AVAIL_F_NO_INTERRUPT);
+        return !(vring_get_avail_flags(vdev, vring) &
+                 VRING_AVAIL_F_NO_INTERRUPT);
     }
     old = vring->signalled_used;
     v = vring->signalled_used_valid;
@@ -202,9 +205,19 @@ static int get_desc(Vring *vring, VirtQueueElement *elem,
     return 0;
 }
 
+static void copy_in_vring_desc(VirtIODevice *vdev,
+                               const struct vring_desc *guest,
+                               struct vring_desc *host)
+{
+    host->addr = virtio_ldq_p(vdev, &guest->addr);
+    host->len = virtio_ldl_p(vdev, &guest->len);
+    host->flags = virtio_lduw_p(vdev, &guest->flags);
+    host->next = virtio_lduw_p(vdev, &guest->next);
+}
+
 /* This is stolen from linux/drivers/vhost/vhost.c. */
-static int get_indirect(Vring *vring, VirtQueueElement *elem,
-                        struct vring_desc *indirect)
+static int get_indirect(VirtIODevice *vdev, Vring *vring,
+                        VirtQueueElement *elem, struct vring_desc *indirect)
 {
     struct vring_desc desc;
     unsigned int i = 0, count, found = 0;
@@ -244,7 +257,7 @@ static int get_indirect(Vring *vring, VirtQueueElement *elem,
             vring->broken = true;
             return -EFAULT;
         }
-        desc = *desc_ptr;
+        copy_in_vring_desc(vdev, desc_ptr, &desc);
         memory_region_unref(mr);
 
         /* Ensure descriptor has been loaded before accessing fields */
@@ -320,7 +333,7 @@ int vring_pop(VirtIODevice *vdev, Vring *vring,
 
     /* Check it isn't doing very strange things with descriptor numbers. */
     last_avail_idx = vring->last_avail_idx;
-    avail_idx = vring->vr.avail->idx;
+    avail_idx = vring_get_avail_idx(vdev, vring);
     barrier(); /* load indices now and not again later */
 
     if (unlikely((uint16_t)(avail_idx - last_avail_idx) > num)) {
@@ -341,7 +354,7 @@ int vring_pop(VirtIODevice *vdev, Vring *vring,
 
     /* Grab the next descriptor number they're advertising, and increment
      * the index we've seen. */
-    head = vring->vr.avail->ring[last_avail_idx % num];
+    head = vring_get_avail_ring(vdev, vring, last_avail_idx % num);
 
     elem->index = head;
 
@@ -365,13 +378,13 @@ int vring_pop(VirtIODevice *vdev, Vring *vring,
             ret = -EFAULT;
             goto out;
         }
-        desc = vring->vr.desc[i];
+        copy_in_vring_desc(vdev, &vring->vr.desc[i], &desc);
 
         /* Ensure descriptor is loaded before accessing fields */
         barrier();
 
         if (desc.flags & VRING_DESC_F_INDIRECT) {
-            ret = get_indirect(vring, elem, &desc);
+            ret = get_indirect(vdev, vring, elem, &desc);
             if (ret < 0) {
                 goto out;
             }
@@ -407,9 +420,9 @@ out:
  *
  * Stolen from linux/drivers/vhost/vhost.c.
  */
-void vring_push(Vring *vring, VirtQueueElement *elem, int len)
+void vring_push(VirtIODevice *vdev, Vring *vring, VirtQueueElement *elem,
+                int len)
 {
-    struct vring_used_elem *used;
     unsigned int head = elem->index;
     uint16_t new;
 
@@ -422,14 +435,16 @@ void vring_push(Vring *vring, VirtQueueElement *elem, int len)
 
     /* The virtqueue contains a ring of used buffers.  Get a pointer to the
      * next entry in that used ring. */
-    used = &vring->vr.used->ring[vring->last_used_idx % vring->vr.num];
-    used->id = head;
-    used->len = len;
+    vring_set_used_ring_id(vdev, vring, vring->last_used_idx % vring->vr.num,
+                           head);
+    vring_set_used_ring_len(vdev, vring, vring->last_used_idx % vring->vr.num,
+                            len);
 
     /* Make sure buffer is written before we update index. */
     smp_wmb();
 
-    new = vring->vr.used->idx = ++vring->last_used_idx;
+    new = ++vring->last_used_idx;
+    vring_set_used_idx(vdev, vring, new);
     if (unlikely((int16_t)(new - vring->signalled_used) < (uint16_t)1)) {
         vring->signalled_used_valid = false;
     }

include/block/block.h

@@ -168,7 +168,8 @@ void bdrv_io_limits_disable(BlockDriverState *bs);
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
 BlockDriver *bdrv_find_protocol(const char *filename,
-                                bool allow_protocol_prefix);
+                                bool allow_protocol_prefix,
+                                Error **errp);
 BlockDriver *bdrv_find_format(const char *format_name);
 BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
                                           bool readonly);

include/block/block_int.h

@@ -369,9 +369,6 @@ struct BlockDriverState {
     /* I/O Limits */
     BlockLimits bl;
 
-    /* Whether the disk can expand beyond total_sectors */
-    int growable;
-
     /* Whether produces zeros when read beyond eof */
     bool zero_beyond_eof;
 

include/block/nbd.h

@@ -99,7 +99,6 @@ void nbd_export_close_all(void);
 
 NBDClient *nbd_client_new(NBDExport *exp, int csock,
                           void (*close)(NBDClient *));
-void nbd_client_close(NBDClient *client);
 void nbd_client_get(NBDClient *client);
 void nbd_client_put(NBDClient *client);
 

include/hw/virtio/dataplane/vring-accessors.h

+#ifndef VRING_ACCESSORS_H
+#define VRING_ACCESSORS_H
+
+#include "hw/virtio/virtio_ring.h"
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-access.h"
+
+static inline uint16_t vring_get_used_idx(VirtIODevice *vdev, Vring *vring)
+{
+    return virtio_tswap16(vdev, vring->vr.used->idx);
+}
+
+static inline void vring_set_used_idx(VirtIODevice *vdev, Vring *vring,
+                                      uint16_t idx)
+{
+    vring->vr.used->idx = virtio_tswap16(vdev, idx);
+}
+
+static inline uint16_t vring_get_avail_idx(VirtIODevice *vdev, Vring *vring)
+{
+    return virtio_tswap16(vdev, vring->vr.avail->idx);
+}
+
+static inline uint16_t vring_get_avail_ring(VirtIODevice *vdev, Vring *vring,
+                                            int i)
+{
+    return virtio_tswap16(vdev, vring->vr.avail->ring[i]);
+}
+
+static inline void vring_set_used_ring_id(VirtIODevice *vdev, Vring *vring,
+                                          int i, uint32_t id)
+{
+    vring->vr.used->ring[i].id = virtio_tswap32(vdev, id);
+}
+
+static inline void vring_set_used_ring_len(VirtIODevice *vdev, Vring *vring,
+                                          int i, uint32_t len)
+{
+    vring->vr.used->ring[i].len = virtio_tswap32(vdev, len);
+}
+
+static inline uint16_t vring_get_used_flags(VirtIODevice *vdev, Vring *vring)
+{
+    return virtio_tswap16(vdev, vring->vr.used->flags);
+}
+
+static inline uint16_t vring_get_avail_flags(VirtIODevice *vdev, Vring *vring)
+{
+    return virtio_tswap16(vdev, vring->vr.avail->flags);
+}
+
+static inline void vring_set_used_flags(VirtIODevice *vdev, Vring *vring,
+                                        uint16_t flags)
+{
+    vring->vr.used->flags |= virtio_tswap16(vdev, flags);
+}
+
+static inline void vring_clear_used_flags(VirtIODevice *vdev, Vring *vring,
+                                          uint16_t flags)
+{
+    vring->vr.used->flags &= virtio_tswap16(vdev, ~flags);
+}
+
+static inline unsigned int vring_get_num(Vring *vring)
+{
+    return vring->vr.num;
+}
+
+/* Are there more descriptors available? */
+static inline bool vring_more_avail(VirtIODevice *vdev, Vring *vring)
+{
+    return vring_get_avail_idx(vdev, vring) != vring->last_avail_idx;
+}
+
+#endif

