From 2b12baf0e3f5679d685ff19ca4ad5e54de0585bb Mon Sep 17 00:00:00 2001 From: Jeff Cody Date: Tue, 14 Feb 2017 11:21:16 -0500 Subject: [PATCH 01/19] qemu-iotests: Test 137 only supports 'file' protocol Since test 137 make uses of qcow2.py, only local files are supported. Signed-off-by: Jeff Cody Signed-off-by: Kevin Wolf --- tests/qemu-iotests/137 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/137 b/tests/qemu-iotests/137 index e5e30de2fa..eb91e517d7 100755 --- a/tests/qemu-iotests/137 +++ b/tests/qemu-iotests/137 @@ -39,7 +39,7 @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.qemu _supported_fmt qcow2 -_supported_proto generic +_supported_proto file _supported_os Linux From dfac03dcd4e88ad218e3c0800720eb60a9aa9bae Mon Sep 17 00:00:00 2001 From: Jeff Cody Date: Tue, 14 Feb 2017 11:21:17 -0500 Subject: [PATCH 02/19] qemu-iotests: add ability to exclude certain protocols from tests Add the ability for shell script tests to exclude specific protocols. This is useful to allow all protocols except ones known to not support a feature used in the test (e.g. .bdrv_create). Signed-off-by: Jeff Cody Signed-off-by: Kevin Wolf --- tests/qemu-iotests/common.rc | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index a3d904fc22..6c0fd4cc61 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -379,6 +379,18 @@ _supported_proto() _notrun "not suitable for this image protocol: $IMGPROTO" } +# tests whether $IMGPROTO is specified as an unsupported image protocol for a test +# +_unsupported_proto() +{ + for f; do + if [ "$f" = "$IMGPROTO" ]; then + _notrun "not suitable for this image protocol: $IMGPROTO" + return + fi + done +} + # tests whether the host OS is one of the supported OSes for a test # _supported_os() From 43421ea05f8dfe85dcbb2d4932730fe8cb74dbf4 Mon Sep 17 00:00:00 2001 From: Jeff Cody Date: Tue, 14 Feb 2017 13:15:07 -0500 Subject: [PATCH 03/19] qemu-iotests: redirect nbd server stdout to /dev/null Some iotests (e.g. 174) try to filter the output of _make_test_image by piping the stdout. Pipe the server stdout to /dev/null, so that filter pipe does not need to wait until process completion. Signed-off-by: Jeff Cody Reviewed-by: Eric Blake Signed-off-by: Kevin Wolf --- tests/qemu-iotests/common.rc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index 6c0fd4cc61..08065dceae 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -172,7 +172,7 @@ _make_test_img() # Start an NBD server on the image file, which is what we'll be talking to if [ $IMGPROTO = "nbd" ]; then - eval "$QEMU_NBD -v -t -b 127.0.0.1 -p 10810 -f $IMGFMT $TEST_IMG_FILE &" + eval "$QEMU_NBD -v -t -b 127.0.0.1 -p 10810 -f $IMGFMT $TEST_IMG_FILE >/dev/null &" sleep 1 # FIXME: qemu-nbd needs to be listening before we continue fi } From f6a7240442727cefe000a5b4fdee4d844ddd6bfe Mon Sep 17 00:00:00 2001 From: Nir Soffer Date: Fri, 3 Feb 2017 21:50:37 +0200 Subject: [PATCH 04/19] qemu-img: Do not truncate before preallocation When using file system that does not support fallocate() (e.g. NFS < 4.2), truncating the file only when preallocation=OFF speeds up creating raw file. Here is example run, tested on Fedora 24 machine, creating raw file on NFS version 3 server. $ time ./qemu-img-master create -f raw -o preallocation=falloc mnt/test 1g Formatting 'mnt/test', fmt=raw size=1073741824 preallocation=falloc real 0m21.185s user 0m0.022s sys 0m0.574s $ time ./qemu-img-fix create -f raw -o preallocation=falloc mnt/test 1g Formatting 'mnt/test', fmt=raw size=1073741824 preallocation=falloc real 0m11.601s user 0m0.016s sys 0m0.525s $ time dd if=/dev/zero of=mnt/test bs=1M count=1024 oflag=direct 1024+0 records in 1024+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 15.6627 s, 68.6 MB/s real 0m16.104s user 0m0.009s sys 0m0.220s Running with strace we can see that without this change we do one pread() and one pwrite() for each block. With this change, we do only one pwrite() per block. $ strace ./qemu-img-master create -f raw -o preallocation=falloc mnt/test 8192 ... pread64(9, "\0", 1, 4095) = 1 pwrite64(9, "\0", 1, 4095) = 1 pread64(9, "\0", 1, 8191) = 1 pwrite64(9, "\0", 1, 8191) = 1 $ strace ./qemu-img-fix create -f raw -o preallocation=falloc mnt/test 8192 ... pwrite64(9, "\0", 1, 4095) = 1 pwrite64(9, "\0", 1, 8191) = 1 This happens because posix_fallocate is checking if each block is allocated before writing a byte to the block, and when truncating the file before preallocation, all blocks are unallocated. Signed-off-by: Nir Soffer Signed-off-by: Kevin Wolf --- block/file-posix.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index 2134e0ef96..442f080eaa 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -1591,12 +1591,6 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp) #endif } - if (ftruncate(fd, total_size) != 0) { - result = -errno; - error_setg_errno(errp, -result, "Could not resize file"); - goto out_close; - } - switch (prealloc) { #ifdef CONFIG_POSIX_FALLOCATE case PREALLOC_MODE_FALLOC: @@ -1636,6 +1630,10 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp) break; } case PREALLOC_MODE_OFF: + if (ftruncate(fd, total_size) != 0) { + result = -errno; + error_setg_errno(errp, -result, "Could not resize file"); + } break; default: result = -EINVAL; @@ -1644,7 +1642,6 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp) break; } -out_close: if (qemu_close(fd) != 0 && result == 0) { result = -errno; error_setg_errno(errp, -result, "Could not close the new file"); From 6f993f3fca4763a6b494ff587d4400b6e8a5ef31 Mon Sep 17 00:00:00 2001 From: Nir Soffer Date: Fri, 17 Feb 2017 02:51:25 +0200 Subject: [PATCH 05/19] qemu-img: Add tests for raw image preallocation Add tests for creating raw image with and without the preallocation option. Signed-off-by: Nir Soffer Signed-off-by: Kevin Wolf --- tests/qemu-iotests/175 | 61 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/175.out | 18 +++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 80 insertions(+) create mode 100755 tests/qemu-iotests/175 create mode 100644 tests/qemu-iotests/175.out diff --git a/tests/qemu-iotests/175 b/tests/qemu-iotests/175 new file mode 100755 index 0000000000..ca56e827cd --- /dev/null +++ b/tests/qemu-iotests/175 @@ -0,0 +1,61 @@ +#!