The following changes since commit f17783e706ab9c7b3a2b69cf48e4f0ba40664f54: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20191220' into staging (2020-01-03 18:50:33 +0000) are available in the Git repository at: https://github.com/XanClic/qemu.git tags/pull-block-2020-01-06 for you to fetch changes up to 503ca1262bab2c11c533a4816d1ff4297d4f58a6: backup-top: Begin drain earlier (2020-01-06 14:26:23 +0100) ---------------------------------------------------------------- Block patches: - Minor fixes and tests from the freeze period (too minor to be included in 4.2) - Allow many bash iotests to test qcow2's external data file feature - Add compress filter driver - Fix Python iotests after 6f6e1698a6 - Fix for the backup job ---------------------------------------------------------------- Andrey Shinkevich (3): block: introduce compress filter driver qcow2: Allow writing compressed data of multiple clusters tests/qemu-iotests: add case to write compressed data of multiple clusters Max Reitz (28): block: Add bdrv_qapi_perm_to_blk_perm() block: Use bdrv_qapi_perm_to_blk_perm() blkdebug: Allow taking/unsharing permissions iotests: Add @error to wait_until_completed iotests: Add test for failing mirror complete iotests: s/qocw2/qcow2/ iotests/qcow2.py: Add dump-header-exts iotests/qcow2.py: Split feature fields into bits iotests: Add _filter_json_filename iotests: Filter refcount_order in 036 iotests: Replace IMGOPTS by _unsupported_imgopts iotests: Drop compat=1.1 in 050 iotests: Let _make_test_img parse its parameters iotests: Add -o and --no-opts to _make_test_img iotests: Inject space into -ocompat=0.10 in 051 iotests: Replace IMGOPTS= by -o iotests: Replace IMGOPTS='' by --no-opts iotests: Drop IMGOPTS use in 267 iotests: Avoid qemu-img create iotests: Use _rm_test_img for deleting test images iotests: Avoid cp/mv of test images iotests: Make 091 work with data_file iotests: Make 110 work with data_file iotests: Make 137 work with data_file iotests: Make 198 work with data_file iotests: Disable data_file where it cannot be used iotests: Allow check -o data_file backup-top: Begin drain earlier PanNengyuan (1): throttle-groups: fix memory leak in throttle_group_set_limit: Philippe Mathieu-Daudé (1): tests/qemu-iotests: Update tests to recent desugarized -accel option Vladimir Sementsov-Ogievskiy (1): qcow2-bitmaps: fix qcow2_can_store_new_dirty_bitmap block.c | 47 +++++---- block/Makefile.objs | 1 + block/backup-top.c | 4 +- block/blkdebug.c | 93 ++++++++++++++++- block/filter-compress.c | 168 +++++++++++++++++++++++++++++++ block/qcow2-bitmap.c | 41 ++++---- block/qcow2.c | 102 ++++++++++++++----- block/throttle-groups.c | 4 +- include/block/block.h | 1 + qapi/block-core.json | 24 ++++- tests/qemu-iotests/007 | 5 +- tests/qemu-iotests/014 | 2 + tests/qemu-iotests/015 | 5 +- tests/qemu-iotests/019 | 6 +- tests/qemu-iotests/020 | 6 +- tests/qemu-iotests/024 | 10 +- tests/qemu-iotests/026 | 5 +- tests/qemu-iotests/028 | 2 +- tests/qemu-iotests/029 | 7 +- tests/qemu-iotests/031 | 9 +- tests/qemu-iotests/031.out | 36 +++---- tests/qemu-iotests/036 | 15 +-- tests/qemu-iotests/036.out | 66 ++---------- tests/qemu-iotests/039 | 27 ++--- tests/qemu-iotests/039.out | 22 ++-- tests/qemu-iotests/041 | 44 ++++++++ tests/qemu-iotests/041.out | 4 +- tests/qemu-iotests/043 | 4 +- tests/qemu-iotests/046 | 2 + tests/qemu-iotests/048 | 4 +- tests/qemu-iotests/050 | 8 +- tests/qemu-iotests/051 | 7 +- tests/qemu-iotests/053 | 4 +- tests/qemu-iotests/058 | 7 +- tests/qemu-iotests/059 | 20 ++-- tests/qemu-iotests/060 | 14 +-- tests/qemu-iotests/060.out | 20 ++-- tests/qemu-iotests/061 | 63 ++++++------ tests/qemu-iotests/061.out | 72 ++++++------- tests/qemu-iotests/062 | 5 +- tests/qemu-iotests/063 | 18 ++-- tests/qemu-iotests/063.out | 3 +- tests/qemu-iotests/066 | 7 +- tests/qemu-iotests/067 | 6 +- tests/qemu-iotests/068 | 6 +- tests/qemu-iotests/069 | 2 +- tests/qemu-iotests/071 | 7 +- tests/qemu-iotests/073 | 4 + tests/qemu-iotests/074 | 4 +- tests/qemu-iotests/079 | 3 +- tests/qemu-iotests/080 | 7 +- tests/qemu-iotests/081 | 6 +- tests/qemu-iotests/085 | 18 ++-- tests/qemu-iotests/085.out | 8 +- tests/qemu-iotests/088 | 2 +- tests/qemu-iotests/090 | 2 + tests/qemu-iotests/091 | 2 +- tests/qemu-iotests/091.out | 2 - tests/qemu-iotests/092 | 2 +- tests/qemu-iotests/094 | 4 +- tests/qemu-iotests/095 | 5 +- tests/qemu-iotests/098 | 6 +- tests/qemu-iotests/099 | 10 +- tests/qemu-iotests/103 | 5 +- tests/qemu-iotests/106 | 2 +- tests/qemu-iotests/108 | 10 +- tests/qemu-iotests/109 | 4 +- tests/qemu-iotests/110 | 11 +- tests/qemu-iotests/110.out | 4 +- tests/qemu-iotests/111 | 3 +- tests/qemu-iotests/112 | 37 +++---- tests/qemu-iotests/114 | 2 + tests/qemu-iotests/115 | 3 +- tests/qemu-iotests/121 | 9 +- tests/qemu-iotests/122 | 6 +- tests/qemu-iotests/123 | 4 +- tests/qemu-iotests/125 | 2 +- tests/qemu-iotests/137 | 17 +++- tests/qemu-iotests/137.out | 6 +- tests/qemu-iotests/138 | 8 +- tests/qemu-iotests/141 | 4 +- tests/qemu-iotests/142 | 2 +- tests/qemu-iotests/144 | 4 +- tests/qemu-iotests/153 | 12 +-- tests/qemu-iotests/156 | 10 +- tests/qemu-iotests/159 | 2 +- tests/qemu-iotests/160 | 3 +- tests/qemu-iotests/161 | 4 +- tests/qemu-iotests/170 | 2 +- tests/qemu-iotests/172 | 6 +- tests/qemu-iotests/173 | 3 +- tests/qemu-iotests/174 | 2 +- tests/qemu-iotests/175 | 2 +- tests/qemu-iotests/176 | 7 +- tests/qemu-iotests/178 | 6 +- tests/qemu-iotests/182 | 2 +- tests/qemu-iotests/183 | 2 +- tests/qemu-iotests/185 | 4 +- tests/qemu-iotests/187 | 6 +- tests/qemu-iotests/190 | 4 +- tests/qemu-iotests/191 | 11 +- tests/qemu-iotests/195 | 2 +- tests/qemu-iotests/197 | 6 +- tests/qemu-iotests/198 | 6 +- tests/qemu-iotests/198.out | 4 +- tests/qemu-iotests/200 | 7 +- tests/qemu-iotests/201 | 6 +- tests/qemu-iotests/214 | 46 ++++++++- tests/qemu-iotests/214.out | 14 +++ tests/qemu-iotests/215 | 6 +- tests/qemu-iotests/217 | 3 +- tests/qemu-iotests/220 | 5 +- tests/qemu-iotests/225 | 2 +- tests/qemu-iotests/229 | 3 +- tests/qemu-iotests/232 | 4 +- tests/qemu-iotests/235 | 2 +- tests/qemu-iotests/243 | 10 +- tests/qemu-iotests/244 | 15 +-- tests/qemu-iotests/247 | 4 +- tests/qemu-iotests/249 | 4 +- tests/qemu-iotests/250 | 5 +- tests/qemu-iotests/252 | 2 +- tests/qemu-iotests/261 | 5 +- tests/qemu-iotests/265 | 2 +- tests/qemu-iotests/267 | 17 ++-- tests/qemu-iotests/273 | 3 + tests/qemu-iotests/check | 6 +- tests/qemu-iotests/common.filter | 47 ++++++++- tests/qemu-iotests/common.rc | 63 ++++++++++-- tests/qemu-iotests/iotests.py | 18 ++-- tests/qemu-iotests/qcow2.py | 23 ++++- 131 files changed, 1139 insertions(+), 552 deletions(-) create mode 100644 block/filter-compress.c -- 2.24.1 We need some way to correlate QAPI BlockPermission values with BLK_PERM_* flags. We could: (1) have the same order in the QAPI definition as the the BLK_PERM_* flags are in LSb-first order. However, then there is no guarantee that they actually match (e.g. when someone modifies the QAPI schema without thinking of the BLK_PERM_* definitions). We could add static assertions, but these would break what’s good about this solution, namely its simplicity. (2) define the BLK_PERM_* flags based on the BlockPermission values. But this way whenever someone were to modify the QAPI order (perfectly sensible in theory), the BLK_PERM_* values would change. Because these values are used for file locking, this might break file locking between different qemu versions. Therefore, go the slightly more cumbersome way: Add a function to translate from the QAPI constants to the BLK_PERM_* flags. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20191108123455.39445-2-mreitz@redhat.com Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 18 ++++++++++++++++++ include/block/block.h | 1 + 2 files changed, 19 insertions(+) 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, *nshared = shared; } +uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm) +{ + static const uint64_t permissions[] = { + [BLOCK_PERMISSION_CONSISTENT_READ] = BLK_PERM_CONSISTENT_READ, + [BLOCK_PERMISSION_WRITE] = BLK_PERM_WRITE, + [BLOCK_PERMISSION_WRITE_UNCHANGED] = BLK_PERM_WRITE_UNCHANGED, + [BLOCK_PERMISSION_RESIZE] = BLK_PERM_RESIZE, + [BLOCK_PERMISSION_GRAPH_MOD] = BLK_PERM_GRAPH_MOD, + }; + + QEMU_BUILD_BUG_ON(ARRAY_SIZE(permissions) != BLOCK_PERMISSION__MAX); + QEMU_BUILD_BUG_ON(1UL << ARRAY_SIZE(permissions) != BLK_PERM_ALL + 1); + + assert(qapi_perm < BLOCK_PERMISSION__MAX); + + return permissions[qapi_perm]; +} + static void bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs) { 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 @@ enum { }; char *bdrv_perm_names(uint64_t perm); +uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm); /* disk I/O throttling */ void bdrv_init(void); -- 2.24.1 We can save some LoC in xdbg_graph_add_edge() by using bdrv_qapi_perm_to_blk_perm(). Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20191108123455.39445-3-mreitz@redhat.com Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 29 ++++++++--------------------- 1 file changed, 8 insertions(+), 21 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void xdbg_graph_add_node(XDbgBlockGraphConstructor *gr, void *node, static void xdbg_graph_add_edge(XDbgBlockGraphConstructor *gr, void *parent, const BdrvChild *child) { - typedef struct { - unsigned int flag; - BlockPermission num; - } PermissionMap; - - static const PermissionMap permissions[] = { - { BLK_PERM_CONSISTENT_READ, BLOCK_PERMISSION_CONSISTENT_READ }, - { BLK_PERM_WRITE, BLOCK_PERMISSION_WRITE }, - { BLK_PERM_WRITE_UNCHANGED, BLOCK_PERMISSION_WRITE_UNCHANGED }, - { BLK_PERM_RESIZE, BLOCK_PERMISSION_RESIZE }, - { BLK_PERM_GRAPH_MOD, BLOCK_PERMISSION_GRAPH_MOD }, - { 0, 0 } - }; - const PermissionMap *p; + BlockPermission qapi_perm; XDbgBlockGraphEdge *edge; - QEMU_BUILD_BUG_ON(1UL << (ARRAY_SIZE(permissions) - 1) != BLK_PERM_ALL + 1); - edge = g_new0(XDbgBlockGraphEdge, 1); edge->parent = xdbg_graph_node_num(gr, parent); edge->child = xdbg_graph_node_num(gr, child->bs); edge->name = g_strdup(child->name); - for (p = permissions; p->flag; p++) { - if (p->flag & child->perm) { - QAPI_LIST_ADD(edge->perm, p->num); + for (qapi_perm = 0; qapi_perm < BLOCK_PERMISSION__MAX; qapi_perm++) { + uint64_t flag = bdrv_qapi_perm_to_blk_perm(qapi_perm); + + if (flag & child->perm) { + QAPI_LIST_ADD(edge->perm, qapi_perm); } - if (p->flag & child->shared_perm) { - QAPI_LIST_ADD(edge->shared_perm, p->num); + if (flag & child->shared_perm) { + QAPI_LIST_ADD(edge->shared_perm, qapi_perm); } } -- 2.24.1 Sometimes it is useful to be able to add a node to the block graph that takes or unshare a certain set of permissions for debugging purposes. This patch adds this capability to blkdebug. (Note that you cannot make blkdebug release or share permissions that it needs to take or cannot share, because this might result in assertion failures in the block layer. But if the blkdebug node has no parents, it will not take any permissions and share everything by default, so you can then freely choose what permissions to take and share.) Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20191108123455.39445-4-mreitz@redhat.com Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/blkdebug.c | 93 +++++++++++++++++++++++++++++++++++++++++++- qapi/block-core.json | 14 ++++++- 2 files changed, 105 insertions(+), 2 deletions(-) diff --git a/block/blkdebug.c b/block/blkdebug.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -XXX,XX +XXX,XX @@ #include "qemu/cutils.h" #include "qemu/config-file.h" #include "block/block_int.h" +#include "block/qdict.h" #include "qemu/module.h" #include "qemu/option.h" +#include "qapi/qapi-visit-block-core.h" #include "qapi/qmp/qdict.h" +#include "qapi/qmp/qlist.h" #include "qapi/qmp/qstring.h" +#include "qapi/qobject-input-visitor.h" #include "sysemu/qtest.h" typedef struct BDRVBlkdebugState { @@ -XXX,XX +XXX,XX @@ typedef struct BDRVBlkdebugState { uint64_t opt_discard; uint64_t max_discard; + uint64_t take_child_perms; + uint64_t unshare_child_perms; + /* For blkdebug_refresh_filename() */ char *config_file; @@ -XXX,XX +XXX,XX @@ static void blkdebug_parse_filename(const char *filename, QDict *options, qdict_put_str(options, "x-image", filename); } +static int blkdebug_parse_perm_list(uint64_t *dest, QDict *options, + const char *prefix, Error **errp) +{ + int ret = 0; + QDict *subqdict = NULL; + QObject *crumpled_subqdict = NULL; + Visitor *v = NULL; + BlockPermissionList *perm_list = NULL, *element; + Error *local_err = NULL; + + *dest = 0; + + qdict_extract_subqdict(options, &subqdict, prefix); + if (!qdict_size(subqdict)) { + goto out; + } + + crumpled_subqdict = qdict_crumple(subqdict, errp); + if (!crumpled_subqdict) { + ret = -EINVAL; + goto out; + } + + v = qobject_input_visitor_new(crumpled_subqdict); + visit_type_BlockPermissionList(v, NULL, &perm_list, &local_err); + if (local_err) { + error_propagate(errp, local_err); + ret = -EINVAL; + goto out; + } + + for (element = perm_list; element; element = element->next) { + *dest |= bdrv_qapi_perm_to_blk_perm(element->value); + } + +out: + qapi_free_BlockPermissionList(perm_list); + visit_free(v); + qobject_unref(subqdict); + qobject_unref(crumpled_subqdict); + return ret; +} + +static int blkdebug_parse_perms(BDRVBlkdebugState *s, QDict *options, + Error **errp) +{ + int ret; + + ret = blkdebug_parse_perm_list(&s->take_child_perms, options, + "take-child-perms.", errp); + if (ret < 0) { + return ret; + } + + ret = blkdebug_parse_perm_list(&s->unshare_child_perms, options, + "unshare-child-perms.", errp); + if (ret < 0) { + return ret; + } + + return 0; +} + static QemuOptsList runtime_opts = { .name = "blkdebug", .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head), @@ -XXX,XX +XXX,XX @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags, /* Set initial state */ s->state = 1; + /* Parse permissions modifiers before opening the image file */ + ret = blkdebug_parse_perms(s, options, errp); + if (ret < 0) { + goto out; + } + /* Open the image file */ bs->file = bdrv_open_child(qemu_opt_get(opts, "x-image"), options, "image", bs, &child_file, false, &local_err); @@ -XXX,XX +XXX,XX @@ static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state, return 0; } +static void blkdebug_child_perm(BlockDriverState *bs, BdrvChild *c, + const BdrvChildRole *role, + BlockReopenQueue *reopen_queue, + uint64_t perm, uint64_t shared, + uint64_t *nperm, uint64_t *nshared) +{ + BDRVBlkdebugState *s = bs->opaque; + + bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared, + nperm, nshared); + + *nperm |= s->take_child_perms; + *nshared &= ~s->unshare_child_perms; +} + static const char *const blkdebug_strong_runtime_opts[] = { "config", "inject-error.", @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_blkdebug = { .bdrv_file_open = blkdebug_open, .bdrv_close = blkdebug_close, .bdrv_reopen_prepare = blkdebug_reopen_prepare, - .bdrv_child_perm = bdrv_filter_default_perms, + .bdrv_child_perm = blkdebug_child_perm, .bdrv_getlength = blkdebug_getlength, .bdrv_refresh_filename = blkdebug_refresh_filename, 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 @@ # # @set-state: array of state-change descriptions # +# @take-child-perms: Permissions to take on @image in addition to what +# is necessary anyway (which depends on how the +# blkdebug node is used). Defaults to none. +# (since 5.0) +# +# @unshare-child-perms: Permissions not to share on @image in addition +# to what cannot be shared anyway (which depends +# on how the blkdebug node is used). Defaults +# to none. (since 5.0) +# # Since: 2.9 ## { 'struct': 'BlockdevOptionsBlkdebug', @@ -XXX,XX +XXX,XX @@ '*opt-write-zero': 'int32', '*max-write-zero': 'int32', '*opt-discard': 'int32', '*max-discard': 'int32', '*inject-error': ['BlkdebugInjectErrorOptions'], - '*set-state': ['BlkdebugSetStateOptions'] } } + '*set-state': ['BlkdebugSetStateOptions'], + '*take-child-perms': ['BlockPermission'], + '*unshare-child-perms': ['BlockPermission'] } } ## # @BlockdevOptionsBlklogwrites: -- 2.24.1 Callers can use this new parameter to expect failure during the completion process. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20191108123455.39445-5-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ class QMPTestCase(unittest.TestCase): self.assert_no_active_block_jobs() return result - def wait_until_completed(self, drive='drive0', check_offset=True, wait=60.0): + def wait_until_completed(self, drive='drive0', check_offset=True, wait=60.0, + error=None): '''Wait for a block job to finish, returning the event''' while True: for event in self.vm.get_qmp_events(wait=wait): if event['event'] == 'BLOCK_JOB_COMPLETED': self.assert_qmp(event, 'data/device', drive) - self.assert_qmp_absent(event, 'data/error') - if check_offset: - self.assert_qmp(event, 'data/offset', event['data']['len']) + if error is None: + self.assert_qmp_absent(event, 'data/error') + if check_offset: + self.assert_qmp(event, 'data/offset', + event['data']['len']) + else: + self.assert_qmp(event, 'data/error', error) self.assert_no_active_block_jobs() return event elif event['event'] == 'JOB_STATUS_CHANGE': @@ -XXX,XX +XXX,XX @@ class QMPTestCase(unittest.TestCase): self.assert_qmp(event, 'data/type', 'mirror') self.assert_qmp(event, 'data/offset', event['data']['len']) - def complete_and_wait(self, drive='drive0', wait_ready=True): + def complete_and_wait(self, drive='drive0', wait_ready=True, + completion_error=None): '''Complete a block job and wait for it to finish''' if wait_ready: self.wait_ready(drive=drive) @@ -XXX,XX +XXX,XX @@ class QMPTestCase(unittest.TestCase): result = self.vm.qmp('block-job-complete', device=drive) self.assert_qmp(result, 'return', {}) - event = self.wait_until_completed(drive=drive) + event = self.wait_until_completed(drive=drive, error=completion_error) self.assert_qmp(event, 'data/type', 'mirror') def pause_wait(self, job_id='job0'): -- 2.24.1 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Tested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: John Snow <jsnow@redhat.com> Message-id: 20191108123455.39445-6-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/041 | 44 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/041.out | 4 ++-- 2 files changed, 46 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -XXX,XX +XXX,XX @@ class TestOrphanedSource(iotests.QMPTestCase): target='dest-ro') self.assert_qmp(result, 'error/class', 'GenericError') + def test_failing_permission_in_complete(self): + self.assert_no_active_block_jobs() + + # Unshare consistent-read on the target + # (The mirror job does not care) + result = self.vm.qmp('blockdev-add', + driver='blkdebug', + node_name='dest-perm', + image='dest', + unshare_child_perms=['consistent-read']) + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('blockdev-mirror', job_id='job', device='src', + sync='full', target='dest', + filter_node_name='mirror-filter') + self.assert_qmp(result, 'return', {}) + + # Require consistent-read on the source + # (We can only add this node once the job has started, or it + # will complain that it does not want to run on non-root nodes) + result = self.vm.qmp('blockdev-add', + driver='blkdebug', + node_name='src-perm', + image='src', + take_child_perms=['consistent-read']) + self.assert_qmp(result, 'return', {}) + + # While completing, mirror will attempt to replace src by + # dest, which must fail because src-perm requires + # consistent-read but dest-perm does not share it; thus + # aborting the job when it is supposed to complete + self.complete_and_wait('job', + completion_error='Operation not permitted') + + # Assert that all of our nodes are still there (except for the + # mirror filter, which should be gone despite the failure) + nodes = self.vm.qmp('query-named-block-nodes')['return'] + nodes = [node['node-name'] for node in nodes] + + for expect in ('src', 'src-perm', 'dest', 'dest-perm'): + self.assertTrue(expect in nodes, '%s disappeared' % expect) + self.assertFalse('mirror-filter' in nodes, + 'Mirror filter node did not disappear') + if __name__ == '__main__': iotests.main(supported_fmts=['qcow2', 'qed'], supported_protocols=['file']) diff --git a/tests/qemu-iotests/041.out b/tests/qemu-iotests/041.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/041.out +++ b/tests/qemu-iotests/041.out @@ -XXX,XX +XXX,XX @@ -.......................................................................................... +........................................................................................... ---------------------------------------------------------------------- -Ran 90 tests +Ran 91 tests OK -- 2.24.1 From: PanNengyuan <pannengyuan@huawei.com> This avoid a memory leak when qom-set is called to set throttle_group limits, here is an easy way to reproduce: 1. run qemu-iotests as follow and check the result with asan: ./check -qcow2 184 Following is the asan output backtrack: Direct leak of 912 byte(s) in 3 object(s) allocated from: #0 0xffff8d7ab3c3 in __interceptor_calloc (/lib64/libasan.so.4+0xd33c3) #1 0xffff8d4c31cb in g_malloc0 (/lib64/libglib-2.0.so.0+0x571cb) #2 0x190c857 in qobject_input_start_struct /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qapi/qobject-input-visitor.c:295 #3 0x19070df in visit_start_struct /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qapi/qapi-visit-core.c:49 #4 0x1948b87 in visit_type_ThrottleLimits qapi/qapi-visit-block-core.c:3759 #5 0x17e4aa3 in throttle_group_set_limits /mnt/sdc/qemu-master/qemu-4.2.0-rc0/block/throttle-groups.c:900 #6 0x1650eff in object_property_set /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qom/object.c:1272 #7 0x1658517 in object_property_set_qobject /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qom/qom-qobject.c:26 #8 0x15880bb in qmp_qom_set /mnt/sdc/qemu-master/qemu-4.2.0-rc0/qom/qom-qmp-cmds.c:74 #9 0x157e3e3 in qmp_marshal_qom_set qapi/qapi-commands-qom.c:154 Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: PanNengyuan <pannengyuan@huawei.com> Message-id: 1574835614-42028-1-git-send-email-pannengyuan@huawei.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/throttle-groups.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/throttle-groups.c b/block/throttle-groups.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle-groups.c +++ b/block/throttle-groups.c @@ -XXX,XX +XXX,XX @@ static void throttle_group_set_limits(Object *obj, Visitor *v, { ThrottleGroup *tg = THROTTLE_GROUP(obj); ThrottleConfig cfg; - ThrottleLimits arg = { 0 }; - ThrottleLimits *argp = &arg; + ThrottleLimits *argp; Error *local_err = NULL; visit_type_ThrottleLimits(v, name, &argp, &local_err); @@ -XXX,XX +XXX,XX @@ static void throttle_group_set_limits(Object *obj, Visitor *v, unlock: qemu_mutex_unlock(&tg->lock); ret: + qapi_free_ThrottleLimits(argp); error_propagate(errp, local_err); return; } -- 2.24.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> qcow2_can_store_new_dirty_bitmap works wrong, as it considers only bitmaps already stored in the qcow2 image and ignores persistent BdrvDirtyBitmap objects. So, let's instead count persistent BdrvDirtyBitmaps. We load all qcow2 bitmaps on open, so there should not be any bitmap in the image for which we don't have BdrvDirtyBitmaps version. If it is - it's a kind of corruption, and no reason to check for corruptions here (open() and close() are better places for it). Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20191014115126.15360-2-vsementsov@virtuozzo.com Reviewed-by: Max Reitz <mreitz@redhat.com> Cc: qemu-stable@nongnu.org Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2-bitmap.c | 41 ++++++++++++++++++----------------------- 1 file changed, 18 insertions(+), 23 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 @@ bool coroutine_fn qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs, Error **errp) { BDRVQcow2State *s = bs->opaque; - bool found; - Qcow2BitmapList *bm_list; + BdrvDirtyBitmap *bitmap; + uint64_t bitmap_directory_size = 0; + uint32_t nb_bitmaps = 0; + + if (bdrv_find_dirty_bitmap(bs, name)) { + error_setg(errp, "Bitmap already exists: %s", name); + return false; + } if (s->qcow_version < 3) { /* Without autoclear_features, we would always have to assume @@ -XXX,XX +XXX,XX @@ bool coroutine_fn qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs, goto fail; } - if (s->nb_bitmaps == 0) { - return true; + FOR_EACH_DIRTY_BITMAP(bs, bitmap) { + if (bdrv_dirty_bitmap_get_persistence(bitmap)) { + nb_bitmaps++; + bitmap_directory_size += + calc_dir_entry_size(strlen(bdrv_dirty_bitmap_name(bitmap)), 0); + } } + nb_bitmaps++; + bitmap_directory_size += calc_dir_entry_size(strlen(name), 0); - if (s->nb_bitmaps >= QCOW2_MAX_BITMAPS) { + if (nb_bitmaps > QCOW2_MAX_BITMAPS) { error_setg(errp, "Maximum number of persistent bitmaps is already reached"); goto fail; } - if (s->bitmap_directory_size + calc_dir_entry_size(strlen(name), 0) > - QCOW2_MAX_BITMAP_DIRECTORY_SIZE) - { + if (bitmap_directory_size > QCOW2_MAX_BITMAP_DIRECTORY_SIZE) { error_setg(errp, "Not enough space in the bitmap directory"); goto fail; } - qemu_co_mutex_lock(&s->lock); - bm_list = bitmap_list_load(bs, s->bitmap_directory_offset, - s->bitmap_directory_size, errp); - qemu_co_mutex_unlock(&s->lock); - if (bm_list == NULL) { - goto fail; - } - - found = find_bitmap_by_name(bm_list, name); - bitmap_list_free(bm_list); - if (found) { - error_setg(errp, "Bitmap with the same name is already stored"); - goto fail; - } - return true; fail: -- 2.24.1 Probably due to blind copy-pasting, we have several instances of "qocw2" in our iotests. Fix them. Reported-by: Maxim Levitsky <mlevitsk@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20191107163708.833192-2-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/060 | 2 +- tests/qemu-iotests/061 | 2 +- tests/qemu-iotests/062 | 2 +- tests/qemu-iotests/066 | 2 +- tests/qemu-iotests/068 | 2 +- tests/qemu-iotests/108 | 2 +- tests/qemu-iotests/138 | 2 +- tests/qemu-iotests/261 | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ _filter_io_error() . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file _supported_os Linux diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/061 +++ b/tests/qemu-iotests/061 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file _supported_os Linux diff --git a/tests/qemu-iotests/062 b/tests/qemu-iotests/062 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/062 +++ b/tests/qemu-iotests/062 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto generic diff --git a/tests/qemu-iotests/066 b/tests/qemu-iotests/066 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/066 +++ b/tests/qemu-iotests/066 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto generic diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/068 +++ b/tests/qemu-iotests/068 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto generic diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/108 +++ b/tests/qemu-iotests/108 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file _supported_os Linux diff --git a/tests/qemu-iotests/138 b/tests/qemu-iotests/138 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/138 +++ b/tests/qemu-iotests/138 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file _supported_os Linux diff --git a/tests/qemu-iotests/261 b/tests/qemu-iotests/261 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/261 +++ b/tests/qemu-iotests/261 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.rc . ./common.filter -# This tests qocw2-specific low-level functionality +# This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file _supported_os Linux -- 2.24.1 This is useful for tests that want to whitelist fields from dump-header (with grep) but still print all header extensions. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-3-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/qcow2.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tests/qemu-iotests/qcow2.py b/tests/qemu-iotests/qcow2.py index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/qcow2.py +++ b/tests/qemu-iotests/qcow2.py @@ -XXX,XX +XXX,XX @@ def cmd_dump_header(fd): h.dump() h.dump_extensions() +def cmd_dump_header_exts(fd): + h = QcowHeader(fd) + h.dump_extensions() + def cmd_set_header(fd, name, value): try: value = int(value, 0) @@ -XXX,XX +XXX,XX @@ def cmd_set_feature_bit(fd, group, bit): cmds = [ [ 'dump-header', cmd_dump_header, 0, 'Dump image header and header extensions' ], + [ 'dump-header-exts', cmd_dump_header_exts, 0, 'Dump image header extensions' ], [ 'set-header', cmd_set_header, 2, 'Set a field in the header'], [ 'add-header-ext', cmd_add_header_ext, 2, 'Add a header extension' ], [ 'add-header-ext-stdio', cmd_add_header_ext_stdio, 1, 'Add a header extension, data from stdin' ], -- 2.24.1 Print the feature fields as a set of bits so that filtering is easier. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-4-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/031.out | 36 +++++++++---------- tests/qemu-iotests/036.out | 18 +++++----- tests/qemu-iotests/039.out | 22 ++++++------ tests/qemu-iotests/060.out | 20 +++++------ tests/qemu-iotests/061.out | 72 ++++++++++++++++++------------------- tests/qemu-iotests/137.out | 2 +- tests/qemu-iotests/qcow2.py | 18 +++++++--- 7 files changed, 99 insertions(+), 89 deletions(-) diff --git a/tests/qemu-iotests/031.out b/tests/qemu-iotests/031.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/031.out +++ b/tests/qemu-iotests/031.out @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 104 diff --git a/tests/qemu-iotests/036.out b/tests/qemu-iotests/036.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/036.out +++ b/tests/qemu-iotests/036.out @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x8000000000000000 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [63] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x8000000000000000 +incompatible_features [] +compatible_features [] +autoclear_features [63] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 104 diff --git a/tests/qemu-iotests/039.out b/tests/qemu-iotests/039.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/039.out +++ b/tests/qemu-iotests/039.out @@ -XXX,XX +XXX,XX @@ QA output created by 039 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -incompatible_features 0x0 +incompatible_features [] No errors were found on the image. == Creating a dirty image file == @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ./common.rc: Killed ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" ) -incompatible_features 0x1 +incompatible_features [0] ERROR cluster 5 refcount=0 reference=1 ERROR OFLAG_COPIED data cluster: l2_entry=8000000000050000 refcount=0 @@ -XXX,XX +XXX,XX @@ Data may be corrupted, or further writes to the image may corrupt it. == Read-only access must still work == read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -incompatible_features 0x1 +incompatible_features [0] == Repairing the image file must succeed == ERROR cluster 5 refcount=0 reference=1 @@ -XXX,XX +XXX,XX @@ The following inconsistencies were found and repaired: Double checking the fixed image now... No errors were found on the image. -incompatible_features 0x0 +incompatible_features [] == Data should still be accessible after repair == read 512/512 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ./common.rc: Killed ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" ) -incompatible_features 0x1 +incompatible_features [0] ERROR cluster 5 refcount=0 reference=1 Rebuilding refcount structure Repairing cluster 1 refcount=1 reference=0 Repairing cluster 2 refcount=1 reference=0 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -incompatible_features 0x0 +incompatible_features [] == Creating an image file with lazy_refcounts=off == Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ./common.rc: Killed ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" ) -incompatible_features 0x0 +incompatible_features [] No errors were found on the image. == Committing to a backing file with lazy_refcounts=on == @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/ wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Image committed. -incompatible_features 0x0 -incompatible_features 0x0 +incompatible_features [] +incompatible_features [] No errors were found on the image. No errors were found on the image. @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ./common.rc: Killed ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" ) -incompatible_features 0x1 +incompatible_features [0] ERROR cluster 5 refcount=0 reference=1 ERROR OFLAG_COPIED data cluster: l2_entry=8000000000050000 refcount=0 @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ./common.rc: Killed ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" ) -incompatible_features 0x0 +incompatible_features [] No errors were found on the image. *** done diff --git a/tests/qemu-iotests/060.out b/tests/qemu-iotests/060.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/060.out +++ b/tests/qemu-iotests/060.out @@ -XXX,XX +XXX,XX @@ ERROR cluster 3 refcount=1 reference=3 1 errors were found on the image. Data may be corrupted, or further writes to the image may corrupt it. -incompatible_features 0x0 +incompatible_features [] qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with active L1 table); further corruption events will be suppressed write failed: Input/output error -incompatible_features 0x2 +incompatible_features [1] image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 64 MiB (67108864 bytes) @@ -XXX,XX +XXX,XX @@ ERROR cluster 2 refcount=1 reference=2 2 errors were found on the image. Data may be corrupted, or further writes to the image may corrupt it. -incompatible_features 0x0 +incompatible_features [] qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with refcount block); further corruption events will be suppressed write failed: Input/output error -incompatible_features 0x2 +incompatible_features [1] ERROR refcount block 0 refcount=2 ERROR cluster 2 refcount=1 reference=2 Rebuilding refcount structure @@ -XXX,XX +XXX,XX @@ The following inconsistencies were found and repaired: Double checking the fixed image now... No errors were found on the image. -incompatible_features 0x0 +incompatible_features [] wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -incompatible_features 0x0 +incompatible_features [] === Testing cluster data reference into inactive L2 table === @@ -XXX,XX +XXX,XX @@ Data may be corrupted, or further writes to the image may corrupt it. 1 leaked clusters were found on the image. This means waste of disk space, but no harm to data. -incompatible_features 0x0 +incompatible_features [] qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with inactive L2 table); further corruption events will be suppressed write failed: Input/output error -incompatible_features 0x2 +incompatible_features [1] ERROR cluster 4 refcount=1 reference=2 Leaked cluster 9 refcount=1 reference=0 Repairing cluster 4 refcount=1 reference=2 @@ -XXX,XX +XXX,XX @@ The following inconsistencies were found and repaired: Double checking the fixed image now... No errors were found on the image. -incompatible_features 0x0 +incompatible_features [] wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -incompatible_features 0x0 +incompatible_features [] read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) No errors were found on the image. diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/061.out +++ b/tests/qemu-iotests/061.out @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x1 -autoclear_features 0x0 +incompatible_features [] +compatible_features [0] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x1 -autoclear_features 0x0 +incompatible_features [] +compatible_features [0] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x1 -compatible_features 0x1 -autoclear_features 0x0 +incompatible_features [0] +compatible_features [0] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x80000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x40000000000 -autoclear_features 0x40000000000 +incompatible_features [] +compatible_features [42] +autoclear_features [42] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 72 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x1 -autoclear_features 0x0 +incompatible_features [] +compatible_features [0] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x10000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x1 -compatible_features 0x1 -autoclear_features 0x0 +incompatible_features [0] +compatible_features [0] +autoclear_features [] refcount_order 4 header_length 104 @@ -XXX,XX +XXX,XX @@ refcount_table_offset 0x80000 refcount_table_clusters 1 nb_snapshots 0 snapshot_offset 0x0 -incompatible_features 0x0 -compatible_features 0x0 -autoclear_features 0x0 +incompatible_features [] +compatible_features [] +autoclear_features [] refcount_order 4 header_length 104 diff --git a/tests/qemu-iotests/137.out b/tests/qemu-iotests/137.