Merge remote-tracking branch 'kwolf/for-anthony' into staging

12 files changed, 283 insertions, 633 deletions

diff --git a/block.c b/block.c
index e865fab27e..9873b57edd 100644
--- a/block.c
+++ b/block.c
@@ -44,6 +44,8 @@
 #include <windows.h>
 #endif
 
+#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
+
 static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load);
 static BlockDriverAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
@@ -55,16 +57,6 @@ static BlockDriverAIOCB *bdrv_aio_flush_em(BlockDriverState *bs,
         BlockDriverCompletionFunc *cb, void *opaque);
 static BlockDriverAIOCB *bdrv_aio_noop_em(BlockDriverState *bs,
         BlockDriverCompletionFunc *cb, void *opaque);
-static int bdrv_read_em(BlockDriverState *bs, int64_t sector_num,
-                        uint8_t *buf, int nb_sectors);
-static int bdrv_write_em(BlockDriverState *bs, int64_t sector_num,
-                         const uint8_t *buf, int nb_sectors);
-static BlockDriverAIOCB *bdrv_co_aio_readv_em(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque);
-static BlockDriverAIOCB *bdrv_co_aio_writev_em(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque);
 static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
                                          int64_t sector_num, int nb_sectors,
                                          QEMUIOVector *iov);
@@ -72,6 +64,18 @@ static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
                                          int64_t sector_num, int nb_sectors,
                                          QEMUIOVector *iov);
 static int coroutine_fn bdrv_co_flush_em(BlockDriverState *bs);
+static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
+                                               int64_t sector_num,
+                                               QEMUIOVector *qiov,
+                                               int nb_sectors,
+                                               BlockDriverCompletionFunc *cb,
+                                               void *opaque,
+                                               bool is_write);
+static void coroutine_fn bdrv_co_do_rw(void *opaque);
 
 static QTAILQ_HEAD(, BlockDriverState) bdrv_states =
     QTAILQ_HEAD_INITIALIZER(bdrv_states);
@@ -184,24 +188,18 @@ void path_combine(char *dest, int dest_size,
 
 void bdrv_register(BlockDriver *bdrv)
 {
-    if (bdrv->bdrv_co_readv) {
-        /* Emulate AIO by coroutines, and sync by AIO */
-        bdrv->bdrv_aio_readv = bdrv_co_aio_readv_em;
-        bdrv->bdrv_aio_writev = bdrv_co_aio_writev_em;
-        bdrv->bdrv_read = bdrv_read_em;
-        bdrv->bdrv_write = bdrv_write_em;
-     } else {
+    /* Block drivers without coroutine functions need emulation */
+    if (!bdrv->bdrv_co_readv) {
         bdrv->bdrv_co_readv = bdrv_co_readv_em;
         bdrv->bdrv_co_writev = bdrv_co_writev_em;
 
+        /* bdrv_co_readv_em()/brdv_co_writev_em() work in terms of aio, so if
+         * the block driver lacks aio we need to emulate that too.
+         */
         if (!bdrv->bdrv_aio_readv) {
             /* add AIO emulation layer */
             bdrv->bdrv_aio_readv = bdrv_aio_readv_em;
             bdrv->bdrv_aio_writev = bdrv_aio_writev_em;
-        } else if (!bdrv->bdrv_read) {
-            /* add synchronous IO emulation layer */
-            bdrv->bdrv_read = bdrv_read_em;
-            bdrv->bdrv_write = bdrv_write_em;
         }
     }
 
@@ -221,6 +219,7 @@ BlockDriverState *bdrv_new(const char *device_name)
     if (device_name[0] != '\0') {
         QTAILQ_INSERT_TAIL(&bdrv_states, bs, list);
     }
+    bdrv_iostatus_disable(bs);
     return bs;
 }
 
@@ -772,6 +771,7 @@ int bdrv_attach_dev(BlockDriverState *bs, void *dev)
         return -EBUSY;
     }
     bs->dev = dev;
+    bdrv_iostatus_reset(bs);
     return 0;
 }
 
@@ -1027,41 +1027,74 @@ static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num,
                                    nb_sectors * BDRV_SECTOR_SIZE);
 }
 
-static inline bool bdrv_has_async_rw(BlockDriver *drv)
-{
-    return drv->bdrv_co_readv != bdrv_co_readv_em
-        || drv->bdrv_aio_readv != bdrv_aio_readv_em;
-}
-
 static inline bool bdrv_has_async_flush(BlockDriver *drv)
 {
     return drv->bdrv_aio_flush != bdrv_aio_flush_em;
 }
 
-/* return < 0 if error. See bdrv_write() for the return codes */
-int bdrv_read(BlockDriverState *bs, int64_t sector_num,
-              uint8_t *buf, int nb_sectors)
+typedef struct RwCo {
+    BlockDriverState *bs;
+    int64_t sector_num;
+    int nb_sectors;
+    QEMUIOVector *qiov;
+    bool is_write;
+    int ret;
+} RwCo;
+
+static void coroutine_fn bdrv_rw_co_entry(void *opaque)
 {
-    BlockDriver *drv = bs->drv;
+    RwCo *rwco = opaque;
 
-    if (!drv)
-        return -ENOMEDIUM;
+    if (!rwco->is_write) {
+        rwco->ret = bdrv_co_do_readv(rwco->bs, rwco->sector_num,
+                                     rwco->nb_sectors, rwco->qiov);
+    } else {
+        rwco->ret = bdrv_co_do_writev(rwco->bs, rwco->sector_num,
+                                      rwco->nb_sectors, rwco->qiov);
+    }
+}
 
-    if (bdrv_has_async_rw(drv) && qemu_in_coroutine()) {
-        QEMUIOVector qiov;
-        struct iovec iov = {
-            .iov_base = (void *)buf,
-            .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
-        };
+/*
+ * Process a synchronous request using coroutines
+ */
+static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
+                      int nb_sectors, bool is_write)
+{
+    QEMUIOVector qiov;
+    struct iovec iov = {
+        .iov_base = (void *)buf,
+        .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
+    };
+    Coroutine *co;
+    RwCo rwco = {
+        .bs = bs,
+        .sector_num = sector_num,
+        .nb_sectors = nb_sectors,
+        .qiov = &qiov,
+        .is_write = is_write,
+        .ret = NOT_DONE,
+    };
 
-        qemu_iovec_init_external(&qiov, &iov, 1);
-        return bdrv_co_readv(bs, sector_num, nb_sectors, &qiov);
-    }
+    qemu_iovec_init_external(&qiov, &iov, 1);
 
