The following changes since commit b2f7a038bb4c4fc5ce6b8486e8513dfd97665e2a: Merge remote-tracking branch 'remotes/rth/tags/pull-softfloat-20181104' into staging (2018-11-05 10:32:49 +0000) are available in the Git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to 1240ac558d348f6c7a5752b1a57c1da58e4efe3e: include: Add a comment to explain the origin of sizes' lookup table (2018-11-05 15:29:59 +0100) ---------------------------------------------------------------- Block layer patches: - auto-read-only option to fix commit job when used with -blockdev - Fix help text related qemu-iotests failure (by improving the help text and updating the reference output) - quorum: Add missing checks when adding/removing child nodes - Don't take address of fields in packed structs - vvfat: Fix crash when reporting error about too many files in directory ---------------------------------------------------------------- Alberto Garcia (7): block: replace "discard" literal with BDRV_OPT_DISCARD macro qcow2: Get the request alignment for encrypted images from QCryptoBlock quorum: Remove quorum_err() quorum: Return an error if the blkverify mode has invalid settings iotest: Test the blkverify mode of the Quorum driver quorum: Forbid adding children in blkverify mode iotest: Test x-blockdev-change on a Quorum Cleber Rosa (1): iotests: make 083 specific to raw Daniel P. Berrangé (1): crypto: initialize sector size even when opening with no IO flag Kevin Wolf (12): vpc: Don't leak opts in vpc_open() block: Update flags in bdrv_set_read_only() block: Add auto-read-only option rbd: Close image in qemu_rbd_open() error path block: Require auto-read-only for existing fallbacks nbd: Support auto-read-only option file-posix: Support auto-read-only option curl: Support auto-read-only option gluster: Support auto-read-only option iscsi: Support auto-read-only option block: Make auto-read-only=on default for -drive qemu-iotests: Test auto-read-only with -drive and -blockdev Leonid Bloch (2): vdi: Use a literal number of bytes for DEFAULT_CLUSTER_SIZE include: Add a comment to explain the origin of sizes' lookup table Li Qiang (1): block: change some function return type to bool Max Reitz (5): option: Make option help nicer to read chardev: Indent list of chardevs qdev-monitor: Make device options help nicer object: Make option help nicer to read fw_cfg: Drop newline in @file description Peter Maydell (5): block/qcow2: Don't take address of fields in packed structs block/qcow: Don't take address of fields in packed structs block/qcow2-bitmap: Don't take address of fields in packed structs block/vhdx: Don't take address of fields in packed structs block/vdi: Don't take address of fields in packed structs Stefan Weil (1): qemu-io-cmds: Fix two format strings Thomas Huth (1): block/vvfat: Fix crash when reporting error about too many files in directory qapi/block-core.json | 7 + block/vhdx.h | 12 +- include/block/block.h | 5 +- include/qemu/option.h | 2 +- include/qemu/units.h | 18 + include/sysemu/block-backend.h | 6 +- block.c | 60 ++- block/block-backend.c | 8 +- block/bochs.c | 17 +- block/cloop.c | 16 +- block/curl.c | 8 +- block/dmg.c | 16 +- block/file-posix.c | 19 +- block/gluster.c | 12 +- block/iscsi.c | 8 +- block/nbd-client.c | 10 +- block/qcow.c | 18 +- block/qcow2-bitmap.c | 24 +- block/qcow2.c | 66 +-- block/quorum.c | 45 +- block/rbd.c | 14 +- block/vdi.c | 68 +-- block/vhdx-endian.c | 118 ++--- block/vhdx-log.c | 4 +- block/vhdx.c | 18 +- block/vpc.c | 2 + block/vvfat.c | 15 +- blockdev.c | 3 +- chardev/char.c | 2 +- crypto/block-qcow.c | 2 + qdev-monitor.c | 13 +- qemu-img.c | 4 +- qemu-io-cmds.c | 4 +- util/qemu-option.c | 32 +- vl.c | 15 +- tests/qemu-iotests/081 | 116 +++++ tests/qemu-iotests/081.out | 70 +++ tests/qemu-iotests/082.out | 956 ++++++++++++++++++++--------------------- tests/qemu-iotests/083 | 2 +- tests/qemu-iotests/232 | 147 +++++++ tests/qemu-iotests/232.out | 59 +++ tests/qemu-iotests/group | 1 + 42 files changed, 1266 insertions(+), 776 deletions(-) create mode 100755 tests/qemu-iotests/232 create mode 100644 tests/qemu-iotests/232.out From: Thomas Huth <thuth@redhat.com> When using the vvfat driver with a directory that contains too many files, QEMU currently crashes. This can be triggered like this for example: mkdir /tmp/vvfattest cd /tmp/vvfattest for ((x=0;x<=513;x++)); do mkdir $x; done qemu-system-x86_64 -drive \ file.driver=vvfat,file.dir=.,read-only=on,media=cdrom Seems like read_directory() is changing the mapping->path variable. Make sure we use the right pointer instead. Signed-off-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vvfat.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ static int init_directories(BDRVVVFATState* s, mapping = array_get(&(s->mapping), i); if (mapping->mode & MODE_DIRECTORY) { + char *path = mapping->path; mapping->begin = cluster; if(read_directory(s, i)) { - error_setg(errp, "Could not read directory %s", - mapping->path); + error_setg(errp, "Could not read directory %s", path); return -1; } mapping = array_get(&(s->mapping), i); -- 2.19.1 From: Alberto Garcia <berto@igalia.com> Signed-off-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ QemuOptsList bdrv_runtime_opts = { .help = "try to optimize zero writes (off, on, unmap)", }, { - .name = "discard", + .name = BDRV_OPT_DISCARD, .type = QEMU_OPT_STRING, .help = "discard operation (ignore/off, unmap/on)", }, @@ -XXX,XX +XXX,XX @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, } } - discard = qemu_opt_get(opts, "discard"); + discard = qemu_opt_get(opts, BDRV_OPT_DISCARD); if (discard != NULL) { if (bdrv_parse_discard_flags(discard, &bs->open_flags) != 0) { error_setg(errp, "Invalid discard option"); @@ -XXX,XX +XXX,XX @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, update_flags_from_options(&reopen_state->flags, opts); - discard = qemu_opt_get_del(opts, "discard"); + discard = qemu_opt_get_del(opts, BDRV_OPT_DISCARD); if (discard != NULL) { if (bdrv_parse_discard_flags(discard, &reopen_state->flags) != 0) { error_setg(errp, "Invalid discard option"); -- 2.19.1 From: Stefan Weil <sw@weilnetz.de> Use %zu instead of %zd for unsigned numbers. This fixes two error messages from the LSTM static code analyzer: This argument should be of type 'ssize_t' but is of type 'unsigned long' Signed-off-by: Stefan Weil <sw@weilnetz.de> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-io-cmds.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int readv_f(BlockBackend *blk, int argc, char **argv) memset(cmp_buf, pattern, qiov.size); if (memcmp(buf, cmp_buf, qiov.size)) { printf("Pattern verification failed at offset %" - PRId64 ", %zd bytes\n", offset, qiov.size); + PRId64 ", %zu bytes\n", offset, qiov.size); ret = -EINVAL; } g_free(cmp_buf); @@ -XXX,XX +XXX,XX @@ static void aio_read_done(void *opaque, int ret) memset(cmp_buf, ctx->pattern, ctx->qiov.size); if (memcmp(ctx->buf, cmp_buf, ctx->qiov.size)) { printf("Pattern verification failed at offset %" - PRId64 ", %zd bytes\n", ctx->offset, ctx->qiov.size); + PRId64 ", %zu bytes\n", ctx->offset, ctx->qiov.size); } g_free(cmp_buf); } -- 2.19.1 From: Peter Maydell <peter.maydell@linaro.org> Taking the address of a field in a packed struct is a bad idea, because it might not be actually aligned enough for that pointer type (and thus cause a crash on dereference on some host architectures). Newer versions of clang warn about this. Avoid the bug by not using the "modify in place" byte swapping functions. There are a few places where the in-place swap function is used on something other than a packed struct field; we convert those anyway, for consistency. This patch was produced with the following spatch script (and hand-editing to fold a few resulting overlength lines): @@ expression E; @@ -be16_to_cpus(&E); +E = be16_to_cpu(E); @@ expression E; @@ -be32_to_cpus(&E); +E = be32_to_cpu(E); @@ expression E; @@ -be64_to_cpus(&E); +E = be64_to_cpu(E); @@ expression E; @@ -cpu_to_be16s(&E); +E = cpu_to_be16(E); @@ expression E; @@ -cpu_to_be32s(&E); +E = cpu_to_be32(E); @@ expression E; @@ -cpu_to_be64s(&E); +E = cpu_to_be64(E); Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: John Snow <jsnow@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 64 +++++++++++++++++++++++++++------------------------ 1 file changed, 34 insertions(+), 30 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, "pread fail from offset %" PRIu64, offset); return 1; } - be32_to_cpus(&ext.magic); - be32_to_cpus(&ext.len); + ext.magic = be32_to_cpu(ext.magic); + ext.len = be32_to_cpu(ext.len); offset += sizeof(ext); #ifdef DEBUG_EXT printf("ext.magic = 0x%x\n", ext.magic); @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, "Unable to read CRYPTO header extension"); return ret; } - be64_to_cpus(&s->crypto_header.offset); - be64_to_cpus(&s->crypto_header.length); + s->crypto_header.offset = be64_to_cpu(s->crypto_header.offset); + s->crypto_header.length = be64_to_cpu(s->crypto_header.length); if ((s->crypto_header.offset % s->cluster_size) != 0) { error_setg(errp, "Encryption header offset '%" PRIu64 "' is " @@ -XXX,XX +XXX,XX @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, return -EINVAL; } - be32_to_cpus(&bitmaps_ext.nb_bitmaps); - be64_to_cpus(&bitmaps_ext.bitmap_directory_size); - be64_to_cpus(&bitmaps_ext.bitmap_directory_offset); + bitmaps_ext.nb_bitmaps = be32_to_cpu(bitmaps_ext.nb_bitmaps); + bitmaps_ext.bitmap_directory_size = + be64_to_cpu(bitmaps_ext.bitmap_directory_size); + bitmaps_ext.bitmap_directory_offset = + be64_to_cpu(bitmaps_ext.bitmap_directory_offset); if (bitmaps_ext.nb_bitmaps > QCOW2_MAX_BITMAPS) { error_setg(errp, @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, error_setg_errno(errp, -ret, "Could not read qcow2 header"); goto fail; } - be32_to_cpus(&header.magic); - be32_to_cpus(&header.version); - be64_to_cpus(&header.backing_file_offset); - be32_to_cpus(&header.backing_file_size); - be64_to_cpus(&header.size); - be32_to_cpus(&header.cluster_bits); - be32_to_cpus(&header.crypt_method); - be64_to_cpus(&header.l1_table_offset); - be32_to_cpus(&header.l1_size); - be64_to_cpus(&header.refcount_table_offset); - be32_to_cpus(&header.refcount_table_clusters); - be64_to_cpus(&header.snapshots_offset); - be32_to_cpus(&header.nb_snapshots); + header.magic = be32_to_cpu(header.magic); + header.version = be32_to_cpu(header.version); + header.backing_file_offset = be64_to_cpu(header.backing_file_offset); + header.backing_file_size = be32_to_cpu(header.backing_file_size); + header.size = be64_to_cpu(header.size); + header.cluster_bits = be32_to_cpu(header.cluster_bits); + header.crypt_method = be32_to_cpu(header.crypt_method); + header.l1_table_offset = be64_to_cpu(header.l1_table_offset); + header.l1_size = be32_to_cpu(header.l1_size); + header.refcount_table_offset = be64_to_cpu(header.refcount_table_offset); + header.refcount_table_clusters = + be32_to_cpu(header.refcount_table_clusters); + header.snapshots_offset = be64_to_cpu(header.snapshots_offset); + header.nb_snapshots = be32_to_cpu(header.nb_snapshots); if (header.magic != QCOW_MAGIC) { error_setg(errp, "Image is not in qcow2 format"); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, header.refcount_order = 4; header.header_length = 72; } else { - be64_to_cpus(&header.incompatible_features); - be64_to_cpus(&header.compatible_features); - be64_to_cpus(&header.autoclear_features); - be32_to_cpus(&header.refcount_order); - be32_to_cpus(&header.header_length); + header.incompatible_features = + be64_to_cpu(header.incompatible_features); + header.compatible_features = be64_to_cpu(header.compatible_features); + header.autoclear_features = be64_to_cpu(header.autoclear_features); + header.refcount_order = be32_to_cpu(header.refcount_order); + header.header_length = be32_to_cpu(header.header_length); if (header.header_length < 104) { error_setg(errp, "qcow2 header too short"); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, goto fail; } for(i = 0;i < s->l1_size; i++) { - be64_to_cpus(&s->l1_table[i]); + s->l1_table[i] = be64_to_cpu(s->l1_table[i]); } } @@ -XXX,XX +XXX,XX @@ int qcow2_update_header(BlockDriverState *bs) /* Full disk encryption header pointer extension */ if (s->crypto_header.offset != 0) { - cpu_to_be64s(&s->crypto_header.offset); - cpu_to_be64s(&s->crypto_header.length); + s->crypto_header.offset = cpu_to_be64(s->crypto_header.offset); + s->crypto_header.length = cpu_to_be64(s->crypto_header.length); ret = header_ext_add(buf, QCOW2_EXT_MAGIC_CRYPTO_HEADER, &s->crypto_header, sizeof(s->crypto_header), buflen); - be64_to_cpus(&s->crypto_header.offset); - be64_to_cpus(&s->crypto_header.length); + s->crypto_header.offset = be64_to_cpu(s->crypto_header.offset); + s->crypto_header.length = be64_to_cpu(s->crypto_header.length); if (ret < 0) { goto fail; } -- 2.19.1 From: Peter Maydell <peter.maydell@linaro.org> Taking the address of a field in a packed struct is a bad idea, because it might not be actually aligned enough for that pointer type (and thus cause a crash on dereference on some host architectures). Newer versions of clang warn about this. Avoid the bug by not using the "modify in place" byte swapping functions. There are a few places where the in-place swap function is used on something other than a packed struct field; we convert those anyway, for consistency. This patch was produced with the following spatch script: @@ expression E; @@ -be16_to_cpus(&E); +E = be16_to_cpu(E); @@ expression E; @@ -be32_to_cpus(&E); +E = be32_to_cpu(E); @@ expression E; @@ -be64_to_cpus(&E); +E = be64_to_cpu(E); @@ expression E; @@ -cpu_to_be16s(&E); +E = cpu_to_be16(E); @@ expression E; @@ -cpu_to_be32s(&E); +E = cpu_to_be32(E); @@ expression E; @@ -cpu_to_be64s(&E); +E = cpu_to_be64(E); Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: John Snow <jsnow@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, if (ret < 0) { goto fail; } - be32_to_cpus(&header.magic); - be32_to_cpus(&header.version); - be64_to_cpus(&header.backing_file_offset); - be32_to_cpus(&header.backing_file_size); - be32_to_cpus(&header.mtime); - be64_to_cpus(&header.size); - be32_to_cpus(&header.crypt_method); - be64_to_cpus(&header.l1_table_offset); + header.magic = be32_to_cpu(header.magic); + header.version = be32_to_cpu(header.version); + header.backing_file_offset = be64_to_cpu(header.backing_file_offset); + header.backing_file_size = be32_to_cpu(header.backing_file_size); + header.mtime = be32_to_cpu(header.mtime); + header.size = be64_to_cpu(header.size); + header.crypt_method = be32_to_cpu(header.crypt_method); + header.l1_table_offset = be64_to_cpu(header.l1_table_offset); if (header.magic != QCOW_MAGIC) { error_setg(errp, "Image not in qcow format"); @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, } for(i = 0;i < s->l1_size; i++) { - be64_to_cpus(&s->l1_table[i]); + s->l1_table[i] = be64_to_cpu(s->l1_table[i]); } /* alloc L2 cache (max. 64k * 16 * 8 = 8 MB) */ -- 2.19.1 From: Peter Maydell <peter.maydell@linaro.org> Taking the address of a field in a packed struct is a bad idea, because it might not be actually aligned enough for that pointer type (and thus cause a crash on dereference on some host architectures). Newer versions of clang warn about this. Avoid the bug by not using the "modify in place" byte swapping functions. There are a few places where the in-place swap function is used on something other than a packed struct field; we convert those anyway, for consistency. This patch was produced with the following spatch script: @@ expression E; @@ -be16_to_cpus(&E); +E = be16_to_cpu(E); @@ expression E; @@ -be32_to_cpus(&E); +E = be32_to_cpu(E); @@ expression E; @@ -be64_to_cpus(&E); +E = be64_to_cpu(E); @@ expression E; @@ -cpu_to_be16s(&E); +E = cpu_to_be16(E); @@ expression E; @@ -cpu_to_be32s(&E); +E = cpu_to_be32(E); @@ expression E; @@ -cpu_to_be64s(&E); +E = cpu_to_be64(E); Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: John Snow <jsnow@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-bitmap.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -XXX,XX +XXX,XX @@ static inline void bitmap_table_to_be(uint64_t *bitmap_table, size_t size) size_t i; for (i = 0; i < size; ++i) { - cpu_to_be64s(&bitmap_table[i]); + bitmap_table[i] = cpu_to_be64(bitmap_table[i]); } } @@ -XXX,XX +XXX,XX @@ static int bitmap_table_load(BlockDriverState *bs, Qcow2BitmapTable *tb, } for (i = 0; i < tb->size; ++i) { - be64_to_cpus(&table[i]); + table[i] = be64_to_cpu(table[i]); ret = check_table_entry(table[i], s->cluster_size); if (ret < 0) { goto fail; @@ -XXX,XX +XXX,XX @@ fail: static inline void bitmap_dir_entry_to_cpu(Qcow2BitmapDirEntry *entry) { - be64_to_cpus(&entry->bitmap_table_offset); - be32_to_cpus(&entry->bitmap_table_size); - be32_to_cpus(&entry->flags); - be16_to_cpus(&entry->name_size); - be32_to_cpus(&entry->extra_data_size); + entry->bitmap_table_offset = be64_to_cpu(entry->bitmap_table_offset); + entry->bitmap_table_size = be32_to_cpu(entry->bitmap_table_size); + entry->flags = be32_to_cpu(entry->flags); + entry->name_size = be16_to_cpu(entry->name_size); + entry->extra_data_size = be32_to_cpu(entry->extra_data_size); } static inline void bitmap_dir_entry_to_be(Qcow2BitmapDirEntry *entry) { - cpu_to_be64s(&entry->bitmap_table_offset); - cpu_to_be32s(&entry->bitmap_table_size); - cpu_to_be32s(&entry->flags); - cpu_to_be16s(&entry->name_size); - cpu_to_be32s(&entry->extra_data_size); + entry->bitmap_table_offset = cpu_to_be64(entry->bitmap_table_offset); + entry->bitmap_table_size = cpu_to_be32(entry->bitmap_table_size); + entry->flags = cpu_to_be32(entry->flags); + entry->name_size = cpu_to_be16(entry->name_size); + entry->extra_data_size = cpu_to_be32(entry->extra_data_size); } static inline int calc_dir_entry_size(size_t name_size, size_t extra_data_size) -- 2.19.1 From: Daniel P. Berrangé <berrange@redhat.com> The qcow2 block driver expects to see a valid sector size even when it has opened the crypto layer with QCRYPTO_BLOCK_OPEN_NO_IO. Signed-off-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- crypto/block-qcow.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/crypto/block-qcow.c b/crypto/block-qcow.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block-qcow.c +++ b/crypto/block-qcow.c @@ -XXX,XX +XXX,XX @@ qcrypto_block_qcow_open(QCryptoBlock *block, Error **errp) { if (flags & QCRYPTO_BLOCK_OPEN_NO_IO) { + block->sector_size = QCRYPTO_BLOCK_QCOW_SECTOR_SIZE; + block->payload_offset = 0; return 0; } else { if (!options->u.qcow.key_secret) { -- 2.19.1 From: Alberto Garcia <berto@igalia.com> This doesn't have any practical effect at the moment because the values of BDRV_SECTOR_SIZE, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE and QCRYPTO_BLOCK_QCOW_SECTOR_SIZE are all the same (512 bytes), but future encryption methods could have different requirements. Signed-off-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp) if (bs->encrypted) { /* Encryption works on a sector granularity */ - bs->bl.request_alignment = BDRV_SECTOR_SIZE; + bs->bl.request_alignment = qcrypto_block_get_sector_size(s->crypto); } bs->bl.pwrite_zeroes_alignment = s->cluster_size; bs->bl.pdiscard_alignment = s->cluster_size; -- 2.19.1 From: Li Qiang <liq3ea@163.com> Signed-off-by: Li Qiang <liq3ea@163.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/sysemu/block-backend.h | 6 +++--- block/block-backend.c | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -XXX,XX +XXX,XX @@ BlockErrorAction blk_get_error_action(BlockBackend *blk, bool is_read, int error); void blk_error_action(BlockBackend *blk, BlockErrorAction action, bool is_read, int error); -int blk_is_read_only(BlockBackend *blk); -int blk_is_sg(BlockBackend *blk); -int blk_enable_write_cache(BlockBackend *blk); +bool blk_is_read_only(BlockBackend *blk); +bool blk_is_sg(BlockBackend *blk); +bool blk_enable_write_cache(BlockBackend *blk); void blk_set_enable_write_cache(BlockBackend *blk, bool wce); void blk_invalidate_cache(BlockBackend *blk, Error **errp); bool blk_is_inserted(BlockBackend *blk); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ void blk_error_action(BlockBackend *blk, BlockErrorAction action, } } -int blk_is_read_only(BlockBackend *blk) +bool blk_is_read_only(BlockBackend *blk) { BlockDriverState *bs = blk_bs(blk); @@ -XXX,XX +XXX,XX @@ int blk_is_read_only(BlockBackend *blk) } } -int blk_is_sg(BlockBackend *blk) +bool blk_is_sg(BlockBackend *blk) { BlockDriverState *bs = blk_bs(blk); if (!bs) { - return 0; + return false; } return bdrv_is_sg(bs); } -int blk_enable_write_cache(BlockBackend *blk) +bool blk_enable_write_cache(BlockBackend *blk) { return blk->enable_write_cache; } -- 2.19.1 From: Cleber Rosa <crosa@redhat.com> While testing the Python 3 changes which touch the 083 test, I noticed that it would fail with qcow2. Expanding the testing, I noticed it had nothing to do with the Python 3 changes, and in fact, it would not pass on anything but raw: raw: pass bochs: not generic cloop: not generic parallels: fail qcow: fail qcow2: fail qed: fail vdi: fail vhdx: fail vmdk: fail vpc: fail luks: fail The errors are a mixture I/O and "image not in xxx format", such as: === Check disconnect before data === Unexpected end-of-file before all bytes were read -read failed: Input/output error +can't open device nbd+tcp://127.0.0.1:PORT/foo: Could not open 'nbd://127.0.0.1:PORT/foo': Input/output error === Check disconnect after data === -read 512/512 bytes at offset 0 -512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +can't open device nbd+tcp://127.0.0.1:PORT/foo: Image not in qcow format I'm not aware if there's a quick fix, so, for the time being, it looks like the honest approach is to make the test known to work on raw only. Signed-off-by: Cleber Rosa <crosa@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/083 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/083 b/tests/qemu-iotests/083 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/083 +++ b/tests/qemu-iotests/083 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -_supported_fmt generic +_supported_fmt raw _supported_proto nbd _supported_os Linux -- 2.19.1 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> --- block/vpc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, } qemu_co_mutex_init(&s->lock); + qemu_opts_del(opts); return 0; fail: + qemu_opts_del(opts); qemu_vfree(s->pagetable); #ifdef CACHE g_free(s->pageentry_u8); -- 2.19.1 From: Peter Maydell <peter.maydell@linaro.org> Taking the address of a field in a packed struct is a bad idea, because it might not be actually aligned enough for that pointer type (and thus cause a crash on dereference on some host architectures). Newer versions of clang warn about this. Avoid the bug by not using the "modify in place" byte swapping functions. There are a few places where the in-place swap function is used on something other than a packed struct field; we convert those anyway, for consistency. Patch produced with scripts/coccinelle/inplace-byteswaps.cocci. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vhdx.h | 12 ++--- block/vhdx-endian.c | 118 ++++++++++++++++++++++---------------------- block/vhdx-log.c | 4 +- block/vhdx.c | 18 +++---- 4 files changed, 76 insertions(+), 76 deletions(-) diff --git a/block/vhdx.h b/block/vhdx.h index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.h +++ b/block/vhdx.h @@ -XXX,XX +XXX,XX @@ int vhdx_log_write_and_flush(BlockDriverState *bs, BDRVVHDXState *s, static inline void leguid_to_cpus(MSGUID *guid) { - le32_to_cpus(&guid->data1); - le16_to_cpus(&guid->data2); - le16_to_cpus(&guid->data3); + guid->data1 = le32_to_cpu(guid->data1); + guid->data2 = le16_to_cpu(guid->data2); + guid->data3 = le16_to_cpu(guid->data3); } static inline void cpu_to_leguids(MSGUID *guid) { - cpu_to_le32s(&guid->data1); - cpu_to_le16s(&guid->data2); - cpu_to_le16s(&guid->data3); + guid->data1 = cpu_to_le32(guid->data1); + guid->data2 = cpu_to_le16(guid->data2); + guid->data3 = cpu_to_le16(guid->data3); } void vhdx_header_le_import(VHDXHeader *h); diff --git a/block/vhdx-endian.c b/block/vhdx-endian.