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

Block patches

# gpg: Signature made Fri 12 Sep 2014 16:09:43 BST using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (22 commits)
  qcow2: Add falloc and full preallocation option
  raw-posix: Add falloc and full preallocation option
  qapi: introduce PreallocMode and new PreallocModes full and falloc.
  block: don't convert file size to sector size
  block: round up file size to nearest sector
  iotests: Send the correct fd in socket_scm_helper
  blockdev: Refuse to drive_del something added with blockdev-add
  block: extend BLOCK_IO_ERROR with reason string
  dataplane: fix virtio_blk_data_plane_create() op blocker error path
  qemu-iotests: Run 025 for Archipelago block driver
  block/archipelago: Implement bdrv_truncate()
  block: Make the block accounting functions operate on BlockAcctStats
  block: rename BlockAcctType members to start with BLOCK_ instead of BDRV_
  block: Extract the block accounting code
  block: Extract the BlockAcctStats structure
  IDE: MMIO IDE device control should be little endian
  thread-pool: Drop unnecessary includes
  xen: Drop redundant bdrv_close() from pci_piix3_xen_ide_unplug()
  xen_disk: Plug memory leak on error path
  qemu-io: Clean up openfile() after commit 2e40134
  ...

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

block.c

@@ -3363,9 +3363,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
 
     bdrv_set_dirty(bs, sector_num, nb_sectors);
 
-    if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
-        bs->wr_highest_sector = sector_num + nb_sectors - 1;
-    }
+    block_acct_highest_sector(&bs->stats, sector_num, nb_sectors);
+
     if (bs->growable && ret >= 0) {
         bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
     }
@@ -3639,6 +3638,19 @@ BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int e
     }
 }
 
+static void send_qmp_error_event(BlockDriverState *bs,
+                                 BlockErrorAction action,
+                                 bool is_read, int error)
+{
+    BlockErrorAction ac;
+
+    ac = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
+    qapi_event_send_block_io_error(bdrv_get_device_name(bs), ac, action,
+                                   bdrv_iostatus_is_enabled(bs),
+                                   error == ENOSPC, strerror(error),
+                                   &error_abort);
+}
+
 /* This is done by device models because, while the block layer knows
  * about the error, it does not know whether an operation comes from
  * the device or the block layer (from a job, for example).
@@ -3664,16 +3676,10 @@ void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
          * also ensures that the STOP/RESUME pair of events is emitted.
          */
         qemu_system_vmstop_request_prepare();
-        qapi_event_send_block_io_error(bdrv_get_device_name(bs),
-                                       is_read ? IO_OPERATION_TYPE_READ :
-                                       IO_OPERATION_TYPE_WRITE,
-                                       action, &error_abort);
+        send_qmp_error_event(bs, action, is_read, error);
         qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
     } else {
-        qapi_event_send_block_io_error(bdrv_get_device_name(bs),
-                                       is_read ? IO_OPERATION_TYPE_READ :
-                                       IO_OPERATION_TYPE_WRITE,
-                                       action, &error_abort);
+        send_qmp_error_event(bs, action, is_read, error);
     }
 }
 
@@ -5566,27 +5572,6 @@ void bdrv_iostatus_set_err(BlockDriverState *bs, int error)
     }
 }
 