-    if (bdrv_check_request(bs, sector_num, nb_sectors))
-        return -EIO;
+    if (qemu_in_coroutine()) {
+        /* Fast-path if already in coroutine context */
+        bdrv_rw_co_entry(&rwco);
+    } else {
+        co = qemu_coroutine_create(bdrv_rw_co_entry);
+        qemu_coroutine_enter(co, &rwco);
+        while (rwco.ret == NOT_DONE) {
+            qemu_aio_wait();
+        }
+    }
+    return rwco.ret;
+}
 
-    return drv->bdrv_read(bs, sector_num, buf, nb_sectors);
+/* return < 0 if error. See bdrv_write() for the return codes */
+int bdrv_read(BlockDriverState *bs, int64_t sector_num,
+              uint8_t *buf, int nb_sectors)
+{
+    return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false);
 }
 
 static void set_dirty_bitmap(BlockDriverState *bs, int64_t sector_num,
@@ -1101,36 +1134,7 @@ static void set_dirty_bitmap(BlockDriverState *bs, int64_t sector_num,
 int bdrv_write(BlockDriverState *bs, int64_t sector_num,
                const uint8_t *buf, int nb_sectors)
 {
-    BlockDriver *drv = bs->drv;
-
-    if (!bs->drv)
-        return -ENOMEDIUM;
-
-    if (bdrv_has_async_rw(drv) && qemu_in_coroutine()) {
-        QEMUIOVector qiov;
-        struct iovec iov = {
-            .iov_base = (void *)buf,
-            .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
-        };
-
-        qemu_iovec_init_external(&qiov, &iov, 1);
-        return bdrv_co_writev(bs, sector_num, nb_sectors, &qiov);
-    }
-
-    if (bs->read_only)
-        return -EACCES;
-    if (bdrv_check_request(bs, sector_num, nb_sectors))
-        return -EIO;
-
-    if (bs->dirty_bitmap) {
-        set_dirty_bitmap(bs, sector_num, nb_sectors, 1);
-    }
-
-    if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
-        bs->wr_highest_sector = sector_num + nb_sectors - 1;
-    }
-
-    return drv->bdrv_write(bs, sector_num, buf, nb_sectors);
+    return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true);
 }
 
 int bdrv_pread(BlockDriverState *bs, int64_t offset,
@@ -1251,13 +1255,14 @@ int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
     return 0;
 }
 
-int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
-    int nb_sectors, QEMUIOVector *qiov)
+/*
+ * Handle a read request in coroutine context
+ */
+static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
 {
     BlockDriver *drv = bs->drv;
 
-    trace_bdrv_co_readv(bs, sector_num, nb_sectors);
-
     if (!drv) {
         return -ENOMEDIUM;
     }
@@ -1268,12 +1273,22 @@ int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
     return drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
 }
 
-int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
+int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
     int nb_sectors, QEMUIOVector *qiov)
 {
-    BlockDriver *drv = bs->drv;
+    trace_bdrv_co_readv(bs, sector_num, nb_sectors);
 
-    trace_bdrv_co_writev(bs, sector_num, nb_sectors);
+    return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov);
+}
+
+/*
+ * Handle a write request in coroutine context
+ */
+static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+    BlockDriver *drv = bs->drv;
+    int ret;
 
     if (!bs->drv) {
         return -ENOMEDIUM;
@@ -1285,6 +1300,8 @@ int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
         return -EIO;
     }
 
+    ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
+
     if (bs->dirty_bitmap) {
         set_dirty_bitmap(bs, sector_num, nb_sectors, 1);
     }
@@ -1293,7 +1310,15 @@ int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
         bs->wr_highest_sector = sector_num + nb_sectors - 1;
     }
 
-    return drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
+    return ret;
+}
+
+int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
+    int nb_sectors, QEMUIOVector *qiov)
+{
+    trace_bdrv_co_writev(bs, sector_num, nb_sectors);
+
+    return bdrv_co_do_writev(bs, sector_num, nb_sectors, qiov);
 }
 
 /**
@@ -1866,6 +1891,11 @@ static void bdrv_print_dict(QObject *obj, void *opaque)
         monitor_printf(mon, " tray-open=%d",
                        qdict_get_bool(bs_dict, "tray-open"));
     }
+
+    if (qdict_haskey(bs_dict, "io-status")) {
+        monitor_printf(mon, " io-status=%s", qdict_get_str(bs_dict, "io-status"));
+    }
+
     if (qdict_haskey(bs_dict, "inserted")) {
         QDict *qdict = qobject_to_qdict(qdict_get(bs_dict, "inserted"));
 
@@ -1891,6 +1921,12 @@ void bdrv_info_print(Monitor *mon, const QObject *data)
     qlist_iter(qobject_to_qlist(data), bdrv_print_dict, mon);
 }
 
+static const char *const io_status_name[BDRV_IOS_MAX] = {
+    [BDRV_IOS_OK] = "ok",
+    [BDRV_IOS_FAILED] = "failed",
+    [BDRV_IOS_ENOSPC] = "nospace",
+};
+
 void bdrv_info(Monitor *mon, QObject **ret_data)
 {
     QList *bs_list;
@@ -1913,6 +1949,12 @@ void bdrv_info(Monitor *mon, QObject **ret_data)
             qdict_put(bs_dict, "tray-open",
                       qbool_from_int(bdrv_dev_is_tray_open(bs)));
         }
+
+        if (bdrv_iostatus_is_enabled(bs)) {
+            qdict_put(bs_dict, "io-status",
+                      qstring_from_str(io_status_name[bs->iostatus]));
+        }
+
         if (bs->drv) {
             QObject *obj;
 
@@ -2314,89 +2356,20 @@ BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
                                  QEMUIOVector *qiov, int nb_sectors,
                                  BlockDriverCompletionFunc *cb, void *opaque)
 {
-    BlockDriver *drv = bs->drv;
-
     trace_bdrv_aio_readv(bs, sector_num, nb_sectors, opaque);
 