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx-endian.c +++ b/block/vhdx-endian.c @@ -XXX,XX +XXX,XX @@ void vhdx_header_le_import(VHDXHeader *h) { assert(h != NULL); - le32_to_cpus(&h->signature); - le32_to_cpus(&h->checksum); - le64_to_cpus(&h->sequence_number); + h->signature = le32_to_cpu(h->signature); + h->checksum = le32_to_cpu(h->checksum); + h->sequence_number = le64_to_cpu(h->sequence_number); leguid_to_cpus(&h->file_write_guid); leguid_to_cpus(&h->data_write_guid); leguid_to_cpus(&h->log_guid); - le16_to_cpus(&h->log_version); - le16_to_cpus(&h->version); - le32_to_cpus(&h->log_length); - le64_to_cpus(&h->log_offset); + h->log_version = le16_to_cpu(h->log_version); + h->version = le16_to_cpu(h->version); + h->log_length = le32_to_cpu(h->log_length); + h->log_offset = le64_to_cpu(h->log_offset); } void vhdx_header_le_export(VHDXHeader *orig_h, VHDXHeader *new_h) @@ -XXX,XX +XXX,XX @@ void vhdx_log_desc_le_import(VHDXLogDescriptor *d) { assert(d != NULL); - le32_to_cpus(&d->signature); - le64_to_cpus(&d->file_offset); - le64_to_cpus(&d->sequence_number); + d->signature = le32_to_cpu(d->signature); + d->file_offset = le64_to_cpu(d->file_offset); + d->sequence_number = le64_to_cpu(d->sequence_number); } void vhdx_log_desc_le_export(VHDXLogDescriptor *d) { assert(d != NULL); - cpu_to_le32s(&d->signature); - cpu_to_le32s(&d->trailing_bytes); - cpu_to_le64s(&d->leading_bytes); - cpu_to_le64s(&d->file_offset); - cpu_to_le64s(&d->sequence_number); + d->signature = cpu_to_le32(d->signature); + d->trailing_bytes = cpu_to_le32(d->trailing_bytes); + d->leading_bytes = cpu_to_le64(d->leading_bytes); + d->file_offset = cpu_to_le64(d->file_offset); + d->sequence_number = cpu_to_le64(d->sequence_number); } void vhdx_log_data_le_import(VHDXLogDataSector *d) { assert(d != NULL); - le32_to_cpus(&d->data_signature); - le32_to_cpus(&d->sequence_high); - le32_to_cpus(&d->sequence_low); + d->data_signature = le32_to_cpu(d->data_signature); + d->sequence_high = le32_to_cpu(d->sequence_high); + d->sequence_low = le32_to_cpu(d->sequence_low); } void vhdx_log_data_le_export(VHDXLogDataSector *d) { assert(d != NULL); - cpu_to_le32s(&d->data_signature); - cpu_to_le32s(&d->sequence_high); - cpu_to_le32s(&d->sequence_low); + d->data_signature = cpu_to_le32(d->data_signature); + d->sequence_high = cpu_to_le32(d->sequence_high); + d->sequence_low = cpu_to_le32(d->sequence_low); } void vhdx_log_entry_hdr_le_import(VHDXLogEntryHeader *hdr) { assert(hdr != NULL); - le32_to_cpus(&hdr->signature); - le32_to_cpus(&hdr->checksum); - le32_to_cpus(&hdr->entry_length); - le32_to_cpus(&hdr->tail); - le64_to_cpus(&hdr->sequence_number); - le32_to_cpus(&hdr->descriptor_count); + hdr->signature = le32_to_cpu(hdr->signature); + hdr->checksum = le32_to_cpu(hdr->checksum); + hdr->entry_length = le32_to_cpu(hdr->entry_length); + hdr->tail = le32_to_cpu(hdr->tail); + hdr->sequence_number = le64_to_cpu(hdr->sequence_number); + hdr->descriptor_count = le32_to_cpu(hdr->descriptor_count); leguid_to_cpus(&hdr->log_guid); - le64_to_cpus(&hdr->flushed_file_offset); - le64_to_cpus(&hdr->last_file_offset); + hdr->flushed_file_offset = le64_to_cpu(hdr->flushed_file_offset); + hdr->last_file_offset = le64_to_cpu(hdr->last_file_offset); } void vhdx_log_entry_hdr_le_export(VHDXLogEntryHeader *hdr) { assert(hdr != NULL); - cpu_to_le32s(&hdr->signature); - cpu_to_le32s(&hdr->checksum); - cpu_to_le32s(&hdr->entry_length); - cpu_to_le32s(&hdr->tail); - cpu_to_le64s(&hdr->sequence_number); - cpu_to_le32s(&hdr->descriptor_count); + hdr->signature = cpu_to_le32(hdr->signature); + hdr->checksum = cpu_to_le32(hdr->checksum); + hdr->entry_length = cpu_to_le32(hdr->entry_length); + hdr->tail = cpu_to_le32(hdr->tail); + hdr->sequence_number = cpu_to_le64(hdr->sequence_number); + hdr->descriptor_count = cpu_to_le32(hdr->descriptor_count); cpu_to_leguids(&hdr->log_guid); - cpu_to_le64s(&hdr->flushed_file_offset); - cpu_to_le64s(&hdr->last_file_offset); + hdr->flushed_file_offset = cpu_to_le64(hdr->flushed_file_offset); + hdr->last_file_offset = cpu_to_le64(hdr->last_file_offset); } @@ -XXX,XX +XXX,XX @@ void vhdx_region_header_le_import(VHDXRegionTableHeader *hdr) { assert(hdr != NULL); - le32_to_cpus(&hdr->signature); - le32_to_cpus(&hdr->checksum); - le32_to_cpus(&hdr->entry_count); + hdr->signature = le32_to_cpu(hdr->signature); + hdr->checksum = le32_to_cpu(hdr->checksum); + hdr->entry_count = le32_to_cpu(hdr->entry_count); } void vhdx_region_header_le_export(VHDXRegionTableHeader *hdr) { assert(hdr != NULL); - cpu_to_le32s(&hdr->signature); - cpu_to_le32s(&hdr->checksum); - cpu_to_le32s(&hdr->entry_count); + hdr->signature = cpu_to_le32(hdr->signature); + hdr->checksum = cpu_to_le32(hdr->checksum); + hdr->entry_count = cpu_to_le32(hdr->entry_count); } void vhdx_region_entry_le_import(VHDXRegionTableEntry *e) @@ -XXX,XX +XXX,XX @@ void vhdx_region_entry_le_import(VHDXRegionTableEntry *e) assert(e != NULL); leguid_to_cpus(&e->guid); - le64_to_cpus(&e->file_offset); - le32_to_cpus(&e->length); - le32_to_cpus(&e->data_bits); + e->file_offset = le64_to_cpu(e->file_offset); + e->length = le32_to_cpu(e->length); + e->data_bits = le32_to_cpu(e->data_bits); } void vhdx_region_entry_le_export(VHDXRegionTableEntry *e) @@ -XXX,XX +XXX,XX @@ void vhdx_region_entry_le_export(VHDXRegionTableEntry *e) assert(e != NULL); cpu_to_leguids(&e->guid); - cpu_to_le64s(&e->file_offset); - cpu_to_le32s(&e->length); - cpu_to_le32s(&e->data_bits); + e->file_offset = cpu_to_le64(e->file_offset); + e->length = cpu_to_le32(e->length); + e->data_bits = cpu_to_le32(e->data_bits); } @@ -XXX,XX +XXX,XX @@ void vhdx_metadata_header_le_import(VHDXMetadataTableHeader *hdr) { assert(hdr != NULL); - le64_to_cpus(&hdr->signature); - le16_to_cpus(&hdr->entry_count); + hdr->signature = le64_to_cpu(hdr->signature); + hdr->entry_count = le16_to_cpu(hdr->entry_count); } void vhdx_metadata_header_le_export(VHDXMetadataTableHeader *hdr) { assert(hdr != NULL); - cpu_to_le64s(&hdr->signature); - cpu_to_le16s(&hdr->entry_count); + hdr->signature = cpu_to_le64(hdr->signature); + hdr->entry_count = cpu_to_le16(hdr->entry_count); } void vhdx_metadata_entry_le_import(VHDXMetadataTableEntry *e) @@ -XXX,XX +XXX,XX @@ void vhdx_metadata_entry_le_import(VHDXMetadataTableEntry *e) assert(e != NULL); leguid_to_cpus(&e->item_id); - le32_to_cpus(&e->offset); - le32_to_cpus(&e->length); - le32_to_cpus(&e->data_bits); + e->offset = le32_to_cpu(e->offset); + e->length = le32_to_cpu(e->length); + e->data_bits = le32_to_cpu(e->data_bits); } void vhdx_metadata_entry_le_export(VHDXMetadataTableEntry *e) { assert(e != NULL); cpu_to_leguids(&e->item_id); - cpu_to_le32s(&e->offset); - cpu_to_le32s(&e->length); - cpu_to_le32s(&e->data_bits); + e->offset = cpu_to_le32(e->offset); + e->length = cpu_to_le32(e->length); + e->data_bits = cpu_to_le32(e->data_bits); } diff --git a/block/vhdx-log.c b/block/vhdx-log.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -XXX,XX +XXX,XX @@ static void vhdx_log_raw_to_le_sector(VHDXLogDescriptor *desc, /* 8 + 4084 + 4 = 4096, 1 log sector */ memcpy(&desc->leading_bytes, data, 8); data += 8; - cpu_to_le64s(&desc->leading_bytes); + desc->leading_bytes = cpu_to_le64(desc->leading_bytes); memcpy(sector->data, data, 4084); data += 4084; memcpy(&desc->trailing_bytes, data, 4); - cpu_to_le32s(&desc->trailing_bytes); + desc->trailing_bytes = cpu_to_le32(desc->trailing_bytes); data += 4; sector->sequence_high = (uint32_t) (seq >> 32); diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset) memset(buf + crc_offset, 0, sizeof(crc)); crc = crc32c(0xffffffff, buf, size); - cpu_to_le32s(&crc); + crc = cpu_to_le32(crc); memcpy(buf + crc_offset, &crc, sizeof(crc)); return crc; @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) goto exit; } - le32_to_cpus(&s->params.block_size); - le32_to_cpus(&s->params.data_bits); + s->params.block_size = le32_to_cpu(s->params.block_size); + s->params.data_bits = le32_to_cpu(s->params.data_bits); /* We now have the file parameters, so we can tell if this is a @@ -XXX,XX +XXX,XX @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) goto exit; } - le64_to_cpus(&s->virtual_disk_size); - le32_to_cpus(&s->logical_sector_size); - le32_to_cpus(&s->physical_sector_size); + s->virtual_disk_size = le64_to_cpu(s->virtual_disk_size); + s->logical_sector_size = le32_to_cpu(s->logical_sector_size); + s->physical_sector_size = le32_to_cpu(s->physical_sector_size); if (s->params.block_size < VHDX_BLOCK_SIZE_MIN || s->params.block_size > VHDX_BLOCK_SIZE_MAX) { @@ -XXX,XX +XXX,XX @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, /* endian convert, and verify populated BAT field file offsets against * region table and log entries */ for (i = 0; i < s->bat_entries; i++) { - le64_to_cpus(&s->bat[i]); + s->bat[i] = le64_to_cpu(s->bat[i]); if (payblocks--) { /* payload bat entries */ if ((s->bat[i] & VHDX_BAT_STATE_BIT_MASK) == @@ -XXX,XX +XXX,XX @@ static int vhdx_create_new_metadata(BlockBackend *blk, mt_file_params->block_size = cpu_to_le32(block_size); if (type == VHDX_TYPE_FIXED) { mt_file_params->data_bits |= VHDX_PARAMS_LEAVE_BLOCKS_ALLOCED; - cpu_to_le32s(&mt_file_params->data_bits); + mt_file_params->data_bits = cpu_to_le32(mt_file_params->data_bits); } vhdx_guid_generate(&mt_page83->page_83_data); @@ -XXX,XX +XXX,XX @@ static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s, sinfo.file_offset = ROUND_UP(sinfo.file_offset, MiB); vhdx_update_bat_table_entry(blk_bs(blk), s, &sinfo, &unused, &unused, block_state); - cpu_to_le64s(&s->bat[sinfo.bat_idx]); + s->bat[sinfo.bat_idx] = cpu_to_le64(s->bat[sinfo.bat_idx]); sector_num += s->sectors_per_block; } ret = blk_pwrite(blk, file_offset, s->bat, length, 0); -- 2.19.1 From: Peter Maydell <peter.maydell@linaro.org> Taking the address of a field in a packed struct is a bad idea, because it might not be actually aligned enough for that pointer type (and thus cause a crash on dereference on some host architectures). Newer versions of clang warn about this. Avoid the bug by not using the "modify in place" byte swapping functions. There are a few places where the in-place swap function is used on something other than a packed struct field; we convert those anyway, for consistency. Patch produced with scripts/coccinelle/inplace-byteswaps.cocci. There are other places where we take the address of a packed member in this file for other purposes than passing it to a byteswap function (all the calls to qemu_uuid_*()); we leave those for now. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vdi.c | 64 ++++++++++++++++++++++++++--------------------------- 1 file changed, 32 insertions(+), 32 deletions(-) diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ typedef struct { static void vdi_header_to_cpu(VdiHeader *header) { - le32_to_cpus(&header->signature); - le32_to_cpus(&header->version); - le32_to_cpus(&header->header_size); - le32_to_cpus(&header->image_type); - le32_to_cpus(&header->image_flags); - le32_to_cpus(&header->offset_bmap); - le32_to_cpus(&header->offset_data); - le32_to_cpus(&header->cylinders); - le32_to_cpus(&header->heads); - le32_to_cpus(&header->sectors); - le32_to_cpus(&header->sector_size); - le64_to_cpus(&header->disk_size); - le32_to_cpus(&header->block_size); - le32_to_cpus(&header->block_extra); - le32_to_cpus(&header->blocks_in_image); - le32_to_cpus(&header->blocks_allocated); + header->signature = le32_to_cpu(header->signature); + header->version = le32_to_cpu(header->version); + header->header_size = le32_to_cpu(header->header_size); + header->image_type = le32_to_cpu(header->image_type); + header->image_flags = le32_to_cpu(header->image_flags); + header->offset_bmap = le32_to_cpu(header->offset_bmap); + header->offset_data = le32_to_cpu(header->offset_data); + header->cylinders = le32_to_cpu(header->cylinders); + header->heads = le32_to_cpu(header->heads); + header->sectors = le32_to_cpu(header->sectors); + header->sector_size = le32_to_cpu(header->sector_size); + header->disk_size = le64_to_cpu(header->disk_size); + header->block_size = le32_to_cpu(header->block_size); + header->block_extra = le32_to_cpu(header->block_extra); + header->blocks_in_image = le32_to_cpu(header->blocks_in_image); + header->blocks_allocated = le32_to_cpu(header->blocks_allocated); qemu_uuid_bswap(&header->uuid_image); qemu_uuid_bswap(&header->uuid_last_snap); qemu_uuid_bswap(&header->uuid_link); @@ -XXX,XX +XXX,XX @@ static void vdi_header_to_cpu(VdiHeader *header) static void vdi_header_to_le(VdiHeader *header) { - cpu_to_le32s(&header->signature); - cpu_to_le32s(&header->version); - cpu_to_le32s(&header->header_size); - cpu_to_le32s(&header->image_type); - cpu_to_le32s(&header->image_flags); - cpu_to_le32s(&header->offset_bmap); - cpu_to_le32s(&header->offset_data); - cpu_to_le32s(&header->cylinders); - cpu_to_le32s(&header->heads); - cpu_to_le32s(&header->sectors); - cpu_to_le32s(&header->sector_size); - cpu_to_le64s(&header->disk_size); - cpu_to_le32s(&header->block_size); - cpu_to_le32s(&header->block_extra); - cpu_to_le32s(&header->blocks_in_image); - cpu_to_le32s(&header->blocks_allocated); + header->signature = cpu_to_le32(header->signature); + header->version = cpu_to_le32(header->version); + header->header_size = cpu_to_le32(header->header_size); + header->image_type = cpu_to_le32(header->image_type); + header->image_flags = cpu_to_le32(header->image_flags); + header->offset_bmap = cpu_to_le32(header->offset_bmap); + header->offset_data = cpu_to_le32(header->offset_data); + header->cylinders = cpu_to_le32(header->cylinders); + header->heads = cpu_to_le32(header->heads); + header->sectors = cpu_to_le32(header->sectors); + header->sector_size = cpu_to_le32(header->sector_size); + header->disk_size = cpu_to_le64(header->disk_size); + header->block_size = cpu_to_le32(header->block_size); + header->block_extra = cpu_to_le32(header->block_extra); + header->blocks_in_image = cpu_to_le32(header->blocks_in_image); + header->blocks_allocated = cpu_to_le32(header->blocks_allocated); qemu_uuid_bswap(&header->uuid_image); qemu_uuid_bswap(&header->uuid_last_snap); qemu_uuid_bswap(&header->uuid_link); -- 2.19.1 From: Alberto Garcia <berto@igalia.com> This is a static function with only one caller, so there's no need to keep it. Inlining the code in quorum_compare() makes it much simpler. Signed-off-by: Alberto Garcia <berto@igalia.com> Reported-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static bool quorum_iovec_compare(QEMUIOVector *a, QEMUIOVector *b) return true; } -static void GCC_FMT_ATTR(2, 3) quorum_err(QuorumAIOCB *acb, - const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - fprintf(stderr, "quorum: offset=%" PRIu64 " bytes=%" PRIu64 " ", - acb->offset, acb->bytes); - vfprintf(stderr, fmt, ap); - fprintf(stderr, "\n"); - va_end(ap); - exit(1); -} - -static bool quorum_compare(QuorumAIOCB *acb, - QEMUIOVector *a, - QEMUIOVector *b) +static bool quorum_compare(QuorumAIOCB *acb, QEMUIOVector *a, QEMUIOVector *b) { BDRVQuorumState *s = acb->bs->opaque; ssize_t offset; @@ -XXX,XX +XXX,XX @@ static bool quorum_compare(QuorumAIOCB *acb, if (s->is_blkverify) { offset = qemu_iovec_compare(a, b); if (offset != -1) { - quorum_err(acb, "contents mismatch at offset %" PRIu64, - acb->offset + offset); + fprintf(stderr, "quorum: offset=%" PRIu64 " bytes=%" PRIu64 + " contents mismatch at offset %" PRIu64 "\n", + acb->offset, acb->bytes, acb->offset + offset); + exit(1); } return true; } -- 2.19.1 From: Alberto Garcia <berto@igalia.com> The blkverify mode of Quorum can only be enabled if the number of children is exactly two and the value of vote-threshold is also two. If the user tries to enable it but the other settings are incorrect then QEMU simply prints an error message to stderr and carries on disabling the blkverify setting. This patch makes quorum_open() fail and return an error in this case. Signed-off-by: Alberto Garcia <berto@igalia.com> Reported-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags, s->read_pattern = ret; if (s->read_pattern == QUORUM_READ_PATTERN_QUORUM) { - /* is the driver in blkverify mode */ - if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false) && - s->num_children == 2 && s->threshold == 2) { - s->is_blkverify = true; - } else if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false)) { - fprintf(stderr, "blkverify mode is set by setting blkverify=on " - "and using two files with vote_threshold=2\n"); + s->is_blkverify = qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false); + if (s->is_blkverify && (s->num_children != 2 || s->threshold != 2)) { + error_setg(&local_err, "blkverify=on can only be set if there are " + "exactly two files and vote-threshold is 2"); + ret = -EINVAL; + goto exit; } s->rewrite_corrupted = qemu_opt_get_bool(opts, QUORUM_OPT_REWRITE, -- 2.19.1 From: Alberto Garcia <berto@igalia.com> Signed-off-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/081 | 30 ++++++++++++++++++++++++++++++ tests/qemu-iotests/081.out | 16 ++++++++++++++++ 2 files changed, 46 insertions(+) diff --git a/tests/qemu-iotests/081 b/tests/qemu-iotests/081 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/081 +++ b/tests/qemu-iotests/081 @@ -XXX,XX +XXX,XX @@ echo "== checking that quorum is broken ==" $QEMU_IO -c "open -o $quorum" -c "read -P 0x32 0 $size" | _filter_qemu_io +echo +echo "== checking the blkverify mode with broken content ==" + +quorum="driver=raw,file.driver=quorum,file.vote-threshold=2,file.blkverify=on" +quorum="$quorum,file.children.0.file.filename=$TEST_DIR/1.raw" +quorum="$quorum,file.children.1.file.filename=$TEST_DIR/2.raw" +quorum="$quorum,file.children.0.driver=raw" +quorum="$quorum,file.children.1.driver=raw" + +$QEMU_IO -c "open -o $quorum" -c "read -P 0x32 0 $size" | _filter_qemu_io + +echo +echo "== writing the same data to both files ==" + +$QEMU_IO -c "write -P 0x32 0 $size" "$TEST_DIR/1.raw" | _filter_qemu_io +$QEMU_IO -c "write -P 0x32 0 $size" "$TEST_DIR/2.raw" | _filter_qemu_io + +echo +echo "== checking the blkverify mode with valid content ==" + +$QEMU_IO -c "open -o $quorum" -c "read -P 0x32 0 $size" | _filter_qemu_io + +echo +echo "== checking the blkverify mode with invalid settings ==" + +quorum="$quorum,file.children.2.file.filename=$TEST_DIR/3.raw" +quorum="$quorum,file.children.2.driver=raw" + +$QEMU_IO -c "open -o $quorum" | _filter_qemu_io + # success, all done echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/081.out b/tests/qemu-iotests/081.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/081.out +++ b/tests/qemu-iotests/081.out @@ -XXX,XX +XXX,XX @@ wrote 10485760/10485760 bytes at offset 0 == checking that quorum is broken == read failed: Input/output error + +== checking the blkverify mode with broken content == +quorum: offset=0 bytes=10485760 contents mismatch at offset 0 + +== writing the same data to both files == +wrote 10485760/10485760 bytes at offset 0 +10 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 10485760/10485760 bytes at offset 0 +10 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== checking the blkverify mode with valid content == +read 10485760/10485760 bytes at offset 0 +10 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== checking the blkverify mode with invalid settings == +can't open: blkverify=on can only be set if there are exactly two files and vote-threshold is 2 *** done -- 2.19.1 From: Alberto Garcia <berto@igalia.com> The blkverify mode of Quorum only works when the number of children is exactly two, so any attempt to add a new one must return an error. quorum_del_child() on the other hand doesn't need any additional check because decreasing the number of children would make it go under the vote threshold. Signed-off-by: Alberto Garcia <berto@igalia.com> Reported-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static void quorum_add_child(BlockDriverState *bs, BlockDriverState *child_bs, char indexstr[32]; int ret; + if (s->is_blkverify) { + error_setg(errp, "Cannot add a child to a quorum in blkverify mode"); + return; + } + assert(s->num_children <= INT_MAX / sizeof(BdrvChild *)); if (s->num_children == INT_MAX / sizeof(BdrvChild *) || s->next_child_index == UINT_MAX) { @@ -XXX,XX +XXX,XX @@ static void quorum_del_child(BlockDriverState *bs, BdrvChild *child, return; } + /* We know now that num_children > threshold, so blkverify must be false */ + assert(!s->is_blkverify); + bdrv_drained_begin(bs); /* We can safely remove this child now */ -- 2.19.1 From: Alberto Garcia <berto@igalia.com> This patch tests that you can add and remove drives from a Quorum using the x-blockdev-change command. Signed-off-by: Alberto Garcia <berto@igalia.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/081 | 86 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/081.out | 54 ++++++++++++++++++++++++ 2 files changed, 140 insertions(+) diff --git a/tests/qemu-iotests/081 b/tests/qemu-iotests/081 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/081 +++ b/tests/qemu-iotests/081 @@ -XXX,XX +XXX,XX @@ quorum="$quorum,file.children.2.driver=raw" $QEMU_IO -c "open -o $quorum" | _filter_qemu_io +echo +echo "== dynamically adding a child to a quorum ==" + +for verify in false true; do + run_qemu <<EOF + { "execute": "qmp_capabilities" } + { "execute": "blockdev-add", + "arguments": { + "driver": "quorum", + "node-name": "drive0-quorum", + "vote-threshold": 2, + "blkverify": ${verify}, + "children": [ + { + "driver": "$IMGFMT", + "file": { + "driver": "file", + "filename": "$TEST_DIR/1.raw" + } + }, + { + "driver": "$IMGFMT", + "file": { + "driver": "file", + "filename": "$TEST_DIR/2.raw" + } + } + ] + } + } + { "execute": "blockdev-add", + "arguments": { + "node-name": "drive3", + "driver": "$IMGFMT", + "file": { + "driver": "file", + "filename": "$TEST_DIR/2.raw" + } + } + } + { "execute": "x-blockdev-change", + "arguments": { "parent": "drive0-quorum", + "node": "drive3" } } + { "execute": "quit" } +EOF +done + +echo +echo "== dynamically removing a child from a quorum ==" + +for verify in false true; do + for vote_threshold in 1 2; do + run_qemu <<EOF + { "execute": "qmp_capabilities" } + { "execute": "blockdev-add", + "arguments": { + "driver": "quorum", + "node-name": "drive0-quorum", + "vote-threshold": ${vote_threshold}, + "blkverify": ${verify}, + "children": [ + { + "driver": "$IMGFMT", + "file": { + "driver": "file", + "filename": "$TEST_DIR/1.raw" + } + }, + { + "driver": "$IMGFMT", + "file": { + "driver": "file", + "filename": "$TEST_DIR/2.raw" + } + } + ] + } + } + { "execute": "x-blockdev-change", + "arguments": { "parent": "drive0-quorum", + "child": "children.1" } } + { "execute": "quit" } +EOF + done +done + # success, all done echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/081.out b/tests/qemu-iotests/081.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/081.out +++ b/tests/qemu-iotests/081.out @@ -XXX,XX +XXX,XX @@ read 10485760/10485760 bytes at offset 0 == checking the blkverify mode with invalid settings == can't open: blkverify=on can only be set if there are exactly two files and vote-threshold is 2 + +== dynamically adding a child to a quorum == +Testing: +QMP_VERSION +{"return": {}} +{"return": {}} +{"return": {}} +{"return": {}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +Testing: +QMP_VERSION +{"return": {}} +{"return": {}} +{"return": {}} +{"error": {"class": "GenericError", "desc": "Cannot add a child to a quorum in blkverify mode"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + + +== dynamically removing a child from a quorum == +Testing: +QMP_VERSION +{"return": {}} +{"return": {}} +{"return": {}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +Testing: +QMP_VERSION +{"return": {}} +{"return": {}} +{"error": {"class": "GenericError", "desc": "The number of children cannot be lower than the vote threshold 2"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +Testing: +QMP_VERSION +{"return": {}} +{"error": {"class": "GenericError", "desc": "blkverify=on can only be set if there are exactly two files and vote-threshold is 2"}} +{"error": {"class": "GenericError", "desc": "Cannot find device=drive0-quorum nor node_name=drive0-quorum"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +Testing: +QMP_VERSION +{"return": {}} +{"return": {}} +{"error": {"class": "GenericError", "desc": "The number of children cannot be lower than the vote threshold 2"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + *** done -- 2.19.1 To fully change the read-only state of a node, we must not only change bs->read_only, but also update bs->open_flags. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> --- block.