-void
-bdrv_acct_start(BlockDriverState *bs, BlockAcctCookie *cookie, int64_t bytes,
-        enum BlockAcctType type)
-{
-    assert(type < BDRV_MAX_IOTYPE);
-
-    cookie->bytes = bytes;
-    cookie->start_time_ns = get_clock();
-    cookie->type = type;
-}
-
-void
-bdrv_acct_done(BlockDriverState *bs, BlockAcctCookie *cookie)
-{
-    assert(cookie->type < BDRV_MAX_IOTYPE);
-
-    bs->nr_bytes[cookie->type] += cookie->bytes;
-    bs->nr_ops[cookie->type]++;
-    bs->total_time_ns[cookie->type] += get_clock() - cookie->start_time_ns;
-}
-
 void bdrv_img_create(const char *filename, const char *fmt,
                      const char *base_filename, const char *base_fmt,
                      char *options, uint64_t img_size, int flags,
@@ -6103,3 +6088,14 @@ void bdrv_refresh_filename(BlockDriverState *bs)
         QDECREF(json);
     }
 }
+
+/* This accessor function purpose is to allow the device models to access the
+ * BlockAcctStats structure embedded inside a BlockDriverState without being
+ * aware of the BlockDriverState structure layout.
+ * It will go away when the BlockAcctStats structure will be moved inside
+ * the device models.
+ */
+BlockAcctStats *bdrv_get_stats(BlockDriverState *bs)
+{
+    return &bs->stats;
+}

block/Makefile.objs

@@ -18,6 +18,7 @@ block-obj-$(CONFIG_RBD) += rbd.o
 block-obj-$(CONFIG_GLUSTERFS) += gluster.o
 block-obj-$(CONFIG_ARCHIPELAGO) += archipelago.o
 block-obj-$(CONFIG_LIBSSH2) += ssh.o
+block-obj-y += accounting.o
 
 common-obj-y += stream.o
 common-obj-y += commit.o

block/accounting.c

@@ -0,0 +1,54 @@
+/*
+ * QEMU System Emulator block accounting
+ *
+ * Copyright (c) 2011 Christoph Hellwig
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "block/accounting.h"
+#include "block/block_int.h"
+
+void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
+                      int64_t bytes, enum BlockAcctType type)
+{
+    assert(type < BLOCK_MAX_IOTYPE);
+
+    cookie->bytes = bytes;
+    cookie->start_time_ns = get_clock();
+    cookie->type = type;
+}
+
+void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)
+{
+    assert(cookie->type < BLOCK_MAX_IOTYPE);
+
+    stats->nr_bytes[cookie->type] += cookie->bytes;
+    stats->nr_ops[cookie->type]++;
+    stats->total_time_ns[cookie->type] += get_clock() - cookie->start_time_ns;
+}
+
+
+void block_acct_highest_sector(BlockAcctStats *stats, int64_t sector_num,
+                               unsigned int nb_sectors)
+{
+    if (stats->wr_highest_sector < sector_num + nb_sectors - 1) {
+        stats->wr_highest_sector = sector_num + nb_sectors - 1;
+    }
+}

block/archipelago.c

@@ -63,8 +63,6 @@
 #include <xseg/xseg.h>
 #include <xseg/protocol.h>
 
-#define ARCHIP_FD_READ      0
-#define ARCHIP_FD_WRITE     1
 #define MAX_REQUEST_SIZE    524288
 
 #define ARCHIPELAGO_OPT_VOLUME      "volume"
@@ -84,6 +82,7 @@ typedef enum {
     ARCHIP_OP_WRITE,
     ARCHIP_OP_FLUSH,
     ARCHIP_OP_VOLINFO,
+    ARCHIP_OP_TRUNCATE,
 } ARCHIPCmd;
 
 typedef struct ArchipelagoAIOCB {
@@ -248,6 +247,7 @@ static void xseg_request_handler(void *state)
                 }
                 break;
             case ARCHIP_OP_VOLINFO:
+            case ARCHIP_OP_TRUNCATE:
                 s->is_signaled = true;
                 qemu_cond_signal(&s->archip_cond);
                 break;
@@ -708,7 +708,8 @@ static int qemu_archipelago_create(const char *filename,
 
     parse_filename_opts(filename, errp, &volname, &segment_name, &mport,
                         &vport);
-    total_size = qemu_opt_get_size_del(options, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(options, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     if (segment_name == NULL) {
         segment_name = g_strdup("archipelago");
@@ -995,6 +996,64 @@ static int64_t qemu_archipelago_getlength(BlockDriverState *bs)
     return ret;
 }
 