-    if (!drv)
-        return NULL;
-    if (bdrv_check_request(bs, sector_num, nb_sectors))
-        return NULL;
-
-    return drv->bdrv_aio_readv(bs, sector_num, qiov, nb_sectors,
-                               cb, opaque);
-}
-
-typedef struct BlockCompleteData {
-    BlockDriverCompletionFunc *cb;
-    void *opaque;
-    BlockDriverState *bs;
-    int64_t sector_num;
-    int nb_sectors;
-} BlockCompleteData;
-
-static void block_complete_cb(void *opaque, int ret)
-{
-    BlockCompleteData *b = opaque;
-
-    if (b->bs->dirty_bitmap) {
-        set_dirty_bitmap(b->bs, b->sector_num, b->nb_sectors, 1);
-    }
-    b->cb(b->opaque, ret);
-    g_free(b);
-}
-
-static BlockCompleteData *blk_dirty_cb_alloc(BlockDriverState *bs,
-                                             int64_t sector_num,
-                                             int nb_sectors,
-                                             BlockDriverCompletionFunc *cb,
-                                             void *opaque)
-{
-    BlockCompleteData *blkdata = g_malloc0(sizeof(BlockCompleteData));
-
-    blkdata->bs = bs;
-    blkdata->cb = cb;
-    blkdata->opaque = opaque;
-    blkdata->sector_num = sector_num;
-    blkdata->nb_sectors = nb_sectors;
-
-    return blkdata;
+    return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors,
+                                 cb, opaque, false);
 }
 
 BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
                                   QEMUIOVector *qiov, int nb_sectors,
                                   BlockDriverCompletionFunc *cb, void *opaque)
 {
-    BlockDriver *drv = bs->drv;
-    BlockDriverAIOCB *ret;
-    BlockCompleteData *blk_cb_data;
-
     trace_bdrv_aio_writev(bs, sector_num, nb_sectors, opaque);
 
-    if (!drv)
-        return NULL;
-    if (bs->read_only)
-        return NULL;
-    if (bdrv_check_request(bs, sector_num, nb_sectors))
-        return NULL;
-
-    if (bs->dirty_bitmap) {
-        blk_cb_data = blk_dirty_cb_alloc(bs, sector_num, nb_sectors, cb,
-                                         opaque);
-        cb = &block_complete_cb;
-        opaque = blk_cb_data;
-    }
-
-    ret = drv->bdrv_aio_writev(bs, sector_num, qiov, nb_sectors,
-                               cb, opaque);
-
-    if (ret) {
-        if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
-            bs->wr_highest_sector = sector_num + nb_sectors - 1;
-        }
-    }
-
-    return ret;
+    return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors,
+                                 cb, opaque, true);
 }
 
 
@@ -2720,9 +2693,9 @@ static BlockDriverAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
 
     if (is_write) {
         qemu_iovec_to_buffer(acb->qiov, acb->bounce);
-        acb->ret = bdrv_write(bs, sector_num, acb->bounce, nb_sectors);
+        acb->ret = bs->drv->bdrv_write(bs, sector_num, acb->bounce, nb_sectors);
     } else {
-        acb->ret = bdrv_read(bs, sector_num, acb->bounce, nb_sectors);
+        acb->ret = bs->drv->bdrv_read(bs, sector_num, acb->bounce, nb_sectors);
     }
 
     qemu_bh_schedule(acb->bh);
@@ -2771,16 +2744,17 @@ static void bdrv_co_rw_bh(void *opaque)
     qemu_aio_release(acb);
 }
 
-static void coroutine_fn bdrv_co_rw(void *opaque)
+/* Invoke bdrv_co_do_readv/bdrv_co_do_writev */
+static void coroutine_fn bdrv_co_do_rw(void *opaque)
 {
     BlockDriverAIOCBCoroutine *acb = opaque;
     BlockDriverState *bs = acb->common.bs;
 
     if (!acb->is_write) {
-        acb->req.error = bs->drv->bdrv_co_readv(bs, acb->req.sector,
+        acb->req.error = bdrv_co_do_readv(bs, acb->req.sector,
             acb->req.nb_sectors, acb->req.qiov);
     } else {
-        acb->req.error = bs->drv->bdrv_co_writev(bs, acb->req.sector,
+        acb->req.error = bdrv_co_do_writev(bs, acb->req.sector,
             acb->req.nb_sectors, acb->req.qiov);
     }
 
@@ -2805,28 +2779,12 @@ static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
     acb->req.qiov = qiov;
     acb->is_write = is_write;
 
-    co = qemu_coroutine_create(bdrv_co_rw);
+    co = qemu_coroutine_create(bdrv_co_do_rw);
     qemu_coroutine_enter(co, acb);
 
     return &acb->common;
 }
 
-static BlockDriverAIOCB *bdrv_co_aio_readv_em(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque,
-                                 false);
-}
-
-static BlockDriverAIOCB *bdrv_co_aio_writev_em(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque,
-                                 true);
-}
-
 static BlockDriverAIOCB *bdrv_aio_flush_em(BlockDriverState *bs,
         BlockDriverCompletionFunc *cb, void *opaque)
 {
@@ -2865,70 +2823,6 @@ static BlockDriverAIOCB *bdrv_aio_noop_em(BlockDriverState *bs,
     return &acb->common;
 }
 
-/**************************************************************/
-/* sync block device emulation */
-
-static void bdrv_rw_em_cb(void *opaque, int ret)
-{
-    *(int *)opaque = ret;
-}
-
-#define NOT_DONE 0x7fffffff
-
-static int bdrv_read_em(BlockDriverState *bs, int64_t sector_num,
-                        uint8_t *buf, int nb_sectors)
-{
-    int async_ret;
-    BlockDriverAIOCB *acb;
-    struct iovec iov;
-    QEMUIOVector qiov;
-
-    async_ret = NOT_DONE;
-    iov.iov_base = (void *)buf;
-    iov.iov_len = nb_sectors * BDRV_SECTOR_SIZE;
-    qemu_iovec_init_external(&qiov, &iov, 1);
-    acb = bdrv_aio_readv(bs, sector_num, &qiov, nb_sectors,
-        bdrv_rw_em_cb, &async_ret);
-    if (acb == NULL) {
-        async_ret = -1;
-        goto fail;
-    }
-
-    while (async_ret == NOT_DONE) {
-        qemu_aio_wait();
-    }
-
-
-fail:
-    return async_ret;
-}
-
-static int bdrv_write_em(BlockDriverState *bs, int64_t sector_num,
-                         const uint8_t *buf, int nb_sectors)
-{
-    int async_ret;
-    BlockDriverAIOCB *acb;
-    struct iovec iov;
-    QEMUIOVector qiov;
-
-    async_ret = NOT_DONE;
-    iov.iov_base = (void *)buf;
-    iov.iov_len = nb_sectors * BDRV_SECTOR_SIZE;
-    qemu_iovec_init_external(&qiov, &iov, 1);
-    acb = bdrv_aio_writev(bs, sector_num, &qiov, nb_sectors,
-        bdrv_rw_em_cb, &async_ret);
-    if (acb == NULL) {
-        async_ret = -1;
-        goto fail;
-    }
-    while (async_ret == NOT_DONE) {
-        qemu_aio_wait();
-    }
-
-fail:
-    return async_ret;
-}
-
 void bdrv_init(void)
 {
     module_call_init(MODULE_INIT_BLOCK);
@@ -2992,11 +2886,11 @@ static int coroutine_fn bdrv_co_io_em(BlockDriverState *bs, int64_t sector_num,
     BlockDriverAIOCB *acb;
 