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp) } bs->read_only = read_only; + + if (read_only) { + bs->open_flags &= ~BDRV_O_RDWR; + } else { + bs->open_flags |= BDRV_O_RDWR; + } + return 0; } -- 2.19.1 If a management application builds the block graph node by node, the protocol layer doesn't inherit its read-only option from the format layer any more, so it must be set explicitly. Backing files should work on read-only storage, but at the same time, a block job like commit should be able to reopen them read-write if they are on read-write storage. However, without option inheritance, reopen only changes the read-only option for the root node (typically the format layer), but not the protocol layer, so reopening fails (the format layer wants to get write permissions, but the protocol layer is still read-only). A simple workaround for the problem in the management tool would be to open the protocol layer always read-write and to make only the format layer read-only for backing files. However, sometimes the file is actually stored on read-only storage and we don't know whether the image can be opened read-write (for example, for NBD it depends on the server we're trying to connect to). This adds an option that makes QEMU try to open the image read-write, but allows it to degrade to a read-only mode without returning an error. The documentation for this option is consciously phrased in a way that allows QEMU to switch to a better model eventually: Instead of trying when the image is first opened, making the read-only flag dynamic and changing it automatically whenever the first BLK_PERM_WRITE user is attached or the last one is detached would be much more useful behaviour. Unfortunately, this more useful behaviour is also a lot harder to implement, and libvirt needs a solution now before it can switch to -blockdev, so let's start with this easier approach for now. Instead of adding a new auto-read-only option, turning the existing read-only into an enum (with a bool alternate for compatibility) was considered, but it complicated the implementation to the point that it didn't seem to be worth it. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- qapi/block-core.json | 7 +++++++ include/block/block.h | 2 ++ block.c | 17 +++++++++++++++++ block/vvfat.c | 1 + blockdev.c | 2 +- 5 files changed, 28 insertions(+), 1 deletion(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # either generally or in certain configurations. In this case, # the default value does not work and the option must be # specified explicitly. +# @auto-read-only: if true and @read-only is false, QEMU may automatically +# decide not to open the image read-write as requested, but +# fall back to read-only instead (and switch between the modes +# later), e.g. depending on whether the image file is writable +# or whether a writing user is attached to the node +# (default: false, since 3.1) # @detect-zeroes: detect and optimize zero writes (Since 2.1) # (default: off) # @force-share: force share all permission on added nodes. @@ -XXX,XX +XXX,XX @@ '*discard': 'BlockdevDiscardOptions', '*cache': 'BlockdevCacheOptions', '*read-only': 'bool', + '*auto-read-only': 'bool', '*force-share': 'bool', '*detect-zeroes': 'BlockdevDetectZeroesOptions' }, 'discriminator': 'driver', diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ typedef struct HDGeometry { select an appropriate protocol driver, ignoring the format layer */ #define BDRV_O_NO_IO 0x10000 /* don't initialize for I/O */ +#define BDRV_O_AUTO_RDONLY 0x20000 /* degrade to read-only if opening read-write fails */ #define BDRV_O_CACHE_MASK (BDRV_O_NOCACHE | BDRV_O_NO_FLUSH) @@ -XXX,XX +XXX,XX @@ typedef struct HDGeometry { #define BDRV_OPT_CACHE_DIRECT "cache.direct" #define BDRV_OPT_CACHE_NO_FLUSH "cache.no-flush" #define BDRV_OPT_READ_ONLY "read-only" +#define BDRV_OPT_AUTO_READ_ONLY "auto-read-only" #define BDRV_OPT_DISCARD "discard" #define BDRV_OPT_FORCE_SHARE "force-share" diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_inherited_options(int *child_flags, QDict *child_options, /* Inherit the read-only option from the parent if it's not set */ qdict_copy_default(child_options, parent_options, BDRV_OPT_READ_ONLY); + qdict_copy_default(child_options, parent_options, BDRV_OPT_AUTO_READ_ONLY); /* Our block drivers take care to send flushes and respect unmap policy, * so we can default to enable both on lower layers regardless of the @@ -XXX,XX +XXX,XX @@ static void bdrv_backing_options(int *child_flags, QDict *child_options, /* backing files always opened read-only */ qdict_set_default_str(child_options, BDRV_OPT_READ_ONLY, "on"); + qdict_set_default_str(child_options, BDRV_OPT_AUTO_READ_ONLY, "off"); flags &= ~BDRV_O_COPY_ON_READ; /* snapshot=on is handled on the top layer */ @@ -XXX,XX +XXX,XX @@ static void update_flags_from_options(int *flags, QemuOpts *opts) *flags |= BDRV_O_RDWR; } + assert(qemu_opt_find(opts, BDRV_OPT_AUTO_READ_ONLY)); + if (qemu_opt_get_bool_del(opts, BDRV_OPT_AUTO_READ_ONLY, false)) { + *flags |= BDRV_O_AUTO_RDONLY; + } } static void update_options_from_flags(QDict *options, int flags) @@ -XXX,XX +XXX,XX @@ static void update_options_from_flags(QDict *options, int flags) if (!qdict_haskey(options, BDRV_OPT_READ_ONLY)) { qdict_put_bool(options, BDRV_OPT_READ_ONLY, !(flags & BDRV_O_RDWR)); } + if (!qdict_haskey(options, BDRV_OPT_AUTO_READ_ONLY)) { + qdict_put_bool(options, BDRV_OPT_AUTO_READ_ONLY, + flags & BDRV_O_AUTO_RDONLY); + } } static void bdrv_assign_node_name(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ QemuOptsList bdrv_runtime_opts = { .type = QEMU_OPT_BOOL, .help = "Node is opened in read-only mode", }, + { + .name = BDRV_OPT_AUTO_READ_ONLY, + .type = QEMU_OPT_BOOL, + .help = "Node can become read-only if opening read-write fails", + }, { .name = "detect-zeroes", .type = QEMU_OPT_STRING, @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp) qdict_set_default_str(qdict, BDRV_OPT_CACHE_DIRECT, "off"); qdict_set_default_str(qdict, BDRV_OPT_CACHE_NO_FLUSH, "off"); qdict_set_default_str(qdict, BDRV_OPT_READ_ONLY, "off"); + qdict_set_default_str(qdict, BDRV_OPT_AUTO_READ_ONLY, "off"); + } bs = bdrv_open_inherit(NULL, reference, qdict, 0, NULL, NULL, errp); diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ static void vvfat_qcow_options(int *child_flags, QDict *child_options, int parent_flags, QDict *parent_options) { qdict_set_default_str(child_options, BDRV_OPT_READ_ONLY, "off"); + qdict_set_default_str(child_options, BDRV_OPT_AUTO_READ_ONLY, "off"); qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on"); } diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_blockdev_change_medium(bool has_device, const char *device, bdrv_flags = blk_get_open_flags_from_root_state(blk); bdrv_flags &= ~(BDRV_O_TEMPORARY | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | - BDRV_O_PROTOCOL); + BDRV_O_PROTOCOL | BDRV_O_AUTO_RDONLY); if (!has_read_only) { read_only = BLOCKDEV_CHANGE_READ_ONLY_MODE_RETAIN; -- 2.19.1 Commit e2b8247a322 introduced an error path in qemu_rbd_open() after calling rbd_open(), but neglected to close the image again in this error path. The error path should contain everything that the regular close function qemu_rbd_close() contains. This adds the missing rbd_close() call. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/rbd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags, "automatically marking the image read-only."); r = bdrv_set_read_only(bs, true, &local_err); if (r < 0) { + rbd_close(s->image); error_propagate(errp, local_err); goto failed_open; } -- 2.19.1 Some block drivers have traditionally changed their node to read-only mode without asking the user. This behaviour has been marked deprecated since 2.11, expecting users to provide an explicit read-only=on option. Now that we have auto-read-only=on, enable these drivers to make use of the option. This is the only use of bdrv_set_read_only(), so we can make it a bit more specific and turn it into a bdrv_apply_auto_read_only() that is more convenient for drivers to use. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- include/block/block.h | 3 ++- block.c | 42 +++++++++++++++++++++++++++--------------- block/bochs.c | 17 ++++++----------- block/cloop.c | 16 +++++----------- block/dmg.c | 16 +++++----------- block/rbd.c | 15 ++++----------- block/vvfat.c | 10 ++-------- 7 files changed, 51 insertions(+), 68 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, bool bdrv_is_read_only(BlockDriverState *bs); int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, bool ignore_allow_rdw, Error **errp); -int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp); +int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg, + Error **errp); bool bdrv_is_writable(BlockDriverState *bs); bool bdrv_is_sg(BlockDriverState *bs); bool bdrv_is_inserted(BlockDriverState *bs); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, return 0; } -/* TODO Remove (deprecated since 2.11) - * Block drivers are not supposed to automatically change bs->read_only. - * Instead, they should just check whether they can provide what the user - * explicitly requested and error out if read-write is requested, but they can - * only provide read-only access. */ -int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp) +/* + * Called by a driver that can only provide a read-only image. + * + * Returns 0 if the node is already read-only or it could switch the node to + * read-only because BDRV_O_AUTO_RDONLY is set. + * + * Returns -EACCES if the node is read-write and BDRV_O_AUTO_RDONLY is not set + * or bdrv_can_set_read_only() forbids making the node read-only. If @errmsg + * is not NULL, it is used as the error message for the Error object. + */ +int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg, + Error **errp) { int ret = 0; - ret = bdrv_can_set_read_only(bs, read_only, false, errp); - if (ret < 0) { - return ret; + if (!(bs->open_flags & BDRV_O_RDWR)) { + return 0; + } + if (!(bs->open_flags & BDRV_O_AUTO_RDONLY)) { + goto fail; } - bs->read_only = read_only; - - if (read_only) { - bs->open_flags &= ~BDRV_O_RDWR; - } else { - bs->open_flags |= BDRV_O_RDWR; + ret = bdrv_can_set_read_only(bs, true, false, NULL); + if (ret < 0) { + goto fail; } + bs->read_only = true; + bs->open_flags &= ~BDRV_O_RDWR; + return 0; + +fail: + error_setg(errp, "%s", errmsg ?: "Image is read-only"); + return -EACCES; } void bdrv_get_full_backing_filename_from_filename(const char *backed, diff --git a/block/bochs.c b/block/bochs.c index XXXXXXX..XXXXXXX 100644 --- a/block/bochs.c +++ b/block/bochs.c @@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, struct bochs_header bochs; int ret; + /* No write support yet */ + ret = bdrv_apply_auto_read_only(bs, NULL, errp); + if (ret < 0) { + return ret; + } + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false, errp); if (!bs->file) { return -EINVAL; } - if (!bdrv_is_read_only(bs)) { - error_report("Opening bochs images without an explicit read-only=on " - "option is deprecated. Future versions will refuse to " - "open the image instead of automatically marking the " - "image read-only."); - ret = bdrv_set_read_only(bs, true, errp); /* no write support yet */ - if (ret < 0) { - return ret; - } - } - ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs)); if (ret < 0) { return ret; diff --git a/block/cloop.c b/block/cloop.c index XXXXXXX..XXXXXXX 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, uint32_t offsets_size, max_compressed_block_size = 1, i; int ret; + ret = bdrv_apply_auto_read_only(bs, NULL, errp); + if (ret < 0) { + return ret; + } + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false, errp); if (!bs->file) { return -EINVAL; } - if (!bdrv_is_read_only(bs)) { - error_report("Opening cloop images without an explicit read-only=on " - "option is deprecated. Future versions will refuse to " - "open the image instead of automatically marking the " - "image read-only."); - ret = bdrv_set_read_only(bs, true, errp); - if (ret < 0) { - return ret; - } - } - /* read header */ ret = bdrv_pread(bs->file, 128, &s->block_size, 4); if (ret < 0) { diff --git a/block/dmg.c b/block/dmg.c index XXXXXXX..XXXXXXX 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -XXX,XX +XXX,XX @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags, int64_t offset; int ret; + ret = bdrv_apply_auto_read_only(bs, NULL, errp); + if (ret < 0) { + return ret; + } + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false, errp); if (!bs->file) { return -EINVAL; } - if (!bdrv_is_read_only(bs)) { - error_report("Opening dmg images without an explicit read-only=on " - "option is deprecated. Future versions will refuse to " - "open the image instead of automatically marking the " - "image read-only."); - ret = bdrv_set_read_only(bs, true, errp); - if (ret < 0) { - return ret; - } - } - block_module_load_one("dmg-bz2"); s->n_chunks = 0; diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags, /* If we are using an rbd snapshot, we must be r/o, otherwise * leave as-is */ if (s->snap != NULL) { - if (!bdrv_is_read_only(bs)) { - error_report("Opening rbd snapshots without an explicit " - "read-only=on option is deprecated. Future versions " - "will refuse to open the image instead of " - "automatically marking the image read-only."); - r = bdrv_set_read_only(bs, true, &local_err); - if (r < 0) { - rbd_close(s->image); - error_propagate(errp, local_err); - goto failed_open; - } + r = bdrv_apply_auto_read_only(bs, "rbd snapshots are read-only", errp); + if (r < 0) { + rbd_close(s->image); + goto failed_open; } } diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags, "Unable to set VVFAT to 'rw' when drive is read-only"); goto fail; } - } else if (!bdrv_is_read_only(bs)) { - error_report("Opening non-rw vvfat images without an explicit " - "read-only=on option is deprecated. Future versions " - "will refuse to open the image instead of " - "automatically marking the image read-only."); - /* read only is the default for safety */ - ret = bdrv_set_read_only(bs, true, &local_err); + } else { + ret = bdrv_apply_auto_read_only(bs, NULL, errp); if (ret < 0) { - error_propagate(errp, local_err); goto fail; } } -- 2.19.1 If read-only=off, but auto-read-only=on is given, open a read-write NBD connection if the server provides a read-write export, but instead of erroring out for read-only exports, just degrade to read-only. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/nbd-client.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/block/nbd-client.c b/block/nbd-client.c index XXXXXXX..XXXXXXX 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -XXX,XX +XXX,XX @@ int nbd_client_init(BlockDriverState *bs, logout("Failed to negotiate with the NBD server\n"); return ret; } - if (client->info.flags & NBD_FLAG_READ_ONLY && - !bdrv_is_read_only(bs)) { - error_setg(errp, - "request for write access conflicts with read-only export"); - return -EACCES; + if (client->info.flags & NBD_FLAG_READ_ONLY) { + ret = bdrv_apply_auto_read_only(bs, "NBD export is read-only", errp); + if (ret < 0) { + return ret; + } } if (client->info.flags & NBD_FLAG_SEND_FUA) { bs->supported_write_flags = BDRV_REQ_FUA; -- 2.19.1 If read-only=off, but auto-read-only=on is given, open the file read-write if we have the permissions, but instead of erroring out for read-only files, just degrade to read-only. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/file-posix.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, s->fd = -1; fd = qemu_open(filename, s->open_flags, 0644); - if (fd < 0) { - ret = -errno; - error_setg_errno(errp, errno, "Could not open '%s'", filename); + ret = fd < 0 ? -errno : 0; + + if (ret == -EACCES || ret == -EROFS) { + /* Try to degrade to read-only, but if it doesn't work, still use the + * normal error message. */ + if (bdrv_apply_auto_read_only(bs, NULL, NULL) == 0) { + bdrv_flags &= ~BDRV_O_RDWR; + raw_parse_flags(bdrv_flags, &s->open_flags); + assert(!(s->open_flags & O_CREAT)); + fd = qemu_open(filename, s->open_flags); + ret = fd < 0 ? -errno : 0; + } + } + + if (ret < 0) { + error_setg_errno(errp, -ret, "Could not open '%s'", filename); if (ret == -EROFS) { ret = -EACCES; } -- 2.19.1 If read-only=off, but auto-read-only=on is given, just degrade to read-only. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/curl.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags, const char *protocol_delimiter; int ret; - - if (flags & BDRV_O_RDWR) { - error_setg(errp, "curl block device does not support writes"); - return -EROFS; + ret = bdrv_apply_auto_read_only(bs, "curl driver does not support writes", + errp); + if (ret < 0) { + return ret; } if (!libcurl_initialized) { -- 2.19.1 If read-only=off, but auto-read-only=on is given, open the file read-write if we have the permissions, but instead of erroring out for read-only files, just degrade to read-only. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Niels de Vos <ndevos@redhat.com> --- block/gluster.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static int qemu_gluster_open(BlockDriverState *bs, QDict *options, qemu_gluster_parse_flags(bdrv_flags, &open_flags); s->fd = glfs_open(s->glfs, gconf->path, open_flags); - if (!s->fd) { - ret = -errno; + ret = s->fd ? 0 : -errno; + + if (ret == -EACCES || ret == -EROFS) { + /* Try to degrade to read-only, but if it doesn't work, still use the + * normal error message. */ + if (bdrv_apply_auto_read_only(bs, NULL, NULL) == 0) { + open_flags = (open_flags & ~O_RDWR) | O_RDONLY; + s->fd = glfs_open(s->glfs, gconf->path, open_flags); + ret = s->fd ? 0 : -errno; + } } s->supports_seek_data = qemu_gluster_test_seek(s->fd); -- 2.19.1 If read-only=off, but auto-read-only=on is given, open the volume read-write if we have the permissions, but instead of erroring out for read-only volumes, just degrade to read-only. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/iscsi.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags, /* Check the write protect flag of the LUN if we want to write */ if (iscsilun->type == TYPE_DISK && (flags & BDRV_O_RDWR) && iscsilun->write_protected) { - error_setg(errp, "Cannot open a write protected LUN as read-write"); - ret = -EACCES; - goto out; + ret = bdrv_apply_auto_read_only(bs, "LUN is write protected", errp); + if (ret < 0) { + goto out; + } + flags &= ~BDRV_O_RDWR; } iscsi_readcapacity_sync(iscsilun, &local_err); -- 2.19.1 While we want machine interfaces like -blockdev and QMP blockdev-add to add as little auto-detection as possible so that management tools are explicit about their needs, -drive is a convenience option for human users. Enabling auto-read-only=on by default there enables users to use read-only images for read-only guest devices without having to specify read-only=on explicitly. If they try to attach the image to a read-write device, they will still get an error message. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- blockdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts, qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, "off"); qdict_set_default_str(bs_opts, BDRV_OPT_READ_ONLY, read_only ? "on" : "off"); + qdict_set_default_str(bs_opts, BDRV_OPT_AUTO_READ_ONLY, "on"); assert((bdrv_flags & BDRV_O_CACHE_MASK) == 0); if (runstate_check(RUN_STATE_INMIGRATE)) { -- 2.19.1 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- tests/qemu-iotests/232 | 147 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/232.out | 59 +++++++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 207 insertions(+) create mode 100755 tests/qemu-iotests/232 create mode 100644 tests/qemu-iotests/232.out diff --git a/tests/qemu-iotests/232 b/tests/qemu-iotests/232 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/232 @@ -XXX,XX +XXX,XX @@ +#!/bin/bash +# +# Test for auto-read-only +# +# Copyright (C) 2018 Red Hat, Inc. +# +# 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 <http://www.gnu.org/licenses/>. +# + +# creator +owner=kwolf@redhat.com + +seq=`basename $0` +echo "QA output created by $seq" + +here=`pwd` +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img + rm -f $TEST_IMG.snap +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt generic +_supported_proto file +_supported_os Linux + +function do_run_qemu() +{ + echo Testing: "$@" + ( + if ! test -t 0; then + while read cmd; do + echo $cmd + done + fi + echo quit + ) | $QEMU -nographic -monitor stdio -nodefaults "$@" + echo +} + +function run_qemu() +{ + do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qemu | _filter_hmp | + _filter_generated_node_ids | _filter_imgfmt +} + +function run_qemu_info_block() +{ + echo "info block -n" | run_qemu "$@" | grep -e "(file" -e "QEMU_PROG" +} + +size=128M + +_make_test_img $size + +echo +echo "=== -drive with read-write image: read-only/auto-read-only combinations ===" +echo + +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=on,auto-read-only=off +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=on,auto-read-only=on +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=on +echo +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=off,auto-read-only=off +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=off,auto-read-only=on +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=off +echo +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,auto-read-only=off +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,auto-read-only=on +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none + +echo +echo "=== -drive with read-only image: read-only/auto-read-only combinations ===" +echo + +chmod a-w $TEST_IMG + +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=on,auto-read-only=off +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=on,auto-read-only=on +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=on +echo +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=off,auto-read-only=off +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=off,auto-read-only=on +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,read-only=off +echo +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,auto-read-only=off +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none,auto-read-only=on +run_qemu_info_block -drive driver=file,file="$TEST_IMG",if=none + +echo +echo "=== -blockdev with read-write image: read-only/auto-read-only combinations ===" +echo + +chmod a+w $TEST_IMG + +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=on,auto-read-only=off +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=on,auto-read-only=on +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=on +echo +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=off,auto-read-only=off +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=off,auto-read-only=on +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=off +echo +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,auto-read-only=off +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,auto-read-only=on +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0 + +echo +echo "=== -blockdev with read-only image: read-only/auto-read-only combinations ===" +echo + +chmod a-w $TEST_IMG + +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=on,auto-read-only=off +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=on,auto-read-only=on +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=on +echo +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=off,auto-read-only=off +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=off,auto-read-only=on +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,read-only=off +echo +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,auto-read-only=off +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0,auto-read-only=on +run_qemu_info_block -blockdev driver=file,filename="$TEST_IMG",node-name=node0 + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/232.out b/tests/qemu-iotests/232.