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

Block patches for 2.3

# gpg: Signature made Fri 06 Feb 2015 17:14:10 GMT using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (47 commits)
  block/raw-posix.c: Fix raw_getlength() on Mac OS X block devices
  block: Eliminate silly QERR_ macros used for encryption keys
  block: New bdrv_add_key(), convert monitor to use it
  blockdev: Eliminate silly QERR_BLOCK_JOB_NOT_ACTIVE macro
  blockdev: Give find_block_job() an Error ** parameter
  qcow2: Rewrite qcow2_alloc_bytes()
  block: Give always priority to unused entries in the qcow2 L2 cache
  nbd: fix max_discard/max_transfer_length
  block: introduce BDRV_REQUEST_MAX_SECTORS
  nbd: Improve error messages
  iotests: Fix 104 for NBD
  iotests: Fix 100 for nbd
  iotests: Fix 083
  block: fix off-by-one error in qcow and qcow2
  qemu-iotests: add 116 invalid QED input file tests
  qed: check for header size overflow
  block/dmg: improve zeroes handling
  block/dmg: support bzip2 block entry types
  block/dmg: factor out block type check
  block/dmg: use SectorNumber from BLKX header
  ...

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

block.c

@@ -2647,7 +2647,7 @@ static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
 {
     int64_t len;
 
-    if (size > INT_MAX) {
+    if (size > BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS) {
         return -EIO;
     }
 
@@ -2671,7 +2671,7 @@ static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
 static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num,
                               int nb_sectors)
 {
-    if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+    if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
         return -EIO;
     }
 
@@ -2758,7 +2758,7 @@ static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
         .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
     };
 
-    if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+    if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
         return -EINVAL;
     }
 
@@ -2826,13 +2826,10 @@ int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
     }
 
     for (;;) {
-        nb_sectors = target_sectors - sector_num;
+        nb_sectors = MIN(target_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS);
         if (nb_sectors <= 0) {
             return 0;
         }
-        if (nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
-            nb_sectors = INT_MAX / BDRV_SECTOR_SIZE;
-        }
         ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n);
         if (ret < 0) {
             error_report("error getting block status at sector %" PRId64 ": %s",
@@ -3167,7 +3164,7 @@ static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
     BdrvRequestFlags flags)
 {
-    if (nb_sectors < 0 || nb_sectors > (UINT_MAX >> BDRV_SECTOR_BITS)) {
+    if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
         return -EINVAL;
     }
 
@@ -3192,10 +3189,7 @@ int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
                             BDRV_REQ_COPY_ON_READ);
 }
 
-/* if no limit is specified in the BlockLimits use a default
- * of 32768 512-byte sectors (16 MiB) per request.
- */
-#define MAX_WRITE_ZEROES_DEFAULT 32768
+#define MAX_WRITE_ZEROES_BOUNCE_BUFFER 32768
 
 static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
@@ -3205,8 +3199,8 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
     struct iovec iov = {0};
     int ret = 0;
 
-    int max_write_zeroes = bs->bl.max_write_zeroes ?
-                           bs->bl.max_write_zeroes : MAX_WRITE_ZEROES_DEFAULT;
+    int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_write_zeroes,
+                                        BDRV_REQUEST_MAX_SECTORS);
 
     while (nb_sectors > 0 && !ret) {
         int num = nb_sectors;
@@ -3242,7 +3236,7 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
         if (ret == -ENOTSUP) {
             /* Fall back to bounce buffer if write zeroes is unsupported */
             int max_xfer_len = MIN_NON_ZERO(bs->bl.max_transfer_length,
-                                            MAX_WRITE_ZEROES_DEFAULT);
+                                            MAX_WRITE_ZEROES_BOUNCE_BUFFER);
             num = MIN(num, max_xfer_len);
             iov.iov_len = num * BDRV_SECTOR_SIZE;
             if (iov.iov_base == NULL) {
@@ -3461,7 +3455,7 @@ static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
     BdrvRequestFlags flags)
 {
-    if (nb_sectors < 0 || nb_sectors > (INT_MAX >> BDRV_SECTOR_BITS)) {
+    if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
         return -EINVAL;
     }
 
@@ -3719,6 +3713,36 @@ int bdrv_set_key(BlockDriverState *bs, const char *key)
     return ret;
 }
 