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/137.out +++ b/tests/qemu-iotests/137.out @@ -XXX,XX +XXX,XX @@ qemu-io: Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ./common.rc: Killed ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" ) -incompatible_features 0x0 +incompatible_features [] Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 wrote 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) diff --git a/tests/qemu-iotests/qcow2.py b/tests/qemu-iotests/qcow2.py index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/qcow2.py +++ b/tests/qemu-iotests/qcow2.py @@ -XXX,XX +XXX,XX @@ class QcowHeader: [ uint64_t, '%#x', 'snapshot_offset' ], # Version 3 header fields - [ uint64_t, '%#x', 'incompatible_features' ], - [ uint64_t, '%#x', 'compatible_features' ], - [ uint64_t, '%#x', 'autoclear_features' ], + [ uint64_t, 'mask', 'incompatible_features' ], + [ uint64_t, 'mask', 'compatible_features' ], + [ uint64_t, 'mask', 'autoclear_features' ], [ uint32_t, '%d', 'refcount_order' ], [ uint32_t, '%d', 'header_length' ], ]; @@ -XXX,XX +XXX,XX @@ class QcowHeader: def dump(self): for f in QcowHeader.fields: - print("%-25s" % f[2], f[1] % self.__dict__[f[2]]) + value = self.__dict__[f[2]] + if f[1] == 'mask': + bits = [] + for bit in range(64): + if value & (1 << bit): + bits.append(bit) + value_str = str(bits) + else: + value_str = f[1] % value + + print("%-25s" % f[2], value_str) print("") def dump_extensions(self): -- 2.24.1 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-5-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/common.filter | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) 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_qmp_empty_return() grep -v '{"return": {}}' } +_filter_json_filename() +{ + $PYTHON -c 'import sys +result, *fnames = sys.stdin.read().split("json:{") +depth = 0 +for fname in fnames: + depth += 1 # For the opening brace in the split separator + for chr_i, chr in enumerate(fname): + if chr == "{": + depth += 1 + elif chr == "}": + depth -= 1 + if depth == 0: + break + + # json:{} filenames may be nested; filter out everything from + # inside the outermost one + if depth == 0: + chr_i += 1 # First character past the filename + result += "json:{ /* filtered */ }" + fname[chr_i:] + +sys.stdout.write(result)' +} + # make sure this script returns success true -- 2.24.1 This test can run just fine with other values for refcount_bits, so we should filter the value from qcow2.py's dump-header. In fact, we can filter everything but the feature bits and header extensions, because that is what the test is about. (036 currently ignores user-specified image options, but that will be fixed in the next patch.) Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-6-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/036 | 9 ++++--- tests/qemu-iotests/036.out | 48 -------------------------------------- 2 files changed, 6 insertions(+), 51 deletions(-) diff --git a/tests/qemu-iotests/036 b/tests/qemu-iotests/036 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/036 +++ b/tests/qemu-iotests/036 @@ -XXX,XX +XXX,XX @@ $PYTHON qcow2.py "$TEST_IMG" set-feature-bit incompatible 63 # Without feature table $PYTHON qcow2.py "$TEST_IMG" del-header-ext 0x6803f857 -$PYTHON qcow2.py "$TEST_IMG" dump-header +$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features +$PYTHON qcow2.py "$TEST_IMG" dump-header-exts _img_info # With feature table containing bit 63 @@ -XXX,XX +XXX,XX @@ echo === Create image with unknown autoclear feature bit === echo _make_test_img 64M $PYTHON qcow2.py "$TEST_IMG" set-feature-bit autoclear 63 -$PYTHON qcow2.py "$TEST_IMG" dump-header +$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features +$PYTHON qcow2.py "$TEST_IMG" dump-header-exts echo echo === Repair image === echo _check_test_img -r all -$PYTHON qcow2.py "$TEST_IMG" dump-header +$PYTHON qcow2.py "$TEST_IMG" dump-header | grep features +$PYTHON qcow2.py "$TEST_IMG" dump-header-exts # success, all done echo "*** done" diff --git a/tests/qemu-iotests/036.out b/tests/qemu-iotests/036.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/036.out +++ b/tests/qemu-iotests/036.out @@ -XXX,XX +XXX,XX @@ QA output created by 036 === Image with unknown incompatible feature bit === Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 -magic 0x514649fb -version 3 -backing_file_offset 0x0 -backing_file_size 0x0 -cluster_bits 16 -size 67108864 -crypt_method 0 -l1_size 1 -l1_table_offset 0x30000 -refcount_table_offset 0x10000 -refcount_table_clusters 1 -nb_snapshots 0 -snapshot_offset 0x0 incompatible_features [63] compatible_features [] autoclear_features [] -refcount_order 4 -header_length 104 - qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Unsupported IMGFMT feature(s): Unknown incompatible feature: 8000000000000000 qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Unsupported IMGFMT feature(s): Test feature @@ -XXX,XX +XXX,XX @@ qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Unsupported IMGFMT feature(s): tes === Create image with unknown autoclear feature bit === Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 -magic 0x514649fb -version 3 -backing_file_offset 0x0 -backing_file_size 0x0 -cluster_bits 16 -size 67108864 -crypt_method 0 -l1_size 1 -l1_table_offset 0x30000 -refcount_table_offset 0x10000 -refcount_table_clusters 1 -nb_snapshots 0 -snapshot_offset 0x0 incompatible_features [] compatible_features [] autoclear_features [63] -refcount_order 4 -header_length 104 - Header extension: magic 0x6803f857 length 192 @@ -XXX,XX +XXX,XX @@ data <binary> === Repair image === No errors were found on the image. -magic 0x514649fb -version 3 -backing_file_offset 0x0 -backing_file_size 0x0 -cluster_bits 16 -size 67108864 -crypt_method 0 -l1_size 1 -l1_table_offset 0x30000 -refcount_table_offset 0x10000 -refcount_table_clusters 1 -nb_snapshots 0 -snapshot_offset 0x0 incompatible_features [] compatible_features [] autoclear_features [] -refcount_order 4 -header_length 104 - Header extension: magic 0x6803f857 length 192 -- 2.24.1 Some tests require compat=1.1 and thus set IMGOPTS='compat=1.1' globally. That is not how it should be done; instead, they should simply set _unsupported_imgopts to compat=0.10 (compat=1.1 is the default anyway). This makes the tests heed user-specified $IMGOPTS. Some do not work with all image options, though, so we need to disable them accordingly. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsky@redhat.com> Message-id: 20191107163708.833192-7-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/036 | 3 +-- tests/qemu-iotests/060 | 4 ++-- tests/qemu-iotests/062 | 3 ++- tests/qemu-iotests/066 | 3 ++- tests/qemu-iotests/068 | 3 ++- tests/qemu-iotests/098 | 4 ++-- 6 files changed, 11 insertions(+), 9 deletions(-) diff --git a/tests/qemu-iotests/036 b/tests/qemu-iotests/036 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/036 +++ b/tests/qemu-iotests/036 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file - # Only qcow2v3 and later supports feature bits -IMGOPTS="compat=1.1" +_unsupported_imgopts 'compat=0.10' echo echo === Image with unknown incompatible feature bit === diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ _filter_io_error() _supported_fmt qcow2 _supported_proto file _supported_os Linux +# These tests only work for compat=1.1 images with refcount_bits=16 +_unsupported_imgopts 'compat=0.10' 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' # The repair process will create a large file - so check for availability first _require_large_file 64G @@ -XXX,XX +XXX,XX @@ l1_offset=196608 # 0x30000 (XXX: just an assumption) l2_offset=262144 # 0x40000 (XXX: just an assumption) l2_offset_after_snapshot=524288 # 0x80000 (XXX: just an assumption) -IMGOPTS="compat=1.1" - OPEN_RW="open -o overlap-check=all $TEST_IMG" # Overlap checks are done before write operations only, therefore opening an # image read-only makes the overlap-check option irrelevant diff --git a/tests/qemu-iotests/062 b/tests/qemu-iotests/062 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/062 +++ b/tests/qemu-iotests/062 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto generic +# We need zero clusters and snapshots +_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' -IMGOPTS="compat=1.1" IMG_SIZE=64M echo diff --git a/tests/qemu-iotests/066 b/tests/qemu-iotests/066 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/066 +++ b/tests/qemu-iotests/066 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto generic +# We need zero clusters and snapshots +_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' # Intentionally create an unaligned image -IMGOPTS="compat=1.1" IMG_SIZE=$((64 * 1024 * 1024 + 512)) echo diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/068 +++ b/tests/qemu-iotests/068 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto generic +# Internal snapshots are (currently) impossible with refcount_bits=1 +_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' -IMGOPTS="compat=1.1" IMG_SIZE=128K case "$QEMU_DEFAULT_MACHINE" in diff --git a/tests/qemu-iotests/098 b/tests/qemu-iotests/098 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/098 +++ b/tests/qemu-iotests/098 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file - -IMGOPTS="compat=1.1" +# The code path we want to test here only works for compat=1.1 images +_unsupported_imgopts 'compat=0.10' for event in l1_update empty_image_prepare reftable_update refblock_alloc; do -- 2.24.1 IMGOPTS can never be empty for qcow2, because the check scripts adds compat=1.1 unless the user specified any compat option themselves. Thus, this block does not do anything and can be dropped. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-8-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/050 | 4 ---- 1 file changed, 4 deletions(-) diff --git a/tests/qemu-iotests/050 b/tests/qemu-iotests/050 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/050 +++ b/tests/qemu-iotests/050 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 qed _supported_proto file -if test "$IMGFMT" = qcow2 && test $IMGOPTS = ""; then - IMGOPTS=compat=1.1 -fi - echo echo "== Creating images ==" -- 2.24.1 This will allow us to add more options than just -b. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-9-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/common.rc | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _make_test_img() # extra qemu-img options can be added by tests # at least one argument (the image size) needs to be added local extra_img_options="" - local image_size=$* local optstr="" local img_name="" local use_backing=0 local backing_file="" local object_options="" + local misc_params=() if [ -n "$TEST_IMG_FILE" ]; then img_name=$TEST_IMG_FILE @@ -XXX,XX +XXX,XX @@ _make_test_img() optstr=$(_optstr_add "$optstr" "key-secret=keysec0") fi - if [ "$1" = "-b" ]; then - use_backing=1 - backing_file=$2 - image_size=$3 - fi + for param; do + if [ "$use_backing" = "1" -a -z "$backing_file" ]; then + backing_file=$param + continue + fi + + case "$param" in + -b) + use_backing=1 + ;; + + *) + misc_params=("${misc_params[@]}" "$param") + ;; + esac + done + if [ \( "$IMGFMT" = "qcow2" -o "$IMGFMT" = "qed" \) -a -n "$CLUSTER_SIZE" ]; then optstr=$(_optstr_add "$optstr" "cluster_size=$CLUSTER_SIZE") fi @@ -XXX,XX +XXX,XX @@ _make_test_img() # XXX(hch): have global image options? ( if [ $use_backing = 1 ]; then - $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options -b "$backing_file" "$img_name" $image_size 2>&1 + $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options -b "$backing_file" "$img_name" "${misc_params[@]}" 2>&1 else - $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options "$img_name" $image_size 2>&1 + $QEMU_IMG create $object_options -f $IMGFMT $extra_img_options "$img_name" "${misc_params[@]}" 2>&1 fi ) | _filter_img_create -- 2.24.1 Blindly overriding IMGOPTS is suboptimal as this discards user-specified options. Whatever options the test needs should simply be appended. Some tests do this (with IMGOPTS=$(_optstr_add "$IMGOPTS" "...")), but that is cumbersome. It’s simpler to just give _make_test_img an -o parameter with which tests can add options. Some tests actually must override the user-specified options, though, for example when creating an image in a different format than the test $IMGFMT. For such cases, --no-opts allows clearing the current option list. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-10-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/common.rc | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _make_test_img() local use_backing=0 local backing_file="" local object_options="" + local opts_param=false local misc_params=() if [ -n "$TEST_IMG_FILE" ]; then @@ -XXX,XX +XXX,XX @@ _make_test_img() if [ "$use_backing" = "1" -a -z "$backing_file" ]; then backing_file=$param continue + elif $opts_param; then + optstr=$(_optstr_add "$optstr" "$param") + opts_param=false + continue fi case "$param" in @@ -XXX,XX +XXX,XX @@ _make_test_img() use_backing=1 ;; + -o) + opts_param=true + ;; + + --no-opts) + optstr="" + ;; + *) misc_params=("${misc_params[@]}" "$param") ;; -- 2.24.1 It did not matter before, but now that _make_test_img understands -o, we should use it properly here. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-11-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/051 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/051 +++ b/tests/qemu-iotests/051 @@ -XXX,XX +XXX,XX @@ echo echo === With version 2 images enabling lazy refcounts must fail === echo -_make_test_img -ocompat=0.10 $size +_make_test_img -o compat=0.10 $size run_qemu -drive file="$TEST_IMG",format=qcow2,lazy-refcounts=on run_qemu -drive file="$TEST_IMG",format=qcow2,lazy-refcounts=off -- 2.24.1 Tests should not overwrite all user-supplied image options, but only add to it (which will effectively overwrite conflicting values). Accomplish this by passing options to _make_test_img via -o instead of $IMGOPTS. For some tests, there is no functional change because they already only appended options to IMGOPTS. For these, this patch is just a simplification. For others, this is a change, so they now heed user-specified $IMGOPTS. Some of those tests do not work with all image options, though, so we need to disable them accordingly. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-12-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/031 | 9 ++++--- tests/qemu-iotests/039 | 24 ++++++------------ tests/qemu-iotests/059 | 18 ++++++------- tests/qemu-iotests/060 | 6 ++--- tests/qemu-iotests/061 | 57 ++++++++++++++++++++++-------------------- tests/qemu-iotests/079 | 3 +-- tests/qemu-iotests/106 | 2 +- tests/qemu-iotests/108 | 2 +- tests/qemu-iotests/112 | 32 ++++++++++++------------ tests/qemu-iotests/115 | 3 +-- tests/qemu-iotests/121 | 6 ++--- tests/qemu-iotests/125 | 2 +- tests/qemu-iotests/137 | 2 +- tests/qemu-iotests/138 | 3 +-- tests/qemu-iotests/175 | 2 +- tests/qemu-iotests/190 | 2 +- tests/qemu-iotests/191 | 3 +-- tests/qemu-iotests/220 | 4 ++- tests/qemu-iotests/243 | 6 +++-- tests/qemu-iotests/244 | 10 +++++--- tests/qemu-iotests/250 | 3 +-- tests/qemu-iotests/265 | 2 +- 22 files changed, 100 insertions(+), 101 deletions(-) diff --git a/tests/qemu-iotests/031 b/tests/qemu-iotests/031 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/031 +++ b/tests/qemu-iotests/031 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file +# We want to test compat=0.10, which does not support refcount widths +# other than 16 +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' CLUSTER_SIZE=65536 # qcow2.py output depends on the exact options used, so override the command # line here as an exception -for IMGOPTS in "compat=0.10" "compat=1.1"; do +for compat in "compat=0.10" "compat=1.1"; do echo - echo ===== Testing with -o $IMGOPTS ===== + echo ===== Testing with -o $compat ===== echo echo === Create image with unknown header extension === echo - _make_test_img 64M + _make_test_img -o $compat 64M $PYTHON qcow2.py "$TEST_IMG" add-header-ext 0x12345678 "This is a test header extension" $PYTHON qcow2.py "$TEST_IMG" dump-header _check_test_img diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/039 +++ b/tests/qemu-iotests/039 @@ -XXX,XX +XXX,XX @@ size=128M echo echo "== Checking that image is clean on shutdown ==" -IMGOPTS="compat=1.1,lazy_refcounts=on" -_make_test_img $size +_make_test_img -o "compat=1.1,lazy_refcounts=on" $size $QEMU_IO -c "write -P 0x5a 0 512" "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "== Creating a dirty image file ==" -IMGOPTS="compat=1.1,lazy_refcounts=on" -_make_test_img $size +_make_test_img -o "compat=1.1,lazy_refcounts=on" $size _NO_VALGRIND \ $QEMU_IO -c "write -P 0x5a 0 512" \ @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0x5a 0 512" "$TEST_IMG" | _filter_qemu_io echo echo "== Opening a dirty image read/write should repair it ==" -IMGOPTS="compat=1.1,lazy_refcounts=on" -_make_test_img $size +_make_test_img -o "compat=1.1,lazy_refcounts=on" $size _NO_VALGRIND \ $QEMU_IO -c "write -P 0x5a 0 512" \ @@ -XXX,XX +XXX,XX @@ $PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features echo echo "== Creating an image file with lazy_refcounts=off ==" -IMGOPTS="compat=1.1,lazy_refcounts=off" -_make_test_img $size +_make_test_img -o "compat=1.1,lazy_refcounts=off" $size _NO_VALGRIND \ $QEMU_IO -c "write -P 0x5a 0 512" \ @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "== Committing to a backing file with lazy_refcounts=on ==" -IMGOPTS="compat=1.1,lazy_refcounts=on" -TEST_IMG="$TEST_IMG".base _make_test_img $size +TEST_IMG="$TEST_IMG".base _make_test_img -o "compat=1.1,lazy_refcounts=on" $size -IMGOPTS="compat=1.1,lazy_refcounts=on,backing_file=$TEST_IMG.base" -_make_test_img $size +_make_test_img -o "compat=1.1,lazy_refcounts=on,backing_file=$TEST_IMG.base" $size $QEMU_IO -c "write 0 512" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG commit "$TEST_IMG" @@ -XXX,XX +XXX,XX @@ TEST_IMG="$TEST_IMG".base _check_test_img echo echo "== Changing lazy_refcounts setting at runtime ==" -IMGOPTS="compat=1.1,lazy_refcounts=off" -_make_test_img $size +_make_test_img -o "compat=1.1,lazy_refcounts=off" $size _NO_VALGRIND \ $QEMU_IO -c "reopen -o lazy-refcounts=on" \ @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "reopen -o lazy-refcounts=on" \ $PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features _check_test_img -IMGOPTS="compat=1.1,lazy_refcounts=on" -_make_test_img $size +_make_test_img -o "compat=1.1,lazy_refcounts=on" $size _NO_VALGRIND \ $QEMU_IO -c "reopen -o lazy-refcounts=off" \ diff --git a/tests/qemu-iotests/059 b/tests/qemu-iotests/059 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/059 +++ b/tests/qemu-iotests/059 @@ -XXX,XX +XXX,XX @@ poke_file "$TEST_IMG" "$grain_table_size_offset" "\x01\x00\x00\x00" echo echo "=== Testing monolithicFlat creation and opening ===" -IMGOPTS="subformat=monolithicFlat" _make_test_img 2G +_make_test_img -o "subformat=monolithicFlat" 2G _img_info _cleanup_test_img echo echo "=== Testing monolithicFlat with zeroed_grain ===" -IMGOPTS="subformat=monolithicFlat,zeroed_grain=on" _make_test_img 2G +_make_test_img -o "subformat=monolithicFlat,zeroed_grain=on" 2G _cleanup_test_img echo echo "=== Testing big twoGbMaxExtentFlat ===" -IMGOPTS="subformat=twoGbMaxExtentFlat" _make_test_img 1000G +_make_test_img -o "subformat=twoGbMaxExtentFlat" 1000G $QEMU_IMG info $TEST_IMG | _filter_testdir | sed -e 's/cid: [0-9]*/cid: XXXXXXXX/' _cleanup_test_img @@ -XXX,XX +XXX,XX @@ _img_info echo echo "=== Testing truncated sparse ===" -IMGOPTS="subformat=monolithicSparse" _make_test_img 100G +_make_test_img -o "subformat=monolithicSparse" 100G truncate -s 10M $TEST_IMG _img_info echo echo "=== Converting to streamOptimized from image with small cluster size===" -TEST_IMG="$TEST_IMG.qcow2" IMGFMT=qcow2 IMGOPTS="cluster_size=4096" _make_test_img 1G +TEST_IMG="$TEST_IMG.qcow2" IMGFMT=qcow2 _make_test_img -o "cluster_size=4096" 1G $QEMU_IO -f qcow2 -c "write -P 0xa 0 512" "$TEST_IMG.qcow2" | _filter_qemu_io $QEMU_IO -f qcow2 -c "write -P 0xb 10240 512" "$TEST_IMG.qcow2" | _filter_qemu_io $QEMU_IMG convert -f qcow2 -O vmdk -o subformat=streamOptimized "$TEST_IMG.qcow2" "$TEST_IMG" 2>&1 @@ -XXX,XX +XXX,XX @@ echo "=== Testing monolithicFlat with internally generated JSON file name ===" echo '--- blkdebug ---' # Should work, because bdrv_dirname() works fine with blkdebug -IMGOPTS="subformat=monolithicFlat" _make_test_img 64M +_make_test_img -o "subformat=monolithicFlat" 64M $QEMU_IO -c "open -o driver=$IMGFMT,file.driver=blkdebug,file.image.filename=$TEST_IMG,file.inject-error.0.event=read_aio" \ -c info \ 2>&1 \ @@ -XXX,XX +XXX,XX @@ _cleanup_test_img echo '--- quorum ---' # Should not work, because bdrv_dirname() does not work with quorum -IMGOPTS="subformat=monolithicFlat" _make_test_img 64M +_make_test_img -o "subformat=monolithicFlat" 64M cp "$TEST_IMG" "$TEST_IMG.orig" filename="json:{ @@ -XXX,XX +XXX,XX @@ _cleanup_test_img echo echo "=== Testing 4TB monolithicFlat creation and IO ===" -IMGOPTS="subformat=monolithicFlat" _make_test_img 4T +_make_test_img -o "subformat=monolithicFlat" 4T _img_info $QEMU_IO -c "write -P 0xa 900G 512" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c "read -v 900G 1024" "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ _cleanup_test_img echo echo "=== Testing qemu-img map on extents ===" for fmt in monolithicSparse twoGbMaxExtentSparse; do - IMGOPTS="subformat=$fmt" _make_test_img 31G + _make_test_img -o "subformat=$fmt" 31G $QEMU_IO -c "write 65024 1k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c "write 2147483136 1k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c "write 5G 1k" "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'write 0k 64k' "$BACKING_IMG" | _filter_qemu_io # compat=0.10 is required in order to make the following discard actually # unallocate the sector rather than make it a zero sector - we want COW, after # all. -IMGOPTS='compat=0.10' _make_test_img -b "$BACKING_IMG" 1G +_make_test_img -o 'compat=0.10' -b "$BACKING_IMG" 1G # Write two clusters, the second one enforces creation of an L2 table after # the first data cluster. $QEMU_IO -c 'write 0k 64k' -c 'write 512M 64k' "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ echo echo "=== Discarding a non-covered in-bounds refblock ===" echo -IMGOPTS='refcount_bits=1' _make_test_img 64M +_make_test_img -o 'refcount_bits=1' 64M # Pretend there's a refblock somewhere where there is no refblock to # cover it (but the covering refblock has a valid index in the @@ -XXX,XX +XXX,XX @@ echo echo "=== Discarding a refblock covered by an unaligned refblock ===" echo -IMGOPTS='refcount_bits=1' _make_test_img 64M +_make_test_img -o 'refcount_bits=1' 64M # Same as above poke_file "$TEST_IMG" "$(($rt_offset+8))" "\x00\x00\x00\x10\x00\x00\x00\x00" diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/061 +++ b/tests/qemu-iotests/061 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# Conversion between different compat versions can only really work +# with refcount_bits=16 +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' echo echo "=== Testing version downgrade with zero expansion ===" echo -IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M +_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io $PYTHON qcow2.py "$TEST_IMG" dump-header $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing version downgrade with zero expansion and 4K cache entries ===" echo -IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M +_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c "write -z 32M 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c map "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing dirty version downgrade ===" echo -IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M +_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M _NO_VALGRIND \ $QEMU_IO -c "write -P 0x2a 0 128k" -c flush \ -c "sigraise $(kill -l KILL)" "$TEST_IMG" 2>&1 | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing version downgrade with unknown compat/autoclear flags ===" echo -IMGOPTS="compat=1.1" _make_test_img 64M +_make_test_img -o "compat=1.1" 64M $PYTHON qcow2.py "$TEST_IMG" set-feature-bit compatible 42 $PYTHON qcow2.py "$TEST_IMG" set-feature-bit autoclear 42 $PYTHON qcow2.py "$TEST_IMG" dump-header @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing version upgrade and resize ===" echo -IMGOPTS="compat=0.10" _make_test_img 64M +_make_test_img -o "compat=0.10" 64M $QEMU_IO -c "write -P 0x2a 42M 64k" "$TEST_IMG" | _filter_qemu_io $PYTHON qcow2.py "$TEST_IMG" dump-header $QEMU_IMG amend -o "compat=1.1,lazy_refcounts=on,size=128M" "$TEST_IMG" @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing dirty lazy_refcounts=off ===" echo -IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img 64M +_make_test_img -o "compat=1.1,lazy_refcounts=on" 64M _NO_VALGRIND \ $QEMU_IO -c "write -P 0x2a 0 128k" -c flush \ -c "sigraise $(kill -l KILL)" "$TEST_IMG" 2>&1 | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing backing file ===" echo -IMGOPTS="compat=1.1" _make_test_img 64M -IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M +_make_test_img -o "compat=1.1" 64M +TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG amend -o "backing_file=$TEST_IMG.base,backing_fmt=qcow2" "$TEST_IMG" @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing invalid configurations ===" echo -IMGOPTS="compat=0.10" _make_test_img 64M +_make_test_img -o "compat=0.10" 64M $QEMU_IMG amend -o "lazy_refcounts=on" "$TEST_IMG" $QEMU_IMG amend -o "compat=1.1" "$TEST_IMG" # actually valid $QEMU_IMG amend -o "compat=0.10,lazy_refcounts=on" "$TEST_IMG" @@ -XXX,XX +XXX,XX @@ $QEMU_IMG amend -o "preallocation=on" "$TEST_IMG" echo echo "=== Testing correct handling of unset value ===" echo -IMGOPTS="compat=1.1,cluster_size=1k" _make_test_img 64M +_make_test_img -o "compat=1.1,cluster_size=1k" 64M echo "Should work:" $QEMU_IMG amend -o "lazy_refcounts=on" "$TEST_IMG" echo "Should not work:" # Just to know which of these tests actually fails @@ -XXX,XX +XXX,XX @@ $QEMU_IMG amend -o "cluster_size=64k" "$TEST_IMG" echo echo "=== Testing zero expansion on inactive clusters ===" echo -IMGOPTS="compat=1.1" _make_test_img 64M +_make_test_img -o "compat=1.1" 64M $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG snapshot -c foo "$TEST_IMG" $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io echo echo "=== Testing zero expansion on shared L2 table ===" echo -IMGOPTS="compat=1.1" _make_test_img 64M +_make_test_img -o "compat=1.1" 64M $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG snapshot -c foo "$TEST_IMG" $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io echo echo "=== Testing zero expansion on backed image ===" echo -IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M +TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io -IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 64M +_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 64M $QEMU_IO -c "read -P 0x2a 0 128k" -c "write -z 0 64k" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" _check_test_img @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 64k" -c "read -P 0x2a 64k 64k" "$TEST_IMG" | _filter_qe echo echo "=== Testing zero expansion on backed inactive clusters ===" echo -IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M +TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io -IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 64M +_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 64M $QEMU_IO -c "write -z 0 64k" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG snapshot -c foo "$TEST_IMG" $QEMU_IO -c "write -P 0x42 0 128k" "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 64k" -c "read -P 0x2a 64k 64k" "$TEST_IMG" | _filter_qe echo echo "=== Testing zero expansion on backed image with shared L2 table ===" echo -IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 64M +TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 64M $QEMU_IO -c "write -P 0x2a 0 128k" "$TEST_IMG.base" | _filter_qemu_io -IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 64M +_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 64M $QEMU_IO -c "write -z 0 128k" "$TEST_IMG" | _filter_qemu_io $QEMU_IMG snapshot -c foo "$TEST_IMG" $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 128k" "$TEST_IMG" | _filter_qemu_io echo echo "=== Testing preallocated zero expansion on full image ===" echo -IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG" _make_test_img 64M +TEST_IMG="$TEST_IMG" _make_test_img -o "compat=1.1" 64M $QEMU_IO -c "write -P 0x2a 0 64M" "$TEST_IMG" -c "write -z 0 64M" | _filter_qemu_io $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" _check_test_img @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "read -P 0 0 64M" "$TEST_IMG" | _filter_qemu_io echo echo "=== Testing progress report without snapshot ===" echo -IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 4G -IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 4G +TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 4G +_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 4G $QEMU_IO -c "write -z 0 64k" \ -c "write -z 1G 64k" \ -c "write -z 2G 64k" \ @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing progress report with snapshot ===" echo -IMGOPTS="compat=1.1" TEST_IMG="$TEST_IMG.base" _make_test_img 4G -IMGOPTS="compat=1.1" _make_test_img -b "$TEST_IMG.base" 4G +TEST_IMG="$TEST_IMG.base" _make_test_img -o "compat=1.1" 4G +_make_test_img -o "compat=1.1" -b "$TEST_IMG.base" 4G $QEMU_IO -c "write -z 0 64k" \ -c "write -z 1G 64k" \ -c "write -z 2G 64k" \ @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Testing version downgrade with external data file ===" echo -IMGOPTS="compat=1.1,data_file=$TEST_IMG.data" _make_test_img 64M +_make_test_img -o "compat=1.1,data_file=$TEST_IMG.data" 64M $QEMU_IMG amend -o "compat=0.10" "$TEST_IMG" _img_info --format-specific _check_test_img @@ -XXX,XX +XXX,XX @@ _check_test_img echo echo "=== Try changing the external data file ===" echo -IMGOPTS="compat=1.1" _make_test_img 64M +_make_test_img -o "compat=1.1" 64M $QEMU_IMG amend -o "data_file=foo" "$TEST_IMG" echo -IMGOPTS="compat=1.1,data_file=$TEST_IMG.data" _make_test_img 64M +_make_test_img -o "compat=1.1,data_file=$TEST_IMG.data" 64M $QEMU_IMG amend -o "data_file=foo" "$TEST_IMG" _img_info --format-specific TEST_IMG="data-file.filename=$TEST_IMG.data,file.filename=$TEST_IMG" _img_info --format-specific --image-opts @@ -XXX,XX +XXX,XX @@ TEST_IMG="data-file.filename=$TEST_IMG.data,file.filename=$TEST_IMG" _img_info - echo echo "=== Clearing and setting data-file-raw ===" echo -IMGOPTS="compat=1.1,data_file=$TEST_IMG.data,data_file_raw=on" _make_test_img 64M +_make_test_img -o "compat=1.1,data_file=$TEST_IMG.data,data_file_raw=on" 64M $QEMU_IMG amend -o "data_file_raw=on" "$TEST_IMG" _img_info --format-specific _check_test_img diff --git a/tests/qemu-iotests/079 b/tests/qemu-iotests/079 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/079 +++ b/tests/qemu-iotests/079 @@ -XXX,XX +XXX,XX @@ echo cluster_sizes="16384 32768 65536 131072 262144 524288 1048576 2097152 4194304" for s in $cluster_sizes; do - IMGOPTS=$(_optstr_add "$IMGOPTS" "preallocation=metadata,cluster_size=$s") \ - _make_test_img 4G + _make_test_img -o "preallocation=metadata,cluster_size=$s" 4G done # success, all done diff --git a/tests/qemu-iotests/106 b/tests/qemu-iotests/106 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/106 +++ b/tests/qemu-iotests/106 @@ -XXX,XX +XXX,XX @@ for create_mode in off falloc full; do echo echo "--- create_mode=$create_mode growth_mode=$growth_mode ---" - IMGOPTS="preallocation=$create_mode" _make_test_img ${CREATION_SIZE}K + _make_test_img -o "preallocation=$create_mode" ${CREATION_SIZE}K $QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K expected_size=0 diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/108 +++ b/tests/qemu-iotests/108 @@ -XXX,XX +XXX,XX @@ echo echo '=== Repairing unreferenced data cluster in new refblock area ===' echo -IMGOPTS='cluster_size=512' _make_test_img 64M +_make_test_img -o 'cluster_size=512' 64M # Allocate the first 128 kB in the image (first refblock) $QEMU_IO -c 'write 0 0x1b200' "$TEST_IMG" | _filter_qemu_io # should be 131072 == 0x20000 diff --git a/tests/qemu-iotests/112 b/tests/qemu-iotests/112 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/112 +++ b/tests/qemu-iotests/112 @@ -XXX,XX +XXX,XX @@ echo '=== refcount_bits limits ===' echo # Must be positive (non-zero) -IMGOPTS="$IMGOPTS,refcount_bits=0" _make_test_img 64M +_make_test_img -o "refcount_bits=0" 64M # Must be positive (non-negative) -IMGOPTS="$IMGOPTS,refcount_bits=-1" _make_test_img 64M +_make_test_img -o "refcount_bits=-1" 64M # May not exceed 64 -IMGOPTS="$IMGOPTS,refcount_bits=128" _make_test_img 64M +_make_test_img -o "refcount_bits=128" 64M # Must be a power of two -IMGOPTS="$IMGOPTS,refcount_bits=42" _make_test_img 64M +_make_test_img -o "refcount_bits=42" 64M # 1 is the minimum -IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M +_make_test_img -o "refcount_bits=1" 64M print_refcount_bits # 64 is the maximum -IMGOPTS="$IMGOPTS,refcount_bits=64" _make_test_img 64M +_make_test_img -o "refcount_bits=64" 64M print_refcount_bits # 16 is the default @@ -XXX,XX +XXX,XX @@ echo '=== refcount_bits and compat=0.10 ===' echo # Should work -IMGOPTS="$IMGOPTS,compat=0.10,refcount_bits=16" _make_test_img 64M +_make_test_img -o "compat=0.10,refcount_bits=16" 64M print_refcount_bits # Should not work -IMGOPTS="$IMGOPTS,compat=0.10,refcount_bits=1" _make_test_img 64M -IMGOPTS="$IMGOPTS,compat=0.10,refcount_bits=64" _make_test_img 64M +_make_test_img -o "compat=0.10,refcount_bits=1" 64M +_make_test_img -o "compat=0.10,refcount_bits=64" 64M echo echo '=== Snapshot limit on refcount_bits=1 ===' echo -IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M +_make_test_img -o "refcount_bits=1" 64M print_refcount_bits $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ echo echo '=== Snapshot limit on refcount_bits=2 ===' echo -IMGOPTS="$IMGOPTS,refcount_bits=2" _make_test_img 64M +_make_test_img -o "refcount_bits=2" 64M print_refcount_bits $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ echo echo '=== Compressed clusters with refcount_bits=1 ===' echo -IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M +_make_test_img -o "refcount_bits=1" 64M print_refcount_bits # Both should fit into a single host cluster; instead of failing to increase the @@ -XXX,XX +XXX,XX @@ echo echo '=== MSb set in 64 bit refcount ===' echo -IMGOPTS="$IMGOPTS,refcount_bits=64" _make_test_img 64M +_make_test_img -o "refcount_bits=64" 64M print_refcount_bits $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ echo echo '=== Snapshot on maximum 64 bit refcount value ===' echo -IMGOPTS="$IMGOPTS,refcount_bits=64" _make_test_img 64M +_make_test_img -o "refcount_bits=64" 64M print_refcount_bits $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io @@ -XXX,XX +XXX,XX @@ echo echo '=== Testing too many references for check ===' echo -IMGOPTS="$IMGOPTS,refcount_bits=1" _make_test_img 64M +_make_test_img -o "refcount_bits=1" 64M print_refcount_bits # This cluster should be created at 0x50000 @@ -XXX,XX +XXX,XX @@ echo echo '=== Multiple walks necessary during amend ===' echo -IMGOPTS="$IMGOPTS,refcount_bits=1,cluster_size=512" _make_test_img 64k +_make_test_img -o "refcount_bits=1,cluster_size=512" 64k # Cluster 0 is the image header, clusters 1 to 4 are used by the L1 table, a # single L2 table, the reftable and a single refblock. This creates 58 data diff --git a/tests/qemu-iotests/115 b/tests/qemu-iotests/115 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/115 +++ b/tests/qemu-iotests/115 @@ -XXX,XX +XXX,XX @@ echo # least 256 MB. We can achieve that by using preallocation=metadata for an image # which has a guest disk size of 256 MB. -IMGOPTS="$IMGOPTS,refcount_bits=64,cluster_size=512,preallocation=metadata" \ - _make_test_img 256M +_make_test_img -o "refcount_bits=64,cluster_size=512,preallocation=metadata" 256M # We know for sure that the L1 and refcount tables do not overlap with any other # structure because the metadata overlap checks would have caught that case. diff --git a/tests/qemu-iotests/121 b/tests/qemu-iotests/121 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/121 +++ b/tests/qemu-iotests/121 @@ -XXX,XX +XXX,XX @@ echo # Preallocation speeds up the write operation, but preallocating everything will # destroy the purpose of the write; so preallocate one KB less than what would # cause a reftable growth... -IMGOPTS='preallocation=metadata,cluster_size=1k' _make_test_img 64512K +_make_test_img -o 'preallocation=metadata,cluster_size=1k' 64512K # ...and make the image the desired size afterwards. $QEMU_IMG resize "$TEST_IMG" 65M @@ -XXX,XX +XXX,XX @@ echo echo '--- Test 2 ---' echo -IMGOPTS='preallocation=metadata,cluster_size=1k' _make_test_img 64513K +_make_test_img -o 'preallocation=metadata,cluster_size=1k' 64513K # This results in an L1 table growth which in turn results in some clusters at # the start of the image becoming free $QEMU_IMG resize "$TEST_IMG" 65M @@ -XXX,XX +XXX,XX @@ echo echo '=== Allocating a new refcount block must not leave holes in the image ===' echo -IMGOPTS='cluster_size=512,refcount_bits=16' _make_test_img 1M +_make_test_img -o 'cluster_size=512,refcount_bits=16' 1M # This results in an image with 256 used clusters: the qcow2 header, # the refcount table, one refcount block, the L1 table, four L2 tables diff --git a/tests/qemu-iotests/125 b/tests/qemu-iotests/125 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/125 +++ b/tests/qemu-iotests/125 @@ -XXX,XX +XXX,XX @@ for GROWTH_SIZE in 16 48 80; do for growth_mode in off metadata falloc full; do echo "--- cluster_size=$cluster_size growth_size=$GROWTH_SIZE create_mode=$create_mode growth_mode=$growth_mode ---" - IMGOPTS="preallocation=$create_mode,cluster_size=$cluster_size" _make_test_img ${CREATION_SIZE} + _make_test_img -o "preallocation=$create_mode,cluster_size=$cluster_size" ${CREATION_SIZE} $QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K host_size_0=$(get_image_size_on_host) diff --git a/tests/qemu-iotests/137 b/tests/qemu-iotests/137 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/137 +++ b/tests/qemu-iotests/137 @@ -XXX,XX +XXX,XX @@ $QEMU_IO \ -c "reopen -o cache-clean-interval=-1" \ "$TEST_IMG" | _filter_qemu_io -IMGOPTS="cluster_size=256k" _make_test_img 32P +_make_test_img -o "cluster_size=256k" 32P $QEMU_IO \ -c "reopen -o l2-cache-entry-size=512,l2-cache-size=1T" \ "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/138 b/tests/qemu-iotests/138 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/138 +++ b/tests/qemu-iotests/138 @@ -XXX,XX +XXX,XX @@ echo echo '=== Check on an image with a multiple of 2^32 clusters ===' echo -IMGOPTS=$(_optstr_add "$IMGOPTS" "cluster_size=512") \ - _make_test_img 512 +_make_test_img -o "cluster_size=512" 512 # Allocate L2 table $QEMU_IO -c 'write 0 512' "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/175 b/tests/qemu-iotests/175 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/175 +++ b/tests/qemu-iotests/175 @@ -XXX,XX +XXX,XX @@ stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_block for mode in off full falloc; do echo echo "== creating image with preallocation $mode ==" - IMGOPTS=preallocation=$mode _make_test_img $size | _filter_imgfmt + _make_test_img -o preallocation=$mode $size | _filter_imgfmt stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $size done diff --git a/tests/qemu-iotests/190 b/tests/qemu-iotests/190 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/190 +++ b/tests/qemu-iotests/190 @@ -XXX,XX +XXX,XX @@ _supported_proto file echo "== Huge file ==" echo -IMGOPTS='cluster_size=2M' _make_test_img 2T +_make_test_img -o 'cluster_size=2M' 2T $QEMU_IMG measure -O raw -f qcow2 "$TEST_IMG" $QEMU_IMG measure -O qcow2 -o cluster_size=64k -f qcow2 "$TEST_IMG" diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/191 +++ b/tests/qemu-iotests/191 @@ -XXX,XX +XXX,XX @@ echo === Preparing and starting VM === echo TEST_IMG="${TEST_IMG}.base" _make_test_img $size -IMGOPTS=$(_optstr_add "$IMGOPTS" "backing_fmt=$IMGFMT") \ - TEST_IMG="${TEST_IMG}.mid" _make_test_img -b "${TEST_IMG}.base" +TEST_IMG="${TEST_IMG}.mid" _make_test_img -o "backing_fmt=$IMGFMT" -b "${TEST_IMG}.base" _make_test_img -b "${TEST_IMG}.mid" TEST_IMG="${TEST_IMG}.ovl2" _make_test_img -b "${TEST_IMG}.mid" diff --git a/tests/qemu-iotests/220 b/tests/qemu-iotests/220 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/220 +++ b/tests/qemu-iotests/220 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# To use a different refcount width but 16 bits we need compat=1.1 +_unsupported_imgopts 'compat=0.10' echo "== Creating huge file ==" @@ -XXX,XX +XXX,XX @@ echo "== Creating huge file ==" # of a HUGE (but very sparse) file. tmpfs works, ext4 does not. _require_large_file 513T -IMGOPTS='cluster_size=2M,refcount_bits=1' _make_test_img 513T +_make_test_img -o 'cluster_size=2M,refcount_bits=1' 513T echo "== Populating refcounts ==" # We want an image with 256M refcounts * 2M clusters = 512T referenced. diff --git a/tests/qemu-iotests/243 b/tests/qemu-iotests/243 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/243 +++ b/tests/qemu-iotests/243 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# External data files do not work with compat=0.10 +_unsupported_imgopts 'compat=0.10' for mode in off metadata falloc full; do @@ -XXX,XX +XXX,XX @@ for mode in off metadata falloc full; do echo "=== preallocation=$mode ===" echo - IMGOPTS="preallocation=$mode" _make_test_img 64M + _make_test_img -o "preallocation=$mode" 64M printf "File size: " du -b $TEST_IMG | cut -f1 @@ -XXX,XX +XXX,XX @@ for mode in off metadata falloc full; do echo "=== External data file: preallocation=$mode ===" echo - IMGOPTS="data_file=$TEST_IMG.data,preallocation=$mode" _make_test_img 64M + _make_test_img -o "data_file=$TEST_IMG.data,preallocation=$mode" 64M echo -n "qcow2 file size: " du -b $TEST_IMG | cut -f1 diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/244 +++ b/tests/qemu-iotests/244 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# External data files do not work with compat=0.10 +_unsupported_imgopts 'compat=0.10' echo echo "=== Create and open image with external data file ===" echo echo "With data file name in the image:" -IMGOPTS="data_file=$TEST_IMG.data" _make_test_img 64M +_make_test_img -o "data_file=$TEST_IMG.data" 64M _check_test_img $QEMU_IO -c "open $TEST_IMG" -c "read -P 0 0 64k" 2>&1 | _filter_qemu_io | _filter_testdir @@ -XXX,XX +XXX,XX @@ echo echo "=== Standalone image with external data file (efficient) ===" echo -IMGOPTS="data_file=$TEST_IMG.data" _make_test_img 64M +_make_test_img -o "data_file=$TEST_IMG.data" 64M echo -n "qcow2 file size before I/O: " du -b $TEST_IMG | cut -f1 @@ -XXX,XX +XXX,XX @@ echo echo "=== Standalone image with external data file (valid raw) ===" echo -IMGOPTS="data_file=$TEST_IMG.data,data_file_raw=on" _make_test_img 64M +_make_test_img -o "data_file=$TEST_IMG.data,data_file_raw=on" 64M echo -n "qcow2 file size before I/O: " du -b $TEST_IMG | cut -f1 @@ -XXX,XX +XXX,XX @@ echo echo "=== bdrv_co_block_status test for file and offset=0 ===" echo -IMGOPTS="data_file=$TEST_IMG.data" _make_test_img 64M +_make_test_img -o "data_file=$TEST_IMG.data" 64M $QEMU_IO -c 'write -P 0x11 0 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c 'read -P 0x11 0 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/250 b/tests/qemu-iotests/250 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/250 +++ b/tests/qemu-iotests/250 @@ -XXX,XX +XXX,XX @@ disk_usage() } size=2100M -IMGOPTS="cluster_size=1M,preallocation=metadata" -_make_test_img $size +_make_test_img -o "cluster_size=1M,preallocation=metadata" $size $QEMU_IO -c 'discard 0 10M' -c 'discard 2090M 10M' \ -c 'write 2090M 10M' -c 'write 0 10M' "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/265 b/tests/qemu-iotests/265 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/265 +++ b/tests/qemu-iotests/265 @@ -XXX,XX +XXX,XX @@ _supported_os Linux echo '--- Writing to the image ---' # Reduce cluster size so we get more and quicker I/O -IMGOPTS='cluster_size=4096' _make_test_img 1M +_make_test_img -o 'cluster_size=4096' 1M (for ((kb = 1024 - 4; kb >= 0; kb -= 4)); do \ echo "aio_write -P 42 $((kb + 1))k 2k"; \ done) \ -- 2.24.1 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-13-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/071 | 4 ++-- tests/qemu-iotests/174 | 2 +- tests/qemu-iotests/178 | 4 ++-- tests/qemu-iotests/197 | 4 ++-- tests/qemu-iotests/215 | 4 ++-- 5 files changed, 9 insertions(+), 9 deletions(-) diff --git a/tests/qemu-iotests/071 b/tests/qemu-iotests/071 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/071 +++ b/tests/qemu-iotests/071 @@ -XXX,XX +XXX,XX @@ echo echo "=== Testing blkverify through filename ===" echo -TEST_IMG="$TEST_IMG.base" IMGOPTS="" IMGFMT="raw" _make_test_img $IMG_SIZE |\ +TEST_IMG="$TEST_IMG.base" IMGFMT="raw" _make_test_img --no-opts $IMG_SIZE |\ _filter_imgfmt _make_test_img $IMG_SIZE $QEMU_IO -c "open -o driver=raw,file.driver=blkverify,file.raw.filename=$TEST_IMG.base $TEST_IMG" \ @@ -XXX,XX +XXX,XX @@ echo echo "=== Testing blkverify through file blockref ===" echo -TEST_IMG="$TEST_IMG.base" IMGOPTS="" IMGFMT="raw" _make_test_img $IMG_SIZE |\ +TEST_IMG="$TEST_IMG.base" IMGFMT="raw" _make_test_img --no-opts $IMG_SIZE |\ _filter_imgfmt _make_test_img $IMG_SIZE $QEMU_IO -c "open -o driver=raw,file.driver=blkverify,file.raw.filename=$TEST_IMG.base,file.test.driver=$IMGFMT,file.test.file.filename=$TEST_IMG" \ diff --git a/tests/qemu-iotests/174 b/tests/qemu-iotests/174 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/174 +++ b/tests/qemu-iotests/174 @@ -XXX,XX +XXX,XX @@ _unsupported_fmt raw size=256K -IMGFMT=raw IMGKEYSECRET= IMGOPTS= _make_test_img $size | _filter_imgfmt +IMGFMT=raw IMGKEYSECRET= _make_test_img --no-opts $size | _filter_imgfmt echo echo "== reading wrong format should fail ==" diff --git a/tests/qemu-iotests/178 b/tests/qemu-iotests/178 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/178 +++ b/tests/qemu-iotests/178 @@ -XXX,XX +XXX,XX @@ $QEMU_IMG measure -O foo "$TEST_IMG" # unknown image file format make_test_img_with_fmt() { # Shadow global variables within this function - local IMGFMT="$1" IMGOPTS="" - _make_test_img "$2" + local IMGFMT="$1" + _make_test_img --no-opts "$2" } qemu_io_with_fmt() { diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/197 +++ b/tests/qemu-iotests/197 @@ -XXX,XX +XXX,XX @@ if [ "$IMGFMT" = "vpc" ]; then 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="$TEST_WRAP" \ - _make_test_img -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create +IMGPROTO=file IMGFMT=qcow2 TEST_IMG_FILE="$TEST_WRAP" \ + _make_test_img --no-opts -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create $QEMU_IO -f qcow2 -c "write -z -u 1M 64k" "$TEST_WRAP" | _filter_qemu_io # Ensure that a read of two clusters, but where one is already allocated, diff --git a/tests/qemu-iotests/215 b/tests/qemu-iotests/215 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/215 +++ b/tests/qemu-iotests/215 @@ -XXX,XX +XXX,XX @@ if [ "$IMGFMT" = "vpc" ]; then 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="$TEST_WRAP" \ - _make_test_img -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create +IMGPROTO=file IMGFMT=qcow2 TEST_IMG_FILE="$TEST_WRAP" \ + _make_test_img --no-opts -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create $QEMU_IO -f qcow2 -c "write -z -u 1M 64k" "$TEST_WRAP" | _filter_qemu_io # Ensure that a read of two clusters, but where one is already allocated, -- 2.24.1 Overwriting IMGOPTS means ignoring all user-supplied options, which is not what we want. Replace the current IMGOPTS use by a new BACKING_FILE variable. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-14-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/267 | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/tests/qemu-iotests/267 b/tests/qemu-iotests/267 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/267 +++ b/tests/qemu-iotests/267 @@ -XXX,XX +XXX,XX @@ size=128M run_test() { - _make_test_img $size + if [ -n "$BACKING_FILE" ]; then + _make_test_img -b "$BACKING_FILE" $size + else + _make_test_img $size + fi printf "savevm snap0\ninfo snapshots\nloadvm snap0\n" | run_qemu "$@" | _filter_date } @@ -XXX,XX +XXX,XX @@ echo TEST_IMG="$TEST_IMG.base" _make_test_img $size -IMGOPTS="backing_file=$TEST_IMG.base" \ +BACKING_FILE="$TEST_IMG.base" \ run_test -blockdev driver=file,filename="$TEST_IMG.base",node-name=backing-file \ -blockdev driver=file,filename="$TEST_IMG",node-name=file \ -blockdev driver=$IMGFMT,file=file,backing=backing-file,node-name=fmt -IMGOPTS="backing_file=$TEST_IMG.base" \ +BACKING_FILE="$TEST_IMG.base" \ run_test -blockdev driver=file,filename="$TEST_IMG.base",node-name=backing-file \ -blockdev driver=$IMGFMT,file=backing-file,node-name=backing-fmt \ -blockdev driver=file,filename="$TEST_IMG",node-name=file \ @@ -XXX,XX +XXX,XX @@ echo echo "=== -blockdev with NBD server on the backing file ===" echo -IMGOPTS="backing_file=$TEST_IMG.base" _make_test_img $size +_make_test_img -b "$TEST_IMG.base" $size cat <<EOF | nbd_server_start unix:$SOCK_DIR/nbd nbd_server_add -w backing-fmt -- 2.24.1 Use _make_test_img whenever possible. This way, we will not ignore user-specified image options. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-15-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/094 | 2 +- tests/qemu-iotests/111 | 3 +-- tests/qemu-iotests/123 | 2 +- tests/qemu-iotests/153 | 2 +- tests/qemu-iotests/200 | 4 ++-- 5 files changed, 6 insertions(+), 7 deletions(-) diff --git a/tests/qemu-iotests/094 b/tests/qemu-iotests/094 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/094 +++ b/tests/qemu-iotests/094 @@ -XXX,XX +XXX,XX @@ _supported_proto nbd _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" _make_test_img 64M -$QEMU_IMG create -f $IMGFMT "$TEST_DIR/source.$IMGFMT" 64M | _filter_img_create +TEST_IMG_FILE="$TEST_DIR/source.$IMGFMT" IMGPROTO=file _make_test_img 64M _launch_qemu -drive if=none,id=src,file="$TEST_DIR/source.$IMGFMT",format=raw \ -nodefaults diff --git a/tests/qemu-iotests/111 b/tests/qemu-iotests/111 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/111 +++ b/tests/qemu-iotests/111 @@ -XXX,XX +XXX,XX @@ _supported_fmt qed qcow qcow2 vmdk _supported_proto file _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" -$QEMU_IMG create -f $IMGFMT -b "$TEST_IMG.inexistent" "$TEST_IMG" 2>&1 \ - | _filter_testdir | _filter_imgfmt +_make_test_img -b "$TEST_IMG.inexistent" # success, all done echo '*** done' diff --git a/tests/qemu-iotests/123 b/tests/qemu-iotests/123 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/123 +++ b/tests/qemu-iotests/123 @@ -XXX,XX +XXX,XX @@ _supported_os Linux SRC_IMG="$TEST_DIR/source.$IMGFMT" _make_test_img 1M -$QEMU_IMG create -f $IMGFMT "$SRC_IMG" 1M | _filter_img_create +TEST_IMG_FILE=$SRC_IMG IMGPROTO=file _make_test_img 1M $QEMU_IO -c 'write -P 42 0 1M' "$SRC_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/153 b/tests/qemu-iotests/153 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/153 +++ b/tests/qemu-iotests/153 @@ -XXX,XX +XXX,XX @@ for opts1 in "" "read-only=on" "read-only=on,force-share=on"; do echo echo "== Creating test image ==" - $QEMU_IMG create -f $IMGFMT "${TEST_IMG}" -b ${TEST_IMG}.base | _filter_img_create + _make_test_img -b "${TEST_IMG}.base" echo echo "== Launching QEMU, opts: '$opts1' ==" diff --git a/tests/qemu-iotests/200 b/tests/qemu-iotests/200 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/200 +++ b/tests/qemu-iotests/200 @@ -XXX,XX +XXX,XX @@ _supported_proto file BACKING_IMG="${TEST_DIR}/backing.img" TEST_IMG="${TEST_DIR}/test.img" -${QEMU_IMG} create -f $IMGFMT "${BACKING_IMG}" 512M | _filter_img_create -${QEMU_IMG} create -f $IMGFMT -F $IMGFMT "${TEST_IMG}" -b "${BACKING_IMG}" 512M | _filter_img_create +TEST_IMG="$BACKING_IMG" _make_test_img 512M +_make_test_img -F $IMGFMT -b "$BACKING_IMG" 512M ${QEMU_IO} -c "write -P 0xa5 512 300M" "${BACKING_IMG}" | _filter_qemu_io -- 2.24.1 Just rm will not delete external data files. Use _rm_test_img every time we delete a test image. (In the process, clean up the indentation of every _cleanup() this patch touches.) ((Also, use quotes consistently. I am happy to see unquoted instances like "rm -rf $TEST_DIR/..." go.)) Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-16-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/019 | 6 +++--- tests/qemu-iotests/020 | 6 +++--- tests/qemu-iotests/024 | 10 +++++----- tests/qemu-iotests/028 | 2 +- tests/qemu-iotests/029 | 2 +- tests/qemu-iotests/043 | 4 +++- tests/qemu-iotests/048 | 2 +- tests/qemu-iotests/050 | 4 ++-- tests/qemu-iotests/053 | 4 ++-- tests/qemu-iotests/058 | 2 +- tests/qemu-iotests/059 | 2 +- tests/qemu-iotests/061 | 2 +- tests/qemu-iotests/063 | 6 ++++-- tests/qemu-iotests/069 | 2 +- tests/qemu-iotests/074 | 2 +- tests/qemu-iotests/080 | 2 +- tests/qemu-iotests/081 | 6 +++--- tests/qemu-iotests/085 | 9 ++++++--- tests/qemu-iotests/088 | 2 +- tests/qemu-iotests/092 | 2 +- tests/qemu-iotests/094 | 2 +- tests/qemu-iotests/095 | 5 +++-- tests/qemu-iotests/099 | 7 ++++--- tests/qemu-iotests/109 | 4 ++-- tests/qemu-iotests/110 | 4 ++-- tests/qemu-iotests/122 | 6 ++++-- tests/qemu-iotests/123 | 2 +- tests/qemu-iotests/141 | 4 +++- tests/qemu-iotests/142 | 2 +- tests/qemu-iotests/144 | 4 +++- tests/qemu-iotests/153 | 10 +++------- tests/qemu-iotests/156 | 8 ++++++-- tests/qemu-iotests/159 | 2 +- tests/qemu-iotests/160 | 3 ++- tests/qemu-iotests/161 | 4 ++-- tests/qemu-iotests/170 | 2 +- tests/qemu-iotests/172 | 6 +++--- tests/qemu-iotests/173 | 3 ++- tests/qemu-iotests/178 | 2 +- tests/qemu-iotests/182 | 2 +- tests/qemu-iotests/183 | 2 +- tests/qemu-iotests/185 | 4 ++-- tests/qemu-iotests/187 | 6 +++--- tests/qemu-iotests/190 | 2 +- tests/qemu-iotests/191 | 6 +++--- tests/qemu-iotests/195 | 2 +- tests/qemu-iotests/197 | 2 +- tests/qemu-iotests/200 | 3 ++- tests/qemu-iotests/215 | 2 +- tests/qemu-iotests/225 | 2 +- tests/qemu-iotests/229 | 3 ++- tests/qemu-iotests/232 | 4 +++- tests/qemu-iotests/243 | 2 +- tests/qemu-iotests/244 | 4 ++-- tests/qemu-iotests/247 | 4 +++- tests/qemu-iotests/249 | 4 ++-- tests/qemu-iotests/252 | 2 +- 57 files changed, 118 insertions(+), 95 deletions(-) diff --git a/tests/qemu-iotests/019 b/tests/qemu-iotests/019 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/019 +++ b/tests/qemu-iotests/019 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img - rm -f "$TEST_IMG.base" - rm -f "$TEST_IMG.orig" + _cleanup_test_img + _rm_test_img "$TEST_IMG.base" + _rm_test_img "$TEST_IMG.orig" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/020 b/tests/qemu-iotests/020 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/020 +++ b/tests/qemu-iotests/020 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img - rm -f "$TEST_IMG.base" - rm -f "$TEST_IMG.orig" + _cleanup_test_img + _rm_test_img "$TEST_IMG.base" + _rm_test_img "$TEST_IMG.orig" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/024 b/tests/qemu-iotests/024 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/024 +++ b/tests/qemu-iotests/024 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_DIR/t.$IMGFMT.base_old" - rm -f "$TEST_DIR/t.$IMGFMT.base_new" + _rm_test_img "$TEST_DIR/t.$IMGFMT.base_old" + _rm_test_img "$TEST_DIR/t.$IMGFMT.base_new" - rm -f "$TEST_DIR/subdir/t.$IMGFMT" - rm -f "$TEST_DIR/subdir/t.$IMGFMT.base_old" - rm -f "$TEST_DIR/subdir/t.$IMGFMT.base_new" + _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT" + _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT.base_old" + _rm_test_img "$TEST_DIR/subdir/t.$IMGFMT.base_new" rmdir "$TEST_DIR/subdir" 2> /dev/null } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/028 b/tests/qemu-iotests/028 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/028 +++ b/tests/qemu-iotests/028 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_qemu - rm -f "${TEST_IMG}.copy" + _rm_test_img "${TEST_IMG}.copy" _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/029 b/tests/qemu-iotests/029 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/029 +++ b/tests/qemu-iotests/029 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f $TEST_IMG.snap + _rm_test_img "$TEST_IMG.snap" _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/043 b/tests/qemu-iotests/043 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/043 +++ b/tests/qemu-iotests/043 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG".[123].base + for img in "$TEST_IMG".[123].base; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/048 b/tests/qemu-iotests/048 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/048 +++ b/tests/qemu-iotests/048 @@ -XXX,XX +XXX,XX @@ _cleanup() { echo "Cleanup" _cleanup_test_img - rm "${TEST_IMG_FILE2}" + _rm_test_img "${TEST_IMG_FILE2}" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/050 b/tests/qemu-iotests/050 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/050 +++ b/tests/qemu-iotests/050 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.old" - rm -f "$TEST_IMG.new" + _rm_test_img "$TEST_IMG.old" + _rm_test_img "$TEST_IMG.new" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/053 b/tests/qemu-iotests/053 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/053 +++ b/tests/qemu-iotests/053 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f "$TEST_IMG.orig" - _cleanup_test_img + _rm_test_img "$TEST_IMG.orig" + _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/058 b/tests/qemu-iotests/058 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/058 +++ b/tests/qemu-iotests/058 @@ -XXX,XX +XXX,XX @@ _cleanup() { nbd_server_stop _cleanup_test_img - rm -f "$converted_image" + _rm_test_img "$converted_image" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/059 b/tests/qemu-iotests/059 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/059 +++ b/tests/qemu-iotests/059 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.qcow2" + IMGFMT=qcow2 _rm_test_img "$TEST_IMG.qcow2" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/061 +++ b/tests/qemu-iotests/061 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f $TEST_IMG.data + _rm_test_img "$TEST_IMG.data" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/063 b/tests/qemu-iotests/063 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/063 +++ b/tests/qemu-iotests/063 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img - rm -f "$TEST_IMG.orig" "$TEST_IMG.raw1" "$TEST_IMG.raw2" + _cleanup_test_img + for img in "$TEST_IMG".{orig,raw1,raw2,target}; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/069 b/tests/qemu-iotests/069 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/069 +++ b/tests/qemu-iotests/069 @@ -XXX,XX +XXX,XX @@ echo "=== Creating an image with a backing file and deleting that file ===" echo TEST_IMG="$TEST_IMG.base" _make_test_img $IMG_SIZE _make_test_img -b "$TEST_IMG.base" $IMG_SIZE -rm -f "$TEST_IMG.base" +_rm_test_img "$TEST_IMG.base" # Just open the image and close it right again (this should print an error message) $QEMU_IO -c quit "$TEST_IMG" 2>&1 | _filter_testdir | _filter_imgfmt diff --git a/tests/qemu-iotests/074 b/tests/qemu-iotests/074 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/074 +++ b/tests/qemu-iotests/074 @@ -XXX,XX +XXX,XX @@ _cleanup() { echo "Cleanup" _cleanup_test_img - rm "${TEST_IMG2}" + _rm_test_img "${TEST_IMG2}" rm -f "$TEST_DIR/blkdebug.conf" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/080 b/tests/qemu-iotests/080 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/080 +++ b/tests/qemu-iotests/080 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f $TEST_IMG.snap + _rm_test_img "$TEST_IMG.snap" _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 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 @@ status=1 # failure is the default! _cleanup() { - rm -rf $TEST_DIR/1.raw - rm -rf $TEST_DIR/2.raw - rm -rf $TEST_DIR/3.raw + _rm_test_img "$TEST_DIR/1.raw" + _rm_test_img "$TEST_DIR/2.raw" + _rm_test_img "$TEST_DIR/3.raw" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/085 b/tests/qemu-iotests/085 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/085 +++ b/tests/qemu-iotests/085 @@ -XXX,XX +XXX,XX @@ _cleanup() _cleanup_qemu for i in $(seq 1 ${SNAPSHOTS}) do - rm -f "${TEST_DIR}/${i}-${snapshot_virt0}" - rm -f "${TEST_DIR}/${i}-${snapshot_virt1}" + _rm_test_img "${TEST_DIR}/${i}-${snapshot_virt0}" + _rm_test_img "${TEST_DIR}/${i}-${snapshot_virt1}" + done + for img in "${TEST_IMG}".{1,2,base} + do + _rm_test_img "$img" done - rm -f "${TEST_IMG}" "${TEST_IMG}.1" "${TEST_IMG}.2" "${TEST_IMG}.base" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/088 b/tests/qemu-iotests/088 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/088 +++ b/tests/qemu-iotests/088 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f $TEST_IMG.snap + _rm_test_img "$TEST_IMG.snap" _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/092 b/tests/qemu-iotests/092 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/092 +++ b/tests/qemu-iotests/092 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f $TEST_IMG.snap + _rm_test_img "$TEST_IMG.snap" _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/094 b/tests/qemu-iotests/094 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/094 +++ b/tests/qemu-iotests/094 @@ -XXX,XX +XXX,XX @@ _cleanup() { _cleanup_qemu _cleanup_test_img - rm -f "$TEST_DIR/source.$IMGFMT" + _rm_test_img "$TEST_DIR/source.$IMGFMT" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/095 b/tests/qemu-iotests/095 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/095 +++ b/tests/qemu-iotests/095 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_qemu - rm -f "${TEST_IMG}.base" "${TEST_IMG}.snp1" - _cleanup_test_img + _rm_test_img "${TEST_IMG}.base" + _rm_test_img "${TEST_IMG}.snp1" + _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/099 b/tests/qemu-iotests/099 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/099 +++ b/tests/qemu-iotests/099 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img + _cleanup_test_img + _rm_test_img "$TEST_IMG.compare" + rm -f "$TEST_DIR/blkdebug.conf" + } trap "_cleanup; exit \$status" 0 1 2 3 15 @@ -XXX,XX +XXX,XX @@ echo test_qemu "file.driver=blkdebug,file.image.filename=$TEST_IMG" -rm -f "$TEST_IMG.compare" "$TEST_DIR/blkdebug.conf" - # success, all done echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/109 b/tests/qemu-iotests/109 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/109 +++ b/tests/qemu-iotests/109 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_qemu - rm -f $TEST_IMG.src - _cleanup_test_img + _rm_test_img "$TEST_IMG.src" + _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/110 b/tests/qemu-iotests/110 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/110 +++ b/tests/qemu-iotests/110 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img - rm -f "$TEST_IMG.copy" + _cleanup_test_img + _rm_test_img "$TEST_IMG.copy" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/122 b/tests/qemu-iotests/122 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/122 +++ b/tests/qemu-iotests/122 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f "$TEST_IMG".[123] - _cleanup_test_img + for img in "$TEST_IMG".[123]; do + _rm_test_img "$img" + done + _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/123 b/tests/qemu-iotests/123 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/123 +++ b/tests/qemu-iotests/123 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$SRC_IMG" + _rm_test_img "$SRC_IMG" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/141 b/tests/qemu-iotests/141 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/141 +++ b/tests/qemu-iotests/141 @@ -XXX,XX +XXX,XX @@ _cleanup() { _cleanup_qemu _cleanup_test_img - rm -f "$TEST_DIR"/{b,m,o}.$IMGFMT + for img in "$TEST_DIR"/{b,m,o}.$IMGFMT; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/142 b/tests/qemu-iotests/142 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/142 +++ b/tests/qemu-iotests/142 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f $TEST_IMG.snap + _rm_test_img "$TEST_IMG.snap" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/144 b/tests/qemu-iotests/144 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/144 +++ b/tests/qemu-iotests/144 @@ -XXX,XX +XXX,XX @@ TMP_SNAP2=${TEST_DIR}/tmp2.qcow2 _cleanup() { _cleanup_qemu - rm -f "${TEST_IMG}" "${TMP_SNAP1}" "${TMP_SNAP2}" + for img in "${TEST_IMG}" "${TMP_SNAP1}" "${TMP_SNAP2}"; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/153 b/tests/qemu-iotests/153 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/153 +++ b/tests/qemu-iotests/153 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "${TEST_IMG}.base" - rm -f "${TEST_IMG}.overlay" - rm -f "${TEST_IMG}.convert" - rm -f "${TEST_IMG}.a" - rm -f "${TEST_IMG}.b" - rm -f "${TEST_IMG}.c" - rm -f "${TEST_IMG}.lnk" + for img in "${TEST_IMG}".{base,overlay,convert,a,b,c,lnk}; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/156 +++ b/tests/qemu-iotests/156 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_qemu - rm -f "$TEST_IMG"{,.target}{,.backing,.overlay} + for img in "$TEST_IMG"{,.target}{,.backing,.overlay}; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 @@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $QEMU_HANDLE \ '"status": "null"' # Remove the source images -rm -f "$TEST_IMG{,.backing,.overlay}" +for img in "$TEST_IMG{,.backing,.overlay}"; do + _rm_test_img "$img" +done echo diff --git a/tests/qemu-iotests/159 b/tests/qemu-iotests/159 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/159 +++ b/tests/qemu-iotests/159 @@ -XXX,XX +XXX,XX @@ status=1 _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.out" + _rm_test_img "$TEST_IMG.out" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/160 b/tests/qemu-iotests/160 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/160 +++ b/tests/qemu-iotests/160 @@ -XXX,XX +XXX,XX @@ status=1 _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.out" "$TEST_IMG.out.dd" + _rm_test_img "$TEST_IMG.out" + _rm_test_img "$TEST_IMG.out.dd" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/161 b/tests/qemu-iotests/161 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/161 +++ b/tests/qemu-iotests/161 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.base" - rm -f "$TEST_IMG.int" + _rm_test_img "$TEST_IMG.base" + _rm_test_img "$TEST_IMG.int" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/170 b/tests/qemu-iotests/170 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/170 +++ b/tests/qemu-iotests/170 @@ -XXX,XX +XXX,XX @@ status=1 _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.out" + _rm_test_img "$TEST_IMG.out" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/172 b/tests/qemu-iotests/172 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/172 +++ b/tests/qemu-iotests/172 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img - rm -f "$TEST_IMG.2" - rm -f "$TEST_IMG.3" + _cleanup_test_img + _rm_test_img "$TEST_IMG.2" + _rm_test_img "$TEST_IMG.3" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/173 b/tests/qemu-iotests/173 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/173 +++ b/tests/qemu-iotests/173 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_qemu - rm -f "${QEMU_TEST_DIR}/image.base" "${QEMU_TEST_DIR}/image.snp1" + _rm_test_img "${TEST_DIR}/image.base" + _rm_test_img "${TEST_DIR}/image.snp1" _cleanup_test_img } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/178 b/tests/qemu-iotests/178 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/178 +++ b/tests/qemu-iotests/178 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.converted" + _rm_test_img "$TEST_IMG.converted" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/182 b/tests/qemu-iotests/182 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/182 +++ b/tests/qemu-iotests/182 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.overlay" + _rm_test_img "$TEST_IMG.overlay" rm -f "$SOCK_DIR/nbd.socket" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/183 b/tests/qemu-iotests/183 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/183 +++ b/tests/qemu-iotests/183 @@ -XXX,XX +XXX,XX @@ MIG_SOCKET="${SOCK_DIR}/migrate" _cleanup() { rm -f "${MIG_SOCKET}" - rm -f "${TEST_IMG}.dest" + _rm_test_img "${TEST_IMG}.dest" _cleanup_test_img _cleanup_qemu } diff --git a/tests/qemu-iotests/185 b/tests/qemu-iotests/185 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/185 +++ b/tests/qemu-iotests/185 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f "${TEST_IMG}.mid" - rm -f "${TEST_IMG}.copy" + _rm_test_img "${TEST_IMG}.mid" + _rm_test_img "${TEST_IMG}.copy" _cleanup_test_img _cleanup_qemu } diff --git a/tests/qemu-iotests/187 b/tests/qemu-iotests/187 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/187 +++ b/tests/qemu-iotests/187 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - _cleanup_test_img - rm -f "$TEST_IMG.2" - rm -f "$TEST_IMG.3" + _cleanup_test_img + _rm_test_img "$TEST_IMG.2" + _rm_test_img "$TEST_IMG.3" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/190 b/tests/qemu-iotests/190 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/190 +++ b/tests/qemu-iotests/190 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.converted" + _rm_test_img "$TEST_IMG.converted" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/191 +++ b/tests/qemu-iotests/191 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { - rm -f "${TEST_IMG}.mid" - rm -f "${TEST_IMG}.ovl2" - rm -f "${TEST_IMG}.ovl3" + _rm_test_img "${TEST_IMG}.mid" + _rm_test_img "${TEST_IMG}.ovl2" + _rm_test_img "${TEST_IMG}.ovl3" _cleanup_test_img _cleanup_qemu } diff --git a/tests/qemu-iotests/195 b/tests/qemu-iotests/195 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/195 +++ b/tests/qemu-iotests/195 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.mid" + _rm_test_img "$TEST_IMG.mid" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/197 +++ b/tests/qemu-iotests/197 @@ -XXX,XX +XXX,XX @@ esac _cleanup() { _cleanup_test_img - rm -f "$TEST_WRAP" + _rm_test_img "$TEST_WRAP" rm -f "$BLKDBG_CONF" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/200 b/tests/qemu-iotests/200 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/200 +++ b/tests/qemu-iotests/200 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_qemu - rm -f "${TEST_IMG}" "${BACKING_IMG}" + _rm_test_img "${TEST_IMG}" + _rm_test_img "${BACKING_IMG}" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/215 b/tests/qemu-iotests/215 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/215 +++ b/tests/qemu-iotests/215 @@ -XXX,XX +XXX,XX @@ esac _cleanup() { _cleanup_test_img - rm -f "$TEST_WRAP" + _rm_test_img "$TEST_WRAP" rm -f "$BLKDBG_CONF" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/225 b/tests/qemu-iotests/225 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/225 +++ b/tests/qemu-iotests/225 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.not_base" + _rm_test_img "$TEST_IMG.not_base" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/229 b/tests/qemu-iotests/229 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/229 +++ b/tests/qemu-iotests/229 @@ -XXX,XX +XXX,XX @@ _cleanup() { _cleanup_qemu _cleanup_test_img - rm -f "$TEST_IMG" "$DEST_IMG" + _rm_test_img "$TEST_IMG" + _rm_test_img "$DEST_IMG" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/232 b/tests/qemu-iotests/232 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/232 +++ b/tests/qemu-iotests/232 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f $TEST_IMG.[01234] + for img in "$TEST_IMG".[01234]; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/243 b/tests/qemu-iotests/243 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/243 +++ b/tests/qemu-iotests/243 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f $TEST_IMG.data + _rm_test_img "$TEST_IMG.data" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/244 +++ b/tests/qemu-iotests/244 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f $TEST_IMG.data - rm -f $TEST_IMG.src + _rm_test_img "$TEST_IMG.data" + _rm_test_img "$TEST_IMG.src" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/247 b/tests/qemu-iotests/247 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/247 +++ b/tests/qemu-iotests/247 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f $TEST_IMG.[01234] + for img in "$TEST_IMG".[01234]; do + _rm_test_img "$img" + done } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/249 b/tests/qemu-iotests/249 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/249 +++ b/tests/qemu-iotests/249 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.base" - rm -f "$TEST_IMG.int" + _rm_test_img "$TEST_IMG.base" + _rm_test_img "$TEST_IMG.int" } trap "_cleanup; exit \$status" 0 1 2 3 15 diff --git a/tests/qemu-iotests/252 b/tests/qemu-iotests/252 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/252 +++ b/tests/qemu-iotests/252 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _cleanup() { _cleanup_test_img - rm -f "$TEST_IMG.base_new" + _rm_test_img "$TEST_IMG.base_new" } trap "_cleanup; exit \$status" 0 1 2 3 15 -- 2.24.1 This will not work with external data files, so try to get tests working without it as far as possible. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-17-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/063 | 12 ++++-------- tests/qemu-iotests/063.out | 3 ++- tests/qemu-iotests/085 | 9 +++------ tests/qemu-iotests/085.out | 8 ++++---- 4 files changed, 13 insertions(+), 19 deletions(-) diff --git a/tests/qemu-iotests/063 b/tests/qemu-iotests/063 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/063 +++ b/tests/qemu-iotests/063 @@ -XXX,XX +XXX,XX @@ _unsupported_imgopts "subformat=monolithicFlat" \ _make_test_img 4M echo "== Testing conversion with -n fails with no target file ==" -# check .orig file does not exist -rm -f "$TEST_IMG.orig" if $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG" "$TEST_IMG.orig" >/dev/null 2>&1; then exit 1 fi echo "== Testing conversion with -n succeeds with a target file ==" -rm -f "$TEST_IMG.orig" -cp "$TEST_IMG" "$TEST_IMG.orig" +_rm_test_img "$TEST_IMG.orig" +TEST_IMG="$TEST_IMG.orig" _make_test_img 4M if ! $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG" "$TEST_IMG.orig" ; then exit 1 fi @@ -XXX,XX +XXX,XX @@ fi _check_test_img echo "== Testing conversion to a smaller file fails ==" -rm -f "$TEST_IMG.orig" -mv "$TEST_IMG" "$TEST_IMG.orig" -_make_test_img 2M -if $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG.orig" "$TEST_IMG" >/dev/null 2>&1; then +TEST_IMG="$TEST_IMG.target" _make_test_img 2M +if $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n "$TEST_IMG" "$TEST_IMG.target" >/dev/null 2>&1; then exit 1 fi diff --git a/tests/qemu-iotests/063.out b/tests/qemu-iotests/063.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/063.out +++ b/tests/qemu-iotests/063.out @@ -XXX,XX +XXX,XX @@ QA output created by 063 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=4194304 == Testing conversion with -n fails with no target file == == Testing conversion with -n succeeds with a target file == +Formatting 'TEST_DIR/t.IMGFMT.orig', fmt=IMGFMT size=4194304 == Testing conversion to raw is the same after conversion with -n == == Testing conversion back to original format == No errors were found on the image. == Testing conversion to a smaller file fails == -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2097152 +Formatting 'TEST_DIR/t.IMGFMT.target', fmt=IMGFMT size=2097152 == Regression testing for copy offloading bug == Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 Formatting 'TEST_DIR/t.IMGFMT.target', fmt=IMGFMT size=1048576 diff --git a/tests/qemu-iotests/085 b/tests/qemu-iotests/085 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/085 +++ b/tests/qemu-iotests/085 @@ -XXX,XX +XXX,XX @@ add_snapshot_image() { base_image="${TEST_DIR}/$((${1}-1))-${snapshot_virt0}" snapshot_file="${TEST_DIR}/${1}-${snapshot_virt0}" - _make_test_img -u -b "${base_image}" "$size" - mv "${TEST_IMG}" "${snapshot_file}" + TEST_IMG=$snapshot_file _make_test_img -u -b "${base_image}" "$size" do_blockdev_add "$1" "'backing': null, " "${snapshot_file}" } @@ -XXX,XX +XXX,XX @@ blockdev_snapshot() size=128M -_make_test_img $size -mv "${TEST_IMG}" "${TEST_IMG}.1" -_make_test_img $size -mv "${TEST_IMG}" "${TEST_IMG}.2" +TEST_IMG="$TEST_IMG.1" _make_test_img $size +TEST_IMG="$TEST_IMG.2" _make_test_img $size echo echo === Running QEMU === diff --git a/tests/qemu-iotests/085.out b/tests/qemu-iotests/085.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/085.out +++ b/tests/qemu-iotests/085.out @@ -XXX,XX +XXX,XX @@ QA output created by 085 -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 +Formatting 'TEST_DIR/t.IMGFMT.1', fmt=IMGFMT size=134217728 +Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=134217728 === Running QEMU === @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 size=134217728 backing_fil === Create a couple of snapshots using blockdev-snapshot === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/10-snapshot-v0.IMGFMT +Formatting 'TEST_DIR/11-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/10-snapshot-v0.IMGFMT { 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_11', 'backing': null, 'file': { 'driver': 'file', 'filename': 'TEST_DIR/11-snapshot-v0.IMGFMT', 'node-name': 'file_11' } } } {"return": {}} { 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_11' } } {"return": {}} -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/11-snapshot-v0.IMGFMT +Formatting 'TEST_DIR/12-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/11-snapshot-v0.IMGFMT { 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_12', 'backing': null, 'file': { 'driver': 'file', 'filename': 'TEST_DIR/12-snapshot-v0.IMGFMT', 'node-name': 'file_12' } } } {"return": {}} { 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_12' } } -- 2.24.1 The image end offset as reported by qemu-img check is different when using an external data file; we do not care about its value here, so we can just filter it. Incidentally, common.rc already has _check_test_img for us which does exactly that. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-18-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/091 | 2 +- tests/qemu-iotests/091.out | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/tests/qemu-iotests/091 b/tests/qemu-iotests/091 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/091 +++ b/tests/qemu-iotests/091 @@ -XXX,XX +XXX,XX @@ echo "Check image pattern" ${QEMU_IO} -c "read -P 0x22 0 4M" "${TEST_IMG}" | _filter_testdir | _filter_qemu_io echo "Running 'qemu-img check -r all \$TEST_IMG'" -"${QEMU_IMG}" check -r all "${TEST_IMG}" 2>&1 | _filter_testdir | _filter_qemu +_check_test_img -r all echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/091.out b/tests/qemu-iotests/091.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/091.out +++ b/tests/qemu-iotests/091.out @@ -XXX,XX +XXX,XX @@ read 4194304/4194304 bytes at offset 0 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Running 'qemu-img check -r all $TEST_IMG' No errors were found on the image. -80/16384 = 0.49% allocated, 0.00% fragmented, 0.00% compressed clusters -Image end offset: 5570560 *** done -- 2.24.1 The only difference is that the json:{} filename of the image looks different. We actually do not care about that filename in this test, we are only interested in (1) that there is a json:{} filename, and (2) whether the backing filename can be constructed. So just filter out the json:{} data, thus making this test pass both with and without data_file. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-19-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/110 | 7 +++++-- tests/qemu-iotests/110.out | 4 ++-- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/tests/qemu-iotests/110 b/tests/qemu-iotests/110 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/110 +++ b/tests/qemu-iotests/110 @@ -XXX,XX +XXX,XX @@ echo # Across blkdebug without a config file, you cannot reconstruct filenames, so # qemu is incapable of knowing the directory of the top image from the filename # alone. However, using bdrv_dirname(), it should still work. +# (Filter out the json:{} filename so this test works with external data files) TEST_IMG="json:{ 'driver': '$IMGFMT', 'file': { @@ -XXX,XX +XXX,XX @@ TEST_IMG="json:{ } ] } -}" _img_info | _filter_img_info | grep -v 'backing file format' +}" _img_info | _filter_img_info | grep -v 'backing file format' \ + | _filter_json_filename echo echo '=== Backing name is always relative to the backed image ===' @@ -XXX,XX +XXX,XX @@ TEST_IMG="json:{ } ] } -}" _img_info | _filter_img_info | grep -v 'backing file format' +}" _img_info | _filter_img_info | grep -v 'backing file format' \ + | _filter_json_filename # success, all done diff --git a/tests/qemu-iotests/110.out b/tests/qemu-iotests/110.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/110.out +++ b/tests/qemu-iotests/110.out @@ -XXX,XX +XXX,XX @@ backing file: t.IMGFMT.base (actual path: TEST_DIR/t.IMGFMT.base) === Non-reconstructable filename === -image: json:{"driver": "IMGFMT", "file": {"set-state.0.event": "read_aio", "image": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, "driver": "blkdebug", "set-state.0.new_state": 42}} +image: json:{ /* filtered */ } file format: IMGFMT virtual size: 64 MiB (67108864 bytes) backing file: t.IMGFMT.base (actual path: TEST_DIR/t.IMGFMT.base) @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file=t.IMGFMT.b === Nodes without a common directory === -image: json:{"driver": "IMGFMT", "file": {"children": [{"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, {"driver": "file", "filename": "TEST_DIR/t.IMGFMT.copy"}], "driver": "quorum", "vote-threshold": 1}} +image: json:{ /* filtered */ } file format: IMGFMT virtual size: 64 MiB (67108864 bytes) backing file: t.IMGFMT.base (cannot determine actual path) -- 2.24.1 When using an external data file, there are no refcounts for data clusters. We thus have to adjust the corruption test in this patch to not be based around a data cluster allocation, but the L2 table allocation (L2 tables are still refcounted with external data files). Furthermore, we should not print qcow2.py's list of incompatible features because it differs depending on whether there is an external data file or not. With those two changes, the test will work both with and without external data files (once that options works with the iotests at all). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-20-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/137 | 15 +++++++++++---- tests/qemu-iotests/137.out | 6 ++---- 2 files changed, 13 insertions(+), 8 deletions(-) diff --git a/tests/qemu-iotests/137 b/tests/qemu-iotests/137 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/137 +++ b/tests/qemu-iotests/137 @@ -XXX,XX +XXX,XX @@ $QEMU_IO \ "$TEST_IMG" 2>&1 | _filter_qemu_io # The dirty bit must not be set -$PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features +# (Filter the external data file bit) +if $PYTHON qcow2.py "$TEST_IMG" dump-header | grep incompatible_features \ + | grep -q '\<0\>' +then + echo 'ERROR: Dirty bit set' +else + echo 'OK: Dirty bit not set' +fi # Similarly we can test whether corruption detection has been enabled: -# Create L1/L2, overwrite first entry in refcount block, allocate something. +# Create L1, overwrite refcounts, force allocation of L2 by writing +# data. # Disabling the checks should fail, so the corruption must be detected. _make_test_img 64M -$QEMU_IO -c "write 0 64k" "$TEST_IMG" | _filter_qemu_io -poke_file "$TEST_IMG" "$((0x20000))" "\x00\x00" +poke_file "$TEST_IMG" "$((0x20000))" "\x00\x00\x00\x00\x00\x00\x00\x00" $QEMU_IO \ -c "reopen -o overlap-check=none,lazy-refcounts=42" \ -c "write 64k 64k" \ diff --git a/tests/qemu-iotests/137.out b/tests/qemu-iotests/137.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/137.out +++ b/tests/qemu-iotests/137.out @@ -XXX,XX +XXX,XX @@ qemu-io: Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ./common.rc: Killed ( VALGRIND_QEMU="${VALGRIND_QEMU_IO}" _qemu_proc_exec "${VALGRIND_LOGFILE}" "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" ) -incompatible_features [] +OK: Dirty bit not set Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 -wrote 65536/65536 bytes at offset 0 -64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-io: Parameter 'lazy-refcounts' expects 'on' or 'off' -qcow2: Marking image as corrupt: Preventing invalid write on metadata (overlaps with qcow2_header); further corruption events will be suppressed +qcow2: Marking image as corrupt: Preventing invalid allocation of L2 table at offset 0; further corruption events will be suppressed write failed: Input/output error *** done -- 2.24.1 We do not care about the json:{} filenames here, so we can just filter them out and thus make the test work both with and without external data files. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-21-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/198 | 6 ++++-- tests/qemu-iotests/198.out | 4 ++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/tests/qemu-iotests/198 b/tests/qemu-iotests/198 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/198 +++ b/tests/qemu-iotests/198 @@ -XXX,XX +XXX,XX @@ echo echo "== checking image base ==" $QEMU_IMG info --image-opts $IMGSPECBASE | _filter_img_info --format-specific \ | sed -e "/^disk size:/ D" -e '/refcount bits:/ D' -e '/compat:/ D' \ - -e '/lazy refcounts:/ D' -e '/corrupt:/ D' + -e '/lazy refcounts:/ D' -e '/corrupt:/ D' -e '/^\s*data file/ D' \ + | _filter_json_filename echo echo "== checking image layer ==" $QEMU_IMG info --image-opts $IMGSPECLAYER | _filter_img_info --format-specific \ | sed -e "/^disk size:/ D" -e '/refcount bits:/ D' -e '/compat:/ D' \ - -e '/lazy refcounts:/ D' -e '/corrupt:/ D' + -e '/lazy refcounts:/ D' -e '/corrupt:/ D' -e '/^\s*data file/ D' \ + | _filter_json_filename # success, all done diff --git a/tests/qemu-iotests/198.out b/tests/qemu-iotests/198.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/198.out +++ b/tests/qemu-iotests/198.out @@ -XXX,XX +XXX,XX @@ read 16777216/16777216 bytes at offset 0 16 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) == checking image base == -image: json:{"encrypt.key-secret": "sec0", "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT.base"}} +image: json:{ /* filtered */ } file format: IMGFMT virtual size: 16 MiB (16777216 bytes) Format specific information: @@ -XXX,XX +XXX,XX @@ Format specific information: master key iters: 1024 == checking image layer == -image: json:{"encrypt.key-secret": "sec1", "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}} +image: json:{ /* filtered */ } file format: IMGFMT virtual size: 16 MiB (16777216 bytes) backing file: TEST_DIR/t.IMGFMT.base -- 2.24.1 Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20191107163708.833192-22-mreitz@redhat.com [mreitz: Also disable 273] Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/007 | 5 +++-- tests/qemu-iotests/014 | 2 ++ tests/qemu-iotests/015 | 5 +++-- tests/qemu-iotests/026 | 5 ++++- tests/qemu-iotests/029 | 5 +++-- tests/qemu-iotests/031 | 6 +++--- tests/qemu-iotests/036 | 5 +++-- tests/qemu-iotests/039 | 3 +++ tests/qemu-iotests/046 | 2 ++ tests/qemu-iotests/048 | 2 ++ tests/qemu-iotests/051 | 5 +++-- tests/qemu-iotests/058 | 5 +++-- tests/qemu-iotests/060 | 6 ++++-- tests/qemu-iotests/061 | 6 ++++-- tests/qemu-iotests/062 | 2 +- tests/qemu-iotests/066 | 4 +++- tests/qemu-iotests/067 | 6 ++++-- tests/qemu-iotests/068 | 5 +++-- tests/qemu-iotests/071 | 3 +++ tests/qemu-iotests/073 | 4 ++++ tests/qemu-iotests/074 | 2 ++ tests/qemu-iotests/080 | 5 +++-- tests/qemu-iotests/090 | 2 ++ tests/qemu-iotests/098 | 6 ++++-- tests/qemu-iotests/099 | 3 ++- tests/qemu-iotests/103 | 5 +++-- tests/qemu-iotests/108 | 6 ++++-- tests/qemu-iotests/112 | 5 +++-- tests/qemu-iotests/114 | 2 ++ tests/qemu-iotests/121 | 3 +++ tests/qemu-iotests/138 | 3 +++ tests/qemu-iotests/156 | 2 ++ tests/qemu-iotests/176 | 7 +++++-- tests/qemu-iotests/191 | 2 ++ tests/qemu-iotests/201 | 6 +++--- tests/qemu-iotests/214 | 3 ++- tests/qemu-iotests/217 | 3 ++- tests/qemu-iotests/220 | 5 +++-- tests/qemu-iotests/243 | 6 ++++-- tests/qemu-iotests/244 | 5 +++-- tests/qemu-iotests/250 | 2 ++ tests/qemu-iotests/261 | 3 ++- tests/qemu-iotests/267 | 5 +++-- tests/qemu-iotests/273 | 3 +++ 44 files changed, 127 insertions(+), 53 deletions(-) diff --git a/tests/qemu-iotests/007 b/tests/qemu-iotests/007 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/007 +++ b/tests/qemu-iotests/007 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto generic # refcount_bits must be at least 4 so we can create ten internal snapshots -# (1 bit supports none, 2 bits support two, 4 bits support 14) -_unsupported_imgopts 'refcount_bits=\(1\|2\)[^0-9]' +# (1 bit supports none, 2 bits support two, 4 bits support 14); +# snapshot are generally impossible with external data files +_unsupported_imgopts 'refcount_bits=\(1\|2\)[^0-9]' data_file echo echo "creating image" diff --git a/tests/qemu-iotests/014 b/tests/qemu-iotests/014 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/014 +++ b/tests/qemu-iotests/014 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# Compression and snapshots do not work with external data files +_unsupported_imgopts data_file TEST_OFFSETS="0 4294967296" TEST_OPS="writev read write readv" diff --git a/tests/qemu-iotests/015 b/tests/qemu-iotests/015 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/015 +++ b/tests/qemu-iotests/015 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # actually any format that supports snapshots _supported_fmt qcow2 _supported_proto generic -# Internal snapshots are (currently) impossible with refcount_bits=1 -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file echo echo "creating image" diff --git a/tests/qemu-iotests/026 b/tests/qemu-iotests/026 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/026 +++ b/tests/qemu-iotests/026 @@ -XXX,XX +XXX,XX @@ _supported_cache_modes writethrough none # 32 and 64 bits do not work either, however, due to different leaked cluster # count on error. # Thus, the only remaining option is refcount_bits=16. -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# +# As for data_file, none of the refcount tests can work for it. +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' \ + data_file echo "Errors while writing 128 kB" echo diff --git a/tests/qemu-iotests/029 b/tests/qemu-iotests/029 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/029 +++ b/tests/qemu-iotests/029 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto generic _unsupported_proto vxhs -# Internal snapshots are (currently) impossible with refcount_bits=1 -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file offset_size=24 offset_l1_size=36 diff --git a/tests/qemu-iotests/031 b/tests/qemu-iotests/031 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/031 +++ b/tests/qemu-iotests/031 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file -# We want to test compat=0.10, which does not support refcount widths -# other than 16 -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# We want to test compat=0.10, which does not support external data +# files or refcount widths other than 16 +_unsupported_imgopts data_file 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' CLUSTER_SIZE=65536 diff --git a/tests/qemu-iotests/036 b/tests/qemu-iotests/036 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/036 +++ b/tests/qemu-iotests/036 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto file -# Only qcow2v3 and later supports feature bits -_unsupported_imgopts 'compat=0.10' +# Only qcow2v3 and later supports feature bits; +# qcow2.py does not support external data files +_unsupported_imgopts 'compat=0.10' data_file echo echo === Image with unknown incompatible feature bit === diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/039 +++ b/tests/qemu-iotests/039 @@ -XXX,XX +XXX,XX @@ _supported_proto file _supported_os Linux _default_cache_mode writethrough _supported_cache_modes writethrough +# Some of these test cases expect no external data file so that all +# clusters are part of the qcow2 image and refcounted +_unsupported_imgopts data_file size=128M diff --git a/tests/qemu-iotests/046 b/tests/qemu-iotests/046 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/046 +++ b/tests/qemu-iotests/046 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file +# data_file does not support compressed clusters +_unsupported_imgopts data_file CLUSTER_SIZE=64k size=128M diff --git a/tests/qemu-iotests/048 b/tests/qemu-iotests/048 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/048 +++ b/tests/qemu-iotests/048 @@ -XXX,XX +XXX,XX @@ _compare() _supported_fmt raw qcow2 qed luks _supported_proto file _supported_os Linux +# Using 'cp' is incompatible with external data files +_unsupported_imgopts data_file # Remove once all tests are fixed to use TEST_IMG_FILE # correctly and common.rc sets it unconditionally diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/051 +++ b/tests/qemu-iotests/051 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file # A compat=0.10 image is created in this test which does not support anything -# other than refcount_bits=16 -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# other than refcount_bits=16; +# it also will not support an external data file +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file _require_drivers nbd do_run_qemu() diff --git a/tests/qemu-iotests/058 b/tests/qemu-iotests/058 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/058 +++ b/tests/qemu-iotests/058 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow2 _supported_proto file _supported_os Linux _require_command QEMU_NBD -# Internal snapshots are (currently) impossible with refcount_bits=1 -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file nbd_snapshot_img="nbd:unix:$nbd_unix_socket" diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/060 +++ b/tests/qemu-iotests/060 @@ -XXX,XX +XXX,XX @@ _filter_io_error() _supported_fmt qcow2 _supported_proto file _supported_os Linux -# These tests only work for compat=1.1 images with refcount_bits=16 -_unsupported_imgopts 'compat=0.10' 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# These tests only work for compat=1.1 images without an external +# data file with refcount_bits=16 +_unsupported_imgopts 'compat=0.10' data_file \ + 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' # The repair process will create a large file - so check for availability first _require_large_file 64G diff --git a/tests/qemu-iotests/061 b/tests/qemu-iotests/061 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/061 +++ b/tests/qemu-iotests/061 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow2 _supported_proto file _supported_os Linux # Conversion between different compat versions can only really work -# with refcount_bits=16 -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# with refcount_bits=16; +# we have explicit tests for data_file here, but the whole test does +# not work with it +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file echo echo "=== Testing version downgrade with zero expansion ===" diff --git a/tests/qemu-iotests/062 b/tests/qemu-iotests/062 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/062 +++ b/tests/qemu-iotests/062 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto generic # We need zero clusters and snapshots -_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' +_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file IMG_SIZE=64M diff --git a/tests/qemu-iotests/066 b/tests/qemu-iotests/066 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/066 +++ b/tests/qemu-iotests/066 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto generic # We need zero clusters and snapshots -_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' +# (TODO: Consider splitting the snapshot part into a separate test +# file, so this one runs with refcount_bits=1 and data_file) +_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file # Intentionally create an unaligned image IMG_SIZE=$((64 * 1024 * 1024 + 512)) diff --git a/tests/qemu-iotests/067 b/tests/qemu-iotests/067 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/067 +++ b/tests/qemu-iotests/067 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! _supported_fmt qcow2 _supported_proto file -# Because anything other than 16 would change the output of query-block -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# Because anything other than 16 would change the output of query-block, +# and external data files would change the output of +# query-named-block-nodes +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file do_run_qemu() { diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/068 +++ b/tests/qemu-iotests/068 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This tests qcow2-specific low-level functionality _supported_fmt qcow2 _supported_proto generic -# Internal snapshots are (currently) impossible with refcount_bits=1 -_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'compat=0.10' 'refcount_bits=1[^0-9]' data_file IMG_SIZE=128K diff --git a/tests/qemu-iotests/071 b/tests/qemu-iotests/071 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/071 +++ b/tests/qemu-iotests/071 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _require_drivers blkdebug blkverify +# blkdebug can only inject errors on bs->file, not on the data_file, +# so thie test does not work with external data files +_unsupported_imgopts data_file do_run_qemu() { diff --git a/tests/qemu-iotests/073 b/tests/qemu-iotests/073 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/073 +++ b/tests/qemu-iotests/073 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto generic _unsupported_proto vxhs +# External data files do not support compressed clusters +# (TODO: Consider writing a version for external data files that does +# not test compressed clusters) +_unsupported_imgopts data_file CLUSTER_SIZE=64k size=128M diff --git a/tests/qemu-iotests/074 b/tests/qemu-iotests/074 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/074 +++ b/tests/qemu-iotests/074 @@ -XXX,XX +XXX,XX @@ _compare() _supported_fmt qcow2 _supported_proto file _supported_os Linux +# blkdebug can only inject errors on bs->file +_unsupported_imgopts data_file # Setup test basic parameters TEST_IMG2=$TEST_IMG.2 diff --git a/tests/qemu-iotests/080 b/tests/qemu-iotests/080 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/080 +++ b/tests/qemu-iotests/080 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -# - Internal snapshots are (currently) impossible with refcount_bits=1 +# - Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files # - This is generally a test for compat=1.1 images -_unsupported_imgopts 'refcount_bits=1[^0-9]' 'compat=0.10' +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file 'compat=0.10' header_size=104 diff --git a/tests/qemu-iotests/090 b/tests/qemu-iotests/090 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/090 +++ b/tests/qemu-iotests/090 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file nfs +# External data files do not support compressed clusters +_unsupported_imgopts data_file IMG_SIZE=128K diff --git a/tests/qemu-iotests/098 b/tests/qemu-iotests/098 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/098 +++ b/tests/qemu-iotests/098 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file -# The code path we want to test here only works for compat=1.1 images -_unsupported_imgopts 'compat=0.10' +# The code path we want to test here only works for compat=1.1 images; +# blkdebug can only inject errors on bs->file, so external data files +# do not work with this test +_unsupported_imgopts 'compat=0.10' data_file for event in l1_update empty_image_prepare reftable_update refblock_alloc; do diff --git a/tests/qemu-iotests/099 b/tests/qemu-iotests/099 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/099 +++ b/tests/qemu-iotests/099 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow qcow2 qed vdi vhdx vmdk vpc _supported_proto file _supported_os Linux _require_drivers blkdebug blkverify +# data_file would change the json:{} filenames _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" data_file do_run_qemu() { diff --git a/tests/qemu-iotests/103 b/tests/qemu-iotests/103 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/103 +++ b/tests/qemu-iotests/103 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file nfs -# Internal snapshots are (currently) impossible with refcount_bits=1 -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file IMG_SIZE=64K diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/108 +++ b/tests/qemu-iotests/108 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -# This test directly modifies a refblock so it relies on refcount_bits being 16 -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# This test directly modifies a refblock so it relies on refcount_bits being 16; +# and the low-level modification it performs are not tuned for external data +# files +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file echo echo '=== Repairing an image without any refcount table ===' diff --git a/tests/qemu-iotests/112 b/tests/qemu-iotests/112 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/112 +++ b/tests/qemu-iotests/112 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file # This test will set refcount_bits on its own which would conflict with the -# manual setting; compat will be overridden as well -_unsupported_imgopts refcount_bits 'compat=0.10' +# manual setting; compat will be overridden as well; +# and external data files do not work well with our refcount testing +_unsupported_imgopts refcount_bits 'compat=0.10' data_file print_refcount_bits() { diff --git a/tests/qemu-iotests/114 b/tests/qemu-iotests/114 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/114 +++ b/tests/qemu-iotests/114 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto generic _unsupported_proto vxhs +# qcow2.py does not work too well with external data files +_unsupported_imgopts data_file TEST_IMG="$TEST_IMG.base" _make_test_img 64M diff --git a/tests/qemu-iotests/121 b/tests/qemu-iotests/121 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/121 +++ b/tests/qemu-iotests/121 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# Refcount structures are used much differently with external data +# files +_unsupported_imgopts data_file echo echo '=== New refcount structures may not conflict with existing structures ===' diff --git a/tests/qemu-iotests/138 b/tests/qemu-iotests/138 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/138 +++ b/tests/qemu-iotests/138 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# With an external data file, data clusters are not refcounted +# (and so qemu-img check does not check their refcount) +_unsupported_imgopts data_file echo echo '=== Check on an image with a multiple of 2^32 clusters ===' diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/156 +++ b/tests/qemu-iotests/156 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 qed _supported_proto generic _unsupported_proto vxhs +# Copying files around with cp does not work with external data files +_unsupported_imgopts data_file # Create source disk TEST_IMG="$TEST_IMG.backing" _make_test_img 1M diff --git a/tests/qemu-iotests/176 b/tests/qemu-iotests/176 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/176 +++ b/tests/qemu-iotests/176 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -# Persistent dirty bitmaps require compat=1.1 -_unsupported_imgopts 'compat=0.10' +# Persistent dirty bitmaps require compat=1.1; +# Internal snapshots forbid using an external data file +# (they work with refcount_bits=1 here, though, because there actually +# is no data when creating the snapshot) +_unsupported_imgopts 'compat=0.10' data_file run_qemu() { diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/191 +++ b/tests/qemu-iotests/191 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file +# An external data file would change the query-named-block-nodes output +_unsupported_imgopts data_file size=64M diff --git a/tests/qemu-iotests/201 b/tests/qemu-iotests/201 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/201 +++ b/tests/qemu-iotests/201 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow2 _supported_proto generic _supported_os Linux -# Internal snapshots are (currently) impossible with refcount_bits=1 -# This was taken from test 080 -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file size=64M _make_test_img $size diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/214 +++ b/tests/qemu-iotests/214 @@ -XXX,XX +XXX,XX @@ _supported_proto file # Repairing the corrupted image requires qemu-img check to store a # refcount up to 3, which requires at least two refcount bits. -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# External data files do not support compressed clusters. +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file echo diff --git a/tests/qemu-iotests/217 b/tests/qemu-iotests/217 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/217 +++ b/tests/qemu-iotests/217 @@ -XXX,XX +XXX,XX @@ _supported_proto file # This test needs clusters with at least a refcount of 2 so that # OFLAG_COPIED is not set. refcount_bits=1 is therefore unsupported. -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# (As are external data files.) +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file echo echo '=== Simulating an I/O error during snapshot deletion ===' diff --git a/tests/qemu-iotests/220 b/tests/qemu-iotests/220 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/220 +++ b/tests/qemu-iotests/220 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -# To use a different refcount width but 16 bits we need compat=1.1 -_unsupported_imgopts 'compat=0.10' +# To use a different refcount width but 16 bits we need compat=1.1, +# and external data files do not support compressed clusters. +_unsupported_imgopts 'compat=0.10' data_file echo "== Creating huge file ==" diff --git a/tests/qemu-iotests/243 b/tests/qemu-iotests/243 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/243 +++ b/tests/qemu-iotests/243 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -# External data files do not work with compat=0.10 -_unsupported_imgopts 'compat=0.10' +# External data files do not work with compat=0.10, and because there +# is an explicit case for external data files here, we cannot allow +# the user to specify whether to use one +_unsupported_imgopts 'compat=0.10' data_file for mode in off metadata falloc full; do diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/244 +++ b/tests/qemu-iotests/244 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -# External data files do not work with compat=0.10 -_unsupported_imgopts 'compat=0.10' +# External data files do not work with compat=0.10, and because we use +# our own external data file, we cannot let the user specify one +_unsupported_imgopts 'compat=0.10' data_file echo echo "=== Create and open image with external data file ===" diff --git a/tests/qemu-iotests/250 b/tests/qemu-iotests/250 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/250 +++ b/tests/qemu-iotests/250 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# This test does not make much sense with external data files +_unsupported_imgopts data_file # This test checks that qcow2_process_discards does not truncate a discard # request > 2G. diff --git a/tests/qemu-iotests/261 b/tests/qemu-iotests/261 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/261 +++ b/tests/qemu-iotests/261 @@ -XXX,XX +XXX,XX @@ _supported_os Linux # (1) We create a v2 image that supports nothing but refcount_bits=16 # (2) We do some refcount management on our own which expects # refcount_bits=16 -_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' +# As for data files, they do not support snapshots at all. +_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file # Parameters: # $1: image filename diff --git a/tests/qemu-iotests/267 b/tests/qemu-iotests/267 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/267 +++ b/tests/qemu-iotests/267 @@ -XXX,XX +XXX,XX @@ _supported_proto file _supported_os Linux _require_drivers copy-on-read -# Internal snapshots are (currently) impossible with refcount_bits=1 -_unsupported_imgopts 'refcount_bits=1[^0-9]' +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file do_run_qemu() { diff --git a/tests/qemu-iotests/273 b/tests/qemu-iotests/273 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/273 +++ b/tests/qemu-iotests/273 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux +# External data files would add nodes to the block graph, so it would +# not match the reference output +_unsupported_imgopts data_file do_run_qemu() { -- 2.24.1 The problem with allowing the data_file option is that you want to use a different data file per image used in the test. Therefore, we need to allow patterns like -o data_file='$TEST_IMG.data_file'. Then, we need to filter it out from qemu-img map, qemu-img create, and remove the data file in _rm_test_img. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-id: 20191107163708.833192-23-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/common.filter | 23 +++++++++++++++++++++-- tests/qemu-iotests/common.rc | 22 +++++++++++++++++++++- 2 files changed, 42 insertions(+), 3 deletions(-) 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_actual_image_size() # replace driver-specific options in the "Formatting..." line _filter_img_create() { - $SED -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \ + data_file_filter=() + if data_file=$(_get_data_file "$TEST_IMG"); then + data_file_filter=(-e "s# data_file=$data_file##") + fi + + $SED "${data_file_filter[@]}" \ + -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \ -e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \ -e "s#$TEST_DIR#TEST_DIR#g" \ -e "s#$SOCK_DIR#SOCK_DIR#g" \ @@ -XXX,XX +XXX,XX @@ _filter_img_info() # human and json output _filter_qemu_img_map() { + # Assuming the data_file value in $IMGOPTS contains a '$TEST_IMG', + # create a filter that replaces the data file name by $TEST_IMG. + # Example: + # In $IMGOPTS: 'data_file=$TEST_IMG.data_file' + # Then data_file_pattern == '\(.*\).data_file' + # And data_file_filter == -e 's#\(.*\).data_file#\1# + data_file_filter=() + if data_file_pattern=$(_get_data_file '\\(.*\\)'); then + data_file_filter=(-e "s#$data_file_pattern#\\1#") + fi + $SED -e 's/\([0-9a-fx]* *[0-9a-fx]* *\)[0-9a-fx]* */\1/g' \ -e 's/"offset": [0-9]\+/"offset": OFFSET/g' \ - -e 's/Mapped to *//' | _filter_testdir | _filter_imgfmt + -e 's/Mapped to *//' \ + "${data_file_filter[@]}" \ + | _filter_testdir | _filter_imgfmt } _filter_nbd() diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _stop_nbd_server() fi } +# Gets the data_file value from IMGOPTS and replaces the '$TEST_IMG' +# pattern by '$1' +# Caution: The replacement is done with sed, so $1 must be escaped +# properly. (The delimiter is '#'.) +_get_data_file() +{ + if ! echo "$IMGOPTS" | grep -q 'data_file='; then + return 1 + fi + + echo "$IMGOPTS" | sed -e 's/.*data_file=\([^,]*\).*/\1/' \ + | sed -e "s#\\\$TEST_IMG#$1#" +} + _make_test_img() { # extra qemu-img options can be added by tests @@ -XXX,XX +XXX,XX @@ _make_test_img() fi if [ -n "$IMGOPTS" ]; then - optstr=$(_optstr_add "$optstr" "$IMGOPTS") + imgopts_expanded=$(echo "$IMGOPTS" | sed -e "s#\\\$TEST_IMG#$img_name#") + optstr=$(_optstr_add "$optstr" "$imgopts_expanded") fi if [ -n "$IMGKEYSECRET" ]; then object_options="--object secret,id=keysec0,data=$IMGKEYSECRET" @@ -XXX,XX +XXX,XX @@ _rm_test_img() # Remove all the extents for vmdk "$QEMU_IMG" info "$img" 2>/dev/null | grep 'filename:' | cut -f 2 -d: \ | xargs -I {} rm -f "{}" + elif [ "$IMGFMT" = "qcow2" ]; then + # Remove external data file + if data_file=$(_get_data_file "$img"); then + rm -f "$data_file" + fi fi rm -f "$img" } -- 2.24.1 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Allow writing all the data compressed through the filter driver. The written data will be aligned by the cluster size. Based on the QEMU current implementation, that data can be written to unallocated clusters only. May be used for a backup job. Suggested-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 1575288906-551879-2-git-send-email-andrey.shinkevich@virtuozzo.com [mreitz: Replace NULL bdrv_get_format_name() by "(no format)"] Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/Makefile.objs | 1 + block/filter-compress.c | 168 ++++++++++++++++++++++++++++++++++++++++ qapi/block-core.json | 10 ++- 3 files changed, 175 insertions(+), 4 deletions(-) create mode 100644 block/filter-compress.c diff --git a/block/Makefile.objs b/block/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/block/Makefile.objs +++ b/block/Makefile.objs @@ -XXX,XX +XXX,XX @@ block-obj-y += crypto.o block-obj-y += aio_task.o block-obj-y += backup-top.o +block-obj-y += filter-compress.o common-obj-y += stream.o diff --git a/block/filter-compress.c b/block/filter-compress.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/filter-compress.c @@ -XXX,XX +XXX,XX @@ +/* + * Compress filter block driver + * + * Copyright (c) 2019 Virtuozzo International GmbH + * + * Author: + * Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> + * (based on block/copy-on-read.c by Max Reitz) + * + * 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 or + * (at your option) any later version of the License. + * + * 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/>. + */ + +#include "qemu/osdep.h" +#include "block/block_int.h" +#include "qemu/module.h" +#include "qapi/error.h" + + +static int compress_open(BlockDriverState *bs, QDict *options, int flags, + Error **errp) +{ + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false, + errp); + if (!bs->file) { + return -EINVAL; + } + + if (!bs->file->bs->drv || !block_driver_can_compress(bs->file->bs->drv)) { + error_setg(errp, + "Compression is not supported for underlying format: %s", + bdrv_get_format_name(bs->file->bs) ?: "(no format)"); + + return -ENOTSUP; + } + + bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED | + (BDRV_REQ_FUA & bs->file->bs->supported_write_flags); + + bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED | + ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & + bs->file->bs->supported_zero_flags); + + return 0; +} + + +static int64_t compress_getlength(BlockDriverState *bs) +{ + return bdrv_getlength(bs->file->bs); +} + + +static int coroutine_fn compress_co_preadv_part(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, + size_t qiov_offset, + int flags) +{ + return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset, + flags); +} + + +static int coroutine_fn compress_co_pwritev_part(BlockDriverState *bs, + uint64_t offset, + uint64_t bytes, + QEMUIOVector *qiov, + size_t qiov_offset, int flags) +{ + return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset, + flags | BDRV_REQ_WRITE_COMPRESSED); +} + + +static int coroutine_fn compress_co_pwrite_zeroes(BlockDriverState *bs, + int64_t offset, int bytes, + BdrvRequestFlags flags) +{ + return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags); +} + + +static int coroutine_fn compress_co_pdiscard(BlockDriverState *bs, + int64_t offset, int bytes) +{ + return bdrv_co_pdiscard(bs->file, offset, bytes); +} + + +static void compress_refresh_limits(BlockDriverState *bs, Error **errp) +{ + BlockDriverInfo bdi; + int ret; + + if (!bs->file) { + return; + } + + ret = bdrv_get_info(bs->file->bs, &bdi); + if (ret < 0 || bdi.cluster_size == 0) { + return; + } + + bs->bl.request_alignment = bdi.cluster_size; +} + + +static void compress_eject(BlockDriverState *bs, bool eject_flag) +{ + bdrv_eject(bs->file->bs, eject_flag); +} + + +static void compress_lock_medium(BlockDriverState *bs, bool locked) +{ + bdrv_lock_medium(bs->file->bs, locked); +} + + +static bool compress_recurse_is_first_non_filter(BlockDriverState *bs, + BlockDriverState *candidate) +{ + return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); +} + + +static BlockDriver bdrv_compress = { + .format_name = "compress", + + .bdrv_open = compress_open, + .bdrv_child_perm = bdrv_filter_default_perms, + + .bdrv_getlength = compress_getlength, + + .bdrv_co_preadv_part = compress_co_preadv_part, + .bdrv_co_pwritev_part = compress_co_pwritev_part, + .bdrv_co_pwrite_zeroes = compress_co_pwrite_zeroes, + .bdrv_co_pdiscard = compress_co_pdiscard, + .bdrv_refresh_limits = compress_refresh_limits, + + .bdrv_eject = compress_eject, + .bdrv_lock_medium = compress_lock_medium, + + .bdrv_co_block_status = bdrv_co_block_status_from_file, + + .bdrv_recurse_is_first_non_filter = compress_recurse_is_first_non_filter, + + .has_variable_length = true, + .is_filter = true, +}; + +static void bdrv_compress_init(void) +{ + bdrv_register(&bdrv_compress); +} + +block_init(bdrv_compress_init); 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 @@ # @copy-on-read: Since 3.0 # @blklogwrites: Since 3.0 # @blkreplay: Since 4.2 +# @compress: Since 5.0 # # Since: 2.9 ## { 'enum': 'BlockdevDriver', 'data': [ 'blkdebug', 'blklogwrites', 'blkreplay', 'blkverify', 'bochs', - 'cloop', 'copy-on-read', 'dmg', 'file', 'ftp', 'ftps', 'gluster', - 'host_cdrom', 'host_device', 'http', 'https', 'iscsi', 'luks', - 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', 'qcow', - 'qcow2', 'qed', 'quorum', 'raw', 'rbd', + 'cloop', 'compress', 'copy-on-read', 'dmg', 'file', 'ftp', 'ftps', + 'gluster', 'host_cdrom', 'host_device', 'http', 'https', 'iscsi', + 'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', + 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd', { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' }, 'sheepdog', 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] } @@ -XXX,XX +XXX,XX @@ 'blkreplay': 'BlockdevOptionsBlkreplay', 'bochs': 'BlockdevOptionsGenericFormat', 'cloop': 'BlockdevOptionsGenericFormat', + 'compress': 'BlockdevOptionsGenericFormat', 'copy-on-read':'BlockdevOptionsGenericFormat', 'dmg': 'BlockdevOptionsGenericFormat', 'file': 'BlockdevOptionsFile', -- 2.24.1 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> QEMU currently supports writing compressed data of the size equal to one cluster. This patch allows writing QCOW2 compressed data that exceed one cluster. Now, we split buffered data into separate clusters and write them compressed using the block/aio_task API. Suggested-by: Pavel Butsykin <pbutsykin@virtuozzo.com> Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 1575288906-551879-3-git-send-email-andrey.shinkevich@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 102 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 75 insertions(+), 27 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 @@ fail: return ret; } -/* XXX: put compressed sectors first, then all the cluster aligned - tables to avoid losing bytes in alignment */ static coroutine_fn int -qcow2_co_pwritev_compressed_part(BlockDriverState *bs, +qcow2_co_pwritev_compressed_task(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, size_t qiov_offset) { @@ -XXX,XX +XXX,XX @@ qcow2_co_pwritev_compressed_part(BlockDriverState *bs, uint8_t *buf, *out_buf; uint64_t cluster_offset; - if (has_data_file(bs)) { - return -ENOTSUP; - } - - if (bytes == 0) { - /* align end of file to a sector boundary to ease reading with - sector based I/Os */ - int64_t len = bdrv_getlength(bs->file->bs); - if (len < 0) { - return len; - } - return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL); - } - - if (offset_into_cluster(s, offset)) { - return -EINVAL; - } + assert(bytes == s->cluster_size || (bytes < s->cluster_size && + (offset + bytes == bs->total_sectors << BDRV_SECTOR_BITS))); buf = qemu_blockalign(bs, s->cluster_size); - if (bytes != s->cluster_size) { - if (bytes > s->cluster_size || - offset + bytes != bs->total_sectors << BDRV_SECTOR_BITS) - { - qemu_vfree(buf); - return -EINVAL; - } + if (bytes < s->cluster_size) { /* Zero-pad last write if image size is not cluster aligned */ memset(buf + bytes, 0, s->cluster_size - bytes); } @@ -XXX,XX +XXX,XX @@ fail: return ret; } +static coroutine_fn int qcow2_co_pwritev_compressed_task_entry(AioTask *task) +{ + Qcow2AioTask *t = container_of(task, Qcow2AioTask, task); + + assert(!t->cluster_type && !t->l2meta); + + return qcow2_co_pwritev_compressed_task(t->bs, t->offset, t->bytes, t->qiov, + t->qiov_offset); +} + +/* + * XXX: put compressed sectors first, then all the cluster aligned + * tables to avoid losing bytes in alignment + */ +static coroutine_fn int +qcow2_co_pwritev_compressed_part(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, size_t qiov_offset) +{ + BDRVQcow2State *s = bs->opaque; + AioTaskPool *aio = NULL; + int ret = 0; + + if (has_data_file(bs)) { + return -ENOTSUP; + } + + if (bytes == 0) { + /* + * align end of file to a sector boundary to ease reading with + * sector based I/Os + */ + int64_t len = bdrv_getlength(bs->file->bs); + if (len < 0) { + return len; + } + return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL); + } + + if (offset_into_cluster(s, offset)) { + return -EINVAL; + } + + while (bytes && aio_task_pool_status(aio) == 0) { + uint64_t chunk_size = MIN(bytes, s->cluster_size); + + if (!aio && chunk_size != bytes) { + aio = aio_task_pool_new(QCOW2_MAX_WORKERS); + } + + ret = qcow2_add_task(bs, aio, qcow2_co_pwritev_compressed_task_entry, + 0, 0, offset, chunk_size, qiov, qiov_offset, NULL); + if (ret < 0) { + break; + } + qiov_offset += chunk_size; + offset += chunk_size; + bytes -= chunk_size; + } + + if (aio) { + aio_task_pool_wait_all(aio); + if (ret == 0) { + ret = aio_task_pool_status(aio); + } + g_free(aio); + } + + return ret; +} + static int coroutine_fn qcow2_co_preadv_compressed(BlockDriverState *bs, uint64_t file_cluster_offset, -- 2.24.1 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Add the case to the iotest #214 that checks possibility of writing compressed data of more than one cluster size. The test case involves the compress filter driver showing a sample usage of that. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 1575288906-551879-4-git-send-email-andrey.shinkevich@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/214 | 43 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/214.out | 14 +++++++++++++ 2 files changed, 57 insertions(+) diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/214 +++ b/tests/qemu-iotests/214 @@ -XXX,XX +XXX,XX @@ _check_test_img -r all $QEMU_IO -c "read -P 0x11 0 4M" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir $QEMU_IO -c "read -P 0x22 4M 4M" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir +echo +echo "=== Write compressed data of multiple clusters ===" +echo +cluster_size=0x10000 +_make_test_img 2M -o cluster_size=$cluster_size + +echo "Write uncompressed data:" +let data_size="8 * $cluster_size" +$QEMU_IO -c "write -P 0xaa 0 $data_size" "$TEST_IMG" \ + 2>&1 | _filter_qemu_io | _filter_testdir +sizeA=$($QEMU_IMG info --output=json "$TEST_IMG" | + sed -n '/"actual-size":/ s/[^0-9]//gp') + +_make_test_img 2M -o cluster_size=$cluster_size +echo "Write compressed data:" +let data_size="3 * $cluster_size + $cluster_size / 2" +# Set compress on. That will align the written data +# by the cluster size and will write them compressed. +QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT \ +$QEMU_IO -c "write -P 0xbb 0 $data_size" --image-opts \ + "driver=compress,file.driver=$IMGFMT,file.file.driver=file,file.file.filename=$TEST_IMG" \ + 2>&1 | _filter_qemu_io | _filter_testdir + +let offset="4 * $cluster_size + $cluster_size / 4" +QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT \ +$QEMU_IO -c "write -P 0xcc $offset $data_size" "json:{\ + 'driver': 'compress', + 'file': {'driver': '$IMGFMT', + 'file': {'driver': 'file', + 'filename': '$TEST_IMG'}}}" | \ + _filter_qemu_io | _filter_testdir + +sizeB=$($QEMU_IMG info --output=json "$TEST_IMG" | + sed -n '/"actual-size":/ s/[^0-9]//gp') + +if [ $sizeA -le $sizeB ] +then + echo "Compression ERROR" +fi + +$QEMU_IMG check --output=json "$TEST_IMG" | + sed -n 's/,$//; /"compressed-clusters":/ s/^ *//p' + # success, all done echo '*** done' rm -f $seq.full diff --git a/tests/qemu-iotests/214.out b/tests/qemu-iotests/214.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/214.out +++ b/tests/qemu-iotests/214.out @@ -XXX,XX +XXX,XX @@ read 4194304/4194304 bytes at offset 0 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 4194304/4194304 bytes at offset 4194304 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Write compressed data of multiple clusters === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2097152 +Write uncompressed data: +wrote 524288/524288 bytes at offset 0 +512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2097152 +Write compressed data: +wrote 229376/229376 bytes at offset 0 +224 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 229376/229376 bytes at offset 278528 +224 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +"compressed-clusters": 8 *** done -- 2.24.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Commit 6f6e1698a6 desugarized "-machine accel=" to a list of "-accel" options. Since now "-machine accel" and "-accel" became incompatible, update the iotests to the new format. Error reported here: https://gitlab.com/qemu-project/qemu/-/jobs/385801004#L3400 Reported-by: GitLab CI Fixes: 6f6e1698a6 (vl: configure accelerators from -accel options) Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200106130951.29873-1-philmd@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/235 | 2 +- tests/qemu-iotests/check | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tests/qemu-iotests/235 b/tests/qemu-iotests/235 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/235 +++ b/tests/qemu-iotests/235 @@ -XXX,XX +XXX,XX @@ qemu_img_create('-f', iotests.imgfmt, '-o', 'preallocation=metadata', disk, str(size)) vm = QEMUMachine(iotests.qemu_prog) -vm.add_args('-machine', 'accel=kvm:tcg') +vm.add_args('-accel', 'kvm', '-accel', 'tcg') if iotests.qemu_default_machine == 's390-ccw-virtio': vm.add_args('-no-shutdown') vm.add_args('-drive', 'id=src,file=' + disk) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ export QEMU_PROG="$(type -p "$QEMU_PROG")" case "$QEMU_PROG" in *qemu-system-arm|*qemu-system-aarch64) - export QEMU_OPTIONS="-nodefaults -display none -machine virt,accel=qtest" + export QEMU_OPTIONS="-nodefaults -display none -machine virt -accel qtest" ;; *qemu-system-tricore) - export QEMU_OPTIONS="-nodefaults -display none -machine tricore_testboard,accel=qtest" + export QEMU_OPTIONS="-nodefaults -display none -machine tricore_testboard -accel qtest" ;; *) - export QEMU_OPTIONS="-nodefaults -display none -machine accel=qtest" + export QEMU_OPTIONS="-nodefaults -display none -accel qtest" ;; esac -- 2.24.1 When dropping backup-top, we need to drain the node before freeing the BlockCopyState. Otherwise, requests may still be in flight and then the assertion in shres_destroy() will fail. (This becomes visible in intermittent failure of 056.) Cc: qemu-stable@nongnu.org Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20191219182638.104621-1-mreitz@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup-top.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/backup-top.c b/block/backup-top.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup-top.c +++ b/block/backup-top.c @@ -XXX,XX +XXX,XX @@ void bdrv_backup_top_drop(BlockDriverState *bs) BDRVBackupTopState *s = bs->opaque; AioContext *aio_context = bdrv_get_aio_context(bs); - block_copy_state_free(s->bcs); - aio_context_acquire(aio_context); bdrv_drained_begin(bs); + block_copy_state_free(s->bcs); + s->active = false; bdrv_child_refresh_perms(bs, bs->backing, &error_abort); bdrv_replace_node(bs, backing_bs(bs), &error_abort); -- 2.24.1 The following changes since commit c1eb2ddf0f8075faddc5f7c3d39feae3e8e9d6b4: Update version for v8.0.0 release (2023-04-19 17:27:13 +0100) are available in the Git repository at: https://gitlab.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to 36e5e9b22abe56aa00ca067851555ad8127a7966: tracing: install trace events file only if necessary (2023-04-20 07:39:43 -0400) ---------------------------------------------------------------- Pull request Sam Li's zoned storage work and fixes I collected during the 8.0 freeze. ---------------------------------------------------------------- Carlos Santos (1): tracing: install trace events file only if necessary Philippe Mathieu-Daudé (1): block/dmg: Declare a type definition for DMG uncompress function Sam Li (17): block/block-common: add zoned device structs block/file-posix: introduce helper functions for sysfs attributes block/block-backend: add block layer APIs resembling Linux ZonedBlockDevice ioctls block/raw-format: add zone operations to pass through requests block: add zoned BlockDriver check to block layer iotests: test new zone operations block: add some trace events for new block layer APIs docs/zoned-storage: add zoned device documentation file-posix: add tracking of the zone write pointers block: introduce zone append write for zoned devices qemu-iotests: test zone append operation block: add some trace events for zone append include: update virtio_blk headers to v6.3-rc1 virtio-blk: add zoned storage emulation for zoned devices block: add accounting for zone append operation virtio-blk: add some trace events for zoned emulation docs/zoned-storage:add zoned emulation use case Thomas De Schampheleire (1): tracetool: use relative paths for '#line' preprocessor directives docs/devel/index-api.rst | 1 + docs/devel/zoned-storage.rst | 62 ++ qapi/block-core.json | 68 +- qapi/block.json | 4 + meson.build | 4 + block/dmg.h | 8 +- include/block/accounting.h | 1 + include/block/block-common.h | 57 ++ include/block/block-io.h | 13 + include/block/block_int-common.h | 37 + include/block/raw-aio.h | 8 +- include/standard-headers/drm/drm_fourcc.h | 12 + include/standard-headers/linux/ethtool.h | 48 +- include/standard-headers/linux/fuse.h | 45 +- include/standard-headers/linux/pci_regs.h | 1 + include/standard-headers/linux/vhost_types.h | 2 + include/standard-headers/linux/virtio_blk.h | 105 +++ include/sysemu/block-backend-io.h | 27 + linux-headers/asm-arm64/kvm.h | 1 + linux-headers/asm-x86/kvm.h | 34 +- linux-headers/linux/kvm.h | 9 + linux-headers/linux/vfio.h | 15 +- linux-headers/linux/vhost.h | 8 + block.c | 19 + block/block-backend.c | 193 ++++++ block/dmg.c | 7 +- block/file-posix.c | 677 +++++++++++++++++-- block/io.c | 68 ++ block/io_uring.c | 4 + block/linux-aio.c | 3 + block/qapi-sysemu.c | 11 + block/qapi.c | 18 + block/raw-format.c | 26 + hw/block/virtio-blk-common.c | 2 + hw/block/virtio-blk.c | 405 +++++++++++ hw/virtio/virtio-qmp.c | 2 + qemu-io-cmds.c | 224 ++++++ block/trace-events | 4 + docs/system/qemu-block-drivers.rst.inc | 6 + hw/block/trace-events | 7 + scripts/tracetool/backend/ftrace.py | 4 +- scripts/tracetool/backend/log.py | 4 +- scripts/tracetool/backend/syslog.py | 4 +- tests/qemu-iotests/tests/zoned | 105 +++ tests/qemu-iotests/tests/zoned.out | 69 ++ trace/meson.build | 2 +- 46 files changed, 2353 insertions(+), 81 deletions(-) create mode 100644 docs/devel/zoned-storage.rst create mode 100755 tests/qemu-iotests/tests/zoned create mode 100644 tests/qemu-iotests/tests/zoned.out -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-2-faithilikerun@gmail.com [Adjust commit message prefix as suggested by Philippe Mathieu-Daudé <philmd@linaro.org>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block-common.h | 43 ++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/include/block/block-common.h b/include/block/block-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-common.h +++ b/include/block/block-common.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockDriver BlockDriver; typedef struct BdrvChild BdrvChild; typedef struct BdrvChildClass BdrvChildClass; +typedef enum BlockZoneOp { + BLK_ZO_OPEN, + BLK_ZO_CLOSE, + BLK_ZO_FINISH, + BLK_ZO_RESET, +} BlockZoneOp; + +typedef enum BlockZoneModel { + BLK_Z_NONE = 0x0, /* Regular block device */ + BLK_Z_HM = 0x1, /* Host-managed zoned block device */ + BLK_Z_HA = 0x2, /* Host-aware zoned block device */ +} BlockZoneModel; + +typedef enum BlockZoneState { + BLK_ZS_NOT_WP = 0x0, + BLK_ZS_EMPTY = 0x1, + BLK_ZS_IOPEN = 0x2, + BLK_ZS_EOPEN = 0x3, + BLK_ZS_CLOSED = 0x4, + BLK_ZS_RDONLY = 0xD, + BLK_ZS_FULL = 0xE, + BLK_ZS_OFFLINE = 0xF, +} BlockZoneState; + +typedef enum BlockZoneType { + BLK_ZT_CONV = 0x1, /* Conventional random writes supported */ + BLK_ZT_SWR = 0x2, /* Sequential writes required */ + BLK_ZT_SWP = 0x3, /* Sequential writes preferred */ +} BlockZoneType; + +/* + * Zone descriptor data structure. + * Provides information on a zone with all position and size values in bytes. + */ +typedef struct BlockZoneDescriptor { + uint64_t start; + uint64_t length; + uint64_t cap; + uint64_t wp; + BlockZoneType type; + BlockZoneState state; +} BlockZoneDescriptor; + typedef struct BlockDriverInfo { /* in bytes, 0 if irrelevant */ int cluster_size; -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Use get_sysfs_str_val() to get the string value of device zoned model. Then get_sysfs_zoned_model() can convert it to BlockZoneModel type of QEMU. Use get_sysfs_long_val() to get the long value of zoned device information. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-3-faithilikerun@gmail.com [Adjust commit message prefix as suggested by Philippe Mathieu-Daudé <philmd@linaro.org>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block_int-common.h | 3 + block/file-posix.c | 130 ++++++++++++++++++++++--------- 2 files changed, 95 insertions(+), 38 deletions(-) diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockLimits { * an explicit monitor command to load the disk inside the guest). */ bool has_variable_length; + + /* device zone model */ + BlockZoneModel zoned; } BlockLimits; typedef struct BdrvOpBlocker BdrvOpBlocker; 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 hdev_get_max_hw_transfer(int fd, struct stat *st) #endif } -static int hdev_get_max_segments(int fd, struct stat *st) +/* + * Get a sysfs attribute value as character string. + */ +static int get_sysfs_str_val(struct stat *st, const char *attribute, + char **val) { +#ifdef CONFIG_LINUX + g_autofree char *sysfspath = NULL; + int ret; + size_t len; + + if (!S_ISBLK(st->st_mode)) { + return -ENOTSUP; + } + + sysfspath = g_strdup_printf("/sys/dev/block/%u:%u/queue/%s", + major(st->st_rdev), minor(st->st_rdev), + attribute); + ret = g_file_get_contents(sysfspath, val, &len, NULL); + if (ret == -1) { + return -ENOENT; + } + + /* The file is ended with '\n' */ + char *p; + p = *val; + if (*(p + len - 1) == '\n') { + *(p + len - 1) = '\0'; + } + return ret; +#else + return -ENOTSUP; +#endif +} + +static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned) +{ + g_autofree char *val = NULL; + int ret; + + ret = get_sysfs_str_val(st, "zoned", &val); + if (ret < 0) { + return ret; + } + + if (strcmp(val, "host-managed") == 0) { + *zoned = BLK_Z_HM; + } else if (strcmp(val, "host-aware") == 0) { + *zoned = BLK_Z_HA; + } else if (strcmp(val, "none") == 0) { + *zoned = BLK_Z_NONE; + } else { + return -ENOTSUP; + } + return 0; +} + +/* + * Get a sysfs attribute value as a long integer. + */ +static long get_sysfs_long_val(struct stat *st, const char *attribute) { #ifdef CONFIG_LINUX - char buf[32]; + g_autofree char *str = NULL; const char *end; - char *sysfspath = NULL; + long val; + int ret; + + ret = get_sysfs_str_val(st, attribute, &str); + if (ret < 0) { + return ret; + } + + /* The file is ended with '\n', pass 'end' to accept that. */ + ret = qemu_strtol(str, &end, 10, &val); + if (ret == 0 && end && *end == '\0') { + ret = val; + } + return ret; +#else + return -ENOTSUP; +#endif +} + +static int hdev_get_max_segments(int fd, struct stat *st) +{ +#ifdef CONFIG_LINUX int ret; - int sysfd = -1; - long max_segments; if (S_ISCHR(st->st_mode)) { if (ioctl(fd, SG_GET_SG_TABLESIZE, &ret) == 0) { @@ -XXX,XX +XXX,XX @@ static int hdev_get_max_segments(int fd, struct stat *st) } return -ENOTSUP; } - - if (!S_ISBLK(st->st_mode)) { - return -ENOTSUP; - } - - sysfspath = g_strdup_printf("/sys/dev/block/%u:%u/queue/max_segments", - major(st->st_rdev), minor(st->st_rdev)); - sysfd = open(sysfspath, O_RDONLY); - if (sysfd == -1) { - ret = -errno; - goto out; - } - ret = RETRY_ON_EINTR(read(sysfd, buf, sizeof(buf) - 1)); - if (ret < 0) { - ret = -errno; - goto out; - } else if (ret == 0) { - ret = -EIO; - goto out; - } - buf[ret] = 0; - /* The file is ended with '\n', pass 'end' to accept that. */ - ret = qemu_strtol(buf, &end, 10, &max_segments); - if (ret == 0 && end && *end == '\n') { - ret = max_segments; - } - -out: - if (sysfd != -1) { - close(sysfd); - } - g_free(sysfspath); - return ret; + return get_sysfs_long_val(st, "max_segments"); #else return -ENOTSUP; #endif @@ -XXX,XX +XXX,XX @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) { BDRVRawState *s = bs->opaque; struct stat st; + int ret; + BlockZoneModel zoned; s->needs_alignment = raw_needs_alignment(bs); raw_probe_alignment(bs, s->fd, errp); @@ -XXX,XX +XXX,XX @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) bs->bl.max_hw_iov = ret; } } + + ret = get_sysfs_zoned_model(&st, &zoned); + if (ret < 0) { + zoned = BLK_Z_NONE; + } + bs->bl.zoned = zoned; } static int check_for_dasd(int fd) -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Add zoned device option to host_device BlockDriver. It will be presented only for zoned host block devices. By adding zone management operations to the host_block_device BlockDriver, users can use the new block layer APIs including Report Zone and four zone management operations (open, close, finish, reset, reset_all). Qemu-io uses the new APIs to perform zoned storage commands of the device: zone_report(zrp), zone_open(zo), zone_close(zc), zone_reset(zrs), zone_finish(zf). For example, to test zone_report, use following command: $ ./build/qemu-io --image-opts -n driver=host_device, filename=/dev/nullb0 -c "zrp offset nr_zones" Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-4-faithilikerun@gmail.com [Adjust commit message prefix as suggested by Philippe Mathieu-Daudé <philmd@linaro.org> and remove spurious ret = -errno in raw_co_zone_mgmt(). --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- meson.build | 4 + include/block/block-io.h | 9 + include/block/block_int-common.h | 21 ++ include/block/raw-aio.h | 6 +- include/sysemu/block-backend-io.h | 18 ++ block/block-backend.c | 133 +++++++++++++ block/file-posix.c | 306 +++++++++++++++++++++++++++++- block/io.c | 41 ++++ qemu-io-cmds.c | 149 +++++++++++++++ 9 files changed, 684 insertions(+), 3 deletions(-) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ config_host_data.set('CONFIG_REPLICATION', get_option('replication').allowed()) # has_header config_host_data.set('CONFIG_EPOLL', cc.has_header('sys/epoll.h')) config_host_data.set('CONFIG_LINUX_MAGIC_H', cc.has_header('linux/magic.h')) +config_host_data.set('CONFIG_BLKZONED', cc.has_header('linux/blkzoned.h')) config_host_data.set('CONFIG_VALGRIND_H', cc.has_header('valgrind/valgrind.h')) config_host_data.set('HAVE_BTRFS_H', cc.has_header('linux/btrfs.h')) config_host_data.set('HAVE_DRM_H', cc.has_header('libdrm/drm.h')) @@ -XXX,XX +XXX,XX @@ config_host_data.set('HAVE_SIGEV_NOTIFY_THREAD_ID', config_host_data.set('HAVE_STRUCT_STAT_ST_ATIM', cc.has_member('struct stat', 'st_atim', prefix: '#include <sys/stat.h>')) +config_host_data.set('HAVE_BLK_ZONE_REP_CAPACITY', + cc.has_member('struct blk_zone', 'capacity', + prefix: '#include <linux/blkzoned.h>')) # has_type config_host_data.set('CONFIG_IOVEC', diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn GRAPH_RDLOCK bdrv_co_flush(BlockDriverState *bs); int coroutine_fn GRAPH_RDLOCK bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes); +/* Report zone information of zone block device. */ +int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_report(BlockDriverState *bs, + int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones); +int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_mgmt(BlockDriverState *bs, + BlockZoneOp op, + int64_t offset, int64_t len); + bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_load_vmstate)( BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); + int coroutine_fn (*bdrv_co_zone_report)(BlockDriverState *bs, + int64_t offset, unsigned int *nr_zones, + BlockZoneDescriptor *zones); + int coroutine_fn (*bdrv_co_zone_mgmt)(BlockDriverState *bs, BlockZoneOp op, + int64_t offset, int64_t len); + /* removable device specific */ bool coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_is_inserted)( BlockDriverState *bs); @@ -XXX,XX +XXX,XX @@ typedef struct BlockLimits { /* device zone model */ BlockZoneModel zoned; + + /* zone size expressed in bytes */ + uint32_t zone_size; + + /* total number of zones */ + uint32_t nr_zones; + + /* maximum sectors of a zone append write operation */ + int64_t max_append_sectors; + + /* maximum number of open zones */ + int64_t max_open_zones; + + /* maximum number of active zones */ + int64_t max_active_zones; } BlockLimits; typedef struct BdrvOpBlocker BdrvOpBlocker; diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/raw-aio.h +++ b/include/block/raw-aio.h @@ -XXX,XX +XXX,XX @@ #define QEMU_AIO_WRITE_ZEROES 0x0020 #define QEMU_AIO_COPY_RANGE 0x0040 #define QEMU_AIO_TRUNCATE 0x0080 +#define QEMU_AIO_ZONE_REPORT 0x0100 +#define QEMU_AIO_ZONE_MGMT 0x0200 #define QEMU_AIO_TYPE_MASK \ (QEMU_AIO_READ | \ QEMU_AIO_WRITE | \ @@ -XXX,XX +XXX,XX @@ QEMU_AIO_DISCARD | \ QEMU_AIO_WRITE_ZEROES | \ QEMU_AIO_COPY_RANGE | \ - QEMU_AIO_TRUNCATE) + QEMU_AIO_TRUNCATE | \ + QEMU_AIO_ZONE_REPORT | \ + QEMU_AIO_ZONE_MGMT) /* AIO flags */ #define QEMU_AIO_MISALIGNED 0x1000 diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset, BlockCompletionFunc *cb, void *opaque); BlockAIOCB *blk_aio_flush(BlockBackend *blk, BlockCompletionFunc *cb, void *opaque); +BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones, + BlockCompletionFunc *cb, void *opaque); +BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op, + int64_t offset, int64_t len, + BlockCompletionFunc *cb, void *opaque); BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes, BlockCompletionFunc *cb, void *opaque); void blk_aio_cancel_async(BlockAIOCB *acb); @@ -XXX,XX +XXX,XX @@ int co_wrapper_mixed blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, int64_t bytes, BdrvRequestFlags flags); +int coroutine_fn blk_co_zone_report(BlockBackend *blk, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones); +int co_wrapper_mixed blk_zone_report(BlockBackend *blk, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones); +int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op, + int64_t offset, int64_t len); +int co_wrapper_mixed blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op, + int64_t offset, int64_t len); + int co_wrapper_mixed blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, 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 @@ int coroutine_fn blk_co_flush(BlockBackend *blk) return ret; } +static void coroutine_fn blk_aio_zone_report_entry(void *opaque) +{ + BlkAioEmAIOCB *acb = opaque; + BlkRwCo *rwco = &acb->rwco; + + rwco->ret = blk_co_zone_report(rwco->blk, rwco->offset, + (unsigned int*)acb->bytes,rwco->iobuf); + blk_aio_complete(acb); +} + +BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones, + BlockCompletionFunc *cb, void *opaque) +{ + BlkAioEmAIOCB *acb; + Coroutine *co; + IO_CODE(); + + blk_inc_in_flight(blk); + acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque); + acb->rwco = (BlkRwCo) { + .blk = blk, + .offset = offset, + .iobuf = zones, + .ret = NOT_DONE, + }; + acb->bytes = (int64_t)nr_zones, + acb->has_returned = false; + + co = qemu_coroutine_create(blk_aio_zone_report_entry, acb); + aio_co_enter(blk_get_aio_context(blk), co); + + acb->has_returned = true; + if (acb->rwco.ret != NOT_DONE) { + replay_bh_schedule_oneshot_event(blk_get_aio_context(blk), + blk_aio_complete_bh, acb); + } + + return &acb->common; +} + +static void coroutine_fn blk_aio_zone_mgmt_entry(void *opaque) +{ + BlkAioEmAIOCB *acb = opaque; + BlkRwCo *rwco = &acb->rwco; + + rwco->ret = blk_co_zone_mgmt(rwco->blk, (BlockZoneOp)rwco->iobuf, + rwco->offset, acb->bytes); + blk_aio_complete(acb); +} + +BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op, + int64_t offset, int64_t len, + BlockCompletionFunc *cb, void *opaque) { + BlkAioEmAIOCB *acb; + Coroutine *co; + IO_CODE(); + + blk_inc_in_flight(blk); + acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque); + acb->rwco = (BlkRwCo) { + .blk = blk, + .offset = offset, + .iobuf = (void *)op, + .ret = NOT_DONE, + }; + acb->bytes = len; + acb->has_returned = false; + + co = qemu_coroutine_create(blk_aio_zone_mgmt_entry, acb); + aio_co_enter(blk_get_aio_context(blk), co); + + acb->has_returned = true; + if (acb->rwco.ret != NOT_DONE) { + replay_bh_schedule_oneshot_event(blk_get_aio_context(blk), + blk_aio_complete_bh, acb); + } + + return &acb->common; +} + +/* + * Send a zone_report command. + * offset is a byte offset from the start of the device. No alignment + * required for offset. + * nr_zones represents IN maximum and OUT actual. + */ +int coroutine_fn blk_co_zone_report(BlockBackend *blk, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones) +{ + int ret; + IO_CODE(); + + blk_inc_in_flight(blk); /* increase before waiting */ + blk_wait_while_drained(blk); + if (!blk_is_available(blk)) { + blk_dec_in_flight(blk); + return -ENOMEDIUM; + } + ret = bdrv_co_zone_report(blk_bs(blk), offset, nr_zones, zones); + blk_dec_in_flight(blk); + return ret; +} + +/* + * Send a zone_management command. + * op is the zone operation; + * offset is the byte offset from the start of the zoned device; + * len is the maximum number of bytes the command should operate