+static int qemu_archipelago_truncate(BlockDriverState *bs, int64_t offset)
+{
+    int ret, targetlen;
+    struct xseg_request *req;
+    BDRVArchipelagoState *s = bs->opaque;
+    AIORequestData *reqdata = g_new(AIORequestData, 1);
+
+    const char *volname = s->volname;
+    targetlen = strlen(volname);
+    req = xseg_get_request(s->xseg, s->srcport, s->mportno, X_ALLOC);
+    if (!req) {
+        archipelagolog("Cannot get XSEG request\n");
+        return err_exit2;
+    }
+
+    ret = xseg_prep_request(s->xseg, req, targetlen, 0);
+    if (ret < 0) {
+        archipelagolog("Cannot prepare XSEG request\n");
+        goto err_exit;
+    }
+    char *target = xseg_get_target(s->xseg, req);
+    if (!target) {
+        archipelagolog("Cannot get XSEG target\n");
+        goto err_exit;
+    }
+    memcpy(target, volname, targetlen);
+    req->offset = offset;
+    req->op = X_TRUNCATE;
+
+    reqdata->op = ARCHIP_OP_TRUNCATE;
+    reqdata->volname = volname;
+
+    xseg_set_req_data(s->xseg, req, reqdata);
+
+    xport p = xseg_submit(s->xseg, req, s->srcport, X_ALLOC);
+    if (p == NoPort) {
+        archipelagolog("Cannot submit XSEG request\n");
+        goto err_exit;
+    }
+
+    xseg_signal(s->xseg, p);
+    qemu_mutex_lock(&s->archip_mutex);
+    while (!s->is_signaled) {
+        qemu_cond_wait(&s->archip_cond, &s->archip_mutex);
+    }
+    s->is_signaled = false;
+    qemu_mutex_unlock(&s->archip_mutex);
+    xseg_put_request(s->xseg, req, s->srcport);
+    g_free(reqdata);
+    return 0;
+
+err_exit:
+    xseg_put_request(s->xseg, req, s->srcport);
+err_exit2:
+    g_free(reqdata);
+    return -EIO;
+}
+
 static QemuOptsList qemu_archipelago_create_opts = {
     .name = "archipelago-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(qemu_archipelago_create_opts.head),
@@ -1024,6 +1083,7 @@ static BlockDriver bdrv_archipelago = {
     .bdrv_close          = qemu_archipelago_close,
     .bdrv_create         = qemu_archipelago_create,
     .bdrv_getlength      = qemu_archipelago_getlength,
+    .bdrv_truncate       = qemu_archipelago_truncate,
     .bdrv_aio_readv      = qemu_archipelago_aio_readv,
     .bdrv_aio_writev     = qemu_archipelago_aio_writev,
     .bdrv_aio_flush      = qemu_archipelago_aio_flush,

block/cow.c

@@ -335,7 +335,8 @@ static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
     BlockDriverState *cow_bs = NULL;
 
     /* Read out options */
-    image_sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    image_sectors = DIV_ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                                 BDRV_SECTOR_SIZE);
     image_filename = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
 
     ret = bdrv_create_file(filename, opts, &local_err);

block/gluster.c

@@ -494,8 +494,8 @@ static int qemu_gluster_create(const char *filename,
         goto out;
     }
 
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
     if (!tmp || !strcmp(tmp, "off")) {
@@ -516,9 +516,8 @@ static int qemu_gluster_create(const char *filename,
     if (!fd) {
         ret = -errno;
     } else {
-        if (!glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE)) {
-            if (prealloc && qemu_gluster_zerofill(fd, 0,
-                    total_size * BDRV_SECTOR_SIZE)) {
+        if (!glfs_ftruncate(fd, total_size)) {
+            if (prealloc && qemu_gluster_zerofill(fd, 0, total_size)) {
                 ret = -errno;
             }
         } else {

block/iscsi.c

@@ -1531,8 +1531,8 @@ static int iscsi_create(const char *filename, QemuOpts *opts, Error **errp)
     bs = bdrv_new("", &error_abort);
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = DIV_ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                              BDRV_SECTOR_SIZE);
     bs->opaque = g_new0(struct IscsiLun, 1);
     iscsilun = bs->opaque;
 

block/nfs.c

@@ -418,7 +418,8 @@ static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
     client->aio_context = qemu_get_aio_context();
 