/bin/bash +# +# Test creating raw image preallocation mode +# +# Copyright (C) 2017 Nir Soffer +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . +# + +# creator +owner=nirsof@gmail.com + +seq=`basename $0` +echo "QA output created by $seq" + +here=`pwd` +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt raw +_supported_proto file +_supported_os Linux + +size=1m + +echo +echo "== creating image with default preallocation ==" +_make_test_img $size | _filter_imgfmt +stat -c "size=%s, blocks=%b" $TEST_IMG + +for mode in off full falloc; do + echo + echo "== creating image with preallocation $mode ==" + IMGOPTS=preallocation=$mode _make_test_img $size | _filter_imgfmt + stat -c "size=%s, blocks=%b" $TEST_IMG +done + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/175.out b/tests/qemu-iotests/175.out new file mode 100644 index 0000000000..76c02c6a57 --- /dev/null +++ b/tests/qemu-iotests/175.out @@ -0,0 +1,18 @@ +QA output created by 175 + +== creating image with default preallocation == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 +size=1048576, blocks=0 + +== creating image with preallocation off == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=off +size=1048576, blocks=0 + +== creating image with preallocation full == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=full +size=1048576, blocks=2048 + +== creating image with preallocation falloc == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=falloc +size=1048576, blocks=2048 + *** done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index 985b9a6a36..1f4bf03185 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -167,3 +167,4 @@ 172 auto 173 rw auto 174 auto +175 auto quick From 5a1dad9d5a5777c4883de78d9f35bd8141175798 Mon Sep 17 00:00:00 2001 From: Nir Soffer Date: Fri, 17 Feb 2017 02:51:26 +0200 Subject: [PATCH 06/19] qemu-img: Truncate before full preallocation In a previous commit (qemu-img: Do not truncate before preallocation) we moved truncate to the PREALLOC_MODE_OFF branch to avoid slowdown in posix_fallocate(). However this change is not optimal when using PREALLOC_MODE_FULL, since knowing the final size from the beginning could allow the file system driver to do less allocations and possibly avoid fragmentation of the file. Now we truncate also before doing full preallocation. Signed-off-by: Nir Soffer Signed-off-by: Kevin Wolf --- block/file-posix.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/block/file-posix.c b/block/file-posix.c index 442f080eaa..d24e34be36 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -1604,6 +1604,17 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp) #endif case PREALLOC_MODE_FULL: { + /* + * Knowing the final size from the beginning could allow the file + * system driver to do less allocations and possibly avoid + * fragmentation of the file. + */ + if (ftruncate(fd, total_size) != 0) { + result = -errno; + error_setg_errno(errp, -result, "Could not resize file"); + goto out_close; + } + int64_t num = 0, left = total_size; buf = g_malloc0(65536); @@ -1642,6 +1653,7 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp) break; } +out_close: if (qemu_close(fd) != 0 && result == 0) { result = -errno; error_setg_errno(errp, -result, "Could not close the new file"); From c6ccc2c5e6a58a847f51075abfef20e212c1a3e5 Mon Sep 17 00:00:00 2001 From: Nir Soffer Date: Fri, 17 Feb 2017 02:51:27 +0200 Subject: [PATCH 07/19] qemu-img: Improve documentation for PREALLOC_MODE_FALLOC Now that we are truncating the file in both PREALLOC_MODE_FULL and PREALLOC_MODE_OFF, not truncating in PREALLOC_MODE_FALLOC looks odd. Add a comment explaining why we do not truncate in this case. Signed-off-by: Nir Soffer Signed-off-by: Kevin Wolf --- block/file-posix.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/block/file-posix.c b/block/file-posix.c index d24e34be36..4de1abd023 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -1594,9 +1594,14 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp) switch (prealloc) { #ifdef CONFIG_POSIX_FALLOCATE case PREALLOC_MODE_FALLOC: - /* posix_fallocate() doesn't set errno. */ + /* + * Truncating before posix_fallocate() makes it about twice slower on + * file systems that do not support fallocate(), trying to check if a + * block is allocated before allocating it, so don't do that here. + */ result = -posix_fallocate(fd, 0, total_size); if (result != 0) { + /* posix_fallocate() doesn't set errno. */ error_setg_errno(errp, -result, "Could not preallocate data for the new file"); } From 2c3b44da07d341557a8203cc509ea07fe3605e11 Mon Sep 17 00:00:00 2001 From: John Snow Date: Thu, 16 Feb 2017 17:00:00 -0500 Subject: [PATCH 08/19] iotests: Fix another race in 030 We can't rely on a non-paused job to be present and running for us. Assume that if the job is not present that it completed already. Signed-off-by: John Snow Reviewed-by: Fam Zheng Signed-off-by: Kevin Wolf --- tests/qemu-iotests/030 | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/030 b/tests/qemu-iotests/030 index 54db54a1ea..0d472d5f27 100755 --- a/tests/qemu-iotests/030 +++ b/tests/qemu-iotests/030 @@ -547,11 +547,14 @@ class TestEIO(TestErrors): while not completed: for event in self.vm.get_qmp_events(wait=True): if event['event'] == 'BLOCK_JOB_ERROR': + error = True self.assert_qmp(event, 'data/device', 'drive0') self.assert_qmp(event, 'data/operation', 'read') result = self.vm.qmp('query-block-jobs') + if result == {'return': []}: + # Job finished too quickly + continue self.assert_qmp(result, 'return[0]/paused', False) - error = True elif event['event'] == 'BLOCK_JOB_COMPLETED': self.assertTrue(error, 'job completed unexpectedly') self.assert_qmp(event, 'data/type', 'stream') From 7dad9ee6467e0e3024fbe09f8a363148558b8eef Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Fri, 17 Feb 2017 11:23:33 +0100 Subject: [PATCH 09/19] blockdev: Use BlockBackend to resize in qmp_block_resize() In order to be able to do permission checking and to keep working with the BdrvChild based bdrv_truncate() that this involves, we need to create a temporary BlockBackend to resize the image. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- blockdev.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/blockdev.c b/blockdev.c index bbf9d4d8f1..2b2f6ceef0 100644 --- a/blockdev.c +++ b/blockdev.c @@ -2858,6 +2858,7 @@ void qmp_block_resize(bool has_device, const char *device, int64_t size, Error **errp) { Error *local_err = NULL; + BlockBackend *blk = NULL; BlockDriverState *bs; AioContext *aio_context; int ret; @@ -2888,10 +2889,13 @@ void qmp_block_resize(bool has_device, const char *device, goto out; } + blk = blk_new(); + blk_insert_bs(blk, bs); + /* complete all in-flight operations before resizing the device */ bdrv_drain_all(); - ret = bdrv_truncate(bs, size); + ret = blk_truncate(blk, size); switch (ret) { case 0: break; @@ -2913,6 +2917,7 @@ void qmp_block_resize(bool has_device, const char *device, } out: + blk_unref(blk); aio_context_release(aio_context); } From 70b27f364315e4ad4cb77cdebe530e5bdbdf3dcb Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Fri, 17 Feb 2017 10:58:25 +0100 Subject: [PATCH 10/19] qcow2: Use BB for resizing in qcow2_amend_options() In order to able to convert bdrv_truncate() to take a BdrvChild and later to correctly check the resize permission here, we need to use a BlockBackend for resizing the image. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block/qcow2.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/qcow2.c b/block/qcow2.c index 3e274bd1ba..254545a83b 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -3250,7 +3250,11 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, } if (new_size) { - ret = bdrv_truncate(bs, new_size); + BlockBackend *blk = blk_new(); + blk_insert_bs(blk, bs); + ret = blk_truncate(blk, new_size); + blk_unref(blk); + if (ret < 0) { return ret; } From becc347e1ca6884b4bc74a0572d3206bee7fec13 Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Fri, 17 Feb 2017 11:11:28 +0100 Subject: [PATCH 11/19] mirror: Resize active commit base in mirror_run() This is more consistent with the commit block job, and it moves the code to a place where we already have the necessary BlockBackends to resize the base image when bdrv_truncate() is changed to require a BdrvChild. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block/mirror.c | 50 ++++++++++++++++++++++---------------------------- 1 file changed, 22 insertions(+), 28 deletions(-) diff --git a/block/mirror.c b/block/mirror.c index ca8547b1d3..3d50857300 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -662,7 +662,28 @@ static void coroutine_fn mirror_run(void *opaque) if (s->bdev_length < 0) { ret = s->bdev_length; goto immediate_exit; - } else if (s->bdev_length == 0) { + } + + /* Active commit must resize the base image if its size differs from the + * active layer. */ + if (s->base == blk_bs(s->target)) { + int64_t base_length; + + base_length = blk_getlength(s->target); + if (base_length < 0) { + ret = base_length; + goto immediate_exit; + } + + if (s->bdev_length > base_length) { + ret = blk_truncate(s->target, s->bdev_length); + if (ret < 0) { + goto immediate_exit; + } + } + } + + if (s->bdev_length == 0) { /* Report BLOCK_JOB_READY and wait for complete. */ block_job_event_ready(&s->common); s->synced = true; @@ -1063,9 +1084,7 @@ void commit_active_start(const char *job_id, BlockDriverState *bs, BlockCompletionFunc *cb, void *opaque, Error **errp, bool auto_complete) { - int64_t length, base_length; int orig_base_flags; - int ret; Error *local_err = NULL; orig_base_flags = bdrv_get_flags(base); @@ -1074,31 +1093,6 @@ void commit_active_start(const char *job_id, BlockDriverState *bs, return; } - length = bdrv_getlength(bs); - if (length < 0) { - error_setg_errno(errp, -length, - "Unable to determine length of %s", bs->filename); - goto error_restore_flags; - } - - base_length = bdrv_getlength(base); - if (base_length < 0) { - error_setg_errno(errp, -base_length, - "Unable to determine length of %s", base->filename); - goto error_restore_flags; - } - - if (length > base_length) { - ret = bdrv_truncate(base, length); - if (ret < 0) { - error_setg_errno(errp, -ret, - "Top image %s is larger than base image %s, and " - "resize of base image failed", - bs->filename, base->filename); - goto error_restore_flags; - } - } - mirror_start_job(job_id, bs, creation_flags, base, NULL, speed, 0, 0, MIRROR_LEAVE_BACKING_CHAIN, on_error, on_error, true, cb, opaque, &local_err, From 52cdbc5869a3fbbe4d91c83e97dffb212af28ce3 Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Thu, 16 Feb 2017 18:39:03 +0100 Subject: [PATCH 12/19] block: Pass BdrvChild to bdrv_truncate() Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block.c | 3 ++- block/blkdebug.c | 2 +- block/block-backend.c | 2 +- block/crypto.c | 2 +- block/parallels.c | 8 ++++---- block/qcow.c | 4 ++-- block/qcow2-refcount.c | 2 +- block/qcow2.c | 4 ++-- block/raw-format.c | 2 +- block/vhdx-log.c | 2 +- block/vhdx.c | 2 +- include/block/block.h | 2 +- 12 files changed, 18 insertions(+), 17 deletions(-) diff --git a/block.c b/block.c index 743c349100..d951b5dc9e 100644 --- a/block.c +++ b/block.c @@ -2626,8 +2626,9 @@ exit: /** * Truncate file to 'offset' bytes (needed only for file protocols) */ -int bdrv_truncate(BlockDriverState *bs, int64_t offset) +int bdrv_truncate(BdrvChild *child, int64_t offset) { + BlockDriverState *bs = child->bs; BlockDriver *drv = bs->drv; int ret; if (!drv) diff --git a/block/blkdebug.c b/block/blkdebug.c index d8eee1b9b4..6117ce5fca 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -663,7 +663,7 @@ static int64_t blkdebug_getlength(BlockDriverState *bs) static int blkdebug_truncate(BlockDriverState *bs, int64_t offset) { - return bdrv_truncate(bs->file->bs, offset); + return bdrv_truncate(bs->file, offset); } static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options) diff --git a/block/block-backend.c b/block/block-backend.c index 819f27213a..492e71e41f 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -1605,7 +1605,7 @@ int blk_truncate(BlockBackend *blk, int64_t offset) return -ENOMEDIUM; } - return bdrv_truncate(blk_bs(blk), offset); + return bdrv_truncate(blk->root, offset); } static void blk_pdiscard_entry(void *opaque) diff --git a/block/crypto.c b/block/crypto.c index 7aa7eb553e..e05e4dda47 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -383,7 +383,7 @@ static int block_crypto_truncate(BlockDriverState *bs, int64_t offset) offset += payload_offset; - return bdrv_truncate(bs->file->bs, offset); + return bdrv_truncate(bs->file, offset); } static void block_crypto_close(BlockDriverState *bs) diff --git a/block/parallels.c b/block/parallels.c index 2ccefa7d85..ac94dfb497 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -215,7 +215,7 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num, s->data_end << BDRV_SECTOR_BITS, space << BDRV_SECTOR_BITS, 0); } else { - ret = bdrv_truncate(bs->file->bs, + ret = bdrv_truncate(bs->file, (s->data_end + space) << BDRV_SECTOR_BITS); } if (ret < 0) { @@ -449,7 +449,7 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res, size - res->image_end_offset); res->leaks += count; if (fix & BDRV_FIX_LEAKS) { - ret = bdrv_truncate(bs->file->bs, res->image_end_offset); + ret = bdrv_truncate(bs->file, res->image_end_offset); if (ret < 0) { res->check_errors++; return ret; @@ -681,7 +681,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, goto fail_options; } if (!bdrv_has_zero_init(bs->file->bs) || - bdrv_truncate(bs->file->bs, bdrv_getlength(bs->file->bs)) != 0) { + bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs)) != 0) { s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE; } @@ -724,7 +724,7 @@ static void parallels_close(BlockDriverState *bs) } if (bs->open_flags & BDRV_O_RDWR) { - bdrv_truncate(bs->file->bs, s->data_end << BDRV_SECTOR_BITS); + bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS); } g_free(s->bat_dirty_bmap); diff --git a/block/qcow.c b/block/qcow.c index fb738fc507..4534515db9 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -467,7 +467,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs, /* round to cluster size */ cluster_offset = (cluster_offset + s->cluster_size - 1) & ~(s->cluster_size - 1); - bdrv_truncate(bs->file->bs, cluster_offset + s->cluster_size); + bdrv_truncate(bs->file, cluster_offset + s->cluster_size); /* if encrypted, we must initialize the cluster content which won't be written */ if (bs->encrypted && @@ -909,7 +909,7 @@ static int qcow_make_empty(BlockDriverState *bs) if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table, l1_length) < 0) return -1; - ret = bdrv_truncate(bs->file->bs, s->l1_table_offset + l1_length); + ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length); if (ret < 0) return ret; diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index 3dbde18612..9e96f64c8b 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -1734,7 +1734,7 @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res, goto resize_fail; } - ret = bdrv_truncate(bs->file->bs, offset + s->cluster_size); + ret = bdrv_truncate(bs->file, offset + s->cluster_size); if (ret < 0) { goto resize_fail; } diff --git a/block/qcow2.c b/block/qcow2.c index 254545a83b..3e1172b325 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2570,7 +2570,7 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, /* align end of file to a sector boundary to ease reading with sector based I/Os */ cluster_offset = bdrv_getlength(bs->file->bs); - return bdrv_truncate(bs->file->bs, cluster_offset); + return bdrv_truncate(bs->file, cluster_offset); } buf = qemu_blockalign(bs, s->cluster_size); @@ -2784,7 +2784,7 @@ static int make_completely_empty(BlockDriverState *bs) goto fail; } - ret = bdrv_truncate(bs->file->bs, (3 + l1_clusters) * s->cluster_size); + ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size); if (ret < 0) { goto fail; } diff --git a/block/raw-format.c b/block/raw-format.c index 8404a82e0c..0ddffbd0cd 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -341,7 +341,7 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset) s->size = offset; offset += s->offset; - return bdrv_truncate(bs->file->bs, offset); + return bdrv_truncate(bs->file, offset); } static int raw_media_changed(BlockDriverState *bs) diff --git a/block/vhdx-log.c b/block/vhdx-log.c index 02eb104310..67a91c0de5 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -548,7 +548,7 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s, if (new_file_size % (1024*1024)) { /* round up to nearest 1MB boundary */ new_file_size = ((new_file_size >> 20) + 1) << 20; - bdrv_truncate(bs->file->bs, new_file_size); + bdrv_truncate(bs->file, new_file_size); } } qemu_vfree(desc_entries); diff --git a/block/vhdx.c b/block/vhdx.c index 68db9e074e..c67772e2f7 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -1165,7 +1165,7 @@ static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s, /* per the spec, the address for a block is in units of 1MB */ *new_offset = ROUND_UP(*new_offset, 1024 * 1024); - return bdrv_truncate(bs->file->bs, *new_offset + s->block_size); + return bdrv_truncate(bs->file, *new_offset + s->block_size); } /* diff --git a/include/block/block.h b/include/block/block.h index 4e81f2069b..a4cd06f884 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -253,7 +253,7 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs, const char *backing_file); int bdrv_get_backing_file_depth(BlockDriverState *bs); void bdrv_refresh_filename(BlockDriverState *bs); -int bdrv_truncate(BlockDriverState *bs, int64_t offset); +int bdrv_truncate(BdrvChild *child, int64_t offset); int64_t bdrv_nb_sectors(BlockDriverState *bs); int64_t bdrv_getlength(BlockDriverState *bs); int64_t bdrv_get_allocated_file_size(BlockDriverState *bs); From 4e4bf5c42c8b2847a90367936a6df6c277f4a76a Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Fri, 16 Dec 2016 18:52:37 +0100 Subject: [PATCH 13/19] block: Attach bs->file only during .bdrv_open() The way that attaching bs->file worked was a bit unusual in that it was the only child that would be attached to a node which is not opened yet. Because of this, the block layer couldn't know yet which permissions the driver would eventually need. This patch moves the point where bs->file is attached to the beginning of the individual .bdrv_open() implementations, so drivers already know what they are going to do with the child. This is also more consistent with how driver-specific children work. For a moment, bdrv_open() gets its own BdrvChild to perform image probing, but instead of directly assigning this BdrvChild to the BDS, it becomes a temporary one and the node name is passed as an option to the drivers, so that they can simply use bdrv_open_child() to create another reference for their own use. This duplicated child for (the not opened yet) bs is not the final state, a follow-up patch will change the image probing code to use a BlockBackend, which is completely independent of bs. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block.c | 35 ++++++++++++++++++++++++----------- block/bochs.c | 6 ++++++ block/cloop.c | 6 ++++++ block/crypto.c | 6 ++++++ block/dmg.c | 6 ++++++ block/parallels.c | 6 ++++++ block/qcow.c | 6 ++++++ block/qcow2.c | 18 +++++++++++++++--- block/qed.c | 18 +++++++++++++++--- block/raw-format.c | 6 ++++++ block/replication.c | 6 ++++++ block/vdi.c | 6 ++++++ block/vhdx.c | 6 ++++++ block/vmdk.c | 6 ++++++ block/vpc.c | 6 ++++++ tests/qemu-iotests/051.out | 4 ++-- tests/qemu-iotests/051.pc.out | 4 ++-- 17 files changed, 130 insertions(+), 21 deletions(-) diff --git a/block.c b/block.c index d951b5dc9e..40c4dee2da 100644 --- a/block.c +++ b/block.c @@ -1103,13 +1103,6 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file, assert(!drv->bdrv_needs_filename || filename != NULL); ret = drv->bdrv_file_open(bs, options, open_flags, &local_err); } else { - if (file == NULL) { - error_setg(errp, "Can't use '%s' as a block driver for the " - "protocol level", drv->format_name); - ret = -EINVAL; - goto free_and_fail; - } - bs->file = file; ret = drv->bdrv_open(bs, options, open_flags, &local_err); } @@ -1145,7 +1138,6 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file, return 0; free_and_fail: - bs->file = NULL; g_free(bs->opaque); bs->opaque = NULL; bs->drv = NULL; @@ -1368,7 +1360,18 @@ void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child) } if (child->bs->inherits_from == parent) { - child->bs->inherits_from = NULL; + BdrvChild *c; + + /* Remove inherits_from only when the last reference between parent and + * child->bs goes away. */ + QLIST_FOREACH(c, &parent->children, next) { + if (c != child && c->bs == child->bs) { + break; + } + } + if (c == NULL) { + child->bs->inherits_from = NULL; + } } bdrv_root_unref_child(child); @@ -1789,13 +1792,20 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, qdict_del(options, "backing"); } - /* Open