on. It + * should be aligned with the device zone size. + */ +int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op, + int64_t offset, int64_t len) +{ + int ret; + IO_CODE(); + + blk_inc_in_flight(blk); + blk_wait_while_drained(blk); + + ret = blk_check_byte_request(blk, offset, len); + if (ret < 0) { + blk_dec_in_flight(blk); + return ret; + } + + ret = bdrv_co_zone_mgmt(blk_bs(blk), op, offset, len); + blk_dec_in_flight(blk); + return ret; +} + void blk_drain(BlockBackend *blk) { BlockDriverState *bs = blk_bs(blk); 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 @@ #include <sys/param.h> #include <sys/syscall.h> #include <sys/vfs.h> +#if defined(CONFIG_BLKZONED) +#include <linux/blkzoned.h> +#endif #include <linux/cdrom.h> #include <linux/fd.h> #include <linux/fs.h> @@ -XXX,XX +XXX,XX @@ typedef struct RawPosixAIOData { PreallocMode prealloc; Error **errp; } truncate; + struct { + unsigned int *nr_zones; + BlockZoneDescriptor *zones; + } zone_report; + struct { + unsigned long op; + } zone_mgmt; }; } RawPosixAIOData; @@ -XXX,XX +XXX,XX @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) zoned = BLK_Z_NONE; } bs->bl.zoned = zoned; + if (zoned != BLK_Z_NONE) { + /* + * The zoned device must at least have zone size and nr_zones fields. + */ + ret = get_sysfs_long_val(&st, "chunk_sectors"); + if (ret < 0) { + error_setg_errno(errp, -ret, "Unable to read chunk_sectors " + "sysfs attribute"); + goto out; + } else if (!ret) { + error_setg(errp, "Read 0 from chunk_sectors sysfs attribute"); + goto out; + } + bs->bl.zone_size = ret << BDRV_SECTOR_BITS; + + ret = get_sysfs_long_val(&st, "nr_zones"); + if (ret < 0) { + error_setg_errno(errp, -ret, "Unable to read nr_zones " + "sysfs attribute"); + goto out; + } else if (!ret) { + error_setg(errp, "Read 0 from nr_zones sysfs attribute"); + goto out; + } + bs->bl.nr_zones = ret; + + ret = get_sysfs_long_val(&st, "zone_append_max_bytes"); + if (ret > 0) { + bs->bl.max_append_sectors = ret >> BDRV_SECTOR_BITS; + } + + ret = get_sysfs_long_val(&st, "max_open_zones"); + if (ret >= 0) { + bs->bl.max_open_zones = ret; + } + + ret = get_sysfs_long_val(&st, "max_active_zones"); + if (ret >= 0) { + bs->bl.max_active_zones = ret; + } + return; + } +out: + bs->bl.zoned = BLK_Z_NONE; } static int check_for_dasd(int fd) @@ -XXX,XX +XXX,XX @@ static int hdev_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz) BDRVRawState *s = bs->opaque; int ret; - /* If DASD, get blocksizes */ + /* If DASD or zoned devices, get blocksizes */ if (check_for_dasd(s->fd) < 0) { - return -ENOTSUP; + /* zoned devices are not DASD */ + if (bs->bl.zoned == BLK_Z_NONE) { + return -ENOTSUP; + } } ret = probe_logical_blocksize(s->fd, &bsz->log); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd, } #endif +/* + * parse_zone - Fill a zone descriptor + */ +#if defined(CONFIG_BLKZONED) +static inline int parse_zone(struct BlockZoneDescriptor *zone, + const struct blk_zone *blkz) { + zone->start = blkz->start << BDRV_SECTOR_BITS; + zone->length = blkz->len << BDRV_SECTOR_BITS; + zone->wp = blkz->wp << BDRV_SECTOR_BITS; + +#ifdef HAVE_BLK_ZONE_REP_CAPACITY + zone->cap = blkz->capacity << BDRV_SECTOR_BITS; +#else + zone->cap = blkz->len << BDRV_SECTOR_BITS; +#endif + + switch (blkz->type) { + case BLK_ZONE_TYPE_SEQWRITE_REQ: + zone->type = BLK_ZT_SWR; + break; + case BLK_ZONE_TYPE_SEQWRITE_PREF: + zone->type = BLK_ZT_SWP; + break; + case BLK_ZONE_TYPE_CONVENTIONAL: + zone->type = BLK_ZT_CONV; + break; + default: + error_report("Unsupported zone type: 0x%x", blkz->type); + return -ENOTSUP; + } + + switch (blkz->cond) { + case BLK_ZONE_COND_NOT_WP: + zone->state = BLK_ZS_NOT_WP; + break; + case BLK_ZONE_COND_EMPTY: + zone->state = BLK_ZS_EMPTY; + break; + case BLK_ZONE_COND_IMP_OPEN: + zone->state = BLK_ZS_IOPEN; + break; + case BLK_ZONE_COND_EXP_OPEN: + zone->state = BLK_ZS_EOPEN; + break; + case BLK_ZONE_COND_CLOSED: + zone->state = BLK_ZS_CLOSED; + break; + case BLK_ZONE_COND_READONLY: + zone->state = BLK_ZS_RDONLY; + break; + case BLK_ZONE_COND_FULL: + zone->state = BLK_ZS_FULL; + break; + case BLK_ZONE_COND_OFFLINE: + zone->state = BLK_ZS_OFFLINE; + break; + default: + error_report("Unsupported zone state: 0x%x", blkz->cond); + return -ENOTSUP; + } + return 0; +} +#endif + +#if defined(CONFIG_BLKZONED) +static int handle_aiocb_zone_report(void *opaque) +{ + RawPosixAIOData *aiocb = opaque; + int fd = aiocb->aio_fildes; + unsigned int *nr_zones = aiocb->zone_report.nr_zones; + BlockZoneDescriptor *zones = aiocb->zone_report.zones; + /* zoned block devices use 512-byte sectors */ + uint64_t sector = aiocb->aio_offset / 512; + + struct blk_zone *blkz; + size_t rep_size; + unsigned int nrz; + int ret, n = 0, i = 0; + + nrz = *nr_zones; + rep_size = sizeof(struct blk_zone_report) + nrz * sizeof(struct blk_zone); + g_autofree struct blk_zone_report *rep = NULL; + rep = g_malloc(rep_size); + + blkz = (struct blk_zone *)(rep + 1); + while (n < nrz) { + memset(rep, 0, rep_size); + rep->sector = sector; + rep->nr_zones = nrz - n; + + do { + ret = ioctl(fd, BLKREPORTZONE, rep); + } while (ret != 0 && errno == EINTR); + if (ret != 0) { + error_report("%d: ioctl BLKREPORTZONE at %" PRId64 " failed %d", + fd, sector, errno); + return -errno; + } + + if (!rep->nr_zones) { + break; + } + + for (i = 0; i < rep->nr_zones; i++, n++) { + ret = parse_zone(&zones[n], &blkz[i]); + if (ret != 0) { + return ret; + } + + /* The next report should start after the last zone reported */ + sector = blkz[i].start + blkz[i].len; + } + } + + *nr_zones = n; + return 0; +} +#endif + +#if defined(CONFIG_BLKZONED) +static int handle_aiocb_zone_mgmt(void *opaque) +{ + RawPosixAIOData *aiocb = opaque; + int fd = aiocb->aio_fildes; + uint64_t sector = aiocb->aio_offset / 512; + int64_t nr_sectors = aiocb->aio_nbytes / 512; + struct blk_zone_range range; + int ret; + + /* Execute the operation */ + range.sector = sector; + range.nr_sectors = nr_sectors; + do { + ret = ioctl(fd, aiocb->zone_mgmt.op, &range); + } while (ret != 0 && errno == EINTR); + + return ret; +} +#endif + static int handle_aiocb_copy_range(void *opaque) { RawPosixAIOData *aiocb = opaque; @@ -XXX,XX +XXX,XX @@ static void raw_account_discard(BDRVRawState *s, uint64_t nbytes, int ret) } } +/* + * zone report - Get a zone block device's information in the form + * of an array of zone descriptors. + * zones is an array of zone descriptors to hold zone information on reply; + * offset can be any byte within the entire size of the device; + * nr_zones is the maxium number of sectors the command should operate on. + */ +#if defined(CONFIG_BLKZONED) +static int coroutine_fn raw_co_zone_report(BlockDriverState *bs, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones) { + BDRVRawState *s = bs->opaque; + RawPosixAIOData acb = (RawPosixAIOData) { + .bs = bs, + .aio_fildes = s->fd, + .aio_type = QEMU_AIO_ZONE_REPORT, + .aio_offset = offset, + .zone_report = { + .nr_zones = nr_zones, + .zones = zones, + }, + }; + + return raw_thread_pool_submit(bs, handle_aiocb_zone_report, &acb); +} +#endif + +/* + * zone management operations - Execute an operation on a zone + */ +#if defined(CONFIG_BLKZONED) +static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, + int64_t offset, int64_t len) { + BDRVRawState *s = bs->opaque; + RawPosixAIOData acb; + int64_t zone_size, zone_size_mask; + const char *op_name; + unsigned long zo; + int ret; + int64_t capacity = bs->total_sectors << BDRV_SECTOR_BITS; + + zone_size = bs->bl.zone_size; + zone_size_mask = zone_size - 1; + if (offset & zone_size_mask) { + error_report("sector offset %" PRId64 " is not aligned to zone size " + "%" PRId64 "", offset / 512, zone_size / 512); + return -EINVAL; + } + + if (((offset + len) < capacity && len & zone_size_mask) || + offset + len > capacity) { + error_report("number of sectors %" PRId64 " is not aligned to zone size" + " %" PRId64 "", len / 512, zone_size / 512); + return -EINVAL; + } + + switch (op) { + case BLK_ZO_OPEN: + op_name = "BLKOPENZONE"; + zo = BLKOPENZONE; + break; + case BLK_ZO_CLOSE: + op_name = "BLKCLOSEZONE"; + zo = BLKCLOSEZONE; + break; + case BLK_ZO_FINISH: + op_name = "BLKFINISHZONE"; + zo = BLKFINISHZONE; + break; + case BLK_ZO_RESET: + op_name = "BLKRESETZONE"; + zo = BLKRESETZONE; + break; + default: + error_report("Unsupported zone op: 0x%x", op); + return -ENOTSUP; + } + + acb = (RawPosixAIOData) { + .bs = bs, + .aio_fildes = s->fd, + .aio_type = QEMU_AIO_ZONE_MGMT, + .aio_offset = offset, + .aio_nbytes = len, + .zone_mgmt = { + .op = zo, + }, + }; + + ret = raw_thread_pool_submit(bs, handle_aiocb_zone_mgmt, &acb); + if (ret != 0) { + error_report("ioctl %s failed %d", op_name, ret); + } + + return ret; +} +#endif + static coroutine_fn int raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes, bool blkdev) @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_host_device = { #ifdef __linux__ .bdrv_co_ioctl = hdev_co_ioctl, #endif + + /* zoned device */ +#if defined(CONFIG_BLKZONED) + /* zone management operations */ + .bdrv_co_zone_report = raw_co_zone_report, + .bdrv_co_zone_mgmt = raw_co_zone_mgmt, +#endif }; #if defined(__linux__) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__) 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 @@ out: return co.ret; } +int coroutine_fn bdrv_co_zone_report(BlockDriverState *bs, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones) +{ + BlockDriver *drv = bs->drv; + CoroutineIOCompletion co = { + .coroutine = qemu_coroutine_self(), + }; + IO_CODE(); + + bdrv_inc_in_flight(bs); + if (!drv || !drv->bdrv_co_zone_report || bs->bl.zoned == BLK_Z_NONE) { + co.ret = -ENOTSUP; + goto out; + } + co.ret = drv->bdrv_co_zone_report(bs, offset, nr_zones, zones); +out: + bdrv_dec_in_flight(bs); + return co.ret; +} + +int coroutine_fn bdrv_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, + int64_t offset, int64_t len) +{ + BlockDriver *drv = bs->drv; + CoroutineIOCompletion co = { + .coroutine = qemu_coroutine_self(), + }; + IO_CODE(); + + bdrv_inc_in_flight(bs); + if (!drv || !drv->bdrv_co_zone_mgmt || bs->bl.zoned == BLK_Z_NONE) { + co.ret = -ENOTSUP; + goto out; + } + co.ret = drv->bdrv_co_zone_mgmt(bs, op, offset, len); +out: + bdrv_dec_in_flight(bs); + return co.ret; +} + void *qemu_blockalign(BlockDriverState *bs, size_t size) { IO_CODE(); 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 const cmdinfo_t flush_cmd = { .oneline = "flush all in-core file state to disk", }; +static inline int64_t tosector(int64_t bytes) +{ + return bytes >> BDRV_SECTOR_BITS; +} + +static int zone_report_f(BlockBackend *blk, int argc, char **argv) +{ + int ret; + int64_t offset; + unsigned int nr_zones; + + ++optind; + offset = cvtnum(argv[optind]); + ++optind; + nr_zones = cvtnum(argv[optind]); + + g_autofree BlockZoneDescriptor *zones = NULL; + zones = g_new(BlockZoneDescriptor, nr_zones); + ret = blk_zone_report(blk, offset, &nr_zones, zones); + if (ret < 0) { + printf("zone report failed: %s\n", strerror(-ret)); + } else { + for (int i = 0; i < nr_zones; ++i) { + printf("start: 0x%" PRIx64 ", len 0x%" PRIx64 ", " + "cap"" 0x%" PRIx64 ", wptr 0x%" PRIx64 ", " + "zcond:%u, [type: %u]\n", + tosector(zones[i].start), tosector(zones[i].length), + tosector(zones[i].cap), tosector(zones[i].wp), + zones[i].state, zones[i].type); + } + } + return ret; +} + +static const cmdinfo_t zone_report_cmd = { + .name = "zone_report", + .altname = "zrp", + .cfunc = zone_report_f, + .argmin = 2, + .argmax = 2, + .args = "offset number", + .oneline = "report zone information", +}; + +static int zone_open_f(BlockBackend *blk, int argc, char **argv) +{ + int ret; + int64_t offset, len; + ++optind; + offset = cvtnum(argv[optind]); + ++optind; + len = cvtnum(argv[optind]); + ret = blk_zone_mgmt(blk, BLK_ZO_OPEN, offset, len); + if (ret < 0) { + printf("zone open failed: %s\n", strerror(-ret)); + } + return ret; +} + +static const cmdinfo_t zone_open_cmd = { + .name = "zone_open", + .altname = "zo", + .cfunc = zone_open_f, + .argmin = 2, + .argmax = 2, + .args = "offset len", + .oneline = "explicit open a range of zones in zone block device", +}; + +static int zone_close_f(BlockBackend *blk, int argc, char **argv) +{ + int ret; + int64_t offset, len; + ++optind; + offset = cvtnum(argv[optind]); + ++optind; + len = cvtnum(argv[optind]); + ret = blk_zone_mgmt(blk, BLK_ZO_CLOSE, offset, len); + if (ret < 0) { + printf("zone close failed: %s\n", strerror(-ret)); + } + return ret; +} + +static const cmdinfo_t zone_close_cmd = { + .name = "zone_close", + .altname = "zc", + .cfunc = zone_close_f, + .argmin = 2, + .argmax = 2, + .args = "offset len", + .oneline = "close a range of zones in zone block device", +}; + +static int zone_finish_f(BlockBackend *blk, int argc, char **argv) +{ + int ret; + int64_t offset, len; + ++optind; + offset = cvtnum(argv[optind]); + ++optind; + len = cvtnum(argv[optind]); + ret = blk_zone_mgmt(blk, BLK_ZO_FINISH, offset, len); + if (ret < 0) { + printf("zone finish failed: %s\n", strerror(-ret)); + } + return ret; +} + +static const cmdinfo_t zone_finish_cmd = { + .name = "zone_finish", + .altname = "zf", + .cfunc = zone_finish_f, + .argmin = 2, + .argmax = 2, + .args = "offset len", + .oneline = "finish a range of zones in zone block device", +}; + +static int zone_reset_f(BlockBackend *blk, int argc, char **argv) +{ + int ret; + int64_t offset, len; + ++optind; + offset = cvtnum(argv[optind]); + ++optind; + len = cvtnum(argv[optind]); + ret = blk_zone_mgmt(blk, BLK_ZO_RESET, offset, len); + if (ret < 0) { + printf("zone reset failed: %s\n", strerror(-ret)); + } + return ret; +} + +static const cmdinfo_t zone_reset_cmd = { + .name = "zone_reset", + .altname = "zrs", + .cfunc = zone_reset_f, + .argmin = 2, + .argmax = 2, + .args = "offset len", + .oneline = "reset a zone write pointer in zone block device", +}; + static int truncate_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t truncate_cmd = { .name = "truncate", @@ -XXX,XX +XXX,XX @@ static void __attribute((constructor)) init_qemuio_commands(void) qemuio_add_command(&aio_write_cmd); qemuio_add_command(&aio_flush_cmd); qemuio_add_command(&flush_cmd); + qemuio_add_command(&zone_report_cmd); + qemuio_add_command(&zone_open_cmd); + qemuio_add_command(&zone_close_cmd); + qemuio_add_command(&zone_finish_cmd); + qemuio_add_command(&zone_reset_cmd); qemuio_add_command(&truncate_cmd); qemuio_add_command(&length_cmd); qemuio_add_command(&info_cmd); -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> raw-format driver usually sits on top of file-posix driver. It needs to pass through requests of zone commands. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-5-faithilikerun@gmail.com [Adjust commit message prefix as suggested by Philippe Mathieu-Daudé <philmd@linaro.org>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/raw-format.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ raw_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes) return bdrv_co_pdiscard(bs->file, offset, bytes); } +static int coroutine_fn GRAPH_RDLOCK +raw_co_zone_report(BlockDriverState *bs, int64_t offset, + unsigned int *nr_zones, + BlockZoneDescriptor *zones) +{ + return bdrv_co_zone_report(bs->file->bs, offset, nr_zones, zones); +} + +static int coroutine_fn GRAPH_RDLOCK +raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, + int64_t offset, int64_t len) +{ + return bdrv_co_zone_mgmt(bs->file->bs, op, offset, len); +} + static int64_t coroutine_fn GRAPH_RDLOCK raw_co_getlength(BlockDriverState *bs) { @@ -XXX,XX +XXX,XX @@ BlockDriver bdrv_raw = { .bdrv_co_pwritev = &raw_co_pwritev, .bdrv_co_pwrite_zeroes = &raw_co_pwrite_zeroes, .bdrv_co_pdiscard = &raw_co_pdiscard, + .bdrv_co_zone_report = &raw_co_zone_report, + .bdrv_co_zone_mgmt = &raw_co_zone_mgmt, .bdrv_co_block_status = &raw_co_block_status, .bdrv_co_copy_range_from = &raw_co_copy_range_from, .bdrv_co_copy_range_to = &raw_co_copy_range_to, -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Putting zoned/non-zoned BlockDrivers on top of each other is not allowed. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-6-faithilikerun@gmail.com [Adjust commit message prefix as suggested by Philippe Mathieu-Daudé <philmd@linaro.org> and clarify that the check is about zoned BlockDrivers. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block_int-common.h | 5 +++++ block.c | 19 +++++++++++++++++++ block/file-posix.c | 12 ++++++++++++ block/raw-format.c | 1 + 4 files changed, 37 insertions(+) diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { */ bool is_format; + /* + * Set to true if the BlockDriver supports zoned children. + */ + bool supports_zoned_children; + /* * Drivers not implementing bdrv_parse_filename nor bdrv_open should have * this field set to true, except ones that are defined only by their diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_add_child(BlockDriverState *parent_bs, BlockDriverState *child_bs, return; } + /* + * Non-zoned block drivers do not follow zoned storage constraints + * (i.e. sequential writes to zones). Refuse mixing zoned and non-zoned + * drivers in a graph. + */ + if (!parent_bs->drv->supports_zoned_children && + child_bs->bl.zoned == BLK_Z_HM) { + /* + * The host-aware model allows zoned storage constraints and random + * write. Allow mixing host-aware and non-zoned drivers. Using + * host-aware device as a regular device. + */ + error_setg(errp, "Cannot add a %s child to a %s parent", + child_bs->bl.zoned == BLK_Z_HM ? "zoned" : "non-zoned", + parent_bs->drv->supports_zoned_children ? + "support zoned children" : "not support zoned children"); + return; + } + if (!QLIST_EMPTY(&child_bs->parents)) { error_setg(errp, "The node %s already has a parent", child_bs->node_name); 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, goto fail; } } +#ifdef CONFIG_BLKZONED + /* + * The kernel page cache does not reliably work for writes to SWR zones + * of zoned block device because it can not guarantee the order of writes. + */ + if ((bs->bl.zoned != BLK_Z_NONE) && + (!(s->open_flags & O_DIRECT))) { + error_setg(errp, "The driver supports zoned devices, and it requires " + "cache.direct=on, which was not specified."); + return -EINVAL; /* No host kernel page cache */ + } +#endif if (S_ISBLK(st.st_mode)) { #ifdef __linux__ diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static void raw_child_perm(BlockDriverState *bs, BdrvChild *c, BlockDriver bdrv_raw = { .format_name = "raw", .instance_size = sizeof(BDRVRawState), + .supports_zoned_children = true, .bdrv_probe = &raw_probe, .bdrv_reopen_prepare = &raw_reopen_prepare, .bdrv_reopen_commit = &raw_reopen_commit, -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> The new block layer APIs of zoned block devices can be tested by: $ tests/qemu-iotests/check zoned Run each zone operation on a newly created null_blk device and see whether it outputs the same zone information. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-7-faithilikerun@gmail.com [Adjust commit message prefix as suggested by Philippe Mathieu-Daudé <philmd@linaro.org>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qemu-iotests/tests/zoned | 89 ++++++++++++++++++++++++++++++ tests/qemu-iotests/tests/zoned.out | 53 ++++++++++++++++++ 2 files changed, 142 insertions(+) create mode 100755 tests/qemu-iotests/tests/zoned create mode 100644 tests/qemu-iotests/tests/zoned.out diff --git a/tests/qemu-iotests/tests/zoned b/tests/qemu-iotests/tests/zoned new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/tests/zoned @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env bash +# +# Test zone management operations. +# + +seq="$(basename $0)" +echo "QA output created by $seq" +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img + sudo -n rmmod null_blk +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ../common.rc +. ../common.filter +. ../common.qemu + +# This test only runs on Linux hosts with raw image files. +_supported_fmt raw +_supported_proto file +_supported_os Linux + +sudo -n true || \ + _notrun 'Password-less sudo required' + +IMG="--image-opts -n driver=host_device,filename=/dev/nullb0" +QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT + +echo "Testing a null_blk device:" +echo "case 1: if the operations work" +sudo -n modprobe null_blk nr_devices=1 zoned=1 +sudo -n chmod 0666 /dev/nullb0 + +echo "(1) report the first zone:" +$QEMU_IO $IMG -c "zrp 0 1" +echo +echo "report the first 10 zones" +$QEMU_IO $IMG -c "zrp 0 10" +echo +echo "report the last zone:" +$QEMU_IO $IMG -c "zrp 0x3e70000000 2" # 0x3e70000000 / 512 = 0x1f380000 +echo +echo +echo "(2) opening the first zone" +$QEMU_IO $IMG -c "zo 0 268435456" # 268435456 / 512 = 524288 +echo "report after:" +$QEMU_IO $IMG -c "zrp 0 1" +echo +echo "opening the second zone" +$QEMU_IO $IMG -c "zo 268435456 268435456" # +echo "report after:" +$QEMU_IO $IMG -c "zrp 268435456 1" +echo +echo "opening the last zone" +$QEMU_IO $IMG -c "zo 0x3e70000000 268435456" +echo "report after:" +$QEMU_IO $IMG -c "zrp 0x3e70000000 2" +echo +echo +echo "(3) closing the first zone" +$QEMU_IO $IMG -c "zc 0 268435456" +echo "report after:" +$QEMU_IO $IMG -c "zrp 0 1" +echo +echo "closing the last zone" +$QEMU_IO $IMG -c "zc 0x3e70000000 268435456" +echo "report after:" +$QEMU_IO $IMG -c "zrp 0x3e70000000 2" +echo +echo +echo "(4) finishing the second zone" +$QEMU_IO $IMG -c "zf 268435456 268435456" +echo "After finishing a zone:" +$QEMU_IO $IMG -c "zrp 268435456 1" +echo +echo +echo "(5) resetting the second zone" +$QEMU_IO $IMG -c "zrs 268435456 268435456" +echo "After resetting a zone:" +$QEMU_IO $IMG -c "zrp 268435456 1" + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/tests/zoned.out b/tests/qemu-iotests/tests/zoned.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/tests/zoned.out @@ -XXX,XX +XXX,XX @@ +QA output created by zoned +Testing a null_blk device: +case 1: if the operations work +(1) report the first zone: +start: 0x0, len 0x80000, cap 0x80000, wptr 0x0, zcond:1, [type: 2] + +report the first 10 zones +start: 0x0, len 0x80000, cap 0x80000, wptr 0x0, zcond:1, [type: 2] +start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80000, zcond:1, [type: 2] +start: 0x100000, len 0x80000, cap 0x80000, wptr 0x100000, zcond:1, [type: 2] +start: 0x180000, len 0x80000, cap 0x80000, wptr 0x180000, zcond:1, [type: 2] +start: 0x200000, len 0x80000, cap 0x80000, wptr 0x200000, zcond:1, [type: 2] +start: 0x280000, len 0x80000, cap 0x80000, wptr 0x280000, zcond:1, [type: 2] +start: 0x300000, len 0x80000, cap 0x80000, wptr 0x300000, zcond:1, [type: 2] +start: 0x380000, len 0x80000, cap 0x80000, wptr 0x380000, zcond:1, [type: 2] +start: 0x400000, len 0x80000, cap 0x80000, wptr 0x400000, zcond:1, [type: 2] +start: 0x480000, len 0x80000, cap 0x80000, wptr 0x480000, zcond:1, [type: 2] + +report the last zone: +start: 0x1f380000, len 0x80000, cap 0x80000, wptr 0x1f380000, zcond:1, [type: 2] + + +(2) opening the first zone +report after: +start: 0x0, len 0x80000, cap 0x80000, wptr 0x0, zcond:3, [type: 2] + +opening the second zone +report after: +start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80000, zcond:3, [type: 2] + +opening the last zone +report after: +start: 0x1f380000, len 0x80000, cap 0x80000, wptr 0x1f380000, zcond:3, [type: 2] + + +(3) closing the first zone +report after: +start: 0x0, len 0x80000, cap 0x80000, wptr 0x0, zcond:1, [type: 2] + +closing the last zone +report after: +start: 0x1f380000, len 0x80000, cap 0x80000, wptr 0x1f380000, zcond:1, [type: 2] + + +(4) finishing the second zone +After finishing a zone: +start: 0x80000, len 0x80000, cap 0x80000, wptr 0x100000, zcond:14, [type: 2] + + +(5) resetting the second zone +After resetting a zone: +start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80000, zcond:1, [type: 2] +*** done -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-8-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/file-posix.c | 3 +++ block/trace-events | 2 ++ 2 files changed, 5 insertions(+) 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 coroutine_fn raw_co_zone_report(BlockDriverState *bs, int64_t offset, }, }; + trace_zbd_zone_report(bs, *nr_zones, offset >> BDRV_SECTOR_BITS); return raw_thread_pool_submit(bs, handle_aiocb_zone_report, &acb); } #endif @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, }, }; + trace_zbd_zone_mgmt(bs, op_name, offset >> BDRV_SECTOR_BITS, + len >> BDRV_SECTOR_BITS); ret = raw_thread_pool_submit(bs, handle_aiocb_zone_mgmt, &acb); if (ret != 0) { error_report("ioctl %s failed %d", op_name, ret); diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ file_FindEjectableOpticalMedia(const char *media) "Matching using %s" file_setup_cdrom(const char *partition) "Using %s as optical disc" file_hdev_is_sg(int type, int version) "SG device found: type=%d, version=%d" file_flush_fdatasync_failed(int err) "errno %d" +zbd_zone_report(void *bs, unsigned int nr_zones, int64_t sector) "bs %p report %d zones starting at sector offset 0x%" PRIx64 "" +zbd_zone_mgmt(void *bs, const char *op_name, int64_t sector, int64_t len) "bs %p %s starts at sector offset 0x%" PRIx64 " over a range of 0x%" PRIx64 " sectors" # ssh.c sftp_error(const char *op, const char *ssh_err, int ssh_err_code, int sftp_err_code) "%s failed: %s (libssh error code: %d, sftp error code: %d)" -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Add the documentation about the zoned device support to virtio-blk emulation. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Acked-by: Kevin Wolf <kwolf@redhat.com> Message-id: 20230324090605.28361-9-faithilikerun@gmail.com [Add index-api.rst to fix "zoned-storage.rst:document isn't included in any toctree" error. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- docs/devel/index-api.rst | 1 + docs/devel/zoned-storage.rst | 43 ++++++++++++++++++++++++++ docs/system/qemu-block-drivers.rst.inc | 6 ++++ 3 files changed, 50 insertions(+) create mode 100644 docs/devel/zoned-storage.rst diff --git a/docs/devel/index-api.rst b/docs/devel/index-api.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/index-api.rst +++ b/docs/devel/index-api.rst @@ -XXX,XX +XXX,XX @@ generated from in-code annotations to function prototypes. memory modules ui + zoned-storage diff --git a/docs/devel/zoned-storage.rst b/docs/devel/zoned-storage.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/devel/zoned-storage.rst @@ -XXX,XX +XXX,XX @@ +============= +zoned-storage +============= + +Zoned Block Devices (ZBDs) divide the LBA space into block regions called zones +that are larger than the LBA size. They can only allow sequential writes, which +can reduce write amplification in SSDs, and potentially lead to higher +throughput and increased capacity. More details about ZBDs can be found at: + +https://zonedstorage.io/docs/introduction/zoned-storage + +1. Block layer APIs for zoned storage +------------------------------------- +QEMU block layer supports three zoned storage models: +- BLK_Z_HM: The host-managed zoned model only allows sequential writes access +to zones. It supports ZBD-specific I/O commands that can be used by a host to +manage the zones of a device. +- BLK_Z_HA: The host-aware zoned model allows random write operations in +zones, making it backward compatible with regular block devices. +- BLK_Z_NONE: The non-zoned model has no zones support. It includes both +regular and drive-managed ZBD devices. ZBD-specific I/O commands are not +supported. + +The block device information resides inside BlockDriverState. QEMU uses +BlockLimits struct(BlockDriverState::bl) that is continuously accessed by the +block layer while processing I/O requests. A BlockBackend has a root pointer to +a BlockDriverState graph(for example, raw format on top of file-posix). The +zoned storage information can be propagated from the leaf BlockDriverState all +the way up to the BlockBackend. If the zoned storage model in file-posix is +set to BLK_Z_HM, then block drivers will declare support for zoned host device. + +The block layer APIs support commands needed for zoned storage devices, +including report zones, four zone operations, and zone append. + +2. Emulating zoned storage controllers +-------------------------------------- +When the BlockBackend's BlockLimits model reports a zoned storage device, users +like the virtio-blk emulation or the qemu-io-cmds.c utility can use block layer +APIs for zoned storage emulation or testing. + +For example, to test zone_report on a null_blk device using qemu-io is: +$ path/to/qemu-io --image-opts -n driver=host_device,filename=/dev/nullb0 +-c "zrp offset nr_zones" diff --git a/docs/system/qemu-block-drivers.rst.inc b/docs/system/qemu-block-drivers.rst.inc index XXXXXXX..XXXXXXX 100644 --- a/docs/system/qemu-block-drivers.rst.inc +++ b/docs/system/qemu-block-drivers.rst.inc @@ -XXX,XX +XXX,XX @@ Hard disks you may corrupt your host data (use the ``-snapshot`` command line option or modify the device permissions accordingly). +Zoned block devices + Zoned block devices can be passed through to the guest if the emulated storage + controller supports zoned storage. Use ``--blockdev host_device, + node-name=drive0,filename=/dev/nullb0,cache.direct=on`` to pass through + ``/dev/nullb0`` as ``drive0``. + Windows ^^^^^^^ -- 2.39.2 From: Philippe Mathieu-Daudé <philmd@linaro.org> Introduce the BdrvDmgUncompressFunc type defintion. To emphasis dmg_uncompress_bz2 and dmg_uncompress_lzfse are pointer to functions, declare them using this new typedef. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230320152610.32052-1-philmd@linaro.org Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/dmg.h | 8 ++++---- block/dmg.c | 7 ++----- 2 files changed, 6 insertions(+), 9 deletions(-) diff --git a/block/dmg.h b/block/dmg.h index XXXXXXX..XXXXXXX 100644 --- a/block/dmg.h +++ b/block/dmg.h @@ -XXX,XX +XXX,XX @@ typedef struct BDRVDMGState { z_stream zstream; } BDRVDMGState; -extern int (*dmg_uncompress_bz2)(char *next_in, unsigned int avail_in, - char *next_out, unsigned int avail_out); +typedef int BdrvDmgUncompressFunc(char *next_in, unsigned int avail_in, + char *next_out, unsigned int avail_out); -extern int (*dmg_uncompress_lzfse)(char *next_in, unsigned int avail_in, - char *next_out, unsigned int avail_out); +extern BdrvDmgUncompressFunc *dmg_uncompress_bz2; +extern BdrvDmgUncompressFunc *dmg_uncompress_lzfse; #endif 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 @@ #include "qemu/memalign.h" #include "dmg.h" -int (*dmg_uncompress_bz2)(char *next_in, unsigned int avail_in, - char *next_out, unsigned int avail_out); - -int (*dmg_uncompress_lzfse)(char *next_in, unsigned int avail_in, - char *next_out, unsigned int avail_out); +BdrvDmgUncompressFunc *dmg_uncompress_bz2; +BdrvDmgUncompressFunc *dmg_uncompress_lzfse; enum { /* Limit chunk sizes to prevent unreasonable amounts of memory being used -- 2.39.2 From: Thomas De Schampheleire <thomas.de_schampheleire@nokia.com> The event filename is an absolute path. Convert it to a relative path when writing '#line' directives, to preserve reproducibility of the generated output when different base paths are used. Signed-off-by: Thomas De Schampheleire <thomas.de_schampheleire@nokia.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20230406080045.21696-1-thomas.de_schampheleire@nokia.com> --- scripts/tracetool/backend/ftrace.py | 4 +++- scripts/tracetool/backend/log.py | 4 +++- scripts/tracetool/backend/syslog.py | 4 +++- 3 files changed, 9 insertions(+), 3 deletions(-) diff --git a/scripts/tracetool/backend/ftrace.py b/scripts/tracetool/backend/ftrace.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/tracetool/backend/ftrace.py +++ b/scripts/tracetool/backend/ftrace.py @@ -XXX,XX +XXX,XX @@ __email__ = "stefanha@redhat.com" +import os.path + from tracetool import out @@ -XXX,XX +XXX,XX @@ def generate_h(event, group): args=event.args, event_id="TRACE_" + event.name.upper(), event_lineno=event.lineno, - event_filename=event.filename, + event_filename=os.path.relpath(event.filename), fmt=event.fmt.rstrip("\n"), argnames=argnames) diff --git a/scripts/tracetool/backend/log.py b/scripts/tracetool/backend/log.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/tracetool/backend/log.py +++ b/scripts/tracetool/backend/log.py @@ -XXX,XX +XXX,XX @@ __email__ = "stefanha@redhat.com" +import os.path + from tracetool import out @@ -XXX,XX +XXX,XX @@ def generate_h(event, group): ' }', cond=cond, event_lineno=event.lineno, - event_filename=event.filename, + event_filename=os.path.relpath(event.filename), name=event.name, fmt=event.fmt.rstrip("\n"), argnames=argnames) diff --git a/scripts/tracetool/backend/syslog.py b/scripts/tracetool/backend/syslog.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/tracetool/backend/syslog.py +++ b/scripts/tracetool/backend/syslog.py @@ -XXX,XX +XXX,XX @@ __email__ = "stefanha@redhat.com" +import os.path + from tracetool import out @@ -XXX,XX +XXX,XX @@ def generate_h(event, group): ' }', cond=cond, event_lineno=event.lineno, - event_filename=event.filename, + event_filename=os.path.relpath(event.filename), name=event.name, fmt=event.fmt.rstrip("\n"), argnames=argnames) -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Since Linux doesn't have a user API to issue zone append operations to zoned devices from user space, the file-posix driver is modified to add zone append emulation using regular writes. To do this, the file-posix driver tracks the wp location of all zones of the device. It uses an array of uint64_t. The most significant bit of each wp location indicates if the zone type is conventional zones. The zones wp can be changed due to the following operations issued: - zone reset: change the wp to the start offset of that zone - zone finish: change to the end location of that zone - write to a zone - zone append Signed-off-by: Sam Li <faithilikerun@gmail.com> Message-id: 20230407081657.17947-2-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block-common.h | 14 +++ include/block/block_int-common.h | 5 + block/file-posix.c | 173 ++++++++++++++++++++++++++++++- 3 files changed, 189 insertions(+), 3 deletions(-) diff --git a/include/block/block-common.h b/include/block/block-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-common.h +++ b/include/block/block-common.