include/hw/virtio/dataplane/vring.h

@@ -31,17 +31,6 @@ typedef struct {
     bool broken;                    /* was there a fatal error? */
 } Vring;
 
-static inline unsigned int vring_get_num(Vring *vring)
-{
-    return vring->vr.num;
-}
-
-/* Are there more descriptors available? */
-static inline bool vring_more_avail(Vring *vring)
-{
-    return vring->vr.avail->idx != vring->last_avail_idx;
-}
-
 /* Fail future vring_pop() and vring_push() calls until reset */
 static inline void vring_set_broken(Vring *vring)
 {
@@ -54,6 +43,7 @@ void vring_disable_notification(VirtIODevice *vdev, Vring *vring);
 bool vring_enable_notification(VirtIODevice *vdev, Vring *vring);
 bool vring_should_notify(VirtIODevice *vdev, Vring *vring);
 int vring_pop(VirtIODevice *vdev, Vring *vring, VirtQueueElement *elem);
-void vring_push(Vring *vring, VirtQueueElement *elem, int len);
+void vring_push(VirtIODevice *vdev, Vring *vring, VirtQueueElement *elem,
+                int len);
 
 #endif /* VRING_H */

include/qemu-io.h

@@ -22,7 +22,7 @@
 
 #define CMD_FLAG_GLOBAL ((int)0x80000000) /* don't iterate "args" */
 
-typedef int (*cfunc_t)(BlockDriverState *bs, int argc, char **argv);
+typedef int (*cfunc_t)(BlockBackend *blk, int argc, char **argv);
 typedef void (*helpfunc_t)(void);
 
 typedef struct cmdinfo {
@@ -40,7 +40,7 @@ typedef struct cmdinfo {
 
 extern bool qemuio_misalign;
 
-bool qemuio_command(BlockDriverState *bs, const char *cmd);
+bool qemuio_command(BlockBackend *blk, const char *cmd);
 
 void qemuio_add_command(const cmdinfo_t *ci);
 int qemuio_command_usage(const cmdinfo_t *ci);

include/sysemu/block-backend.h

@@ -62,6 +62,9 @@ typedef struct BlockDevOps {
 
 BlockBackend *blk_new(const char *name, Error **errp);
 BlockBackend *blk_new_with_bs(const char *name, Error **errp);
+BlockBackend *blk_new_open(const char *name, const char *filename,
+                           const char *reference, QDict *options, int flags,
+                           Error **errp);
 void blk_ref(BlockBackend *blk);
 void blk_unref(BlockBackend *blk);
 const char *blk_name(BlockBackend *blk);
@@ -91,6 +94,7 @@ int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count);
 int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count);
 int64_t blk_getlength(BlockBackend *blk);
 void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr);
+int64_t blk_nb_sectors(BlockBackend *blk);
 BlockAIOCB *blk_aio_readv(BlockBackend *blk, int64_t sector_num,
                           QEMUIOVector *iov, int nb_sectors,
                           BlockCompletionFunc *cb, void *opaque);
@@ -151,5 +155,14 @@ BlockAcctStats *blk_get_stats(BlockBackend *blk);
 
 void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
                   BlockCompletionFunc *cb, void *opaque);
+int coroutine_fn blk_co_write_zeroes(BlockBackend *blk, int64_t sector_num,
+                                     int nb_sectors, BdrvRequestFlags flags);
+int blk_write_compressed(BlockBackend *blk, int64_t sector_num,
+                         const uint8_t *buf, int nb_sectors);
+int blk_truncate(BlockBackend *blk, int64_t offset);
+int blk_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors);
+int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
+                     int64_t pos, int size);
+int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size);
 
 #endif

nbd.c

@@ -874,7 +874,7 @@ void nbd_client_put(NBDClient *client)
 {
     if (--client->refcount == 0) {
         /* The last reference should be dropped by client->close,
-         * which is called by nbd_client_close.
+         * which is called by client_close.
          */
         assert(client->closing);
 
@@ -889,7 +889,7 @@ void nbd_client_put(NBDClient *client)
     }
 }
 
-void nbd_client_close(NBDClient *client)
+static void client_close(NBDClient *client)
 {
     if (client->closing) {
         return;
@@ -1026,7 +1026,7 @@ void nbd_export_close(NBDExport *exp)
 
     nbd_export_get(exp);
     QTAILQ_FOREACH_SAFE(client, &exp->clients, next, next) {
-        nbd_client_close(client);
+        client_close(client);
     }
     nbd_export_set_name(exp, NULL);
     nbd_export_put(exp);
@@ -1311,7 +1311,7 @@ done:
 
 out:
     nbd_request_put(req);
-    nbd_client_close(client);
+    client_close(client);
 }
 
 static void nbd_read(void *opaque)

qemu-img.c

@@ -261,6 +261,7 @@ static int print_block_option_help(const char *filename, const char *fmt)
 {
     BlockDriver *drv, *proto_drv;
     QemuOptsList *create_opts = NULL;
+    Error *local_err = NULL;
 
     /* Find driver and parse its options */
     drv = bdrv_find_format(fmt);
@@ -271,9 +272,10 @@ static int print_block_option_help(const char *filename, const char *fmt)
 
     create_opts = qemu_opts_append(create_opts, drv->create_opts);
     if (filename) {
-        proto_drv = bdrv_find_protocol(filename, true);
+        proto_drv = bdrv_find_protocol(filename, true, &local_err);
         if (!proto_drv) {
-            error_report("Unknown protocol '%s'", filename);
+            qerror_report_err(local_err);
+            error_free(local_err);
             qemu_opts_free(create_opts);
             return 1;
         }
@@ -291,32 +293,24 @@ static BlockBackend *img_open(const char *id, const char *filename,
 {
     BlockBackend *blk;
     BlockDriverState *bs;
-    BlockDriver *drv;
     char password[256];
     Error *local_err = NULL;
-    int ret;
-
-    blk = blk_new_with_bs(id, &error_abort);
-    bs = blk_bs(blk);
+    QDict *options = NULL;
 
     if (fmt) {
-        drv = bdrv_find_format(fmt);
-        if (!drv) {
-            error_report("Unknown file format '%s'", fmt);
-            goto fail;
-        }
-    } else {
-        drv = NULL;
+        options = qdict_new();
+        qdict_put(options, "driver", qstring_from_str(fmt));
     }
 
