1 | The following changes since commit 4c8c1cc544dbd5e2564868e61c5037258e393832: | 1 | The following changes since commit 9a7beaad3dbba982f7a461d676b55a5c3851d312: |
---|---|---|---|
2 | 2 | ||
3 | Merge remote-tracking branch 'remotes/vivier/tags/m68k-for-2.10-pull-request' into staging (2017-06-22 19:01:58 +0100) | 3 | Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20210304' into staging (2021-03-05 10:47:46 +0000) |
4 | 4 | ||
5 | are available in the git repository at: | 5 | are available in the Git repository at: |
6 | |||
7 | 6 | ||
8 | git://repo.or.cz/qemu/kevin.git tags/for-upstream | 7 | git://repo.or.cz/qemu/kevin.git tags/for-upstream |
9 | 8 | ||
10 | for you to fetch changes up to 1512008812410ca4054506a7c44343088abdd977: | 9 | for you to fetch changes up to 67bedc3aed5c455b629c2cb5f523b536c46adff9: |
11 | 10 | ||
12 | Merge remote-tracking branch 'mreitz/tags/pull-block-2017-06-23' into queue-block (2017-06-23 14:09:12 +0200) | 11 | docs: qsd: Explain --export nbd,name=... default (2021-03-05 17:09:46 +0100) |
13 | 12 | ||
14 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
14 | Block layer patches: | ||
15 | 15 | ||
16 | Block layer patches | 16 | - qemu-storage-daemon: add --pidfile option |
17 | - qemu-storage-daemon: CLI error messages include the option name now | ||
18 | - vhost-user-blk export: Misc fixes, added test cases | ||
19 | - docs: Improvements for qemu-storage-daemon documentation | ||
20 | - parallels: load bitmap extension | ||
21 | - backup-top: Don't crash on post-finalize accesses | ||
22 | - iotests improvements | ||
17 | 23 | ||
18 | ---------------------------------------------------------------- | 24 | ---------------------------------------------------------------- |
19 | Alberto Garcia (9): | 25 | Alberto Garcia (1): |
20 | throttle: Update throttle-groups.c documentation | 26 | iotests: Drop deprecated 'props' from object-add |
21 | qcow2: Remove unused Error variable in do_perform_cow() | ||
22 | qcow2: Use unsigned int for both members of Qcow2COWRegion | ||
23 | qcow2: Make perform_cow() call do_perform_cow() twice | ||
24 | qcow2: Split do_perform_cow() into _read(), _encrypt() and _write() | ||
25 | qcow2: Allow reading both COW regions with only one request | ||
26 | qcow2: Pass a QEMUIOVector to do_perform_cow_{read,write}() | ||
27 | qcow2: Merge the writing of the COW regions with the guest data | ||
28 | qcow2: Use offset_into_cluster() and offset_to_l2_index() | ||
29 | 27 | ||
30 | Kevin Wolf (37): | 28 | Coiby Xu (1): |
31 | commit: Fix completion with extra reference | 29 | test: new qTest case to test the vhost-user-blk-server |
32 | qemu-iotests: Allow starting new qemu after cleanup | ||
33 | qemu-iotests: Test exiting qemu with running job | ||
34 | doc: Document generic -blockdev options | ||
35 | doc: Document driver-specific -blockdev options | ||
36 | qed: Use bottom half to resume waiting requests | ||
37 | qed: Make qed_read_table() synchronous | ||
38 | qed: Remove callback from qed_read_table() | ||
39 | qed: Remove callback from qed_read_l2_table() | ||
40 | qed: Remove callback from qed_find_cluster() | ||
41 | qed: Make qed_read_backing_file() synchronous | ||
42 | qed: Make qed_copy_from_backing_file() synchronous | ||
43 | qed: Remove callback from qed_copy_from_backing_file() | ||
44 | qed: Make qed_write_header() synchronous | ||
45 | qed: Remove callback from qed_write_header() | ||
46 | qed: Make qed_write_table() synchronous | ||
47 | qed: Remove GenericCB | ||
48 | qed: Remove callback from qed_write_table() | ||
49 | qed: Make qed_aio_read_data() synchronous | ||
50 | qed: Make qed_aio_write_main() synchronous | ||
51 | qed: Inline qed_commit_l2_update() | ||
52 | qed: Add return value to qed_aio_write_l1_update() | ||
53 | qed: Add return value to qed_aio_write_l2_update() | ||
54 | qed: Add return value to qed_aio_write_main() | ||
55 | qed: Add return value to qed_aio_write_cow() | ||
56 | qed: Add return value to qed_aio_write_inplace/alloc() | ||
57 | qed: Add return value to qed_aio_read/write_data() | ||
58 | qed: Remove ret argument from qed_aio_next_io() | ||
59 | qed: Remove recursion in qed_aio_next_io() | ||
60 | qed: Implement .bdrv_co_readv/writev | ||
61 | qed: Use CoQueue for serialising allocations | ||
62 | qed: Simplify request handling | ||
63 | qed: Use a coroutine for need_check_timer | ||
64 | qed: Add coroutine_fn to I/O path functions | ||
65 | qed: Use bdrv_co_* for coroutine_fns | ||
66 | block: Remove bdrv_aio_readv/writev/flush() | ||
67 | Merge remote-tracking branch 'mreitz/tags/pull-block-2017-06-23' into queue-block | ||
68 | 30 | ||
69 | Manos Pitsidianakis (1): | 31 | Eric Blake (1): |
70 | block: change variable names in BlockDriverState | 32 | iotests: Fix up python style in 300 |
33 | |||
34 | Kevin Wolf (1): | ||
35 | docs: qsd: Explain --export nbd,name=... default | ||
71 | 36 | ||
72 | Max Reitz (3): | 37 | Max Reitz (3): |
73 | blkdebug: Catch bs->exact_filename overflow | 38 | backup: Remove nodes from job in .clean() |
74 | blkverify: Catch bs->exact_filename overflow | 39 | backup-top: Refuse I/O in inactive state |
75 | block: Do not strcmp() with NULL uri->scheme | 40 | iotests/283: Check that finalize drops backup-top |
76 | 41 | ||
77 | Stefan Hajnoczi (10): | 42 | Paolo Bonzini (2): |
78 | block: count bdrv_co_rw_vmstate() requests | 43 | storage-daemon: report unexpected arguments on the fly |
79 | block: use BDRV_POLL_WHILE() in bdrv_rw_vmstate() | 44 | storage-daemon: include current command line option in the errors |
80 | migration: avoid recursive AioContext locking in save_vmstate() | ||
81 | migration: use bdrv_drain_all_begin/end() instead bdrv_drain_all() | ||
82 | virtio-pci: use ioeventfd even when KVM is disabled | ||
83 | migration: hold AioContext lock for loadvm qemu_fclose() | ||
84 | qemu-iotests: 068: extract _qemu() function | ||
85 | qemu-iotests: 068: use -drive/-device instead of -hda | ||
86 | qemu-iotests: 068: test iothread mode | ||
87 | qemu-img: don't shadow opts variable in img_dd() | ||
88 | 45 | ||
89 | Stephen Bates (1): | 46 | Stefan Hajnoczi (14): |
90 | nvme: Add support for Read Data and Write Data in CMBs. | 47 | qemu-storage-daemon: add --pidfile option |
48 | docs: show how to spawn qemu-storage-daemon with fd passing | ||
49 | docs: replace insecure /tmp examples in qsd docs | ||
50 | vhost-user-blk: fix blkcfg->num_queues endianness | ||
51 | libqtest: add qtest_socket_server() | ||
52 | libqtest: add qtest_kill_qemu() | ||
53 | libqtest: add qtest_remove_abrt_handler() | ||
54 | tests/qtest: add multi-queue test case to vhost-user-blk-test | ||
55 | block/export: fix blk_size double byteswap | ||
56 | block/export: use VIRTIO_BLK_SECTOR_BITS | ||
57 | block/export: fix vhost-user-blk export sector number calculation | ||
58 | block/export: port virtio-blk discard/write zeroes input validation | ||
59 | vhost-user-blk-test: test discard/write zeroes invalid inputs | ||
60 | block/export: port virtio-blk read/write range check | ||
91 | 61 | ||
92 | sochin.jiang (1): | 62 | Stefano Garzarella (1): |
93 | fix: avoid an infinite loop or a dangling pointer problem in img_commit | 63 | blockjob: report a better error message |
94 | 64 | ||
95 | block/Makefile.objs | 2 +- | 65 | Vladimir Sementsov-Ogievskiy (7): |
96 | block/blkdebug.c | 46 +-- | 66 | qcow2-bitmap: make bytes_covered_by_bitmap_cluster() public |
97 | block/blkreplay.c | 8 +- | 67 | parallels.txt: fix bitmap L1 table description |
98 | block/blkverify.c | 12 +- | 68 | block/parallels: BDRVParallelsState: add cluster_size field |
99 | block/block-backend.c | 22 +- | 69 | parallels: support bitmap extension for read-only mode |
100 | block/commit.c | 7 + | 70 | iotests.py: add unarchive_sample_image() helper |
101 | block/file-posix.c | 34 +- | 71 | iotests: add parallels-read-bitmap test |
102 | block/io.c | 240 ++----------- | 72 | MAINTAINERS: update parallels block driver |
103 | block/iscsi.c | 20 +- | ||
104 | block/mirror.c | 8 +- | ||
105 | block/nbd-client.c | 8 +- | ||
106 | block/nbd-client.h | 4 +- | ||
107 | block/nbd.c | 6 +- | ||
108 | block/nfs.c | 2 +- | ||
109 | block/qcow2-cluster.c | 201 ++++++++--- | ||
110 | block/qcow2.c | 94 +++-- | ||
111 | block/qcow2.h | 11 +- | ||
112 | block/qed-cluster.c | 124 +++---- | ||
113 | block/qed-gencb.c | 33 -- | ||
114 | block/qed-table.c | 261 +++++--------- | ||
115 | block/qed.c | 779 ++++++++++++++++------------------------- | ||
116 | block/qed.h | 54 +-- | ||
117 | block/raw-format.c | 8 +- | ||
118 | block/rbd.c | 4 +- | ||
119 | block/sheepdog.c | 12 +- | ||
120 | block/ssh.c | 2 +- | ||
121 | block/throttle-groups.c | 2 +- | ||
122 | block/trace-events | 3 - | ||
123 | blockjob.c | 4 +- | ||
124 | hw/block/nvme.c | 83 +++-- | ||
125 | hw/block/nvme.h | 1 + | ||
126 | hw/virtio/virtio-pci.c | 2 +- | ||
127 | include/block/block.h | 16 +- | ||
128 | include/block/block_int.h | 6 +- | ||
129 | include/block/blockjob.h | 18 + | ||
130 | include/sysemu/block-backend.h | 20 +- | ||
131 | migration/savevm.c | 32 +- | ||
132 | qemu-img.c | 29 +- | ||
133 | qemu-io-cmds.c | 46 +-- | ||
134 | qemu-options.hx | 221 ++++++++++-- | ||
135 | tests/qemu-iotests/068 | 37 +- | ||
136 | tests/qemu-iotests/068.out | 11 +- | ||
137 | tests/qemu-iotests/185 | 206 +++++++++++ | ||
138 | tests/qemu-iotests/185.out | 59 ++++ | ||
139 | tests/qemu-iotests/common.qemu | 3 + | ||
140 | tests/qemu-iotests/group | 1 + | ||
141 | 46 files changed, 1477 insertions(+), 1325 deletions(-) | ||
142 | delete mode 100644 block/qed-gencb.c | ||
143 | create mode 100755 tests/qemu-iotests/185 | ||
144 | create mode 100644 tests/qemu-iotests/185.out | ||
145 | 73 | ||
74 | docs/interop/parallels.txt | 28 +- | ||
75 | docs/tools/qemu-storage-daemon.rst | 68 +- | ||
76 | block/parallels.h | 7 +- | ||
77 | include/block/dirty-bitmap.h | 2 + | ||
78 | tests/qtest/libqos/libqtest.h | 37 + | ||
79 | tests/qtest/libqos/vhost-user-blk.h | 48 + | ||
80 | block/backup-top.c | 10 + | ||
81 | block/backup.c | 1 + | ||
82 | block/dirty-bitmap.c | 13 + | ||
83 | block/export/vhost-user-blk-server.c | 150 +++- | ||
84 | block/parallels-ext.c | 300 +++++++ | ||
85 | block/parallels.c | 26 +- | ||
86 | block/qcow2-bitmap.c | 16 +- | ||
87 | blockjob.c | 10 +- | ||
88 | hw/block/vhost-user-blk.c | 7 +- | ||
89 | storage-daemon/qemu-storage-daemon.c | 56 +- | ||
90 | tests/qtest/libqos/vhost-user-blk.c | 130 +++ | ||
91 | tests/qtest/libqtest.c | 82 +- | ||
92 | tests/qtest/vhost-user-blk-test.c | 983 +++++++++++++++++++++ | ||
93 | tests/qemu-iotests/iotests.py | 10 + | ||
94 | MAINTAINERS | 5 + | ||
95 | block/meson.build | 3 +- | ||
96 | tests/qemu-iotests/087 | 8 +- | ||
97 | tests/qemu-iotests/184 | 18 +- | ||
98 | tests/qemu-iotests/218 | 2 +- | ||
99 | tests/qemu-iotests/235 | 2 +- | ||
100 | tests/qemu-iotests/245 | 4 +- | ||
101 | tests/qemu-iotests/258 | 6 +- | ||
102 | tests/qemu-iotests/258.out | 4 +- | ||
103 | tests/qemu-iotests/283 | 53 ++ | ||
104 | tests/qemu-iotests/283.out | 15 + | ||
105 | tests/qemu-iotests/295 | 2 +- | ||
106 | tests/qemu-iotests/296 | 2 +- | ||
107 | tests/qemu-iotests/300 | 10 +- | ||
108 | .../sample_images/parallels-with-bitmap.bz2 | Bin 0 -> 203 bytes | ||
109 | .../sample_images/parallels-with-bitmap.sh | 51 ++ | ||
110 | tests/qemu-iotests/tests/parallels-read-bitmap | 55 ++ | ||
111 | tests/qemu-iotests/tests/parallels-read-bitmap.out | 6 + | ||
112 | tests/qtest/libqos/meson.build | 1 + | ||
113 | tests/qtest/meson.build | 4 + | ||
114 | 40 files changed, 2098 insertions(+), 137 deletions(-) | ||
115 | create mode 100644 tests/qtest/libqos/vhost-user-blk.h | ||
116 | create mode 100644 block/parallels-ext.c | ||
117 | create mode 100644 tests/qtest/libqos/vhost-user-blk.c | ||
118 | create mode 100644 tests/qtest/vhost-user-blk-test.c | ||
119 | create mode 100644 tests/qemu-iotests/sample_images/parallels-with-bitmap.bz2 | ||
120 | create mode 100755 tests/qemu-iotests/sample_images/parallels-with-bitmap.sh | ||
121 | create mode 100755 tests/qemu-iotests/tests/parallels-read-bitmap | ||
122 | create mode 100644 tests/qemu-iotests/tests/parallels-read-bitmap.out | ||
123 | |||
124 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | commit_complete() can't assume that after its block_job_completed() the | ||
2 | job is actually immediately freed; someone else may still be holding | ||
3 | references. In this case, the op blockers on the intermediate nodes make | ||
4 | the graph reconfiguration in the completion code fail. | ||
5 | 1 | ||
6 | Call block_job_remove_all_bdrv() manually so that we know for sure that | ||
7 | any blockers on intermediate nodes are given up. | ||
8 | |||
9 | Cc: qemu-stable@nongnu.org | ||
10 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
11 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
12 | Reviewed-by: Max Reitz <mreitz@redhat.com> | ||
13 | --- | ||
14 | block/commit.c | 7 +++++++ | ||
15 | 1 file changed, 7 insertions(+) | ||
16 | |||
17 | diff --git a/block/commit.c b/block/commit.c | ||
18 | index XXXXXXX..XXXXXXX 100644 | ||
19 | --- a/block/commit.c | ||
20 | +++ b/block/commit.c | ||
21 | @@ -XXX,XX +XXX,XX @@ static void commit_complete(BlockJob *job, void *opaque) | ||
22 | } | ||
23 | g_free(s->backing_file_str); | ||
24 | blk_unref(s->top); | ||
25 | + | ||
26 | + /* If there is more than one reference to the job (e.g. if called from | ||
27 | + * block_job_finish_sync()), block_job_completed() won't free it and | ||
28 | + * therefore the blockers on the intermediate nodes remain. This would | ||
29 | + * cause bdrv_set_backing_hd() to fail. */ | ||
30 | + block_job_remove_all_bdrv(job); | ||
31 | + | ||
32 | block_job_completed(&s->common, ret); | ||
33 | g_free(data); | ||
34 | |||
35 | -- | ||
36 | 1.8.3.1 | ||
37 | |||
38 | diff view generated by jsdifflib |
1 | From: Alberto Garcia <berto@igalia.com> | 1 | From: Alberto Garcia <berto@igalia.com> |
---|---|---|---|
2 | 2 | ||
3 | We already have functions for doing these calculations, so let's use | ||
4 | them instead of doing everything by hand. This makes the code a bit | ||
5 | more readable. | ||
6 | |||
7 | Signed-off-by: Alberto Garcia <berto@igalia.com> | 3 | Signed-off-by: Alberto Garcia <berto@igalia.com> |
4 | Message-Id: <20210222115737.2993-1-berto@igalia.com> | ||
8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
9 | --- | 6 | --- |
10 | block/qcow2-cluster.c | 4 ++-- | 7 | tests/qemu-iotests/087 | 8 ++------ |
11 | block/qcow2.c | 2 +- | 8 | tests/qemu-iotests/184 | 18 ++++++------------ |
12 | 2 files changed, 3 insertions(+), 3 deletions(-) | 9 | tests/qemu-iotests/218 | 2 +- |
13 | 10 | tests/qemu-iotests/235 | 2 +- | |
14 | diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c | 11 | tests/qemu-iotests/245 | 4 ++-- |
12 | tests/qemu-iotests/258 | 6 +++--- | ||
13 | tests/qemu-iotests/258.out | 4 ++-- | ||
14 | tests/qemu-iotests/295 | 2 +- | ||
15 | tests/qemu-iotests/296 | 2 +- | ||
16 | 9 files changed, 19 insertions(+), 29 deletions(-) | ||
17 | |||
18 | diff --git a/tests/qemu-iotests/087 b/tests/qemu-iotests/087 | ||
19 | index XXXXXXX..XXXXXXX 100755 | ||
20 | --- a/tests/qemu-iotests/087 | ||
21 | +++ b/tests/qemu-iotests/087 | ||
22 | @@ -XXX,XX +XXX,XX @@ run_qemu <<EOF | ||
23 | "arguments": { | ||
24 | "qom-type": "secret", | ||
25 | "id": "sec0", | ||
26 | - "props": { | ||
27 | - "data": "123456" | ||
28 | - } | ||
29 | + "data": "123456" | ||
30 | } | ||
31 | } | ||
32 | { "execute": "blockdev-add", | ||
33 | @@ -XXX,XX +XXX,XX @@ run_qemu <<EOF | ||
34 | "arguments": { | ||
35 | "qom-type": "secret", | ||
36 | "id": "sec0", | ||
37 | - "props": { | ||
38 | - "data": "123456" | ||
39 | - } | ||
40 | + "data": "123456" | ||
41 | } | ||
42 | } | ||
43 | { "execute": "blockdev-add", | ||
44 | diff --git a/tests/qemu-iotests/184 b/tests/qemu-iotests/184 | ||
45 | index XXXXXXX..XXXXXXX 100755 | ||
46 | --- a/tests/qemu-iotests/184 | ||
47 | +++ b/tests/qemu-iotests/184 | ||
48 | @@ -XXX,XX +XXX,XX @@ run_qemu <<EOF | ||
49 | "arguments": { | ||
50 | "qom-type": "throttle-group", | ||
51 | "id": "group0", | ||
52 | - "props": { | ||
53 | - "limits" : { | ||
54 | - "iops-total": 1000 | ||
55 | - } | ||
56 | + "limits" : { | ||
57 | + "iops-total": 1000 | ||
58 | } | ||
59 | } | ||
60 | } | ||
61 | @@ -XXX,XX +XXX,XX @@ run_qemu <<EOF | ||
62 | "arguments": { | ||
63 | "qom-type": "throttle-group", | ||
64 | "id": "group0", | ||
65 | - "props" : { | ||
66 | - "limits": { | ||
67 | - "iops-total": 1000 | ||
68 | - } | ||
69 | + "limits": { | ||
70 | + "iops-total": 1000 | ||
71 | } | ||
72 | } | ||
73 | } | ||
74 | @@ -XXX,XX +XXX,XX @@ run_qemu <<EOF | ||
75 | "arguments": { | ||
76 | "qom-type": "throttle-group", | ||
77 | "id": "group0", | ||
78 | - "props" : { | ||
79 | - "limits": { | ||
80 | - "iops-total": 1000 | ||
81 | - } | ||
82 | + "limits": { | ||
83 | + "iops-total": 1000 | ||
84 | } | ||
85 | } | ||
86 | } | ||
87 | diff --git a/tests/qemu-iotests/218 b/tests/qemu-iotests/218 | ||
88 | index XXXXXXX..XXXXXXX 100755 | ||
89 | --- a/tests/qemu-iotests/218 | ||
90 | +++ b/tests/qemu-iotests/218 | ||
91 | @@ -XXX,XX +XXX,XX @@ with iotests.VM() as vm, \ | ||
92 | vm.launch() | ||
93 | |||
94 | ret = vm.qmp('object-add', qom_type='throttle-group', id='tg', | ||