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockZoneDescriptor { BlockZoneState state; } BlockZoneDescriptor; +/* + * Track write pointers of a zone in bytes. + */ +typedef struct BlockZoneWps { + CoMutex colock; + uint64_t wp[]; +} BlockZoneWps; + typedef struct BlockDriverInfo { /* in bytes, 0 if irrelevant */ int cluster_size; @@ -XXX,XX +XXX,XX @@ typedef enum { #define BDRV_SECTOR_BITS 9 #define BDRV_SECTOR_SIZE (1ULL << BDRV_SECTOR_BITS) +/* + * Get the first most significant bit of wp. If it is zero, then + * the zone type is SWR. + */ +#define BDRV_ZT_IS_CONV(wp) (wp & (1ULL << 63)) + #define BDRV_REQUEST_MAX_SECTORS MIN_CONST(SIZE_MAX >> BDRV_SECTOR_BITS, \ INT_MAX >> BDRV_SECTOR_BITS) #define BDRV_REQUEST_MAX_BYTES (BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS) diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockLimits { /* maximum number of active zones */ int64_t max_active_zones; + + int64_t write_granularity; } BlockLimits; typedef struct BdrvOpBlocker BdrvOpBlocker; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { CoMutex bsc_modify_lock; /* Always non-NULL, but must only be dereferenced under an RCU read guard */ BdrvBlockStatusCache *block_status_cache; + + /* array of write pointers' location of each zone in the zoned device. */ + BlockZoneWps *wps; }; struct BlockBackendRootState { 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 hdev_get_max_segments(int fd, struct stat *st) #endif } +#if defined(CONFIG_BLKZONED) +/* + * If the reset_all flag is true, then the wps of zone whose state is + * not readonly or offline should be all reset to the start sector. + * Else, take the real wp of the device. + */ +static int get_zones_wp(BlockDriverState *bs, int fd, int64_t offset, + unsigned int nrz, bool reset_all) +{ + struct blk_zone *blkz; + size_t rep_size; + uint64_t sector = offset >> BDRV_SECTOR_BITS; + BlockZoneWps *wps = bs->wps; + int j = offset / bs->bl.zone_size; + int ret, n = 0, i = 0; + rep_size = sizeof(struct blk_zone_report) + nrz * sizeof(struct blk_zone); + g_autofree struct blk_zone_report *rep = NULL; + + rep = g_malloc(rep_size); + blkz = (struct blk_zone *)(rep + 1); + while (n < nrz) { + memset(rep, 0, rep_size); + rep->sector = sector; + rep->nr_zones = nrz - n; + + do { + ret = ioctl(fd, BLKREPORTZONE, rep); + } while (ret != 0 && errno == EINTR); + if (ret != 0) { + error_report("%d: ioctl BLKREPORTZONE at %" PRId64 " failed %d", + fd, offset, errno); + return -errno; + } + + if (!rep->nr_zones) { + break; + } + + for (i = 0; i < rep->nr_zones; ++i, ++n, ++j) { + /* + * The wp tracking cares only about sequential writes required and + * sequential write preferred zones so that the wp can advance to + * the right location. + * Use the most significant bit of the wp location to indicate the + * zone type: 0 for SWR/SWP zones and 1 for conventional zones. + */ + if (blkz[i].type == BLK_ZONE_TYPE_CONVENTIONAL) { + wps->wp[j] |= 1ULL << 63; + } else { + switch(blkz[i].cond) { + case BLK_ZONE_COND_FULL: + case BLK_ZONE_COND_READONLY: + /* Zone not writable */ + wps->wp[j] = (blkz[i].start + blkz[i].len) << BDRV_SECTOR_BITS; + break; + case BLK_ZONE_COND_OFFLINE: + /* Zone not writable nor readable */ + wps->wp[j] = (blkz[i].start) << BDRV_SECTOR_BITS; + break; + default: + if (reset_all) { + wps->wp[j] = blkz[i].start << BDRV_SECTOR_BITS; + } else { + wps->wp[j] = blkz[i].wp << BDRV_SECTOR_BITS; + } + break; + } + } + } + sector = blkz[i - 1].start + blkz[i - 1].len; + } + + return 0; +} + +static void update_zones_wp(BlockDriverState *bs, int fd, int64_t offset, + unsigned int nrz) +{ + if (get_zones_wp(bs, fd, offset, nrz, 0) < 0) { + error_report("update zone wp failed"); + } +} +#endif + static void raw_refresh_limits(BlockDriverState *bs, Error **errp) { BDRVRawState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) if (ret >= 0) { bs->bl.max_active_zones = ret; } + + ret = get_sysfs_long_val(&st, "physical_block_size"); + if (ret >= 0) { + bs->bl.write_granularity = ret; + } + + /* The refresh_limits() function can be called multiple times. */ + g_free(bs->wps); + bs->wps = g_malloc(sizeof(BlockZoneWps) + + sizeof(int64_t) * bs->bl.nr_zones); + ret = get_zones_wp(bs, s->fd, 0, bs->bl.nr_zones, 0); + if (ret < 0) { + error_setg_errno(errp, -ret, "report wps failed"); + bs->wps = NULL; + return; + } + qemu_co_mutex_init(&bs->wps->colock); return; } out: @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset, { BDRVRawState *s = bs->opaque; RawPosixAIOData acb; + int ret; if (fd_open(bs) < 0) return -EIO; +#if defined(CONFIG_BLKZONED) + if (type & QEMU_AIO_WRITE && bs->wps) { + qemu_co_mutex_lock(&bs->wps->colock); + } +#endif /* * When using O_DIRECT, the request must be aligned to be able to use @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset, } else if (s->use_linux_io_uring) { LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs)); assert(qiov->size == bytes); - return luring_co_submit(bs, aio, s->fd, offset, qiov, type); + ret = luring_co_submit(bs, aio, s->fd, offset, qiov, type); + goto out; #endif #ifdef CONFIG_LINUX_AIO } else if (s->use_linux_aio) { LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs)); assert(qiov->size == bytes); - return laio_co_submit(bs, aio, s->fd, offset, qiov, type, + ret = laio_co_submit(bs, aio, s->fd, offset, qiov, type, s->aio_max_batch); + goto out; #endif } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset, }; assert(qiov->size == bytes); - return raw_thread_pool_submit(bs, handle_aiocb_rw, &acb); + ret = raw_thread_pool_submit(bs, handle_aiocb_rw, &acb); + +out: +#if defined(CONFIG_BLKZONED) + BlockZoneWps *wps = bs->wps; + if (ret == 0) { + if (type & QEMU_AIO_WRITE && wps && bs->bl.zone_size) { + uint64_t *wp = &wps->wp[offset / bs->bl.zone_size]; + if (!BDRV_ZT_IS_CONV(*wp)) { + /* Advance the wp if needed */ + if (offset + bytes > *wp) { + *wp = offset + bytes; + } + } + } + } else { + if (type & QEMU_AIO_WRITE) { + update_zones_wp(bs, s->fd, 0, 1); + } + } + + if (type & QEMU_AIO_WRITE && wps) { + qemu_co_mutex_unlock(&wps->colock); + } +#endif + return ret; } static int coroutine_fn raw_co_preadv(BlockDriverState *bs, int64_t offset, @@ -XXX,XX +XXX,XX @@ static void raw_close(BlockDriverState *bs) BDRVRawState *s = bs->opaque; if (s->fd >= 0) { +#if defined(CONFIG_BLKZONED) + g_free(bs->wps); +#endif qemu_close(s->fd); s->fd = -1; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, const char *op_name; unsigned long zo; int ret; + BlockZoneWps *wps = bs->wps; int64_t capacity = bs->total_sectors << BDRV_SECTOR_BITS; zone_size = bs->bl.zone_size; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, return -EINVAL; } + QEMU_LOCK_GUARD(&wps->colock); + uint32_t i = offset / bs->bl.zone_size; + uint32_t nrz = len / bs->bl.zone_size; + uint64_t *wp = &wps->wp[i]; + if (BDRV_ZT_IS_CONV(*wp) && len != capacity) { + error_report("zone mgmt operations are not allowed for conventional zones"); + return -EIO; + } + switch (op) { case BLK_ZO_OPEN: op_name = "BLKOPENZONE"; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, len >> BDRV_SECTOR_BITS); ret = raw_thread_pool_submit(bs, handle_aiocb_zone_mgmt, &acb); if (ret != 0) { + update_zones_wp(bs, s->fd, offset, i); error_report("ioctl %s failed %d", op_name, ret); + return ret; + } + + if (zo == BLKRESETZONE && len == capacity) { + ret = get_zones_wp(bs, s->fd, 0, bs->bl.nr_zones, 1); + if (ret < 0) { + error_report("reporting single wp failed"); + return ret; + } + } else if (zo == BLKRESETZONE) { + for (int j = 0; j < nrz; ++j) { + wp[j] = offset + j * zone_size; + } + } else if (zo == BLKFINISHZONE) { + for (int j = 0; j < nrz; ++j) { + /* The zoned device allows the last zone smaller that the + * zone size. */ + wp[j] = MIN(offset + (j + 1) * zone_size, offset + len); + } } return ret; -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> A zone append command is a write operation that specifies the first logical block of a zone as the write position. When writing to a zoned block device using zone append, the byte offset of the call may point at any position within the zone to which the data is being appended. Upon completion the device will respond with the position where the data has been written in the zone. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20230407081657.17947-3-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block-io.h | 4 +++ include/block/block_int-common.h | 3 ++ include/block/raw-aio.h | 4 ++- include/sysemu/block-backend-io.h | 9 +++++ block/block-backend.c | 60 +++++++++++++++++++++++++++++++ block/file-posix.c | 58 ++++++++++++++++++++++++++---- block/io.c | 27 ++++++++++++++ block/io_uring.c | 4 +++ block/linux-aio.c | 3 ++ block/raw-format.c | 8 +++++ 10 files changed, 172 insertions(+), 8 deletions(-) diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_report(BlockDriverState *bs, int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, int64_t offset, int64_t len); +int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_append(BlockDriverState *bs, + int64_t *offset, + QEMUIOVector *qiov, + BdrvRequestFlags flags); bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); int bdrv_block_status(BlockDriverState *bs, int64_t offset, diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { BlockZoneDescriptor *zones); int coroutine_fn (*bdrv_co_zone_mgmt)(BlockDriverState *bs, BlockZoneOp op, int64_t offset, int64_t len); + int coroutine_fn (*bdrv_co_zone_append)(BlockDriverState *bs, + int64_t *offset, QEMUIOVector *qiov, + BdrvRequestFlags flags); /* removable device specific */ bool coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_is_inserted)( diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/raw-aio.h +++ b/include/block/raw-aio.h @@ -XXX,XX +XXX,XX @@ #define QEMU_AIO_TRUNCATE 0x0080 #define QEMU_AIO_ZONE_REPORT 0x0100 #define QEMU_AIO_ZONE_MGMT 0x0200 +#define QEMU_AIO_ZONE_APPEND 0x0400 #define QEMU_AIO_TYPE_MASK \ (QEMU_AIO_READ | \ QEMU_AIO_WRITE | \ @@ -XXX,XX +XXX,XX @@ QEMU_AIO_COPY_RANGE | \ QEMU_AIO_TRUNCATE | \ QEMU_AIO_ZONE_REPORT | \ - QEMU_AIO_ZONE_MGMT) + QEMU_AIO_ZONE_MGMT | \ + QEMU_AIO_ZONE_APPEND) /* AIO flags */ #define QEMU_AIO_MISALIGNED 0x1000 diff --git a/include/sysemu/block-backend-io.h b/include/sysemu/block-backend-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend-io.h +++ b/include/sysemu/block-backend-io.h @@ -XXX,XX +XXX,XX @@ BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset, BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op, int64_t offset, int64_t len, BlockCompletionFunc *cb, void *opaque); +BlockAIOCB *blk_aio_zone_append(BlockBackend *blk, int64_t *offset, + QEMUIOVector *qiov, BdrvRequestFlags flags, + BlockCompletionFunc *cb, void *opaque); BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes, BlockCompletionFunc *cb, void *opaque); void blk_aio_cancel_async(BlockAIOCB *acb); @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op, int64_t offset, int64_t len); int co_wrapper_mixed blk_zone_mgmt(BlockBackend *blk, BlockZoneOp op, int64_t offset, int64_t len); +int coroutine_fn blk_co_zone_append(BlockBackend *blk, int64_t *offset, + QEMUIOVector *qiov, + BdrvRequestFlags flags); +int co_wrapper_mixed blk_zone_append(BlockBackend *blk, int64_t *offset, + QEMUIOVector *qiov, + BdrvRequestFlags flags); int co_wrapper_mixed blk_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes); 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 @@ BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op, return &acb->common; } +static void coroutine_fn blk_aio_zone_append_entry(void *opaque) +{ + BlkAioEmAIOCB *acb = opaque; + BlkRwCo *rwco = &acb->rwco; + + rwco->ret = blk_co_zone_append(rwco->blk, (int64_t *)acb->bytes, + rwco->iobuf, rwco->flags); + blk_aio_complete(acb); +} + +BlockAIOCB *blk_aio_zone_append(BlockBackend *blk, int64_t *offset, + QEMUIOVector *qiov, BdrvRequestFlags flags, + BlockCompletionFunc *cb, void *opaque) { + BlkAioEmAIOCB *acb; + Coroutine *co; + IO_CODE(); + + blk_inc_in_flight(blk); + acb = blk_aio_get(&blk_aio_em_aiocb_info, blk, cb, opaque); + acb->rwco = (BlkRwCo) { + .blk = blk, + .ret = NOT_DONE, + .flags = flags, + .iobuf = qiov, + }; + acb->bytes = (int64_t)offset; + acb->has_returned = false; + + co = qemu_coroutine_create(blk_aio_zone_append_entry, acb); + aio_co_enter(blk_get_aio_context(blk), co); + acb->has_returned = true; + if (acb->rwco.ret != NOT_DONE) { + replay_bh_schedule_oneshot_event(blk_get_aio_context(blk), + blk_aio_complete_bh, acb); + } + + return &acb->common; +} + /* * Send a zone_report command. * offset is a byte offset from the start of the device. No alignment @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_zone_mgmt(BlockBackend *blk, BlockZoneOp op, return ret; } +/* + * Send a zone_append command. + */ +int coroutine_fn blk_co_zone_append(BlockBackend *blk, int64_t *offset, + QEMUIOVector *qiov, BdrvRequestFlags flags) +{ + int ret; + IO_CODE(); + + blk_inc_in_flight(blk); + blk_wait_while_drained(blk); + if (!blk_is_available(blk)) { + blk_dec_in_flight(blk); + return -ENOMEDIUM; + } + + ret = bdrv_co_zone_append(blk_bs(blk), offset, qiov, flags); + blk_dec_in_flight(blk); + return ret; +} + void blk_drain(BlockBackend *blk) { BlockDriverState *bs = blk_bs(blk); 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 @@ typedef struct BDRVRawState { bool has_write_zeroes:1; bool use_linux_aio:1; bool use_linux_io_uring:1; + int64_t *offset; /* offset of zone append operation */ int page_cache_inconsistent; /* errno from fdatasync failure */ bool has_fallocate; bool needs_alignment; @@ -XXX,XX +XXX,XX @@ static ssize_t handle_aiocb_rw_vector(RawPosixAIOData *aiocb) ssize_t len; len = RETRY_ON_EINTR( - (aiocb->aio_type & QEMU_AIO_WRITE) ? + (aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) ? qemu_pwritev(aiocb->aio_fildes, aiocb->io.iov, aiocb->io.niov, @@ -XXX,XX +XXX,XX @@ static ssize_t handle_aiocb_rw_linear(RawPosixAIOData *aiocb, char *buf) ssize_t len; while (offset < aiocb->aio_nbytes) { - if (aiocb->aio_type & QEMU_AIO_WRITE) { + if (aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) { len = pwrite(aiocb->aio_fildes, (const char *)buf + offset, aiocb->aio_nbytes - offset, @@ -XXX,XX +XXX,XX @@ static int handle_aiocb_rw(void *opaque) } nbytes = handle_aiocb_rw_linear(aiocb, buf); - if (!(aiocb->aio_type & QEMU_AIO_WRITE)) { + if (!(aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND))) { char *p = buf; size_t count = aiocb->aio_nbytes, copy; int i; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset, if (fd_open(bs) < 0) return -EIO; #if defined(CONFIG_BLKZONED) - if (type & QEMU_AIO_WRITE && bs->wps) { + if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) && bs->wps) { qemu_co_mutex_lock(&bs->wps->colock); + if (type & QEMU_AIO_ZONE_APPEND && bs->bl.zone_size) { + int index = offset / bs->bl.zone_size; + offset = bs->wps->wp[index]; + } } #endif @@ -XXX,XX +XXX,XX @@ out: #if defined(CONFIG_BLKZONED) BlockZoneWps *wps = bs->wps; if (ret == 0) { - if (type & QEMU_AIO_WRITE && wps && bs->bl.zone_size) { + if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) + && wps && bs->bl.zone_size) { uint64_t *wp = &wps->wp[offset / bs->bl.zone_size]; if (!BDRV_ZT_IS_CONV(*wp)) { + if (type & QEMU_AIO_ZONE_APPEND) { + *s->offset = *wp; + } /* Advance the wp if needed */ if (offset + bytes > *wp) { *wp = offset + bytes; @@ -XXX,XX +XXX,XX @@ out: } } } else { - if (type & QEMU_AIO_WRITE) { + if (type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) { update_zones_wp(bs, s->fd, 0, 1); } } - if (type & QEMU_AIO_WRITE && wps) { + if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) && wps) { qemu_co_mutex_unlock(&wps->colock); } #endif @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, } #endif +#if defined(CONFIG_BLKZONED) +static int coroutine_fn raw_co_zone_append(BlockDriverState *bs, + int64_t *offset, + QEMUIOVector *qiov, + BdrvRequestFlags flags) { + assert(flags == 0); + int64_t zone_size_mask = bs->bl.zone_size - 1; + int64_t iov_len = 0; + int64_t len = 0; + BDRVRawState *s = bs->opaque; + s->offset = offset; + + if (*offset & zone_size_mask) { + error_report("sector offset %" PRId64 " is not aligned to zone size " + "%" PRId32 "", *offset / 512, bs->bl.zone_size / 512); + return -EINVAL; + } + + int64_t wg = bs->bl.write_granularity; + int64_t wg_mask = wg - 1; + for (int i = 0; i < qiov->niov; i++) { + iov_len = qiov->iov[i].iov_len; + if (iov_len & wg_mask) { + error_report("len of IOVector[%d] %" PRId64 " is not aligned to " + "block size %" PRId64 "", i, iov_len, wg); + return -EINVAL; + } + len += iov_len; + } + + return raw_co_prw(bs, *offset, len, qiov, QEMU_AIO_ZONE_APPEND); +} +#endif + static coroutine_fn int raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes, bool blkdev) @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_host_device = { /* zone management operations */ .bdrv_co_zone_report = raw_co_zone_report, .bdrv_co_zone_mgmt = raw_co_zone_mgmt, + .bdrv_co_zone_append = raw_co_zone_append, #endif }; 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 @@ out: return co.ret; } +int coroutine_fn bdrv_co_zone_append(BlockDriverState *bs, int64_t *offset, + QEMUIOVector *qiov, + BdrvRequestFlags flags) +{ + int ret; + BlockDriver *drv = bs->drv; + CoroutineIOCompletion co = { + .coroutine = qemu_coroutine_self(), + }; + IO_CODE(); + + ret = bdrv_check_qiov_request(*offset, qiov->size, qiov, 0, NULL); + if (ret < 0) { + return ret; + } + + bdrv_inc_in_flight(bs); + if (!drv || !drv->bdrv_co_zone_append || bs->bl.zoned == BLK_Z_NONE) { + co.ret = -ENOTSUP; + goto out; + } + co.ret = drv->bdrv_co_zone_append(bs, offset, qiov, flags); +out: + bdrv_dec_in_flight(bs); + return co.ret; +} + void *qemu_blockalign(BlockDriverState *bs, size_t size) { IO_CODE(); diff --git a/block/io_uring.c b/block/io_uring.c index XXXXXXX..XXXXXXX 100644 --- a/block/io_uring.c +++ b/block/io_uring.c @@ -XXX,XX +XXX,XX @@ static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s, io_uring_prep_writev(sqes, fd, luringcb->qiov->iov, luringcb->qiov->niov, offset); break; + case QEMU_AIO_ZONE_APPEND: + io_uring_prep_writev(sqes, fd, luringcb->qiov->iov, + luringcb->qiov->niov, offset); + break; case QEMU_AIO_READ: io_uring_prep_readv(sqes, fd, luringcb->qiov->iov, luringcb->qiov->niov, offset); diff --git a/block/linux-aio.c b/block/linux-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -XXX,XX +XXX,XX @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset, case QEMU_AIO_WRITE: io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset); break; + case QEMU_AIO_ZONE_APPEND: + io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset); + break; case QEMU_AIO_READ: io_prep_preadv(iocbs, fd, qiov->iov, qiov->niov, offset); break; diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op, return bdrv_co_zone_mgmt(bs->file->bs, op, offset, len); } +static int coroutine_fn GRAPH_RDLOCK +raw_co_zone_append(BlockDriverState *bs,int64_t *offset, QEMUIOVector *qiov, + BdrvRequestFlags flags) +{ + return bdrv_co_zone_append(bs->file->bs, offset, qiov, flags); +} + static int64_t coroutine_fn GRAPH_RDLOCK raw_co_getlength(BlockDriverState *bs) { @@ -XXX,XX +XXX,XX @@ BlockDriver bdrv_raw = { .bdrv_co_pdiscard = &raw_co_pdiscard, .bdrv_co_zone_report = &raw_co_zone_report, .bdrv_co_zone_mgmt = &raw_co_zone_mgmt, + .bdrv_co_zone_append = &raw_co_zone_append, .bdrv_co_block_status = &raw_co_block_status, .bdrv_co_copy_range_from = &raw_co_copy_range_from, .bdrv_co_copy_range_to = &raw_co_copy_range_to, -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> The patch tests zone append writes by reporting the zone wp after the completion of the call. "zap -p" option can print the sector offset value after completion, which should be the start sector where the append write begins. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20230407081657.17947-4-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qemu-io-cmds.c | 75 ++++++++++++++++++++++++++++++ tests/qemu-iotests/tests/zoned | 16 +++++++ tests/qemu-iotests/tests/zoned.out | 16 +++++++ 3 files changed, 107 insertions(+) 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 const cmdinfo_t zone_reset_cmd = { .oneline = "reset a zone write pointer in zone block device", }; +static int do_aio_zone_append(BlockBackend *blk, QEMUIOVector *qiov, + int64_t *offset, int flags, int *total) +{ + int async_ret = NOT_DONE; + + blk_aio_zone_append(blk, offset, qiov, flags, aio_rw_done, &async_ret); + while (async_ret == NOT_DONE) { + main_loop_wait(false); + } + + *total = qiov->size; + return async_ret < 0 ? async_ret : 1; +} + +static int zone_append_f(BlockBackend *blk, int argc, char **argv) +{ + int ret; + bool pflag = false; + int flags = 0; + int total = 0; + int64_t offset; + char *buf; + int c, nr_iov; + int pattern = 0xcd; + QEMUIOVector qiov; + + if (optind > argc - 3) { + return -EINVAL; + } + + if ((c = getopt(argc, argv, "p")) != -1) { + pflag = true; + } + + offset = cvtnum(argv[optind]); + if (offset < 0) { + print_cvtnum_err(offset, argv[optind]); + return offset; + } + optind++; + nr_iov = argc - optind; + buf = create_iovec(blk, &qiov, &argv[optind], nr_iov, pattern, + flags & BDRV_REQ_REGISTERED_BUF); + if (buf == NULL) { + return -EINVAL; + } + ret = do_aio_zone_append(blk, &qiov, &offset, flags, &total); + if (ret < 0) { + printf("zone append failed: %s\n", strerror(-ret)); + goto out; + } + + if (pflag) { + printf("After zap done, the append sector is 0x%" PRIx64 "\n", + tosector(offset)); + } + +out: + qemu_io_free(blk, buf, qiov.size, + flags & BDRV_REQ_REGISTERED_BUF); + qemu_iovec_destroy(&qiov); + return ret; +} + +static const cmdinfo_t zone_append_cmd = { + .name = "zone_append", + .altname = "zap", + .cfunc = zone_append_f, + .argmin = 3, + .argmax = 4, + .args = "offset len [len..]", + .oneline = "append write a number of bytes at a specified offset", +}; + static int truncate_f(BlockBackend *blk, int argc, char **argv); static const cmdinfo_t truncate_cmd = { .name = "truncate", @@ -XXX,XX +XXX,XX @@ static void __attribute((constructor)) init_qemuio_commands(void) qemuio_add_command(&zone_close_cmd); qemuio_add_command(&zone_finish_cmd); qemuio_add_command(&zone_reset_cmd); + qemuio_add_command(&zone_append_cmd); qemuio_add_command(&truncate_cmd); qemuio_add_command(&length_cmd); qemuio_add_command(&info_cmd); diff --git a/tests/qemu-iotests/tests/zoned b/tests/qemu-iotests/tests/zoned index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/tests/zoned +++ b/tests/qemu-iotests/tests/zoned @@ -XXX,XX +XXX,XX @@ echo "(5) resetting the second zone" $QEMU_IO $IMG -c "zrs 268435456 268435456" echo "After resetting a zone:" $QEMU_IO $IMG -c "zrp 268435456 1" +echo +echo +echo "(6) append write" # the physical block size of the device is 4096 +$QEMU_IO $IMG -c "zrp 0 1" +$QEMU_IO $IMG -c "zap -p 0 0x1000 0x2000" +echo "After appending the first zone firstly:" +$QEMU_IO $IMG -c "zrp 0 1" +$QEMU_IO $IMG -c "zap -p 0 0x1000 0x2000" +echo "After appending the first zone secondly:" +$QEMU_IO $IMG -c "zrp 0 1" +$QEMU_IO $IMG -c "zap -p 268435456 0x1000 0x2000" +echo "After appending the second zone firstly:" +$QEMU_IO $IMG -c "zrp 268435456 1" +$QEMU_IO $IMG -c "zap -p 268435456 0x1000 0x2000" +echo "After appending the second zone secondly:" +$QEMU_IO $IMG -c "zrp 268435456 1" # success, all done echo "*** done" diff --git a/tests/qemu-iotests/tests/zoned.out b/tests/qemu-iotests/tests/zoned.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/tests/zoned.out +++ b/tests/qemu-iotests/tests/zoned.out @@ -XXX,XX +XXX,XX @@ start: 0x80000, len 0x80000, cap 0x80000, wptr 0x100000, zcond:14, [type: 2] (5) resetting the second zone After resetting a zone: start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80000, zcond:1, [type: 2] + + +(6) append write +start: 0x0, len 0x80000, cap 0x80000, wptr 0x0, zcond:1, [type: 2] +After zap done, the append sector is 0x0 +After appending the first zone firstly: +start: 0x0, len 0x80000, cap 0x80000, wptr 0x18, zcond:2, [type: 2] +After zap done, the append sector is 0x18 +After appending the first zone secondly: +start: 0x0, len 0x80000, cap 0x80000, wptr 0x30, zcond:2, [type: 2] +After zap done, the append sector is 0x80000 +After appending the second zone firstly: +start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80018, zcond:2, [type: 2] +After zap done, the append sector is 0x80018 +After appending the second zone secondly: +start: 0x80000, len 0x80000, cap 0x80000, wptr 0x80030, zcond:2, [type: 2] *** done -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20230407081657.17947-5-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/file-posix.c | 3 +++ block/trace-events | 2 ++ 2 files changed, 5 insertions(+) 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 @@ out: if (!BDRV_ZT_IS_CONV(*wp)) { if (type & QEMU_AIO_ZONE_APPEND) { *s->offset = *wp; + trace_zbd_zone_append_complete(bs, *s->offset + >> BDRV_SECTOR_BITS); } /* Advance the wp if needed */ if (offset + bytes > *wp) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_zone_append(BlockDriverState *bs, len += iov_len; } + trace_zbd_zone_append(bs, *offset >> BDRV_SECTOR_BITS); return raw_co_prw(bs, *offset, len, qiov, QEMU_AIO_ZONE_APPEND); } #endif diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ file_hdev_is_sg(int type, int version) "SG device found: type=%d, version=%d" file_flush_fdatasync_failed(int err) "errno %d" zbd_zone_report(void *bs, unsigned int nr_zones, int64_t sector) "bs %p report %d zones starting at sector offset 0x%" PRIx64 "" zbd_zone_mgmt(void *bs, const char *op_name, int64_t sector, int64_t len) "bs %p %s starts at sector offset 0x%" PRIx64 " over a range of 0x%" PRIx64 " sectors" +zbd_zone_append(void *bs, int64_t sector) "bs %p append at sector offset 0x%" PRIx64 "" +zbd_zone_append_complete(void *bs, int64_t sector) "bs %p returns append sector 0x%" PRIx64 "" # ssh.c sftp_error(const char *op, const char *ssh_err, int ssh_err_code, int sftp_err_code) "%s failed: %s (libssh error code: %d, sftp error code: %d)" -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Use scripts/update-linux-headers.sh to update headers to 6.3-rc1. Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Message-id: 20230407082528.18841-2-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/standard-headers/drm/drm_fourcc.h | 12 +++ include/standard-headers/linux/ethtool.h | 48 ++++++++- include/standard-headers/linux/fuse.h | 45 +++++++- include/standard-headers/linux/pci_regs.h | 1 + include/standard-headers/linux/vhost_types.h | 2 + include/standard-headers/linux/virtio_blk.h | 105 +++++++++++++++++++ linux-headers/asm-arm64/kvm.h | 1 + linux-headers/asm-x86/kvm.h | 34 +++++- linux-headers/linux/kvm.h | 9 ++ linux-headers/linux/vfio.h | 15 +-- linux-headers/linux/vhost.h | 8 ++ 11 files changed, 270 insertions(+), 10 deletions(-) diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -XXX,XX +XXX,XX @@ extern "C" { * * The authoritative list of format modifier codes is found in * `include/uapi/drm/drm_fourcc.h` + * + * Open Source User Waiver + * ----------------------- + * + * Because this is the authoritative source for pixel formats and modifiers + * referenced by GL, Vulkan extensions and other standards and hence used both + * by open source and closed source driver stacks, the usual requirement for an + * upstream in-kernel or open source userspace user does not apply. + * + * To ensure, as much as feasible, compatibility across stacks and avoid + * confusion with incompatible enumerations stakeholders for all relevant driver + * stacks should approve additions. */ #define fourcc_code(a, b, c, d) ((uint32_t)(a) | ((uint32_t)(b) << 8) | \ diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -XXX,XX +XXX,XX @@ enum ethtool_stringset { ETH_SS_COUNT }; +/** + * enum ethtool_mac_stats_src - source of ethtool MAC statistics + * @ETHTOOL_MAC_STATS_SRC_AGGREGATE: + * if device supports a MAC merge layer, this retrieves the aggregate + * statistics of the eMAC and pMAC. Otherwise, it retrieves just the + * statistics of the single (express) MAC. + * @ETHTOOL_MAC_STATS_SRC_EMAC: + * if device supports a MM layer, this retrieves the eMAC statistics. + * Otherwise, it retrieves the statistics of the single (express) MAC. + * @ETHTOOL_MAC_STATS_SRC_PMAC: + * if device supports a MM layer, this retrieves the pMAC statistics. + */ +enum ethtool_mac_stats_src { + ETHTOOL_MAC_STATS_SRC_AGGREGATE, + ETHTOOL_MAC_STATS_SRC_EMAC, + ETHTOOL_MAC_STATS_SRC_PMAC, +}; + /** * enum ethtool_module_power_mode_policy - plug-in module power mode policy * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode. @@ -XXX,XX +XXX,XX @@ enum ethtool_podl_pse_pw_d_status { ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR, }; +/** + * enum ethtool_mm_verify_status - status of MAC Merge Verify function + * @ETHTOOL_MM_VERIFY_STATUS_UNKNOWN: + * verification status is unknown + * @ETHTOOL_MM_VERIFY_STATUS_INITIAL: + * the 802.3 Verify State diagram is in the state INIT_VERIFICATION + * @ETHTOOL_MM_VERIFY_STATUS_VERIFYING: + * the Verify State diagram is in the state VERIFICATION_IDLE, + * SEND_VERIFY or WAIT_FOR_RESPONSE + * @ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED: + * indicates that the Verify State diagram is in the state VERIFIED + * @ETHTOOL_MM_VERIFY_STATUS_FAILED: + * the Verify State diagram is in the state VERIFY_FAIL + * @ETHTOOL_MM_VERIFY_STATUS_DISABLED: + * verification of preemption operation is disabled + */ +enum ethtool_mm_verify_status { + ETHTOOL_MM_VERIFY_STATUS_UNKNOWN, + ETHTOOL_MM_VERIFY_STATUS_INITIAL, + ETHTOOL_MM_VERIFY_STATUS_VERIFYING, + ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED, + ETHTOOL_MM_VERIFY_STATUS_FAILED, + ETHTOOL_MM_VERIFY_STATUS_DISABLED, +}; + /** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS @@ -XXX,XX +XXX,XX @@ struct ethtool_rxnfc { uint32_t rule_cnt; uint32_t rss_context; }; - uint32_t rule_locs[0]; + uint32_t rule_locs[]; }; @@ -XXX,XX +XXX,XX @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT = 96, ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT = 97, ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT = 98, + ETHTOOL_LINK_MODE_10baseT1S_Full_BIT = 99, + ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, + ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/fuse.h +++ b/include/standard-headers/linux/fuse.h @@ -XXX,XX +XXX,XX @@ * 7.38 * - add FUSE_EXPIRE_ONLY flag to fuse_notify_inval_entry * - add FOPEN_PARALLEL_DIRECT_WRITES + * - add total_extlen to fuse_in_header + * - add FUSE_MAX_NR_SECCTX + * - add extension header + * - add FUSE_EXT_GROUPS + * - add FUSE_CREATE_SUPP_GROUP */ #ifndef _LINUX_FUSE_H @@ -XXX,XX +XXX,XX @@ struct fuse_file_lock { * FUSE_SECURITY_CTX: add security context to create, mkdir, symlink, and * mknod * FUSE_HAS_INODE_DAX: use per inode DAX + * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, + * symlink and mknod (single group that matches parent) */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -XXX,XX +XXX,XX @@ struct fuse_file_lock { /* bits 32..63 get shifted down 32 bits into the flags2 field */ #define FUSE_SECURITY_CTX (1ULL << 32) #define FUSE_HAS_INODE_DAX (1ULL << 33) +#define FUSE_CREATE_SUPP_GROUP (1ULL << 34) /** * CUSE INIT request/reply flags @@ -XXX,XX +XXX,XX @@ struct fuse_file_lock { */ #define FUSE_EXPIRE_ONLY (1 << 0) +/** + * extension type + * FUSE_MAX_NR_SECCTX: maximum value of &fuse_secctx_header.nr_secctx + * FUSE_EXT_GROUPS: &fuse_supp_groups extension + */ +enum fuse_ext_type { + /* Types 0..31 are reserved for fuse_secctx_header */ + FUSE_MAX_NR_SECCTX = 31, + FUSE_EXT_GROUPS = 32, +}; + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ @@ -XXX,XX +XXX,XX @@ struct fuse_in_header { uint32_t uid; uint32_t gid; uint32_t pid; - uint32_t padding; + uint16_t total_extlen; /* length of extensions in 8byte units */ + uint16_t padding; }; struct fuse_out_header { @@ -XXX,XX +XXX,XX @@ struct fuse_secctx_header { uint32_t nr_secctx; }; +/** + * struct fuse_ext_header - extension header + * @size: total size of this extension including this header + * @type: type of extension + * + * This is made compatible with fuse_secctx_header by using type values > + * FUSE_MAX_NR_SECCTX + */ +struct fuse_ext_header { + uint32_t size; + uint32_t type; +}; + +/** + * struct fuse_supp_groups - Supplementary group extension + * @nr_groups: number of supplementary groups + * @groups: flexible array of group IDs + */ +struct fuse_supp_groups { + uint32_t nr_groups; + uint32_t groups[]; +}; + #endif /* _LINUX_FUSE_H */ diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -XXX,XX +XXX,XX @@ #define PCI_EXP_LNKCTL2_TX_MARGIN 0x0380 /* Transmit Margin */ #define PCI_EXP_LNKCTL2_HASD 0x0020 /* HW Autonomous Speed Disable */ #define PCI_EXP_LNKSTA2 0x32 /* Link Status 2 */ +#define PCI_EXP_LNKSTA2_FLIT 0x0400 /* Flit Mode Status */ #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32 /* end of v2 EPs w/ link */ #define PCI_EXP_SLTCAP2 0x34 /* Slot Capabilities 2 */ #define PCI_EXP_SLTCAP2_IBPD 0x00000001 /* In-band PD Disable Supported */ diff --git a/include/standard-headers/linux/vhost_types.h b/include/standard-headers/linux/vhost_types.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/vhost_types.h +++ b/include/standard-headers/linux/vhost_types.h @@ -XXX,XX +XXX,XX @@ struct vhost_vdpa_iova_range { #define VHOST_BACKEND_F_IOTLB_ASID 0x3 /* Device can be suspended */ #define VHOST_BACKEND_F_SUSPEND 0x4 +/* Device can be resumed */ +#define VHOST_BACKEND_F_RESUME 0x5 #endif diff --git a/include/standard-headers/linux/virtio_blk.h b/include/standard-headers/linux/virtio_blk.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/virtio_blk.h +++ b/include/standard-headers/linux/virtio_blk.h @@ -XXX,XX +XXX,XX @@ #define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */ #define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */ #define VIRTIO_BLK_F_SECURE_ERASE 16 /* Secure Erase is supported */ +#define VIRTIO_BLK_F_ZONED 17 /* Zoned block device */ /* Legacy feature bits */ #ifndef VIRTIO_BLK_NO_LEGACY @@ -XXX,XX +XXX,XX @@ struct virtio_blk_config { /* Secure erase commands must be aligned to this number of sectors. */ __virtio32 secure_erase_sector_alignment; + /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */ + struct virtio_blk_zoned_characteristics { + uint32_t zone_sectors; + uint32_t max_open_zones; + uint32_t max_active_zones; + uint32_t max_append_sectors; + uint32_t write_granularity; + uint8_t model; + uint8_t unused2[3]; + } zoned; } QEMU_PACKED; /* @@ -XXX,XX +XXX,XX @@ struct virtio_blk_config { /* Secure erase command */ #define VIRTIO_BLK_T_SECURE_ERASE 14 +/* Zone append command */ +#define VIRTIO_BLK_T_ZONE_APPEND 15 + +/* Report zones command */ +#define VIRTIO_BLK_T_ZONE_REPORT 16 + +/* Open zone command */ +#define VIRTIO_BLK_T_ZONE_OPEN 18 + +/* Close zone command */ +#define VIRTIO_BLK_T_ZONE_CLOSE 20 + +/* Finish zone command */ +#define VIRTIO_BLK_T_ZONE_FINISH 22 + +/* Reset zone command */ +#define VIRTIO_BLK_T_ZONE_RESET 24 + +/* Reset All zones command */ +#define VIRTIO_BLK_T_ZONE_RESET_ALL 26 + #ifndef VIRTIO_BLK_NO_LEGACY /* Barrier before this op. */ #define VIRTIO_BLK_T_BARRIER 0x80000000 @@ -XXX,XX +XXX,XX @@ struct virtio_blk_outhdr { __virtio64 sector; }; +/* + * Supported zoned device models. + */ + +/* Regular block device */ +#define VIRTIO_BLK_Z_NONE 0 +/* Host-managed zoned device */ +#define VIRTIO_BLK_Z_HM 1 +/* Host-aware zoned device */ +#define VIRTIO_BLK_Z_HA 2 + +/* + * Zone descriptor. A part of VIRTIO_BLK_T_ZONE_REPORT command reply. + */ +struct virtio_blk_zone_descriptor { + /* Zone capacity */ + uint64_t z_cap; + /* The starting sector of the zone */ + uint64_t z_start; + /* Zone write pointer position in sectors */ + uint64_t z_wp; + /* Zone type */ + uint8_t z_type; + /* Zone state */ + uint8_t z_state; + uint8_t reserved[38]; +}; + +struct virtio_blk_zone_report { + uint64_t nr_zones; + uint8_t reserved[56]; + struct virtio_blk_zone_descriptor zones[]; +}; + +/* + * Supported zone types. + */ + +/* Conventional zone */ +#define VIRTIO_BLK_ZT_CONV 1 +/* Sequential Write Required zone */ +#define VIRTIO_BLK_ZT_SWR 2 +/* Sequential Write Preferred zone */ +#define VIRTIO_BLK_ZT_SWP 3 + +/* + * Zone states that are available for zones of all types. + */ + +/* Not a write pointer (conventional zones only) */ +#define VIRTIO_BLK_ZS_NOT_WP 0 +/* Empty */ +#define VIRTIO_BLK_ZS_EMPTY 1 +/* Implicitly Open */ +#define VIRTIO_BLK_ZS_IOPEN 2 +/* Explicitly Open */ +#define VIRTIO_BLK_ZS_EOPEN 3 +/* Closed */ +#define VIRTIO_BLK_ZS_CLOSED 4 +/* Read-Only */ +#define VIRTIO_BLK_ZS_RDONLY 13 +/* Full */ +#define VIRTIO_BLK_ZS_FULL 14 +/* Offline */ +#define VIRTIO_BLK_ZS_OFFLINE 15 + /* Unmap this range (only valid for write zeroes command) */ #define VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP 0x00000001 @@ -XXX,XX +XXX,XX @@ struct virtio_scsi_inhdr { #define VIRTIO_BLK_S_OK 0 #define VIRTIO_BLK_S_IOERR 1 #define VIRTIO_BLK_S_UNSUPP 2 + +/* Error codes that are specific to zoned block devices */ +#define VIRTIO_BLK_S_ZONE_INVALID_CMD 3 +#define VIRTIO_BLK_S_ZONE_UNALIGNED_WP 4 +#define VIRTIO_BLK_S_ZONE_OPEN_RESOURCE 5 +#define VIRTIO_BLK_S_ZONE_ACTIVE_RESOURCE 6 + #endif /* _LINUX_VIRTIO_BLK_H */ diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -XXX,XX +XXX,XX @@ struct kvm_regs { #define KVM_ARM_VCPU_SVE 4 /* enable SVE for this CPU */ #define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */ #define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */ +#define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */ struct kvm_vcpu_init { __u32 target; diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -XXX,XX +XXX,XX @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <linux/stddef.h> #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 @@ -XXX,XX +XXX,XX @@ struct kvm_nested_state { * KVM_{GET,PUT}_NESTED_STATE ioctl values. */ union { - struct kvm_vmx_nested_state_data vmx[0]; - struct kvm_svm_nested_state_data svm[0]; + __DECLARE_FLEX_ARRAY(struct kvm_vmx_nested_state_data, vmx); + __DECLARE_FLEX_ARRAY(struct kvm_svm_nested_state_data, svm); } data; }; @@ -XXX,XX +XXX,XX @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) + +/* + * Masked event layout. + * Bits Description + * ---- ----------- + * 7:0 event select (low bits) + * 15:8 umask match + * 31:16 unused + * 35:32 event select (high bits) + * 36:54 unused + * 55 exclude bit + * 63:56 umask mask + */ + +#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \ + (((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \ + (((mask) & 0xFFULL) << 56) | \ + (((match) & 0xFFULL) << 8) | \ + ((__u64)(!!