+/*
+ * Provide an encryption key for @bs.
+ * If @key is non-null:
+ *     If @bs is not encrypted, fail.
+ *     Else if the key is invalid, fail.
+ *     Else set @bs's key to @key, replacing the existing key, if any.
+ * If @key is null:
+ *     If @bs is encrypted and still lacks a key, fail.
+ *     Else do nothing.
+ * On failure, store an error object through @errp if non-null.
+ */
+void bdrv_add_key(BlockDriverState *bs, const char *key, Error **errp)
+{
+    if (key) {
+        if (!bdrv_is_encrypted(bs)) {
+            error_setg(errp, "Device '%s' is not encrypted",
+                      bdrv_get_device_name(bs));
+        } else if (bdrv_set_key(bs, key) < 0) {
+            error_set(errp, QERR_INVALID_PASSWORD);
+        }
+    } else {
+        if (bdrv_key_required(bs)) {
+            error_set(errp, ERROR_CLASS_DEVICE_ENCRYPTED,
+                      "'%s' (%s) is encrypted",
+                      bdrv_get_device_name(bs),
+                      bdrv_get_encrypted_filename(bs));
+        }
+    }
+}
+
 const char *bdrv_get_format_name(BlockDriverState *bs)
 {
     return bs->drv ? bs->drv->format_name : NULL;
@@ -4562,6 +4586,8 @@ static int multiwrite_merge(BlockDriverState *bs, BlockRequest *reqs,
         }
     }
 
+    block_acct_merge_done(&bs->stats, BLOCK_ACCT_WRITE, num_reqs - outidx - 1);
+
     return outidx + 1;
 }
 
@@ -5097,11 +5123,6 @@ static void coroutine_fn bdrv_discard_co_entry(void *opaque)
     rwco->ret = bdrv_co_discard(rwco->bs, rwco->sector_num, rwco->nb_sectors);
 }
 
-/* if no limit is specified in the BlockLimits use a default
- * of 32768 512-byte sectors (16 MiB) per request.
- */
-#define MAX_DISCARD_DEFAULT 32768
-
 int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
                                  int nb_sectors)
 {
@@ -5126,7 +5147,7 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
         return 0;
     }
 
-    max_discard = bs->bl.max_discard ?  bs->bl.max_discard : MAX_DISCARD_DEFAULT;
+    max_discard = MIN_NON_ZERO(bs->bl.max_discard, BDRV_REQUEST_MAX_SECTORS);
     while (nb_sectors > 0) {
         int ret;
         int num = nb_sectors;

block/Makefile.objs

@@ -20,6 +20,7 @@ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
 block-obj-$(CONFIG_ARCHIPELAGO) += archipelago.o
 block-obj-$(CONFIG_LIBSSH2) += ssh.o
 block-obj-y += accounting.o
+block-obj-y += write-threshold.o
 
 common-obj-y += stream.o
 common-obj-y += commit.o
@@ -36,5 +37,6 @@ gluster.o-libs     := $(GLUSTERFS_LIBS)
 ssh.o-cflags       := $(LIBSSH2_CFLAGS)
 ssh.o-libs         := $(LIBSSH2_LIBS)
 archipelago.o-libs := $(ARCHIPELAGO_LIBS)
+dmg.o-libs         := $(BZIP2_LIBS)
 qcow.o-libs        := -lz
 linux-aio.o-libs   := -laio

block/accounting.c

@@ -54,3 +54,10 @@ void block_acct_highest_sector(BlockAcctStats *stats, int64_t sector_num,
         stats->wr_highest_sector = sector_num + nb_sectors - 1;
     }
 }
+
+void block_acct_merge_done(BlockAcctStats *stats, enum BlockAcctType type,
+                      int num_requests)
+{
+    assert(type < BLOCK_MAX_IOTYPE);
+    stats->merged[type] += num_requests;
+}

block/block-backend.c

@@ -580,6 +580,11 @@ int blk_get_flags(BlockBackend *blk)
     return bdrv_get_flags(blk->bs);
 }
 
+int blk_get_max_transfer_length(BlockBackend *blk)
+{
+    return blk->bs->bl.max_transfer_length;
+}
+
 void blk_set_guest_block_size(BlockBackend *blk, int align)
 {
     bdrv_set_guest_block_size(blk->bs, align);

block/nbd-client.c

@@ -373,7 +373,7 @@ void nbd_client_session_close(NbdClientSession *client)
 }
 
 int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
-    int sock, const char *export)
+                            int sock, const char *export, Error **errp)
 {
     int ret;
 
@@ -382,7 +382,7 @@ int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
     qemu_set_block(sock);
     ret = nbd_receive_negotiate(sock, export,
                                 &client->nbdflags, &client->size,
-                                &client->blocksize);
+                                &client->blocksize, errp);
     if (ret < 0) {
         logout("Failed to negotiate with the NBD server\n");
         closesocket(sock);

block/nbd-client.h

@@ -36,7 +36,7 @@ typedef struct NbdClientSession {
 } NbdClientSession;
 
 int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
-                            int sock, const char *export_name);
+                            int sock, const char *export_name, Error **errp);
 void nbd_client_session_close(NbdClientSession *client);
 
 int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,

block/nbd.c

@@ -271,7 +271,7 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* NBD handshake */
-    result = nbd_client_session_init(&s->client, bs, sock, export);
+    result = nbd_client_session_init(&s->client, bs, sock, export, errp);
     g_free(export);
     return result;
 }
@@ -301,6 +301,12 @@ static int nbd_co_flush(BlockDriverState *bs)
     return nbd_client_session_co_flush(&s->client);
 }
 