95 | - props={'x-bps-read': 4096}) | ||
96 | + limits={'bps-read': 4096}) | ||
97 | assert ret['return'] == {} | ||
98 | |||
99 | ret = vm.qmp('blockdev-add', | ||
100 | diff --git a/tests/qemu-iotests/235 b/tests/qemu-iotests/235 | ||
101 | index XXXXXXX..XXXXXXX 100755 | ||
102 | --- a/tests/qemu-iotests/235 | ||
103 | +++ b/tests/qemu-iotests/235 | ||
104 | @@ -XXX,XX +XXX,XX @@ vm.add_args('-drive', 'id=src,file=' + disk) | ||
105 | vm.launch() | ||
106 | |||
107 | log(vm.qmp('object-add', qom_type='throttle-group', id='tg0', | ||
108 | - props={ 'x-bps-total': size })) | ||
109 | + limits={'bps-total': size})) | ||
110 | |||
111 | log(vm.qmp('blockdev-add', | ||
112 | **{ 'node-name': 'target', | ||
113 | diff --git a/tests/qemu-iotests/245 b/tests/qemu-iotests/245 | ||
114 | index XXXXXXX..XXXXXXX 100755 | ||
115 | --- a/tests/qemu-iotests/245 | ||
116 | +++ b/tests/qemu-iotests/245 | ||
117 | @@ -XXX,XX +XXX,XX @@ class TestBlockdevReopen(iotests.QMPTestCase): | ||
118 | ###### throttle ###### | ||
119 | ###################### | ||
120 | opts = { 'qom-type': 'throttle-group', 'id': 'group0', | ||
121 | - 'props': { 'limits': { 'iops-total': 1000 } } } | ||
122 | + 'limits': { 'iops-total': 1000 } } | ||
123 | result = self.vm.qmp('object-add', conv_keys = False, **opts) | ||
124 | self.assert_qmp(result, 'return', {}) | ||
125 | |||
126 | opts = { 'qom-type': 'throttle-group', 'id': 'group1', | ||
127 | - 'props': { 'limits': { 'iops-total': 2000 } } } | ||
128 | + 'limits': { 'iops-total': 2000 } } | ||
129 | result = self.vm.qmp('object-add', conv_keys = False, **opts) | ||
130 | self.assert_qmp(result, 'return', {}) | ||
131 | |||
132 | diff --git a/tests/qemu-iotests/258 b/tests/qemu-iotests/258 | ||
133 | index XXXXXXX..XXXXXXX 100755 | ||
134 | --- a/tests/qemu-iotests/258 | ||
135 | +++ b/tests/qemu-iotests/258 | ||
136 | @@ -XXX,XX +XXX,XX @@ def test_concurrent_finish(write_to_stream_node): | ||
137 | vm.qmp_log('object-add', | ||
138 | qom_type='throttle-group', | ||
139 | id='tg', | ||
140 | - props={ | ||
141 | - 'x-iops-write': 1, | ||
142 | - 'x-iops-write-max': 1 | ||
143 | + limits={ | ||
144 | + 'iops-write': 1, | ||
145 | + 'iops-write-max': 1 | ||
146 | }) | ||
147 | |||
148 | vm.qmp_log('blockdev-add', | ||
149 | diff --git a/tests/qemu-iotests/258.out b/tests/qemu-iotests/258.out | ||
15 | index XXXXXXX..XXXXXXX 100644 | 150 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/block/qcow2-cluster.c | 151 | --- a/tests/qemu-iotests/258.out |
17 | +++ b/block/qcow2-cluster.c | 152 | +++ b/tests/qemu-iotests/258.out |
18 | @@ -XXX,XX +XXX,XX @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset, | 153 | @@ -XXX,XX +XXX,XX @@ Running tests: |
19 | 154 | ||
20 | /* find the cluster offset for the given disk offset */ | 155 | === Commit and stream finish concurrently (letting stream write) === |
21 | 156 | ||
22 | - l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1); | 157 | -{"execute": "object-add", "arguments": {"id": "tg", "props": {"x-iops-write": 1, "x-iops-write-max": 1}, "qom-type": "throttle-group"}} |
23 | + l2_index = offset_to_l2_index(s, offset); | 158 | +{"execute": "object-add", "arguments": {"id": "tg", "limits": {"iops-write": 1, "iops-write-max": 1}, "qom-type": "throttle-group"}} |
24 | *cluster_offset = be64_to_cpu(l2_table[l2_index]); | 159 | {"return": {}} |
25 | 160 | {"execute": "blockdev-add", "arguments": {"backing": {"backing": {"backing": {"backing": {"driver": "raw", "file": {"driver": "file", "filename": "TEST_DIR/PID-node0.img"}, "node-name": "node0"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-node1.img"}, "node-name": "node1"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-node2.img"}, "node-name": "node2"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-node3.img"}, "node-name": "node3"}, "driver": "IMGFMT", "file": {"driver": "throttle", "file": {"driver": "file", "filename": "TEST_DIR/PID-node4.img"}, "throttle-group": "tg"}, "node-name": "node4"}} | |
26 | nb_clusters = size_to_clusters(s, bytes_needed); | 161 | {"return": {}} |
27 | @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, | 162 | @@ -XXX,XX +XXX,XX @@ Running tests: |
28 | 163 | ||
29 | /* find the cluster offset for the given disk offset */ | 164 | === Commit and stream finish concurrently (letting commit write) === |
30 | 165 | ||
31 | - l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1); | 166 | -{"execute": "object-add", "arguments": {"id": "tg", "props": {"x-iops-write": 1, "x-iops-write-max": 1}, "qom-type": "throttle-group"}} |
32 | + l2_index = offset_to_l2_index(s, offset); | 167 | +{"execute": "object-add", "arguments": {"id": "tg", "limits": {"iops-write": 1, "iops-write-max": 1}, "qom-type": "throttle-group"}} |
33 | 168 | {"return": {}} | |
34 | *new_l2_table = l2_table; | 169 | {"execute": "blockdev-add", "arguments": {"backing": {"backing": {"backing": {"backing": {"driver": "raw", "file": {"driver": "throttle", "file": {"driver": "file", "filename": "TEST_DIR/PID-node0.img"}, "throttle-group": "tg"}, "node-name": "node0"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-node1.img"}, "node-name": "node1"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-node2.img"}, "node-name": "node2"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-node3.img"}, "node-name": "node3"}, "driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-node4.img"}, "node-name": "node4"}} |
35 | *new_l2_index = l2_index; | 170 | {"return": {}} |
36 | diff --git a/block/qcow2.c b/block/qcow2.c | 171 | diff --git a/tests/qemu-iotests/295 b/tests/qemu-iotests/295 |
37 | index XXXXXXX..XXXXXXX 100644 | 172 | index XXXXXXX..XXXXXXX 100755 |
38 | --- a/block/qcow2.c | 173 | --- a/tests/qemu-iotests/295 |
39 | +++ b/block/qcow2.c | 174 | +++ b/tests/qemu-iotests/295 |
40 | @@ -XXX,XX +XXX,XX @@ static int validate_table_offset(BlockDriverState *bs, uint64_t offset, | 175 | @@ -XXX,XX +XXX,XX @@ class Secret: |
41 | } | 176 | |
42 | 177 | def to_qmp_object(self): | |
43 | /* Tables must be cluster aligned */ | 178 | return { "qom_type" : "secret", "id": self.id(), |
44 | - if (offset & (s->cluster_size - 1)) { | 179 | - "props": { "data": self.secret() } } |
45 | + if (offset_into_cluster(s, offset) != 0) { | 180 | + "data": self.secret() } |
46 | return -EINVAL; | 181 | |
47 | } | 182 | ################################################################################ |
183 | class EncryptionSetupTestCase(iotests.QMPTestCase): | ||
184 | diff --git a/tests/qemu-iotests/296 b/tests/qemu-iotests/296 | ||
185 | index XXXXXXX..XXXXXXX 100755 | ||
186 | --- a/tests/qemu-iotests/296 | ||
187 | +++ b/tests/qemu-iotests/296 | ||
188 | @@ -XXX,XX +XXX,XX @@ class Secret: | ||
189 | |||
190 | def to_qmp_object(self): | ||
191 | return { "qom_type" : "secret", "id": self.id(), | ||
192 | - "props": { "data": self.secret() } } | ||
193 | + "data": self.secret() } | ||
194 | |||
195 | ################################################################################ | ||
48 | 196 | ||
49 | -- | 197 | -- |
50 | 1.8.3.1 | 198 | 2.29.2 |
51 | 199 | ||
52 | 200 | diff view generated by jsdifflib |
1 | From: Max Reitz <mreitz@redhat.com> | 1 | From: Max Reitz <mreitz@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | The bs->exact_filename field may not be sufficient to store the full | 3 | The block job holds a reference to the backup-top node (because it is |
4 | blkverify node filename. In this case, we should not generate a filename | 4 | passed as the main job BDS to block_job_create()). Therefore, |
5 | at all instead of an unusable one. | 5 | bdrv_backup_top_drop() cannot delete the backup-top node (replacing it |
6 | by its child does not affect the job parent, because that has | ||
7 | .stay_at_node set). That is a problem, because all of its I/O functions | ||
8 | assume the BlockCopyState (s->bcs) to be valid and that it has a | ||
9 | filtered child; but after bdrv_backup_top_drop(), neither of those | ||
10 | things are true. | ||
6 | 11 | ||
7 | Cc: qemu-stable@nongnu.org | 12 | It does not make sense to add new parents to backup-top after |
8 | Reported-by: Qu Wenruo <quwenruo@cn.fujitsu.com> | 13 | backup_clean(), so we should detach it from the job before |
14 | bdrv_backup_top_drop(). Because there is no function to do that for a | ||
15 | single node, just detach all of the job's nodes -- the job does not do | ||
16 | anything past backup_clean() anyway. | ||
17 | |||
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 18 | Signed-off-by: Max Reitz <mreitz@redhat.com> |
10 | Message-id: 20170613172006.19685-3-mreitz@redhat.com | 19 | Message-Id: <20210219153348.41861-2-mreitz@redhat.com> |
11 | Reviewed-by: Alberto Garcia <berto@igalia.com> | 20 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
12 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
13 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
14 | --- | 21 | --- |
15 | block/blkverify.c | 12 ++++++++---- | 22 | block/backup.c | 1 + |
16 | 1 file changed, 8 insertions(+), 4 deletions(-) | 23 | 1 file changed, 1 insertion(+) |
17 | 24 | ||
18 | diff --git a/block/blkverify.c b/block/blkverify.c | 25 | diff --git a/block/backup.c b/block/backup.c |
19 | index XXXXXXX..XXXXXXX 100644 | 26 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/block/blkverify.c | 27 | --- a/block/backup.c |
21 | +++ b/block/blkverify.c | 28 | +++ b/block/backup.c |
22 | @@ -XXX,XX +XXX,XX @@ static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options) | 29 | @@ -XXX,XX +XXX,XX @@ static void backup_abort(Job *job) |
23 | if (bs->file->bs->exact_filename[0] | 30 | static void backup_clean(Job *job) |
24 | && s->test_file->bs->exact_filename[0]) | 31 | { |
25 | { | 32 | BackupBlockJob *s = container_of(job, BackupBlockJob, common.job); |
26 | - snprintf(bs->exact_filename, sizeof(bs->exact_filename), | 33 | + block_job_remove_all_bdrv(&s->common); |
27 | - "blkverify:%s:%s", | 34 | bdrv_backup_top_drop(s->backup_top); |
28 | - bs->file->bs->exact_filename, | ||
29 | - s->test_file->bs->exact_filename); | ||
30 | + int ret = snprintf(bs->exact_filename, sizeof(bs->exact_filename), | ||
31 | + "blkverify:%s:%s", | ||
32 | + bs->file->bs->exact_filename, | ||
33 | + s->test_file->bs->exact_filename); | ||
34 | + if (ret >= sizeof(bs->exact_filename)) { | ||
35 | + /* An overflow makes the filename unusable, so do not report any */ | ||
36 | + bs->exact_filename[0] = 0; | ||
37 | + } | ||
38 | } | ||
39 | } | 35 | } |
40 | 36 | ||
41 | -- | 37 | -- |
42 | 1.8.3.1 | 38 | 2.29.2 |
43 | 39 | ||
44 | 40 | diff view generated by jsdifflib |
1 | From: Max Reitz <mreitz@redhat.com> | 1 | From: Max Reitz <mreitz@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | uri_parse(...)->scheme may be NULL. In fact, probably every field may be | 3 | When the backup-top node transitions from active to inactive in |
4 | NULL, and the callers do test this for all of the other fields but not | 4 | bdrv_backup_top_drop(), the BlockCopyState is freed and the filtered |
5 | for scheme (except for block/gluster.c; block/vxhs.c does not access | 5 | child is removed, so the node effectively becomes unusable. |
6 | that field at all). | ||
7 | 6 | ||
8 | We can easily fix this by using g_strcmp0() instead of strcmp(). | 7 | However, noone told its I/O functions this, so they will happily |
8 | continue accessing bs->backing and s->bcs. Prevent that by aborting | ||
9 | early when s->active is false. | ||
9 | 10 | ||
10 | Cc: qemu-stable@nongnu.org | 11 | (After the preceding patch, the node should be gone after |
12 | bdrv_backup_top_drop(), so this should largely be a theoretical problem. | ||
13 | But still, better to be safe than sorry, and also I think it just makes | ||
14 | sense to check s->active in the I/O functions.) | ||
15 | |||
11 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 16 | Signed-off-by: Max Reitz <mreitz@redhat.com> |
12 | Message-id: 20170613205726.13544-1-mreitz@redhat.com | 17 | Message-Id: <20210219153348.41861-3-mreitz@redhat.com> |
13 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | 18 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
14 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
15 | --- | 19 | --- |
16 | block/nbd.c | 6 +++--- | 20 | block/backup-top.c | 10 ++++++++++ |
17 | block/nfs.c | 2 +- | 21 | 1 file changed, 10 insertions(+) |
18 | block/sheepdog.c | 6 +++--- | ||
19 | block/ssh.c | 2 +- | ||
20 | 4 files changed, 8 insertions(+), 8 deletions(-) | ||
21 | 22 | ||
22 | diff --git a/block/nbd.c b/block/nbd.c | 23 | diff --git a/block/backup-top.c b/block/backup-top.c |
23 | index XXXXXXX..XXXXXXX 100644 | 24 | index XXXXXXX..XXXXXXX 100644 |
24 | --- a/block/nbd.c | 25 | --- a/block/backup-top.c |
25 | +++ b/block/nbd.c | 26 | +++ b/block/backup-top.c |
26 | @@ -XXX,XX +XXX,XX @@ static int nbd_parse_uri(const char *filename, QDict *options) | 27 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int backup_top_co_preadv( |
27 | } | 28 | BlockDriverState *bs, uint64_t offset, uint64_t bytes, |
28 | 29 | QEMUIOVector *qiov, int flags) | |
29 | /* transport */ | 30 | { |
30 | - if (!strcmp(uri->scheme, "nbd")) { | 31 | + BDRVBackupTopState *s = bs->opaque; |
31 | + if (!g_strcmp0(uri->scheme, "nbd")) { | 32 | + |
32 | is_unix = false; | 33 | + if (!s->active) { |
33 | - } else if (!strcmp(uri->scheme, "nbd+tcp")) { | 34 | + return -EIO; |
34 | + } else if (!g_strcmp0(uri->scheme, "nbd+tcp")) { | 35 | + } |
35 | is_unix = false; | 36 | + |
36 | - } else if (!strcmp(uri->scheme, "nbd+unix")) { | 37 | return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags); |
37 | + } else if (!g_strcmp0(uri->scheme, "nbd+unix")) { | 38 | } |
38 | is_unix = true; | 39 | |
39 | } else { | 40 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset, |
40 | ret = -EINVAL; | 41 | BDRVBackupTopState *s = bs->opaque; |
41 | diff --git a/block/nfs.c b/block/nfs.c | 42 | uint64_t off, end; |
42 | index XXXXXXX..XXXXXXX 100644 | 43 | |
43 | --- a/block/nfs.c | 44 | + if (!s->active) { |
44 | +++ b/block/nfs.c | 45 | + return -EIO; |
45 | @@ -XXX,XX +XXX,XX @@ static int nfs_parse_uri(const char *filename, QDict *options, Error **errp) | 46 | + } |
46 | error_setg(errp, "Invalid URI specified"); | 47 | + |
47 | goto out; | 48 | if (flags & BDRV_REQ_WRITE_UNCHANGED) { |
48 | } | 49 | return 0; |
49 | - if (strcmp(uri->scheme, "nfs") != 0) { | ||
50 | + if (g_strcmp0(uri->scheme, "nfs") != 0) { | ||
51 | error_setg(errp, "URI scheme must be 'nfs'"); | ||
52 | goto out; | ||
53 | } | ||
54 | diff --git a/block/sheepdog.c b/block/sheepdog.c | ||
55 | index XXXXXXX..XXXXXXX 100644 | ||
56 | --- a/block/sheepdog.c | ||
57 | +++ b/block/sheepdog.c | ||
58 | @@ -XXX,XX +XXX,XX @@ static void sd_parse_uri(SheepdogConfig *cfg, const char *filename, | ||
59 | } | ||
60 | |||
61 | /* transport */ | ||
62 | - if (!strcmp(uri->scheme, "sheepdog")) { | ||
63 | + if (!g_strcmp0(uri->scheme, "sheepdog")) { | ||
64 | is_unix = false; | ||
65 | - } else if (!strcmp(uri->scheme, "sheepdog+tcp")) { | ||
66 | + } else if (!g_strcmp0(uri->scheme, "sheepdog+tcp")) { | ||
67 | is_unix = false; | ||
68 | - } else if (!strcmp(uri->scheme, "sheepdog+unix")) { | ||
69 | + } else if (!g_strcmp0(uri->scheme, "sheepdog+unix")) { | ||
70 | is_unix = true; | ||
71 | } else { | ||
72 | error_setg(&err, "URI scheme must be 'sheepdog', 'sheepdog+tcp'," | ||
73 | diff --git a/block/ssh.c b/block/ssh.c | ||
74 | index XXXXXXX..XXXXXXX 100644 | ||
75 | --- a/block/ssh.c | ||
76 | +++ b/block/ssh.c | ||
77 | @@ -XXX,XX +XXX,XX @@ static int parse_uri(const char *filename, QDict *options, Error **errp) | ||
78 | return -EINVAL; | ||
79 | } | ||
80 | |||
81 | - if (strcmp(uri->scheme, "ssh") != 0) { | ||
82 | + if (g_strcmp0(uri->scheme, "ssh") != 0) { | ||
83 | error_setg(errp, "URI scheme must be 'ssh'"); | ||
84 | goto err; | ||
85 | } | 50 | } |
86 | -- | 51 | -- |
87 | 1.8.3.1 | 52 | 2.29.2 |
88 | 53 | ||
89 | 54 | diff view generated by jsdifflib |
1 | From: Max Reitz <mreitz@redhat.com> | 1 | From: Max Reitz <mreitz@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | The bs->exact_filename field may not be sufficient to store the full | 3 | Without any of HEAD^ or HEAD^^ applied, qemu will most likely crash on |
4 | blkdebug node filename. In this case, we should not generate a filename | 4 | the qemu-io invocation, for a variety of immediate reasons. The |
5 | at all instead of an unusable one. | 5 | underlying problem is generally a use-after-free access into |
6 | backup-top's BlockCopyState. | ||
6 | 7 | ||
7 | Cc: qemu-stable@nongnu.org | 8 | With only HEAD^ applied, qemu-io will run into an EIO (which is not |
8 | Reported-by: Qu Wenruo <quwenruo@cn.fujitsu.com> | 9 | capture by the output, but you can see that the qemu-io invocation will |
10 | be accepted (i.e., qemu-io will run) in contrast to the reference | ||
11 | output, where the node name cannot be found), and qemu will then crash | ||
12 | in query-named-block-nodes: bdrv_get_allocated_file_size() detects | ||
13 | backup-top to be a filter and passes the request through to its child. | ||
14 | However, after bdrv_backup_top_drop(), that child is NULL, so the | ||
15 | recursive call crashes. | ||
16 | |||
17 | With HEAD^^ applied, this test should pass. | ||