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     ret = nfs_client_open(client, url, O_CREAT, errp);
     if (ret < 0) {

block/qapi.c

@@ -333,15 +333,16 @@ static BlockStats *bdrv_query_stats(const BlockDriverState *bs)
     }
 
     s->stats = g_malloc0(sizeof(*s->stats));
-    s->stats->rd_bytes = bs->nr_bytes[BDRV_ACCT_READ];
-    s->stats->wr_bytes = bs->nr_bytes[BDRV_ACCT_WRITE];
-    s->stats->rd_operations = bs->nr_ops[BDRV_ACCT_READ];
-    s->stats->wr_operations = bs->nr_ops[BDRV_ACCT_WRITE];
-    s->stats->wr_highest_offset = bs->wr_highest_sector * BDRV_SECTOR_SIZE;
-    s->stats->flush_operations = bs->nr_ops[BDRV_ACCT_FLUSH];
-    s->stats->wr_total_time_ns = bs->total_time_ns[BDRV_ACCT_WRITE];
-    s->stats->rd_total_time_ns = bs->total_time_ns[BDRV_ACCT_READ];
-    s->stats->flush_total_time_ns = bs->total_time_ns[BDRV_ACCT_FLUSH];
+    s->stats->rd_bytes = bs->stats.nr_bytes[BLOCK_ACCT_READ];
+    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->wr_highest_offset =
+        bs->stats.wr_highest_sector * BDRV_SECTOR_SIZE;
+    s->stats->flush_operations = bs->stats.nr_ops[BLOCK_ACCT_FLUSH];
+    s->stats->wr_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_WRITE];
+    s->stats->rd_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_READ];
+    s->stats->flush_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_FLUSH];
 
     if (bs->file) {
         s->has_parent = true;

block/qcow.c

@@ -725,7 +725,8 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     BlockDriverState *qcow_bs;
 
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
         flags |= BLOCK_FLAG_ENCRYPT;
@@ -753,7 +754,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     memset(&header, 0, sizeof(header));
     header.magic = cpu_to_be32(QCOW_MAGIC);
     header.version = cpu_to_be32(QCOW_VERSION);
-    header.size = cpu_to_be64(total_size * 512);
+    header.size = cpu_to_be64(total_size);
     header_size = sizeof(header);
     backing_filename_len = 0;
     if (backing_file) {
@@ -775,7 +776,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
     header_size = (header_size + 7) & ~7;
     shift = header.cluster_bits + header.l2_bits;
-    l1_size = ((total_size * 512) + (1LL << shift) - 1) >> shift;
+    l1_size = (total_size + (1LL << shift) - 1) >> shift;
 
     header.l1_table_offset = cpu_to_be64(header_size);
     if (flags & BLOCK_FLAG_ENCRYPT) {

block/qcow2.c

@@ -30,6 +30,7 @@
 #include "qemu/error-report.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qbool.h"
+#include "qapi/util.h"
 #include "trace.h"
 #include "qemu/option_int.h"
 
@@ -1738,7 +1739,7 @@ static int preallocate(BlockDriverState *bs)
 
 static int qcow2_create2(const char *filename, int64_t total_size,
                          const char *backing_file, const char *backing_format,
-                         int flags, size_t cluster_size, int prealloc,
+                         int flags, size_t cluster_size, PreallocMode prealloc,
                          QemuOpts *opts, int version,
                          Error **errp)
 {
@@ -1771,6 +1772,56 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     Error *local_err = NULL;
     int ret;
 