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/232.out @@ -XXX,XX +XXX,XX @@ +QA output created by 232 +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 + +=== -drive with read-write image: read-only/auto-read-only combinations === + +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) + +NODE_NAME: TEST_DIR/t.IMGFMT (file) +NODE_NAME: TEST_DIR/t.IMGFMT (file) +NODE_NAME: TEST_DIR/t.IMGFMT (file) + +NODE_NAME: TEST_DIR/t.IMGFMT (file) +NODE_NAME: TEST_DIR/t.IMGFMT (file) +NODE_NAME: TEST_DIR/t.IMGFMT (file) + +=== -drive with read-only image: read-only/auto-read-only combinations === + +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) + +QEMU_PROG: -drive driver=file,file=TEST_DIR/t.IMGFMT,if=none,read-only=off,auto-read-only=off: Could not open 'TEST_DIR/t.IMGFMT': Permission denied +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) + +QEMU_PROG: -drive driver=file,file=TEST_DIR/t.IMGFMT,if=none,auto-read-only=off: Could not open 'TEST_DIR/t.IMGFMT': Permission denied +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) +NODE_NAME: TEST_DIR/t.IMGFMT (file, read-only) + +=== -blockdev with read-write image: read-only/auto-read-only combinations === + +node0: TEST_DIR/t.IMGFMT (file, read-only) +node0: TEST_DIR/t.IMGFMT (file, read-only) +node0: TEST_DIR/t.IMGFMT (file, read-only) + +node0: TEST_DIR/t.IMGFMT (file) +node0: TEST_DIR/t.IMGFMT (file) +node0: TEST_DIR/t.IMGFMT (file) + +node0: TEST_DIR/t.IMGFMT (file) +node0: TEST_DIR/t.IMGFMT (file) +node0: TEST_DIR/t.IMGFMT (file) + +=== -blockdev with read-only image: read-only/auto-read-only combinations === + +node0: TEST_DIR/t.IMGFMT (file, read-only) +node0: TEST_DIR/t.IMGFMT (file, read-only) +node0: TEST_DIR/t.IMGFMT (file, read-only) + +QEMU_PROG: -blockdev driver=file,filename=TEST_DIR/t.IMGFMT,node-name=node0,read-only=off,auto-read-only=off: Could not open 'TEST_DIR/t.IMGFMT': Permission denied +node0: TEST_DIR/t.IMGFMT (file, read-only) +QEMU_PROG: -blockdev driver=file,filename=TEST_DIR/t.IMGFMT,node-name=node0,read-only=off: Could not open 'TEST_DIR/t.IMGFMT': Permission denied + +QEMU_PROG: -blockdev driver=file,filename=TEST_DIR/t.IMGFMT,node-name=node0,auto-read-only=off: Could not open 'TEST_DIR/t.IMGFMT': Permission denied +node0: TEST_DIR/t.IMGFMT (file, read-only) +QEMU_PROG: -blockdev driver=file,filename=TEST_DIR/t.IMGFMT,node-name=node0: Could not open 'TEST_DIR/t.IMGFMT': Permission denied +*** done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -XXX,XX +XXX,XX @@ 227 auto quick 229 auto quick 231 auto quick +232 auto quick -- 2.19.1 From: Max Reitz <mreitz@redhat.com> This adds some whitespace into the option help (including indentation) and puts angle brackets around the type names. Furthermore, the list name is no longer printed as part of every line, but only once in advance, and only if the caller did not print a caption already. This patch also restores the description alignment we had before commit 9cbef9d68ee1d8d0, just at 24 instead of 16 characters like we used to. This increase is because now we have the type and two spaces of indentation before the description, and with a usual type name length of three chracters, this sums up to eight additional characters -- which means that we now need 24 characters to get the same amount of padding for most options. Also, 24 is a third of 80, which makes it kind of a round number in terminal terms. Finally, this patch amends the reference output of iotest 082 to match the changes (and thus makes it pass again). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/option.h | 2 +- qemu-img.c | 4 +- util/qemu-option.c | 32 +- tests/qemu-iotests/082.out | 956 ++++++++++++++++++------------------- 4 files changed, 507 insertions(+), 487 deletions(-) diff --git a/include/qemu/option.h b/include/qemu/option.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/option.h +++ b/include/qemu/option.h @@ -XXX,XX +XXX,XX @@ typedef int (*qemu_opts_loopfunc)(void *opaque, QemuOpts *opts, Error **errp); int qemu_opts_foreach(QemuOptsList *list, qemu_opts_loopfunc func, void *opaque, Error **errp); void qemu_opts_print(QemuOpts *opts, const char *sep); -void qemu_opts_print_help(QemuOptsList *list); +void qemu_opts_print_help(QemuOptsList *list, bool print_caption); void qemu_opts_free(QemuOptsList *list); QemuOptsList *qemu_opts_append(QemuOptsList *dst, QemuOptsList *list); diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int print_block_option_help(const char *filename, const char *fmt) } printf("Supported options:\n"); - qemu_opts_print_help(create_opts); + qemu_opts_print_help(create_opts, false); qemu_opts_free(create_opts); return 0; } @@ -XXX,XX +XXX,XX @@ static int print_amend_option_help(const char *format) assert(drv->create_opts); printf("Creation options for '%s':\n", format); - qemu_opts_print_help(drv->create_opts); + qemu_opts_print_help(drv->create_opts, false); printf("\nNote that not all of these options may be amendable.\n"); return 0; } diff --git a/util/qemu-option.c b/util/qemu-option.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-option.c +++ b/util/qemu-option.c @@ -XXX,XX +XXX,XX @@ static const char *opt_type_to_string(enum QemuOptType type) g_assert_not_reached(); } -void qemu_opts_print_help(QemuOptsList *list) +/** + * Print the list of options available in the given list. If + * @print_caption is true, a caption (including the list name, if it + * exists) is printed. The options itself will be indented, so + * @print_caption should only be set to false if the caller prints its + * own custom caption (so that the indentation makes sense). + */ +void qemu_opts_print_help(QemuOptsList *list, bool print_caption) { QemuOptDesc *desc; int i; @@ -XXX,XX +XXX,XX @@ void qemu_opts_print_help(QemuOptsList *list) desc = list->desc; while (desc && desc->name) { GString *str = g_string_new(NULL); - if (list->name) { - g_string_append_printf(str, "%s.", list->name); - } - g_string_append_printf(str, "%s=%s", desc->name, + g_string_append_printf(str, " %s=<%s>", desc->name, opt_type_to_string(desc->type)); if (desc->help) { + if (str->len < 24) { + g_string_append_printf(str, "%*s", 24 - (int)str->len, ""); + } g_string_append_printf(str, " - %s", desc->help); } g_ptr_array_add(array, g_string_free(str, false)); @@ -XXX,XX +XXX,XX @@ void qemu_opts_print_help(QemuOptsList *list) } g_ptr_array_sort(array, (GCompareFunc)qemu_pstrcmp0); + if (print_caption && array->len > 0) { + if (list->name) { + printf("%s options:\n", list->name); + } else { + printf("Options:\n"); + } + } else if (array->len == 0) { + if (list->name) { + printf("There are no options for %s.\n", list->name); + } else { + printf("No options available.\n"); + } + } for (i = 0; i < array->len; i++) { printf("%s\n", (char *)array->pdata[i]); } @@ -XXX,XX +XXX,XX @@ QemuOpts *qemu_opts_parse_noisily(QemuOptsList *list, const char *params, opts = opts_parse(list, params, permit_abbrev, false, &invalidp, &err); if (err) { if (invalidp && has_help_option(params)) { - qemu_opts_print_help(list); + qemu_opts_print_help(list, true); error_free(err); } else { error_report_err(err); diff --git a/tests/qemu-iotests/082.out b/tests/qemu-iotests/082.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/082.out +++ b/tests/qemu-iotests/082.out @@ -XXX,XX +XXX,XX @@ cluster_size: 8192 Testing: create -f qcow2 -o help TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -o ? TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -o cluster_size=4k,help TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -o cluster_size=4k,? TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -o help,cluster_size=4k TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -o ?,cluster_size=4k TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -o cluster_size=4k -o help TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -o cluster_size=4k -o ? TEST_DIR/t.qcow2 128M Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -f qcow2 -u -o backing_file=TEST_DIR/t.qcow2,,help TEST_DIR/t.qcow2 128M Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=134217728 backing_file=TEST_DIR/t.qcow2,,help cluster_size=65536 lazy_refcounts=off refcount_bits=16 @@ -XXX,XX +XXX,XX @@ qemu-img: Invalid option list: ,, Testing: create -f qcow2 -o help Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: create -o help Supported options: -size Virtual disk size + size=<size> - Virtual disk size Testing: create -f bochs -o help qemu-img: Format driver 'bochs' does not support image creation @@ -XXX,XX +XXX,XX @@ cluster_size: 8192 Testing: convert -O qcow2 -o help TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o ? TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o cluster_size=4k,help TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o cluster_size=4k,? TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o help,cluster_size=4k TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o ?,cluster_size=4k TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o cluster_size=4k -o help TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o cluster_size=4k -o ? TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits -nocow Turn off copy-on-write (valid only on btrfs) + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + nocow=<bool (on/off)> - Turn off copy-on-write (valid only on btrfs) + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -O qcow2 -o backing_file=TEST_DIR/t.qcow2,,help TEST_DIR/t.qcow2 TEST_DIR/t.qcow2.base qemu-img: Could not open 'TEST_DIR/t.qcow2.base': Could not open backing file: Could not open 'TEST_DIR/t.qcow2,help': No such file or directory @@ -XXX,XX +XXX,XX @@ qemu-img: Invalid option list: ,, Testing: convert -O qcow2 -o help Supported options: -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Testing: convert -o help Supported options: -size Virtual disk size + size=<size> - Virtual disk size Testing: convert -O bochs -o help qemu-img: Format driver 'bochs' does not support image creation @@ -XXX,XX +XXX,XX @@ cluster_size: 65536 Testing: amend -f qcow2 -o help TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: amend -f qcow2 -o ? TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k,help TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k,? TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: amend -f qcow2 -o help,cluster_size=4k TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: amend -f qcow2 -o ?,cluster_size=4k TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k -o help TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: amend -f qcow2 -o cluster_size=4k -o ? TEST_DIR/t.qcow2 Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. @@ -XXX,XX +XXX,XX @@ qemu-img: Invalid option list: ,, Testing: amend -f qcow2 -o help Creation options for 'qcow2': -size Virtual disk size -compat Compatibility level (0.10 or 1.1) -backing_file File name of a base image -backing_fmt Image format of the base image -encryption Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) -encrypt.format Encrypt the image, format choices: 'aes', 'luks' -encrypt.key-secret ID of secret providing qcow AES key or LUKS passphrase -encrypt.cipher-alg Name of encryption cipher algorithm -encrypt.cipher-mode Name of encryption cipher mode -encrypt.ivgen-alg Name of IV generator algorithm -encrypt.ivgen-hash-alg Name of IV generator hash algorithm -encrypt.hash-alg Name of encryption hash algorithm -encrypt.iter-time Time to spend in PBKDF in milliseconds -cluster_size qcow2 cluster size -preallocation Preallocation mode (allowed values: off, metadata, falloc, full) -lazy_refcounts Postpone refcount updates -refcount_bits Width of a reference count entry in bits + backing_file=<str> - File name of a base image + backing_fmt=<str> - Image format of the base image + cluster_size=<size> - qcow2 cluster size + compat=<str> - Compatibility level (0.10 or 1.1) + encrypt.cipher-alg=<str> - Name of encryption cipher algorithm + encrypt.cipher-mode=<str> - Name of encryption cipher mode + encrypt.format=<str> - Encrypt the image, format choices: 'aes', 'luks' + encrypt.hash-alg=<str> - Name of encryption hash algorithm + encrypt.iter-time=<num> - Time to spend in PBKDF in milliseconds + encrypt.ivgen-alg=<str> - Name of IV generator algorithm + encrypt.ivgen-hash-alg=<str> - Name of IV generator hash algorithm + encrypt.key-secret=<str> - ID of secret providing qcow AES key or LUKS passphrase + encryption=<bool (on/off)> - Encrypt the image with format 'aes'. (Deprecated in favor of encrypt.format=aes) + lazy_refcounts=<bool (on/off)> - Postpone refcount updates + preallocation=<str> - Preallocation mode (allowed values: off, metadata, falloc, full) + refcount_bits=<num> - Width of a reference count entry in bits + size=<size> - Virtual disk size Note that not all of these options may be amendable. Testing: convert -o help Supported options: -size Virtual disk size + size=<size> - Virtual disk size Testing: amend -f bochs -o help qemu-img: Format driver 'bochs' does not support option amendment -- 2.19.1 From: Max Reitz <mreitz@redhat.com> Following the example of qemu_opts_print_help(), indent all entries in the list of character devices. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- chardev/char.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/chardev/char.c b/chardev/char.c index XXXXXXX..XXXXXXX 100644 --- a/chardev/char.c +++ b/chardev/char.c @@ -XXX,XX +XXX,XX @@ help_string_append(const char *name, void *opaque) { GString *str = opaque; - g_string_append_printf(str, "\n%s", name); + g_string_append_printf(str, "\n %s", name); } static const char *chardev_alias_translate(const char *name) -- 2.19.1 From: Max Reitz <mreitz@redhat.com> Just like in qemu_opts_print_help(), print the device name as a caption instead of on every single line, indent all options, add angle brackets around types, and align the descriptions after 24 characters. Also, separate the descriptions with " - " instead of putting them in parentheses, because that is what we do everywhere else. This does look a bit funny here because basically all bits have the description "on/off", but funny does not mean it is less readable. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qdev-monitor.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/qdev-monitor.c b/qdev-monitor.c index XXXXXXX..XXXXXXX 100644 --- a/qdev-monitor.c +++ b/qdev-monitor.c @@ -XXX,XX +XXX,XX @@ int qdev_device_help(QemuOpts *opts) goto error; } + if (prop_list) { + out_printf("%s options:\n", driver); + } else { + out_printf("There are no options for %s.\n", driver); + } for (prop = prop_list; prop; prop = prop->next) { - out_printf("%s.%s=%s", driver, prop->value->name, prop->value->type); + int len; + out_printf(" %s=<%s>%n", prop->value->name, prop->value->type, &len); if (prop->value->has_description) { - out_printf(" (%s)\n", prop->value->description); + if (len < 24) { + out_printf("%*s", 24 - len, ""); + } + out_printf(" - %s\n", prop->value->description); } else { out_printf("\n"); } -- 2.19.1 From: Max Reitz <mreitz@redhat.com> Just like in qemu_opts_print_help(), print the object name as a caption instead of on every single line, indent all options, add angle brackets around types, and align the descriptions after 24 characters. Also, indent every object name in the list of available objects. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- vl.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/vl.c b/vl.c index XXXXXXX..XXXXXXX 100644 --- a/vl.c +++ b/vl.c @@ -XXX,XX +XXX,XX @@ static bool object_create_initial(const char *type, QemuOpts *opts) list = object_class_get_list_sorted(TYPE_USER_CREATABLE, false); for (l = list; l != NULL; l = l->next) { ObjectClass *oc = OBJECT_CLASS(l->data); - printf("%s\n", object_class_get_name(oc)); + printf(" %s\n", object_class_get_name(oc)); } g_slist_free(list); exit(0); @@ -XXX,XX +XXX,XX @@ static bool object_create_initial(const char *type, QemuOpts *opts) } str = g_string_new(NULL); - g_string_append_printf(str, "%s.%s=%s", type, - prop->name, prop->type); + g_string_append_printf(str, " %s=<%s>", prop->name, prop->type); if (prop->description) { + if (str->len < 24) { + g_string_append_printf(str, "%*s", 24 - (int)str->len, ""); + } g_string_append_printf(str, " - %s", prop->description); } g_ptr_array_add(array, g_string_free(str, false)); } g_ptr_array_sort(array, (GCompareFunc)qemu_pstrcmp0); + if (array->len > 0) { + printf("%s options:\n", type); + } else { + printf("There are no options for %s.\n", type); + } for (i = 0; i < array->len; i++) { printf("%s\n", (char *)array->pdata[i]); } -- 2.19.1 From: Max Reitz <mreitz@redhat.com> There is no good reason why there should be a newline in this description, so remove it. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- vl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vl.c b/vl.c index XXXXXXX..XXXXXXX 100644 --- a/vl.c +++ b/vl.c @@ -XXX,XX +XXX,XX @@ static QemuOptsList qemu_fw_cfg_opts = { }, { .name = "file", .type = QEMU_OPT_STRING, - .help = "Sets the name of the file from which\n" + .help = "Sets the name of the file from which " "the fw_cfg blob will be loaded", }, { .name = "string", -- 2.19.1 From: Leonid Bloch <lbloch@janustech.com> If an expression is used to define DEFAULT_CLUSTER_SIZE, when compiled, it will be embedded as a literal expression in the binary (as the default value) because it is stringified to mark the size of the default value. Now this is fixed by using a defined number to define this value. Signed-off-by: Leonid Bloch <lbloch@janustech.com> Reviewed-by: Stefan Weil <sw@weilnetz.de> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vdi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ #define BLOCK_OPT_STATIC "static" #define SECTOR_SIZE 512 -#define DEFAULT_CLUSTER_SIZE (1 * MiB) +#define DEFAULT_CLUSTER_SIZE S_1MiB #if defined(CONFIG_VDI_DEBUG) #define VDI_DEBUG 1 @@ -XXX,XX +XXX,XX @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } else if (header.block_size != DEFAULT_CLUSTER_SIZE) { error_setg(errp, "unsupported VDI image (block size %" PRIu32 - " is not %" PRIu64 ")", + " is not %" PRIu32 ")", header.block_size, DEFAULT_CLUSTER_SIZE); ret = -ENOTSUP; goto fail; -- 2.19.1 From: Leonid Bloch <lbloch@janustech.com> The lookup table for power-of-two sizes was added in commit 540b8492618eb for the purpose of having convenient shortcuts for these sizes in cases when the literal number has to be present at compile time, and expressions as '(1 * KiB)' can not be used. One such case is the stringification of sizes. Beyond that, it is convenient to use these shortcuts for all power-of-two sizes, even if they don't have to be literal numbers. Despite its convenience, this table introduced 55 lines of "dumb" code, the purpose and origin of which are obscure without reading the message of the commit which introduced it. This patch fixes that by adding a comment to the code itself with a brief explanation for the reasoning behind this table. This comment includes the short AWK script that generated the table, so that anyone who's interested could make sure that the values in it are correct (otherwise these values look as if they were typed manually). Signed-off-by: Leonid Bloch <lbloch@janustech.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/units.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/include/qemu/units.h b/include/qemu/units.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/units.h +++ b/include/qemu/units.h @@ -XXX,XX +XXX,XX @@ #define PiB (INT64_C(1) << 50) #define EiB (INT64_C(1) << 60) +/* + * The following lookup table is intended to be used when a literal string of + * the number of bytes is required (for example if it needs to be stringified). + * It can also be used for generic shortcuts of power-of-two sizes. + * This table is generated using the AWK script below: + * + * BEGIN { + * suffix="KMGTPE"; + * for(i=10; i<64; i++) { + * val=2**i; + * s=substr(suffix, int(i/10), 1); + * n=2**(i%10); + * pad=21-int(log(n)/log(10)); + * printf("#define S_%d%siB %*d\n", n, s, pad, val); + * } + * } + */ + #define S_1KiB 1024 #define S_2KiB 2048 #define S_4KiB 4096 -- 2.19.1 The following changes since commit 281f327487c9c9b1599f93c589a408bbf4a651b8: Merge remote-tracking branch 'remotes/vivier/tags/m68k-for-2.12-pull-request' into staging (2017-12-22 00:11:36 +0000) are available in the git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to 1a63a907507fbbcfaee3f622907ec244b7eabda8: block: Keep nodes drained between reopen_queue/multiple (2017-12-22 15:05:32 +0100) ---------------------------------------------------------------- Block layer patches ---------------------------------------------------------------- Doug Gale (1): nvme: Add tracing Edgar Kaziakhmedov (1): qcow2: get rid of qcow2_backing_read1 routine Fam Zheng (2): block: Open backing image in force share mode for size probe block: Remove unused bdrv_requests_pending John Snow (1): iotests: fix 197 for vpc Kevin Wolf (27): block: Formats don't need CONSISTENT_READ with NO_IO block: Make bdrv_drain_invoke() recursive block: Call .drain_begin only once in bdrv_drain_all_begin() test-bdrv-drain: Test BlockDriver callbacks for drain block: bdrv_drain_recurse(): Remove unused begin parameter block: Don't wait for requests in bdrv_drain*_end() block: Unify order in drain functions block: Don't acquire AioContext in hmp_qemu_io() block: Document that x-blockdev-change breaks quorum children list block: Assert drain_all is only called from main AioContext block: Make bdrv_drain() driver callbacks non-recursive test-bdrv-drain: Test callback for bdrv_drain test-bdrv-drain: Test bs->quiesce_counter blockjob: Pause job on draining any job BDS test-bdrv-drain: Test drain vs. block jobs block: Don't block_job_pause_all() in bdrv_drain_all() block: Nested drain_end must still call callbacks test-bdrv-drain: Test nested drain sections block: Don't notify parents in drain call chain block: Add bdrv_subtree_drained_begin/end() test-bdrv-drain: Tests for bdrv_subtree_drain test-bdrv-drain: Test behaviour in coroutine context test-bdrv-drain: Recursive draining with multiple parents block: Allow graph changes in subtree drained section test-bdrv-drain: Test graph changes in drained section commit: Simplify reopen of base block: Keep nodes drained between reopen_queue/multiple Thomas Huth (3): block: Remove the obsolete -drive boot=on|off parameter block: Remove the deprecated -hdachs option block: Mention -drive cyls/heads/secs/trans/serial/addr in deprecation chapter qapi/block-core.json | 4 + block/qcow2.h | 3 - include/block/block.h | 15 +- include/block/block_int.h | 6 +- block.c | 75 ++++- block/commit.c | 8 +- block/io.c | 164 +++++++--- block/qcow2.c | 51 +-- block/replication.c | 6 + blockdev.c | 11 - blockjob.c | 22 +- hmp.c | 6 - hw/block/nvme.c | 349 +++++++++++++++++---- qemu-io-cmds.c | 3 + tests/test-bdrv-drain.c | 651 +++++++++++++++++++++++++++++++++++++++ vl.c | 86 +----- hw/block/trace-events | 93 ++++++ qemu-doc.texi | 29 +- qemu-options.hx | 19 +- tests/Makefile.include | 2 + tests/qemu-iotests/197 | 4 + tests/qemu-iotests/common.filter | 3 +- 22 files changed, 1294 insertions(+), 316 deletions(-) create mode 100644 tests/test-bdrv-drain.c Commit 1f4ad7d fixed 'qemu-img info' for raw images that are currently in use as a mirror target. It is not enough for image formats, though, as these still unconditionally request BLK_PERM_CONSISTENT_READ. As this permission is geared towards whether the guest-visible data is consistent, and has no impact on whether the metadata is sane, and 'qemu-img info' does not read guest-visible data (except for the raw format), it makes sense to not require BLK_PERM_CONSISTENT_READ if there is not going to be any guest I/O performed, regardless of image format. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, assert(role == &child_backing || role == &child_file); if (!backing) { + int flags = bdrv_reopen_get_flags(reopen_queue, bs); + /* Apart from the modifications below, the same permissions are * forwarded and left alone as for filters */ bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared, @@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, /* bs->file always needs to be consistent because of the metadata. We * can never allow other users to resize or write to it. */ - perm |= BLK_PERM_CONSISTENT_READ; + if (!(flags & BDRV_O_NO_IO)) { + perm |= BLK_PERM_CONSISTENT_READ; + } shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE); } else { /* We want consistent read from backing files if the parent needs it. -- 2.13.6 From: John Snow <jsnow@redhat.com> VPC has some difficulty creating geometries of particular size. However, we can indeed force it to use a literal one, so let's do that for the sake of test 197, which is testing some specific offsets. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Lukáš Doktor <ldoktor@redhat.com> --- tests/qemu-iotests/197 | 4 ++++ tests/qemu-iotests/common.filter | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/197 +++ b/tests/qemu-iotests/197 @@ -XXX,XX +XXX,XX @@ echo '=== Copy-on-read ===' echo # Prep the images +# VPC rounds image sizes to a specific geometry, force a specific size. +if [ "$IMGFMT" = "vpc" ]; then + IMGOPTS=$(_optstr_add "$IMGOPTS" "force_size") +fi _make_test_img 4G $QEMU_IO -c "write -P 55 3G 1k" "$TEST_IMG" | _filter_qemu_io IMGPROTO=file IMGFMT=qcow2 IMGOPTS= TEST_IMG_FILE="$TEST_WRAP" \ diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -XXX,XX +XXX,XX @@ _filter_img_create() -e "s# log_size=[0-9]\\+##g" \ -e "s# refcount_bits=[0-9]\\+##g" \ -e "s# key-secret=[a-zA-Z0-9]\\+##g" \ - -e "s# iter-time=[0-9]\\+##g" + -e "s# iter-time=[0-9]\\+##g" \ + -e "s# force_size=\\(on\\|off\\)##g" } _filter_img_info() -- 2.13.6 This change separates bdrv_drain_invoke(), which calls the BlockDriver drain callbacks, from bdrv_drain_recurse(). Instead, the function performs its own recursion now. One reason for this is that bdrv_drain_recurse() can be called multiple times by bdrv_drain_all_begin(), but the callbacks may only be called once. The separation is necessary to fix this bug. The other reason is that we intend to go to a model where we call all driver callbacks first, and only then start polling. This is not fully achieved yet with this patch, as bdrv_drain_invoke() contains a BDRV_POLL_WHILE() loop for the block driver callbacks, which can still call callbacks for any unrelated event. It's a step in this direction anyway. Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_drain_invoke_entry(void *opaque) bdrv_wakeup(bs); } +/* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) { + BdrvChild *child, *tmp; BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin}; if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) || @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) data.co = qemu_coroutine_create(bdrv_drain_invoke_entry, &data); bdrv_coroutine_enter(bs, data.co); BDRV_POLL_WHILE(bs, !data.done); + + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { + bdrv_drain_invoke(child->bs, begin); + } } static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) BdrvChild *child, *tmp; bool waited; - /* Ensure any pending metadata writes are submitted to bs->file. */ - bdrv_drain_invoke(bs, begin); - /* Wait for drained requests to finish */ waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) bdrv_parent_drained_begin(bs); } + bdrv_drain_invoke(bs, true); bdrv_drain_recurse(bs, true); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) } bdrv_parent_drained_end(bs); + bdrv_drain_invoke(bs, false); bdrv_drain_recurse(bs, false); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { + /* FIXME Calling this multiple times is wrong */ + bdrv_drain_invoke(bs, true); waited |= bdrv_drain_recurse(bs, true); } } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_context_acquire(aio_context); aio_enable_external(aio_context); bdrv_parent_drained_end(bs); + bdrv_drain_invoke(bs, false); bdrv_drain_recurse(bs, false); aio_context_release(aio_context); } -- 2.13.6 bdrv_drain_all_begin() used to call the .bdrv_co_drain_begin() driver callback inside its polling loop. This means that how many times it got called for each node depended on long it had to poll the event loop. This is obviously not right and results in nodes that stay drained even after bdrv_drain_all_end(), which calls .bdrv_co_drain_begin() once per node. Fix bdrv_drain_all_begin() to call the callback only once, too. Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); bdrv_parent_drained_begin(bs); aio_disable_external(aio_context); + bdrv_drain_invoke(bs, true); aio_context_release(aio_context); if (!g_slist_find(aio_ctxs, aio_context)) { @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { - /* FIXME Calling this multiple times is wrong */ - bdrv_drain_invoke(bs, true); waited |= bdrv_drain_recurse(bs, true); } } -- 2.13.6 This adds a test case that the BlockDriver callbacks for drain are called in bdrv_drained_all_begin/end(), and that both of them are called exactly once. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- tests/test-bdrv-drain.c | 137 ++++++++++++++++++++++++++++++++++++++++++++++++ tests/Makefile.include | 2 + 2 files changed, 139 insertions(+) create mode 100644 tests/test-bdrv-drain.c diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ +/* + * Block node draining tests + * + * Copyright (c) 2017 Kevin Wolf <kwolf@redhat.com> + * + * 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 "qemu/osdep.h" +#include "block/block.h" +#include "sysemu/block-backend.h" +#include "qapi/error.h" + +typedef struct BDRVTestState { + int drain_count; +} BDRVTestState; + +static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + s->drain_count++; +} + +static void coroutine_fn bdrv_test_co_drain_end(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + s->drain_count--; +} + +static void bdrv_test_close(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + g_assert_cmpint(s->drain_count, >, 0); +} + +static int coroutine_fn bdrv_test_co_preadv(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, int flags) +{ + /* We want this request to stay until the polling loop in drain waits for + * it to complete. We need to sleep a while as bdrv_drain_invoke() comes + * first and polls its result, too, but it shouldn't accidentally complete + * this request yet. */ + qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 100000); + + return 0; +} + +static BlockDriver bdrv_test = { + .format_name = "test", + .instance_size = sizeof(BDRVTestState), + + .bdrv_close = bdrv_test_close, + .bdrv_co_preadv = bdrv_test_co_preadv, + + .bdrv_co_drain_begin = bdrv_test_co_drain_begin, + .bdrv_co_drain_end = bdrv_test_co_drain_end, +}; + +static void aio_ret_cb(void *opaque, int ret) +{ + int *aio_ret = opaque; + *aio_ret = ret; +} + +static void test_drv_cb_drain_all(void) +{ + BlockBackend *blk; + BlockDriverState *bs; + BDRVTestState *s; + BlockAIOCB *acb; + int aio_ret; + + QEMUIOVector qiov; + struct iovec iov = { + .iov_base = NULL, + .iov_len = 0, + }; + qemu_iovec_init_external(&qiov, &iov, 1); + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + s = bs->opaque; + blk_insert_bs(blk, bs, &error_abort); + + /* Simple bdrv_drain_all_begin/end pair, check that CBs are called */ + g_assert_cmpint(s->drain_count, ==, 0); + bdrv_drain_all_begin(); + g_assert_cmpint(s->drain_count, ==, 1); + bdrv_drain_all_end(); + g_assert_cmpint(s->drain_count, ==, 0); + + /* Now do the same while a request is pending */ + aio_ret = -EINPROGRESS; + acb = blk_aio_preadv(blk, 0, &qiov, 0, aio_ret_cb, &aio_ret); + g_assert(acb != NULL); + g_assert_cmpint(aio_ret, ==, -EINPROGRESS); + + g_assert_cmpint(s->drain_count, ==, 0); + bdrv_drain_all_begin(); + g_assert_cmpint(aio_ret, ==, 0); + g_assert_cmpint(s->drain_count, ==, 1); + bdrv_drain_all_end(); + g_assert_cmpint(s->drain_count, ==, 0); + + bdrv_unref(bs); + blk_unref(blk); +} + +int main(int argc, char **argv) +{ + bdrv_init(); + qemu_init_main_loop(&error_abort); + + g_test_init(&argc, &argv, NULL); + + g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); + + return g_test_run(); +} diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ gcov-files-test-thread-pool-y = thread-pool.c gcov-files-test-hbitmap-y = util/hbitmap.c check-unit-y += tests/test-hbitmap$(EXESUF) gcov-files-test-hbitmap-y = blockjob.c +check-unit-y += tests/test-bdrv-drain$(EXESUF) check-unit-y += tests/test-blockjob$(EXESUF) check-unit-y += tests/test-blockjob-txn$(EXESUF) check-unit-y += tests/test-x86-cpuid$(EXESUF) @@ -XXX,XX +XXX,XX @@ tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y) tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y) tests/test-aio-multithread$(EXESUF): tests/test-aio-multithread.o $(test-block-obj-y) tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y) +tests/test-bdrv-drain$(EXESUF): tests/test-bdrv-drain.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob$(EXESUF): tests/test-blockjob.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob-txn$(EXESUF): tests/test-blockjob-txn.o $(test-block-obj-y) $(test-util-obj-y) tests/test-thread-pool$(EXESUF): tests/test-thread-pool.o $(test-block-obj-y) -- 2.13.6 Now that the bdrv_drain_invoke() calls are pulled up to the callers of bdrv_drain_recurse(), the 'begin' parameter isn't needed any more. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) } } -static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) +static bool bdrv_drain_recurse(BlockDriverState *bs) { BdrvChild *child, *tmp; bool waited; @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) */ bdrv_ref(bs); } - waited |= bdrv_drain_recurse(bs, begin); + waited |= bdrv_drain_recurse(bs); if (in_main_loop) { bdrv_unref(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) } bdrv_drain_invoke(bs, true); - bdrv_drain_recurse(bs, true); + bdrv_drain_recurse(bs); } void bdrv_drained_end(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs, false); + bdrv_drain_recurse(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { - waited |= bdrv_drain_recurse(bs, true); + waited |= bdrv_drain_recurse(bs); } } aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs, false); + bdrv_drain_recurse(bs); aio_context_release(aio_context); } -- 2.13.6 The device is drained, so there is no point in waiting for requests at the end of the drained section. Remove the bdrv_drain_recurse() calls there. The bdrv_drain_recurse() calls were introduced in commit 481cad48e5e in order to call the .bdrv_co_drain_end() driver callback. This is now done by a separate bdrv_drain_invoke() call. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs); aio_context_release(aio_context); } -- 2.13.6 Drain requests are propagated to child nodes, parent nodes and directly to the AioContext. The order in which this happened was different between all combinations of drain/drain_all and begin/end. The correct order is to keep children only drained when their parents are also drained. This means that at the start of a drained section, the AioContext needs to be drained first, the parents second and only then the children. The correct order for the end of a drained section is the opposite. This patch changes the three other functions to follow the example of bdrv_drained_begin(), which is the only one that got it right. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) return; } + /* Stop things in parent-to-child order */ if (atomic_fetch_inc(&bs->quiesce_counter) == 0) { aio_disable_external(bdrv_get_aio_context(bs)); bdrv_parent_drained_begin(bs); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) return; } - bdrv_parent_drained_end(bs); + /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false); + bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); + /* Stop things in parent-to-child order */ aio_context_acquire(aio_context); - bdrv_parent_drained_begin(bs); aio_disable_external(aio_context); + bdrv_parent_drained_begin(bs); bdrv_drain_invoke(bs, true); aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); + /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); - aio_enable_external(aio_context); - bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); + bdrv_parent_drained_end(bs); + aio_enable_external(aio_context); aio_context_release(aio_context); } -- 2.13.6 Commit 15afd94a047 added code to acquire and release the AioContext in qemuio_command(). This means that the lock is taken twice now in the call path from hmp_qemu_io(). This causes BDRV_POLL_WHILE() to hang for any requests issued to nodes in a non-mainloop AioContext. Dropping the first locking from hmp_qemu_io() fixes the problem. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- hmp.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/hmp.c b/hmp.c index XXXXXXX..XXXXXXX 100644 --- a/hmp.c +++ b/hmp.c @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) { BlockBackend *blk; BlockBackend *local_blk = NULL; - AioContext *aio_context; const char* device = qdict_get_str(qdict, "device"); const char* command = qdict_get_str(qdict, "command"); Error *err = NULL; @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) } } - aio_context = blk_get_aio_context(blk); - aio_context_acquire(aio_context); - /* * Notably absent: Proper permission management. This is sad, but it seems * almost impossible to achieve without changing the semantics and thereby @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) */ qemuio_command(blk, command); - aio_context_release(aio_context); - fail: blk_unref(local_blk); hmp_handle_error(mon, &err); -- 2.13.6 From: Edgar Kaziakhmedov <edgar.kaziakhmedov@virtuozzo.com> Since bdrv_co_preadv does all neccessary checks including reading after the end of the backing file, avoid duplication of verification before bdrv_co_preadv call. Signed-off-by: Edgar Kaziakhmedov <edgar.kaziakhmedov@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.h | 3 --- block/qcow2.c | 51 ++++++++------------------------------------------- 2 files changed, 8 insertions(+), 46 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ uint32_t offset_to_reftable_index(BDRVQcow2State *s, uint64_t offset) } /* qcow2.c functions */ -int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t sector_num, int nb_sectors); - int64_t qcow2_refcount_metadata_size(int64_t clusters, size_t cluster_size, int refcount_order, bool generous_increase, uint64_t *refblock_count); diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs, return status; } -/* handle reading after the end of the backing file */ -int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t offset, int bytes) -{ - uint64_t bs_size = bs->total_sectors * BDRV_SECTOR_SIZE; - int n1; - - if ((offset + bytes) <= bs_size) { - return bytes; - } - - if (offset >= bs_size) { - n1 = 0; - } else { - n1 = bs_size - offset; - } - - qemu_iovec_memset(qiov, n1, 0, bytes - n1); - - return n1; -} - static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) { BDRVQcow2State *s = bs->opaque; - int offset_in_cluster, n1; + int offset_in_cluster; int ret; unsigned int cur_bytes; /* number of bytes in current iteration */ uint64_t cluster_offset = 0; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, case QCOW2_CLUSTER_UNALLOCATED: if (bs->backing) { - /* read from the base image */ - n1 = qcow2_backing_read1(bs->backing->bs, &hd_qiov, - offset, cur_bytes); - if (n1 > 0) { - QEMUIOVector local_qiov; - - qemu_iovec_init(&local_qiov, hd_qiov.niov); - qemu_iovec_concat(&local_qiov, &hd_qiov, 0, n1); - - BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); - qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_preadv(bs->backing, offset, n1, - &local_qiov, 0); - qemu_co_mutex_lock(&s->lock); - - qemu_iovec_destroy(&local_qiov); - - if (ret < 0) { - goto fail; - } + BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); + qemu_co_mutex_unlock(&s->lock); + ret = bdrv_co_preadv(bs->backing, offset, cur_bytes, + &hd_qiov, 0); + qemu_co_mutex_lock(&s->lock); + if (ret < 0) { + goto fail; } } else { /* Note: in this case, no need to wait */ -- 2.13.6 Removing a quorum child node with x-blockdev-change results in a quorum driver state that cannot be recreated with create options because it would require a list with gaps. This causes trouble in at least .bdrv_refresh_filename(). Document this problem so that we won't accidentally mark the command stable without having addressed it. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> --- qapi/block-core.json | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # does not support all kinds of operations, all kinds of children, nor # all block drivers. # +# FIXME Removing children from a quorum node means introducing gaps in the +# child indices. This cannot be represented in the 'children' list of +# BlockdevOptionsQuorum, as returned by .bdrv_refresh_filename(). +# # Warning: The data in a new quorum child MUST be consistent with that of # the rest of the array. # -- 2.13.6 From: Doug Gale <doug16k@gmail.com> Add trace output for commands, errors, and undefined behavior. Add guest error log output for undefined behavior. Report invalid undefined accesses to MMIO. Annotate unlikely error checks with unlikely. Signed-off-by: Doug Gale <doug16k@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/block/nvme.c | 349 ++++++++++++++++++++++++++++++++++++++++++-------- hw/block/trace-events | 93 ++++++++++++++ 2 files changed, 390 insertions(+), 52 deletions(-) diff --git a/hw/block/nvme.c b/hw/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nvme.c +++ b/hw/block/nvme.c @@ -XXX,XX +XXX,XX @@ #include "qapi/visitor.h" #include "sysemu/block-backend.h" +#include "qemu/log.h" +#include "trace.h" #include "nvme.h" +#define NVME_GUEST_ERR(trace, fmt, ...) \ + do { \ + (trace_##trace)(__VA_ARGS__); \ + qemu_log_mask(LOG_GUEST_ERROR, #trace \ + " in %s: " fmt "\n", __func__, ## __VA_ARGS__); \ + } while (0) + static void nvme_process_sq(void *opaque); static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size) @@ -XXX,XX +XXX,XX @@ static void nvme_isr_notify(NvmeCtrl *n, NvmeCQueue *cq) { if (cq->irq_enabled) { if (msix_enabled(&(n->parent_obj))) { + trace_nvme_irq_msix(cq->vector); msix_notify(&(n->parent_obj), cq->vector); } else { + trace_nvme_irq_pin(); pci_irq_pulse(&n->parent_obj); } + } else { + trace_nvme_irq_masked(); } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, trans_len = MIN(len, trans_len); int num_prps = (len >> n->page_bits) + 1; - if (!prp1) { + if (unlikely(!prp1)) { + trace_nvme_err_invalid_prp(); return NVME_INVALID_FIELD | NVME_DNR; } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr && prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, } len -= trans_len; if (len) { - if (!prp2) { + if (unlikely(!prp2)) { + trace_nvme_err_invalid_prp2_missing(); goto unmap; } if (len > n->page_size) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, uint64_t prp_ent = le64_to_cpu(prp_list[i]); if (i == n->max_prp_ents - 1 && len > n->page_size) { - if (!prp_ent || prp_ent & (n->page_size - 1)) { + if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + trace_nvme_err_invalid_prplist_ent(prp_ent); goto unmap; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, prp_ent = le64_to_cpu(prp_list[i]); } - if (!prp_ent || prp_ent & (n->page_size - 1)) { + if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + trace_nvme_err_invalid_prplist_ent(prp_ent); goto unmap; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, i++; } } else { - if (prp2 & (n->page_size - 1)) { + if (unlikely(prp2 & (n->page_size - 1))) { + trace_nvme_err_invalid_prp2_align(prp2); goto unmap; } if (qsg->nsg) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, QEMUIOVector iov; uint16_t status = NVME_SUCCESS; + trace_nvme_dma_read(prp1, prp2); + if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) { return NVME_INVALID_FIELD | NVME_DNR; } if (qsg.nsg > 0) { - if (dma_buf_read(ptr, len, &qsg)) { + if (unlikely(dma_buf_read(ptr, len, &qsg))) { + trace_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } qemu_sglist_destroy(&qsg); } else { - if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) { + if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) { + trace_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } qemu_iovec_destroy(&iov); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, uint64_t aio_slba = slba << (data_shift - BDRV_SECTOR_BITS); uint32_t aio_nlb = nlb << (data_shift - BDRV_SECTOR_BITS); - if (slba + nlb > ns->id_ns.nsze) { + if (unlikely(slba + nlb > ns->id_ns.nsze)) { + trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return NVME_LBA_RANGE | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0; enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ; - if ((slba + nlb) > ns->id_ns.nsze) { + trace_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba); + + if (unlikely((slba + nlb) > ns->id_ns.nsze)) { block_acct_invalid(blk_get_stats(n->conf.blk), acct); + trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return NVME_LBA_RANGE | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) NvmeNamespace *ns; uint32_t nsid = le32_to_cpu(cmd->nsid); - if (nsid == 0 || nsid > n->num_namespaces) { + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { + trace_nvme_err_invalid_ns(nsid, n->num_namespaces); return NVME_INVALID_NSID | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) case NVME_CMD_READ: return nvme_rw(n, ns, cmd, req); default: + trace_nvme_err_invalid_opc(cmd->opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd) NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); - if (!qid || nvme_check_sqid(n, qid)) { + if (unlikely(!qid || nvme_check_sqid(n, qid))) { + trace_nvme_err_invalid_del_sq(qid); return NVME_INVALID_QID | NVME_DNR; } + trace_nvme_del_sq(qid); + sq = n->sq[qid]; while (!QTAILQ_EMPTY(&sq->out_req_list)) { req = QTAILQ_FIRST(&sq->out_req_list); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd) uint16_t qflags = le16_to_cpu(c->sq_flags); uint64_t prp1 = le64_to_cpu(c->prp1); - if (!cqid || nvme_check_cqid(n, cqid)) { + trace_nvme_create_sq(prp1, sqid, cqid, qsize, qflags); + + if (unlikely(!cqid || nvme_check_cqid(n, cqid))) { + trace_nvme_err_invalid_create_sq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (!sqid || !nvme_check_sqid(n, sqid)) { + if (unlikely(!sqid || !nvme_check_sqid(n, sqid))) { + trace_nvme_err_invalid_create_sq_sqid(sqid); return NVME_INVALID_QID | NVME_DNR; } - if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + trace_nvme_err_invalid_create_sq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (!prp1 || prp1 & (n->page_size - 1)) { + if (unlikely(!prp1 || prp1 & (n->page_size - 1))) { + trace_nvme_err_invalid_create_sq_addr(prp1); return NVME_INVALID_FIELD | NVME_DNR; } - if (!(NVME_SQ_FLAGS_PC(qflags))) { + if (unlikely(!(NVME_SQ_FLAGS_PC(qflags)))) { + trace_nvme_err_invalid_create_sq_qflags(NVME_SQ_FLAGS_PC(qflags)); return NVME_INVALID_FIELD | NVME_DNR; } sq = g_malloc0(sizeof(*sq)); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd) NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); - if (!qid || nvme_check_cqid(n, qid)) { + if (unlikely(!qid || nvme_check_cqid(n, qid))) { + trace_nvme_err_invalid_del_cq_cqid(qid); return NVME_INVALID_CQID | NVME_DNR; } cq = n->cq[qid]; - if (!QTAILQ_EMPTY(&cq->sq_list)) { + if (unlikely(!QTAILQ_EMPTY(&cq->sq_list))) { + trace_nvme_err_invalid_del_cq_notempty(qid); return NVME_INVALID_QUEUE_DEL; } + trace_nvme_del_cq(qid); nvme_free_cq(cq, n); return NVME_SUCCESS; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd) uint16_t qflags = le16_to_cpu(c->cq_flags); uint64_t prp1 = le64_to_cpu(c->prp1); - if (!cqid || !nvme_check_cqid(n, cqid)) { + trace_nvme_create_cq(prp1, cqid, vector, qsize, qflags, + NVME_CQ_FLAGS_IEN(qflags) != 0); + + if (unlikely(!cqid || !nvme_check_cqid(n, cqid))) { + trace_nvme_err_invalid_create_cq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + trace_nvme_err_invalid_create_cq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (!prp1) { + if (unlikely(!prp1)) { + trace_nvme_err_invalid_create_cq_addr(prp1); return NVME_INVALID_FIELD | NVME_DNR; } - if (vector > n->num_queues) { + if (unlikely(vector > n->num_queues)) { + trace_nvme_err_invalid_create_cq_vector(vector); return NVME_INVALID_IRQ_VECTOR | NVME_DNR; } - if (!(NVME_CQ_FLAGS_PC(qflags))) { + if (unlikely(!