     if (is_write) {
-        acb = bdrv_aio_writev(bs, sector_num, iov, nb_sectors,
-                              bdrv_co_io_em_complete, &co);
+        acb = bs->drv->bdrv_aio_writev(bs, sector_num, iov, nb_sectors,
+                                       bdrv_co_io_em_complete, &co);
     } else {
-        acb = bdrv_aio_readv(bs, sector_num, iov, nb_sectors,
-                             bdrv_co_io_em_complete, &co);
+        acb = bs->drv->bdrv_aio_readv(bs, sector_num, iov, nb_sectors,
+                                      bdrv_co_io_em_complete, &co);
     }
 
     trace_bdrv_co_io_em(bs, sector_num, nb_sectors, is_write, acb);
@@ -3183,6 +3077,44 @@ int bdrv_in_use(BlockDriverState *bs)
     return bs->in_use;
 }
 
+void bdrv_iostatus_enable(BlockDriverState *bs)
+{
+    bs->iostatus = BDRV_IOS_OK;
+}
+
+/* The I/O status is only enabled if the drive explicitly
+ * enables it _and_ the VM is configured to stop on errors */
+bool bdrv_iostatus_is_enabled(const BlockDriverState *bs)
+{
+    return (bs->iostatus != BDRV_IOS_INVAL &&
+           (bs->on_write_error == BLOCK_ERR_STOP_ENOSPC ||
+            bs->on_write_error == BLOCK_ERR_STOP_ANY    ||
+            bs->on_read_error == BLOCK_ERR_STOP_ANY));
+}
+
+void bdrv_iostatus_disable(BlockDriverState *bs)
+{
+    bs->iostatus = BDRV_IOS_INVAL;
+}
+
+void bdrv_iostatus_reset(BlockDriverState *bs)
+{
+    if (bdrv_iostatus_is_enabled(bs)) {
+        bs->iostatus = BDRV_IOS_OK;
+    }
+}
+
+/* XXX: Today this is set by device models because it makes the implementation
+   quite simple. However, the block layer knows about the error, so it's
+   possible to implement this without device models being involved */
+void bdrv_iostatus_set_err(BlockDriverState *bs, int error)
+{
+    if (bdrv_iostatus_is_enabled(bs) && bs->iostatus == BDRV_IOS_OK) {
+        assert(error >= 0);
+        bs->iostatus = error == ENOSPC ? BDRV_IOS_ENOSPC : BDRV_IOS_FAILED;
+    }
+}
+
 void
 bdrv_acct_start(BlockDriverState *bs, BlockAcctCookie *cookie, int64_t bytes,
         enum BlockAcctType type)
diff --git a/block.h b/block.h
index 16bfa0a3d6..e77988e49c 100644
--- a/block.h
+++ b/block.h
@@ -77,6 +77,16 @@ typedef enum {
     BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
 } BlockMonEventAction;
 
+typedef enum {
+    BDRV_IOS_INVAL, BDRV_IOS_OK, BDRV_IOS_FAILED, BDRV_IOS_ENOSPC,
+    BDRV_IOS_MAX
+} BlockIOStatus;
+
+void bdrv_iostatus_enable(BlockDriverState *bs);
+void bdrv_iostatus_reset(BlockDriverState *bs);
+void bdrv_iostatus_disable(BlockDriverState *bs);
+bool bdrv_iostatus_is_enabled(const BlockDriverState *bs);
+void bdrv_iostatus_set_err(BlockDriverState *bs, int error);
 void bdrv_mon_event(const BlockDriverState *bdrv,
                     BlockMonEventAction action, int is_read);
 void bdrv_info_print(Monitor *mon, const QObject *data);
diff --git a/block/raw-posix.c b/block/raw-posix.c
index 305998ddb3..c7f5544edd 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -297,273 +297,6 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 */
 