18 | |||
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 19 | Signed-off-by: Max Reitz <mreitz@redhat.com> |
10 | Message-id: 20170613172006.19685-2-mreitz@redhat.com | 20 | Message-Id: <20210219153348.41861-4-mreitz@redhat.com> |
11 | Reviewed-by: Alberto Garcia <berto@igalia.com> | 21 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
12 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
13 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
14 | --- | 22 | --- |
15 | block/blkdebug.c | 10 +++++++--- | 23 | tests/qemu-iotests/283 | 53 ++++++++++++++++++++++++++++++++++++++ |
16 | 1 file changed, 7 insertions(+), 3 deletions(-) | 24 | tests/qemu-iotests/283.out | 15 +++++++++++ |
25 | 2 files changed, 68 insertions(+) | ||
17 | 26 | ||
18 | diff --git a/block/blkdebug.c b/block/blkdebug.c | 27 | diff --git a/tests/qemu-iotests/283 b/tests/qemu-iotests/283 |
28 | index XXXXXXX..XXXXXXX 100755 | ||
29 | --- a/tests/qemu-iotests/283 | ||
30 | +++ b/tests/qemu-iotests/283 | ||
31 | @@ -XXX,XX +XXX,XX @@ vm.qmp_log('blockdev-add', **{ | ||
32 | vm.qmp_log('blockdev-backup', sync='full', device='source', target='target') | ||
33 | |||
34 | vm.shutdown() | ||
35 | + | ||
36 | + | ||
37 | +print('\n=== backup-top should be gone after job-finalize ===\n') | ||
38 | + | ||
39 | +# Check that the backup-top node is gone after job-finalize. | ||
40 | +# | ||
41 | +# During finalization, the node becomes inactive and can no longer | ||
42 | +# function. If it is still present, new parents might be attached, and | ||
43 | +# there would be no meaningful way to handle their I/O requests. | ||
44 | + | ||
45 | +vm = iotests.VM() | ||
46 | +vm.launch() | ||
47 | + | ||
48 | +vm.qmp_log('blockdev-add', **{ | ||
49 | + 'node-name': 'source', | ||
50 | + 'driver': 'null-co', | ||
51 | +}) | ||
52 | + | ||
53 | +vm.qmp_log('blockdev-add', **{ | ||
54 | + 'node-name': 'target', | ||
55 | + 'driver': 'null-co', | ||
56 | +}) | ||
57 | + | ||
58 | +vm.qmp_log('blockdev-backup', | ||
59 | + job_id='backup', | ||
60 | + device='source', | ||
61 | + target='target', | ||
62 | + sync='full', | ||
63 | + filter_node_name='backup-filter', | ||
64 | + auto_finalize=False, | ||
65 | + auto_dismiss=False) | ||
66 | + | ||
67 | +vm.event_wait('BLOCK_JOB_PENDING', 5.0) | ||
68 | + | ||
69 | +# The backup-top filter should still be present prior to finalization | ||
70 | +assert vm.node_info('backup-filter') is not None | ||
71 | + | ||
72 | +vm.qmp_log('job-finalize', id='backup') | ||
73 | +vm.event_wait('BLOCK_JOB_COMPLETED', 5.0) | ||
74 | + | ||
75 | +# The filter should be gone now. Check that by trying to access it | ||
76 | +# with qemu-io (which will most likely crash qemu if it is still | ||
77 | +# there.). | ||
78 | +vm.qmp_log('human-monitor-command', | ||
79 | + command_line='qemu-io backup-filter "write 0 1M"') | ||
80 | + | ||
81 | +# (Also, do an explicit check.) | ||
82 | +assert vm.node_info('backup-filter') is None | ||
83 | + | ||
84 | +vm.qmp_log('job-dismiss', id='backup') | ||
85 | +vm.event_wait('JOB_STATUS_CHANGE', 5.0, {'data': {'status': 'null'}}) | ||
86 | + | ||
87 | +vm.shutdown() | ||
88 | diff --git a/tests/qemu-iotests/283.out b/tests/qemu-iotests/283.out | ||
19 | index XXXXXXX..XXXXXXX 100644 | 89 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/block/blkdebug.c | 90 | --- a/tests/qemu-iotests/283.out |
21 | +++ b/block/blkdebug.c | 91 | +++ b/tests/qemu-iotests/283.out |
22 | @@ -XXX,XX +XXX,XX @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options) | 92 | @@ -XXX,XX +XXX,XX @@ |
23 | } | 93 | {"return": {}} |
24 | 94 | {"execute": "blockdev-backup", "arguments": {"device": "source", "sync": "full", "target": "target"}} | |
25 | if (!force_json && bs->file->bs->exact_filename[0]) { | 95 | {"error": {"class": "GenericError", "desc": "Cannot set permissions for backup-top filter: Conflicts with use by other as 'image', which uses 'write' on base"}} |
26 | - snprintf(bs->exact_filename, sizeof(bs->exact_filename), | 96 | + |
27 | - "blkdebug:%s:%s", s->config_file ?: "", | 97 | +=== backup-top should be gone after job-finalize === |
28 | - bs->file->bs->exact_filename); | 98 | + |
29 | + int ret = snprintf(bs->exact_filename, sizeof(bs->exact_filename), | 99 | +{"execute": "blockdev-add", "arguments": {"driver": "null-co", "node-name": "source"}} |
30 | + "blkdebug:%s:%s", s->config_file ?: "", | 100 | +{"return": {}} |
31 | + bs->file->bs->exact_filename); | 101 | +{"execute": "blockdev-add", "arguments": {"driver": "null-co", "node-name": "target"}} |
32 | + if (ret >= sizeof(bs->exact_filename)) { | 102 | +{"return": {}} |
33 | + /* An overflow makes the filename unusable, so do not report any */ | 103 | +{"execute": "blockdev-backup", "arguments": {"auto-dismiss": false, "auto-finalize": false, "device": "source", "filter-node-name": "backup-filter", "job-id": "backup", "sync": "full", "target": "target"}} |
34 | + bs->exact_filename[0] = 0; | 104 | +{"return": {}} |
35 | + } | 105 | +{"execute": "job-finalize", "arguments": {"id": "backup"}} |
36 | } | 106 | +{"return": {}} |
37 | 107 | +{"execute": "human-monitor-command", "arguments": {"command-line": "qemu-io backup-filter \"write 0 1M\""}} | |
38 | opts = qdict_new(); | 108 | +{"return": "Error: Cannot find device= nor node_name=backup-filter\r\n"} |
109 | +{"execute": "job-dismiss", "arguments": {"id": "backup"}} | ||
110 | +{"return": {}} | ||
39 | -- | 111 | -- |
40 | 1.8.3.1 | 112 | 2.29.2 |
41 | 113 | ||
42 | 114 | diff view generated by jsdifflib |
1 | All functions that are marked coroutine_fn can directly call the | 1 | From: Eric Blake <eblake@redhat.com> |
---|---|---|---|
2 | bdrv_co_* version of functions instead of going through the wrapper. | ||
3 | 2 | ||
3 | Break some long lines, and relax our type hints to be more generic to | ||
4 | any JSON, in order to more easily permit the additional JSON depth now | ||
5 | possible in migration parameters. Detected by iotest 297. | ||
6 | |||
7 | Fixes: ca4bfec41d56 | ||
8 | (qemu-iotests: 300: Add test case for modifying persistence of bitmap) | ||
9 | Reported-by: Kevin Wolf <kwolf@redhat.com> | ||
10 | Signed-off-by: Eric Blake <eblake@redhat.com> | ||
11 | Message-Id: <20210215220518.1745469-1-eblake@redhat.com> | ||
12 | Reviewed-by: John Snow <jsnow@redhat.com> | ||
13 | Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
4 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 14 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
5 | Reviewed-by: Manos Pitsidianakis <el13635@mail.ntua.gr> | ||
6 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
7 | --- | 15 | --- |
8 | block/qed.c | 16 +++++++++------- | 16 | tests/qemu-iotests/300 | 10 ++++++---- |
9 | 1 file changed, 9 insertions(+), 7 deletions(-) | 17 | 1 file changed, 6 insertions(+), 4 deletions(-) |
10 | 18 | ||
11 | diff --git a/block/qed.c b/block/qed.c | 19 | diff --git a/tests/qemu-iotests/300 b/tests/qemu-iotests/300 |
12 | index XXXXXXX..XXXXXXX 100644 | 20 | index XXXXXXX..XXXXXXX 100755 |
13 | --- a/block/qed.c | 21 | --- a/tests/qemu-iotests/300 |
14 | +++ b/block/qed.c | 22 | +++ b/tests/qemu-iotests/300 |
15 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_write_header(BDRVQEDState *s) | 23 | @@ -XXX,XX +XXX,XX @@ |
16 | }; | 24 | import os |
17 | qemu_iovec_init_external(&qiov, &iov, 1); | 25 | import random |
18 | 26 | import re | |
19 | - ret = bdrv_preadv(s->bs->file, 0, &qiov); | 27 | -from typing import Dict, List, Optional, Union |
20 | + ret = bdrv_co_preadv(s->bs->file, 0, qiov.size, &qiov, 0); | 28 | +from typing import Dict, List, Optional |
21 | if (ret < 0) { | 29 | |
22 | goto out; | 30 | import iotests |
23 | } | 31 | |
24 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_write_header(BDRVQEDState *s) | 32 | @@ -XXX,XX +XXX,XX @@ import iotests |
25 | /* Update header */ | 33 | # pylint: disable=wrong-import-order |
26 | qed_header_cpu_to_le(&s->header, (QEDHeader *) buf); | 34 | import qemu |
27 | 35 | ||
28 | - ret = bdrv_pwritev(s->bs->file, 0, &qiov); | 36 | -BlockBitmapMapping = List[Dict[str, Union[str, List[Dict[str, str]]]]] |
29 | + ret = bdrv_co_pwritev(s->bs->file, 0, qiov.size, &qiov, 0); | 37 | +BlockBitmapMapping = List[Dict[str, object]] |
30 | if (ret < 0) { | 38 | |
31 | goto out; | 39 | mig_sock = os.path.join(iotests.sock_dir, 'mig_sock') |
32 | } | 40 | |
33 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_read_backing_file(BDRVQEDState *s, uint64_t pos, | 41 | @@ -XXX,XX +XXX,XX @@ class TestCrossAliasMigration(TestDirtyBitmapMigration): |
34 | qemu_iovec_concat(*backing_qiov, qiov, 0, size); | 42 | |
35 | 43 | class TestAliasTransformMigration(TestDirtyBitmapMigration): | |
36 | BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO); | 44 | """ |
37 | - ret = bdrv_preadv(s->bs->backing, pos, *backing_qiov); | 45 | - Tests the 'transform' option which modifies bitmap persistence on migration. |
38 | + ret = bdrv_co_preadv(s->bs->backing, pos, size, *backing_qiov, 0); | 46 | + Tests the 'transform' option which modifies bitmap persistence on |
39 | if (ret < 0) { | 47 | + migration. |
40 | return ret; | 48 | """ |
41 | } | 49 | |
42 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s, | 50 | src_node_name = 'node-a' |
43 | } | 51 | @@ -XXX,XX +XXX,XX @@ class TestAliasTransformMigration(TestDirtyBitmapMigration): |
44 | 52 | bitmaps = self.vm_b.query_bitmaps() | |
45 | BLKDBG_EVENT(s->bs->file, BLKDBG_COW_WRITE); | 53 | |
46 | - ret = bdrv_pwritev(s->bs->file, offset, &qiov); | 54 | for node in bitmaps: |
47 | + ret = bdrv_co_pwritev(s->bs->file, offset, qiov.size, &qiov, 0); | 55 | - bitmaps[node] = sorted(((bmap['name'], bmap['persistent']) for bmap in bitmaps[node])) |
48 | if (ret < 0) { | 56 | + bitmaps[node] = sorted(((bmap['name'], bmap['persistent']) |
49 | goto out; | 57 | + for bmap in bitmaps[node])) |
50 | } | 58 | |
51 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_aio_write_main(QEDAIOCB *acb) | 59 | self.assertEqual(bitmaps, |
52 | trace_qed_aio_write_main(s, acb, 0, offset, acb->cur_qiov.size); | 60 | {'node-a': [('bmap-a', True), ('bmap-b', False)], |
53 | |||
54 | BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO); | ||
55 | - ret = bdrv_pwritev(s->bs->file, offset, &acb->cur_qiov); | ||
56 | + ret = bdrv_co_pwritev(s->bs->file, offset, acb->cur_qiov.size, | ||
57 | + &acb->cur_qiov, 0); | ||
58 | if (ret < 0) { | ||
59 | return ret; | ||
60 | } | ||
61 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_aio_write_main(QEDAIOCB *acb) | ||
62 | * region. The solution is to flush after writing a new data | ||
63 | * cluster and before updating the L2 table. | ||
64 | */ | ||
65 | - ret = bdrv_flush(s->bs->file->bs); | ||
66 | + ret = bdrv_co_flush(s->bs->file->bs); | ||
67 | if (ret < 0) { | ||
68 | return ret; | ||
69 | } | ||
70 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_aio_read_data(void *opaque, int ret, | ||
71 | } | ||
72 | |||
73 | BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); | ||
74 | - ret = bdrv_preadv(bs->file, offset, &acb->cur_qiov); | ||
75 | + ret = bdrv_co_preadv(bs->file, offset, acb->cur_qiov.size, | ||
76 | + &acb->cur_qiov, 0); | ||
77 | if (ret < 0) { | ||
78 | return ret; | ||
79 | } | ||
80 | -- | 61 | -- |
81 | 1.8.3.1 | 62 | 2.29.2 |
82 | 63 | ||
83 | 64 | diff view generated by jsdifflib |
1 | From: "sochin.jiang" <sochin.jiang@huawei.com> | 1 | From: Stefano Garzarella <sgarzare@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | img_commit could fall into an infinite loop calling run_block_job() if | 3 | When a block job fails, we report strerror(-job->job.ret) error |
4 | its blockjob fails on any I/O error, fix this already known problem. | 4 | message, also if the job set an error object. |
5 | Let's report a better error message using error_get_pretty(job->job.err). | ||
5 | 6 | ||
6 | Signed-off-by: sochin.jiang <sochin.jiang@huawei.com> | 7 | If an error object was not set, strerror(-job->ret) is used as fallback, |
7 | Message-id: 1497509253-28941-1-git-send-email-sochin.jiang@huawei.com | 8 | as explained in include/qemu/job.h: |
8 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 9 | |
10 | typedef struct Job { | ||
11 | ... | ||
12 | /** | ||
13 | * Error object for a failed job. | ||
14 | * If job->ret is nonzero and an error object was not set, it will be set | ||
15 | * to strerror(-job->ret) during job_completed. | ||
16 | */ | ||
17 | Error *err; | ||
18 | } | ||
19 | |||
20 | In block_job_query() there can be a transient where 'job.err' is not set | ||
21 | by a scheduled bottom half. In that case we use strerror(-job->ret) as it | ||
22 | was before. | ||
23 | |||
24 | Suggested-by: Kevin Wolf <kwolf@redhat.com> | ||
25 | Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> | ||
26 | Message-Id: <20210225103633.76746-1-sgarzare@redhat.com> | ||
27 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
9 | --- | 28 | --- |
10 | blockjob.c | 4 ++-- | 29 | blockjob.c | 10 +++++++--- |
11 | include/block/blockjob.h | 18 ++++++++++++++++++ | 30 | 1 file changed, 7 insertions(+), 3 deletions(-) |
12 | qemu-img.c | 20 +++++++++++++------- | ||
13 | 3 files changed, 33 insertions(+), 9 deletions(-) | ||
14 | 31 | ||
15 | diff --git a/blockjob.c b/blockjob.c | 32 | diff --git a/blockjob.c b/blockjob.c |
16 | index XXXXXXX..XXXXXXX 100644 | 33 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/blockjob.c | 34 | --- a/blockjob.c |
18 | +++ b/blockjob.c | 35 | +++ b/blockjob.c |
19 | @@ -XXX,XX +XXX,XX @@ static void block_job_resume(BlockJob *job) | 36 | @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp) |
20 | block_job_enter(job); | 37 | info->status = job->job.status; |
38 | info->auto_finalize = job->job.auto_finalize; | ||
39 | info->auto_dismiss = job->job.auto_dismiss; | ||
40 | - info->has_error = job->job.ret != 0; | ||
41 | - info->error = job->job.ret ? g_strdup(strerror(-job->job.ret)) : NULL; | ||
42 | + if (job->job.ret) { | ||
43 | + info->has_error = true; | ||
44 | + info->error = job->job.err ? | ||
45 | + g_strdup(error_get_pretty(job->job.err)) : | ||
46 | + g_strdup(strerror(-job->job.ret)); | ||
47 | + } | ||
48 | return info; | ||
21 | } | 49 | } |
22 | 50 | ||
23 | -static void block_job_ref(BlockJob *job) | 51 | @@ -XXX,XX +XXX,XX @@ static void block_job_event_completed(Notifier *n, void *opaque) |
24 | +void block_job_ref(BlockJob *job) | 52 | } |
25 | { | 53 | |
26 | ++job->refcnt; | 54 | if (job->job.ret < 0) { |
27 | } | 55 | - msg = strerror(-job->job.ret); |
28 | @@ -XXX,XX +XXX,XX @@ static void block_job_attached_aio_context(AioContext *new_context, | 56 | + msg = error_get_pretty(job->job.err); |
29 | void *opaque); | 57 | } |
30 | static void block_job_detach_aio_context(void *opaque); | 58 | |
31 | 59 | qapi_event_send_block_job_completed(job_type(&job->job), | |
32 | -static void block_job_unref(BlockJob *job) | ||
33 | +void block_job_unref(BlockJob *job) | ||
34 | { | ||
35 | if (--job->refcnt == 0) { | ||
36 | BlockDriverState *bs = blk_bs(job->blk); | ||
37 | diff --git a/include/block/blockjob.h b/include/block/blockjob.h | ||
38 | index XXXXXXX..XXXXXXX 100644 | ||
39 | --- a/include/block/blockjob.h | ||
40 | +++ b/include/block/blockjob.h | ||
41 | @@ -XXX,XX +XXX,XX @@ void block_job_iostatus_reset(BlockJob *job); | ||
42 | BlockJobTxn *block_job_txn_new(void); | ||
43 | |||
44 | /** | ||
45 | + * block_job_ref: | ||
46 | + * | ||
47 | + * Add a reference to BlockJob refcnt, it will be decreased with | ||
48 | + * block_job_unref, and then be freed if it comes to be the last | ||
49 | + * reference. | ||
50 | + */ | ||
51 | +void block_job_ref(BlockJob *job); | ||
52 | + | ||
53 | +/** | ||
54 | + * block_job_unref: | ||
55 | + * | ||
56 | + * Release a reference that was previously acquired with block_job_ref | ||
57 | + * or block_job_create. If it's the last reference to the object, it will be | ||
58 | + * freed. | ||
59 | + */ | ||
60 | +void block_job_unref(BlockJob *job); | ||
61 | + | ||
62 | +/** | ||
63 | * block_job_txn_unref: | ||
64 | * | ||
65 | * Release a reference that was previously acquired with block_job_txn_add_job | ||
66 | diff --git a/qemu-img.c b/qemu-img.c | ||
67 | index XXXXXXX..XXXXXXX 100644 | ||
68 | --- a/qemu-img.c | ||
69 | +++ b/qemu-img.c | ||
70 | @@ -XXX,XX +XXX,XX @@ static void common_block_job_cb(void *opaque, int ret) | ||
71 | static void run_block_job(BlockJob *job, Error **errp) | ||
72 | { | ||
73 | AioContext *aio_context = blk_get_aio_context(job->blk); | ||
74 | + int ret = 0; | ||
75 | |||
76 | - /* FIXME In error cases, the job simply goes away and we access a dangling | ||
77 | - * pointer below. */ | ||
78 | aio_context_acquire(aio_context); | ||
79 | + block_job_ref(job); | ||
80 | do { | ||
81 | aio_poll(aio_context, true); | ||
82 | qemu_progress_print(job->len ? | ||
83 | ((float)job->offset / job->len * 100.f) : 0.0f, 0); | ||
84 | - } while (!job->ready); | ||
85 | + } while (!job->ready && !job->completed); | ||
86 | |||
87 | - block_job_complete_sync(job, errp); | ||
88 | + if (!job->completed) { | ||
89 | + ret = block_job_complete_sync(job, errp); | ||
90 | + } else { | ||
91 | + ret = job->ret; | ||
92 | + } | ||
93 | + block_job_unref(job); | ||
94 | aio_context_release(aio_context); | ||
95 | |||