-    ret = bdrv_open(&bs, filename, NULL, NULL, flags, drv, &local_err);
-    if (ret < 0) {
+    blk = blk_new_open(id, filename, NULL, options, flags, &local_err);
+    if (!blk) {
         error_report("Could not open '%s': %s", filename,
                      error_get_pretty(local_err));
         error_free(local_err);
         goto fail;
     }
 
+    bs = blk_bs(blk);
     if (bdrv_is_encrypted(bs) && require_io) {
         qprintf(quiet, "Disk image '%s' is encrypted.\n", filename);
         if (read_password(password, sizeof(password)) < 0) {
@@ -1016,19 +1010,19 @@ static int64_t sectors_to_process(int64_t total, int64_t from)
  * Returns 0 in case sectors are filled with 0, 1 if sectors contain non-zero
  * data and negative value on error.
  *
- * @param bs:  Driver used for accessing file
+ * @param blk:  BlockBackend for the image
  * @param sect_num: Number of first sector to check
  * @param sect_count: Number of sectors to check
  * @param filename: Name of disk file we are checking (logging purpose)
  * @param buffer: Allocated buffer for storing read data
  * @param quiet: Flag for quiet mode
  */
-static int check_empty_sectors(BlockDriverState *bs, int64_t sect_num,
+static int check_empty_sectors(BlockBackend *blk, int64_t sect_num,
                                int sect_count, const char *filename,
                                uint8_t *buffer, bool quiet)
 {
     int pnum, ret = 0;
-    ret = bdrv_read(bs, sect_num, buffer, sect_count);
+    ret = blk_read(blk, sect_num, buffer, sect_count);
     if (ret < 0) {
         error_report("Error while reading offset %" PRId64 " of %s: %s",
                      sectors_to_bytes(sect_num), filename, strerror(-ret));
@@ -1138,16 +1132,16 @@ static int img_compare(int argc, char **argv)
     }
     bs2 = blk_bs(blk2);
 
-    buf1 = qemu_blockalign(bs1, IO_BUF_SIZE);
-    buf2 = qemu_blockalign(bs2, IO_BUF_SIZE);
-    total_sectors1 = bdrv_nb_sectors(bs1);
+    buf1 = blk_blockalign(blk1, IO_BUF_SIZE);
+    buf2 = blk_blockalign(blk2, IO_BUF_SIZE);
+    total_sectors1 = blk_nb_sectors(blk1);
     if (total_sectors1 < 0) {
         error_report("Can't get size of %s: %s",
                      filename1, strerror(-total_sectors1));
         ret = 4;
         goto out;
     }
-    total_sectors2 = bdrv_nb_sectors(bs2);
+    total_sectors2 = blk_nb_sectors(blk2);
     if (total_sectors2 < 0) {
         error_report("Can't get size of %s: %s",
                      filename2, strerror(-total_sectors2));
@@ -1189,7 +1183,7 @@ static int img_compare(int argc, char **argv)
 
         if (allocated1 == allocated2) {
             if (allocated1) {
-                ret = bdrv_read(bs1, sector_num, buf1, nb_sectors);
+                ret = blk_read(blk1, sector_num, buf1, nb_sectors);
                 if (ret < 0) {
                     error_report("Error while reading offset %" PRId64 " of %s:"
                                  " %s", sectors_to_bytes(sector_num), filename1,
@@ -1197,7 +1191,7 @@ static int img_compare(int argc, char **argv)
                     ret = 4;
                     goto out;
                 }
-                ret = bdrv_read(bs2, sector_num, buf2, nb_sectors);
+                ret = blk_read(blk2, sector_num, buf2, nb_sectors);
                 if (ret < 0) {
                     error_report("Error while reading offset %" PRId64
                                  " of %s: %s", sectors_to_bytes(sector_num),
@@ -1224,10 +1218,10 @@ static int img_compare(int argc, char **argv)
             }
 
             if (allocated1) {
-                ret = check_empty_sectors(bs1, sector_num, nb_sectors,
+                ret = check_empty_sectors(blk1, sector_num, nb_sectors,
                                           filename1, buf1, quiet);
             } else {
-                ret = check_empty_sectors(bs2, sector_num, nb_sectors,
+                ret = check_empty_sectors(blk2, sector_num, nb_sectors,
                                           filename2, buf1, quiet);
             }
             if (ret) {
@@ -1244,18 +1238,18 @@ static int img_compare(int argc, char **argv)
     }
 
     if (total_sectors1 != total_sectors2) {
-        BlockDriverState *bs_over;
+        BlockBackend *blk_over;
         int64_t total_sectors_over;
         const char *filename_over;
 
         qprintf(quiet, "Warning: Image size mismatch!\n");
         if (total_sectors1 > total_sectors2) {
             total_sectors_over = total_sectors1;
-            bs_over = bs1;
+            blk_over = blk1;
             filename_over = filename1;
         } else {
             total_sectors_over = total_sectors2;
-            bs_over = bs2;
+            blk_over = blk2;
             filename_over = filename2;
         }
 
@@ -1264,7 +1258,7 @@ static int img_compare(int argc, char **argv)
             if (nb_sectors <= 0) {
                 break;
             }
-            ret = bdrv_is_allocated_above(bs_over, NULL, sector_num,
+            ret = bdrv_is_allocated_above(blk_bs(blk_over), NULL, sector_num,
                                           nb_sectors, &pnum);
             if (ret < 0) {
                 ret = 3;
@@ -1275,7 +1269,7 @@ static int img_compare(int argc, char **argv)
             }
             nb_sectors = pnum;
             if (ret) {
-                ret = check_empty_sectors(bs_over, sector_num, nb_sectors,
+                ret = check_empty_sectors(blk_over, sector_num, nb_sectors,
                                           filename_over, buf1, quiet);
                 if (ret) {
                     if (ret < 0) {
@@ -1484,7 +1478,7 @@ static int img_convert(int argc, char **argv)
             goto out;
         }
         bs[bs_i] = blk_bs(blk[bs_i]);
-        bs_sectors[bs_i] = bdrv_nb_sectors(bs[bs_i]);
+        bs_sectors[bs_i] = blk_nb_sectors(blk[bs_i]);
         if (bs_sectors[bs_i] < 0) {
             error_report("Could not get size of %s: %s",
                          argv[optind + bs_i], strerror(-bs_sectors[bs_i]));
@@ -1524,13 +1518,15 @@ static int img_convert(int argc, char **argv)
         goto out;
     }
 
-    proto_drv = bdrv_find_protocol(out_filename, true);
+    proto_drv = bdrv_find_protocol(out_filename, true, &local_err);
     if (!proto_drv) {
-        error_report("Unknown protocol '%s'", out_filename);
+        qerror_report_err(local_err);
+        error_free(local_err);
         ret = -1;
         goto out;
     }
 
+    if (!skip_create) {
         if (!drv->create_opts) {
             error_report("Format driver '%s' does not support image creation",
                          drv->format_name);
@@ -1560,6 +1556,7 @@ static int img_convert(int argc, char **argv)
         if (ret < 0) {
             goto out;
         }
+    }
 
     /* Get backing file name if -o backing_file was used */
     out_baseimg_param = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
@@ -1633,10 +1630,10 @@ static int img_convert(int argc, char **argv)
                                          out_bs->bl.discard_alignment))
                     );
 