 /*
- * offset and count are in bytes, but must be multiples of 512 for files
- * opened with O_DIRECT. buf must be aligned to 512 bytes then.
- *
- * This function may be called without alignment if the caller ensures
- * that O_DIRECT is not in effect.
- */
-static int raw_pread_aligned(BlockDriverState *bs, int64_t offset,
-                     uint8_t *buf, int count)
-{
-    BDRVRawState *s = bs->opaque;
-    int ret;
-
-    ret = fd_open(bs);
-    if (ret < 0)
-        return ret;
-
-    ret = pread(s->fd, buf, count, offset);
-    if (ret == count)
-        return ret;
-
-    /* Allow reads beyond the end (needed for pwrite) */
-    if ((ret == 0) && bs->growable) {
-        int64_t size = raw_getlength(bs);
-        if (offset >= size) {
-            memset(buf, 0, count);
-            return count;
-        }
-    }
-
-    DEBUG_BLOCK_PRINT("raw_pread(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
-                      "] read failed %d : %d = %s\n",
-                      s->fd, bs->filename, offset, buf, count,
-                      bs->total_sectors, ret, errno, strerror(errno));
-
-    /* Try harder for CDrom. */
-    if (s->type != FTYPE_FILE) {
-        ret = pread(s->fd, buf, count, offset);
-        if (ret == count)
-            return ret;
-        ret = pread(s->fd, buf, count, offset);
-        if (ret == count)
-            return ret;
-
-        DEBUG_BLOCK_PRINT("raw_pread(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
-                          "] retry read failed %d : %d = %s\n",
-                          s->fd, bs->filename, offset, buf, count,
-                          bs->total_sectors, ret, errno, strerror(errno));
-    }
-
-    return  (ret < 0) ? -errno : ret;
-}
-
-/*
- * offset and count are in bytes, but must be multiples of the sector size
- * for files opened with O_DIRECT. buf must be aligned to sector size bytes
- * then.
- *
- * This function may be called without alignment if the caller ensures
- * that O_DIRECT is not in effect.
- */
-static int raw_pwrite_aligned(BlockDriverState *bs, int64_t offset,
-                      const uint8_t *buf, int count)
-{
-    BDRVRawState *s = bs->opaque;
-    int ret;
-
-    ret = fd_open(bs);
-    if (ret < 0)
-        return -errno;
-
-    ret = pwrite(s->fd, buf, count, offset);
-    if (ret == count)
-        return ret;
-
-    DEBUG_BLOCK_PRINT("raw_pwrite(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
-                      "] write failed %d : %d = %s\n",
-                      s->fd, bs->filename, offset, buf, count,
-                      bs->total_sectors, ret, errno, strerror(errno));
-
-    return  (ret < 0) ? -errno : ret;
-}
-
-
-/*
- * offset and count are in bytes and possibly not aligned. For files opened
- * with O_DIRECT, necessary alignments are ensured before calling
- * raw_pread_aligned to do the actual read.
- */
-static int raw_pread(BlockDriverState *bs, int64_t offset,
-                     uint8_t *buf, int count)
-{
-    BDRVRawState *s = bs->opaque;
-    unsigned sector_mask = bs->buffer_alignment - 1;
-    int size, ret, shift, sum;
-
-    sum = 0;
-
-    if (s->aligned_buf != NULL)  {
-
-        if (offset & sector_mask) {
-            /* align offset on a sector size bytes boundary */
-
-            shift = offset & sector_mask;
-            size = (shift + count + sector_mask) & ~sector_mask;
-            if (size > s->aligned_buf_size)
-                size = s->aligned_buf_size;
-            ret = raw_pread_aligned(bs, offset - shift, s->aligned_buf, size);
-            if (ret < 0)
-                return ret;
-
-            size = bs->buffer_alignment - shift;
-            if (size > count)
-                size = count;
-            memcpy(buf, s->aligned_buf + shift, size);
-
-            buf += size;
-            offset += size;
-            count -= size;
-            sum += size;
-
-            if (count == 0)
-                return sum;
-        }
-        if (count & sector_mask || (uintptr_t) buf & sector_mask) {
-
-            /* read on aligned buffer */
-
-            while (count) {
-
-                size = (count + sector_mask) & ~sector_mask;
-                if (size > s->aligned_buf_size)
-                    size = s->aligned_buf_size;
-
-                ret = raw_pread_aligned(bs, offset, s->aligned_buf, size);
-                if (ret < 0) {
-                    return ret;
-                } else if (ret == 0) {
-                    fprintf(stderr, "raw_pread: read beyond end of file\n");
-                    abort();
-                }
-
-                size = ret;
-                if (size > count)
-                    size = count;
-
-                memcpy(buf, s->aligned_buf, size);
-
-                buf += size;
-                offset += size;
-                count -= size;
-                sum += size;
-            }
-
-            return sum;
-        }
-    }
-
-    return raw_pread_aligned(bs, offset, buf, count) + sum;
-}
-
-static int raw_read(BlockDriverState *bs, int64_t sector_num,
-                    uint8_t *buf, int nb_sectors)
-{
-    int ret;
-
-    ret = raw_pread(bs, sector_num * BDRV_SECTOR_SIZE, buf,
-                    nb_sectors * BDRV_SECTOR_SIZE);
-    if (ret == (nb_sectors * BDRV_SECTOR_SIZE))
-        ret = 0;
-    return ret;
-}
-
-/*
- * offset and count are in bytes and possibly not aligned. For files opened
- * with O_DIRECT, necessary alignments are ensured before calling
- * raw_pwrite_aligned to do the actual write.
- */
-static int raw_pwrite(BlockDriverState *bs, int64_t offset,
-                      const uint8_t *buf, int count)
-{
-    BDRVRawState *s = bs->opaque;
-    unsigned sector_mask = bs->buffer_alignment - 1;
-    int size, ret, shift, sum;
-
-    sum = 0;
-
-    if (s->aligned_buf != NULL) {
-
-        if (offset & sector_mask) {
-            /* align offset on a sector size bytes boundary */
-            shift = offset & sector_mask;
-            ret = raw_pread_aligned(bs, offset - shift, s->aligned_buf,
-                                    bs->buffer_alignment);
-            if (ret < 0)
-                return ret;
-
-            size = bs->buffer_alignment - shift;
-            if (size > count)
-                size = count;
-            memcpy(s->aligned_buf + shift, buf, size);
-
-            ret = raw_pwrite_aligned(bs, offset - shift, s->aligned_buf,
-                                     bs->buffer_alignment);
-            if (ret < 0)
-                return ret;
-
-            buf += size;
-            offset += size;
-            count -= size;
-            sum += size;
-
-            if (count == 0)
-                return sum;
-        }
-        if (count & sector_mask || (uintptr_t) buf & sector_mask) {
-
-            while ((size = (count & ~sector_mask)) != 0) {
-
-                if (size > s->aligned_buf_size)
-                    size = s->aligned_buf_size;
-
-                memcpy(s->aligned_buf, buf, size);
-
-                ret = raw_pwrite_aligned(bs, offset, s->aligned_buf, size);
-                if (ret < 0)
-                    return ret;
-
-                buf += ret;
-                offset += ret;
-                count -= ret;
-                sum += ret;
-            }
-            /* here, count < sector_size because (count & ~sector_mask) == 0 */
-            if (count) {
-                ret = raw_pread_aligned(bs, offset, s->aligned_buf,
-                                     bs->buffer_alignment);
-                if (ret < 0)
-                    return ret;
-                 memcpy(s->aligned_buf, buf, count);
-
-                 ret = raw_pwrite_aligned(bs, offset, s->aligned_buf,
-                                     bs->buffer_alignment);
-                 if (ret < 0)
-                     return ret;
-                 if (count < ret)
-                     ret = count;
-
-                 sum += ret;
-            }
-            return sum;
-        }
-    }
-    return raw_pwrite_aligned(bs, offset, buf, count) + sum;
-}
-
-static int raw_write(BlockDriverState *bs, int64_t sector_num,
-                     const uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    ret = raw_pwrite(bs, sector_num * BDRV_SECTOR_SIZE, buf,
-                     nb_sectors * BDRV_SECTOR_SIZE);
-    if (ret == (nb_sectors * BDRV_SECTOR_SIZE))
-        ret = 0;
-    return ret;
-}
-
-/*
  * Check if all memory in this vector is sector aligned.
  */
 static int qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
@@ -649,10 +382,24 @@ static void raw_close(BlockDriverState *bs)
 static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
     BDRVRawState *s = bs->opaque;
-    if (s->type != FTYPE_FILE)
-        return -ENOTSUP;
-    if (ftruncate(s->fd, offset) < 0)
+    struct stat st;
+
+    if (fstat(s->fd, &st)) {
         return -errno;
+    }
+
+    if (S_ISREG(st.st_mode)) {
+        if (ftruncate(s->fd, offset) < 0) {
+            return -errno;
+        }
+    } else if (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode)) {
+       if (offset > raw_getlength(bs)) {
+           return -EINVAL;
+       }
+    } else {
+        return -ENOTSUP;
+    }
+
     return 0;
 }
 