+static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
+{
+    bs->bl.max_discard = UINT32_MAX >> BDRV_SECTOR_BITS;
+    bs->bl.max_transfer_length = UINT32_MAX >> BDRV_SECTOR_BITS;
+}
+
 static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors)
 {
@@ -396,6 +402,7 @@ static BlockDriver bdrv_nbd = {
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_discard            = nbd_co_discard,
+    .bdrv_refresh_limits        = nbd_refresh_limits,
     .bdrv_getlength             = nbd_getlength,
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
     .bdrv_attach_aio_context    = nbd_attach_aio_context,
@@ -413,6 +420,7 @@ static BlockDriver bdrv_nbd_tcp = {
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_discard            = nbd_co_discard,
+    .bdrv_refresh_limits        = nbd_refresh_limits,
     .bdrv_getlength             = nbd_getlength,
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
     .bdrv_attach_aio_context    = nbd_attach_aio_context,
@@ -430,6 +438,7 @@ static BlockDriver bdrv_nbd_unix = {
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_discard            = nbd_co_discard,
+    .bdrv_refresh_limits        = nbd_refresh_limits,
     .bdrv_getlength             = nbd_getlength,
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
     .bdrv_attach_aio_context    = nbd_attach_aio_context,

block/qapi.c

@@ -24,6 +24,7 @@
 
 #include "block/qapi.h"
 #include "block/block_int.h"
+#include "block/write-threshold.h"
 #include "qmp-commands.h"
 #include "qapi-visit.h"
 #include "qapi/qmp-output-visitor.h"
@@ -89,6 +90,8 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
         info->iops_size = cfg.op_size;
     }
 
+    info->write_threshold = bdrv_write_threshold_get(bs);
+
     return info;
 }
 
@@ -335,6 +338,8 @@ static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
     s->stats->wr_bytes = bs->stats.nr_bytes[BLOCK_ACCT_WRITE];
     s->stats->rd_operations = bs->stats.nr_ops[BLOCK_ACCT_READ];
     s->stats->wr_operations = bs->stats.nr_ops[BLOCK_ACCT_WRITE];
+    s->stats->rd_merged = bs->stats.merged[BLOCK_ACCT_READ];
+    s->stats->wr_merged = bs->stats.merged[BLOCK_ACCT_WRITE];
     s->stats->wr_highest_offset =
         bs->stats.wr_highest_sector * BDRV_SECTOR_SIZE;
     s->stats->flush_operations = bs->stats.nr_ops[BLOCK_ACCT_FLUSH];

block/qcow.c

@@ -215,7 +215,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     /* read the backing file name */
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
-        if (len > 1023 || len > sizeof(bs->backing_file)) {
+        if (len > 1023 || len >= sizeof(bs->backing_file)) {
             error_setg(errp, "Backing file name too long");
             ret = -EINVAL;
             goto fail;

block/qcow2-cache.c

@@ -253,7 +253,9 @@ static int qcow2_cache_find_entry_to_replace(Qcow2Cache *c)
 
         /* Give newer hits priority */
         /* TODO Check how to optimize the replacement strategy */
-        c->entries[i].cache_hits /= 2;
+        if (c->entries[i].cache_hits > 1) {
+            c->entries[i].cache_hits /= 2;
+        }
     }
 