-    buf = qemu_blockalign(out_bs, bufsectors * BDRV_SECTOR_SIZE);
+    buf = blk_blockalign(out_blk, bufsectors * BDRV_SECTOR_SIZE);
 
     if (skip_create) {
-        int64_t output_sectors = bdrv_nb_sectors(out_bs);
+        int64_t output_sectors = blk_nb_sectors(out_blk);
         if (output_sectors < 0) {
             error_report("unable to get output image length: %s\n",
                          strerror(-output_sectors));
@@ -1704,7 +1701,7 @@ static int img_convert(int argc, char **argv)
                 nlow = remainder > bs_sectors[bs_i] - bs_num
                     ? bs_sectors[bs_i] - bs_num : remainder;
 
-                ret = bdrv_read(bs[bs_i], bs_num, buf2, nlow);
+                ret = blk_read(blk[bs_i], bs_num, buf2, nlow);
                 if (ret < 0) {
                     error_report("error while reading sector %" PRId64 ": %s",
                                  bs_num, strerror(-ret));
@@ -1719,7 +1716,7 @@ static int img_convert(int argc, char **argv)
             assert (remainder == 0);
 
             if (!buffer_is_zero(buf, n * BDRV_SECTOR_SIZE)) {
-                ret = bdrv_write_compressed(out_bs, sector_num, buf, n);
+                ret = blk_write_compressed(out_blk, sector_num, buf, n);
                 if (ret != 0) {
                     error_report("error while compressing sector %" PRId64
                                  ": %s", sector_num, strerror(-ret));
@@ -1730,7 +1727,7 @@ static int img_convert(int argc, char **argv)
             qemu_progress_print(100.0 * sector_num / total_sectors, 0);
         }
         /* signal EOF to align */
-        bdrv_write_compressed(out_bs, 0, NULL, 0);
+        blk_write_compressed(out_blk, 0, NULL, 0);
     } else {
         int64_t sectors_to_read, sectors_read, sector_num_next_status;
         bool count_allocated_sectors;
@@ -1831,7 +1828,7 @@ restart:
             }
 
             n1 = n;
-            ret = bdrv_read(bs[bs_i], sector_num - bs_offset, buf, n);
+            ret = blk_read(blk[bs_i], sector_num - bs_offset, buf, n);
             if (ret < 0) {
                 error_report("error while reading sector %" PRId64 ": %s",
                              sector_num - bs_offset, strerror(-ret));
@@ -1844,7 +1841,7 @@ restart:
             while (n > 0) {
                 if (!has_zero_init ||
                     is_allocated_sectors_min(buf1, n, &n1, min_sparse)) {
-                    ret = bdrv_write(out_bs, sector_num, buf1, n1);
+                    ret = blk_write(out_blk, sector_num, buf1, n1);
                     if (ret < 0) {
                         error_report("error while writing sector %" PRId64
                                      ": %s", sector_num, strerror(-ret));
@@ -2268,7 +2265,7 @@ static int img_map(int argc, char **argv)
         printf("%-16s%-16s%-16s%s\n", "Offset", "Length", "Mapped to", "File");
     }
 
-    length = bdrv_getlength(bs);
+    length = blk_getlength(blk);
     while (curr.start + curr.length < length) {
         int64_t nsectors_left;
         int64_t sector_num;
@@ -2437,8 +2434,7 @@ static int img_snapshot(int argc, char **argv)
 static int img_rebase(int argc, char **argv)
 {
     BlockBackend *blk = NULL, *blk_old_backing = NULL, *blk_new_backing = NULL;
-    BlockDriverState *bs = NULL, *bs_old_backing = NULL, *bs_new_backing = NULL;
-    BlockDriver *old_backing_drv, *new_backing_drv;
+    BlockDriverState *bs = NULL;
     char *filename;
     const char *fmt, *cache, *src_cache, *out_basefmt, *out_baseimg;
     int c, flags, src_flags, ret;
@@ -2532,22 +2528,8 @@ static int img_rebase(int argc, char **argv)
     }
     bs = blk_bs(blk);
 
-    /* Find the right drivers for the backing files */
-    old_backing_drv = NULL;
-    new_backing_drv = NULL;
-
-    if (!unsafe && bs->backing_format[0] != '\0') {
-        old_backing_drv = bdrv_find_format(bs->backing_format);
-        if (old_backing_drv == NULL) {
-            error_report("Invalid format name: '%s'", bs->backing_format);
-            ret = -1;
-            goto out;
-        }
-    }
-
     if (out_basefmt != NULL) {
-        new_backing_drv = bdrv_find_format(out_basefmt);
-        if (new_backing_drv == NULL) {
+        if (bdrv_find_format(out_basefmt) == NULL) {
             error_report("Invalid format name: '%s'", out_basefmt);
             ret = -1;
             goto out;
@@ -2557,24 +2539,34 @@ static int img_rebase(int argc, char **argv)
     /* For safe rebasing we need to compare old and new backing file */
     if (!unsafe) {
         char backing_name[PATH_MAX];
+        QDict *options = NULL;
+
+        if (bs->backing_format[0] != '\0') {
+            options = qdict_new();
+            qdict_put(options, "driver", qstring_from_str(bs->backing_format));
+        }
 
-        blk_old_backing = blk_new_with_bs("old_backing", &error_abort);
-        bs_old_backing = blk_bs(blk_old_backing);
         bdrv_get_backing_filename(bs, backing_name, sizeof(backing_name));
-        ret = bdrv_open(&bs_old_backing, backing_name, NULL, NULL, src_flags,
-                        old_backing_drv, &local_err);
-        if (ret) {
+        blk_old_backing = blk_new_open("old_backing", backing_name, NULL,
+                                       options, src_flags, &local_err);
+        if (!blk_old_backing) {
             error_report("Could not open old backing file '%s': %s",
                          backing_name, error_get_pretty(local_err));
             error_free(local_err);
             goto out;
         }
+
         if (out_baseimg[0]) {
-            blk_new_backing = blk_new_with_bs("new_backing", &error_abort);
-            bs_new_backing = blk_bs(blk_new_backing);
-            ret = bdrv_open(&bs_new_backing, out_baseimg, NULL, NULL, src_flags,
-                            new_backing_drv, &local_err);
-            if (ret) {
+            if (out_basefmt) {
+                options = qdict_new();
+                qdict_put(options, "driver", qstring_from_str(out_basefmt));
+            } else {
+                options = NULL;
+            }
+
+            blk_new_backing = blk_new_open("new_backing", out_baseimg, NULL,
+                                           options, src_flags, &local_err);
+            if (!blk_new_backing) {
                 error_report("Could not open new backing file '%s': %s",
                              out_baseimg, error_get_pretty(local_err));
                 error_free(local_err);
@@ -2602,17 +2594,17 @@ static int img_rebase(int argc, char **argv)
         uint8_t * buf_new;
         float local_progress = 0;
 
-        buf_old = qemu_blockalign(bs, IO_BUF_SIZE);
-        buf_new = qemu_blockalign(bs, IO_BUF_SIZE);
+        buf_old = blk_blockalign(blk, IO_BUF_SIZE);
+        buf_new = blk_blockalign(blk, IO_BUF_SIZE);
 