96 | - /* A block job may finish instantaneously without publishing any progress, | ||
97 | - * so just signal completion here */ | ||
98 | - qemu_progress_print(100.f, 0); | ||
99 | + /* publish completion progress only when success */ | ||
100 | + if (!ret) { | ||
101 | + qemu_progress_print(100.f, 0); | ||
102 | + } | ||
103 | } | ||
104 | |||
105 | static int img_commit(int argc, char **argv) | ||
106 | -- | 60 | -- |
107 | 1.8.3.1 | 61 | 2.29.2 |
108 | 62 | ||
109 | 63 | diff view generated by jsdifflib |
1 | Now that we process a request in the same coroutine from beginning to | 1 | From: Paolo Bonzini <pbonzini@redhat.com> |
---|---|---|---|
2 | end and don't drop out of it any more, we can look like a proper | ||
3 | coroutine-based driver and simply call qed_aio_next_io() and get a | ||
4 | return value from it instead of spawning an additional coroutine that | ||
5 | reenters the parent when it's done. | ||
6 | 2 | ||
3 | If the first character of optstring is '-', then each nonoption argv | ||
4 | element is handled as if it were the argument of an option with character | ||
5 | code 1. This removes the reordering of the argv array, and enables usage | ||
6 | of loc_set_cmdline to provide better error messages. | ||
7 | |||
8 | Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> | ||
9 | Message-Id: <20210301152844.291799-2-pbonzini@redhat.com> | ||
10 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
7 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 11 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
8 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
9 | --- | 12 | --- |
10 | block/qed.c | 101 +++++++++++++----------------------------------------------- | 13 | storage-daemon/qemu-storage-daemon.c | 9 ++++----- |
11 | block/qed.h | 3 +- | 14 | 1 file changed, 4 insertions(+), 5 deletions(-) |
12 | 2 files changed, 22 insertions(+), 82 deletions(-) | ||
13 | 15 | ||
14 | diff --git a/block/qed.c b/block/qed.c | 16 | diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c |
15 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/block/qed.c | 18 | --- a/storage-daemon/qemu-storage-daemon.c |
17 | +++ b/block/qed.c | 19 | +++ b/storage-daemon/qemu-storage-daemon.c |
18 | @@ -XXX,XX +XXX,XX @@ | 20 | @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) |
19 | #include "qapi/qmp/qerror.h" | 21 | * they are given on the command lines. This means that things must be |
20 | #include "sysemu/block-backend.h" | 22 | * defined first before they can be referenced in another option. |
21 | 23 | */ | |
22 | -static const AIOCBInfo qed_aiocb_info = { | 24 | - while ((c = getopt_long(argc, argv, "hT:V", long_options, NULL)) != -1) { |
23 | - .aiocb_size = sizeof(QEDAIOCB), | 25 | + while ((c = getopt_long(argc, argv, "-hT:V", long_options, NULL)) != -1) { |
24 | -}; | 26 | switch (c) { |
25 | - | 27 | case '?': |
26 | static int bdrv_qed_probe(const uint8_t *buf, int buf_size, | 28 | exit(EXIT_FAILURE); |
27 | const char *filename) | 29 | @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) |
28 | { | 30 | qobject_unref(args); |
29 | @@ -XXX,XX +XXX,XX @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s) | 31 | break; |
30 | return l2_table; | ||
31 | } | ||
32 | |||
33 | -static void qed_aio_next_io(QEDAIOCB *acb); | ||
34 | - | ||
35 | -static void qed_aio_start_io(QEDAIOCB *acb) | ||
36 | -{ | ||
37 | - qed_aio_next_io(acb); | ||
38 | -} | ||
39 | - | ||
40 | static void qed_plug_allocating_write_reqs(BDRVQEDState *s) | ||
41 | { | ||
42 | assert(!s->allocating_write_reqs_plugged); | ||
43 | @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs, | ||
44 | |||
45 | static BDRVQEDState *acb_to_s(QEDAIOCB *acb) | ||
46 | { | ||
47 | - return acb->common.bs->opaque; | ||
48 | + return acb->bs->opaque; | ||
49 | } | ||
50 | |||
51 | /** | ||
52 | @@ -XXX,XX +XXX,XX @@ static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index, | ||
53 | } | ||
54 | } | ||
55 | |||
56 | -static void qed_aio_complete_bh(void *opaque) | ||
57 | -{ | ||
58 | - QEDAIOCB *acb = opaque; | ||
59 | - BDRVQEDState *s = acb_to_s(acb); | ||
60 | - BlockCompletionFunc *cb = acb->common.cb; | ||
61 | - void *user_opaque = acb->common.opaque; | ||
62 | - int ret = acb->bh_ret; | ||
63 | - | ||
64 | - qemu_aio_unref(acb); | ||
65 | - | ||
66 | - /* Invoke callback */ | ||
67 | - qed_acquire(s); | ||
68 | - cb(user_opaque, ret); | ||
69 | - qed_release(s); | ||
70 | -} | ||
71 | - | ||
72 | -static void qed_aio_complete(QEDAIOCB *acb, int ret) | ||
73 | +static void qed_aio_complete(QEDAIOCB *acb) | ||
74 | { | ||
75 | BDRVQEDState *s = acb_to_s(acb); | ||
76 | |||
77 | - trace_qed_aio_complete(s, acb, ret); | ||
78 | - | ||
79 | /* Free resources */ | ||
80 | qemu_iovec_destroy(&acb->cur_qiov); | ||
81 | qed_unref_l2_cache_entry(acb->request.l2_table); | ||
82 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete(QEDAIOCB *acb, int ret) | ||
83 | acb->qiov->iov[0].iov_base = NULL; | ||
84 | } | ||
85 | |||
86 | - /* Arrange for a bh to invoke the completion function */ | ||
87 | - acb->bh_ret = ret; | ||
88 | - aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs), | ||
89 | - qed_aio_complete_bh, acb); | ||
90 | - | ||
91 | /* Start next allocating write request waiting behind this one. Note that | ||
92 | * requests enqueue themselves when they first hit an unallocated cluster | ||
93 | * but they wait until the entire request is finished before waking up the | ||
94 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | ||
95 | struct iovec *iov = acb->qiov->iov; | ||
96 | |||
97 | if (!iov->iov_base) { | ||
98 | - iov->iov_base = qemu_try_blockalign(acb->common.bs, iov->iov_len); | ||
99 | + iov->iov_base = qemu_try_blockalign(acb->bs, iov->iov_len); | ||
100 | if (iov->iov_base == NULL) { | ||
101 | return -ENOMEM; | ||
102 | } | 32 | } |
103 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_read_data(void *opaque, int ret, uint64_t offset, size_t len) | 33 | + case 1: |
104 | { | 34 | + error_report("Unexpected argument: %s", optarg); |
105 | QEDAIOCB *acb = opaque; | 35 | + exit(EXIT_FAILURE); |
106 | BDRVQEDState *s = acb_to_s(acb); | 36 | default: |
107 | - BlockDriverState *bs = acb->common.bs; | 37 | g_assert_not_reached(); |
108 | + BlockDriverState *bs = acb->bs; | ||
109 | |||
110 | /* Adjust offset into cluster */ | ||
111 | offset += qed_offset_into_cluster(s, acb->cur_pos); | ||
112 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_read_data(void *opaque, int ret, uint64_t offset, size_t len) | ||
113 | /** | ||
114 | * Begin next I/O or complete the request | ||
115 | */ | ||
116 | -static void qed_aio_next_io(QEDAIOCB *acb) | ||
117 | +static int qed_aio_next_io(QEDAIOCB *acb) | ||
118 | { | ||
119 | BDRVQEDState *s = acb_to_s(acb); | ||
120 | uint64_t offset; | ||
121 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb) | ||
122 | |||
123 | /* Complete request */ | ||
124 | if (acb->cur_pos >= acb->end_pos) { | ||
125 | - qed_aio_complete(acb, 0); | ||
126 | - return; | ||
127 | + ret = 0; | ||
128 | + break; | ||
129 | } | ||
130 | |||
131 | /* Find next cluster and start I/O */ | ||
132 | len = acb->end_pos - acb->cur_pos; | ||
133 | ret = qed_find_cluster(s, &acb->request, acb->cur_pos, &len, &offset); | ||
134 | if (ret < 0) { | ||
135 | - qed_aio_complete(acb, ret); | ||
136 | - return; | ||
137 | + break; | ||
138 | } | ||
139 | |||
140 | if (acb->flags & QED_AIOCB_WRITE) { | ||
141 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb) | ||
142 | } | ||
143 | |||
144 | if (ret < 0 && ret != -EAGAIN) { | ||
145 | - qed_aio_complete(acb, ret); | ||
146 | - return; | ||
147 | + break; | ||
148 | } | 38 | } |
149 | } | 39 | } |
150 | -} | 40 | - if (optind != argc) { |
151 | 41 | - error_report("Unexpected argument: %s", argv[optind]); | |
152 | -typedef struct QEDRequestCo { | 42 | - exit(EXIT_FAILURE); |
153 | - Coroutine *co; | 43 | - } |
154 | - bool done; | ||
155 | - int ret; | ||
156 | -} QEDRequestCo; | ||
157 | - | ||
158 | -static void qed_co_request_cb(void *opaque, int ret) | ||
159 | -{ | ||
160 | - QEDRequestCo *co = opaque; | ||
161 | - | ||
162 | - co->done = true; | ||
163 | - co->ret = ret; | ||
164 | - qemu_coroutine_enter_if_inactive(co->co); | ||
165 | + trace_qed_aio_complete(s, acb, ret); | ||
166 | + qed_aio_complete(acb); | ||
167 | + return ret; | ||
168 | } | 44 | } |
169 | 45 | ||
170 | static int coroutine_fn qed_co_request(BlockDriverState *bs, int64_t sector_num, | 46 | int main(int argc, char *argv[]) |
171 | QEMUIOVector *qiov, int nb_sectors, | ||
172 | int flags) | ||
173 | { | ||
174 | - QEDRequestCo co = { | ||
175 | - .co = qemu_coroutine_self(), | ||
176 | - .done = false, | ||
177 | + QEDAIOCB acb = { | ||
178 | + .bs = bs, | ||
179 | + .cur_pos = (uint64_t) sector_num * BDRV_SECTOR_SIZE, | ||
180 | + .end_pos = (sector_num + nb_sectors) * BDRV_SECTOR_SIZE, | ||
181 | + .qiov = qiov, | ||
182 | + .flags = flags, | ||
183 | }; | ||
184 | - QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, qed_co_request_cb, &co); | ||
185 | - | ||
186 | - trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors, &co, flags); | ||
187 | + qemu_iovec_init(&acb.cur_qiov, qiov->niov); | ||
188 | |||
189 | - acb->flags = flags; | ||
190 | - acb->qiov = qiov; | ||
191 | - acb->qiov_offset = 0; | ||
192 | - acb->cur_pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE; | ||
193 | - acb->end_pos = acb->cur_pos + nb_sectors * BDRV_SECTOR_SIZE; | ||
194 | - acb->backing_qiov = NULL; | ||
195 | - acb->request.l2_table = NULL; | ||
196 | - qemu_iovec_init(&acb->cur_qiov, qiov->niov); | ||
197 | + trace_qed_aio_setup(bs->opaque, &acb, sector_num, nb_sectors, NULL, flags); | ||
198 | |||
199 | /* Start request */ | ||
200 | - qed_aio_start_io(acb); | ||
201 | - | ||
202 | - if (!co.done) { | ||
203 | - qemu_coroutine_yield(); | ||
204 | - } | ||
205 | - | ||
206 | - return co.ret; | ||
207 | + return qed_aio_next_io(&acb); | ||
208 | } | ||
209 | |||
210 | static int coroutine_fn bdrv_qed_co_readv(BlockDriverState *bs, | ||
211 | diff --git a/block/qed.h b/block/qed.h | ||
212 | index XXXXXXX..XXXXXXX 100644 | ||
213 | --- a/block/qed.h | ||
214 | +++ b/block/qed.h | ||
215 | @@ -XXX,XX +XXX,XX @@ enum { | ||
216 | }; | ||
217 | |||
218 | typedef struct QEDAIOCB { | ||
219 | - BlockAIOCB common; | ||
220 | - int bh_ret; /* final return status for completion bh */ | ||
221 | + BlockDriverState *bs; | ||
222 | QSIMPLEQ_ENTRY(QEDAIOCB) next; /* next request */ | ||
223 | int flags; /* QED_AIOCB_* bits ORed together */ | ||
224 | uint64_t end_pos; /* request end on block device, in bytes */ | ||
225 | -- | 47 | -- |
226 | 1.8.3.1 | 48 | 2.29.2 |
227 | 49 | ||
228 | 50 | diff view generated by jsdifflib |
1 | From: Stephen Bates <sbates@raithlin.com> | 1 | From: Paolo Bonzini <pbonzini@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Add the ability for the NVMe model to support both the RDS and WDS | 3 | Use the location management facilities that the emulator uses, so that |
4 | modes in the Controller Memory Buffer. | 4 | the current command line option appears in the error message. |
5 | 5 | ||
6 | Although not currently supported in the upstreamed Linux kernel a fork | 6 | Before: |
7 | with support exists [1] and user-space test programs that build on | ||
8 | this also exist [2]. | ||
9 | 7 | ||
10 | Useful for testing CMB functionality in preperation for real CMB | 8 | $ storage-daemon/qemu-storage-daemon --nbd key..= |
11 | enabled NVMe devices (coming soon). | 9 | qemu-storage-daemon: Invalid parameter 'key..' |
12 | 10 | ||
13 | [1] https://github.com/sbates130272/linux-p2pmem | 11 | After: |
14 | [2] https://github.com/sbates130272/p2pmem-test | ||
15 | 12 | ||
16 | Signed-off-by: Stephen Bates <sbates@raithlin.com> | 13 | $ storage-daemon/qemu-storage-daemon --nbd key..= |
17 | Reviewed-by: Logan Gunthorpe <logang@deltatee.com> | 14 | qemu-storage-daemon: --nbd key..=: Invalid parameter 'key..' |
18 | Reviewed-by: Keith Busch <keith.busch@intel.com> | 15 | |
16 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
17 | Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> | ||
18 | Message-Id: <20210301152844.291799-3-pbonzini@redhat.com> | ||
19 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 19 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
20 | --- | 20 | --- |
21 | hw/block/nvme.c | 83 +++++++++++++++++++++++++++++++++++++++------------------ | 21 | storage-daemon/qemu-storage-daemon.c | 19 +++++++++++++++++-- |
22 | hw/block/nvme.h | 1 + | 22 | 1 file changed, 17 insertions(+), 2 deletions(-) |
23 | 2 files changed, 58 insertions(+), 26 deletions(-) | ||
24 | 23 | ||
25 | diff --git a/hw/block/nvme.c b/hw/block/nvme.c | 24 | diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c |
26 | index XXXXXXX..XXXXXXX 100644 | 25 | index XXXXXXX..XXXXXXX 100644 |
27 | --- a/hw/block/nvme.c | 26 | --- a/storage-daemon/qemu-storage-daemon.c |
28 | +++ b/hw/block/nvme.c | 27 | +++ b/storage-daemon/qemu-storage-daemon.c |
29 | @@ -XXX,XX +XXX,XX @@ | 28 | @@ -XXX,XX +XXX,XX @@ static void init_qmp_commands(void) |
30 | * cmb_size_mb=<cmb_size_mb[optional]> | 29 | qmp_marshal_qmp_capabilities, QCO_ALLOW_PRECONFIG); |
31 | * | ||
32 | * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at | ||
33 | - * offset 0 in BAR2 and supports SQS only for now. | ||
34 | + * offset 0 in BAR2 and supports only WDS, RDS and SQS for now. | ||
35 | */ | ||
36 | |||
37 | #include "qemu/osdep.h" | ||
38 | @@ -XXX,XX +XXX,XX @@ static void nvme_isr_notify(NvmeCtrl *n, NvmeCQueue *cq) | ||
39 | } | ||
40 | } | 30 | } |
41 | 31 | ||
42 | -static uint16_t nvme_map_prp(QEMUSGList *qsg, uint64_t prp1, uint64_t prp2, | 32 | +static int getopt_set_loc(int argc, char **argv, const char *optstring, |
43 | - uint32_t len, NvmeCtrl *n) | 33 | + const struct option *longopts) |
44 | +static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, | 34 | +{ |
45 | + uint64_t prp2, uint32_t len, NvmeCtrl *n) | 35 | + int c, save_index; |
36 | + | ||
37 | + optarg = NULL; | ||
38 | + save_index = optind; | ||
39 | + c = getopt_long(argc, argv, optstring, longopts, NULL); | ||
40 | + if (optarg) { | ||
41 | + loc_set_cmdline(argv, save_index, MAX(1, optind - save_index)); | ||
42 | + } | ||
43 | + return c; | ||
44 | +} | ||
45 | + | ||
46 | static void process_options(int argc, char *argv[]) | ||
46 | { | 47 | { |
47 | hwaddr trans_len = n->page_size - (prp1 % n->page_size); | 48 | int c; |
48 | trans_len = MIN(len, trans_len); | 49 | @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) |
49 | @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, uint64_t prp1, uint64_t prp2, | 50 | * they are given on the command lines. This means that things must be |
50 | 51 | * defined first before they can be referenced in another option. | |
51 | if (!prp1) { | 52 | */ |
52 | return NVME_INVALID_FIELD | NVME_DNR; | 53 | - while ((c = getopt_long(argc, argv, "-hT:V", long_options, NULL)) != -1) { |
53 | + } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr && | 54 | + while ((c = getopt_set_loc(argc, argv, "-hT:V", long_options)) != -1) { |
54 | + prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) { | 55 | switch (c) { |
55 | + qsg->nsg = 0; | 56 | case '?': |
56 | + qemu_iovec_init(iov, num_prps); | 57 | exit(EXIT_FAILURE); |
57 | + qemu_iovec_add(iov, (void *)&n->cmbuf[prp1 - n->ctrl_mem.addr], trans_len); | 58 | @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) |
58 | + } else { | 59 | break; |
59 | + pci_dma_sglist_init(qsg, &n->parent_obj, num_prps); | ||
60 | + qemu_sglist_add(qsg, prp1, trans_len); | ||
61 | } | ||
62 | - | ||
63 | - pci_dma_sglist_init(qsg, &n->parent_obj, num_prps); | ||
64 | - qemu_sglist_add(qsg, prp1, trans_len); | ||
65 | len -= trans_len; | ||
66 | if (len) { | ||
67 | if (!prp2) { | ||
68 | @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, uint64_t prp1, uint64_t prp2, | ||
69 | |||
70 | nents = (len + n->page_size - 1) >> n->page_bits; | ||
71 | prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t); | ||
72 | - pci_dma_read(&n->parent_obj, prp2, (void *)prp_list, prp_trans); | ||
73 | + nvme_addr_read(n, prp2, (void *)prp_list, prp_trans); | ||
74 | while (len != 0) { | ||
75 | uint64_t prp_ent = le64_to_cpu(prp_list[i]); | ||
76 | |||
77 | @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, uint64_t prp1, uint64_t prp2, | ||
78 | i = 0; | ||
79 | nents = (len + n->page_size - 1) >> n->page_bits; | ||
80 | prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t); | ||
81 | - pci_dma_read(&n->parent_obj, prp_ent, (void *)prp_list, | ||
82 | + nvme_addr_read(n, prp_ent, (void *)prp_list, | ||
83 | prp_trans); | ||
84 | prp_ent = le64_to_cpu(prp_list[i]); | ||
85 | } | ||
86 | @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, uint64_t prp1, uint64_t prp2, | ||
87 | } | ||
88 | |||
89 | trans_len = MIN(len, n->page_size); | ||
90 | - qemu_sglist_add(qsg, prp_ent, trans_len); | ||
91 | + if (qsg->nsg){ | ||
92 | + qemu_sglist_add(qsg, prp_ent, trans_len); | ||
93 | + } else { | ||
94 | + qemu_iovec_add(iov, (void *)&n->cmbuf[prp_ent - n->ctrl_mem.addr], trans_len); | ||
95 | + } | ||
96 | len -= trans_len; | ||
97 | i++; | ||
98 | } | 60 | } |
99 | @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, uint64_t prp1, uint64_t prp2, | 61 | case 1: |