+    if (prealloc == PREALLOC_MODE_FULL || prealloc == PREALLOC_MODE_FALLOC) {
+        int64_t meta_size = 0;
+        uint64_t nreftablee, nrefblocke, nl1e, nl2e;
+        int64_t aligned_total_size = align_offset(total_size, cluster_size);
+
+        /* header: 1 cluster */
+        meta_size += cluster_size;
+
+        /* total size of L2 tables */
+        nl2e = aligned_total_size / cluster_size;
+        nl2e = align_offset(nl2e, cluster_size / sizeof(uint64_t));
+        meta_size += nl2e * sizeof(uint64_t);
+
+        /* total size of L1 tables */
+        nl1e = nl2e * sizeof(uint64_t) / cluster_size;
+        nl1e = align_offset(nl1e, cluster_size / sizeof(uint64_t));
+        meta_size += nl1e * sizeof(uint64_t);
+
+        /* total size of refcount blocks
+         *
+         * note: every host cluster is reference-counted, including metadata
+         * (even refcount blocks are recursively included).
+         * Let:
+         *   a = total_size (this is the guest disk size)
+         *   m = meta size not including refcount blocks and refcount tables
+         *   c = cluster size
+         *   y1 = number of refcount blocks entries
+         *   y2 = meta size including everything
+         * then,
+         *   y1 = (y2 + a)/c
+         *   y2 = y1 * sizeof(u16) + y1 * sizeof(u16) * sizeof(u64) / c + m
+         * we can get y1:
+         *   y1 = (a + m) / (c - sizeof(u16) - sizeof(u16) * sizeof(u64) / c)
+         */
+        nrefblocke = (aligned_total_size + meta_size + cluster_size) /
+            (cluster_size - sizeof(uint16_t) -
+             1.0 * sizeof(uint16_t) * sizeof(uint64_t) / cluster_size);
+        nrefblocke = align_offset(nrefblocke, cluster_size / sizeof(uint16_t));
+        meta_size += nrefblocke * sizeof(uint16_t);
+
+        /* total size of refcount tables */
+        nreftablee = nrefblocke * sizeof(uint16_t) / cluster_size;
+        nreftablee = align_offset(nreftablee, cluster_size / sizeof(uint64_t));
+        meta_size += nreftablee * sizeof(uint64_t);
+
+        qemu_opt_set_number(opts, BLOCK_OPT_SIZE,
+                            aligned_total_size + meta_size);
+        qemu_opt_set(opts, BLOCK_OPT_PREALLOC, PreallocMode_lookup[prealloc]);
+    }
+
     ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
@@ -1859,7 +1910,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     /* Okay, now that we have a valid image, let's give it the right size */
-    ret = bdrv_truncate(bs, total_size * BDRV_SECTOR_SIZE);
+    ret = bdrv_truncate(bs, total_size);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not resize image");
         goto out;
@@ -1876,7 +1927,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     /* And if we're supposed to preallocate metadata, do that now */
-    if (prealloc) {
+    if (prealloc != PREALLOC_MODE_OFF) {
         BDRVQcowState *s = bs->opaque;
         qemu_co_mutex_lock(&s->lock);
         ret = preallocate(bs);
@@ -1912,16 +1963,17 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
     char *backing_file = NULL;
     char *backing_fmt = NULL;
     char *buf = NULL;
-    uint64_t sectors = 0;
+    uint64_t size = 0;
     int flags = 0;
     size_t cluster_size = DEFAULT_CLUSTER_SIZE;
-    int prealloc = 0;
+    PreallocMode prealloc;
     int version = 3;
     Error *local_err = NULL;
     int ret;
 
     /* Read out options */
-    sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                    BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
     if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
@@ -1930,12 +1982,11 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
     cluster_size = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE,
                                          DEFAULT_CLUSTER_SIZE);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    if (!buf || !strcmp(buf, "off")) {
-        prealloc = 0;
-    } else if (!strcmp(buf, "metadata")) {
-        prealloc = 1;
-    } else {
-        error_setg(errp, "Invalid preallocation mode: '%s'", buf);
+    prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
+                               PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
+                               &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
         ret = -EINVAL;
         goto finish;
     }
@@ -1957,7 +2008,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
         flags |= BLOCK_FLAG_LAZY_REFCOUNTS;
     }
 