@@ -896,8 +643,6 @@ static BlockDriver bdrv_file = {
     .instance_size = sizeof(BDRVRawState),
     .bdrv_probe = NULL, /* no probe for protocols */
     .bdrv_file_open = raw_open,
-    .bdrv_read = raw_read,
-    .bdrv_write = raw_write,
     .bdrv_close = raw_close,
     .bdrv_create = raw_create,
     .bdrv_flush = raw_flush,
@@ -1176,8 +921,7 @@ static BlockDriver bdrv_host_device = {
     .bdrv_aio_writev	= raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_read          = raw_read,
-    .bdrv_write         = raw_write,
+    .bdrv_truncate      = raw_truncate,
     .bdrv_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
@@ -1297,8 +1041,7 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_read          = raw_read,
-    .bdrv_write         = raw_write,
+    .bdrv_truncate      = raw_truncate,
     .bdrv_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
@@ -1398,8 +1141,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_read          = raw_read,
-    .bdrv_write         = raw_write,
+    .bdrv_truncate      = raw_truncate,
     .bdrv_getlength     = raw_getlength,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
@@ -1519,8 +1261,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_read          = raw_read,
-    .bdrv_write         = raw_write,
+    .bdrv_truncate      = raw_truncate,
     .bdrv_getlength     = raw_getlength,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
diff --git a/block/raw.c b/block/raw.c
index 63cf2d3bf3..5ca606b68a 100644
--- a/block/raw.c
+++ b/block/raw.c
@@ -9,30 +9,16 @@ static int raw_open(BlockDriverState *bs, int flags)
     return 0;
 }
 
-static int raw_read(BlockDriverState *bs, int64_t sector_num,
-                    uint8_t *buf, int nb_sectors)
+static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
+                                     int nb_sectors, QEMUIOVector *qiov)
 {
-    return bdrv_read(bs->file, sector_num, buf, nb_sectors);
+    return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov);
 }
 
-static int raw_write(BlockDriverState *bs, int64_t sector_num,
-                     const uint8_t *buf, int nb_sectors)
+static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
+                                      int nb_sectors, QEMUIOVector *qiov)
 {
-    return bdrv_write(bs->file, sector_num, buf, nb_sectors);
-}
-
-static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
-    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-    BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
-}
-
-static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
-    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-    BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    return bdrv_co_writev(bs->file, sector_num, nb_sectors, qiov);
 }
 
 static void raw_close(BlockDriverState *bs)
@@ -129,15 +115,13 @@ static BlockDriver bdrv_raw = {
 
     .bdrv_open          = raw_open,
     .bdrv_close         = raw_close,
-    .bdrv_read          = raw_read,
-    .bdrv_write         = raw_write,
+    .bdrv_co_readv      = raw_co_readv,
+    .bdrv_co_writev     = raw_co_writev,
     .bdrv_flush         = raw_flush,
     .bdrv_probe         = raw_probe,
     .bdrv_getlength     = raw_getlength,
     .bdrv_truncate      = raw_truncate,
 
-    .bdrv_aio_readv     = raw_aio_readv,
-    .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush     = raw_aio_flush,
     .bdrv_discard       = raw_discard,
 
diff --git a/block/vvfat.c b/block/vvfat.c
index f567c9adb9..7e9e35a3a3 100644
--- a/block/vvfat.c
+++ b/block/vvfat.c
@@ -86,8 +86,7 @@ static inline void array_init(array_t* array,unsigned int item_size)
 
 static inline void array_free(array_t* array)
 {
-    if(array->pointer)
-        free(array->pointer);
+    g_free(array->pointer);
     array->size=array->next=0;
 }
 
@@ -169,7 +168,7 @@ static inline int array_roll(array_t* array,int index_to,int index_from,int coun
 
     memcpy(to,buf,is*count);
 
-    free(buf);
+    g_free(buf);
 
     return 0;
 }
@@ -732,7 +731,7 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
 	snprintf(buffer,length,"%s/%s",dirname,entry->d_name);
 
 	if(stat(buffer,&st)<0) {
-	    free(buffer);
+            g_free(buffer);
             continue;
 	}
 
@@ -755,7 +754,7 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
 	    direntry->begin=0; /* do that later */
         if (st.st_size > 0x7fffffff) {
 	    fprintf(stderr, "File %s is larger than 2GB\n", buffer);
-	    free(buffer);
+            g_free(buffer);
             closedir(dir);
 	    return -2;
         }
@@ -825,20 +824,6 @@ static inline off_t cluster2sector(BDRVVVFATState* s, uint32_t cluster_num)
     return s->faked_sectors + s->sectors_per_cluster * cluster_num;
 }
 
-static inline uint32_t sector_offset_in_cluster(BDRVVVFATState* s,off_t sector_num)
-{
-    return (sector_num-s->first_sectors_number-2*s->sectors_per_fat)%s->sectors_per_cluster;
-}
-
-#ifdef DBG
-static direntry_t* get_direntry_for_mapping(BDRVVVFATState* s,mapping_t* mapping)
-{
-    if(mapping->mode==MODE_UNDEFINED)
-	return 0;
-    return (direntry_t*)(s->directory.pointer+sizeof(direntry_t)*mapping->dir_index);
-}
-#endif
-
 static int init_directories(BDRVVVFATState* s,
 	const char* dirname)
 {
@@ -1138,25 +1123,6 @@ static inline mapping_t* find_mapping_for_cluster(BDRVVVFATState* s,int cluster_
     return mapping;
 }
 
-/*
- * This function simply compares path == mapping->path. Since the mappings
- * are sorted by cluster, this is expensive: O(n).
- */
-static inline mapping_t* find_mapping_for_path(BDRVVVFATState* s,
-	const char* path)
-{
-    int i;
-
-    for (i = 0; i < s->mapping.next; i++) {
-	mapping_t* mapping = array_get(&(s->mapping), i);
-	if (mapping->first_mapping_index < 0 &&
-		!strcmp(path, mapping->path))
-	    return mapping;
-    }
-
-    return NULL;
-}
-
 static int open_file(BDRVVVFATState* s,mapping_t* mapping)
 {
     if(!mapping)
@@ -1223,23 +1189,6 @@ read_cluster_directory:
 }
 