-        num_sectors = bdrv_nb_sectors(bs);
+        num_sectors = blk_nb_sectors(blk);
         if (num_sectors < 0) {
             error_report("Could not get size of '%s': %s",
                          filename, strerror(-num_sectors));
             ret = -1;
             goto out;
         }
-        old_backing_num_sectors = bdrv_nb_sectors(bs_old_backing);
+        old_backing_num_sectors = blk_nb_sectors(blk_old_backing);
         if (old_backing_num_sectors < 0) {
             char backing_name[PATH_MAX];
 
@@ -2622,8 +2614,8 @@ static int img_rebase(int argc, char **argv)
             ret = -1;
             goto out;
         }
-        if (bs_new_backing) {
-            new_backing_num_sectors = bdrv_nb_sectors(bs_new_backing);
+        if (blk_new_backing) {
+            new_backing_num_sectors = blk_nb_sectors(blk_new_backing);
             if (new_backing_num_sectors < 0) {
                 error_report("Could not get size of '%s': %s",
                              out_baseimg, strerror(-new_backing_num_sectors));
@@ -2668,21 +2660,21 @@ static int img_rebase(int argc, char **argv)
                     n = old_backing_num_sectors - sector;
                 }
 
-                ret = bdrv_read(bs_old_backing, sector, buf_old, n);
+                ret = blk_read(blk_old_backing, sector, buf_old, n);
                 if (ret < 0) {
                     error_report("error while reading from old backing file");
                     goto out;
                 }
             }
 
-            if (sector >= new_backing_num_sectors || !bs_new_backing) {
+            if (sector >= new_backing_num_sectors || !blk_new_backing) {
                 memset(buf_new, 0, n * BDRV_SECTOR_SIZE);
             } else {
                 if (sector + n > new_backing_num_sectors) {
                     n = new_backing_num_sectors - sector;
                 }
 
-                ret = bdrv_read(bs_new_backing, sector, buf_new, n);
+                ret = blk_read(blk_new_backing, sector, buf_new, n);
                 if (ret < 0) {
                     error_report("error while reading from new backing file");
                     goto out;
@@ -2698,7 +2690,7 @@ static int img_rebase(int argc, char **argv)
                 if (compare_sectors(buf_old + written * 512,
                     buf_new + written * 512, n - written, &pnum))
                 {
-                    ret = bdrv_write(bs, sector + written,
+                    ret = blk_write(blk, sector + written,
                                     buf_old + written * 512, pnum);
                     if (ret < 0) {
                         error_report("Error while writing to COW image: %s",
@@ -2764,7 +2756,6 @@ static int img_resize(int argc, char **argv)
     int64_t n, total_size;
     bool quiet = false;
     BlockBackend *blk = NULL;
-    BlockDriverState *bs = NULL;
     QemuOpts *param;
     static QemuOptsList resize_options = {
         .name = "resize_options",
@@ -2846,10 +2837,9 @@ static int img_resize(int argc, char **argv)
         ret = -1;
         goto out;
     }
-    bs = blk_bs(blk);
 
     if (relative) {
-        total_size = bdrv_getlength(bs) + n * relative;
+        total_size = blk_getlength(blk) + n * relative;
     } else {
         total_size = n;
     }
@@ -2859,7 +2849,7 @@ static int img_resize(int argc, char **argv)
         goto out;
     }
 
-    ret = bdrv_truncate(bs, total_size);
+    ret = blk_truncate(blk, total_size);
     switch (ret) {
     case 0:
         qprintf(quiet, "Image resized.\n");

qemu-io.c

@@ -28,7 +28,6 @@
 static char *progname;
 
 static BlockBackend *qemuio_blk;
-static BlockDriverState *qemuio_bs;
 
 /* qemu-io commands passed using -c */
 static int ncmdline;
@@ -36,10 +35,9 @@ static char **cmdline;
 
 static ReadLineState *readline_state;
 
-static int close_f(BlockDriverState *bs, int argc, char **argv)
+static int close_f(BlockBackend *blk, int argc, char **argv)
 {
     blk_unref(qemuio_blk);
-    qemuio_bs = NULL;
     qemuio_blk = NULL;
     return 0;
 }
@@ -51,32 +49,22 @@ static const cmdinfo_t close_cmd = {
     .oneline    = "close the current open file",
 };
 
-static int openfile(char *name, BlockDriver *drv, int flags, int growable,
-                    QDict *opts)
+static int openfile(char *name, int flags, QDict *opts)
 {
     Error *local_err = NULL;
 
-    if (qemuio_bs) {
+    if (qemuio_blk) {
         fprintf(stderr, "file open already, try 'help close'\n");
         QDECREF(opts);
         return 1;
     }
 
-    qemuio_blk = blk_new_with_bs("hda", &error_abort);
-    qemuio_bs = blk_bs(qemuio_blk);
-
-    if (growable) {
-        flags |= BDRV_O_PROTOCOL;
-    }
-
-    if (bdrv_open(&qemuio_bs, name, NULL, opts, flags, drv, &local_err) < 0) {
+    qemuio_blk = blk_new_open("hda", name, NULL, opts, flags, &local_err);
+    if (!qemuio_blk) {
         fprintf(stderr, "%s: can't open%s%s: %s\n", progname,
                 name ? " device " : "", name ?: "",
                 error_get_pretty(local_err));
         error_free(local_err);
-        blk_unref(qemuio_blk);
-        qemuio_bs = NULL;
-        qemuio_blk = NULL;
         return 1;
     }
 
@@ -96,12 +84,11 @@ static void open_help(void)
 " -r, -- open file read-only\n"
 " -s, -- use snapshot file\n"
 " -n, -- disable host cache\n"
-" -g, -- allow file to grow (only applies to protocols)\n"
 " -o, -- options to be given to the block driver"
 "\n");
 }
 
-static int open_f(BlockDriverState *bs, int argc, char **argv);
+static int open_f(BlockBackend *blk, int argc, char **argv);
 
 static const cmdinfo_t open_cmd = {
     .name       = "open",
@@ -125,11 +112,10 @@ static QemuOptsList empty_opts = {
     },
 };
 
-static int open_f(BlockDriverState *bs, int argc, char **argv)
+static int open_f(BlockBackend *blk, int argc, char **argv)
 {
     int flags = 0;
     int readonly = 0;
-    int growable = 0;
     int c;
     QemuOpts *qopts;
     QDict *opts;
@@ -145,9 +131,6 @@ static int open_f(BlockDriverState *bs, int argc, char **argv)
         case 'r':
             readonly = 1;
             break;
-        case 'g':
-            growable = 1;
-            break;
         case 'o':
             if (!qemu_opts_parse(&empty_opts, optarg, 0)) {
                 printf("could not parse option list -- %s\n", optarg);
@@ -170,16 +153,16 @@ static int open_f(BlockDriverState *bs, int argc, char **argv)
     qemu_opts_reset(&empty_opts);
 
     if (optind == argc - 1) {
-        return openfile(argv[optind], NULL, flags, growable, opts);
+        return openfile(argv[optind], flags, opts);
     } else if (optind == argc) {
-        return openfile(NULL, NULL, flags, growable, opts);
+        return openfile(NULL, flags, opts);
     } else {
         QDECREF(opts);
         return qemuio_command_usage(&open_cmd);
     }
 }
 