(NVME_CQ_FLAGS_PC(qflags)))) { + trace_nvme_err_invalid_create_cq_qflags(NVME_CQ_FLAGS_PC(qflags)); return NVME_INVALID_FIELD | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c) uint64_t prp1 = le64_to_cpu(c->prp1); uint64_t prp2 = le64_to_cpu(c->prp2); + trace_nvme_identify_ctrl(); + return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl), prp1, prp2); } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c) uint64_t prp1 = le64_to_cpu(c->prp1); uint64_t prp2 = le64_to_cpu(c->prp2); - if (nsid == 0 || nsid > n->num_namespaces) { + trace_nvme_identify_ns(nsid); + + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { + trace_nvme_err_invalid_ns(nsid, n->num_namespaces); return NVME_INVALID_NSID | NVME_DNR; } ns = &n->namespaces[nsid - 1]; + return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns), prp1, prp2); } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c) uint16_t ret; int i, j = 0; + trace_nvme_identify_nslist(min_nsid); + list = g_malloc0(data_len); for (i = 0; i < n->num_namespaces; i++) { if (i < min_nsid) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd) case 0x02: return nvme_identify_nslist(n, c); default: + trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns)); return NVME_INVALID_FIELD | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) switch (dw10) { case NVME_VOLATILE_WRITE_CACHE: result = blk_enable_write_cache(n->conf.blk); + trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled"); break; case NVME_NUMBER_OF_QUEUES: result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16)); + trace_nvme_getfeat_numq(result); break; default: + trace_nvme_err_invalid_getfeat(dw10); return NVME_INVALID_FIELD | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) blk_set_enable_write_cache(n->conf.blk, dw11 & 1); break; case NVME_NUMBER_OF_QUEUES: + trace_nvme_setfeat_numq((dw11 & 0xFFFF) + 1, + ((dw11 >> 16) & 0xFFFF) + 1, + n->num_queues - 1, n->num_queues - 1); req->cqe.result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16)); break; default: + trace_nvme_err_invalid_setfeat(dw10); return NVME_INVALID_FIELD | NVME_DNR; } return NVME_SUCCESS; @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) case NVME_ADM_CMD_GET_FEATURES: return nvme_get_feature(n, cmd, req); default: + trace_nvme_err_invalid_admin_opc(cmd->opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static int nvme_start_ctrl(NvmeCtrl *n) uint32_t page_bits = NVME_CC_MPS(n->bar.cc) + 12; uint32_t page_size = 1 << page_bits; - if (n->cq[0] || n->sq[0] || !n->bar.asq || !n->bar.acq || - n->bar.asq & (page_size - 1) || n->bar.acq & (page_size - 1) || - NVME_CC_MPS(n->bar.cc) < NVME_CAP_MPSMIN(n->bar.cap) || - NVME_CC_MPS(n->bar.cc) > NVME_CAP_MPSMAX(n->bar.cap) || - NVME_CC_IOCQES(n->bar.cc) < NVME_CTRL_CQES_MIN(n->id_ctrl.cqes) || - NVME_CC_IOCQES(n->bar.cc) > NVME_CTRL_CQES_MAX(n->id_ctrl.cqes) || - NVME_CC_IOSQES(n->bar.cc) < NVME_CTRL_SQES_MIN(n->id_ctrl.sqes) || - NVME_CC_IOSQES(n->bar.cc) > NVME_CTRL_SQES_MAX(n->id_ctrl.sqes) || - !NVME_AQA_ASQS(n->bar.aqa) || !NVME_AQA_ACQS(n->bar.aqa)) { + if (unlikely(n->cq[0])) { + trace_nvme_err_startfail_cq(); + return -1; + } + if (unlikely(n->sq[0])) { + trace_nvme_err_startfail_sq(); + return -1; + } + if (unlikely(!n->bar.asq)) { + trace_nvme_err_startfail_nbarasq(); + return -1; + } + if (unlikely(!n->bar.acq)) { + trace_nvme_err_startfail_nbaracq(); + return -1; + } + if (unlikely(n->bar.asq & (page_size - 1))) { + trace_nvme_err_startfail_asq_misaligned(n->bar.asq); + return -1; + } + if (unlikely(n->bar.acq & (page_size - 1))) { + trace_nvme_err_startfail_acq_misaligned(n->bar.acq); + return -1; + } + if (unlikely(NVME_CC_MPS(n->bar.cc) < + NVME_CAP_MPSMIN(n->bar.cap))) { + trace_nvme_err_startfail_page_too_small( + NVME_CC_MPS(n->bar.cc), + NVME_CAP_MPSMIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_MPS(n->bar.cc) > + NVME_CAP_MPSMAX(n->bar.cap))) { + trace_nvme_err_startfail_page_too_large( + NVME_CC_MPS(n->bar.cc), + NVME_CAP_MPSMAX(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOCQES(n->bar.cc) < + NVME_CTRL_CQES_MIN(n->id_ctrl.cqes))) { + trace_nvme_err_startfail_cqent_too_small( + NVME_CC_IOCQES(n->bar.cc), + NVME_CTRL_CQES_MIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOCQES(n->bar.cc) > + NVME_CTRL_CQES_MAX(n->id_ctrl.cqes))) { + trace_nvme_err_startfail_cqent_too_large( + NVME_CC_IOCQES(n->bar.cc), + NVME_CTRL_CQES_MAX(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOSQES(n->bar.cc) < + NVME_CTRL_SQES_MIN(n->id_ctrl.sqes))) { + trace_nvme_err_startfail_sqent_too_small( + NVME_CC_IOSQES(n->bar.cc), + NVME_CTRL_SQES_MIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOSQES(n->bar.cc) > + NVME_CTRL_SQES_MAX(n->id_ctrl.sqes))) { + trace_nvme_err_startfail_sqent_too_large( + NVME_CC_IOSQES(n->bar.cc), + NVME_CTRL_SQES_MAX(n->bar.cap)); + return -1; + } + if (unlikely(!NVME_AQA_ASQS(n->bar.aqa))) { + trace_nvme_err_startfail_asqent_sz_zero(); + return -1; + } + if (unlikely(!NVME_AQA_ACQS(n->bar.aqa))) { + trace_nvme_err_startfail_acqent_sz_zero(); return -1; } @@ -XXX,XX +XXX,XX @@ static int nvme_start_ctrl(NvmeCtrl *n) static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, unsigned size) { + if (unlikely(offset & (sizeof(uint32_t) - 1))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_misaligned32, + "MMIO write not 32-bit aligned," + " offset=0x%"PRIx64"", offset); + /* should be ignored, fall through for now */ + } + + if (unlikely(size < sizeof(uint32_t))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_toosmall, + "MMIO write smaller than 32-bits," + " offset=0x%"PRIx64", size=%u", + offset, size); + /* should be ignored, fall through for now */ + } + switch (offset) { - case 0xc: + case 0xc: /* INTMS */ + if (unlikely(msix_enabled(&(n->parent_obj)))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix, + "undefined access to interrupt mask set" + " when MSI-X is enabled"); + /* should be ignored, fall through for now */ + } n->bar.intms |= data & 0xffffffff; n->bar.intmc = n->bar.intms; + trace_nvme_mmio_intm_set(data & 0xffffffff, + n->bar.intmc); break; - case 0x10: + case 0x10: /* INTMC */ + if (unlikely(msix_enabled(&(n->parent_obj)))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix, + "undefined access to interrupt mask clr" + " when MSI-X is enabled"); + /* should be ignored, fall through for now */ + } n->bar.intms &= ~(data & 0xffffffff); n->bar.intmc = n->bar.intms; + trace_nvme_mmio_intm_clr(data & 0xffffffff, + n->bar.intmc); break; - case 0x14: + case 0x14: /* CC */ + trace_nvme_mmio_cfg(data & 0xffffffff); /* Windows first sends data, then sends enable bit */ if (!NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc) && !NVME_CC_SHN(data) && !NVME_CC_SHN(n->bar.cc)) @@ -XXX,XX +XXX,XX @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, if (NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc)) { n->bar.cc = data; - if (nvme_start_ctrl(n)) { + if (unlikely(nvme_start_ctrl(n))) { + trace_nvme_err_startfail(); n->bar.csts = NVME_CSTS_FAILED; } else { + trace_nvme_mmio_start_success(); n->bar.csts = NVME_CSTS_READY; } } else if (!NVME_CC_EN(data) && NVME_CC_EN(n->bar.cc)) { + trace_nvme_mmio_stopped(); nvme_clear_ctrl(n); n->bar.csts &= ~NVME_CSTS_READY; } if (NVME_CC_SHN(data) && !(NVME_CC_SHN(n->bar.cc))) { - nvme_clear_ctrl(n); - n->bar.cc = data; - n->bar.csts |= NVME_CSTS_SHST_COMPLETE; + trace_nvme_mmio_shutdown_set(); + nvme_clear_ctrl(n); + n->bar.cc = data; + n->bar.csts |= NVME_CSTS_SHST_COMPLETE; } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(n->bar.cc)) { - n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE; - n->bar.cc = data; + trace_nvme_mmio_shutdown_cleared(); + n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE; + n->bar.cc = data; + } + break; + case 0x1C: /* CSTS */ + if (data & (1 << 4)) { + NVME_GUEST_ERR(nvme_ub_mmiowr_ssreset_w1c_unsupported, + "attempted to W1C CSTS.NSSRO" + " but CAP.NSSRS is zero (not supported)"); + } else if (data != 0) { + NVME_GUEST_ERR(nvme_ub_mmiowr_ro_csts, + "attempted to set a read only bit" + " of controller status"); + } + break; + case 0x20: /* NSSR */ + if (data == 0x4E564D65) { + trace_nvme_ub_mmiowr_ssreset_unsupported(); + } else { + /* The spec says that writes of other values have no effect */ + return; } break; - case 0x24: + case 0x24: /* AQA */ n->bar.aqa = data & 0xffffffff; + trace_nvme_mmio_aqattr(data & 0xffffffff); break; - case 0x28: + case 0x28: /* ASQ */ n->bar.asq = data; + trace_nvme_mmio_asqaddr(data); break; - case 0x2c: + case 0x2c: /* ASQ hi */ n->bar.asq |= data << 32; + trace_nvme_mmio_asqaddr_hi(data, n->bar.asq); break; - case 0x30: + case 0x30: /* ACQ */ + trace_nvme_mmio_acqaddr(data); n->bar.acq = data; break; - case 0x34: + case 0x34: /* ACQ hi */ n->bar.acq |= data << 32; + trace_nvme_mmio_acqaddr_hi(data, n->bar.acq); break; + case 0x38: /* CMBLOC */ + NVME_GUEST_ERR(nvme_ub_mmiowr_cmbloc_reserved, + "invalid write to reserved CMBLOC" + " when CMBSZ is zero, ignored"); + return; + case 0x3C: /* CMBSZ */ + NVME_GUEST_ERR(nvme_ub_mmiowr_cmbsz_readonly, + "invalid write to read only CMBSZ, ignored"); + return; default: + NVME_GUEST_ERR(nvme_ub_mmiowr_invalid, + "invalid MMIO write," + " offset=0x%"PRIx64", data=%"PRIx64"", + offset, data); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) uint8_t *ptr = (uint8_t *)&n->bar; uint64_t val = 0; + if (unlikely(addr & (sizeof(uint32_t) - 1))) { + NVME_GUEST_ERR(nvme_ub_mmiord_misaligned32, + "MMIO read not 32-bit aligned," + " offset=0x%"PRIx64"", addr); + /* should RAZ, fall through for now */ + } else if (unlikely(size < sizeof(uint32_t))) { + NVME_GUEST_ERR(nvme_ub_mmiord_toosmall, + "MMIO read smaller than 32-bits," + " offset=0x%"PRIx64"", addr); + /* should RAZ, fall through for now */ + } + if (addr < sizeof(n->bar)) { memcpy(&val, ptr + addr, size); + } else { + NVME_GUEST_ERR(nvme_ub_mmiord_invalid_ofs, + "MMIO read beyond last register," + " offset=0x%"PRIx64", returning 0", addr); } + return val; } @@ -XXX,XX +XXX,XX @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) { uint32_t qid; - if (addr & ((1 << 2) - 1)) { + if (unlikely(addr & ((1 << 2) - 1))) { + NVME_GUEST_ERR(nvme_ub_db_wr_misaligned, + "doorbell write not 32-bit aligned," + " offset=0x%"PRIx64", ignoring", addr); return; } if (((addr - 0x1000) >> 2) & 1) { + /* Completion queue doorbell write */ + uint16_t new_head = val & 0xffff; int start_sqs; NvmeCQueue *cq; qid = (addr - (0x1000 + (1 << 2))) >> 3; - if (nvme_check_cqid(n, qid)) { + if (unlikely(nvme_check_cqid(n, qid))) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cq, + "completion queue doorbell write" + " for nonexistent queue," + " sqid=%"PRIu32", ignoring", qid); return; } cq = n->cq[qid]; - if (new_head >= cq->size) { + if (unlikely(new_head >= cq->size)) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cqhead, + "completion queue doorbell write value" + " beyond queue size, sqid=%"PRIu32"," + " new_head=%"PRIu16", ignoring", + qid, new_head); return; } @@ -XXX,XX +XXX,XX @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) nvme_isr_notify(n, cq); } } else { + /* Submission queue doorbell write */ + uint16_t new_tail = val & 0xffff; NvmeSQueue *sq; qid = (addr - 0x1000) >> 3; - if (nvme_check_sqid(n, qid)) { + if (unlikely(nvme_check_sqid(n, qid))) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sq, + "submission queue doorbell write" + " for nonexistent queue," + " sqid=%"PRIu32", ignoring", qid); return; } sq = n->sq[qid]; - if (new_tail >= sq->size) { + if (unlikely(new_tail >= sq->size)) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sqtail, + "submission queue doorbell write value" + " beyond queue size, sqid=%"PRIu32"," + " new_tail=%"PRIu16", ignoring", + qid, new_tail); return; } diff --git a/hw/block/trace-events b/hw/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -XXX,XX +XXX,XX @@ virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint6 hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d" hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int trans) "blk %p CHS %u %u %u trans %d" +# hw/block/nvme.c +# nvme traces for successful events +nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u" +nvme_irq_pin(void) "pulsing IRQ pin" +nvme_irq_masked(void) "IRQ is masked" +nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" +nvme_rw(char const *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64"" +nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16"" +nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d" +nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16"" +nvme_del_cq(uint16_t cqid) "deleted completion queue, sqid=%"PRIu16"" +nvme_identify_ctrl(void) "identify controller" +nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16"" +nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16"" +nvme_getfeat_vwcache(char const* result) "get feature volatile write cache, result=%s" +nvme_getfeat_numq(int result) "get feature number of queues, result=%d" +nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d" +nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64"" +nvme_mmio_aqattr(uint64_t data) "wrote MMIO, admin queue attributes=0x%"PRIx64"" +nvme_mmio_asqaddr(uint64_t data) "wrote MMIO, admin submission queue address=0x%"PRIx64"" +nvme_mmio_acqaddr(uint64_t data) "wrote MMIO, admin completion queue address=0x%"PRIx64"" +nvme_mmio_asqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin submission queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +nvme_mmio_acqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin completion queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +nvme_mmio_start_success(void) "setting controller enable bit succeeded" +nvme_mmio_stopped(void) "cleared controller enable bit" +nvme_mmio_shutdown_set(void) "shutdown bit set" +nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" + +# nvme traces for error conditions +nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" +nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64"" +nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64"" +nvme_err_invalid_prp2_missing(void) "PRP2 is null and more data to be transferred" +nvme_err_invalid_field(void) "invalid field" +nvme_err_invalid_prp(void) "invalid PRP" +nvme_err_invalid_sgl(void) "invalid SGL" +nvme_err_invalid_ns(uint32_t ns, uint32_t limit) "invalid namespace %u not within 1-%u" +nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8"" +nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8"" +nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64"" +nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, sid=%"PRIu16"" +nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission queue, invalid cqid=%"PRIu16"" +nvme_err_invalid_create_sq_sqid(uint16_t sqid) "failed creating submission queue, invalid sqid=%"PRIu16"" +nvme_err_invalid_create_sq_size(uint16_t qsize) "failed creating submission queue, invalid qsize=%"PRIu16"" +nvme_err_invalid_create_sq_addr(uint64_t addr) "failed creating submission queue, addr=0x%"PRIx64"" +nvme_err_invalid_create_sq_qflags(uint16_t qflags) "failed creating submission queue, qflags=%"PRIu16"" +nvme_err_invalid_del_cq_cqid(uint16_t cqid) "failed deleting completion queue, cqid=%"PRIu16"" +nvme_err_invalid_del_cq_notempty(uint16_t cqid) "failed deleting completion queue, it is not empty, cqid=%"PRIu16"" +nvme_err_invalid_create_cq_cqid(uint16_t cqid) "failed creating completion queue, cqid=%"PRIu16"" +nvme_err_invalid_create_cq_size(uint16_t size) "failed creating completion queue, size=%"PRIu16"" +nvme_err_invalid_create_cq_addr(uint64_t addr) "failed creating completion queue, addr=0x%"PRIx64"" +nvme_err_invalid_create_cq_vector(uint16_t vector) "failed creating completion queue, vector=%"PRIu16"" +nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion queue, qflags=%"PRIu16"" +nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16"" +nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32"" +nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32"" +nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues" +nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues" +nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null" +nvme_err_startfail_nbaracq(void) "nvme_start_ctrl failed because the admin completion queue address is null" +nvme_err_startfail_asq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin submission queue address is misaligned: 0x%"PRIx64"" +nvme_err_startfail_acq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin completion queue address is misaligned: 0x%"PRIx64"" +nvme_err_startfail_page_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too small: log2size=%u, min=%u" +nvme_err_startfail_page_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too large: log2size=%u, max=%u" +nvme_err_startfail_cqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too small: log2size=%u, min=%u" +nvme_err_startfail_cqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too large: log2size=%u, max=%u" +nvme_err_startfail_sqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too small: log2size=%u, min=%u" +nvme_err_startfail_sqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too large: log2size=%u, max=%u" +nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the admin submission queue size is zero" +nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero" +nvme_err_startfail(void) "setting controller enable bit failed" + +# Traces for undefined behavior +nvme_ub_mmiowr_misaligned32(uint64_t offset) "MMIO write not 32-bit aligned, offset=0x%"PRIx64"" +nvme_ub_mmiowr_toosmall(uint64_t offset, unsigned size) "MMIO write smaller than 32 bits, offset=0x%"PRIx64", size=%u" +nvme_ub_mmiowr_intmask_with_msix(void) "undefined access to interrupt mask set when MSI-X is enabled" +nvme_ub_mmiowr_ro_csts(void) "attempted to set a read only bit of controller status" +nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CAP.NSSRS is zero (not supported)" +nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)" +nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored" +nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored" +nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64"" +nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64"" +nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64"" +nvme_ub_mmiord_invalid_ofs(uint64_t offset) "MMIO read beyond last register, offset=0x%"PRIx64", returning 0" +nvme_ub_db_wr_misaligned(uint64_t offset) "doorbell write not 32-bit aligned, offset=0x%"PRIx64", ignoring" +nvme_ub_db_wr_invalid_cq(uint32_t qid) "completion queue doorbell write for nonexistent queue, cqid=%"PRIu32", ignoring" +nvme_ub_db_wr_invalid_cqhead(uint32_t qid, uint16_t new_head) "completion queue doorbell write value beyond queue size, cqid=%"PRIu32", new_head=%"PRIu16", ignoring" +nvme_ub_db_wr_invalid_sq(uint32_t qid) "submission queue doorbell write for nonexistent queue, sqid=%"PRIu32", ignoring" +nvme_ub_db_wr_invalid_sqtail(uint32_t qid, uint16_t new_tail) "submission queue doorbell write value beyond queue size, sqid=%"PRIu32", new_head=%"PRIu16", ignoring" + # hw/block/xen_disk.c xen_disk_alloc(char *name) "%s" xen_disk_init(char *name) "%s" -- 2.13.6 From: Fam Zheng <famz@redhat.com> Management tools create overlays of running guests with qemu-img: $ qemu-img create -b /image/in/use.qcow2 -f qcow2 /overlay/image.qcow2 but this doesn't work anymore due to image locking: qemu-img: /overlay/image.qcow2: Failed to get shared "write" lock Is another process using the image? Could not open backing image to determine size. Use the force share option to allow this use case again. Cc: qemu-stable@nongnu.org Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_img_create(const char *filename, const char *fmt, back_flags = flags; back_flags &= ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING); + backing_options = qdict_new(); if (backing_fmt) { - backing_options = qdict_new(); qdict_put_str(backing_options, "driver", backing_fmt); } + qdict_put_bool(backing_options, BDRV_OPT_FORCE_SHARE, true); bs = bdrv_open(full_backing, NULL, backing_options, back_flags, &local_err); -- 2.13.6 From: Thomas Huth <thuth@redhat.com> It's not working anymore since QEMU v1.3.0 - time to remove it now. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 11 ----------- qemu-doc.texi | 6 ------ 2 files changed, 17 deletions(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_legacy_drive_opts = { .type = QEMU_OPT_STRING, .help = "chs translation (auto, lba, none)", },{ - .name = "boot", - .type = QEMU_OPT_BOOL, - .help = "(deprecated, ignored)", - },{ .name = "addr", .type = QEMU_OPT_STRING, .help = "pci address (virtio only)", @@ -XXX,XX +XXX,XX @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type) goto fail; } - /* Deprecated option boot=[on|off] */ - if (qemu_opt_get(legacy_opts, "boot") != NULL) { - fprintf(stderr, "qemu-kvm: boot=on|off is deprecated and will be " - "ignored. Future versions will reject this parameter. Please " - "update your scripts.\n"); - } - /* Other deprecated options */ if (!qtest_enabled()) { for (i = 0; i < ARRAY_SIZE(deprecated); i++) { diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ deprecated. @section System emulator command line arguments -@subsection -drive boot=on|off (since 1.3.0) - -The ``boot=on|off'' option to the ``-drive'' argument is -ignored. Applications should use the ``bootindex=N'' parameter -to set an absolute ordering between devices instead. - @subsection -tdf (since 1.3.0) The ``-tdf'' argument is ignored. The behaviour implemented -- 2.13.6 From: Thomas Huth <thuth@redhat.com> It's been marked as deprecated since QEMU v2.10.0, and so far nobody complained that we should keep it, so let's remove this legacy option now to simplify the code quite a bit. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- vl.c | 86 ++------------------------------------------------------- qemu-doc.texi | 8 ------ qemu-options.hx | 19 ++----------- 3 files changed, 4 insertions(+), 109 deletions(-) diff --git a/vl.c b/vl.c index XXXXXXX..XXXXXXX 100644 --- a/vl.c +++ b/vl.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) const char *boot_order = NULL; const char *boot_once = NULL; DisplayState *ds; - int cyls, heads, secs, translation; QemuOpts *opts, *machine_opts; - QemuOpts *hda_opts = NULL, *icount_opts = NULL, *accel_opts = NULL; + QemuOpts *icount_opts = NULL, *accel_opts = NULL; QemuOptsList *olist; int optind; const char *optarg; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) cpu_model = NULL; snapshot = 0; - cyls = heads = secs = 0; - translation = BIOS_ATA_TRANSLATION_AUTO; nb_nics = 0; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) if (optind >= argc) break; if (argv[optind][0] != '-') { - hda_opts = drive_add(IF_DEFAULT, 0, argv[optind++], HD_OPTS); + drive_add(IF_DEFAULT, 0, argv[optind++], HD_OPTS); } else { const QEMUOption *popt; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) cpu_model = optarg; break; case QEMU_OPTION_hda: - { - char buf[256]; - if (cyls == 0) - snprintf(buf, sizeof(buf), "%s", HD_OPTS); - else - snprintf(buf, sizeof(buf), - "%s,cyls=%d,heads=%d,secs=%d%s", - HD_OPTS , cyls, heads, secs, - translation == BIOS_ATA_TRANSLATION_LBA ? - ",trans=lba" : - translation == BIOS_ATA_TRANSLATION_NONE ? - ",trans=none" : ""); - drive_add(IF_DEFAULT, 0, optarg, buf); - break; - } case QEMU_OPTION_hdb: case QEMU_OPTION_hdc: case QEMU_OPTION_hdd: @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) case QEMU_OPTION_snapshot: snapshot = 1; break; - case QEMU_OPTION_hdachs: - { - const char *p; - p = optarg; - cyls = strtol(p, (char **)&p, 0); - if (cyls < 1 || cyls > 16383) - goto chs_fail; - if (*p != ',') - goto chs_fail; - p++; - heads = strtol(p, (char **)&p, 0); - if (heads < 1 || heads > 16) - goto chs_fail; - if (*p != ',') - goto chs_fail; - p++; - secs = strtol(p, (char **)&p, 0); - if (secs < 1 || secs > 63) - goto chs_fail; - if (*p == ',') { - p++; - if (!strcmp(p, "large")) { - translation = BIOS_ATA_TRANSLATION_LARGE; - } else if (!strcmp(p, "rechs")) { - translation = BIOS_ATA_TRANSLATION_RECHS; - } else if (!strcmp(p, "none")) { - translation = BIOS_ATA_TRANSLATION_NONE; - } else if (!strcmp(p, "lba")) { - translation = BIOS_ATA_TRANSLATION_LBA; - } else if (!strcmp(p, "auto")) { - translation = BIOS_ATA_TRANSLATION_AUTO; - } else { - goto chs_fail; - } - } else if (*p != '\0') { - chs_fail: - error_report("invalid physical CHS format"); - exit(1); - } - if (hda_opts != NULL) { - qemu_opt_set_number(hda_opts, "cyls", cyls, - &error_abort); - qemu_opt_set_number(hda_opts, "heads", heads, - &error_abort); - qemu_opt_set_number(hda_opts, "secs", secs, - &error_abort); - if (translation == BIOS_ATA_TRANSLATION_LARGE) { - qemu_opt_set(hda_opts, "trans", "large", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_RECHS) { - qemu_opt_set(hda_opts, "trans", "rechs", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_LBA) { - qemu_opt_set(hda_opts, "trans", "lba", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_NONE) { - qemu_opt_set(hda_opts, "trans", "none", - &error_abort); - } - } - } - error_report("'-hdachs' is deprecated, please use '-device" - " ide-hd,cyls=c,heads=h,secs=s,...' instead"); - break; case QEMU_OPTION_numa: opts = qemu_opts_parse_noisily(qemu_find_opts("numa"), optarg, true); diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ The ``--net dump'' argument is now replaced with the ``-object filter-dump'' argument which works in combination with the modern ``-netdev`` backends instead. -@subsection -hdachs (since 2.10.0) - -The ``-hdachs'' argument is now a synonym for setting -the ``cyls'', ``heads'', ``secs'', and ``trans'' properties -on the ``ide-hd'' device using the ``-device'' argument. -The new syntax allows different settings to be provided -per disk. - @subsection -usbdevice (since 2.10.0) The ``-usbdevice DEV'' argument is now a synonym for setting diff --git a/qemu-options.hx b/qemu-options.