 #ifdef DEBUG
-static void hexdump(const void* address, uint32_t len)
-{
-    const unsigned char* p = address;
-    int i, j;
-
-    for (i = 0; i < len; i += 16) {
-	for (j = 0; j < 16 && i + j < len; j++)
-	    fprintf(stderr, "%02x ", p[i + j]);
-	for (; j < 16; j++)
-	    fprintf(stderr, "   ");
-	fprintf(stderr, " ");
-	for (j = 0; j < 16 && i + j < len; j++)
-	    fprintf(stderr, "%c", (p[i + j] < ' ' || p[i + j] > 0x7f) ? '.' : p[i + j]);
-	fprintf(stderr, "\n");
-    }
-}
-
 static void print_direntry(const direntry_t* direntry)
 {
     int j = 0;
@@ -1375,7 +1324,7 @@ DLOG(fprintf(stderr, "clear_commits (%d commits)\n", s->commits.next));
 	assert(commit->path || commit->action == ACTION_WRITEOUT);
 	if (commit->action != ACTION_WRITEOUT) {
 	    assert(commit->path);
-	    free(commit->path);
+            g_free(commit->path);
 	} else
 	    assert(commit->path == NULL);
     }
@@ -1741,7 +1690,7 @@ static int check_directory_consistency(BDRVVVFATState *s,
 
     long_file_name lfn;
     int path_len = strlen(path);
-    char path2[PATH_MAX];
+    char path2[PATH_MAX + 1];
 
     assert(path_len < PATH_MAX); /* len was tested before! */
     pstrcpy(path2, sizeof(path2), path);
@@ -1782,7 +1731,7 @@ DLOG(fprintf(stderr, "read cluster %d (sector %d)\n", (int)cluster_num, (int)clu
 	if (subret) {
 	    fprintf(stderr, "Error fetching direntries\n");
 	fail:
-	    free(cluster);
+            g_free(cluster);
 	    return 0;
 	}
 
@@ -1850,7 +1799,7 @@ DLOG(fprintf(stderr, "check direntry %d:\n", i); print_direntry(direntries + i))
 	cluster_num = modified_fat_get(s, cluster_num);
     } while(!fat_eof(s, cluster_num));
 
-    free(cluster);
+    g_free(cluster);
     return ret;
 }
 
@@ -1995,8 +1944,9 @@ static int remove_mapping(BDRVVVFATState* s, int mapping_index)
     mapping_t* first_mapping = array_get(&(s->mapping), 0);
 
     /* free mapping */
-    if (mapping->first_mapping_index < 0)
-	free(mapping->path);
+    if (mapping->first_mapping_index < 0) {
+        g_free(mapping->path);
+    }
 
     /* remove from s->mapping */
     array_remove(&(s->mapping), mapping_index);
@@ -2232,11 +2182,15 @@ static int commit_one_file(BDRVVVFATState* s,
     if (fd < 0) {
 	fprintf(stderr, "Could not open %s... (%s, %d)\n", mapping->path,
 		strerror(errno), errno);
+        g_free(cluster);
 	return fd;
     }
-    if (offset > 0)
-	if (lseek(fd, offset, SEEK_SET) != offset)
-	    return -3;
+    if (offset > 0) {
+        if (lseek(fd, offset, SEEK_SET) != offset) {
+            g_free(cluster);
+            return -3;
+        }
+    }
 
     while (offset < size) {
 	uint32_t c1;
@@ -2252,11 +2206,15 @@ static int commit_one_file(BDRVVVFATState* s,
 	ret = vvfat_read(s->bs, cluster2sector(s, c),
 	    (uint8_t*)cluster, (rest_size + 0x1ff) / 0x200);
 
-	if (ret < 0)
-	    return ret;
+        if (ret < 0) {
+            g_free(cluster);
+            return ret;
+        }
 
-	if (write(fd, cluster, rest_size) < 0)
-	    return -2;
+        if (write(fd, cluster, rest_size) < 0) {
+            g_free(cluster);
+            return -2;
+        }
 
 	offset += rest_size;
 	c = c1;
@@ -2265,9 +2223,11 @@ static int commit_one_file(BDRVVVFATState* s,
     if (ftruncate(fd, size)) {
         perror("ftruncate()");
         close(fd);
+        g_free(cluster);
         return -4;
     }
     close(fd);
+    g_free(cluster);
 
     return commit_mappings(s, first_cluster, dir_index);
 }
@@ -2399,7 +2359,7 @@ static int handle_renames_and_mkdirs(BDRVVVFATState* s)
 		}
 	    }
 
-	    free(old_path);
+            g_free(old_path);
 	    array_remove(&(s->commits), i);
 	    continue;
 	} else if (commit->action == ACTION_MKDIR) {
@@ -2775,7 +2735,7 @@ static int write_target_commit(BlockDriverState *bs, int64_t sector_num,
 static void write_target_close(BlockDriverState *bs) {
     BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque);
     bdrv_delete(s->qcow);
-    free(s->qcow_filename);
+    g_free(s->qcow_filename);
 }
 
 static BlockDriver vvfat_write_target = {
@@ -2836,8 +2796,7 @@ static void vvfat_close(BlockDriverState *bs)
     array_free(&(s->fat));
     array_free(&(s->directory));
     array_free(&(s->mapping));
-    if(s->cluster_buffer)
-        free(s->cluster_buffer);
+    g_free(s->cluster_buffer);
 }
 