-static int quit_f(BlockDriverState *bs, int argc, char **argv)
+static int quit_f(BlockBackend *blk, int argc, char **argv)
 {
     return 1;
 }
@@ -206,7 +189,6 @@ static void usage(const char *name)
 "  -r, --read-only      export read-only\n"
 "  -s, --snapshot       use snapshot file\n"
 "  -n, --nocache        disable host cache\n"
-"  -g, --growable       allow file to grow (only applies to protocols)\n"
 "  -m, --misalign       misalign allocations for O_DIRECT\n"
 "  -k, --native-aio     use kernel AIO implementation (on Linux only)\n"
 "  -t, --cache=MODE     use the given cache mode for the image\n"
@@ -317,7 +299,7 @@ static void command_loop(void)
     char *input;
 
     for (i = 0; !done && i < ncmdline; i++) {
-        done = qemuio_command(qemuio_bs, cmdline[i]);
+        done = qemuio_command(qemuio_blk, cmdline[i]);
     }
     if (cmdline) {
         g_free(cmdline);
@@ -342,7 +324,7 @@ static void command_loop(void)
         if (input == NULL) {
             break;
         }
-        done = qemuio_command(qemuio_bs, input);
+        done = qemuio_command(qemuio_blk, input);
         g_free(input);
 
         prompted = 0;
@@ -365,7 +347,6 @@ static void reenable_tty_echo(void)
 int main(int argc, char **argv)
 {
     int readonly = 0;
-    int growable = 0;
     const char *sopt = "hVc:d:f:rsnmgkt:T:";
     const struct option lopt[] = {
         { "help", 0, NULL, 'h' },
@@ -377,7 +358,6 @@ int main(int argc, char **argv)
         { "snapshot", 0, NULL, 's' },
         { "nocache", 0, NULL, 'n' },
         { "misalign", 0, NULL, 'm' },
-        { "growable", 0, NULL, 'g' },
         { "native-aio", 0, NULL, 'k' },
         { "discard", 1, NULL, 'd' },
         { "cache", 1, NULL, 't' },
@@ -387,8 +367,8 @@ int main(int argc, char **argv)
     int c;
     int opt_index = 0;
     int flags = BDRV_O_UNMAP;
-    BlockDriver *drv = NULL;
     Error *local_error = NULL;
+    QDict *opts = NULL;
 
 #ifdef CONFIG_POSIX
     signal(SIGPIPE, SIG_IGN);
@@ -414,11 +394,10 @@ int main(int argc, char **argv)
             }
             break;
         case 'f':
-            drv = bdrv_find_format(optarg);
-            if (!drv) {
-                error_report("Invalid format '%s'", optarg);
-                exit(EXIT_FAILURE);
+            if (!opts) {
+                opts = qdict_new();
             }
+            qdict_put(opts, "driver", qstring_from_str(optarg));
             break;
         case 'c':
             add_user_command(optarg);
@@ -429,9 +408,6 @@ int main(int argc, char **argv)
         case 'm':
             qemuio_misalign = true;
             break;
-        case 'g':
-            growable = 1;
-            break;
         case 'k':
             flags |= BDRV_O_NATIVE_AIO;
             break;
@@ -489,7 +465,7 @@ int main(int argc, char **argv)
     }
 
     if ((argc - optind) == 1) {
-        openfile(argv[optind], drv, flags, growable, NULL);
+        openfile(argv[optind], flags, opts);
     }
     command_loop();
 

qemu-nbd.c

@@ -391,7 +391,6 @@ int main(int argc, char **argv)
 {
     BlockBackend *blk;
     BlockDriverState *bs;
-    BlockDriver *drv;
     off_t dev_offset = 0;
     uint32_t nbdflags = 0;
     bool disconnect = false;
@@ -434,7 +433,7 @@ int main(int argc, char **argv)
     char *end;
     int flags = BDRV_O_RDWR;
     int partition = -1;
-    int ret;
+    int ret = 0;
     int fd;
     bool seen_cache = false;
     bool seen_discard = false;
@@ -445,6 +444,7 @@ int main(int argc, char **argv)
     const char *fmt = NULL;
     Error *local_err = NULL;
     BlockdevDetectZeroesOptions detect_zeroes = BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
+    QDict *options = NULL;
 
     /* The client thread uses SIGTERM to interrupt the server.  A signal
      * handler ensures that "qemu-nbd -v -c" exits with a nice status code.
@@ -689,24 +689,17 @@ int main(int argc, char **argv)
     atexit(bdrv_close_all);
 
     if (fmt) {
-        drv = bdrv_find_format(fmt);
-        if (!drv) {
-            errx(EXIT_FAILURE, "Unknown file format '%s'", fmt);
-        }
-    } else {
-        drv = NULL;
+        options = qdict_new();
+        qdict_put(options, "driver", qstring_from_str(fmt));
     }
 
-    blk = blk_new_with_bs("hda", &error_abort);
-    bs = blk_bs(blk);
-
     srcpath = argv[optind];
-    ret = bdrv_open(&bs, srcpath, NULL, NULL, flags, drv, &local_err);
-    if (ret < 0) {
-        errno = -ret;
-        err(EXIT_FAILURE, "Failed to bdrv_open '%s': %s", argv[optind],
+    blk = blk_new_open("hda", srcpath, NULL, options, flags, &local_err);
+    if (!blk) {
+        errx(EXIT_FAILURE, "Failed to blk_new_open '%s': %s", argv[optind],
              error_get_pretty(local_err));
     }
+    bs = blk_bs(blk);
 
     if (sn_opts) {
         ret = bdrv_snapshot_load_tmp(bs,

savevm.c

@@ -821,7 +821,7 @@ void qemu_savevm_state_cancel(void)
     }
 }
 
-static int qemu_savevm_state(QEMUFile *f)
+static int qemu_savevm_state(QEMUFile *f, Error **errp)
 {
     int ret;
     MigrationParams params = {
@@ -829,7 +829,7 @@ static int qemu_savevm_state(QEMUFile *f)
         .shared = 0
     };
 
-    if (qemu_savevm_state_blocked(NULL)) {
+    if (qemu_savevm_state_blocked(errp)) {
         return -EINVAL;
     }
 
@@ -850,6 +850,7 @@ static int qemu_savevm_state(QEMUFile *f)
     }
     if (ret != 0) {
         qemu_savevm_state_cancel();
+        error_setg_errno(errp, -ret, "Error while writing VM state");
     }
     return ret;
 }
@@ -1102,6 +1103,7 @@ void do_savevm(Monitor *mon, const QDict *qdict)
     qemu_timeval tv;
     struct tm tm;
     const char *name = qdict_get_try_str(qdict, "name");
+    Error *local_err = NULL;
 