     if (min_index == -1) {

block/qcow2-refcount.c

@@ -759,54 +759,54 @@ int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t offset, cluster_offset;
-    int free_in_cluster;
+    int64_t offset;
+    size_t free_in_cluster;
+    int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC_BYTES);
     assert(size > 0 && size <= s->cluster_size);
-    if (s->free_byte_offset == 0) {
-        offset = qcow2_alloc_clusters(bs, s->cluster_size);
-        if (offset < 0) {
-            return offset;
+    assert(!s->free_byte_offset || offset_into_cluster(s, s->free_byte_offset));
+
+    offset = s->free_byte_offset;
+
+    if (offset) {
+        int refcount = qcow2_get_refcount(bs, offset >> s->cluster_bits);
+        if (refcount < 0) {
+            return refcount;
         }
-        s->free_byte_offset = offset;
-    }
- redo:
-    free_in_cluster = s->cluster_size -
-        offset_into_cluster(s, s->free_byte_offset);
-    if (size <= free_in_cluster) {
-        /* enough space in current cluster */
-        offset = s->free_byte_offset;
-        s->free_byte_offset += size;
-        free_in_cluster -= size;
-        if (free_in_cluster == 0)
-            s->free_byte_offset = 0;
-        if (offset_into_cluster(s, offset) != 0)
-            qcow2_update_cluster_refcount(bs, offset >> s->cluster_bits, 1,
-                                          QCOW2_DISCARD_NEVER);
-    } else {
-        offset = qcow2_alloc_clusters(bs, s->cluster_size);
-        if (offset < 0) {
-            return offset;
-        }
-        cluster_offset = start_of_cluster(s, s->free_byte_offset);
-        if ((cluster_offset + s->cluster_size) == offset) {
-            /* we are lucky: contiguous data */
-            offset = s->free_byte_offset;
-            qcow2_update_cluster_refcount(bs, offset >> s->cluster_bits, 1,
-                                          QCOW2_DISCARD_NEVER);
-            s->free_byte_offset += size;
-        } else {
-            s->free_byte_offset = offset;
-            goto redo;
+
+        if (refcount == 0xffff) {
+            offset = 0;
         }
     }
 
-    /* The cluster refcount was incremented, either by qcow2_alloc_clusters()
-     * or explicitly by qcow2_update_cluster_refcount().  Refcount blocks must
-     * be flushed before the caller's L2 table updates.
-     */
+    free_in_cluster = s->cluster_size - offset_into_cluster(s, offset);
+    if (!offset || free_in_cluster < size) {
+        int64_t new_cluster = alloc_clusters_noref(bs, s->cluster_size);
+        if (new_cluster < 0) {
+            return new_cluster;
+        }
+
+        if (!offset || ROUND_UP(offset, s->cluster_size) != new_cluster) {
+            offset = new_cluster;
+        }
+    }
+
+    assert(offset);
+    ret = update_refcount(bs, offset, size, 1, QCOW2_DISCARD_NEVER);
+    if (ret < 0) {
+        return ret;
+    }
+
+    /* The cluster refcount was incremented; refcount blocks must be flushed
+     * before the caller's L2 table updates. */
     qcow2_cache_set_dependency(bs, s->l2_table_cache, s->refcount_block_cache);
+
+    s->free_byte_offset = offset + size;
+    if (!offset_into_cluster(s, s->free_byte_offset)) {
+        s->free_byte_offset = 0;
+    }
+
     return offset;
 }
 

block/qcow2.c

@@ -869,7 +869,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
         if (len > MIN(1023, s->cluster_size - header.backing_file_offset) ||
-            len > sizeof(bs->backing_file)) {
+            len >= sizeof(bs->backing_file)) {
             error_setg(errp, "Backing file name too long");
             ret = -EINVAL;
             goto fail;

block/qed.c

@@ -440,6 +440,11 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
     s->l2_mask = s->table_nelems - 1;
     s->l1_shift = s->l2_shift + ffs(s->table_nelems) - 1;
 
+    /* Header size calculation must not overflow uint32_t */
+    if (s->header.header_size > UINT32_MAX / s->header.cluster_size) {
+        return -EINVAL;
+    }
+
     if ((s->header.features & QED_F_BACKING_FILE)) {
         if ((uint64_t)s->header.backing_filename_offset +
             s->header.backing_filename_size >

block/qed.h

@@ -133,7 +133,6 @@ typedef struct QEDAIOCB {
     int bh_ret;                     /* final return status for completion bh */
     QSIMPLEQ_ENTRY(QEDAIOCB) next;  /* next request */
     int flags;                      /* QED_AIOCB_* bits ORed together */
-    bool *finished;                 /* signal for cancel completion */
     uint64_t end_pos;               /* request end on block device, in bytes */
 
     /* User scatter-gather list */

block/raw-posix.c

@@ -60,7 +60,7 @@
 #define FS_NOCOW_FL                     0x00800000 /* Do not cow file */
 #endif
 #endif
-#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+#if defined(CONFIG_FALLOCATE_PUNCH_HOLE) || defined(CONFIG_FALLOCATE_ZERO_RANGE)
 #include <linux/falloc.h>
 #endif
 #if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -147,6 +147,7 @@ typedef struct BDRVRawState {
     bool has_discard:1;
     bool has_write_zeroes:1;
     bool discard_zeroes:1;
+    bool has_fallocate;
     bool needs_alignment;
 } BDRVRawState;
 
@@ -452,6 +453,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     }
     if (S_ISREG(st.st_mode)) {
         s->discard_zeroes = true;
+        s->has_fallocate = true;
     }
     if (S_ISBLK(st.st_mode)) {
 #ifdef BLKDISCARDZEROES
@@ -893,42 +895,110 @@ static int xfs_discard(BDRVRawState *s, int64_t offset, uint64_t bytes)
 }
 #endif
 