(exclude)) << 55)) + +#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ + (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) + /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -XXX,XX +XXX,XX @@ struct kvm_s390_mem_op { struct { __u8 ar; /* the access register number */ __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ }; __u32 sida_offset; /* offset into the sida */ __u8 reserved[32]; /* ignored */ @@ -XXX,XX +XXX,XX @@ struct kvm_s390_mem_op { #define KVM_S390_MEMOP_SIDA_WRITE 3 #define KVM_S390_MEMOP_ABSOLUTE_READ 4 #define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) #define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -XXX,XX +XXX,XX @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 +#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -XXX,XX +XXX,XX @@ /* Supports VFIO_DMA_UNMAP_FLAG_ALL */ #define VFIO_UNMAP_ALL 9 -/* Supports the vaddr flag for DMA map and unmap */ +/* + * Supports the vaddr flag for DMA map and unmap. Not supported for mediated + * devices, so this capability is subject to change as groups are added or + * removed. + */ #define VFIO_UPDATE_VADDR 10 /* @@ -XXX,XX +XXX,XX @@ struct vfio_iommu_type1_info_dma_avail { * Map process virtual addresses to IO virtual addresses using the * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. * - * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova, and - * unblock translation of host virtual addresses in the iova range. The vaddr + * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova. The vaddr * must have previously been invalidated with VFIO_DMA_UNMAP_FLAG_VADDR. To * maintain memory consistency within the user application, the updated vaddr * must address the same memory object as originally mapped. Failure to do so @@ -XXX,XX +XXX,XX @@ struct vfio_bitmap { * must be 0. This cannot be combined with the get-dirty-bitmap flag. * * If flags & VFIO_DMA_UNMAP_FLAG_VADDR, do not unmap, but invalidate host - * virtual addresses in the iova range. Tasks that attempt to translate an - * iova's vaddr will block. DMA to already-mapped pages continues. This - * cannot be combined with the get-dirty-bitmap flag. + * virtual addresses in the iova range. DMA to already-mapped pages continues. + * Groups may not be added to the container while any addresses are invalid. + * This cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -XXX,XX +XXX,XX @@ */ #define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) +/* Resume a device so it can resume processing virtqueue requests + * + * After the return of this ioctl the device will have restored all the + * necessary states and it is fully operational to continue processing the + * virtqueue descriptors. + */ +#define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E) + #endif -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> This patch extends virtio-blk emulation to handle zoned device commands by calling the new block layer APIs to perform zoned device I/O on behalf of the guest. It supports Report Zone, four zone oparations (open, close, finish, reset), and Append Zone. The VIRTIO_BLK_F_ZONED feature bit will only be set if the host does support zoned block devices. Regular block devices(conventional zones) will not be set. The guest os can use blktests, fio to test those commands on zoned devices. Furthermore, using zonefs to test zone append write is also supported. Signed-off-by: Sam Li <faithilikerun@gmail.com> Message-id: 20230407082528.18841-3-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- hw/block/virtio-blk-common.c | 2 + hw/block/virtio-blk.c | 389 +++++++++++++++++++++++++++++++++++ hw/virtio/virtio-qmp.c | 2 + 3 files changed, 393 insertions(+) diff --git a/hw/block/virtio-blk-common.c b/hw/block/virtio-blk-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk-common.c +++ b/hw/block/virtio-blk-common.c @@ -XXX,XX +XXX,XX @@ static const VirtIOFeature feature_sizes[] = { .end = endof(struct virtio_blk_config, discard_sector_alignment)}, {.flags = 1ULL << VIRTIO_BLK_F_WRITE_ZEROES, .end = endof(struct virtio_blk_config, write_zeroes_may_unmap)}, + {.flags = 1ULL << VIRTIO_BLK_F_ZONED, + .end = endof(struct virtio_blk_config, zoned)}, {} }; diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "qemu/error-report.h" #include "qemu/main-loop.h" +#include "block/block_int.h" #include "trace.h" #include "hw/block/block.h" #include "hw/qdev-properties.h" @@ -XXX,XX +XXX,XX @@ err: return err_status; } +typedef struct ZoneCmdData { + VirtIOBlockReq *req; + struct iovec *in_iov; + unsigned in_num; + union { + struct { + unsigned int nr_zones; + BlockZoneDescriptor *zones; + } zone_report_data; + struct { + int64_t offset; + } zone_append_data; + }; +} ZoneCmdData; + +/* + * check zoned_request: error checking before issuing requests. If all checks + * passed, return true. + * append: true if only zone append requests issued. + */ +static bool check_zoned_request(VirtIOBlock *s, int64_t offset, int64_t len, + bool append, uint8_t *status) { + BlockDriverState *bs = blk_bs(s->blk); + int index; + + if (!virtio_has_feature(s->host_features, VIRTIO_BLK_F_ZONED)) { + *status = VIRTIO_BLK_S_UNSUPP; + return false; + } + + if (offset < 0 || len < 0 || len > (bs->total_sectors << BDRV_SECTOR_BITS) + || offset > (bs->total_sectors << BDRV_SECTOR_BITS) - len) { + *status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + return false; + } + + if (append) { + if (bs->bl.write_granularity) { + if ((offset % bs->bl.write_granularity) != 0) { + *status = VIRTIO_BLK_S_ZONE_UNALIGNED_WP; + return false; + } + } + + index = offset / bs->bl.zone_size; + if (BDRV_ZT_IS_CONV(bs->wps->wp[index])) { + *status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + return false; + } + + if (len / 512 > bs->bl.max_append_sectors) { + if (bs->bl.max_append_sectors == 0) { + *status = VIRTIO_BLK_S_UNSUPP; + } else { + *status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + } + return false; + } + } + return true; +} + +static void virtio_blk_zone_report_complete(void *opaque, int ret) +{ + ZoneCmdData *data = opaque; + VirtIOBlockReq *req = data->req; + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(req->dev); + struct iovec *in_iov = data->in_iov; + unsigned in_num = data->in_num; + int64_t zrp_size, n, j = 0; + int64_t nz = data->zone_report_data.nr_zones; + int8_t err_status = VIRTIO_BLK_S_OK; + + if (ret) { + err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + goto out; + } + + struct virtio_blk_zone_report zrp_hdr = (struct virtio_blk_zone_report) { + .nr_zones = cpu_to_le64(nz), + }; + zrp_size = sizeof(struct virtio_blk_zone_report) + + sizeof(struct virtio_blk_zone_descriptor) * nz; + n = iov_from_buf(in_iov, in_num, 0, &zrp_hdr, sizeof(zrp_hdr)); + if (n != sizeof(zrp_hdr)) { + virtio_error(vdev, "Driver provided input buffer that is too small!"); + err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + goto out; + } + + for (size_t i = sizeof(zrp_hdr); i < zrp_size; + i += sizeof(struct virtio_blk_zone_descriptor), ++j) { + struct virtio_blk_zone_descriptor desc = + (struct virtio_blk_zone_descriptor) { + .z_start = cpu_to_le64(data->zone_report_data.zones[j].start + >> BDRV_SECTOR_BITS), + .z_cap = cpu_to_le64(data->zone_report_data.zones[j].cap + >> BDRV_SECTOR_BITS), + .z_wp = cpu_to_le64(data->zone_report_data.zones[j].wp + >> BDRV_SECTOR_BITS), + }; + + switch (data->zone_report_data.zones[j].type) { + case BLK_ZT_CONV: + desc.z_type = VIRTIO_BLK_ZT_CONV; + break; + case BLK_ZT_SWR: + desc.z_type = VIRTIO_BLK_ZT_SWR; + break; + case BLK_ZT_SWP: + desc.z_type = VIRTIO_BLK_ZT_SWP; + break; + default: + g_assert_not_reached(); + } + + switch (data->zone_report_data.zones[j].state) { + case BLK_ZS_RDONLY: + desc.z_state = VIRTIO_BLK_ZS_RDONLY; + break; + case BLK_ZS_OFFLINE: + desc.z_state = VIRTIO_BLK_ZS_OFFLINE; + break; + case BLK_ZS_EMPTY: + desc.z_state = VIRTIO_BLK_ZS_EMPTY; + break; + case BLK_ZS_CLOSED: + desc.z_state = VIRTIO_BLK_ZS_CLOSED; + break; + case BLK_ZS_FULL: + desc.z_state = VIRTIO_BLK_ZS_FULL; + break; + case BLK_ZS_EOPEN: + desc.z_state = VIRTIO_BLK_ZS_EOPEN; + break; + case BLK_ZS_IOPEN: + desc.z_state = VIRTIO_BLK_ZS_IOPEN; + break; + case BLK_ZS_NOT_WP: + desc.z_state = VIRTIO_BLK_ZS_NOT_WP; + break; + default: + g_assert_not_reached(); + } + + /* TODO: it takes O(n^2) time complexity. Optimizations required. */ + n = iov_from_buf(in_iov, in_num, i, &desc, sizeof(desc)); + if (n != sizeof(desc)) { + virtio_error(vdev, "Driver provided input buffer " + "for descriptors that is too small!"); + err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + } + } + +out: + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); + virtio_blk_req_complete(req, err_status); + virtio_blk_free_request(req); + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); + g_free(data->zone_report_data.zones); + g_free(data); +} + +static void virtio_blk_handle_zone_report(VirtIOBlockReq *req, + struct iovec *in_iov, + unsigned in_num) +{ + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(s); + unsigned int nr_zones; + ZoneCmdData *data; + int64_t zone_size, offset; + uint8_t err_status; + + if (req->in_len < sizeof(struct virtio_blk_inhdr) + + sizeof(struct virtio_blk_zone_report) + + sizeof(struct virtio_blk_zone_descriptor)) { + virtio_error(vdev, "in buffer too small for zone report"); + return; + } + + /* start byte offset of the zone report */ + offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS; + if (!check_zoned_request(s, offset, 0, false, &err_status)) { + goto out; + } + nr_zones = (req->in_len - sizeof(struct virtio_blk_inhdr) - + sizeof(struct virtio_blk_zone_report)) / + sizeof(struct virtio_blk_zone_descriptor); + + zone_size = sizeof(BlockZoneDescriptor) * nr_zones; + data = g_malloc(sizeof(ZoneCmdData)); + data->req = req; + data->in_iov = in_iov; + data->in_num = in_num; + data->zone_report_data.nr_zones = nr_zones; + data->zone_report_data.zones = g_malloc(zone_size), + + blk_aio_zone_report(s->blk, offset, &data->zone_report_data.nr_zones, + data->zone_report_data.zones, + virtio_blk_zone_report_complete, data); + return; +out: + virtio_blk_req_complete(req, err_status); + virtio_blk_free_request(req); +} + +static void virtio_blk_zone_mgmt_complete(void *opaque, int ret) +{ + VirtIOBlockReq *req = opaque; + VirtIOBlock *s = req->dev; + int8_t err_status = VIRTIO_BLK_S_OK; + + if (ret) { + err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + } + + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); + virtio_blk_req_complete(req, err_status); + virtio_blk_free_request(req); + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); +} + +static int virtio_blk_handle_zone_mgmt(VirtIOBlockReq *req, BlockZoneOp op) +{ + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(s); + BlockDriverState *bs = blk_bs(s->blk); + int64_t offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS; + uint64_t len; + uint64_t capacity = bs->total_sectors << BDRV_SECTOR_BITS; + uint8_t err_status = VIRTIO_BLK_S_OK; + + uint32_t type = virtio_ldl_p(vdev, &req->out.type); + if (type == VIRTIO_BLK_T_ZONE_RESET_ALL) { + /* Entire drive capacity */ + offset = 0; + len = capacity; + } else { + if (bs->bl.zone_size > capacity - offset) { + /* The zoned device allows the last smaller zone. */ + len = capacity - bs->bl.zone_size * (bs->bl.nr_zones - 1); + } else { + len = bs->bl.zone_size; + } + } + + if (!check_zoned_request(s, offset, len, false, &err_status)) { + goto out; + } + + blk_aio_zone_mgmt(s->blk, op, offset, len, + virtio_blk_zone_mgmt_complete, req); + + return 0; +out: + virtio_blk_req_complete(req, err_status); + virtio_blk_free_request(req); + return err_status; +} + +static void virtio_blk_zone_append_complete(void *opaque, int ret) +{ + ZoneCmdData *data = opaque; + VirtIOBlockReq *req = data->req; + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(req->dev); + int64_t append_sector, n; + uint8_t err_status = VIRTIO_BLK_S_OK; + + if (ret) { + err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + goto out; + } + + virtio_stq_p(vdev, &append_sector, + data->zone_append_data.offset >> BDRV_SECTOR_BITS); + n = iov_from_buf(data->in_iov, data->in_num, 0, &append_sector, + sizeof(append_sector)); + if (n != sizeof(append_sector)) { + virtio_error(vdev, "Driver provided input buffer less than size of " + "append_sector"); + err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; + goto out; + } + +out: + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); + virtio_blk_req_complete(req, err_status); + virtio_blk_free_request(req); + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); + g_free(data); +} + +static int virtio_blk_handle_zone_append(VirtIOBlockReq *req, + struct iovec *out_iov, + struct iovec *in_iov, + uint64_t out_num, + unsigned in_num) { + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(s); + uint8_t err_status = VIRTIO_BLK_S_OK; + + int64_t offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS; + int64_t len = iov_size(out_iov, out_num); + + if (!check_zoned_request(s, offset, len, true, &err_status)) { + goto out; + } + + ZoneCmdData *data = g_malloc(sizeof(ZoneCmdData)); + data->req = req; + data->in_iov = in_iov; + data->in_num = in_num; + data->zone_append_data.offset = offset; + qemu_iovec_init_external(&req->qiov, out_iov, out_num); + blk_aio_zone_append(s->blk, &data->zone_append_data.offset, &req->qiov, 0, + virtio_blk_zone_append_complete, data); + return 0; + +out: + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); + virtio_blk_req_complete(req, err_status); + virtio_blk_free_request(req); + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); + return err_status; +} + static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb) { uint32_t type; @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb) case VIRTIO_BLK_T_FLUSH: virtio_blk_handle_flush(req, mrb); break; + case VIRTIO_BLK_T_ZONE_REPORT: + virtio_blk_handle_zone_report(req, in_iov, in_num); + break; + case VIRTIO_BLK_T_ZONE_OPEN: + virtio_blk_handle_zone_mgmt(req, BLK_ZO_OPEN); + break; + case VIRTIO_BLK_T_ZONE_CLOSE: + virtio_blk_handle_zone_mgmt(req, BLK_ZO_CLOSE); + break; + case VIRTIO_BLK_T_ZONE_FINISH: + virtio_blk_handle_zone_mgmt(req, BLK_ZO_FINISH); + break; + case VIRTIO_BLK_T_ZONE_RESET: + virtio_blk_handle_zone_mgmt(req, BLK_ZO_RESET); + break; + case VIRTIO_BLK_T_ZONE_RESET_ALL: + virtio_blk_handle_zone_mgmt(req, BLK_ZO_RESET); + break; case VIRTIO_BLK_T_SCSI_CMD: virtio_blk_handle_scsi(req); break; @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb) virtio_blk_free_request(req); break; } + case VIRTIO_BLK_T_ZONE_APPEND & ~VIRTIO_BLK_T_OUT: + /* + * Passing out_iov/out_num and in_iov/in_num is not safe + * to access req->elem.out_sg directly because it may be + * modified by virtio_blk_handle_request(). + */ + virtio_blk_handle_zone_append(req, out_iov, in_iov, out_num, in_num); + break; /* * VIRTIO_BLK_T_DISCARD and VIRTIO_BLK_T_WRITE_ZEROES are defined with * VIRTIO_BLK_T_OUT flag set. We masked this flag in the switch statement, @@ -XXX,XX +XXX,XX @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config) { VirtIOBlock *s = VIRTIO_BLK(vdev); BlockConf *conf = &s->conf.conf; + BlockDriverState *bs = blk_bs(s->blk); struct virtio_blk_config blkcfg; uint64_t capacity; int64_t length; @@ -XXX,XX +XXX,XX @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config) blkcfg.write_zeroes_may_unmap = 1; virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1); } + if (bs->bl.zoned != BLK_Z_NONE) { + switch (bs->bl.zoned) { + case BLK_Z_HM: + blkcfg.zoned.model = VIRTIO_BLK_Z_HM; + break; + case BLK_Z_HA: + blkcfg.zoned.model = VIRTIO_BLK_Z_HA; + break; + default: + g_assert_not_reached(); + } + + virtio_stl_p(vdev, &blkcfg.zoned.zone_sectors, + bs->bl.zone_size / 512); + virtio_stl_p(vdev, &blkcfg.zoned.max_active_zones, + bs->bl.max_active_zones); + virtio_stl_p(vdev, &blkcfg.zoned.max_open_zones, + bs->bl.max_open_zones); + virtio_stl_p(vdev, &blkcfg.zoned.write_granularity, blk_size); + virtio_stl_p(vdev, &blkcfg.zoned.max_append_sectors, + bs->bl.max_append_sectors); + } else { + blkcfg.zoned.model = VIRTIO_BLK_Z_NONE; + } memcpy(config, &blkcfg, s->config_size); } @@ -XXX,XX +XXX,XX @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIOBlock *s = VIRTIO_BLK(dev); VirtIOBlkConf *conf = &s->conf; + BlockDriverState *bs = blk_bs(conf->conf.blk); Error *err = NULL; unsigned i; @@ -XXX,XX +XXX,XX @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp) return; } + if (bs->bl.zoned != BLK_Z_NONE) { + virtio_add_feature(&s->host_features, VIRTIO_BLK_F_ZONED); + if (bs->bl.zoned == BLK_Z_HM) { + virtio_clear_feature(&s->host_features, VIRTIO_BLK_F_DISCARD); + } + } + if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD) && (!conf->max_discard_sectors || conf->max_discard_sectors > BDRV_REQUEST_MAX_SECTORS)) { diff --git a/hw/virtio/virtio-qmp.c b/hw/virtio/virtio-qmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/virtio-qmp.c +++ b/hw/virtio/virtio-qmp.c @@ -XXX,XX +XXX,XX @@ static const qmp_virtio_feature_map_t virtio_blk_feature_map[] = { "VIRTIO_BLK_F_DISCARD: Discard command supported"), FEATURE_ENTRY(VIRTIO_BLK_F_WRITE_ZEROES, \ "VIRTIO_BLK_F_WRITE_ZEROES: Write zeroes command supported"), + FEATURE_ENTRY(VIRTIO_BLK_F_ZONED, \ + "VIRTIO_BLK_F_ZONED: Zoned block devices"), #ifndef VIRTIO_BLK_NO_LEGACY FEATURE_ENTRY(VIRTIO_BLK_F_BARRIER, \ "VIRTIO_BLK_F_BARRIER: Request barriers supported"), -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Taking account of the new zone append write operation for zoned devices, BLOCK_ACCT_ZONE_APPEND enum is introduced as other I/O request type (read, write, flush). Signed-off-by: Sam Li <faithilikerun@gmail.com> Message-id: 20230407082528.18841-4-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-core.json | 68 ++++++++++++++++++++++++++++++++------ qapi/block.json | 4 +++ include/block/accounting.h | 1 + block/qapi-sysemu.c | 11 ++++++ block/qapi.c | 18 ++++++++++ hw/block/virtio-blk.c | 4 +++ 6 files changed, 95 insertions(+), 11 deletions(-) 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 @@ # @min_wr_latency_ns: Minimum latency of write operations in the # defined interval, in nanoseconds. # +# @min_zone_append_latency_ns: Minimum latency of zone append operations +# in the defined interval, in nanoseconds +# (since 8.1) +# # @min_flush_latency_ns: Minimum latency of flush operations in the # defined interval, in nanoseconds. # @@ -XXX,XX +XXX,XX @@ # @max_wr_latency_ns: Maximum latency of write operations in the # defined interval, in nanoseconds. # +# @max_zone_append_latency_ns: Maximum latency of zone append operations +# in the defined interval, in nanoseconds +# (since 8.1) +# # @max_flush_latency_ns: Maximum latency of flush operations in the # defined interval, in nanoseconds. # @@ -XXX,XX +XXX,XX @@ # @avg_wr_latency_ns: Average latency of write operations in the # defined interval, in nanoseconds. # +# @avg_zone_append_latency_ns: Average latency of zone append operations +# in the defined interval, in nanoseconds +# (since 8.1) +# # @avg_flush_latency_ns: Average latency of flush operations in the # defined interval, in nanoseconds. # @@ -XXX,XX +XXX,XX @@ # @avg_wr_queue_depth: Average number of pending write operations # in the defined interval. # +# @avg_zone_append_queue_depth: Average number of pending zone append +# operations in the defined interval +# (since 8.1). +# # Since: 2.5 ## { 'struct': 'BlockDeviceTimedStats', 'data': { 'interval_length': 'int', 'min_rd_latency_ns': 'int', 'max_rd_latency_ns': 'int', 'avg_rd_latency_ns': 'int', 'min_wr_latency_ns': 'int', 'max_wr_latency_ns': 'int', - 'avg_wr_latency_ns': 'int', 'min_flush_latency_ns': 'int', - 'max_flush_latency_ns': 'int', 'avg_flush_latency_ns': 'int', - 'avg_rd_queue_depth': 'number', 'avg_wr_queue_depth': 'number' } } + 'avg_wr_latency_ns': 'int', 'min_zone_append_latency_ns': 'int', + 'max_zone_append_latency_ns': 'int', + 'avg_zone_append_latency_ns': 'int', + 'min_flush_latency_ns': 'int', 'max_flush_latency_ns': 'int', + 'avg_flush_latency_ns': 'int', 'avg_rd_queue_depth': 'number', + 'avg_wr_queue_depth': 'number', + 'avg_zone_append_queue_depth': 'number' } } ## # @BlockDeviceStats: @@ -XXX,XX +XXX,XX @@ # # @wr_bytes: The number of bytes written by the device. # +# @zone_append_bytes: The number of bytes appended by the zoned devices +# (since 8.1) +# # @unmap_bytes: The number of bytes unmapped by the device (Since 4.2) # # @rd_operations: The number of read operations performed by the device. # # @wr_operations: The number of write operations performed by the device. # +# @zone_append_operations: The number of zone append operations performed +# by the zoned devices (since 8.1) +# # @flush_operations: The number of cache flush operations performed by the # device (since 0.15) # @@ -XXX,XX +XXX,XX @@ # # @wr_total_time_ns: Total time spent on writes in nanoseconds (since 0.15). # +# @zone_append_total_time_ns: Total time spent on zone append writes +# in nanoseconds (since 8.1) +# # @flush_total_time_ns: Total time spent on cache flushes in nanoseconds # (since 0.15). # @@ -XXX,XX +XXX,XX @@ # @wr_merged: Number of write requests that have been merged into another # request (Since 2.3). # +# @zone_append_merged: Number of zone append requests that have been merged +# into another request (since 8.1) +# # @unmap_merged: Number of unmap requests that have been merged into another # request (Since 4.2) # @@ -XXX,XX +XXX,XX @@ # @failed_wr_operations: The number of failed write operations # performed by the device (Since 2.5) # +# @failed_zone_append_operations: The number of failed zone append write +# operations performed by the zoned devices +# (since 8.1) +# # @failed_flush_operations: The number of failed flush operations # performed by the device (Since 2.5) # @@ -XXX,XX +XXX,XX @@ # @invalid_wr_operations: The number of invalid write operations # performed by the device (Since 2.5) # +# @invalid_zone_append_operations: The number of invalid zone append operations +# performed by the zoned device (since 8.1) +# # @invalid_flush_operations: The number of invalid flush operations # performed by the device (Since 2.5) # @@ -XXX,XX +XXX,XX @@ # # @wr_latency_histogram: @BlockLatencyHistogramInfo. (Since 4.0) # +# @zone_append_latency_histogram: @BlockLatencyHistogramInfo. (since 8.1) +# # @flush_latency_histogram: @BlockLatencyHistogramInfo. (Since 4.0) # # Since: 0.14 ## { 'struct': 'BlockDeviceStats', - 'data': {'rd_bytes': 'int', 'wr_bytes': 'int', 'unmap_bytes' : 'int', - 'rd_operations': 'int', 'wr_operations': 'int', + 'data': {'rd_bytes': 'int', 'wr_bytes': 'int', 'zone_append_bytes': 'int', + 'unmap_bytes' : 'int', 'rd_operations': 'int', + 'wr_operations': 'int', 'zone_append_operations': 'int', 'flush_operations': 'int', 'unmap_operations': 'int', 'rd_total_time_ns': 'int', 'wr_total_time_ns': 'int', - 'flush_total_time_ns': 'int', 'unmap_total_time_ns': 'int', - 'wr_highest_offset': 'int', - 'rd_merged': 'int', 'wr_merged': 'int', 'unmap_merged': 'int', - '*idle_time_ns': 'int', + 'zone_append_total_time_ns': 'int', 'flush_total_time_ns': 'int', + 'unmap_total_time_ns': 'int', 'wr_highest_offset': 'int', + 'rd_merged': 'int', 'wr_merged': 'int', 'zone_append_merged': 'int', + 'unmap_merged': 'int', '*idle_time_ns': 'int', 'failed_rd_operations': 'int', 'failed_wr_operations': 'int', - 'failed_flush_operations': 'int', 'failed_unmap_operations': 'int', - 'invalid_rd_operations': 'int', 'invalid_wr_operations': 'int', + 'failed_zone_append_operations': 'int', + 'failed_flush_operations': 'int', + 'failed_unmap_operations': 'int', 'invalid_rd_operations': 'int', + 'invalid_wr_operations': 'int', + 'invalid_zone_append_operations': 'int', 'invalid_flush_operations': 'int', 'invalid_unmap_operations': 'int', 'account_invalid': 'bool', 'account_failed': 'bool', 'timed_stats': ['BlockDeviceTimedStats'], '*rd_latency_histogram': 'BlockLatencyHistogramInfo', '*wr_latency_histogram': 'BlockLatencyHistogramInfo', + '*zone_append_latency_histogram': 'BlockLatencyHistogramInfo', '*flush_latency_histogram': 'BlockLatencyHistogramInfo' } } ## diff --git a/qapi/block.json b/qapi/block.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block.json +++ b/qapi/block.json @@ -XXX,XX +XXX,XX @@ # @boundaries-write: list of interval boundary values for write latency # histogram. # +# @boundaries-zap: list of interval boundary values for zone append write +# latency histogram. +# # @boundaries-flush: list of interval boundary values for flush latency # histogram. # @@ -XXX,XX +XXX,XX @@ '*boundaries': ['uint64'], '*boundaries-read': ['uint64'], '*boundaries-write': ['uint64'], + '*boundaries-zap': ['uint64'], '*boundaries-flush': ['uint64'] }, 'allow-preconfig': true } diff --git a/include/block/accounting.h b/include/block/accounting.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/accounting.h +++ b/include/block/accounting.h @@ -XXX,XX +XXX,XX @@ enum BlockAcctType { BLOCK_ACCT_READ, BLOCK_ACCT_WRITE, BLOCK_ACCT_FLUSH, + BLOCK_ACCT_ZONE_APPEND, BLOCK_ACCT_UNMAP, BLOCK_MAX_IOTYPE, }; diff --git a/block/qapi-sysemu.c b/block/qapi-sysemu.c index XXXXXXX..XXXXXXX 100644 --- a/block/qapi-sysemu.c +++ b/block/qapi-sysemu.c @@ -XXX,XX +XXX,XX @@ void qmp_block_latency_histogram_set( bool has_boundaries, uint64List *boundaries, bool has_boundaries_read, uint64List *boundaries_read, bool has_boundaries_write, uint64List *boundaries_write, + bool has_boundaries_append, uint64List *boundaries_append, bool has_boundaries_flush, uint64List *boundaries_flush, Error **errp) { @@ -XXX,XX +XXX,XX @@ void qmp_block_latency_histogram_set( } } + if (has_boundaries || has_boundaries_append) { + ret = block_latency_histogram_set( + stats, BLOCK_ACCT_ZONE_APPEND, + has_boundaries_append ? boundaries_append : boundaries); + if (ret) { + error_setg(errp, "Device '%s' set append write boundaries fail", id); + return; + } + } + if (has_boundaries || has_boundaries_flush) { ret = block_latency_histogram_set( stats, BLOCK_ACCT_FLUSH, diff --git a/block/qapi.c b/block/qapi.c index XXXXXXX..XXXXXXX 100644 --- a/block/qapi.c +++ b/block/qapi.c @@ -XXX,XX +XXX,XX @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk) ds->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ]; ds->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE]; + ds->zone_append_bytes = stats->nr_bytes[BLOCK_ACCT_ZONE_APPEND]; ds->unmap_bytes = stats->nr_bytes[BLOCK_ACCT_UNMAP]; ds->rd_operations = stats->nr_ops[BLOCK_ACCT_READ]; ds->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE]; + ds->zone_append_operations = stats->nr_ops[BLOCK_ACCT_ZONE_APPEND]; ds->unmap_operations = stats->nr_ops[BLOCK_ACCT_UNMAP]; ds->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ]; ds->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE]; + ds->failed_zone_append_operations = + stats->failed_ops[BLOCK_ACCT_ZONE_APPEND]; ds->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH]; ds->failed_unmap_operations = stats->failed_ops[BLOCK_ACCT_UNMAP]; ds->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ]; ds->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE]; + ds->invalid_zone_append_operations = + stats->invalid_ops[BLOCK_ACCT_ZONE_APPEND]; ds->invalid_flush_operations = stats->invalid_ops[BLOCK_ACCT_FLUSH]; ds->invalid_unmap_operations = stats->invalid_ops[BLOCK_ACCT_UNMAP]; ds->rd_merged = stats->merged[BLOCK_ACCT_READ]; ds->wr_merged = stats->merged[BLOCK_ACCT_WRITE]; + ds->zone_append_merged = stats->merged[BLOCK_ACCT_ZONE_APPEND]; ds->unmap_merged = stats->merged[BLOCK_ACCT_UNMAP]; ds->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH]; ds->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE]; + ds->zone_append_total_time_ns = + stats->total_time_ns[BLOCK_ACCT_ZONE_APPEND]; ds->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ]; ds->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH]; ds->unmap_total_time_ns = stats->total_time_ns[BLOCK_ACCT_UNMAP]; @@ -XXX,XX +XXX,XX @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk) TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ]; TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE]; + TimedAverage *zap = &ts->latency[BLOCK_ACCT_ZONE_APPEND]; TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH]; dev_stats->interval_length = ts->interval_length; @@ -XXX,XX +XXX,XX @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk) dev_stats->max_wr_latency_ns = timed_average_max(wr); dev_stats->avg_wr_latency_ns = timed_average_avg(wr); + dev_stats->min_zone_append_latency_ns = timed_average_min(zap); + dev_stats->max_zone_append_latency_ns = timed_average_max(zap); + dev_stats->avg_zone_append_latency_ns = timed_average_avg(zap); + dev_stats->min_flush_latency_ns = timed_average_min(fl); dev_stats->max_flush_latency_ns = timed_average_max(fl); dev_stats->avg_flush_latency_ns = timed_average_avg(fl); @@ -XXX,XX +XXX,XX @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk) block_acct_queue_depth(ts, BLOCK_ACCT_READ); dev_stats->avg_wr_queue_depth = block_acct_queue_depth(ts, BLOCK_ACCT_WRITE); + dev_stats->avg_zone_append_queue_depth = + block_acct_queue_depth(ts, BLOCK_ACCT_ZONE_APPEND); QAPI_LIST_PREPEND(ds->timed_stats, dev_stats); } @@ -XXX,XX +XXX,XX @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk) = bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_READ]); ds->wr_latency_histogram = bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_WRITE]); + ds->zone_append_latency_histogram + = bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_ZONE_APPEND]); ds->flush_latency_histogram = bdrv_latency_histogram_stats(&hgram[BLOCK_ACCT_FLUSH]); } diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_zone_append(VirtIOBlockReq *req, data->in_num = in_num; data->zone_append_data.offset = offset; qemu_iovec_init_external(&req->qiov, out_iov, out_num); + + block_acct_start(blk_get_stats(s->blk), &req->acct, len, + BLOCK_ACCT_ZONE_APPEND); + blk_aio_zone_append(s->blk, &data->zone_append_data.offset, &req->qiov, 0, virtio_blk_zone_append_complete, data); return 0; -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Signed-off-by: Sam Li <faithilikerun@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20230407082528.18841-5-faithilikerun@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- hw/block/virtio-blk.c | 12 ++++++++++++ hw/block/trace-events | 7 +++++++ 2 files changed, 19 insertions(+) diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static void virtio_blk_zone_report_complete(void *opaque, int ret) int64_t nz = data->zone_report_data.nr_zones; int8_t err_status = VIRTIO_BLK_S_OK; + trace_virtio_blk_zone_report_complete(vdev, req, nz, ret); if (ret) { err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; goto out; @@ -XXX,XX +XXX,XX @@ static void virtio_blk_handle_zone_report(VirtIOBlockReq *req, nr_zones = (req->in_len - sizeof(struct virtio_blk_inhdr) - sizeof(struct virtio_blk_zone_report)) / sizeof(struct virtio_blk_zone_descriptor); + trace_virtio_blk_handle_zone_report(vdev, req, + offset >> BDRV_SECTOR_BITS, nr_zones); zone_size = sizeof(BlockZoneDescriptor) * nr_zones; data = g_malloc(sizeof(ZoneCmdData)); @@ -XXX,XX +XXX,XX @@ static void virtio_blk_zone_mgmt_complete(void *opaque, int ret) { VirtIOBlockReq *req = opaque; VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(s); int8_t err_status = VIRTIO_BLK_S_OK; + trace_virtio_blk_zone_mgmt_complete(vdev, req,ret); if (ret) { err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_zone_mgmt(VirtIOBlockReq *req, BlockZoneOp op) /* Entire drive capacity */ offset = 0; len = capacity; + trace_virtio_blk_handle_zone_reset_all(vdev, req, 0, + bs->total_sectors); } else { if (bs->bl.zone_size > capacity - offset) { /* The zoned device allows the last smaller zone. */ @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_zone_mgmt(VirtIOBlockReq *req, BlockZoneOp op) } else { len = bs->bl.zone_size; } + trace_virtio_blk_handle_zone_mgmt(vdev, req, op, + offset >> BDRV_SECTOR_BITS, + len >> BDRV_SECTOR_BITS); } if (!check_zoned_request(s, offset, len, false, &err_status)) { @@ -XXX,XX +XXX,XX @@ static void virtio_blk_zone_append_complete(void *opaque, int ret) err_status = VIRTIO_BLK_S_ZONE_INVALID_CMD; goto out; } + trace_virtio_blk_zone_append_complete(vdev, req, append_sector, ret); out: aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_zone_append(VirtIOBlockReq *req, int64_t offset = virtio_ldq_p(vdev, &req->out.sector) << BDRV_SECTOR_BITS; int64_t len = iov_size(out_iov, out_num); + trace_virtio_blk_handle_zone_append(vdev, req, offset >> BDRV_SECTOR_BITS); if (!check_zoned_request(s, offset, len, true, &err_status)) { goto out; } 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 @@ pflash_write_unknown(const char *name, uint8_t cmd) "%s: unknown command 0x%02x" # virtio-blk.c virtio_blk_req_complete(void *vdev, void *req, int status) "vdev %p req %p status %d" virtio_blk_rw_complete(void *vdev, void *req, int ret) "vdev %p req %p ret %d" +virtio_blk_zone_report_complete(void *vdev, void *req, unsigned int nr_zones, int ret) "vdev %p req %p nr_zones %u ret %d" +virtio_blk_zone_mgmt_complete(void *vdev, void *req, int ret) "vdev %p req %p ret %d" +virtio_blk_zone_append_complete(void *vdev, void *req, int64_t sector, int ret) "vdev %p req %p, append sector 0x%" PRIx64 " ret %d" virtio_blk_handle_write(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu" virtio_blk_handle_read(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu" virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint64_t offset, size_t size, bool is_write) "vdev %p mrb %p start %d num_reqs %d offset %"PRIu64" size %zu is_write %d" +virtio_blk_handle_zone_report(void *vdev, void *req, int64_t sector, unsigned int nr_zones) "vdev %p req %p sector 0x%" PRIx64 " nr_zones %u" +virtio_blk_handle_zone_mgmt(void *vdev, void *req, uint8_t op, int64_t sector, int64_t len) "vdev %p req %p op 0x%x sector 0x%" PRIx64 " len 0x%" PRIx64 "" +virtio_blk_handle_zone_reset_all(void *vdev, void *req, int64_t sector, int64_t len) "vdev %p req %p sector 0x%" PRIx64 " cap 0x%" PRIx64 "" +virtio_blk_handle_zone_append(void *vdev, void *req, int64_t sector) "vdev %p req %p, append sector 0x%" PRIx64 "" # hd-geometry.c hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d" -- 2.39.2 From: Sam Li <faithilikerun@gmail.com> Add the documentation about the example of using virtio-blk driver to pass the zoned block devices through to the guest. Signed-off-by: Sam Li <faithilikerun@gmail.com> Message-id: 20230407082528.18841-6-faithilikerun@gmail.com [Fix Sphinx indentation error by turning command-lines into pre-formatted text. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- docs/devel/zoned-storage.rst | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/docs/devel/zoned-storage.rst b/docs/devel/zoned-storage.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/zoned-storage.rst +++ b/docs/devel/zoned-storage.rst @@ -XXX,XX +XXX,XX @@ When the BlockBackend's BlockLimits model reports a zoned storage device, users like the virtio-blk emulation or the qemu-io-cmds.c utility can use block layer APIs for zoned storage emulation or testing. -For example, to test zone_report on a null_blk device using qemu-io is: -$ path/to/qemu-io --image-opts -n driver=host_device,filename=/dev/nullb0 --c "zrp offset nr_zones" +For example, to test zone_report on a null_blk device using qemu-io is:: + + $ path/to/qemu-io --image-opts -n driver=host_device,filename=/dev/nullb0 -c "zrp offset nr_zones" + +To expose the host's zoned block device through virtio-blk, the command line +can be (includes the -device parameter):: + + -blockdev node-name=drive0,driver=host_device,filename=/dev/nullb0,cache.direct=on \ + -device virtio-blk-pci,drive=drive0 + +Or only use the -drive parameter:: + + -driver driver=host_device,file=/dev/nullb0,if=virtio,cache.direct=on + +Additionally, QEMU has several ways of supporting zoned storage, including: +(1) Using virtio-scsi: --device scsi-block allows for the passing through of +SCSI ZBC devices, enabling the attachment of ZBC or ZAC HDDs to QEMU. +(2) PCI device pass-through: While NVMe ZNS emulation is available for testing +purposes, it cannot yet pass through a zoned device from the host. To pass on +the NVMe ZNS device to the guest, use VFIO PCI pass the entire NVMe PCI adapter +through to the guest. Likewise, an HDD HBA can be passed on to QEMU all HDDs +attached to the HBA. -- 2.39.2 From: Carlos Santos <casantos@redhat.com> It is not useful when configuring with --enable-trace-backends=nop. Signed-off-by: Carlos Santos <casantos@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20230408010410.281263-1-casantos@redhat.com> --- trace/meson.build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/trace/meson.build b/trace/meson.build index XXXXXXX..XXXXXXX 100644 --- a/trace/meson.build +++ b/trace/meson.build @@ -XXX,XX +XXX,XX @@ trace_events_all = custom_target('trace-events-all', input: trace_events_files, command: [ 'cat', '@INPUT@' ], capture: true, - install: true, + install: get_option('trace_backends') != [ 'nop' ], install_dir: qemu_datadir) if 'ust' in get_option('trace_backends') -- 2.39.2