     /* Verify if there is a device that doesn't support snapshots and is writable */
     bs = NULL;
@@ -1160,11 +1162,12 @@ void do_savevm(Monitor *mon, const QDict *qdict)
         monitor_printf(mon, "Could not open VM state file\n");
         goto the_end;
     }
-    ret = qemu_savevm_state(f);
+    ret = qemu_savevm_state(f, &local_err);
     vm_state_size = qemu_ftell(f);
     qemu_fclose(f);
     if (ret < 0) {
-        monitor_printf(mon, "Error %d while writing VM\n", ret);
+        monitor_printf(mon, "%s\n", error_get_pretty(local_err));
+        error_free(local_err);
         goto the_end;
     }
 

scripts/qtest.py

+# QEMU qtest library
+#
+# Copyright (C) 2015 Red Hat Inc.
+#
+# Authors:
+#  Fam Zheng <famz@redhat.com>
+#
+# This work is licensed under the terms of the GNU GPL, version 2.  See
+# the COPYING file in the top-level directory.
+#
+# Based on qmp.py.
+#
+
+import errno
+import socket
+
+class QEMUQtestProtocol(object):
+    def __init__(self, address, server=False):
+        """
+        Create a QEMUQtestProtocol object.
+
+        @param address: QEMU address, can be either a unix socket path (string)
+                        or a tuple in the form ( address, port ) for a TCP
+                        connection
+        @param server: server mode, listens on the socket (bool)
+        @raise socket.error on socket connection errors
+        @note No connection is established, this is done by the connect() or
+              accept() methods
+        """
+        self._address = address
+        self._sock = self._get_sock()
+        if server:
+            self._sock.bind(self._address)
+            self._sock.listen(1)
+
+    def _get_sock(self):
+        if isinstance(self._address, tuple):
+            family = socket.AF_INET
+        else:
+            family = socket.AF_UNIX
+        return socket.socket(family, socket.SOCK_STREAM)
+
+    def connect(self):
+        """
+        Connect to the qtest socket.
+
+        @raise socket.error on socket connection errors
+        """
+        self._sock.connect(self._address)
+
+    def accept(self):
+        """
+        Await connection from QEMU.
+
+        @raise socket.error on socket connection errors
+        """
+        self._sock, _ = self._sock.accept()
+
+    def cmd(self, qtest_cmd):
+        """
+        Send a qtest command on the wire.
+
+        @param qtest_cmd: qtest command text to be sent
+        """
+        self._sock.sendall(qtest_cmd + "\n")
+
+    def close(self):
+        self._sock.close()
+
+    def settimeout(self, timeout):
+        self._sock.settimeout(timeout)

tests/Makefile

@@ -307,9 +307,10 @@ tests/test-mul64$(EXESUF): tests/test-mul64.o libqemuutil.a
 tests/test-bitops$(EXESUF): tests/test-bitops.o libqemuutil.a
 
 libqos-obj-y = tests/libqos/pci.o tests/libqos/fw_cfg.o tests/libqos/malloc.o
-libqos-obj-y += tests/libqos/i2c.o
+libqos-obj-y += tests/libqos/i2c.o tests/libqos/libqos.o
 libqos-pc-obj-y = $(libqos-obj-y) tests/libqos/pci-pc.o
-libqos-pc-obj-y += tests/libqos/malloc-pc.o
+libqos-pc-obj-y += tests/libqos/malloc-pc.o tests/libqos/libqos-pc.o
+libqos-pc-obj-y += tests/libqos/ahci.o
 libqos-omap-obj-y = $(libqos-obj-y) tests/libqos/i2c-omap.o
 libqos-virtio-obj-y = $(libqos-obj-y) $(libqos-pc-obj-y) tests/libqos/virtio.o tests/libqos/virtio-pci.o
 libqos-usb-obj-y = $(libqos-pc-obj-y) tests/libqos/usb.o

tests/libqos/libqos-pc.c

+#include "libqos/libqos-pc.h"
+#include "libqos/malloc-pc.h"
+
+static QOSOps qos_ops = {
+    .init_allocator = pc_alloc_init_flags,
+    .uninit_allocator = pc_alloc_uninit
+};
+
+QOSState *qtest_pc_boot(const char *cmdline_fmt, ...)
+{
+    QOSState *qs;
+    va_list ap;
+
+    va_start(ap, cmdline_fmt);
+    qs = qtest_vboot(&qos_ops, cmdline_fmt, ap);
+    va_end(ap);
+
+    return qs;
+}
+
+void qtest_pc_shutdown(QOSState *qs)
+{
+    return qtest_shutdown(qs);
+}

tests/libqos/libqos-pc.h

+#ifndef __libqos_pc_h
+#define __libqos_pc_h
+
+#include "libqos/libqos.h"
+
+QOSState *qtest_pc_boot(const char *cmdline_fmt, ...);
+void qtest_pc_shutdown(QOSState *qs);
+
+#endif

tests/libqos/libqos.c

+#include <stdio.h>
+#include <stdlib.h>
+#include <glib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/wait.h>
+
+#include "libqtest.h"
+#include "libqos/libqos.h"
+#include "libqos/pci.h"
+
+/*** Test Setup & Teardown ***/
+
+/**
+ * Launch QEMU with the given command line,
+ * and then set up interrupts and our guest malloc interface.
+ */
+QOSState *qtest_vboot(QOSOps *ops, const char *cmdline_fmt, va_list ap)
+{
+    char *cmdline;
+
+    struct QOSState *qs = g_malloc(sizeof(QOSState));
+
+    cmdline = g_strdup_vprintf(cmdline_fmt, ap);
+    qs->qts = qtest_start(cmdline);
+    qs->ops = ops;
+    qtest_irq_intercept_in(global_qtest, "ioapic");
+    if (ops && ops->init_allocator) {
+        qs->alloc = ops->init_allocator(ALLOC_NO_FLAGS);
+    }
+
+    g_free(cmdline);
+    return qs;
+}
+
+/**
+ * Launch QEMU with the given command line,
+ * and then set up interrupts and our guest malloc interface.
+ */
+QOSState *qtest_boot(QOSOps *ops, const char *cmdline_fmt, ...)
+{
+    QOSState *qs;
+    va_list ap;
+
+    va_start(ap, cmdline_fmt);
+    qs = qtest_vboot(ops, cmdline_fmt, ap);
+    va_end(ap);
+
+    return qs;
+}
+
+/**
+ * Tear down the QEMU instance.
+ */
+void qtest_shutdown(QOSState *qs)
+{
+    if (qs->alloc && qs->ops && qs->ops->uninit_allocator) {
+        qs->ops->uninit_allocator(qs->alloc);
+        qs->alloc = NULL;
+    }
+    qtest_quit(qs->qts);
+    g_free(qs);
+}

tests/libqos/libqos.h

+#ifndef __libqos_h
+#define __libqos_h
+
+#include "libqtest.h"
+#include "libqos/pci.h"
+#include "libqos/malloc-pc.h"
+
+typedef struct QOSOps {
+    QGuestAllocator *(*init_allocator)(QAllocOpts);
+    void (*uninit_allocator)(QGuestAllocator *);
+} QOSOps;
+
+typedef struct QOSState {
+    QTestState *qts;
+    QGuestAllocator *alloc;
+    QOSOps *ops;
+} QOSState;
+
+QOSState *qtest_vboot(QOSOps *ops, const char *cmdline_fmt, va_list ap);
+QOSState *qtest_boot(QOSOps *ops, const char *cmdline_fmt, ...);
+void qtest_shutdown(QOSState *qs);
+
+static inline uint64_t qmalloc(QOSState *q, size_t bytes)
+{
+    return guest_alloc(q->alloc, bytes);
+}
+
+static inline void qfree(QOSState *q, uint64_t addr)
+{
+    guest_free(q->alloc, addr);
+}
+
+#endif

tests/libqos/malloc-pc.c

@@ -32,31 +32,17 @@ void pc_alloc_uninit(QGuestAllocator *allocator)
 