-    if (backing_file && prealloc) {
+    if (backing_file && prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Backing file and preallocation cannot be used at "
                    "the same time");
         ret = -EINVAL;
@@ -1971,7 +2022,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
         goto finish;
     }
 
-    ret = qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
+    ret = qcow2_create2(filename, size, backing_file, backing_fmt, flags,
                         cluster_size, prealloc, opts, version, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -2517,7 +2568,8 @@ static QemuOptsList qcow2_create_opts = {
         {
             .name = BLOCK_OPT_PREALLOC,
             .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode (allowed values: off, metadata)"
+            .help = "Preallocation mode (allowed values: off, metadata, "
+                    "falloc, full)"
         },
         {
             .name = BLOCK_OPT_LAZY_REFCOUNTS,

block/qed.c

@@ -648,7 +648,8 @@ static int bdrv_qed_create(const char *filename, QemuOpts *opts, Error **errp)
     char *backing_fmt = NULL;
     int ret;
 
-    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
     cluster_size = qemu_opt_get_size_del(opts,

block/raw-posix.c

@@ -30,6 +30,7 @@
 #include "block/thread-pool.h"
 #include "qemu/iov.h"
 #include "raw-aio.h"
+#include "qapi/util.h"
 
 #if defined(__APPLE__) && (__MACH__)
 #include <paths.h>
@@ -1365,44 +1366,92 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
     int result = 0;
     int64_t total_size = 0;
     bool nocow = false;
+    PreallocMode prealloc;
+    char *buf = NULL;
+    Error *local_err = NULL;
 
     strstart(filename, "file:", &filename);
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     nocow = qemu_opt_get_bool(opts, BLOCK_OPT_NOCOW, false);
+    buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
+    prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
+                               PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
+                               &local_err);
+    g_free(buf);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        result = -EINVAL;
+        goto out;
+    }
 
     fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                    0644);
     if (fd < 0) {
         result = -errno;
         error_setg_errno(errp, -result, "Could not create file");
-    } else {
-        if (nocow) {
-#ifdef __linux__
-            /* Set NOCOW flag to solve performance issue on fs like btrfs.
-             * This is an optimisation. The FS_IOC_SETFLAGS ioctl return value
-             * will be ignored since any failure of this operation should not
-             * block the left work.
-             */
-            int attr;
-            if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
-                attr |= FS_NOCOW_FL;
-                ioctl(fd, FS_IOC_SETFLAGS, &attr);
-            }
-#endif
-        }
-
-        if (ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
-            result = -errno;
-            error_setg_errno(errp, -result, "Could not resize file");
-        }
-        if (qemu_close(fd) != 0) {
-            result = -errno;
-            error_setg_errno(errp, -result, "Could not close the new file");
-        }
+        goto out;
     }
+
+    if (nocow) {
+#ifdef __linux__
+        /* Set NOCOW flag to solve performance issue on fs like btrfs.
+         * This is an optimisation. The FS_IOC_SETFLAGS ioctl return value
+         * will be ignored since any failure of this operation should not
+         * block the left work.
+         */
+        int attr;
+        if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
+            attr |= FS_NOCOW_FL;
+            ioctl(fd, FS_IOC_SETFLAGS, &attr);
+        }
+#endif
+    }
+
+    if (ftruncate(fd, total_size) != 0) {
+        result = -errno;
+        error_setg_errno(errp, -result, "Could not resize file");
+        goto out_close;
+    }
+
+    if (prealloc == PREALLOC_MODE_FALLOC) {
+        /* posix_fallocate() doesn't set errno. */
+        result = -posix_fallocate(fd, 0, total_size);
+        if (result != 0) {
+            error_setg_errno(errp, -result,
+                             "Could not preallocate data for the new file");
+        }
+    } else if (prealloc == PREALLOC_MODE_FULL) {
+        buf = g_malloc0(65536);
+        int64_t num = 0, left = total_size;
+
+        while (left > 0) {
+            num = MIN(left, 65536);
+            result = write(fd, buf, num);
+            if (result < 0) {
+                result = -errno;
+                error_setg_errno(errp, -result,
+                                 "Could not write to the new file");
+                break;
+            }
+            left -= num;
+        }
+        fsync(fd);
+        g_free(buf);
+    } else if (prealloc != PREALLOC_MODE_OFF) {
+        result = -EINVAL;
+        error_setg(errp, "Unsupported preallocation mode: %s",
+                   PreallocMode_lookup[prealloc]);
+    }
+
+out_close:
+    if (qemu_close(fd) != 0 && result == 0) {
+        result = -errno;
+        error_setg_errno(errp, -result, "Could not close the new file");
+    }
+out:
     return result;
 }
 