image file without format layer */ + /* Open image file without format layer. This BdrvChild is only used for + * probing, the block drivers will do their own bdrv_open_child() for the + * same BDS, which is why we put the node name back into options. */ if ((flags & BDRV_O_PROTOCOL) == 0) { + /* FIXME Shouldn't attach a child to a node that isn't opened yet. */ file = bdrv_open_child(filename, options, "file", bs, &child_file, true, &local_err); if (local_err) { goto fail; } + if (file != NULL) { + qdict_put(options, "file", + qstring_from_str(bdrv_get_node_name(file->bs))); + } } /* Image format probing */ @@ -1835,7 +1845,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, goto fail; } - if (file && (bs->file != file)) { + if (file) { bdrv_unref_child(bs, file); file = NULL; } @@ -1901,6 +1911,9 @@ fail: if (file != NULL) { bdrv_unref_child(bs, file); } + if (bs->file != NULL) { + bdrv_unref_child(bs, bs->file); + } QDECREF(snapshot_options); QDECREF(bs->explicit_options); QDECREF(bs->options); diff --git a/block/bochs.c b/block/bochs.c index 8c9652ebeb..7dd2ac4f51 100644 --- a/block/bochs.c +++ b/block/bochs.c @@ -104,6 +104,12 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, struct bochs_header bochs; int ret; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + bs->read_only = true; /* no write support yet */ ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs)); diff --git a/block/cloop.c b/block/cloop.c index 7b75f7ef7b..877c9b0d1b 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -66,6 +66,12 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, uint32_t offsets_size, max_compressed_block_size = 1, i; int ret; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + bs->read_only = true; /* read header */ diff --git a/block/crypto.c b/block/crypto.c index e05e4dda47..7cb2ff2946 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -300,6 +300,12 @@ static int block_crypto_open_generic(QCryptoBlockFormat format, QCryptoBlockOpenOptions *open_opts = NULL; unsigned int cflags = 0; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &local_err); if (local_err) { diff --git a/block/dmg.c b/block/dmg.c index 58a3ae86c1..8e387cdfe5 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -413,6 +413,12 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags, int64_t offset; int ret; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + block_module_load_one("dmg-bz2"); bs->read_only = true; diff --git a/block/parallels.c b/block/parallels.c index ac94dfb497..b2ec09f7e6 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -581,6 +581,12 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, Error *local_err = NULL; char *buf; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph)); if (ret < 0) { goto fail; diff --git a/block/qcow.c b/block/qcow.c index 4534515db9..038b05ab1b 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -106,6 +106,12 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, QCowHeader header; Error *local_err = NULL; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + ret = bdrv_pread(bs->file, 0, &header, sizeof(header)); if (ret < 0) { goto fail; diff --git a/block/qcow2.c b/block/qcow2.c index 3e1172b325..21e61427eb 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -814,8 +814,8 @@ static int qcow2_update_options(BlockDriverState *bs, QDict *options, return ret; } -static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, - Error **errp) +static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags, + Error **errp) { BDRVQcow2State *s = bs->opaque; unsigned int len, i; @@ -1205,6 +1205,18 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, return ret; } +static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, + Error **errp) +{ + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + + return qcow2_do_open(bs, options, flags, errp); +} + static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp) { BDRVQcow2State *s = bs->opaque; @@ -1785,7 +1797,7 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp) options = qdict_clone_shallow(bs->options); flags &= ~BDRV_O_INACTIVE; - ret = qcow2_open(bs, options, flags, &local_err); + ret = qcow2_do_open(bs, options, flags, &local_err); QDECREF(options); if (local_err) { error_propagate(errp, local_err); diff --git a/block/qed.c b/block/qed.c index 0b62c7799e..62a0a09326 100644 --- a/block/qed.c +++ b/block/qed.c @@ -415,8 +415,8 @@ static void bdrv_qed_drain(BlockDriverState *bs) } } -static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags, - Error **errp) +static int bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int flags, + Error **errp) { BDRVQEDState *s = bs->opaque; QEDHeader le_header; @@ -550,6 +550,18 @@ out: return ret; } +static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags, + Error **errp) +{ + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + + return bdrv_qed_do_open(bs, options, flags, errp); +} + static void bdrv_qed_refresh_limits(BlockDriverState *bs, Error **errp) { BDRVQEDState *s = bs->opaque; @@ -1629,7 +1641,7 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs, Error **errp) bdrv_qed_close(bs); memset(s, 0, sizeof(BDRVQEDState)); - ret = bdrv_qed_open(bs, NULL, bs->open_flags, &local_err); + ret = bdrv_qed_do_open(bs, NULL, bs->open_flags, &local_err); if (local_err) { error_propagate(errp, local_err); error_prepend(errp, "Could not reopen qed layer: "); diff --git a/block/raw-format.c b/block/raw-format.c index 0ddffbd0cd..ce34d1b1cd 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -384,6 +384,12 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, BDRVRawState *s = bs->opaque; int ret; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + bs->sg = bs->file->bs->sg; bs->supported_write_flags = BDRV_REQ_FUA & bs->file->bs->supported_write_flags; diff --git a/block/replication.c b/block/replication.c index 729dd12499..eff85c77ba 100644 --- a/block/replication.c +++ b/block/replication.c @@ -86,6 +86,12 @@ static int replication_open(BlockDriverState *bs, QDict *options, const char *mode; const char *top_id; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + ret = -EINVAL; opts = qemu_opts_create(&replication_runtime_opts, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &local_err); diff --git a/block/vdi.c b/block/vdi.c index 0aeb940aa8..18b4773aac 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -363,6 +363,12 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, int ret; Error *local_err = NULL; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + logout("\n"); ret = bdrv_read(bs->file, 0, (uint8_t *)&header, 1); diff --git a/block/vhdx.c b/block/vhdx.c index c67772e2f7..9918ee98ff 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -898,6 +898,12 