 QGuestAllocator *pc_alloc_init_flags(QAllocOpts flags)
 {
-    QGuestAllocator *s = g_malloc0(sizeof(*s));
+    QGuestAllocator *s;
     uint64_t ram_size;
     QFWCFG *fw_cfg = pc_fw_cfg_init();
-    MemBlock *node;
-
-    s->opts = flags;
-    s->page_size = PAGE_SIZE;
 
     ram_size = qfw_cfg_get_u64(fw_cfg, FW_CFG_RAM_SIZE);
-
-    /* Start at 1MB */
-    s->start = 1 << 20;
-
-    /* Respect PCI hole */
-    s->end = MIN(ram_size, 0xE0000000);
+    s = alloc_init_flags(flags, 1 << 20, MIN(ram_size, 0xE0000000));
+    alloc_set_page_size(s, PAGE_SIZE);
 
     /* clean-up */
     g_free(fw_cfg);
 
-    QTAILQ_INIT(&s->used);
-    QTAILQ_INIT(&s->free);
-
-    node = mlist_new(s->start, s->end - s->start);
-    QTAILQ_INSERT_HEAD(&s->free, node, MLIST_ENTNAME);
-
     return s;
 }
 

tests/libqos/malloc.c

@@ -16,6 +16,26 @@
 #include <inttypes.h>
 #include <glib.h>
 
+typedef QTAILQ_HEAD(MemList, MemBlock) MemList;
+
+typedef struct MemBlock {
+    QTAILQ_ENTRY(MemBlock) MLIST_ENTNAME;
+    uint64_t size;
+    uint64_t addr;
+} MemBlock;
+
+struct QGuestAllocator {
+    QAllocOpts opts;
+    uint64_t start;
+    uint64_t end;
+    uint32_t page_size;
+
+    MemList used;
+    MemList free;
+};
+
+#define DEFAULT_PAGE_SIZE 4096
+
 static void mlist_delete(MemList *list, MemBlock *node)
 {
     g_assert(list && node);
@@ -103,6 +123,21 @@ static void mlist_coalesce(MemList *head, MemBlock *node)
     } while (merge);
 }
 
+static MemBlock *mlist_new(uint64_t addr, uint64_t size)
+{
+    MemBlock *block;
+
+    if (!size) {
+        return NULL;
+    }
+    block = g_malloc0(sizeof(MemBlock));
+
+    block->addr = addr;
+    block->size = size;
+
+    return block;
+}
+
 static uint64_t mlist_fulfill(QGuestAllocator *s, MemBlock *freenode,
                                                                 uint64_t size)
 {
@@ -187,21 +222,6 @@ static void mlist_free(QGuestAllocator *s, uint64_t addr)
     mlist_coalesce(&s->free, node);
 }
 
-MemBlock *mlist_new(uint64_t addr, uint64_t size)
-{
-    MemBlock *block;
-
-    if (!size) {
-        return NULL;
-    }
-    block = g_malloc0(sizeof(MemBlock));
-
-    block->addr = addr;
-    block->size = size;
-
-    return block;
-}
-
 /*
  * Mostly for valgrind happiness, but it does offer
  * a chokepoint for debugging guest memory leaks, too.
@@ -268,3 +288,44 @@ void guest_free(QGuestAllocator *allocator, uint64_t addr)
         mlist_check(allocator);
     }
 }
+
+QGuestAllocator *alloc_init(uint64_t start, uint64_t end)
+{
+    QGuestAllocator *s = g_malloc0(sizeof(*s));
+    MemBlock *node;
+
+    s->start = start;
+    s->end = end;
+
+    QTAILQ_INIT(&s->used);
+    QTAILQ_INIT(&s->free);
+
+    node = mlist_new(s->start, s->end - s->start);
+    QTAILQ_INSERT_HEAD(&s->free, node, MLIST_ENTNAME);
+
+    s->page_size = DEFAULT_PAGE_SIZE;
+
+    return s;
+}
+
+QGuestAllocator *alloc_init_flags(QAllocOpts opts,
+                                  uint64_t start, uint64_t end)
+{
+    QGuestAllocator *s = alloc_init(start, end);
+    s->opts = opts;
+    return s;
+}
+
+void alloc_set_page_size(QGuestAllocator *allocator, size_t page_size)
+{
+    /* Can't alter the page_size for an allocator in-use */
+    g_assert(QTAILQ_EMPTY(&allocator->used));
+
+    g_assert(is_power_of_2(page_size));
+    allocator->page_size = page_size;
+}
+
+void alloc_set_flags(QGuestAllocator *allocator, QAllocOpts opts)
+{
+    allocator->opts |= opts;
+}

tests/libqos/malloc.h

@@ -17,8 +17,6 @@
 #include <sys/types.h>
 #include "qemu/queue.h"
 
-#define MLIST_ENTNAME entries
-
 typedef enum {
     ALLOC_NO_FLAGS    = 0x00,
     ALLOC_LEAK_WARN   = 0x01,
@@ -26,28 +24,18 @@ typedef enum {
     ALLOC_PARANOID    = 0x04
 } QAllocOpts;
 
-typedef QTAILQ_HEAD(MemList, MemBlock) MemList;
-typedef struct MemBlock {
-    QTAILQ_ENTRY(MemBlock) MLIST_ENTNAME;
-    uint64_t size;
-    uint64_t addr;
-} MemBlock;
-
-typedef struct QGuestAllocator {
-    QAllocOpts opts;
-    uint64_t start;
-    uint64_t end;
-    uint32_t page_size;
+typedef struct QGuestAllocator QGuestAllocator;
 
-    MemList used;
-    MemList free;
-} QGuestAllocator;
-
-MemBlock *mlist_new(uint64_t addr, uint64_t size);
 void alloc_uninit(QGuestAllocator *allocator);
 
 /* Always returns page aligned values */
 uint64_t guest_alloc(QGuestAllocator *allocator, size_t size);
 void guest_free(QGuestAllocator *allocator, uint64_t addr);
 
+QGuestAllocator *alloc_init(uint64_t start, uint64_t end);
+QGuestAllocator *alloc_init_flags(QAllocOpts flags,
+                                  uint64_t start, uint64_t end);
+void alloc_set_page_size(QGuestAllocator *allocator, size_t page_size);
+void alloc_set_flags(QGuestAllocator *allocator, QAllocOpts opts);
+
 #endif

tests/qemu-iotests/016.out

-QA output created by 016
-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
-
-== reading at EOF ==
-read 512/512 bytes at offset 134217728
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-
-== reading far past EOF ==
-read 512/512 bytes at offset 268435456
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-
-== writing at EOF ==
-wrote 512/512 bytes at offset 134217728
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 134217728
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-
-== writing far past EOF ==
-wrote 512/512 bytes at offset 268435456
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 268435456
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-*** done

tests/qemu-iotests/051

@@ -93,6 +93,7 @@ echo
 run_qemu -drive file="$TEST_IMG",format=foo
 run_qemu -drive file="$TEST_IMG",driver=foo
 run_qemu -drive file="$TEST_IMG",driver=raw,format=qcow2
+run_qemu -drive file="$TEST_IMG",driver=qcow2,format=qcow2
 
 echo
 echo === Overriding backing file ===

tests/qemu-iotests/093.out

+..
+----------------------------------------------------------------------
+Ran 2 tests
+
+OK