100 | if (prp2 & (n->page_size - 1)) { | 62 | - error_report("Unexpected argument: %s", optarg); |
101 | goto unmap; | 63 | + error_report("Unexpected argument"); |
102 | } | 64 | exit(EXIT_FAILURE); |
103 | - qemu_sglist_add(qsg, prp2, len); | 65 | default: |
104 | + if (qsg->nsg) { | 66 | g_assert_not_reached(); |
105 | + qemu_sglist_add(qsg, prp2, len); | ||
106 | + } else { | ||
107 | + qemu_iovec_add(iov, (void *)&n->cmbuf[prp2 - n->ctrl_mem.addr], trans_len); | ||
108 | + } | ||
109 | } | 67 | } |
110 | } | 68 | } |
111 | return NVME_SUCCESS; | 69 | + loc_set_none(); |
112 | @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, | ||
113 | uint64_t prp1, uint64_t prp2) | ||
114 | { | ||
115 | QEMUSGList qsg; | ||
116 | + QEMUIOVector iov; | ||
117 | + uint16_t status = NVME_SUCCESS; | ||
118 | |||
119 | - if (nvme_map_prp(&qsg, prp1, prp2, len, n)) { | ||
120 | + if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) { | ||
121 | return NVME_INVALID_FIELD | NVME_DNR; | ||
122 | } | ||
123 | - if (dma_buf_read(ptr, len, &qsg)) { | ||
124 | + if (qsg.nsg > 0) { | ||
125 | + if (dma_buf_read(ptr, len, &qsg)) { | ||
126 | + status = NVME_INVALID_FIELD | NVME_DNR; | ||
127 | + } | ||
128 | qemu_sglist_destroy(&qsg); | ||
129 | - return NVME_INVALID_FIELD | NVME_DNR; | ||
130 | + } else { | ||
131 | + if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) { | ||
132 | + status = NVME_INVALID_FIELD | NVME_DNR; | ||
133 | + } | ||
134 | + qemu_iovec_destroy(&iov); | ||
135 | } | ||
136 | - qemu_sglist_destroy(&qsg); | ||
137 | - return NVME_SUCCESS; | ||
138 | + return status; | ||
139 | } | 70 | } |
140 | 71 | ||
141 | static void nvme_post_cqes(void *opaque) | 72 | int main(int argc, char *argv[]) |
142 | @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, | ||
143 | return NVME_LBA_RANGE | NVME_DNR; | ||
144 | } | ||
145 | |||
146 | - if (nvme_map_prp(&req->qsg, prp1, prp2, data_size, n)) { | ||
147 | + if (nvme_map_prp(&req->qsg, &req->iov, prp1, prp2, data_size, n)) { | ||
148 | block_acct_invalid(blk_get_stats(n->conf.blk), acct); | ||
149 | return NVME_INVALID_FIELD | NVME_DNR; | ||
150 | } | ||
151 | |||
152 | - assert((nlb << data_shift) == req->qsg.size); | ||
153 | - | ||
154 | - req->has_sg = true; | ||
155 | dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct); | ||
156 | - req->aiocb = is_write ? | ||
157 | - dma_blk_write(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE, | ||
158 | - nvme_rw_cb, req) : | ||
159 | - dma_blk_read(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE, | ||
160 | - nvme_rw_cb, req); | ||
161 | + if (req->qsg.nsg > 0) { | ||
162 | + req->has_sg = true; | ||
163 | + req->aiocb = is_write ? | ||
164 | + dma_blk_write(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE, | ||
165 | + nvme_rw_cb, req) : | ||
166 | + dma_blk_read(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE, | ||
167 | + nvme_rw_cb, req); | ||
168 | + } else { | ||
169 | + req->has_sg = false; | ||
170 | + req->aiocb = is_write ? | ||
171 | + blk_aio_pwritev(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb, | ||
172 | + req) : | ||
173 | + blk_aio_preadv(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb, | ||
174 | + req); | ||
175 | + } | ||
176 | |||
177 | return NVME_NO_COMPLETE; | ||
178 | } | ||
179 | @@ -XXX,XX +XXX,XX @@ static int nvme_init(PCIDevice *pci_dev) | ||
180 | NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1); | ||
181 | NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0); | ||
182 | NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0); | ||
183 | - NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 0); | ||
184 | - NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 0); | ||
185 | + NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1); | ||
186 | + NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1); | ||
187 | NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */ | ||
188 | NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->cmb_size_mb); | ||
189 | |||
190 | + n->cmbloc = n->bar.cmbloc; | ||
191 | + n->cmbsz = n->bar.cmbsz; | ||
192 | + | ||
193 | n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz)); | ||
194 | memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n, | ||
195 | "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz)); | ||
196 | diff --git a/hw/block/nvme.h b/hw/block/nvme.h | ||
197 | index XXXXXXX..XXXXXXX 100644 | ||
198 | --- a/hw/block/nvme.h | ||
199 | +++ b/hw/block/nvme.h | ||
200 | @@ -XXX,XX +XXX,XX @@ typedef struct NvmeRequest { | ||
201 | NvmeCqe cqe; | ||
202 | BlockAcctCookie acct; | ||
203 | QEMUSGList qsg; | ||
204 | + QEMUIOVector iov; | ||
205 | QTAILQ_ENTRY(NvmeRequest)entry; | ||
206 | } NvmeRequest; | ||
207 | |||
208 | -- | 73 | -- |
209 | 1.8.3.1 | 74 | 2.29.2 |
210 | 75 | ||
211 | 76 | diff view generated by jsdifflib |
1 | Don't recurse into qed_aio_next_io() and qed_aio_complete() here, but | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | just return an error code and let the caller handle it. | ||
3 | 2 | ||
4 | While refactoring qed_aio_write_alloc() to accomodate the change, | 3 | Daemons often have a --pidfile option where the pid is written to a file |
5 | qed_aio_write_zero_cluster() ended up with a single line, so I chose to | 4 | so that scripts can stop the daemon by sending a signal. |
6 | inline that line and remove the function completely. | ||
7 | 5 | ||
6 | The pid file also acts as a lock to prevent multiple instances of the | ||
7 | daemon from launching for a given pid file. | ||
8 | |||
9 | QEMU, qemu-nbd, qemu-ga, virtiofsd, and qemu-pr-helper all support the | ||
10 | --pidfile option. Add it to qemu-storage-daemon too. | ||
11 | |||
12 | Reported-by: Richard W.M. Jones <rjones@redhat.com> | ||
13 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
14 | Message-Id: <20210302142746.170535-1-stefanha@redhat.com> | ||
15 | Reviewed-by: Richard W.M. Jones <rjones@redhat.com> | ||
8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 16 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
9 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | --- | 17 | --- |
11 | block/qed.c | 58 +++++++++++++++++++++------------------------------------- | 18 | docs/tools/qemu-storage-daemon.rst | 14 +++++++++++ |
12 | 1 file changed, 21 insertions(+), 37 deletions(-) | 19 | storage-daemon/qemu-storage-daemon.c | 36 ++++++++++++++++++++++++++++ |
20 | 2 files changed, 50 insertions(+) | ||
13 | 21 | ||
14 | diff --git a/block/qed.c b/block/qed.c | 22 | diff --git a/docs/tools/qemu-storage-daemon.rst b/docs/tools/qemu-storage-daemon.rst |
15 | index XXXXXXX..XXXXXXX 100644 | 23 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/block/qed.c | 24 | --- a/docs/tools/qemu-storage-daemon.rst |
17 | +++ b/block/qed.c | 25 | +++ b/docs/tools/qemu-storage-daemon.rst |
18 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_main(QEDAIOCB *acb) | 26 | @@ -XXX,XX +XXX,XX @@ Standard options: |
19 | /** | 27 | List object properties with ``<type>,help``. See the :manpage:`qemu(1)` |
20 | * Populate untouched regions of new data cluster | 28 | manual page for a description of the object properties. |
21 | */ | 29 | |
22 | -static void qed_aio_write_cow(void *opaque, int ret) | 30 | +.. option:: --pidfile PATH |
23 | +static int qed_aio_write_cow(QEDAIOCB *acb) | ||
24 | { | ||
25 | - QEDAIOCB *acb = opaque; | ||
26 | BDRVQEDState *s = acb_to_s(acb); | ||
27 | uint64_t start, len, offset; | ||
28 | + int ret; | ||
29 | |||
30 | /* Populate front untouched region of new data cluster */ | ||
31 | start = qed_start_of_cluster(s, acb->cur_pos); | ||
32 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_cow(void *opaque, int ret) | ||
33 | |||
34 | trace_qed_aio_write_prefill(s, acb, start, len, acb->cur_cluster); | ||
35 | ret = qed_copy_from_backing_file(s, start, len, acb->cur_cluster); | ||
36 | - if (ret) { | ||
37 | - qed_aio_complete(acb, ret); | ||
38 | - return; | ||
39 | + if (ret < 0) { | ||
40 | + return ret; | ||
41 | } | ||
42 | |||
43 | /* Populate back untouched region of new data cluster */ | ||
44 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_cow(void *opaque, int ret) | ||
45 | |||
46 | trace_qed_aio_write_postfill(s, acb, start, len, offset); | ||
47 | ret = qed_copy_from_backing_file(s, start, len, offset); | ||
48 | - if (ret) { | ||
49 | - qed_aio_complete(acb, ret); | ||
50 | - return; | ||
51 | - } | ||
52 | - | ||
53 | - ret = qed_aio_write_main(acb); | ||
54 | if (ret < 0) { | ||
55 | - qed_aio_complete(acb, ret); | ||
56 | - return; | ||
57 | + return ret; | ||
58 | } | ||
59 | - qed_aio_next_io(acb, 0); | ||
60 | + | 31 | + |
61 | + return qed_aio_write_main(acb); | 32 | + is the path to a file where the daemon writes its pid. This allows scripts to |
33 | + stop the daemon by sending a signal:: | ||
34 | + | ||
35 | + $ kill -SIGTERM $(<path/to/qsd.pid) | ||
36 | + | ||
37 | + A file lock is applied to the file so only one instance of the daemon can run | ||
38 | + with a given pid file path. The daemon unlinks its pid file when terminating. | ||
39 | + | ||
40 | + The pid file is written after chardevs, exports, and NBD servers have been | ||
41 | + created but before accepting connections. The daemon has started successfully | ||
42 | + when the pid file is written and clients may begin connecting. | ||
43 | + | ||
44 | Examples | ||
45 | -------- | ||
46 | Launch the daemon with QMP monitor socket ``qmp.sock`` so clients can execute | ||
47 | diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c | ||
48 | index XXXXXXX..XXXXXXX 100644 | ||
49 | --- a/storage-daemon/qemu-storage-daemon.c | ||
50 | +++ b/storage-daemon/qemu-storage-daemon.c | ||
51 | @@ -XXX,XX +XXX,XX @@ | ||
52 | #include "sysemu/runstate.h" | ||
53 | #include "trace/control.h" | ||
54 | |||
55 | +static const char *pid_file; | ||
56 | static volatile bool exit_requested = false; | ||
57 | |||
58 | void qemu_system_killed(int signal, pid_t pid) | ||
59 | @@ -XXX,XX +XXX,XX @@ static void help(void) | ||
60 | " See the qemu(1) man page for documentation of the\n" | ||
61 | " objects that can be added.\n" | ||
62 | "\n" | ||
63 | +" --pidfile <path> write process ID to a file after startup\n" | ||
64 | +"\n" | ||
65 | QEMU_HELP_BOTTOM "\n", | ||
66 | error_get_progname()); | ||
62 | } | 67 | } |
63 | 68 | @@ -XXX,XX +XXX,XX @@ enum { | |
64 | /** | 69 | OPTION_MONITOR, |
65 | @@ -XXX,XX +XXX,XX @@ static bool qed_should_set_need_check(BDRVQEDState *s) | 70 | OPTION_NBD_SERVER, |
66 | return !(s->header.features & QED_F_NEED_CHECK); | 71 | OPTION_OBJECT, |
72 | + OPTION_PIDFILE, | ||
73 | }; | ||
74 | |||
75 | extern QemuOptsList qemu_chardev_opts; | ||
76 | @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) | ||
77 | {"monitor", required_argument, NULL, OPTION_MONITOR}, | ||
78 | {"nbd-server", required_argument, NULL, OPTION_NBD_SERVER}, | ||
79 | {"object", required_argument, NULL, OPTION_OBJECT}, | ||
80 | + {"pidfile", required_argument, NULL, OPTION_PIDFILE}, | ||
81 | {"trace", required_argument, NULL, 'T'}, | ||
82 | {"version", no_argument, NULL, 'V'}, | ||
83 | {0, 0, 0, 0} | ||
84 | @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) | ||
85 | qobject_unref(args); | ||
86 | break; | ||
87 | } | ||
88 | + case OPTION_PIDFILE: | ||
89 | + pid_file = optarg; | ||
90 | + break; | ||
91 | case 1: | ||
92 | error_report("Unexpected argument"); | ||
93 | exit(EXIT_FAILURE); | ||
94 | @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) | ||
95 | loc_set_none(); | ||
67 | } | 96 | } |
68 | 97 | ||
69 | -static void qed_aio_write_zero_cluster(void *opaque, int ret) | 98 | +static void pid_file_cleanup(void) |
70 | -{ | 99 | +{ |
71 | - QEDAIOCB *acb = opaque; | 100 | + unlink(pid_file); |
72 | - | 101 | +} |
73 | - if (ret) { | 102 | + |
74 | - qed_aio_complete(acb, ret); | 103 | +static void pid_file_init(void) |
75 | - return; | 104 | +{ |
76 | - } | 105 | + Error *err = NULL; |
77 | - | 106 | + |
78 | - ret = qed_aio_write_l2_update(acb, 1); | 107 | + if (!pid_file) { |
79 | - if (ret < 0) { | 108 | + return; |
80 | - qed_aio_complete(acb, ret); | ||
81 | - return; | ||
82 | - } | ||
83 | - qed_aio_next_io(acb, 0); | ||
84 | -} | ||
85 | - | ||
86 | /** | ||
87 | * Write new data cluster | ||
88 | * | ||
89 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_zero_cluster(void *opaque, int ret) | ||
90 | static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
91 | { | ||
92 | BDRVQEDState *s = acb_to_s(acb); | ||
93 | - BlockCompletionFunc *cb; | ||
94 | int ret; | ||
95 | |||
96 | /* Cancel timer when the first allocating request comes in */ | ||
97 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
98 | qed_aio_start_io(acb); | ||
99 | return; | ||
100 | } | ||
101 | - | ||
102 | - cb = qed_aio_write_zero_cluster; | ||
103 | } else { | ||
104 | - cb = qed_aio_write_cow; | ||
105 | acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters); | ||
106 | } | ||
107 | |||
108 | if (qed_should_set_need_check(s)) { | ||
109 | s->header.features |= QED_F_NEED_CHECK; | ||
110 | ret = qed_write_header(s); | ||
111 | - cb(acb, ret); | ||
112 | + if (ret < 0) { | ||
113 | + qed_aio_complete(acb, ret); | ||
114 | + return; | ||
115 | + } | ||
116 | + } | 109 | + } |
117 | + | 110 | + |
118 | + if (acb->flags & QED_AIOCB_ZERO) { | 111 | + if (!qemu_write_pidfile(pid_file, &err)) { |
119 | + ret = qed_aio_write_l2_update(acb, 1); | 112 | + error_reportf_err(err, "cannot create PID file: "); |
120 | } else { | 113 | + exit(EXIT_FAILURE); |
121 | - cb(acb, 0); | 114 | + } |
122 | + ret = qed_aio_write_cow(acb); | 115 | + |
116 | + atexit(pid_file_cleanup); | ||
117 | +} | ||
118 | + | ||
119 | int main(int argc, char *argv[]) | ||
120 | { | ||
121 | #ifdef CONFIG_POSIX | ||
122 | @@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[]) | ||
123 | qemu_init_main_loop(&error_fatal); | ||
124 | process_options(argc, argv); | ||
125 | |||
126 | + /* | ||
127 | + * Write the pid file after creating chardevs, exports, and NBD servers but | ||
128 | + * before accepting connections. This ordering is documented. Do not change | ||
129 | + * it. | ||
130 | + */ | ||
131 | + pid_file_init(); | ||
132 | + | ||
133 | while (!exit_requested) { | ||
134 | main_loop_wait(false); | ||
123 | } | 135 | } |
124 | + if (ret < 0) { | ||
125 | + qed_aio_complete(acb, ret); | ||
126 | + return; | ||
127 | + } | ||
128 | + qed_aio_next_io(acb, 0); | ||
129 | } | ||
130 | |||
131 | /** | ||
132 | -- | 136 | -- |
133 | 1.8.3.1 | 137 | 2.29.2 |
134 | 138 | ||
135 | 139 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Old kvm.ko versions only supported a tiny number of ioeventfds so | 3 | The QMP monitor, NBD server, and vhost-user-blk export all support file |
4 | virtio-pci avoids ioeventfds when kvm_has_many_ioeventfds() returns 0. | 4 | descriptor passing. This is a useful technique because it allows the |
5 | parent process to spawn and wait for qemu-storage-daemon without busy | ||
6 | waiting, which may delay startup due to arbitrary sleep() calls. | ||
5 | 7 | ||
6 | Do not check kvm_has_many_ioeventfds() when KVM is disabled since it | 8 | This Python example is inspired by the test case written for libnbd by |
7 | always returns 0. Since commit 8c56c1a592b5092d91da8d8943c17777d6462a6f | 9 | Richard W.M. Jones <rjones@redhat.com>: |
8 | ("memory: emulate ioeventfd") it has been possible to use ioeventfds in | 10 | https://gitlab.com/nbdkit/libnbd/-/commit/89113f484effb0e6c322314ba75c1cbe07a04543 |
9 | qtest or TCG mode. | ||
10 | 11 | ||
11 | This patch makes -device virtio-blk-pci,iothread=iothread0 work even | 12 | Thanks to Daniel P. Berrangé <berrange@redhat.com> for suggestions on |
12 | when KVM is disabled. | 13 | how to get this working. Now let's document it! |
13 | 14 | ||
14 | I have tested that virtio-blk-pci works under TCG both with and without | 15 | Reported-by: Richard W.M. Jones <rjones@redhat.com> |
15 | iothread. | 16 | Cc: Kevin Wolf <kwolf@redhat.com> |
16 | 17 | Cc: Daniel P. Berrangé <berrange@redhat.com> | |
17 | Cc: Michael S. Tsirkin <mst@redhat.com> | ||
18 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 18 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
19 | Reviewed-by: Michael S. Tsirkin <mst@redhat.com> | 19 | Message-Id: <20210301172728.135331-2-stefanha@redhat.com> |
20 | Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> | ||
21 | Reviewed-by: Richard W.M. Jones <rjones@redhat.com> | ||
20 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 22 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
21 | --- | 23 | --- |
22 | hw/virtio/virtio-pci.c | 2 +- | 24 | docs/tools/qemu-storage-daemon.rst | 42 ++++++++++++++++++++++++++++-- |
23 | 1 file changed, 1 insertion(+), 1 deletion(-) | 25 | 1 file changed, 40 insertions(+), 2 deletions(-) |
24 | 26 | ||
25 | diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c | 27 | diff --git a/docs/tools/qemu-storage-daemon.rst b/docs/tools/qemu-storage-daemon.rst |
26 | index XXXXXXX..XXXXXXX 100644 | 28 | index XXXXXXX..XXXXXXX 100644 |
27 | --- a/hw/virtio/virtio-pci.c | 29 | --- a/docs/tools/qemu-storage-daemon.rst |
28 | +++ b/hw/virtio/virtio-pci.c | 30 | +++ b/docs/tools/qemu-storage-daemon.rst |