@@ -1585,6 +1634,11 @@ static QemuOptsList raw_create_opts = {
             .type = QEMU_OPT_BOOL,
             .help = "Turn off copy-on-write (valid only on btrfs)"
         },
+        {
+            .name = BLOCK_OPT_PREALLOC,
+            .type = QEMU_OPT_STRING,
+            .help = "Preallocation mode (allowed values: off, falloc, full)"
+        },
         { /* end of list */ }
     }
 };
@@ -1966,8 +2020,8 @@ static int hdev_create(const char *filename, QemuOpts *opts,
     (void)has_prefix;
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     fd = qemu_open(filename, O_WRONLY | O_BINARY);
     if (fd < 0) {
@@ -1983,7 +2037,7 @@ static int hdev_create(const char *filename, QemuOpts *opts,
         error_setg(errp,
                    "The given file is neither a block nor a character device");
         ret = -ENODEV;
-    } else if (lseek(fd, 0, SEEK_END) < total_size * BDRV_SECTOR_SIZE) {
+    } else if (lseek(fd, 0, SEEK_END) < total_size) {
         error_setg(errp, "Device is too small");
         ret = -ENOSPC;
     }

block/raw-win32.c

@@ -511,8 +511,8 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
     strstart(filename, "file:", &filename);
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                    0644);
@@ -521,7 +521,7 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
         return -EIO;
     }
     set_sparse(fd);
-    ftruncate(fd, total_size * 512);
+    ftruncate(fd, total_size);
     qemu_close(fd);
     return 0;
 }

block/rbd.c

@@ -314,7 +314,8 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     /* Read out options */
-    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                     BDRV_SECTOR_SIZE);
     objsize = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE, 0);
     if (objsize) {
         if ((objsize - 1) & objsize) {    /* not a power of 2? */

block/sheepdog.c

@@ -1702,7 +1702,8 @@ static int sd_create(const char *filename, QemuOpts *opts,
         goto out;
     }
 
-    s->inode.vdi_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    s->inode.vdi_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                                 BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
     if (!buf || !strcmp(buf, "off")) {

block/ssh.c

@@ -700,7 +700,8 @@ static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
     ssh_state_init(&s);
 
     /* Get desired file size. */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     DPRINTF("total_size=%" PRIi64, total_size);
 
     uri_options = qdict_new();

block/vdi.c

@@ -700,7 +700,8 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
     logout("\n");
 
     /* Read out options. */
-    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                     BDRV_SECTOR_SIZE);
 #if defined(CONFIG_VDI_BLOCK_SIZE)
     /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
     block_size = qemu_opt_get_size_del(opts,

block/vhdx.c

@@ -1766,7 +1766,8 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     VHDXImageType image_type;
     Error *local_err = NULL;
 
-    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0);
     block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0);
     type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);

block/vmdk.c

@@ -1807,7 +1807,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
         goto exit;
     }
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     adapter_type = qemu_opt_get_del(opts, BLOCK_OPT_ADAPTER_TYPE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     if (qemu_opt_get_bool_del(opts, BLOCK_OPT_COMPAT6, false)) {