-static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
+static int translate_err(int err)
 {
-    int ret = -EOPNOTSUPP;
+    if (err == -ENODEV || err == -ENOSYS || err == -EOPNOTSUPP ||
+        err == -ENOTTY) {
+        err = -ENOTSUP;
+    }
+    return err;
+}
+
+#ifdef CONFIG_FALLOCATE
+static int do_fallocate(int fd, int mode, off_t offset, off_t len)
+{
+    do {
+        if (fallocate(fd, mode, offset, len) == 0) {
+            return 0;
+        }
+    } while (errno == EINTR);
+    return translate_err(-errno);
+}
+#endif
+
+static ssize_t handle_aiocb_write_zeroes_block(RawPosixAIOData *aiocb)
+{
+    int ret = -ENOTSUP;
     BDRVRawState *s = aiocb->bs->opaque;
 
-    if (s->has_write_zeroes == 0) {
+    if (!s->has_write_zeroes) {
         return -ENOTSUP;
     }
 
-    if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
 #ifdef BLKZEROOUT
-        do {
-            uint64_t range[2] = { aiocb->aio_offset, aiocb->aio_nbytes };
-            if (ioctl(aiocb->aio_fildes, BLKZEROOUT, range) == 0) {
-                return 0;
-            }
-        } while (errno == EINTR);
-
-        ret = -errno;
-#endif
-    } else {
-#ifdef CONFIG_XFS
-        if (s->is_xfs) {
-            return xfs_write_zeroes(s, aiocb->aio_offset, aiocb->aio_nbytes);
+    do {
+        uint64_t range[2] = { aiocb->aio_offset, aiocb->aio_nbytes };
+        if (ioctl(aiocb->aio_fildes, BLKZEROOUT, range) == 0) {
+            return 0;
         }
-#endif
-    }
+    } while (errno == EINTR);
 
-    if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
-        ret == -ENOTTY) {
+    ret = translate_err(-errno);
+#endif
+
+    if (ret == -ENOTSUP) {
         s->has_write_zeroes = false;
-        ret = -ENOTSUP;
     }
     return ret;
 }
 
+static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
+{
+    BDRVRawState *s = aiocb->bs->opaque;
+
+    if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
+        return handle_aiocb_write_zeroes_block(aiocb);
+    }
+
+#ifdef CONFIG_XFS
+    if (s->is_xfs) {
+        return xfs_write_zeroes(s, aiocb->aio_offset, aiocb->aio_nbytes);
+    }
+#endif
+
+#ifdef CONFIG_FALLOCATE_ZERO_RANGE
+    if (s->has_write_zeroes) {
+        int ret = do_fallocate(s->fd, FALLOC_FL_ZERO_RANGE,
+                               aiocb->aio_offset, aiocb->aio_nbytes);
+        if (ret == 0 || ret != -ENOTSUP) {
+            return ret;
+        }
+        s->has_write_zeroes = false;
+    }
+#endif
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+    if (s->has_discard && s->has_fallocate) {
+        int ret = do_fallocate(s->fd,
+                               FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                               aiocb->aio_offset, aiocb->aio_nbytes);
+        if (ret == 0) {
+            ret = do_fallocate(s->fd, 0, aiocb->aio_offset, aiocb->aio_nbytes);
+            if (ret == 0 || ret != -ENOTSUP) {
+                return ret;
+            }
+            s->has_fallocate = false;
+        } else if (ret != -ENOTSUP) {
+            return ret;
+        } else {
+            s->has_discard = false;
+        }
+    }
+#endif
+
+#ifdef CONFIG_FALLOCATE
+    if (s->has_fallocate && aiocb->aio_offset >= bdrv_getlength(aiocb->bs)) {
+        int ret = do_fallocate(s->fd, 0, aiocb->aio_offset, aiocb->aio_nbytes);
+        if (ret == 0 || ret != -ENOTSUP) {
+            return ret;
+        }
+        s->has_fallocate = false;
+    }
+#endif
+
+    return -ENOTSUP;
+}
+
 static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
 {
     int ret = -EOPNOTSUPP;
@@ -957,21 +1027,14 @@ static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
 #endif
 
 #ifdef CONFIG_FALLOCATE_PUNCH_HOLE
-        do {
-            if (fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
-                          aiocb->aio_offset, aiocb->aio_nbytes) == 0) {
-                return 0;
-            }
-        } while (errno == EINTR);
-
-        ret = -errno;
+        ret = do_fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                           aiocb->aio_offset, aiocb->aio_nbytes);
 #endif
     }
 