29 | @@ -XXX,XX +XXX,XX @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) | 31 | @@ -XXX,XX +XXX,XX @@ Standard options: |
30 | bool pcie_port = pci_bus_is_express(pci_dev->bus) && | 32 | |
31 | !pci_bus_is_root(pci_dev->bus); | 33 | .. option:: --nbd-server addr.type=inet,addr.host=<host>,addr.port=<port>[,tls-creds=<id>][,tls-authz=<id>][,max-connections=<n>] |
32 | 34 | --nbd-server addr.type=unix,addr.path=<path>[,tls-creds=<id>][,tls-authz=<id>][,max-connections=<n>] | |
33 | - if (!kvm_has_many_ioeventfds()) { | 35 | + --nbd-server addr.type=fd,addr.str=<fd>[,tls-creds=<id>][,tls-authz=<id>][,max-connections=<n>] |
34 | + if (kvm_enabled() && !kvm_has_many_ioeventfds()) { | 36 | |
35 | proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD; | 37 | is a server for NBD exports. Both TCP and UNIX domain sockets are supported. |
36 | } | 38 | - TLS encryption can be configured using ``--object`` tls-creds-* and authz-* |
37 | 39 | - secrets (see below). | |
40 | + A listen socket can be provided via file descriptor passing (see Examples | ||
41 | + below). TLS encryption can be configured using ``--object`` tls-creds-* and | ||
42 | + authz-* secrets (see below). | ||
43 | |||
44 | To configure an NBD server on UNIX domain socket path ``/tmp/nbd.sock``:: | ||
45 | |||
46 | @@ -XXX,XX +XXX,XX @@ QMP commands:: | ||
47 | --chardev socket,path=qmp.sock,server=on,wait=off,id=char1 \ | ||
48 | --monitor chardev=char1 | ||
49 | |||
50 | +Launch the daemon from Python with a QMP monitor socket using file descriptor | ||
51 | +passing so there is no need to busy wait for the QMP monitor to become | ||
52 | +available:: | ||
53 | + | ||
54 | + #!/usr/bin/env python3 | ||
55 | + import subprocess | ||
56 | + import socket | ||
57 | + | ||
58 | + sock_path = '/var/run/qmp.sock' | ||
59 | + | ||
60 | + with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as listen_sock: | ||
61 | + listen_sock.bind(sock_path) | ||
62 | + listen_sock.listen() | ||
63 | + | ||
64 | + fd = listen_sock.fileno() | ||
65 | + | ||
66 | + subprocess.Popen( | ||
67 | + ['qemu-storage-daemon', | ||
68 | + '--chardev', f'socket,fd={fd},server=on,id=char1', | ||
69 | + '--monitor', 'chardev=char1'], | ||
70 | + pass_fds=[fd], | ||
71 | + ) | ||
72 | + | ||
73 | + # listen_sock was automatically closed when leaving the 'with' statement | ||
74 | + # body. If the daemon process terminated early then the following connect() | ||
75 | + # will fail with "Connection refused" because no process has the listen | ||
76 | + # socket open anymore. Launch errors can be detected this way. | ||
77 | + | ||
78 | + qmp_sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) | ||
79 | + qmp_sock.connect(sock_path) | ||
80 | + ...QMP interaction... | ||
81 | + | ||
82 | +The same socket spawning approach also works with the ``--nbd-server | ||
83 | +addr.type=fd,addr.str=<fd>`` and ``--export | ||
84 | +type=vhost-user-blk,addr.type=fd,addr.str=<fd>`` options. | ||
85 | + | ||
86 | Export raw image file ``disk.img`` over NBD UNIX domain socket ``nbd.sock``:: | ||
87 | |||
88 | $ qemu-storage-daemon \ | ||
38 | -- | 89 | -- |
39 | 1.8.3.1 | 90 | 2.29.2 |
40 | 91 | ||
41 | 92 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | AioContext was designed to allow nested acquire/release calls. It uses | 3 | World-writeable directories have security issues. Avoid showing them in |
4 | a recursive mutex so callers don't need to worry about nesting...or so | 4 | the documentation since someone might accidentally use them in |
5 | we thought. | 5 | situations where they are insecure. |
6 | 6 | ||
7 | BDRV_POLL_WHILE() is used to wait for block I/O requests. It releases | 7 | There tend to be 3 security problems: |
8 | the AioContext temporarily around aio_poll(). This gives IOThreads a | 8 | 1. Denial of service. An adversary may be able to create the file |
9 | chance to acquire the AioContext to process I/O completions. | 9 | beforehand, consume all space/inodes, etc to sabotage us. |
10 | 2. Impersonation. An adversary may be able to create a listen socket and | ||
11 | accept incoming connections that were meant for us. | ||
12 | 3. Unauthenticated client access. An adversary may be able to connect to | ||
13 | us if we did not set the uid/gid and permissions correctly. | ||
10 | 14 | ||
11 | It turns out that recursive locking and BDRV_POLL_WHILE() don't mix. | 15 | These can be prevented or mitigated with private /tmp, carefully setting |
12 | BDRV_POLL_WHILE() only releases the AioContext once, so the IOThread | 16 | the umask, etc but that requires special action and does not apply to |
13 | will not be able to acquire the AioContext if it was acquired | 17 | all situations. Just avoid using /tmp in examples. |
14 | multiple times. | ||
15 | 18 | ||
16 | Instead of trying to release AioContext n times in BDRV_POLL_WHILE(), | 19 | Reported-by: Richard W.M. Jones <rjones@redhat.com> |
17 | this patch simply avoids nested locking in save_vmstate(). It's the | 20 | Reported-by: Daniel P. Berrangé <berrange@redhat.com> |
18 | simplest fix and we should step back to consider the big picture with | ||
19 | all the recent changes to block layer threading. | ||
20 | |||
21 | This patch is the final fix to solve 'savevm' hanging with -object | ||
22 | iothread. | ||
23 | |||
24 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 21 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
25 | Reviewed-by: Eric Blake <eblake@redhat.com> | 22 | Message-Id: <20210301172728.135331-3-stefanha@redhat.com> |
26 | Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> | 23 | Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> |
24 | Reviewed-by: Richard W.M. Jones <rjones@redhat.com> | ||
27 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 25 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
28 | --- | 26 | --- |
29 | migration/savevm.c | 12 +++++++++++- | 27 | docs/tools/qemu-storage-daemon.rst | 7 ++++--- |
30 | 1 file changed, 11 insertions(+), 1 deletion(-) | 28 | 1 file changed, 4 insertions(+), 3 deletions(-) |
31 | 29 | ||
32 | diff --git a/migration/savevm.c b/migration/savevm.c | 30 | diff --git a/docs/tools/qemu-storage-daemon.rst b/docs/tools/qemu-storage-daemon.rst |
33 | index XXXXXXX..XXXXXXX 100644 | 31 | index XXXXXXX..XXXXXXX 100644 |
34 | --- a/migration/savevm.c | 32 | --- a/docs/tools/qemu-storage-daemon.rst |
35 | +++ b/migration/savevm.c | 33 | +++ b/docs/tools/qemu-storage-daemon.rst |
36 | @@ -XXX,XX +XXX,XX @@ int save_snapshot(const char *name, Error **errp) | 34 | @@ -XXX,XX +XXX,XX @@ Standard options: |
37 | goto the_end; | 35 | a description of character device properties. A common character device |
38 | } | 36 | definition configures a UNIX domain socket:: |
39 | 37 | ||
40 | + /* The bdrv_all_create_snapshot() call that follows acquires the AioContext | 38 | - --chardev socket,id=char1,path=/tmp/qmp.sock,server=on,wait=off |
41 | + * for itself. BDRV_POLL_WHILE() does not support nested locking because | 39 | + --chardev socket,id=char1,path=/var/run/qsd-qmp.sock,server=on,wait=off |
42 | + * it only releases the lock once. Therefore synchronous I/O will deadlock | 40 | |
43 | + * unless we release the AioContext before bdrv_all_create_snapshot(). | 41 | .. option:: --export [type=]nbd,id=<id>,node-name=<node-name>[,name=<export-name>][,writable=on|off][,bitmap=<name>] |
44 | + */ | 42 | --export [type=]vhost-user-blk,id=<id>,node-name=<node-name>,addr.type=unix,addr.path=<socket-path>[,writable=on|off][,logical-block-size=<block-size>][,num-queues=<num-queues>] |
45 | + aio_context_release(aio_context); | 43 | @@ -XXX,XX +XXX,XX @@ Standard options: |
46 | + aio_context = NULL; | 44 | below). TLS encryption can be configured using ``--object`` tls-creds-* and |
47 | + | 45 | authz-* secrets (see below). |
48 | ret = bdrv_all_create_snapshot(sn, bs, vm_state_size, &bs); | 46 | |
49 | if (ret < 0) { | 47 | - To configure an NBD server on UNIX domain socket path ``/tmp/nbd.sock``:: |
50 | error_setg(errp, "Error while creating snapshot on '%s'", | 48 | + To configure an NBD server on UNIX domain socket path |
51 | @@ -XXX,XX +XXX,XX @@ int save_snapshot(const char *name, Error **errp) | 49 | + ``/var/run/qsd-nbd.sock``:: |
52 | ret = 0; | 50 | |
53 | 51 | - --nbd-server addr.type=unix,addr.path=/tmp/nbd.sock | |
54 | the_end: | 52 | + --nbd-server addr.type=unix,addr.path=/var/run/qsd-nbd.sock |
55 | - aio_context_release(aio_context); | 53 | |
56 | + if (aio_context) { | 54 | .. option:: --object help |
57 | + aio_context_release(aio_context); | 55 | --object <type>,help |
58 | + } | ||
59 | if (saved_vm_running) { | ||
60 | vm_start(); | ||
61 | } | ||
62 | -- | 56 | -- |
63 | 1.8.3.1 | 57 | 2.29.2 |
64 | 58 | ||
65 | 59 | diff view generated by jsdifflib |
1 | All callers pass ret = 0, so we can just remove it. | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Treat the num_queues field as virtio-endian. On big-endian hosts the | ||
4 | vhost-user-blk num_queues field was in the wrong endianness. | ||
5 | |||
6 | Move the blkcfg.num_queues store operation from realize to | ||
7 | vhost_user_blk_update_config() so feature negotiation has finished and | ||
8 | we know the endianness of the device. VIRTIO 1.0 devices are | ||
9 | little-endian, but in case someone wants to use legacy VIRTIO we support | ||
10 | all endianness cases. | ||
11 | |||
12 | Cc: qemu-stable@nongnu.org | ||
13 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
14 | Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com> | ||
15 | Reviewed-by: Michael S. Tsirkin <mst@redhat.com> | ||
16 | Message-Id: <20210223144653.811468-2-stefanha@redhat.com> | ||
3 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 17 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
4 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
5 | --- | 18 | --- |
6 | block/qed.c | 17 ++++++----------- | 19 | hw/block/vhost-user-blk.c | 7 +++---- |
7 | 1 file changed, 6 insertions(+), 11 deletions(-) | 20 | 1 file changed, 3 insertions(+), 4 deletions(-) |
8 | 21 | ||
9 | diff --git a/block/qed.c b/block/qed.c | 22 | diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c |
10 | index XXXXXXX..XXXXXXX 100644 | 23 | index XXXXXXX..XXXXXXX 100644 |
11 | --- a/block/qed.c | 24 | --- a/hw/block/vhost-user-blk.c |
12 | +++ b/block/qed.c | 25 | +++ b/hw/block/vhost-user-blk.c |
13 | @@ -XXX,XX +XXX,XX @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s) | 26 | @@ -XXX,XX +XXX,XX @@ static void vhost_user_blk_update_config(VirtIODevice *vdev, uint8_t *config) |
14 | return l2_table; | 27 | { |
28 | VHostUserBlk *s = VHOST_USER_BLK(vdev); | ||
29 | |||
30 | + /* Our num_queues overrides the device backend */ | ||
31 | + virtio_stw_p(vdev, &s->blkcfg.num_queues, s->num_queues); | ||
32 | + | ||
33 | memcpy(config, &s->blkcfg, sizeof(struct virtio_blk_config)); | ||
15 | } | 34 | } |
16 | 35 | ||
17 | -static void qed_aio_next_io(QEDAIOCB *acb, int ret); | 36 | @@ -XXX,XX +XXX,XX @@ reconnect: |
18 | +static void qed_aio_next_io(QEDAIOCB *acb); | 37 | goto reconnect; |
19 | |||
20 | static void qed_aio_start_io(QEDAIOCB *acb) | ||
21 | { | ||
22 | - qed_aio_next_io(acb, 0); | ||
23 | + qed_aio_next_io(acb); | ||
24 | } | ||
25 | |||
26 | static void qed_plug_allocating_write_reqs(BDRVQEDState *s) | ||
27 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_read_data(void *opaque, int ret, uint64_t offset, size_t len) | ||
28 | /** | ||
29 | * Begin next I/O or complete the request | ||
30 | */ | ||
31 | -static void qed_aio_next_io(QEDAIOCB *acb, int ret) | ||
32 | +static void qed_aio_next_io(QEDAIOCB *acb) | ||
33 | { | ||
34 | BDRVQEDState *s = acb_to_s(acb); | ||
35 | uint64_t offset; | ||
36 | size_t len; | ||
37 | + int ret; | ||
38 | |||
39 | - trace_qed_aio_next_io(s, acb, ret, acb->cur_pos + acb->cur_qiov.size); | ||
40 | + trace_qed_aio_next_io(s, acb, 0, acb->cur_pos + acb->cur_qiov.size); | ||
41 | |||
42 | if (acb->backing_qiov) { | ||
43 | qemu_iovec_destroy(acb->backing_qiov); | ||
44 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb, int ret) | ||
45 | acb->backing_qiov = NULL; | ||
46 | } | 38 | } |
47 | 39 | ||
48 | - /* Handle I/O error */ | 40 | - if (s->blkcfg.num_queues != s->num_queues) { |
49 | - if (ret) { | 41 | - s->blkcfg.num_queues = s->num_queues; |
50 | - qed_aio_complete(acb, ret); | ||
51 | - return; | ||
52 | - } | 42 | - } |
53 | - | 43 | - |
54 | acb->qiov_offset += acb->cur_qiov.size; | 44 | return; |
55 | acb->cur_pos += acb->cur_qiov.size; | 45 | |
56 | qemu_iovec_reset(&acb->cur_qiov); | 46 | virtio_err: |
57 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb, int ret) | ||
58 | } | ||
59 | return; | ||
60 | } | ||
61 | - qed_aio_next_io(acb, 0); | ||
62 | + qed_aio_next_io(acb); | ||
63 | } | ||
64 | |||
65 | static BlockAIOCB *qed_aio_setup(BlockDriverState *bs, | ||
66 | -- | 47 | -- |
67 | 1.8.3.1 | 48 | 2.29.2 |
68 | 49 | ||
69 | 50 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Perform the savevm/loadvm test with both iothread on and off. This | 3 | Add an API that returns a new UNIX domain socket in the listen state. |
4 | covers the recently found savevm/loadvm hang when iothread is enabled. | 4 | The code for this was already there but only used internally in |
5 | init_socket(). | ||
6 | |||
7 | This new API will be used by vhost-user-blk-test. | ||
5 | 8 | ||
6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 9 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
10 | Reviewed-by: Thomas Huth <thuth@redhat.com> | ||
11 | Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> | ||
12 | Message-Id: <20210223144653.811468-3-stefanha@redhat.com> | ||
7 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 13 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
8 | --- | 14 | --- |
9 | tests/qemu-iotests/068 | 23 ++++++++++++++--------- | 15 | tests/qtest/libqos/libqtest.h | 8 +++++++ |
10 | tests/qemu-iotests/068.out | 11 ++++++++++- | 16 | tests/qtest/libqtest.c | 40 ++++++++++++++++++++--------------- |
11 | 2 files changed, 24 insertions(+), 10 deletions(-) | 17 | 2 files changed, 31 insertions(+), 17 deletions(-) |
12 | 18 | ||
13 | diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068 | 19 | diff --git a/tests/qtest/libqos/libqtest.h b/tests/qtest/libqos/libqtest.h |
14 | index XXXXXXX..XXXXXXX 100755 | 20 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/tests/qemu-iotests/068 | 21 | --- a/tests/qtest/libqos/libqtest.h |
16 | +++ b/tests/qemu-iotests/068 | 22 | +++ b/tests/qtest/libqos/libqtest.h |
17 | @@ -XXX,XX +XXX,XX @@ _supported_os Linux | 23 | @@ -XXX,XX +XXX,XX @@ void qtest_qmp_send(QTestState *s, const char *fmt, ...) |
18 | IMGOPTS="compat=1.1" | 24 | void qtest_qmp_send_raw(QTestState *s, const char *fmt, ...) |
19 | IMG_SIZE=128K | 25 | GCC_FMT_ATTR(2, 3); |
20 | 26 | ||
21 | -echo | 27 | +/** |
22 | -echo "=== Saving and reloading a VM state to/from a qcow2 image ===" | 28 | + * qtest_socket_server: |
23 | -echo | 29 | + * @socket_path: the UNIX domain socket path |
24 | -_make_test_img $IMG_SIZE | 30 | + * |
31 | + * Create and return a listen socket file descriptor, or abort on failure. | ||
32 | + */ | ||
33 | +int qtest_socket_server(const char *socket_path); | ||
34 | + | ||
35 | /** | ||
36 | * qtest_vqmp_fds: | ||
37 | * @s: #QTestState instance to operate on. | ||
38 | diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c | ||
39 | index XXXXXXX..XXXXXXX 100644 | ||
40 | --- a/tests/qtest/libqtest.c | ||
41 | +++ b/tests/qtest/libqtest.c | ||
42 | @@ -XXX,XX +XXX,XX @@ static void qtest_client_set_rx_handler(QTestState *s, QTestRecvFn recv); | ||
43 | |||
44 | static int init_socket(const char *socket_path) | ||
45 | { | ||
46 | - struct sockaddr_un addr; | ||
47 | - int sock; | ||
48 | - int ret; | ||
25 | - | 49 | - |
26 | case "$QEMU_DEFAULT_MACHINE" in | 50 | - sock = socket(PF_UNIX, SOCK_STREAM, 0); |
27 | s390-ccw-virtio) | 51 | - g_assert_cmpint(sock, !=, -1); |
28 | platform_parm="-no-shutdown" | 52 | - |
29 | @@ -XXX,XX +XXX,XX @@ _qemu() | 53 | - addr.sun_family = AF_UNIX; |
30 | _filter_qemu | _filter_hmp | 54 | - snprintf(addr.sun_path, sizeof(addr.sun_path), "%s", socket_path); |
55 | + int sock = qtest_socket_server(socket_path); | ||
56 | qemu_set_cloexec(sock); | ||
57 | - | ||
58 | - do { | ||
59 | - ret = bind(sock, (struct sockaddr *)&addr, sizeof(addr)); | ||
60 | - } while (ret == -1 && errno == EINTR); | ||
61 | - g_assert_cmpint(ret, !=, -1); | ||
62 | - ret = listen(sock, 1); | ||
63 | - g_assert_cmpint(ret, !=, -1); | ||
64 | - | ||
65 | return sock; | ||
31 | } | 66 | } |
32 | 67 | ||
33 | -# Give qemu some time to boot before saving the VM state | 68 | @@ -XXX,XX +XXX,XX @@ QDict *qtest_qmp_receive_dict(QTestState *s) |
34 | -bash -c 'sleep 1; echo -e "savevm 0\nquit"' | _qemu | 69 | return qmp_fd_receive(s->qmp_fd); |
35 | -# Now try to continue from that VM state (this should just work) | 70 | } |
36 | -echo quit | _qemu -loadvm 0 | 71 | |
37 | +for extra_args in \ | 72 | +int qtest_socket_server(const char *socket_path) |
38 | + "" \ | 73 | +{ |
39 | + "-object iothread,id=iothread0 -set device.hba0.iothread=iothread0"; do | 74 | + struct sockaddr_un addr; |
40 | + echo | 75 | + int sock; |
41 | + echo "=== Saving and reloading a VM state to/from a qcow2 image ($extra_args) ===" | 76 | + int ret; |