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -XXX,XX +XXX,XX @@ of available connectors of a given interface type. @item media=@var{media} This option defines the type of the media: disk or cdrom. @item cyls=@var{c},heads=@var{h},secs=@var{s}[,trans=@var{t}] -These options have the same definition as they have in @option{-hdachs}. -These parameters are deprecated, use the corresponding parameters +Force disk physical geometry and the optional BIOS translation (trans=none or +lba). These parameters are deprecated, use the corresponding parameters of @code{-device} instead. @item snapshot=@var{snapshot} @var{snapshot} is "on" or "off" and controls snapshot mode for the given drive @@ -XXX,XX +XXX,XX @@ the raw disk image you use is not written back. You can however force the write back by pressing @key{C-a s} (@pxref{disk_images}). ETEXI -DEF("hdachs", HAS_ARG, QEMU_OPTION_hdachs, \ - "-hdachs c,h,s[,t]\n" \ - " force hard disk 0 physical geometry and the optional BIOS\n" \ - " translation (t=none or lba) (usually QEMU can guess them)\n", - QEMU_ARCH_ALL) -STEXI -@item -hdachs @var{c},@var{h},@var{s},[,@var{t}] -@findex -hdachs -Force hard disk 0 physical geometry (1 <= @var{c} <= 16383, 1 <= -@var{h} <= 16, 1 <= @var{s} <= 63) and optionally force the BIOS -translation mode (@var{t}=none, lba or auto). Usually QEMU can guess -all those parameters. This option is deprecated, please use -@code{-device ide-hd,cyls=c,heads=h,secs=s,...} instead. -ETEXI - DEF("fsdev", HAS_ARG, QEMU_OPTION_fsdev, "-fsdev fsdriver,id=id[,path=path,][security_model={mapped-xattr|mapped-file|passthrough|none}]\n" " [,writeout=immediate][,readonly][,socket=socket|sock_fd=sock_fd][,fmode=fmode][,dmode=dmode]\n" -- 2.13.6 From: Thomas Huth <thuth@redhat.com> Looks like we forgot to announce the deprecation of these options in the corresponding chapter of the qemu-doc text, so let's do that now. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-doc.texi | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ longer be directly supported in QEMU. The ``-drive if=scsi'' argument is replaced by the the ``-device BUS-TYPE'' argument combined with ``-drive if=none''. +@subsection -drive cyls=...,heads=...,secs=...,trans=... (since 2.10.0) + +The drive geometry arguments are replaced by the the geometry arguments +that can be specified with the ``-device'' parameter. + +@subsection -drive serial=... (since 2.10.0) + +The drive serial argument is replaced by the the serial argument +that can be specified with the ``-device'' parameter. + +@subsection -drive addr=... (since 2.10.0) + +The drive addr argument is replaced by the the addr argument +that can be specified with the ``-device'' parameter. + @subsection -net dump (since 2.10.0) The ``--net dump'' argument is now replaced with the -- 2.13.6 From: Fam Zheng <famz@redhat.com> Signed-off-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 1 - block/io.c | 18 ------------------ 2 files changed, 19 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ bool blk_dev_is_tray_open(BlockBackend *blk); bool blk_dev_is_medium_locked(BlockBackend *blk); void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes); -bool bdrv_requests_pending(BlockDriverState *bs); void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out); void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in); diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_disable_copy_on_read(BlockDriverState *bs) assert(old >= 1); } -/* Check if any requests are in-flight (including throttled requests) */ -bool bdrv_requests_pending(BlockDriverState *bs) -{ - BdrvChild *child; - - if (atomic_read(&bs->in_flight)) { - return true; - } - - QLIST_FOREACH(child, &bs->children, next) { - if (bdrv_requests_pending(child->bs)) { - return true; - } - } - - return false; -} - typedef struct { Coroutine *co; BlockDriverState *bs; -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/io.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) BdrvNextIterator it; GSList *aio_ctxs = NULL, *ctx; + /* BDRV_POLL_WHILE() for a node can only be called from its own I/O thread + * or the main loop AioContext. We potentially use BDRV_POLL_WHILE() on + * nodes in several different AioContexts, so make sure we're in the main + * context. */ + assert(qemu_get_current_aio_context() == qemu_get_aio_context()); + block_job_pause_all(); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { -- 2.13.6 bdrv_drained_begin() doesn't increase bs->quiesce_counter recursively and also doesn't notify other parent nodes of children, which both means that the child nodes are not actually drained, and bdrv_drained_begin() is providing useful functionality only on a single node. To keep things consistent, we also shouldn't call the block driver callbacks recursively. A proper recursive drain version that provides an actually working drained section for child nodes will be introduced later. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/io.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_drain_invoke_entry(void *opaque) } /* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */ -static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) +static void bdrv_drain_invoke(BlockDriverState *bs, bool begin, bool recursive) { BdrvChild *child, *tmp; BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin}; @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) bdrv_coroutine_enter(bs, data.co); BDRV_POLL_WHILE(bs, !data.done); - QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { - bdrv_drain_invoke(child->bs, begin); + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { + bdrv_drain_invoke(child->bs, begin, true); + } } } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) bdrv_parent_drained_begin(bs); } - bdrv_drain_invoke(bs, true); + bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) } /* Re-enable things in child-to-parent order */ - bdrv_drain_invoke(bs, false); + bdrv_drain_invoke(bs, false, false); bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); aio_disable_external(aio_context); bdrv_parent_drained_begin(bs); - bdrv_drain_invoke(bs, true); + bdrv_drain_invoke(bs, true, true); aio_context_release(aio_context); if (!g_slist_find(aio_ctxs, aio_context)) { @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); - bdrv_drain_invoke(bs, false); + bdrv_drain_invoke(bs, false, true); bdrv_parent_drained_end(bs); aio_enable_external(aio_context); aio_context_release(aio_context); -- 2.13.6 The existing test is for bdrv_drain_all_begin/end() only. Generalise the test case so that it can be run for the other variants as well. At the moment this is only bdrv_drain_begin/end(), but in a while, we'll add another one. Also, add a backing file to the test node to test whether the operations work recursively. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 69 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 62 insertions(+), 7 deletions(-) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_test = { .bdrv_co_drain_begin = bdrv_test_co_drain_begin, .bdrv_co_drain_end = bdrv_test_co_drain_end, + + .bdrv_child_perm = bdrv_format_default_perms, }; static void aio_ret_cb(void *opaque, int ret) @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) *aio_ret = ret; } -static void test_drv_cb_drain_all(void) +enum drain_type { + BDRV_DRAIN_ALL, + BDRV_DRAIN, +}; + +static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) +{ + switch (drain_type) { + case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break; + case BDRV_DRAIN: bdrv_drained_begin(bs); break; + default: g_assert_not_reached(); + } +} + +static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs) +{ + switch (drain_type) { + case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break; + case BDRV_DRAIN: bdrv_drained_end(bs); break; + default: g_assert_not_reached(); + } +} + +static void test_drv_cb_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; - BlockDriverState *bs; - BDRVTestState *s; + BlockDriverState *bs, *backing; + BDRVTestState *s, *backing_s; BlockAIOCB *acb; int aio_ret; @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_all(void) s = bs->opaque; blk_insert_bs(blk, bs, &error_abort); + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs, backing, &error_abort); + /* Simple bdrv_drain_all_begin/end pair, check that CBs are called */ g_assert_cmpint(s->drain_count, ==, 0); - bdrv_drain_all_begin(); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 1); - bdrv_drain_all_end(); + g_assert_cmpint(backing_s->drain_count, ==, !!recursive); + + do_drain_end(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); /* Now do the same while a request is pending */ aio_ret = -EINPROGRESS; @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_all(void) g_assert_cmpint(aio_ret, ==, -EINPROGRESS); g_assert_cmpint(s->drain_count, ==, 0); - bdrv_drain_all_begin(); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(drain_type, bs); + g_assert_cmpint(aio_ret, ==, 0); g_assert_cmpint(s->drain_count, ==, 1); - bdrv_drain_all_end(); + g_assert_cmpint(backing_s->drain_count, ==, !!recursive); + + do_drain_end(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + bdrv_unref(backing); bdrv_unref(bs); blk_unref(blk); } +static void test_drv_cb_drain_all(void) +{ + test_drv_cb_common(BDRV_DRAIN_ALL, true); +} + +static void test_drv_cb_drain(void) +{ + test_drv_cb_common(BDRV_DRAIN, false); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_init(&argc, &argv, NULL); g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); + g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); return g_test_run(); } -- 2.13.6 This is currently only working correctly for bdrv_drain(), not for bdrv_drain_all(). Leave a comment for the drain_all case, we'll address it later. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain(void) test_drv_cb_common(BDRV_DRAIN, false); } +static void test_quiesce_common(enum drain_type drain_type, bool recursive) +{ + BlockBackend *blk; + BlockDriverState *bs, *backing; + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + blk_insert_bs(blk, bs, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + bdrv_set_backing_hd(bs, backing, &error_abort); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + + do_drain_begin(drain_type, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, !!recursive); + + do_drain_end(drain_type, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs); + blk_unref(blk); +} + +static void test_quiesce_drain_all(void) +{ + // XXX drain_all doesn't quiesce + //test_quiesce_common(BDRV_DRAIN_ALL, true); +} + +static void test_quiesce_drain(void) +{ + test_quiesce_common(BDRV_DRAIN, false); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); + g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); + g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + return g_test_run(); } -- 2.13.6 Block jobs already paused themselves when their main BlockBackend entered a drained section. This is not good enough: We also want to pause a block job and may not submit new requests if, for example, the mirror target node should be drained. This implements .drained_begin/end callbacks in child_job in order to consider all block nodes related to the job, and removes the BlockBackend callbacks which are unnecessary now because the root of the job main BlockBackend is always referenced with a child_job, too. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static char *child_job_get_parent_desc(BdrvChild *c) job->id); } -static const BdrvChildRole child_job = { - .get_parent_desc = child_job_get_parent_desc, - .stay_at_node = true, -}; - -static void block_job_drained_begin(void *opaque) +static void child_job_drained_begin(BdrvChild *c) { - BlockJob *job = opaque; + BlockJob *job = c->opaque; block_job_pause(job); } -static void block_job_drained_end(void *opaque) +static void child_job_drained_end(BdrvChild *c) { - BlockJob *job = opaque; + BlockJob *job = c->opaque; block_job_resume(job); } -static const BlockDevOps block_job_dev_ops = { - .drained_begin = block_job_drained_begin, - .drained_end = block_job_drained_end, +static const BdrvChildRole child_job = { + .get_parent_desc = child_job_get_parent_desc, + .drained_begin = child_job_drained_begin, + .drained_end = child_job_drained_end, + .stay_at_node = true, }; void block_job_remove_all_bdrv(BlockJob *job) @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort); bs->job = job; - blk_set_dev_ops(blk, &block_job_dev_ops, job); bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker); QLIST_INSERT_HEAD(&block_jobs, job, job_list); -- 2.13.6 Block jobs must be paused if any of the involved nodes are drained. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 121 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "block/block.h" +#include "block/blockjob_int.h" #include "sysemu/block-backend.h" #include "qapi/error.h" @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } + +typedef struct TestBlockJob { + BlockJob common; + bool should_complete; +} TestBlockJob; + +static void test_job_completed(BlockJob *job, void *opaque) +{ + block_job_completed(job, 0); +} + +static void coroutine_fn test_job_start(void *opaque) +{ + TestBlockJob *s = opaque; + + while (!s->should_complete) { + block_job_sleep_ns(&s->common, 100000); + } + + block_job_defer_to_main_loop(&s->common, test_job_completed, NULL); +} + +static void test_job_complete(BlockJob *job, Error **errp) +{ + TestBlockJob *s = container_of(job, TestBlockJob, common); + s->should_complete = true; +} + +BlockJobDriver test_job_driver = { + .instance_size = sizeof(TestBlockJob), + .start = test_job_start, + .complete = test_job_complete, +}; + +static void test_blockjob_common(enum drain_type drain_type) +{ + BlockBackend *blk_src, *blk_target; + BlockDriverState *src, *target; + BlockJob *job; + int ret; + + src = bdrv_new_open_driver(&bdrv_test, "source", BDRV_O_RDWR, + &error_abort); + blk_src = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + blk_insert_bs(blk_src, src, &error_abort); + + target = bdrv_new_open_driver(&bdrv_test, "target", BDRV_O_RDWR, + &error_abort); + blk_target = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + blk_insert_bs(blk_target, target, &error_abort); + + job = block_job_create("job0", &test_job_driver, src, 0, BLK_PERM_ALL, 0, + 0, NULL, NULL, &error_abort); + block_job_add_bdrv(job, "target", target, 0, BLK_PERM_ALL, &error_abort); + block_job_start(job); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + do_drain_begin(drain_type, src); + + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target, and involves an + * additional block_job_pause_all() */ + g_assert_cmpint(job->pause_count, ==, 3); + } else { + g_assert_cmpint(job->pause_count, ==, 1); + } + /* XXX We don't wait until the job is actually paused. Is this okay? */ + /* g_assert_true(job->paused); */ + g_assert_false(job->busy); /* The job is paused */ + + do_drain_end(drain_type, src); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + do_drain_begin(drain_type, target); + + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target, and involves an + * additional block_job_pause_all() */ + g_assert_cmpint(job->pause_count, ==, 3); + } else { + g_assert_cmpint(job->pause_count, ==, 1); + } + /* XXX We don't wait until the job is actually paused. Is this okay? */ + /* g_assert_true(job->paused); */ + g_assert_false(job->busy); /* The job is paused */ + + do_drain_end(drain_type, target); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + ret = block_job_complete_sync(job, &error_abort); + g_assert_cmpint(ret, ==, 0); + + blk_unref(blk_src); + blk_unref(blk_target); + bdrv_unref(src); + bdrv_unref(target); +} + +static void test_blockjob_drain_all(void) +{ + test_blockjob_common(BDRV_DRAIN_ALL); +} + +static void test_blockjob_drain(void) +{ + test_blockjob_common(BDRV_DRAIN); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); + g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); + return g_test_run(); } -- 2.13.6 Block jobs are already paused using the BdrvChildRole drain callbacks, so we don't need an additional block_job_pause_all() call. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 4 ---- tests/test-bdrv-drain.c | 10 ++++------ 2 files changed, 4 insertions(+), 10 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) * context. */ assert(qemu_get_current_aio_context() == qemu_get_aio_context()); - block_job_pause_all(); - for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); aio_context_release(aio_context); } - - block_job_resume_all(); } void bdrv_drain_all(void) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common(enum drain_type drain_type) do_drain_begin(drain_type, src); if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target, and involves an - * additional block_job_pause_all() */ - g_assert_cmpint(job->pause_count, ==, 3); + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->pause_count, ==, 2); } else { g_assert_cmpint(job->pause_count, ==, 1); } @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common(enum drain_type drain_type) do_drain_begin(drain_type, target); if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target, and involves an - * additional block_job_pause_all() */ - g_assert_cmpint(job->pause_count, ==, 3); + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->pause_count, ==, 2); } else { g_assert_cmpint(job->pause_count, ==, 1); } -- 2.13.6 bdrv_do_drained_begin() restricts the call of parent callbacks and aio_disable_external() to the outermost drain section, but the block driver callbacks are always called. bdrv_do_drained_end() must match this behaviour, otherwise nodes stay drained even if begin/end calls were balanced. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) void bdrv_drained_end(BlockDriverState *bs) { + int old_quiesce_counter; + if (qemu_in_coroutine()) { bdrv_co_yield_to_drain(bs, false); return; } assert(bs->quiesce_counter > 0); - if (atomic_fetch_dec(&bs->quiesce_counter) > 1) { - return; - } + old_quiesce_counter = atomic_fetch_dec(&bs->quiesce_counter); /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false, false); - bdrv_parent_drained_end(bs); - aio_enable_external(bdrv_get_aio_context(bs)); + if (old_quiesce_counter == 1) { + bdrv_parent_drained_end(bs); + aio_enable_external(bdrv_get_aio_context(bs)); + } } /* -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, + DRAIN_TYPE_MAX, }; static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } +static void test_nested(void) +{ + BlockBackend *blk; + BlockDriverState *bs, *backing; + BDRVTestState *s, *backing_s; + enum drain_type outer, inner; + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + s = bs->opaque; + blk_insert_bs(blk, bs, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs, backing, &error_abort); + + for (outer = 0; outer < DRAIN_TYPE_MAX; outer++) { + for (inner = 0; inner < DRAIN_TYPE_MAX; inner++) { + /* XXX bdrv_drain_all() doesn't increase the quiesce_counter */ + int bs_quiesce = (outer != BDRV_DRAIN_ALL) + + (inner != BDRV_DRAIN_ALL); + int backing_quiesce = 0; + int backing_cb_cnt = (outer != BDRV_DRAIN) + + (inner != BDRV_DRAIN); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(outer, bs); + do_drain_begin(inner, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, bs_quiesce); + g_assert_cmpint(backing->quiesce_counter, ==, backing_quiesce); + g_assert_cmpint(s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, backing_cb_cnt); + + do_drain_end(inner, bs); + do_drain_end(outer, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + } + } + + bdrv_unref(backing); + bdrv_unref(bs); + blk_unref(blk); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/nested", test_nested); + g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 This is in preparation for subtree drains, i.e. drained sections that affect not only a single node, but recursively all child nodes, too. Calling the parent callbacks for drain is pointless when we just came from that parent node recursively and leads to multiple increases of bs->quiesce_counter in a single drain call. Don't do it. In order for this to work correctly, the parent callback must be called for every bdrv_drain_begin/end() call, not only for the outermost one: If we have a node N with two parents A and B, recursive draining of A should cause the quiesce_counter of B to increase because its child N is drained independently of B. If now B is recursively drained, too, A must increase its quiesce_counter because N is drained independently of A only now, even if N is going from quiesce_counter 1 to 2. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 4 ++-- block.c | 13 +++++++++---- block/io.c | 47 ++++++++++++++++++++++++++++++++++------------- 3 files changed, 45 insertions(+), 19 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_io_unplug(BlockDriverState *bs); * Begin a quiesced section of all users of @bs. This is part of * bdrv_drained_begin. */ -void bdrv_parent_drained_begin(BlockDriverState *bs); +void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore); /** * bdrv_parent_drained_end: @@ -XXX,XX +XXX,XX @@ void bdrv_parent_drained_begin(BlockDriverState *bs); * End a quiesced section of all users of @bs. This is part of * bdrv_drained_end. */ -void bdrv_parent_drained_end(BlockDriverState *bs); +void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore); /** * bdrv_drained_begin: diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs) { BlockDriverState *old_bs = child->bs; + int i; if (old_bs && new_bs) { assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)); } if (old_bs) { if (old_bs->quiesce_counter && child->role->drained_end) { - child->role->drained_end(child); + for (i = 0; i < old_bs->quiesce_counter; i++) { + child->role->drained_end(child); + } } if (child->role->detach) { child->role->detach(child); @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, if (new_bs) { QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent); if (new_bs->quiesce_counter && child->role->drained_begin) { - child->role->drained_begin(child); + for (i = 0; i < new_bs->quiesce_counter; i++) { + child->role->drained_begin(child); + } } if (child->role->attach) { @@ -XXX,XX +XXX,XX @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context) AioContext *ctx = bdrv_get_aio_context(bs); aio_disable_external(ctx); - bdrv_parent_drained_begin(bs); + bdrv_parent_drained_begin(bs, NULL); bdrv_drain(bs); /* ensure there are no in-flight requests */ while (aio_poll(ctx, false)) { @@ -XXX,XX +XXX,XX @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context) */ aio_context_acquire(new_context); bdrv_attach_aio_context(bs, new_context); - bdrv_parent_drained_end(bs); + bdrv_parent_drained_end(bs, NULL); aio_enable_external(ctx); aio_context_release(new_context); } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags); -void bdrv_parent_drained_begin(BlockDriverState *bs) +void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c, *next; QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { + if (c == ignore) { + continue; + } if (c->role->drained_begin) { c->role->drained_begin(c); } } } -void bdrv_parent_drained_end(BlockDriverState *bs) +void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c, *next; QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { + if (c == ignore) { + continue; + } if (c->role->drained_end) { c->role->drained_end(c); } @@ -XXX,XX +XXX,XX @@ typedef struct { BlockDriverState *bs; bool done; bool begin; + BdrvChild *parent; } BdrvCoDrainData; static void coroutine_fn bdrv_drain_invoke_entry(void *opaque) @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs) return waited; } +static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent); +static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent); + static void bdrv_co_drain_bh_cb(void *opaque) { BdrvCoDrainData *data = opaque; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); if (data->begin) { - bdrv_drained_begin(bs); + bdrv_do_drained_begin(bs, data->parent); } else { - bdrv_drained_end(bs); + bdrv_do_drained_end(bs, data->parent); } data->done = true; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, - bool begin) + bool begin, BdrvChild *parent) { BdrvCoDrainData data; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, .bs = bs, .done = false, .begin = begin, + .parent = parent, }; bdrv_inc_in_flight(bs); aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -void bdrv_drained_begin(BlockDriverState *bs) +static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) { if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, true); + bdrv_co_yield_to_drain(bs, true, parent); return; } /* Stop things in parent-to-child order */ if (atomic_fetch_inc(&bs->quiesce_counter) == 0) { aio_disable_external(bdrv_get_aio_context(bs)); - bdrv_parent_drained_begin(bs); } + bdrv_parent_drained_begin(bs, parent); bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); } -void bdrv_drained_end(BlockDriverState *bs) +void bdrv_drained_begin(BlockDriverState *bs) +{ + bdrv_do_drained_begin(bs, NULL); +} + +static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) { int old_quiesce_counter; if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, false); + bdrv_co_yield_to_drain(bs, false, parent); return; } assert(bs->quiesce_counter > 0); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false, false); + bdrv_parent_drained_end(bs, parent); if (old_quiesce_counter == 1) { - bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } } +void bdrv_drained_end(BlockDriverState *bs) +{ + bdrv_do_drained_end(bs, NULL); +} + /* * Wait for pending requests to complete on a single BlockDriverState subtree, * and suspend block driver's internal I/O until next request arrives. @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) /* Stop things in parent-to-child order */ aio_context_acquire(aio_context); aio_disable_external(aio_context); - bdrv_parent_drained_begin(bs); + bdrv_parent_drained_begin(bs, NULL); bdrv_drain_invoke(bs, true, true); aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); bdrv_drain_invoke(bs, false, true); - bdrv_parent_drained_end(bs); + bdrv_parent_drained_end(bs, NULL); aio_enable_external(aio_context); aio_context_release(aio_context); } -- 2.13.6 bdrv_drained_begin() waits for the completion of requests in the whole subtree, but it only actually keeps its immediate bs parameter quiesced until bdrv_drained_end(). Add a version that keeps the whole subtree drained. As of this commit, graph changes cannot be allowed during a subtree drained section, but this will be fixed soon. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 13 +++++++++++++ block/io.c | 54 ++++++++++++++++++++++++++++++++++++++++----------- 2 files changed, 56 insertions(+), 11 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore); void bdrv_drained_begin(BlockDriverState *bs); /** + * Like bdrv_drained_begin, but recursively begins a quiesced section for + * exclusive access to all child nodes as well. + * + * Graph changes are not allowed during a subtree drain section. + */ +void bdrv_subtree_drained_begin(BlockDriverState *bs); + +/** * bdrv_drained_end: * * End a quiescent section started by bdrv_drained_begin(). */ void bdrv_drained_end(BlockDriverState *bs); +/** + * End a quiescent section started by bdrv_subtree_drained_begin(). + */ +void bdrv_subtree_drained_end(BlockDriverState *bs); + void bdrv_add_child(BlockDriverState *parent, BlockDriverState *child, Error **errp); void bdrv_del_child(BlockDriverState *parent, BdrvChild *child, Error **errp); diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ typedef struct { BlockDriverState *bs; bool done; bool begin; + bool recursive; BdrvChild *parent; } BdrvCoDrainData; @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs) return waited; } -static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent); -static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent); +static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent); +static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent); static void bdrv_co_drain_bh_cb(void *opaque) { @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); if (data->begin) { - bdrv_do_drained_begin(bs, data->parent); + bdrv_do_drained_begin(bs, data->recursive, data->parent); } else { - bdrv_do_drained_end(bs, data->parent); + bdrv_do_drained_end(bs, data->recursive, data->parent); } data->done = true; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, - bool begin, BdrvChild *parent) + bool begin, bool recursive, + BdrvChild *parent) { BdrvCoDrainData data; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, .bs = bs, .done = false, .begin = begin, + .recursive = recursive, .parent = parent, }; bdrv_inc_in_flight(bs); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) +static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { + BdrvChild *child, *next; + if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, true, parent); + bdrv_co_yield_to_drain(bs, true, recursive, parent); return; } @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) bdrv_parent_drained_begin(bs, parent); bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); + + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, next) { + bdrv_do_drained_begin(child->bs, true, child); + } + } } void bdrv_drained_begin(BlockDriverState *bs) { - bdrv_do_drained_begin(bs, NULL); + bdrv_do_drained_begin(bs, false, NULL); +} + +void bdrv_subtree_drained_begin(BlockDriverState *bs) +{ + bdrv_do_drained_begin(bs, true, NULL); } -static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) +static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { + BdrvChild *child, *next; int old_quiesce_counter; if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, false, parent); + bdrv_co_yield_to_drain(bs, false, recursive, parent); return; } assert(bs->quiesce_counter > 0); @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) if (old_quiesce_counter == 1) { aio_enable_external(bdrv_get_aio_context(bs)); } + + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, next) { + bdrv_do_drained_end(child->bs, true, child); + } + } } void bdrv_drained_end(BlockDriverState *bs) { - bdrv_do_drained_end(bs, NULL); + bdrv_do_drained_end(bs, false, NULL); +} + +void bdrv_subtree_drained_end(BlockDriverState *bs) +{ + bdrv_do_drained_end(bs, true, NULL); } /* -- 2.13.6 Add a subtree drain version to the existing test cases. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, + BDRV_SUBTREE_DRAIN, DRAIN_TYPE_MAX, }; @@ -XXX,XX +XXX,XX @@ static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) switch (drain_type) { case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break; case BDRV_DRAIN: bdrv_drained_begin(bs); break; + case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_begin(bs); break; default: g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs) switch (drain_type) { case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break; case BDRV_DRAIN: bdrv_drained_end(bs); break; + case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_end(bs); break; default: g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain(void) test_drv_cb_common(BDRV_DRAIN, false); } +static void test_drv_cb_drain_subtree(void) +{ + test_drv_cb_common(BDRV_SUBTREE_DRAIN, true); +} + static void test_quiesce_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } +static void test_quiesce_drain_subtree(void) +{ + test_quiesce_common(BDRV_SUBTREE_DRAIN, true); +} + static void test_nested(void) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_nested(void) /* XXX bdrv_drain_all() doesn't increase the quiesce_counter */ int bs_quiesce = (outer != BDRV_DRAIN_ALL) + (inner != BDRV_DRAIN_ALL); - int backing_quiesce = 0; + int backing_quiesce = (outer == BDRV_SUBTREE_DRAIN) + + (inner == BDRV_SUBTREE_DRAIN); int backing_cb_cnt = (outer != BDRV_DRAIN) + (inner != BDRV_DRAIN); @@ -XXX,XX +XXX,XX @@ static void test_blockjob_drain(void) test_blockjob_common(BDRV_DRAIN); } +static void test_blockjob_drain_subtree(void) +{ + test_blockjob_common(BDRV_SUBTREE_DRAIN); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); + g_test_add_func("/bdrv-drain/driver-cb/drain_subtree", + test_drv_cb_drain_subtree); g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/quiesce/drain_subtree", + test_quiesce_drain_subtree); g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); + g_test_add_func("/bdrv-drain/blockjob/drain_subtree", + test_blockjob_drain_subtree); return g_test_run(); } -- 2.13.6 If bdrv_do_drained_begin/end() are called in coroutine context, they first use a BH to get out of the coroutine context. Call some existing tests again from a coroutine to cover this code path. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) *aio_ret = ret; } +typedef struct CallInCoroutineData { + void (*entry)(void); + bool done; +} CallInCoroutineData; + +static coroutine_fn void call_in_coroutine_entry(void *opaque) +{ + CallInCoroutineData *data = opaque; + + data->entry(); + data->done = true; +} + +static void call_in_coroutine(void (*entry)(void)) +{ + Coroutine *co; + CallInCoroutineData data = { + .entry = entry, + .done = false, + }; + + co = qemu_coroutine_create(call_in_coroutine_entry, &data); + qemu_coroutine_enter(co); + while (!data.done) { + aio_poll(qemu_get_aio_context(), true); + } +} + enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_subtree(void) test_drv_cb_common(BDRV_SUBTREE_DRAIN, true); } +static void test_drv_cb_co_drain(void) +{ + call_in_coroutine(test_drv_cb_drain); +} + +static void test_drv_cb_co_drain_subtree(void) +{ + call_in_coroutine(test_drv_cb_drain_subtree); +} + static void test_quiesce_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain_subtree(void) test_quiesce_common(BDRV_SUBTREE_DRAIN, true); } +static void test_quiesce_co_drain(void) +{ + call_in_coroutine(test_quiesce_drain); +} + +static void test_quiesce_co_drain_subtree(void) +{ + call_in_coroutine(test_quiesce_drain_subtree); +} + static void test_nested(void) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_subtree", test_drv_cb_drain_subtree); + // XXX bdrv_drain_all() doesn't work in coroutine context + g_test_add_func("/bdrv-drain/driver-cb/co/drain", test_drv_cb_co_drain); + g_test_add_func("/bdrv-drain/driver-cb/co/drain_subtree", + test_drv_cb_co_drain_subtree); + + g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); g_test_add_func("/bdrv-drain/quiesce/drain_subtree", test_quiesce_drain_subtree); + // XXX bdrv_drain_all() doesn't work in coroutine context + g_test_add_func("/bdrv-drain/quiesce/co/drain", test_quiesce_co_drain); + g_test_add_func("/bdrv-drain/quiesce/co/drain_subtree", + test_quiesce_co_drain_subtree); + g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); -- 2.13.6 Test that drain sections are correctly propagated through the graph. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_nested(void) blk_unref(blk); } +static void test_multiparent(void) +{ + BlockBackend *blk_a, *blk_b; + BlockDriverState *bs_a, *bs_b, *backing; + BDRVTestState *a_s, *b_s, *backing_s; + + blk_a = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR, + &error_abort); + a_s = bs_a->opaque; + blk_insert_bs(blk_a, bs_a, &error_abort); + + blk_b = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR, + &error_abort); + b_s = bs_b->opaque; + blk_insert_bs(blk_b, bs_b, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs_a, backing, &error_abort); + bdrv_set_backing_hd(bs_b, backing, &error_abort); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 1); + g_assert_cmpint(bs_b->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, 1); + g_assert_cmpint(a_s->drain_count, ==, 1); + g_assert_cmpint(b_s->drain_count, ==, 1); + g_assert_cmpint(backing_s->drain_count, ==, 1); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 2); + g_assert_cmpint(bs_b->quiesce_counter, ==, 2); + g_assert_cmpint(backing->quiesce_counter, ==, 2); + g_assert_cmpint(a_s->drain_count, ==, 2); + g_assert_cmpint(b_s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, 2); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 1); + g_assert_cmpint(bs_b->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, 1); + g_assert_cmpint(a_s->drain_count, ==, 1); + g_assert_cmpint(b_s->drain_count, ==, 1); + g_assert_cmpint(backing_s->drain_count, ==, 1); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs_a); + bdrv_unref(bs_b); + blk_unref(blk_a); + blk_unref(blk_b); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) test_quiesce_co_drain_subtree); g_test_add_func("/bdrv-drain/nested", test_nested); + g_test_add_func("/bdrv-drain/multiparent", test_multiparent); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 We need to remember how many of the drain sections in which a node is were recursive (i.e. subtree drain rather than node drain), so that they can be correctly applied when children are added or removed during the drained section. With this change, it is safe to modify the graph even inside a bdrv_subtree_drained_begin/end() section. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 2 -- include/block/block_int.h | 5 +++++ block.c | 32 +++++++++++++++++++++++++++++--- block/io.c | 28 ++++++++++++++++++++++++---- 4 files changed, 58 insertions(+), 9 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs); /** * Like bdrv_drained_begin, but recursively begins a quiesced section for * exclusive access to all child nodes as well. - * - * Graph changes are not allowed during a subtree drain section. */ void bdrv_subtree_drained_begin(BlockDriverState *bs); diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* Accessed with atomic ops. */ int quiesce_counter; + int recursive_quiesce_counter; + unsigned int write_gen; /* Current data generation */ /* Protected by reqs_lock. */ @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); +void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent); +void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent); + int get_tmp_filename(char *filename, int size); BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size, const char *filename); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_child_cb_drained_end(BdrvChild *child) bdrv_drained_end(bs); } +static void bdrv_child_cb_attach(BdrvChild *child) +{ + BlockDriverState *bs = child->opaque; + bdrv_apply_subtree_drain(child, bs); +} + +static void bdrv_child_cb_detach(BdrvChild *child) +{ + BlockDriverState *bs = child->opaque; + bdrv_unapply_subtree_drain(child, bs); +} + static int bdrv_child_cb_inactivate(BdrvChild *child) { BlockDriverState *bs = child->opaque; @@ -XXX,XX +XXX,XX @@ const BdrvChildRole child_file = { .inherit_options = bdrv_inherited_options, .drained_begin = bdrv_child_cb_drained_begin, .drained_end = bdrv_child_cb_drained_end, + .attach = bdrv_child_cb_attach, + .detach = bdrv_child_cb_detach, .inactivate = bdrv_child_cb_inactivate, }; @@ -XXX,XX +XXX,XX @@ const BdrvChildRole child_format = { .inherit_options = bdrv_inherited_fmt_options, .drained_begin = bdrv_child_cb_drained_begin, .drained_end = bdrv_child_cb_drained_end, + .attach = bdrv_child_cb_attach, + .detach = bdrv_child_cb_detach, .inactivate = bdrv_child_cb_inactivate, }; @@ -XXX,XX +XXX,XX @@ static void bdrv_backing_attach(BdrvChild *c) parent->backing_blocker); bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET, parent->backing_blocker); + + bdrv_child_cb_attach(c); } static void bdrv_backing_detach(BdrvChild *c) @@ -XXX,XX +XXX,XX @@ static void bdrv_backing_detach(BdrvChild *c) bdrv_op_unblock_all(c->bs, parent->backing_blocker); error_free(parent->backing_blocker); parent->backing_blocker = NULL; + + bdrv_child_cb_detach(c); } /* @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)); } if (old_bs) { + /* Detach first so that the recursive drain sections coming from @child + * are already gone and we only end the drain sections that came from + * elsewhere. */ + if (child->role->detach) { + child->role->detach(child); + } if (old_bs->quiesce_counter && child->role->drained_end) { for (i = 0; i < old_bs->quiesce_counter; i++) { child->role->drained_end(child); } } - if (child->role->detach) { - child->role->detach(child); - } QLIST_REMOVE(child, next_parent); } @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, } } + /* Attach only after starting new drained sections, so that recursive + * drain sections coming from @child don't get an extra .drained_begin + * callback. */ if (child->role->attach) { child->role->attach(child); } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, - BdrvChild *parent) +void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { BdrvChild *child, *next; @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, bdrv_drain_recurse(bs); if (recursive) { + bs->recursive_quiesce_counter++; QLIST_FOREACH_SAFE(child, &bs->children, next, next) { bdrv_do_drained_begin(child->bs, true, child); } @@ -XXX,XX +XXX,XX @@ void bdrv_subtree_drained_begin(BlockDriverState *bs) bdrv_do_drained_begin(bs, true, NULL); } -static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, - BdrvChild *parent) +void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { BdrvChild *child, *next; int old_quiesce_counter; @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, } if (recursive) { + bs->recursive_quiesce_counter--; QLIST_FOREACH_SAFE(child, &bs->children, next, next) { bdrv_do_drained_end(child->bs, true, child); } @@ -XXX,XX +XXX,XX @@ void bdrv_subtree_drained_end(BlockDriverState *bs) bdrv_do_drained_end(bs, true, NULL); } +void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent) +{ + int i; + + for (i = 0; i < new_parent->recursive_quiesce_counter; i++) { + bdrv_do_drained_begin(child->bs, true, child); + } +} + +void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent) +{ + int i; + + for (i = 0; i < old_parent->recursive_quiesce_counter; i++) { + bdrv_do_drained_end(child->bs, true, child); + } +} + /* * Wait for pending requests to complete on a single BlockDriverState subtree, * and suspend block driver's internal I/O until next request arrives. -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_multiparent(void) blk_unref(blk_b); } +static void test_graph_change(void) +{ + BlockBackend *blk_a, *blk_b; + BlockDriverState *bs_a, *bs_b, *backing; + BDRVTestState *a_s, *b_s, *backing_s; + + blk_a = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR, + &error_abort); + a_s = bs_a->opaque; + blk_insert_bs(blk_a, bs_a, &error_abort); + + blk_b = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR, + &error_abort); + b_s = bs_b->opaque; + blk_insert_bs(blk_b, bs_b, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs_a, backing, &error_abort); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + + bdrv_set_backing_hd(bs_b, backing, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 5); + g_assert_cmpint(bs_b->quiesce_counter, ==, 5); + g_assert_cmpint(backing->quiesce_counter, ==, 5); + g_assert_cmpint(a_s->drain_count, ==, 5); + g_assert_cmpint(b_s->drain_count, ==, 5); + g_assert_cmpint(backing_s->drain_count, ==, 5); + + bdrv_set_backing_hd(bs_b, NULL, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 3); + g_assert_cmpint(bs_b->quiesce_counter, ==, 2); + g_assert_cmpint(backing->quiesce_counter, ==, 3); + g_assert_cmpint(a_s->drain_count, ==, 3); + g_assert_cmpint(b_s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, 3); + + bdrv_set_backing_hd(bs_b, backing, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 5); + g_assert_cmpint(bs_b->quiesce_counter, ==, 5); + g_assert_cmpint(backing->quiesce_counter, ==, 5); + g_assert_cmpint(a_s->drain_count, ==, 5); + g_assert_cmpint(b_s->drain_count, ==, 5); + g_assert_cmpint(backing_s->drain_count, ==, 5); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs_a); + bdrv_unref(bs_b); + blk_unref(blk_a); + blk_unref(blk_b); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/multiparent", test_multiparent); + g_test_add_func("/bdrv-drain/graph-change", test_graph_change); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 Since commit bde70715, base is the only node that is reopened in commit_start(). This means that the code, which still involves an explicit BlockReopenQueue, can now be simplified by using bdrv_reopen(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/commit.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, const char *filter_node_name, Error **errp) { CommitBlockJob *s; - BlockReopenQueue *reopen_queue = NULL; int orig_base_flags; BlockDriverState *iter; BlockDriverState *commit_top_bs = NULL; @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, /* convert base to r/w, if necessary */ orig_base_flags = bdrv_get_flags(base); if (!(orig_base_flags & BDRV_O_RDWR)) { - reopen_queue = bdrv_reopen_queue(reopen_queue, base, NULL, - orig_base_flags | BDRV_O_RDWR); - } - - if (reopen_queue) { - bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err); + bdrv_reopen(base, orig_base_flags | BDRV_O_RDWR, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); goto fail; -- 2.13.6 The bdrv_reopen*() implementation doesn't like it if the graph is changed between queuing nodes for reopen and actually reopening them (one of the reasons is that queuing can be recursive). So instead of draining the device only in bdrv_reopen_multiple(), require that callers already drained all affected nodes, and assert this in bdrv_reopen_queue(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block.c | 23 ++++++++++++++++------- block/replication.c | 6 ++++++ qemu-io-cmds.c | 3 +++ 3 files changed, 25 insertions(+), 7 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_open(const char *filename, const char *reference, * returns a pointer to bs_queue, which is either the newly allocated * bs_queue, or the existing bs_queue being used. * + * bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple(). */ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, BdrvChild *child; QDict *old_options, *explicit_options; + /* Make sure that the caller remembered to use a drained section. This is + * important to avoid graph changes between the recursive queuing here and + * bdrv_reopen_multiple(). */ + assert(bs->quiesce_counter > 0); + if (bs_queue == NULL) { bs_queue = g_new0(BlockReopenQueue, 1); QSIMPLEQ_INIT(bs_queue); @@ -XXX,XX +XXX,XX @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, * If all devices prepare successfully, then the changes are committed * to all devices. * + * All affected nodes must be drained between bdrv_reopen_queue() and + * bdrv_reopen_multiple(). */ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **errp) { @@ -XXX,XX +XXX,XX @@ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **er assert(bs_queue != NULL); - aio_context_release(ctx); - bdrv_drain_all_begin(); - aio_context_acquire(ctx); - QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) { + assert(bs_entry->state.bs->quiesce_counter > 0); if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, &local_err)) { error_propagate(errp, local_err); goto cleanup; @@ -XXX,XX +XXX,XX @@ cleanup: } g_free(bs_queue); - bdrv_drain_all_end(); - return ret; } @@ -XXX,XX +XXX,XX @@ int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp) { int ret = -1; Error *local_err = NULL; - BlockReopenQueue *queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags); + BlockReopenQueue *queue; + bdrv_subtree_drained_begin(bs); + + queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags); ret = bdrv_reopen_multiple(bdrv_get_aio_context(bs), queue, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); } + + bdrv_subtree_drained_end(bs); + return ret; } diff --git a/block/replication.c b/block/replication.c index XXXXXXX..XXXXXXX 100644 --- a/block/replication.c +++ b/block/replication.c @@ -XXX,XX +XXX,XX @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, new_secondary_flags = s->orig_secondary_flags; } + bdrv_subtree_drained_begin(s->hidden_disk->bs); + bdrv_subtree_drained_begin(s->secondary_disk->bs); + if (orig_hidden_flags != new_hidden_flags) { reopen_queue = bdrv_reopen_queue(reopen_queue, s->hidden_disk->bs, NULL, new_hidden_flags); @@ -XXX,XX +XXX,XX @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, reopen_queue, &local_err); error_propagate(errp, local_err); } + + bdrv_subtree_drained_end(s->hidden_disk->bs); + bdrv_subtree_drained_end(s->secondary_disk->bs); } static void backup_job_cleanup(BlockDriverState *bs) diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int reopen_f(BlockBackend *blk, int argc, char **argv) opts = qopts ? qemu_opts_to_qdict(qopts, NULL) : NULL; qemu_opts_reset(&reopen_opts); + bdrv_subtree_drained_begin(bs); brq = bdrv_reopen_queue(NULL, bs, opts, flags); bdrv_reopen_multiple(bdrv_get_aio_context(bs), brq, &local_err); + bdrv_subtree_drained_end(bs); + if (local_err) { error_report_err(local_err); } else { -- 2.13.6