 static BlockDriver bdrv_vvfat = {
@@ -2878,11 +2837,5 @@ static void checkpoint(void) {
     direntry = array_get(&(vvv->directory), mapping->dir_index);
     assert(!memcmp(direntry->name, "USB     H  ", 11) || direntry->name[0]==0);
 #endif
-    return;
-    /* avoid compiler warnings: */
-    hexdump(NULL, 100);
-    remove_mapping(vvv, 0);
-    print_mapping(NULL);
-    print_direntry(NULL);
 }
 #endif
diff --git a/block_int.h b/block_int.h
index 8c3b86373c..f2f4f2db38 100644
--- a/block_int.h
+++ b/block_int.h
@@ -199,6 +199,7 @@ struct BlockDriverState {
        drivers. They are not used by the block driver */
     int cyls, heads, secs, translation;
     BlockErrorAction on_read_error, on_write_error;
+    BlockIOStatus iostatus;
     char device_name[32];
     unsigned long *dirty_bitmap;
     int64_t dirty_count;
diff --git a/hw/ide/core.c b/hw/ide/core.c
index 534b186f6f..280a117fe2 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -529,6 +529,7 @@ static int ide_handle_rw_error(IDEState *s, int error, int op)
         s->bus->error_status = op;
         bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read);
         vm_stop(RUN_STATE_IO_ERROR);
+        bdrv_iostatus_set_err(s->bs, error);
     } else {
         if (op & BM_STATUS_DMA_RETRY) {
             dma_buf_commit(s, 0);
@@ -1873,6 +1874,7 @@ int ide_init_drive(IDEState *s, BlockDriverState *bs, IDEDriveKind kind,
     }
 
     ide_reset(s);
+    bdrv_iostatus_enable(bs);
     return 0;
 }
 
diff --git a/hw/scsi-disk.c b/hw/scsi-disk.c
index 4f681ef092..69095780ac 100644
--- a/hw/scsi-disk.c
+++ b/hw/scsi-disk.c
@@ -228,6 +228,7 @@ static int scsi_handle_rw_error(SCSIDiskReq *r, int error, int type)
 
         bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read);
         vm_stop(RUN_STATE_IO_ERROR);
+        bdrv_iostatus_set_err(s->bs, error);
     } else {
         switch (error) {
         case ENOMEM:
@@ -1260,6 +1261,7 @@ static int scsi_initfn(SCSIDevice *dev, uint8_t scsi_type)
 
     s->qdev.type = scsi_type;
     qemu_add_vm_change_state_handler(scsi_dma_restart_cb, s);
+    bdrv_iostatus_enable(s->bs);
     add_boot_device_path(s->qdev.conf.bootindex, &dev->qdev, ",0");
     return 0;
 }
diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c
index 03878bfc5e..2a5d1a92b3 100644
--- a/hw/virtio-blk.c
+++ b/hw/virtio-blk.c
@@ -78,6 +78,7 @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
         s->rq = req;
         bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read);
         vm_stop(RUN_STATE_IO_ERROR);
+        bdrv_iostatus_set_err(s->bs, error);
     } else {
         virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
         bdrv_acct_done(s->bs, &req->acct);
@@ -603,6 +604,7 @@ VirtIODevice *virtio_blk_init(DeviceState *dev, BlockConf *conf,
     bdrv_set_dev_ops(s->bs, &virtio_block_ops, s);
     bdrv_set_buffer_alignment(s->bs, conf->logical_block_size);
 
+    bdrv_iostatus_enable(s->bs);
     add_boot_device_path(conf->bootindex, dev, "/disk@0,0");
 
     return &s->vdev;
diff --git a/linux-aio.c b/linux-aio.c
index bffa6cd0e3..1c635ef12d 100644
--- a/linux-aio.c
+++ b/linux-aio.c
@@ -31,6 +31,8 @@ struct qemu_laiocb {
     struct iocb iocb;
     ssize_t ret;
     size_t nbytes;
+    QEMUIOVector *qiov;
+    bool is_read;
     QLIST_ENTRY(qemu_laiocb) node;
 };
 
@@ -57,10 +59,17 @@ static void qemu_laio_process_completion(struct qemu_laio_state *s,
 
     ret = laiocb->ret;
     if (ret != -ECANCELED) {
-        if (ret == laiocb->nbytes)
+        if (ret == laiocb->nbytes) {
             ret = 0;
-        else if (ret >= 0)
-            ret = -EINVAL;
+        } else if (ret >= 0) {
+            /* Short reads mean EOF, pad with zeros. */
+            if (laiocb->is_read) {
+                qemu_iovec_memset_skip(laiocb->qiov, 0,
+                    laiocb->qiov->size - ret, ret);
+            } else {
+                ret = -EINVAL;
+            }
+        }
 
         laiocb->common.cb(laiocb->common.opaque, ret);
     }
@@ -162,6 +171,8 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
     laiocb->nbytes = nb_sectors * 512;
     laiocb->ctx = s;
     laiocb->ret = -EINPROGRESS;
+    laiocb->is_read = (type == QEMU_AIO_READ);
+    laiocb->qiov = qiov;
 
     iocbs = &laiocb->iocb;
 
@@ -185,10 +196,10 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         goto out_dec_count;
     return &laiocb->common;
 
-out_free_aiocb:
-    qemu_aio_release(laiocb);
 out_dec_count:
     s->count--;
+out_free_aiocb:
+    qemu_aio_release(laiocb);
     return NULL;
 }
 
diff --git a/monitor.c b/monitor.c
index 31b212aa6b..1a2895633e 100644
--- a/monitor.c
+++ b/monitor.c
@@ -1221,6 +1221,11 @@ struct bdrv_iterate_context {
     int err;
 };
 
+static void iostatus_bdrv_it(void *opaque, BlockDriverState *bs)
+{
+    bdrv_iostatus_reset(bs);
+}
+
 /**
  * do_cont(): Resume emulation.
  */
@@ -1237,6 +1242,7 @@ static int do_cont(Monitor *mon, const QDict *qdict, QObject **ret_data)
         return -1;
     }
 
+    bdrv_iterate(iostatus_bdrv_it, NULL);
     bdrv_iterate(encrypted_bdrv_it, &context);
     /* only resume the vm if all keys are set and valid */
     if (!context.err) {
diff --git a/qmp-commands.hx b/qmp-commands.hx
index ea96191c12..9c11e87ddb 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -1154,6 +1154,10 @@ Each json-object contain the following:
                                 "tftp", "vdi", "vmdk", "vpc", "vvfat"
          - "backing_file": backing file name (json-string, optional)
          - "encrypted": true if encrypted, false otherwise (json-bool)
+- "io-status": I/O operation status, only present if the device supports it
+               and the VM is configured to stop on errors. It's always reset
+               to "ok" when the "cont" command is issued (json_string, optional)
+             - Possible values: "ok", "failed", "nospace"
 
 Example:
 
@@ -1161,6 +1165,7 @@ Example:
 <- {
       "return":[
          {
+            "io-status": "ok",
             "device":"ide0-hd0",
             "locked":false,
             "removable":false,
@@ -1173,6 +1178,7 @@ Example:
             "type":"unknown"
          },
          {
+            "io-status": "ok",
             "device":"ide1-cd0",
             "locked":false,
             "removable":true,