42 | + echo | ||
43 | + | 77 | + |
44 | + _make_test_img $IMG_SIZE | 78 | + sock = socket(PF_UNIX, SOCK_STREAM, 0); |
79 | + g_assert_cmpint(sock, !=, -1); | ||
45 | + | 80 | + |
46 | + # Give qemu some time to boot before saving the VM state | 81 | + addr.sun_family = AF_UNIX; |
47 | + bash -c 'sleep 1; echo -e "savevm 0\nquit"' | _qemu $extra_args | 82 | + snprintf(addr.sun_path, sizeof(addr.sun_path), "%s", socket_path); |
48 | + # Now try to continue from that VM state (this should just work) | ||
49 | + echo quit | _qemu $extra_args -loadvm 0 | ||
50 | +done | ||
51 | |||
52 | # success, all done | ||
53 | echo "*** done" | ||
54 | diff --git a/tests/qemu-iotests/068.out b/tests/qemu-iotests/068.out | ||
55 | index XXXXXXX..XXXXXXX 100644 | ||
56 | --- a/tests/qemu-iotests/068.out | ||
57 | +++ b/tests/qemu-iotests/068.out | ||
58 | @@ -XXX,XX +XXX,XX @@ | ||
59 | QA output created by 068 | ||
60 | |||
61 | -=== Saving and reloading a VM state to/from a qcow2 image === | ||
62 | +=== Saving and reloading a VM state to/from a qcow2 image () === | ||
63 | + | 83 | + |
64 | +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=131072 | 84 | + do { |
65 | +QEMU X.Y.Z monitor - type 'help' for more information | 85 | + ret = bind(sock, (struct sockaddr *)&addr, sizeof(addr)); |
66 | +(qemu) savevm 0 | 86 | + } while (ret == -1 && errno == EINTR); |
67 | +(qemu) quit | 87 | + g_assert_cmpint(ret, !=, -1); |
68 | +QEMU X.Y.Z monitor - type 'help' for more information | 88 | + ret = listen(sock, 1); |
69 | +(qemu) quit | 89 | + g_assert_cmpint(ret, !=, -1); |
70 | + | 90 | + |
71 | +=== Saving and reloading a VM state to/from a qcow2 image (-object iothread,id=iothread0 -set device.hba0.iothread=iothread0) === | 91 | + return sock; |
72 | 92 | +} | |
73 | Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=131072 | 93 | + |
74 | QEMU X.Y.Z monitor - type 'help' for more information | 94 | /** |
95 | * Allow users to send a message without waiting for the reply, | ||
96 | * in the case that they choose to discard all replies up until | ||
75 | -- | 97 | -- |
76 | 1.8.3.1 | 98 | 2.29.2 |
77 | 99 | ||
78 | 100 | diff view generated by jsdifflib |
1 | From: Alberto Garcia <berto@igalia.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Instead of calling perform_cow() twice with a different COW region | 3 | Tests that manage multiple processes may wish to kill QEMU before |
4 | each time, call it just once and make perform_cow() handle both | 4 | destroying the QTestState. Expose a function to do that. |
5 | regions. | ||
6 | 5 | ||
7 | This patch simply moves code around. The next one will do the actual | 6 | The vhost-user-blk-test testcase will need this. |
8 | reordering of the COW operations. | ||
9 | 7 | ||
10 | Signed-off-by: Alberto Garcia <berto@igalia.com> | 8 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
11 | Reviewed-by: Eric Blake <eblake@redhat.com> | 9 | Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> |
12 | Reviewed-by: Kevin Wolf <kwolf@redhat.com> | 10 | Message-Id: <20210223144653.811468-4-stefanha@redhat.com> |
13 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 11 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
14 | --- | 12 | --- |
15 | block/qcow2-cluster.c | 36 ++++++++++++++++++++++-------------- | 13 | tests/qtest/libqos/libqtest.h | 11 +++++++++++ |
16 | 1 file changed, 22 insertions(+), 14 deletions(-) | 14 | tests/qtest/libqtest.c | 7 ++++--- |
15 | 2 files changed, 15 insertions(+), 3 deletions(-) | ||
17 | 16 | ||
18 | diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c | 17 | diff --git a/tests/qtest/libqos/libqtest.h b/tests/qtest/libqos/libqtest.h |
19 | index XXXXXXX..XXXXXXX 100644 | 18 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/block/qcow2-cluster.c | 19 | --- a/tests/qtest/libqos/libqtest.h |
21 | +++ b/block/qcow2-cluster.c | 20 | +++ b/tests/qtest/libqos/libqtest.h |
22 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn do_perform_cow(BlockDriverState *bs, | 21 | @@ -XXX,XX +XXX,XX @@ QTestState *qtest_init_without_qmp_handshake(const char *extra_args); |
23 | struct iovec iov; | 22 | */ |
24 | int ret; | 23 | QTestState *qtest_init_with_serial(const char *extra_args, int *sock_fd); |
25 | 24 | ||
26 | + if (bytes == 0) { | 25 | +/** |
27 | + return 0; | 26 | + * qtest_kill_qemu: |
28 | + } | 27 | + * @s: #QTestState instance to operate on. |
28 | + * | ||
29 | + * Kill the QEMU process and wait for it to terminate. It is safe to call this | ||
30 | + * function multiple times. Normally qtest_quit() is used instead because it | ||
31 | + * also frees QTestState. Use qtest_kill_qemu() when you just want to kill QEMU | ||
32 | + * and qtest_quit() will be called later. | ||
33 | + */ | ||
34 | +void qtest_kill_qemu(QTestState *s); | ||
29 | + | 35 | + |
30 | iov.iov_len = bytes; | 36 | /** |
31 | iov.iov_base = qemu_try_blockalign(bs, iov.iov_len); | 37 | * qtest_quit: |
32 | if (iov.iov_base == NULL) { | 38 | * @s: #QTestState instance to operate on. |
33 | @@ -XXX,XX +XXX,XX @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, | 39 | diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c |
34 | return cluster_offset; | 40 | index XXXXXXX..XXXXXXX 100644 |
41 | --- a/tests/qtest/libqtest.c | ||
42 | +++ b/tests/qtest/libqtest.c | ||
43 | @@ -XXX,XX +XXX,XX @@ void qtest_set_expected_status(QTestState *s, int status) | ||
44 | s->expected_status = status; | ||
35 | } | 45 | } |
36 | 46 | ||
37 | -static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r) | 47 | -static void kill_qemu(QTestState *s) |
38 | +static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | 48 | +void qtest_kill_qemu(QTestState *s) |
39 | { | 49 | { |
40 | BDRVQcow2State *s = bs->opaque; | 50 | pid_t pid = s->qemu_pid; |
41 | + Qcow2COWRegion *start = &m->cow_start; | 51 | int wstatus; |
42 | + Qcow2COWRegion *end = &m->cow_end; | 52 | @@ -XXX,XX +XXX,XX @@ static void kill_qemu(QTestState *s) |
43 | int ret; | 53 | kill(pid, SIGTERM); |
44 | 54 | TFR(pid = waitpid(s->qemu_pid, &s->wstatus, 0)); | |
45 | - if (r->nb_bytes == 0) { | 55 | assert(pid == s->qemu_pid); |
46 | + if (start->nb_bytes == 0 && end->nb_bytes == 0) { | 56 | + s->qemu_pid = -1; |
47 | return 0; | ||
48 | } | 57 | } |
49 | 58 | ||
50 | qemu_co_mutex_unlock(&s->lock); | ||
51 | - ret = do_perform_cow(bs, m->offset, m->alloc_offset, r->offset, r->nb_bytes); | ||
52 | - qemu_co_mutex_lock(&s->lock); | ||
53 | - | ||
54 | + ret = do_perform_cow(bs, m->offset, m->alloc_offset, | ||
55 | + start->offset, start->nb_bytes); | ||
56 | if (ret < 0) { | ||
57 | - return ret; | ||
58 | + goto fail; | ||
59 | } | ||
60 | |||
61 | + ret = do_perform_cow(bs, m->offset, m->alloc_offset, | ||
62 | + end->offset, end->nb_bytes); | ||
63 | + | ||
64 | +fail: | ||
65 | + qemu_co_mutex_lock(&s->lock); | ||
66 | + | ||
67 | /* | 59 | /* |
68 | * Before we update the L2 table to actually point to the new cluster, we | 60 | @@ -XXX,XX +XXX,XX @@ static void kill_qemu(QTestState *s) |
69 | * need to be sure that the refcounts have been increased and COW was | 61 | |
70 | * handled. | 62 | static void kill_qemu_hook_func(void *s) |
71 | */ | 63 | { |
72 | - qcow2_cache_depends_on_flush(s->l2_table_cache); | 64 | - kill_qemu(s); |
73 | + if (ret == 0) { | 65 | + qtest_kill_qemu(s); |
74 | + qcow2_cache_depends_on_flush(s->l2_table_cache); | ||
75 | + } | ||
76 | |||
77 | - return 0; | ||
78 | + return ret; | ||
79 | } | 66 | } |
80 | 67 | ||
81 | int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) | 68 | static void sigabrt_handler(int signo) |
82 | @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) | 69 | @@ -XXX,XX +XXX,XX @@ void qtest_quit(QTestState *s) |
83 | } | 70 | /* Uninstall SIGABRT handler on last instance */ |
84 | 71 | cleanup_sigabrt_handler(); | |
85 | /* copy content of unmodified sectors */ | 72 | |
86 | - ret = perform_cow(bs, m, &m->cow_start); | 73 | - kill_qemu(s); |
87 | - if (ret < 0) { | 74 | + qtest_kill_qemu(s); |
88 | - goto err; | 75 | close(s->fd); |
89 | - } | 76 | close(s->qmp_fd); |
90 | - | 77 | g_string_free(s->rx, true); |
91 | - ret = perform_cow(bs, m, &m->cow_end); | ||
92 | + ret = perform_cow(bs, m); | ||
93 | if (ret < 0) { | ||
94 | goto err; | ||
95 | } | ||
96 | -- | 78 | -- |
97 | 1.8.3.1 | 79 | 2.29.2 |
98 | 80 | ||
99 | 81 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Avoid duplicating the QEMU command-line. | 3 | Add a function to remove previously-added abrt handler functions. |
4 | |||
5 | Now that a symmetric pair of add/remove functions exists we can also | ||
6 | balance the SIGABRT handler installation. The signal handler was | ||
7 | installed each time qtest_add_abrt_handler() was called. Now it is | ||
8 | installed when the abrt handler list becomes non-empty and removed again | ||
9 | when the list becomes empty. | ||
10 | |||
11 | The qtest_remove_abrt_handler() function will be used by | ||
12 | vhost-user-blk-test. | ||
4 | 13 | ||
5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 14 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
15 | Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> | ||
16 | Message-Id: <20210223144653.811468-5-stefanha@redhat.com> | ||
6 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 17 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
7 | --- | 18 | --- |
8 | tests/qemu-iotests/068 | 15 +++++++++------ | 19 | tests/qtest/libqos/libqtest.h | 18 ++++++++++++++++++ |
9 | 1 file changed, 9 insertions(+), 6 deletions(-) | 20 | tests/qtest/libqtest.c | 35 +++++++++++++++++++++++++++++------ |
21 | 2 files changed, 47 insertions(+), 6 deletions(-) | ||
10 | 22 | ||
11 | diff --git a/tests/qemu-iotests/068 b/tests/qemu-iotests/068 | 23 | diff --git a/tests/qtest/libqos/libqtest.h b/tests/qtest/libqos/libqtest.h |
12 | index XXXXXXX..XXXXXXX 100755 | 24 | index XXXXXXX..XXXXXXX 100644 |
13 | --- a/tests/qemu-iotests/068 | 25 | --- a/tests/qtest/libqos/libqtest.h |
14 | +++ b/tests/qemu-iotests/068 | 26 | +++ b/tests/qtest/libqos/libqtest.h |
15 | @@ -XXX,XX +XXX,XX @@ case "$QEMU_DEFAULT_MACHINE" in | 27 | @@ -XXX,XX +XXX,XX @@ void qtest_add_data_func_full(const char *str, void *data, |
16 | ;; | 28 | g_free(path); \ |
17 | esac | 29 | } while (0) |
18 | 30 | ||
19 | -# Give qemu some time to boot before saving the VM state | 31 | +/** |
20 | -bash -c 'sleep 1; echo -e "savevm 0\nquit"' |\ | 32 | + * qtest_add_abrt_handler: |
21 | - $QEMU $platform_parm -nographic -monitor stdio -serial none -hda "$TEST_IMG" |\ | 33 | + * @fn: Handler function |
22 | +_qemu() | 34 | + * @data: Argument that is passed to the handler |
35 | + * | ||
36 | + * Add a handler function that is invoked on SIGABRT. This can be used to | ||
37 | + * terminate processes and perform other cleanup. The handler can be removed | ||
38 | + * with qtest_remove_abrt_handler(). | ||
39 | + */ | ||
40 | void qtest_add_abrt_handler(GHookFunc fn, const void *data); | ||
41 | |||
42 | +/** | ||
43 | + * qtest_remove_abrt_handler: | ||
44 | + * @data: Argument previously passed to qtest_add_abrt_handler() | ||
45 | + * | ||
46 | + * Remove an abrt handler that was previously added with | ||
47 | + * qtest_add_abrt_handler(). | ||
48 | + */ | ||
49 | +void qtest_remove_abrt_handler(void *data); | ||
50 | + | ||
51 | /** | ||
52 | * qtest_qmp_assert_success: | ||
53 | * @qts: QTestState instance to operate on | ||
54 | diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c | ||
55 | index XXXXXXX..XXXXXXX 100644 | ||
56 | --- a/tests/qtest/libqtest.c | ||
57 | +++ b/tests/qtest/libqtest.c | ||
58 | @@ -XXX,XX +XXX,XX @@ static void cleanup_sigabrt_handler(void) | ||
59 | sigaction(SIGABRT, &sigact_old, NULL); | ||
60 | } | ||
61 | |||
62 | +static bool hook_list_is_empty(GHookList *hook_list) | ||
23 | +{ | 63 | +{ |
24 | + $QEMU $platform_parm -nographic -monitor stdio -serial none -hda "$TEST_IMG" \ | 64 | + GHook *hook = g_hook_first_valid(hook_list, TRUE); |
25 | + "$@" |\ | 65 | + |
26 | _filter_qemu | _filter_hmp | 66 | + if (!hook) { |
67 | + return false; | ||
68 | + } | ||
69 | + | ||
70 | + g_hook_unref(hook_list, hook); | ||
71 | + return true; | ||
27 | +} | 72 | +} |
28 | + | 73 | + |
29 | +# Give qemu some time to boot before saving the VM state | 74 | void qtest_add_abrt_handler(GHookFunc fn, const void *data) |
30 | +bash -c 'sleep 1; echo -e "savevm 0\nquit"' | _qemu | 75 | { |
31 | # Now try to continue from that VM state (this should just work) | 76 | GHook *hook; |
32 | -echo quit |\ | 77 | |
33 | - $QEMU $platform_parm -nographic -monitor stdio -serial none -hda "$TEST_IMG" -loadvm 0 |\ | 78 | - /* Only install SIGABRT handler once */ |
34 | - _filter_qemu | _filter_hmp | 79 | if (!abrt_hooks.is_setup) { |
35 | +echo quit | _qemu -loadvm 0 | 80 | g_hook_list_init(&abrt_hooks, sizeof(GHook)); |
36 | 81 | } | |
37 | # success, all done | 82 | - setup_sigabrt_handler(); |
38 | echo "*** done" | 83 | + |
84 | + /* Only install SIGABRT handler once */ | ||
85 | + if (hook_list_is_empty(&abrt_hooks)) { | ||
86 | + setup_sigabrt_handler(); | ||
87 | + } | ||
88 | |||
89 | hook = g_hook_alloc(&abrt_hooks); | ||
90 | hook->func = fn; | ||
91 | @@ -XXX,XX +XXX,XX @@ void qtest_add_abrt_handler(GHookFunc fn, const void *data) | ||
92 | g_hook_prepend(&abrt_hooks, hook); | ||
93 | } | ||
94 | |||
95 | +void qtest_remove_abrt_handler(void *data) | ||
96 | +{ | ||
97 | + GHook *hook = g_hook_find_data(&abrt_hooks, TRUE, data); | ||
98 | + g_hook_destroy_link(&abrt_hooks, hook); | ||
99 | + | ||
100 | + /* Uninstall SIGABRT handler on last instance */ | ||
101 | + if (hook_list_is_empty(&abrt_hooks)) { | ||
102 | + cleanup_sigabrt_handler(); | ||
103 | + } | ||
104 | +} | ||
105 | + | ||
106 | static const char *qtest_qemu_binary(void) | ||
107 | { | ||
108 | const char *qemu_bin; | ||
109 | @@ -XXX,XX +XXX,XX @@ QTestState *qtest_init_with_serial(const char *extra_args, int *sock_fd) | ||
110 | |||
111 | void qtest_quit(QTestState *s) | ||
112 | { | ||
113 | - g_hook_destroy_link(&abrt_hooks, g_hook_find_data(&abrt_hooks, TRUE, s)); | ||
114 | - | ||
115 | - /* Uninstall SIGABRT handler on last instance */ | ||
116 | - cleanup_sigabrt_handler(); | ||
117 | + qtest_remove_abrt_handler(s); | ||
118 | |||
119 | qtest_kill_qemu(s); | ||
120 | close(s->fd); | ||
39 | -- | 121 | -- |
40 | 1.8.3.1 | 122 | 2.29.2 |
41 | 123 | ||
42 | 124 | diff view generated by jsdifflib |
1 | Now that we stay in coroutine context for the whole request when doing | 1 | From: Coiby Xu <coiby.xu@gmail.com> |
---|---|---|---|
2 | reads or writes, we can add coroutine_fn annotations to many functions | ||
3 | that can do I/O or yield directly. | ||
4 | 2 | ||
3 | This test case has the same tests as tests/virtio-blk-test.c except for | ||
4 | tests have block_resize. Since the vhost-user-blk export only serves one | ||
5 | client one time, two exports are started by qemu-storage-daemon for the | ||
6 | hotplug test. | ||
7 | |||
8 | Suggested-by: Thomas Huth <thuth@redhat.com> | ||
9 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> | ||
10 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
11 | Message-Id: <20210223144653.811468-6-stefanha@redhat.com> | ||
5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 12 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
6 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
7 | --- | 13 | --- |
8 | block/qed-cluster.c | 5 +++-- | 14 | tests/qtest/libqos/vhost-user-blk.h | 48 ++ |
9 | block/qed.c | 44 ++++++++++++++++++++++++-------------------- | 15 | tests/qtest/libqos/vhost-user-blk.c | 130 +++++ |
10 | block/qed.h | 5 +++-- | 16 | tests/qtest/vhost-user-blk-test.c | 788 ++++++++++++++++++++++++++++ |
11 | 3 files changed, 30 insertions(+), 24 deletions(-) | 17 | MAINTAINERS | 2 + |
18 | tests/qtest/libqos/meson.build | 1 + | ||
19 | tests/qtest/meson.build | 4 + | ||
20 | 6 files changed, 973 insertions(+) | ||
21 | create mode 100644 tests/qtest/libqos/vhost-user-blk.h | ||
22 | create mode 100644 tests/qtest/libqos/vhost-user-blk.c | ||
23 | create mode 100644 tests/qtest/vhost-user-blk-test.c | ||
12 | 24 | ||
13 | diff --git a/block/qed-cluster.c b/block/qed-cluster.c | 25 | diff --git a/tests/qtest/libqos/vhost-user-blk.h b/tests/qtest/libqos/vhost-user-blk.h |
26 | new file mode 100644 | ||
27 | index XXXXXXX..XXXXXXX | ||
28 | --- /dev/null | ||
29 | +++ b/tests/qtest/libqos/vhost-user-blk.h | ||
30 | @@ -XXX,XX +XXX,XX @@ | ||
31 | +/* | ||
32 | + * libqos driver framework | ||
33 | + * | ||
34 | + * Based on tests/qtest/libqos/virtio-blk.c | ||
35 | + * | ||
36 | + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> | ||
37 | + * | ||
38 | + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> | ||
39 | + * | ||
40 | + * This library is free software; you can redistribute it and/or | ||
41 | + * modify it under the terms of the GNU Lesser General Public | ||
42 | + * License version 2 as published by the Free Software Foundation. | ||
43 | + * | ||
44 | + * This library is distributed in the hope that it will be useful, | ||
45 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
46 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | ||
47 | + * Lesser General Public License for more details. | ||
48 | + * | ||
49 | + * You should have received a copy of the GNU Lesser General Public | ||