-    if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
-        ret == -ENOTTY) {
+    ret = translate_err(ret);
+    if (ret == -ENOTSUP) {
         s->has_discard = false;
-        ret = -ENOTSUP;
     }
     return ret;
 }
@@ -1312,7 +1375,20 @@ again:
         if (size == 0)
 #endif
 #if defined(__APPLE__) && defined(__MACH__)
-        size = LLONG_MAX;
+        {
+            uint64_t sectors = 0;
+            uint32_t sector_size = 0;
+
+            if (ioctl(fd, DKIOCGETBLOCKCOUNT, &sectors) == 0
+               && ioctl(fd, DKIOCGETBLOCKSIZE, &sector_size) == 0) {
+                size = sectors * sector_size;
+            } else {
+                size = lseek(fd, 0LL, SEEK_END);
+                if (size < 0) {
+                    return -errno;
+                }
+            }
+        }
 #else
         size = lseek(fd, 0LL, SEEK_END);
         if (size < 0) {

block/write-threshold.c

@@ -0,0 +1,125 @@
+/*
+ * QEMU System Emulator block write threshold notification
+ *
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ *  Francesco Romani <fromani@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#include "block/block_int.h"
+#include "block/coroutine.h"
+#include "block/write-threshold.h"
+#include "qemu/notify.h"
+#include "qapi-event.h"
+#include "qmp-commands.h"
+
+
+uint64_t bdrv_write_threshold_get(const BlockDriverState *bs)
+{
+    return bs->write_threshold_offset;
+}
+
+bool bdrv_write_threshold_is_set(const BlockDriverState *bs)
+{
+    return bs->write_threshold_offset > 0;
+}
+
+static void write_threshold_disable(BlockDriverState *bs)
+{
+    if (bdrv_write_threshold_is_set(bs)) {
+        notifier_with_return_remove(&bs->write_threshold_notifier);
+        bs->write_threshold_offset = 0;
+    }
+}
+
+uint64_t bdrv_write_threshold_exceeded(const BlockDriverState *bs,
+                                       const BdrvTrackedRequest *req)
+{
+    if (bdrv_write_threshold_is_set(bs)) {
+        if (req->offset > bs->write_threshold_offset) {
+            return (req->offset - bs->write_threshold_offset) + req->bytes;
+        }
+        if ((req->offset + req->bytes) > bs->write_threshold_offset) {
+            return (req->offset + req->bytes) - bs->write_threshold_offset;
+        }
+    }
+    return 0;
+}
+
+static int coroutine_fn before_write_notify(NotifierWithReturn *notifier,
+                                            void *opaque)
+{
+    BdrvTrackedRequest *req = opaque;
+    BlockDriverState *bs = req->bs;
+    uint64_t amount = 0;
+
+    amount = bdrv_write_threshold_exceeded(bs, req);
+    if (amount > 0) {
+        qapi_event_send_block_write_threshold(
+            bs->node_name,
+            amount,
+            bs->write_threshold_offset,
+            &error_abort);
+
+        /* autodisable to avoid flooding the monitor */
+        write_threshold_disable(bs);
+    }
+
+    return 0; /* should always let other notifiers run */
+}
+
+static void write_threshold_register_notifier(BlockDriverState *bs)
+{
+    bs->write_threshold_notifier.notify = before_write_notify;
+    notifier_with_return_list_add(&bs->before_write_notifiers,
+                                  &bs->write_threshold_notifier);
+}
+
+static void write_threshold_update(BlockDriverState *bs,
+                                   int64_t threshold_bytes)
+{
+    bs->write_threshold_offset = threshold_bytes;
+}
+
+void bdrv_write_threshold_set(BlockDriverState *bs, uint64_t threshold_bytes)
+{
+    if (bdrv_write_threshold_is_set(bs)) {
+        if (threshold_bytes > 0) {
+            write_threshold_update(bs, threshold_bytes);
+        } else {
+            write_threshold_disable(bs);
+        }
+    } else {
+        if (threshold_bytes > 0) {
+            /* avoid multiple registration */
+            write_threshold_register_notifier(bs);
+            write_threshold_update(bs, threshold_bytes);
+        }
+        /* discard bogus disable request */
+    }
+}
+
+void qmp_block_set_write_threshold(const char *node_name,
+                                   uint64_t threshold_bytes,
+                                   Error **errp)
+{
+    BlockDriverState *bs;
+    AioContext *aio_context;
+
+    bs = bdrv_find_node(node_name);
+    if (!bs) {
+        error_set(errp, QERR_DEVICE_NOT_FOUND, node_name);
+        return;
+    }
+
+    aio_context = bdrv_get_aio_context(bs);
+    aio_context_acquire(aio_context);
+
+    bdrv_write_threshold_set(bs, threshold_bytes);
+
+    aio_context_release(aio_context);
+}

blockdev.c

@@ -1793,7 +1793,6 @@ void qmp_block_passwd(bool has_device, const char *device,
     Error *local_err = NULL;
     BlockDriverState *bs;
     AioContext *aio_context;
-    int err;
 
     bs = bdrv_lookup_bs(has_device ? device : NULL,
                         has_node_name ? node_name : NULL,
@@ -1806,16 +1805,8 @@ void qmp_block_passwd(bool has_device, const char *device,
     aio_context = bdrv_get_aio_context(bs);
     aio_context_acquire(aio_context);
 