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, uint64_t signature; Error *local_err = NULL; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + s->bat = NULL; s->first_visible_write = true; diff --git a/block/vmdk.c b/block/vmdk.c index 393c84d8b1..9d68ec5a4e 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -943,6 +943,12 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags, uint32_t magic; Error *local_err = NULL; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + buf = vmdk_read_desc(bs->file, 0, errp); if (!buf) { return -EINVAL; diff --git a/block/vpc.c b/block/vpc.c index ed6353dbd4..d0df2a1c54 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -220,6 +220,12 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, int disk_type = VHD_DYNAMIC; int ret; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } + opts = qemu_opts_create(&vpc_runtime_opts, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &local_err); if (local_err) { diff --git a/tests/qemu-iotests/051.out b/tests/qemu-iotests/051.out index 42bf4164ca..7524c62025 100644 --- a/tests/qemu-iotests/051.out +++ b/tests/qemu-iotests/051.out @@ -225,7 +225,7 @@ Testing: -drive driver=nbd QEMU_PROG: -drive driver=nbd: NBD server address missing Testing: -drive driver=raw -QEMU_PROG: -drive driver=raw: Can't use 'raw' as a block driver for the protocol level +QEMU_PROG: -drive driver=raw: A block device must be specified for "file" Testing: -drive file.driver=file QEMU_PROG: -drive file.driver=file: The 'file' block driver requires a file name @@ -234,7 +234,7 @@ Testing: -drive file.driver=nbd QEMU_PROG: -drive file.driver=nbd: NBD server address missing Testing: -drive file.driver=raw -QEMU_PROG: -drive file.driver=raw: Can't use 'raw' as a block driver for the protocol level +QEMU_PROG: -drive file.driver=raw: A block device must be specified for "file" Testing: -drive foo=bar QEMU_PROG: -drive foo=bar: Must specify either driver or file diff --git a/tests/qemu-iotests/051.pc.out b/tests/qemu-iotests/051.pc.out index f8047a2e45..e206ad6c29 100644 --- a/tests/qemu-iotests/051.pc.out +++ b/tests/qemu-iotests/051.pc.out @@ -323,7 +323,7 @@ Testing: -drive driver=nbd QEMU_PROG: -drive driver=nbd: NBD server address missing Testing: -drive driver=raw -QEMU_PROG: -drive driver=raw: Can't use 'raw' as a block driver for the protocol level +QEMU_PROG: -drive driver=raw: A block device must be specified for "file" Testing: -drive file.driver=file QEMU_PROG: -drive file.driver=file: The 'file' block driver requires a file name @@ -332,7 +332,7 @@ Testing: -drive file.driver=nbd QEMU_PROG: -drive file.driver=nbd: NBD server address missing Testing: -drive file.driver=raw -QEMU_PROG: -drive file.driver=raw: Can't use 'raw' as a block driver for the protocol level +QEMU_PROG: -drive file.driver=raw: A block device must be specified for "file" Testing: -drive foo=bar QEMU_PROG: -drive foo=bar: Must specify either driver or file From 2d6b86af1496d534f11cf21370345139dce62fcb Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Fri, 17 Feb 2017 17:43:59 +0100 Subject: [PATCH 14/19] block: Factor out bdrv_open_child_bs() This is the part of bdrv_open_child() that opens a BDS with option inheritance, but doesn't attach it as a child to the parent yet. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block.c | 61 ++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 37 insertions(+), 24 deletions(-) diff --git a/block.c b/block.c index 40c4dee2da..6987400f5f 100644 --- a/block.c +++ b/block.c @@ -1546,28 +1546,12 @@ free_exit: return ret; } -/* - * Opens a disk image whose options are given as BlockdevRef in another block - * device's options. - * - * If allow_none is true, no image will be opened if filename is false and no - * BlockdevRef is given. NULL will be returned, but errp remains unset. - * - * bdrev_key specifies the key for the image's BlockdevRef in the options QDict. - * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict - * itself, all options starting with "${bdref_key}." are considered part of the - * BlockdevRef. - * - * The BlockdevRef will be removed from the options QDict. - */ -BdrvChild *bdrv_open_child(const char *filename, - QDict *options, const char *bdref_key, - BlockDriverState* parent, - const BdrvChildRole *child_role, - bool allow_none, Error **errp) +static BlockDriverState * +bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key, + BlockDriverState *parent, const BdrvChildRole *child_role, + bool allow_none, Error **errp) { - BdrvChild *c = NULL; - BlockDriverState *bs; + BlockDriverState *bs = NULL; QDict *image_options; char *bdref_key_dot; const char *reference; @@ -1594,11 +1578,40 @@ BdrvChild *bdrv_open_child(const char *filename, goto done; } - c = bdrv_attach_child(parent, bs, bdref_key, child_role); - done: qdict_del(options, bdref_key); - return c; + return bs; +} + +/* + * Opens a disk image whose options are given as BlockdevRef in another block + * device's options. + * + * If allow_none is true, no image will be opened if filename is false and no + * BlockdevRef is given. NULL will be returned, but errp remains unset. + * + * bdrev_key specifies the key for the image's BlockdevRef in the options QDict. + * That QDict has to be flattened; therefore, if the BlockdevRef is a QDict + * itself, all options starting with "${bdref_key}." are considered part of the + * BlockdevRef. + * + * The BlockdevRef will be removed from the options QDict. + */ +BdrvChild *bdrv_open_child(const char *filename, + QDict *options, const char *bdref_key, + BlockDriverState *parent, + const BdrvChildRole *child_role, + bool allow_none, Error **errp) +{ + BlockDriverState *bs; + + bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_role, + allow_none, errp); + if (bs == NULL) { + return NULL; + } + + return bdrv_attach_child(parent, bs, bdref_key, child_role); } static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs, From 5696c6e350be4d7b45b68e8460da1049bc9efe0a Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Fri, 17 Feb 2017 18:39:24 +0100 Subject: [PATCH 15/19] block: Use BlockBackend for image probing This fixes the use of a parent-less BdrvChild in bdrv_open_inherit() by converting it into a BlockBackend. Which is exactly what it should be, image probing is an external, standalone user of a node. The requests can't be considered to originate from the format driver node because that one isn't even opened yet. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) diff --git a/block.c b/block.c index 6987400f5f..5f1e8aafd7 100644 --- a/block.c +++ b/block.c @@ -588,21 +588,20 @@ BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size, return drv; } -static int find_image_format(BdrvChild *file, const char *filename, +static int find_image_format(BlockBackend *file, const char *filename, BlockDriver **pdrv, Error **errp) { - BlockDriverState *bs = file->bs; BlockDriver *drv; uint8_t buf[BLOCK_PROBE_BUF_SIZE]; int ret = 0; /* Return the raw BlockDriver * to scsi-generic devices or empty drives */ - if (bdrv_is_sg(bs) || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) { + if (blk_is_sg(file) || !blk_is_inserted(file) || blk_getlength(file) == 0) { *pdrv = &bdrv_raw; return ret; } - ret = bdrv_pread(file, 0, buf, sizeof(buf)); + ret = blk_pread(file, 0, buf, sizeof(buf)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read image for determining its " "format"); @@ -974,7 +973,7 @@ QemuOptsList bdrv_runtime_opts = { * * Removes all processed options from *options. */ -static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file, +static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, QDict *options, Error **errp) { int ret, open_flags; @@ -1005,7 +1004,7 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file, assert(drv != NULL); if (file != NULL) { - filename = file->bs->filename; + filename = blk_bs(file)->filename; } else { filename = qdict_get_try_str(options, "filename"); } @@ -1707,7 +1706,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, Error **errp) { int ret; - BdrvChild *file = NULL; + BlockBackend *file = NULL; BlockDriverState *bs; BlockDriver *drv = NULL; const char *drvname; @@ -1805,19 +1804,24 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, qdict_del(options, "backing"); } - /* Open image file without format layer. This BdrvChild is only used for + /* Open image file without format layer. This BlockBackend is only used for * probing, the block drivers will do their own bdrv_open_child() for the * same BDS, which is why we put the node name back into options. */ if ((flags & BDRV_O_PROTOCOL) == 0) { - /* FIXME Shouldn't attach a child to a node that isn't opened yet. */ - file = bdrv_open_child(filename, options, "file", bs, - &child_file, true, &local_err); + BlockDriverState *file_bs; + + file_bs = bdrv_open_child_bs(filename, options, "file", bs, + &child_file, true, &local_err); if (local_err) { goto fail; } - if (file != NULL) { + if (file_bs != NULL) { + file = blk_new(); + blk_insert_bs(file, file_bs); + bdrv_unref(file_bs); + qdict_put(options, "file", - qstring_from_str(bdrv_get_node_name(file->bs))); + qstring_from_str(bdrv_get_node_name(file_bs))); } } @@ -1859,7 +1863,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, } if (file) { - bdrv_unref_child(bs, file); + blk_unref(file); file = NULL; } @@ -1921,9 +1925,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, return bs; fail: - if (file != NULL) { - bdrv_unref_child(bs, file); - } + blk_unref(file); if (bs->file != NULL) { bdrv_unref_child(bs, bs->file); } From 01a5650179a914a7603c77ccf0de9617064541ee Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Wed, 18 Jan 2017 15:51:56 +0100 Subject: [PATCH 16/19] block: Factor out bdrv_open_driver() This is a function that doesn't do any option parsing, but just does some basic BlockDriverState setup and calls the .bdrv_open() function of the block driver. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block.c | 112 ++++++++++++++++++++++++++++++++------------------------ 1 file changed, 65 insertions(+), 47 deletions(-) diff --git a/block.c b/block.c index 5f1e8aafd7..f96d26b795 100644 --- a/block.c +++ b/block.c @@ -925,6 +925,67 @@ out: g_free(gen_node_name); } +static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv, + const char *node_name, QDict *options, + int open_flags, Error **errp) +{ + Error *local_err = NULL; + int ret; + + bdrv_assign_node_name(bs, node_name, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return -EINVAL; + } + + bs->drv = drv; + bs->opaque = g_malloc0(drv->instance_size); + + if (drv->bdrv_file_open) { + assert(!drv->bdrv_needs_filename || bs->filename[0]); + ret = drv->bdrv_file_open(bs, options, open_flags, &local_err); + } else { + ret = drv->bdrv_open(bs, options, open_flags, &local_err); + } + + if (ret < 0) { + if (local_err) { + error_propagate(errp, local_err); + } else if (bs->filename[0]) { + error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename); + } else { + error_setg_errno(errp, -ret, "Could not open image"); + } + goto free_and_fail; + } + + ret = refresh_total_sectors(bs, bs->total_sectors); + if (ret < 0) { + error_setg_errno(errp, -ret, "Could not refresh total sector count"); + goto free_and_fail; + } + + bdrv_refresh_limits(bs, &local_err); + if (local_err) { + error_propagate(errp, local_err); + ret = -EINVAL; + goto free_and_fail; + } + + assert(bdrv_opt_mem_align(bs) != 0); + assert(bdrv_min_mem_align(bs) != 0); + assert(is_power_of_2(bs->bl.request_alignment)); + + return 0; + +free_and_fail: + /* FIXME Close bs first if already opened*/ + g_free(bs->opaque); + bs->opaque = NULL; + bs->drv = NULL; + return ret; +} + QemuOptsList bdrv_runtime_opts = { .name = "bdrv_common", .head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head), @@ -1019,14 +1080,6 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, trace_bdrv_open_common(bs, filename ?: "", bs->open_flags, drv->format_name); - node_name = qemu_opt_get(opts, "node-name"); - bdrv_assign_node_name(bs, node_name, &local_err); - if (local_err) { - error_propagate(errp, local_err); - ret = -EINVAL; - goto fail_opts; - } - bs->read_only = !(bs->open_flags & BDRV_O_RDWR); if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) { @@ -1092,54 +1145,19 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, } pstrcpy(bs->exact_filename, sizeof(bs->exact_filename), bs->filename); - bs->drv = drv; - bs->opaque = g_malloc0(drv->instance_size); - /* Open the image, either directly or using a protocol */ open_flags = bdrv_open_flags(bs, bs->open_flags); - if (drv->bdrv_file_open) { - assert(file == NULL); - assert(!drv->bdrv_needs_filename || filename != NULL); - ret = drv->bdrv_file_open(bs, options, open_flags, &local_err); - } else { - ret = drv->bdrv_open(bs, options, open_flags, &local_err); - } + node_name = qemu_opt_get(opts, "node-name"); + assert(!drv->bdrv_file_open || file == NULL); + ret = bdrv_open_driver(bs, drv, node_name, options, open_flags, errp); if (ret < 0) { - if (local_err) { - error_propagate(errp, local_err); - } else if (bs->filename[0]) { - error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename); - } else { - error_setg_errno(errp, -ret, "Could not open image"); - } - goto free_and_fail; + goto fail_opts; } - ret = refresh_total_sectors(bs, bs->total_sectors); - if (ret < 0) { - error_setg_errno(errp, -ret, "Could not refresh total sector count"); - goto free_and_fail; - } - - bdrv_refresh_limits(bs, &local_err); - if (local_err) { - error_propagate(errp, local_err); - ret = -EINVAL; - goto free_and_fail; - } - - assert(bdrv_opt_mem_align(bs) != 0); - assert(bdrv_min_mem_align(bs) != 0); - assert(is_power_of_2(bs->bl.request_alignment)); - qemu_opts_del(opts); return 0; -free_and_fail: - g_free(bs->opaque); - bs->opaque = NULL; - bs->drv = NULL; fail_opts: qemu_opts_del(opts); return ret; From 680c7f96062e8c9fcc560eaf06fce164e2a564bc Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Wed, 18 Jan 2017 17:16:41 +0100 Subject: [PATCH 17/19] block: Add bdrv_new_open_driver() This function allows to create more or less normal BlockDriverStates even for BlockDrivers that aren't globally registered (e.g. helper filters for block jobs). Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block.c | 30 +++++++++++++++++++++++++++++- include/block/block.h | 2 ++ 2 files changed, 31 insertions(+), 1 deletion(-) diff --git a/block.c b/block.c index f96d26b795..1368cf5409 100644 --- a/block.c +++ b/block.c @@ -939,13 +939,16 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv, } bs->drv = drv; + bs->read_only = !(bs->open_flags & BDRV_O_RDWR); bs->opaque = g_malloc0(drv->instance_size); if (drv->bdrv_file_open) { assert(!drv->bdrv_needs_filename || bs->filename[0]); ret = drv->bdrv_file_open(bs, options, open_flags, &local_err); - } else { + } else if (drv->bdrv_open) { ret = drv->bdrv_open(bs, options, open_flags, &local_err); + } else { + ret = 0; } if (ret < 0) { @@ -986,6 +989,31 @@ free_and_fail: return ret; } +BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, + int flags, Error **errp) +{ + BlockDriverState *bs; + int ret; + + bs = bdrv_new(); + bs->open_flags = flags; + bs->explicit_options = qdict_new(); + bs->options = qdict_new(); + bs->opaque = NULL; + + update_options_from_flags(bs->options, flags); + + ret = bdrv_open_driver(bs, drv, node_name, bs->options, flags, errp); + if (ret < 0) { + QDECREF(bs->explicit_options); + QDECREF(bs->options); + bdrv_unref(bs); + return NULL; + } + + return bs; +} + QemuOptsList bdrv_runtime_opts = { .name = "bdrv_common", .head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head), diff --git a/include/block/block.h b/include/block/block.h index a4cd06f884..bde5ebda18 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -215,6 +215,8 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options, const char *bdref_key, Error **errp); BlockDriverState *bdrv_open(const char *filename, const char *reference, QDict *options, int flags, Error **errp); +BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, + int flags, Error **errp); BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, BlockDriverState *bs, QDict *options, int flags); From a8a4d15c1c34d3cec704fb64eba4a3745a140a97 Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Wed, 15 Feb 2017 20:51:58 +0100 Subject: [PATCH 18/19] vvfat: Use opened node as backing file We should not try to assign a not yet opened node as the backing file, because as soon as the permission system is added it will fail. The just added bdrv_new_open_driver() function is the right tool to open a file with an internal driver, use it. In case anyone wonders whether that magic fake backing file to trigger a special action on 'commit' actually works today: No, not for me. One reason is that we've been adding a raw format driver on top for several years now and raw doesn't support commit. Other reasons include that the backing file isn't writable and the driver doesn't support reopen, and it's also size 0 and the driver doesn't support bdrv_truncate. All of these are easily fixable, but then 'commit' ended up in an infinite loop deep in the vvfat code for me, so I thought I'd best leave it alone. I'm not really sure what it was supposed to do anyway. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- block/vvfat.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/block/vvfat.c b/block/vvfat.c index c6bf67e8f3..7f230be006 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -2968,6 +2968,7 @@ static void write_target_close(BlockDriverState *bs) { static BlockDriver vvfat_write_target = { .format_name = "vvfat_write_target", + .instance_size = sizeof(void*), .bdrv_co_pwritev = write_target_commit, .bdrv_close = write_target_close, }; @@ -3036,14 +3037,13 @@ static int enable_write_target(BlockDriverState *bs, Error **errp) unlink(s->qcow_filename); #endif - backing = bdrv_new(); + backing = bdrv_new_open_driver(&vvfat_write_target, NULL, BDRV_O_ALLOW_RDWR, + &error_abort); + *(void**) backing->opaque = s; + bdrv_set_backing_hd(s->bs, backing); bdrv_unref(backing); - s->bs->backing->bs->drv = &vvfat_write_target; - s->bs->backing->bs->opaque = g_new(void *, 1); - *(void**)s->bs->backing->bs->opaque = s; - return 0; err: From d185cf0ec64cd183218ca7e0810d9130c96ebebc Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Mon, 16 Jan 2017 17:17:38 +0100 Subject: [PATCH 19/19] tests: Use opened block node for block job tests blk_insert_bs() and block job related functions will soon require an opened block node (permission calculations will involve the block driver), so let our tests be consistent with the real users in this respect. Signed-off-by: Kevin Wolf Reviewed-by: Max Reitz --- tests/test-blockjob-txn.c | 6 +++++- tests/test-blockjob.c | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/tests/test-blockjob-txn.c b/tests/test-blockjob-txn.c index b132e39097..f6dfd08746 100644 --- a/tests/test-blockjob-txn.c +++ b/tests/test-blockjob-txn.c @@ -96,7 +96,10 @@ static BlockJob *test_block_job_start(unsigned int iterations, char job_id[24]; data = g_new0(TestBlockJobCBData, 1); - bs = bdrv_new(); + + bs = bdrv_open("null-co://", NULL, NULL, 0, &error_abort); + g_assert_nonnull(bs); + snprintf(job_id, sizeof(job_id), "job%u", counter++); s = block_job_create(job_id, &test_block_job_driver, bs, 0, BLOCK_JOB_DEFAULT, test_block_job_cb, @@ -242,6 +245,7 @@ static void test_pair_jobs_fail_cancel_race(void) int main(int argc, char **argv) { qemu_init_main_loop(&error_abort); + bdrv_init(); g_test_init(&argc, &argv, NULL); g_test_add_func("/single/success", test_single_job_success); diff --git a/tests/test-blockjob.c b/tests/test-blockjob.c index 60b78a3342..068c9e419b 100644 --- a/tests/test-blockjob.c +++ b/tests/test-blockjob.c @@ -54,7 +54,10 @@ static BlockJob *do_test_id(BlockBackend *blk, const char *id, static BlockBackend *create_blk(const char *name) { BlockBackend *blk = blk_new(); - BlockDriverState *bs = bdrv_new(); + BlockDriverState *bs; + + bs = bdrv_open("null-co://", NULL, NULL, 0, &error_abort); + g_assert_nonnull(bs); blk_insert_bs(blk, bs); bdrv_unref(bs); @@ -140,6 +143,7 @@ static void test_job_ids(void) int main(int argc, char **argv) { qemu_init_main_loop(&error_abort); + bdrv_init(); g_test_init(&argc, &argv, NULL); g_test_add_func("/blockjob/ids", test_job_ids);