-    err = bdrv_set_key(bs, password);
-    if (err == -EINVAL) {
-        error_set(errp, QERR_DEVICE_NOT_ENCRYPTED, bdrv_get_device_name(bs));
-        goto out;
-    } else if (err < 0) {
-        error_set(errp, QERR_INVALID_PASSWORD);
-        goto out;
-    }
+    bdrv_add_key(bs, password, errp);
 
-out:
     aio_context_release(aio_context);
 }
 
@@ -1833,18 +1824,7 @@ static void qmp_bdrv_open_encrypted(BlockDriverState *bs, const char *filename,
         return;
     }
 
-    if (bdrv_key_required(bs)) {
-        if (password) {
-            if (bdrv_set_key(bs, password) < 0) {
-                error_set(errp, QERR_INVALID_PASSWORD);
-            }
-        } else {
-            error_set(errp, QERR_DEVICE_ENCRYPTED, bdrv_get_device_name(bs),
-                      bdrv_get_encrypted_filename(bs));
-        }
-    } else if (password) {
-        error_set(errp, QERR_DEVICE_NOT_ENCRYPTED, bdrv_get_device_name(bs));
-    }
+    bdrv_add_key(bs, password, errp);
 }
 
 void qmp_change_blockdev(const char *device, const char *filename,
@@ -2653,7 +2633,8 @@ out:
 }
 
 /* Get the block job for a given device name and acquire its AioContext */
-static BlockJob *find_block_job(const char *device, AioContext **aio_context)
+static BlockJob *find_block_job(const char *device, AioContext **aio_context,
+                                Error **errp)
 {
     BlockDriverState *bs;
 
@@ -2673,6 +2654,8 @@ static BlockJob *find_block_job(const char *device, AioContext **aio_context)
     return bs->job;
 
 notfound:
+    error_set(errp, ERROR_CLASS_DEVICE_NOT_ACTIVE,
+              "No active block job on device '%s'", device);
     *aio_context = NULL;
     return NULL;
 }
@@ -2680,10 +2663,9 @@ notfound:
 void qmp_block_job_set_speed(const char *device, int64_t speed, Error **errp)
 {
     AioContext *aio_context;
-    BlockJob *job = find_block_job(device, &aio_context);
+    BlockJob *job = find_block_job(device, &aio_context, errp);
 
     if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
         return;
     }
 
@@ -2695,10 +2677,9 @@ void qmp_block_job_cancel(const char *device,
                           bool has_force, bool force, Error **errp)
 {
     AioContext *aio_context;
-    BlockJob *job = find_block_job(device, &aio_context);
+    BlockJob *job = find_block_job(device, &aio_context, errp);
 
     if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
         return;
     }
 
@@ -2721,10 +2702,9 @@ out:
 void qmp_block_job_pause(const char *device, Error **errp)
 {
     AioContext *aio_context;
-    BlockJob *job = find_block_job(device, &aio_context);
+    BlockJob *job = find_block_job(device, &aio_context, errp);
 
     if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
         return;
     }
 
@@ -2736,10 +2716,9 @@ void qmp_block_job_pause(const char *device, Error **errp)
 void qmp_block_job_resume(const char *device, Error **errp)
 {
     AioContext *aio_context;
-    BlockJob *job = find_block_job(device, &aio_context);
+    BlockJob *job = find_block_job(device, &aio_context, errp);
 
     if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
         return;
     }
 
@@ -2751,10 +2730,9 @@ void qmp_block_job_resume(const char *device, Error **errp)
 void qmp_block_job_complete(const char *device, Error **errp)
 {
     AioContext *aio_context;
-    BlockJob *job = find_block_job(device, &aio_context);
+    BlockJob *job = find_block_job(device, &aio_context, errp);
 
     if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
         return;
     }
 

configure

@@ -313,6 +313,7 @@ glx=""
 zlib="yes"
 lzo=""
 snappy=""
+bzip2=""
 guest_agent=""
 guest_agent_with_vss="no"
 vss_win32_sdk=""
@@ -1060,6 +1061,10 @@ for opt do
   ;;
   --enable-snappy) snappy="yes"
   ;;
+  --disable-bzip2) bzip2="no"
+  ;;
+  --enable-bzip2) bzip2="yes"
+  ;;
   --enable-guest-agent) guest_agent="yes"
   ;;
   --disable-guest-agent) guest_agent="no"
@@ -1374,6 +1379,8 @@ Advanced options (experts only):
   --enable-usb-redir       enable usb network redirection support
   --enable-lzo             enable the support of lzo compression library
   --enable-snappy          enable the support of snappy compression library
+  --enable-bzip2           enable the support of bzip2 compression library (for
+                           reading bzip2-compressed dmg images)
   --disable-guest-agent    disable building of the QEMU Guest Agent
   --enable-guest-agent     enable building of the QEMU Guest Agent
   --with-vss-sdk=SDK-path  enable Windows VSS support in QEMU Guest Agent
@@ -1819,6 +1826,24 @@ EOF
     fi
 fi
 
+##########################################
+# bzip2 check
+
+if test "$bzip2" != "no" ; then
+    cat > $TMPC << EOF
+#include <bzlib.h>
+int main(void) { BZ2_bzlibVersion(); return 0; }
+EOF
+    if compile_prog "" "-lbz2" ; then
+        bzip2="yes"
+    else
+        if test "$bzip2" = "yes"; then
+            feature_not_found "libbzip2" "Install libbzip2 devel"
+        fi
+        bzip2="no"
+    fi
+fi
+
 ##########################################
 # libseccomp check
 
@@ -3335,6 +3360,22 @@ if compile_prog "" "" ; then
   fallocate_punch_hole=yes
 fi
 
+# check that fallocate supports range zeroing inside the file
+fallocate_zero_range=no
+cat > $TMPC << EOF
+#include <fcntl.h>
+#include <linux/falloc.h>
+
+int main(void)
+{
+    fallocate(0, FALLOC_FL_ZERO_RANGE, 0, 0);
+    return 0;
+}
+EOF
+if compile_prog "" "" ; then
+  fallocate_zero_range=yes
+fi
+
 # check for posix_fallocate
 posix_fallocate=no
 cat > $TMPC << EOF
@@ -4369,6 +4410,7 @@ echo "vhdx              $vhdx"
 echo "Quorum            $quorum"
 echo "lzo support       $lzo"
 echo "snappy support    $snappy"
+echo "bzip2 support     $bzip2"
 echo "NUMA host support $numa"
 
 if test "$sdl_too_old" = "yes"; then
@@ -4567,6 +4609,9 @@ fi
 if test "$fallocate_punch_hole" = "yes" ; then
   echo "CONFIG_FALLOCATE_PUNCH_HOLE=y" >> $config_host_mak
 fi
+if test "$fallocate_zero_range" = "yes" ; then
+  echo "CONFIG_FALLOCATE_ZERO_RANGE=y" >> $config_host_mak
+fi
 if test "$posix_fallocate" = "yes" ; then
   echo "CONFIG_POSIX_FALLOCATE=y" >> $config_host_mak
 fi
@@ -4724,6 +4769,11 @@ if test "$snappy" = "yes" ; then
   echo "CONFIG_SNAPPY=y" >> $config_host_mak
 fi
 
+if test "$bzip2" = "yes" ; then
+  echo "CONFIG_BZIP2=y" >> $config_host_mak
+  echo "BZIP2_LIBS=-lbz2" >> $config_host_mak
+fi
+
 if test "$libiscsi" = "yes" ; then
   echo "CONFIG_LIBISCSI=m" >> $config_host_mak
   echo "LIBISCSI_CFLAGS=$libiscsi_cflags" >> $config_host_mak

hmp.c

@@ -474,6 +474,8 @@ void hmp_info_blockstats(Monitor *mon, const QDict *qdict)
                        " wr_total_time_ns=%" PRId64
                        " rd_total_time_ns=%" PRId64
                        " flush_total_time_ns=%" PRId64
+                       " rd_merged=%" PRId64
+                       " wr_merged=%" PRId64
                        "\n",
                        stats->value->stats->rd_bytes,
                        stats->value->stats->wr_bytes,
@@ -482,7 +484,9 @@ void hmp_info_blockstats(Monitor *mon, const QDict *qdict)
                        stats->value->stats->flush_operations,
                        stats->value->stats->wr_total_time_ns,
                        stats->value->stats->rd_total_time_ns,
-                       stats->value->stats->flush_total_time_ns);
+                       stats->value->stats->flush_total_time_ns,
+                       stats->value->stats->rd_merged,
+                       stats->value->stats->wr_merged);
     }
 
     qapi_free_BlockStatsList(stats_list);