50 | + * License along with this library; if not, see <http://www.gnu.org/licenses/> | ||
51 | + */ | ||
52 | + | ||
53 | +#ifndef TESTS_LIBQOS_VHOST_USER_BLK_H | ||
54 | +#define TESTS_LIBQOS_VHOST_USER_BLK_H | ||
55 | + | ||
56 | +#include "qgraph.h" | ||
57 | +#include "virtio.h" | ||
58 | +#include "virtio-pci.h" | ||
59 | + | ||
60 | +typedef struct QVhostUserBlk QVhostUserBlk; | ||
61 | +typedef struct QVhostUserBlkPCI QVhostUserBlkPCI; | ||
62 | +typedef struct QVhostUserBlkDevice QVhostUserBlkDevice; | ||
63 | + | ||
64 | +struct QVhostUserBlk { | ||
65 | + QVirtioDevice *vdev; | ||
66 | +}; | ||
67 | + | ||
68 | +struct QVhostUserBlkPCI { | ||
69 | + QVirtioPCIDevice pci_vdev; | ||
70 | + QVhostUserBlk blk; | ||
71 | +}; | ||
72 | + | ||
73 | +struct QVhostUserBlkDevice { | ||
74 | + QOSGraphObject obj; | ||
75 | + QVhostUserBlk blk; | ||
76 | +}; | ||
77 | + | ||
78 | +#endif | ||
79 | diff --git a/tests/qtest/libqos/vhost-user-blk.c b/tests/qtest/libqos/vhost-user-blk.c | ||
80 | new file mode 100644 | ||
81 | index XXXXXXX..XXXXXXX | ||
82 | --- /dev/null | ||
83 | +++ b/tests/qtest/libqos/vhost-user-blk.c | ||
84 | @@ -XXX,XX +XXX,XX @@ | ||
85 | +/* | ||
86 | + * libqos driver framework | ||
87 | + * | ||
88 | + * Based on tests/qtest/libqos/virtio-blk.c | ||
89 | + * | ||
90 | + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> | ||
91 | + * | ||
92 | + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> | ||
93 | + * | ||
94 | + * This library is free software; you can redistribute it and/or | ||
95 | + * modify it under the terms of the GNU Lesser General Public | ||
96 | + * License version 2.1 as published by the Free Software Foundation. | ||
97 | + * | ||
98 | + * This library is distributed in the hope that it will be useful, | ||
99 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
100 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | ||
101 | + * Lesser General Public License for more details. | ||
102 | + * | ||
103 | + * You should have received a copy of the GNU Lesser General Public | ||
104 | + * License along with this library; if not, see <http://www.gnu.org/licenses/> | ||
105 | + */ | ||
106 | + | ||
107 | +#include "qemu/osdep.h" | ||
108 | +#include "libqtest.h" | ||
109 | +#include "qemu/module.h" | ||
110 | +#include "standard-headers/linux/virtio_blk.h" | ||
111 | +#include "vhost-user-blk.h" | ||
112 | + | ||
113 | +#define PCI_SLOT 0x04 | ||
114 | +#define PCI_FN 0x00 | ||
115 | + | ||
116 | +/* virtio-blk-device */ | ||
117 | +static void *qvhost_user_blk_get_driver(QVhostUserBlk *v_blk, | ||
118 | + const char *interface) | ||
119 | +{ | ||
120 | + if (!g_strcmp0(interface, "vhost-user-blk")) { | ||
121 | + return v_blk; | ||
122 | + } | ||
123 | + if (!g_strcmp0(interface, "virtio")) { | ||
124 | + return v_blk->vdev; | ||
125 | + } | ||
126 | + | ||
127 | + fprintf(stderr, "%s not present in vhost-user-blk-device\n", interface); | ||
128 | + g_assert_not_reached(); | ||
129 | +} | ||
130 | + | ||
131 | +static void *qvhost_user_blk_device_get_driver(void *object, | ||
132 | + const char *interface) | ||
133 | +{ | ||
134 | + QVhostUserBlkDevice *v_blk = object; | ||
135 | + return qvhost_user_blk_get_driver(&v_blk->blk, interface); | ||
136 | +} | ||
137 | + | ||
138 | +static void *vhost_user_blk_device_create(void *virtio_dev, | ||
139 | + QGuestAllocator *t_alloc, | ||
140 | + void *addr) | ||
141 | +{ | ||
142 | + QVhostUserBlkDevice *vhost_user_blk = g_new0(QVhostUserBlkDevice, 1); | ||
143 | + QVhostUserBlk *interface = &vhost_user_blk->blk; | ||
144 | + | ||
145 | + interface->vdev = virtio_dev; | ||
146 | + | ||
147 | + vhost_user_blk->obj.get_driver = qvhost_user_blk_device_get_driver; | ||
148 | + | ||
149 | + return &vhost_user_blk->obj; | ||
150 | +} | ||
151 | + | ||
152 | +/* virtio-blk-pci */ | ||
153 | +static void *qvhost_user_blk_pci_get_driver(void *object, const char *interface) | ||
154 | +{ | ||
155 | + QVhostUserBlkPCI *v_blk = object; | ||
156 | + if (!g_strcmp0(interface, "pci-device")) { | ||
157 | + return v_blk->pci_vdev.pdev; | ||
158 | + } | ||
159 | + return qvhost_user_blk_get_driver(&v_blk->blk, interface); | ||
160 | +} | ||
161 | + | ||
162 | +static void *vhost_user_blk_pci_create(void *pci_bus, QGuestAllocator *t_alloc, | ||
163 | + void *addr) | ||
164 | +{ | ||
165 | + QVhostUserBlkPCI *vhost_user_blk = g_new0(QVhostUserBlkPCI, 1); | ||
166 | + QVhostUserBlk *interface = &vhost_user_blk->blk; | ||
167 | + QOSGraphObject *obj = &vhost_user_blk->pci_vdev.obj; | ||
168 | + | ||
169 | + virtio_pci_init(&vhost_user_blk->pci_vdev, pci_bus, addr); | ||
170 | + interface->vdev = &vhost_user_blk->pci_vdev.vdev; | ||
171 | + | ||
172 | + g_assert_cmphex(interface->vdev->device_type, ==, VIRTIO_ID_BLOCK); | ||
173 | + | ||
174 | + obj->get_driver = qvhost_user_blk_pci_get_driver; | ||
175 | + | ||
176 | + return obj; | ||
177 | +} | ||
178 | + | ||
179 | +static void vhost_user_blk_register_nodes(void) | ||
180 | +{ | ||
181 | + /* | ||
182 | + * FIXME: every test using these two nodes needs to setup a | ||
183 | + * -drive,id=drive0 otherwise QEMU is not going to start. | ||
184 | + * Therefore, we do not include "produces" edge for virtio | ||
185 | + * and pci-device yet. | ||
186 | + */ | ||
187 | + | ||
188 | + char *arg = g_strdup_printf("id=drv0,chardev=char1,addr=%x.%x", | ||
189 | + PCI_SLOT, PCI_FN); | ||
190 | + | ||
191 | + QPCIAddress addr = { | ||
192 | + .devfn = QPCI_DEVFN(PCI_SLOT, PCI_FN), | ||
193 | + }; | ||
194 | + | ||
195 | + QOSGraphEdgeOptions opts = { }; | ||
196 | + | ||
197 | + /* virtio-blk-device */ | ||
198 | + /** opts.extra_device_opts = "drive=drive0"; */ | ||
199 | + qos_node_create_driver("vhost-user-blk-device", | ||
200 | + vhost_user_blk_device_create); | ||
201 | + qos_node_consumes("vhost-user-blk-device", "virtio-bus", &opts); | ||
202 | + qos_node_produces("vhost-user-blk-device", "vhost-user-blk"); | ||
203 | + | ||
204 | + /* virtio-blk-pci */ | ||
205 | + opts.extra_device_opts = arg; | ||
206 | + add_qpci_address(&opts, &addr); | ||
207 | + qos_node_create_driver("vhost-user-blk-pci", vhost_user_blk_pci_create); | ||
208 | + qos_node_consumes("vhost-user-blk-pci", "pci-bus", &opts); | ||
209 | + qos_node_produces("vhost-user-blk-pci", "vhost-user-blk"); | ||
210 | + | ||
211 | + g_free(arg); | ||
212 | +} | ||
213 | + | ||
214 | +libqos_init(vhost_user_blk_register_nodes); | ||
215 | diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c | ||
216 | new file mode 100644 | ||
217 | index XXXXXXX..XXXXXXX | ||
218 | --- /dev/null | ||
219 | +++ b/tests/qtest/vhost-user-blk-test.c | ||
220 | @@ -XXX,XX +XXX,XX @@ | ||
221 | +/* | ||
222 | + * QTest testcase for Vhost-user Block Device | ||
223 | + * | ||
224 | + * Based on tests/qtest//virtio-blk-test.c | ||
225 | + | ||
226 | + * Copyright (c) 2014 SUSE LINUX Products GmbH | ||
227 | + * Copyright (c) 2014 Marc Marí | ||
228 | + * Copyright (c) 2020 Coiby Xu | ||
229 | + * | ||
230 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. | ||
231 | + * See the COPYING file in the top-level directory. | ||
232 | + */ | ||
233 | + | ||
234 | +#include "qemu/osdep.h" | ||
235 | +#include "libqtest-single.h" | ||
236 | +#include "qemu/bswap.h" | ||
237 | +#include "qemu/module.h" | ||
238 | +#include "standard-headers/linux/virtio_blk.h" | ||
239 | +#include "standard-headers/linux/virtio_pci.h" | ||
240 | +#include "libqos/qgraph.h" | ||
241 | +#include "libqos/vhost-user-blk.h" | ||
242 | +#include "libqos/libqos-pc.h" | ||
243 | + | ||
244 | +#define TEST_IMAGE_SIZE (64 * 1024 * 1024) | ||
245 | +#define QVIRTIO_BLK_TIMEOUT_US (30 * 1000 * 1000) | ||
246 | +#define PCI_SLOT_HP 0x06 | ||
247 | + | ||
248 | +typedef struct { | ||
249 | + pid_t pid; | ||
250 | +} QemuStorageDaemonState; | ||
251 | + | ||
252 | +typedef struct QVirtioBlkReq { | ||
253 | + uint32_t type; | ||
254 | + uint32_t ioprio; | ||
255 | + uint64_t sector; | ||
256 | + char *data; | ||
257 | + uint8_t status; | ||
258 | +} QVirtioBlkReq; | ||
259 | + | ||
260 | +#ifdef HOST_WORDS_BIGENDIAN | ||
261 | +static const bool host_is_big_endian = true; | ||
262 | +#else | ||
263 | +static const bool host_is_big_endian; /* false */ | ||
264 | +#endif | ||
265 | + | ||
266 | +static inline void virtio_blk_fix_request(QVirtioDevice *d, QVirtioBlkReq *req) | ||
267 | +{ | ||
268 | + if (qvirtio_is_big_endian(d) != host_is_big_endian) { | ||
269 | + req->type = bswap32(req->type); | ||
270 | + req->ioprio = bswap32(req->ioprio); | ||
271 | + req->sector = bswap64(req->sector); | ||
272 | + } | ||
273 | +} | ||
274 | + | ||
275 | +static inline void virtio_blk_fix_dwz_hdr(QVirtioDevice *d, | ||
276 | + struct virtio_blk_discard_write_zeroes *dwz_hdr) | ||
277 | +{ | ||
278 | + if (qvirtio_is_big_endian(d) != host_is_big_endian) { | ||
279 | + dwz_hdr->sector = bswap64(dwz_hdr->sector); | ||
280 | + dwz_hdr->num_sectors = bswap32(dwz_hdr->num_sectors); | ||
281 | + dwz_hdr->flags = bswap32(dwz_hdr->flags); | ||
282 | + } | ||
283 | +} | ||
284 | + | ||
285 | +static uint64_t virtio_blk_request(QGuestAllocator *alloc, QVirtioDevice *d, | ||
286 | + QVirtioBlkReq *req, uint64_t data_size) | ||
287 | +{ | ||
288 | + uint64_t addr; | ||
289 | + uint8_t status = 0xFF; | ||
290 | + QTestState *qts = global_qtest; | ||
291 | + | ||
292 | + switch (req->type) { | ||
293 | + case VIRTIO_BLK_T_IN: | ||
294 | + case VIRTIO_BLK_T_OUT: | ||
295 | + g_assert_cmpuint(data_size % 512, ==, 0); | ||
296 | + break; | ||
297 | + case VIRTIO_BLK_T_DISCARD: | ||
298 | + case VIRTIO_BLK_T_WRITE_ZEROES: | ||
299 | + g_assert_cmpuint(data_size % | ||
300 | + sizeof(struct virtio_blk_discard_write_zeroes), ==, 0); | ||
301 | + break; | ||
302 | + default: | ||
303 | + g_assert_cmpuint(data_size, ==, 0); | ||
304 | + } | ||
305 | + | ||
306 | + addr = guest_alloc(alloc, sizeof(*req) + data_size); | ||
307 | + | ||
308 | + virtio_blk_fix_request(d, req); | ||
309 | + | ||
310 | + qtest_memwrite(qts, addr, req, 16); | ||
311 | + qtest_memwrite(qts, addr + 16, req->data, data_size); | ||
312 | + qtest_memwrite(qts, addr + 16 + data_size, &status, sizeof(status)); | ||
313 | + | ||
314 | + return addr; | ||
315 | +} | ||
316 | + | ||
317 | +/* Returns the request virtqueue so the caller can perform further tests */ | ||
318 | +static QVirtQueue *test_basic(QVirtioDevice *dev, QGuestAllocator *alloc) | ||
319 | +{ | ||
320 | + QVirtioBlkReq req; | ||
321 | + uint64_t req_addr; | ||
322 | + uint64_t capacity; | ||
323 | + uint64_t features; | ||
324 | + uint32_t free_head; | ||
325 | + uint8_t status; | ||
326 | + char *data; | ||
327 | + QTestState *qts = global_qtest; | ||
328 | + QVirtQueue *vq; | ||
329 | + | ||
330 | + features = qvirtio_get_features(dev); | ||
331 | + features = features & ~(QVIRTIO_F_BAD_FEATURE | | ||
332 | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | | ||
333 | + (1u << VIRTIO_RING_F_EVENT_IDX) | | ||
334 | + (1u << VIRTIO_BLK_F_SCSI)); | ||
335 | + qvirtio_set_features(dev, features); | ||
336 | + | ||
337 | + capacity = qvirtio_config_readq(dev, 0); | ||
338 | + g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512); | ||
339 | + | ||
340 | + vq = qvirtqueue_setup(dev, alloc, 0); | ||
341 | + | ||
342 | + qvirtio_set_driver_ok(dev); | ||
343 | + | ||
344 | + /* Write and read with 3 descriptor layout */ | ||
345 | + /* Write request */ | ||
346 | + req.type = VIRTIO_BLK_T_OUT; | ||
347 | + req.ioprio = 1; | ||
348 | + req.sector = 0; | ||
349 | + req.data = g_malloc0(512); | ||
350 | + strcpy(req.data, "TEST"); | ||
351 | + | ||
352 | + req_addr = virtio_blk_request(alloc, dev, &req, 512); | ||
353 | + | ||
354 | + g_free(req.data); | ||
355 | + | ||
356 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
357 | + qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true); | ||
358 | + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); | ||
359 | + | ||
360 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
361 | + | ||
362 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
363 | + QVIRTIO_BLK_TIMEOUT_US); | ||
364 | + status = readb(req_addr + 528); | ||
365 | + g_assert_cmpint(status, ==, 0); | ||
366 | + | ||
367 | + guest_free(alloc, req_addr); | ||
368 | + | ||
369 | + /* Read request */ | ||
370 | + req.type = VIRTIO_BLK_T_IN; | ||
371 | + req.ioprio = 1; | ||
372 | + req.sector = 0; | ||
373 | + req.data = g_malloc0(512); | ||
374 | + | ||
375 | + req_addr = virtio_blk_request(alloc, dev, &req, 512); | ||
376 | + | ||
377 | + g_free(req.data); | ||
378 | + | ||
379 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
380 | + qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true); | ||
381 | + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); | ||
382 | + | ||
383 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
384 | + | ||
385 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
386 | + QVIRTIO_BLK_TIMEOUT_US); | ||
387 | + status = readb(req_addr + 528); | ||
388 | + g_assert_cmpint(status, ==, 0); | ||
389 | + | ||
390 | + data = g_malloc0(512); | ||
391 | + qtest_memread(qts, req_addr + 16, data, 512); | ||
392 | + g_assert_cmpstr(data, ==, "TEST"); | ||
393 | + g_free(data); | ||
394 | + | ||
395 | + guest_free(alloc, req_addr); | ||
396 | + | ||
397 | + if (features & (1u << VIRTIO_BLK_F_WRITE_ZEROES)) { | ||
398 | + struct virtio_blk_discard_write_zeroes dwz_hdr; | ||
399 | + void *expected; | ||
400 | + | ||
401 | + /* | ||
402 | + * WRITE_ZEROES request on the same sector of previous test where | ||
403 | + * we wrote "TEST". | ||
404 | + */ | ||
405 | + req.type = VIRTIO_BLK_T_WRITE_ZEROES; | ||
406 | + req.data = (char *) &dwz_hdr; | ||
407 | + dwz_hdr.sector = 0; | ||
408 | + dwz_hdr.num_sectors = 1; | ||
409 | + dwz_hdr.flags = 0; | ||
410 | + | ||
411 | + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); | ||
412 | + | ||
413 | + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); | ||
414 | + | ||
415 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
416 | + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true); | ||
417 | + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), 1, true, | ||
418 | + false); | ||
419 | + | ||
420 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
421 | + | ||
422 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
423 | + QVIRTIO_BLK_TIMEOUT_US); | ||
424 | + status = readb(req_addr + 16 + sizeof(dwz_hdr)); | ||
425 | + g_assert_cmpint(status, ==, 0); | ||
426 | + | ||
427 | + guest_free(alloc, req_addr); | ||
428 | + | ||
429 | + /* Read request to check if the sector contains all zeroes */ | ||
430 | + req.type = VIRTIO_BLK_T_IN; | ||
431 | + req.ioprio = 1; | ||
432 | + req.sector = 0; | ||
433 | + req.data = g_malloc0(512); | ||
434 | + | ||
435 | + req_addr = virtio_blk_request(alloc, dev, &req, 512); | ||
436 | + | ||
437 | + g_free(req.data); | ||
438 | + | ||
439 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
440 | + qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true); | ||
441 | + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); | ||
442 | + | ||
443 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
444 | + | ||
445 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
446 | + QVIRTIO_BLK_TIMEOUT_US); | ||
447 | + status = readb(req_addr + 528); | ||
448 | + g_assert_cmpint(status, ==, 0); | ||
449 | + | ||
450 | + data = g_malloc(512); | ||
451 | + expected = g_malloc0(512); | ||
452 | + qtest_memread(qts, req_addr + 16, data, 512); | ||
453 | + g_assert_cmpmem(data, 512, expected, 512); | ||
454 | + g_free(expected); | ||
455 | + g_free(data); | ||
456 | + | ||
457 | + guest_free(alloc, req_addr); | ||
458 | + } | ||
459 | + | ||
460 | + if (features & (1u << VIRTIO_BLK_F_DISCARD)) { | ||
461 | + struct virtio_blk_discard_write_zeroes dwz_hdr; | ||
462 | + | ||
463 | + req.type = VIRTIO_BLK_T_DISCARD; | ||
464 | + req.data = (char *) &dwz_hdr; | ||
465 | + dwz_hdr.sector = 0; | ||
466 | + dwz_hdr.num_sectors = 1; | ||
467 | + dwz_hdr.flags = 0; | ||
468 | + | ||
469 | + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); | ||
470 | + | ||
471 | + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); | ||
472 | + | ||
473 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
474 | + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true); | ||
475 | + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), | ||
476 | + 1, true, false); | ||
477 | + | ||
478 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
479 | + | ||
480 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
481 | + QVIRTIO_BLK_TIMEOUT_US); | ||
482 | + status = readb(req_addr + 16 + sizeof(dwz_hdr)); | ||
483 | + g_assert_cmpint(status, ==, 0); | ||
484 | + | ||
485 | + guest_free(alloc, req_addr); | ||
486 | + } | ||
487 | + | ||
488 | + if (features & (1u << VIRTIO_F_ANY_LAYOUT)) { | ||
489 | + /* Write and read with 2 descriptor layout */ | ||
490 | + /* Write request */ | ||
491 | + req.type = VIRTIO_BLK_T_OUT; | ||
492 | + req.ioprio = 1; | ||
493 | + req.sector = 1; | ||
494 | + req.data = g_malloc0(512); | ||
495 | + strcpy(req.data, "TEST"); | ||
496 | + | ||
497 | + req_addr = virtio_blk_request(alloc, dev, &req, 512); | ||
498 | + | ||
499 | + g_free(req.data); | ||
500 | + | ||
501 | + free_head = qvirtqueue_add(qts, vq, req_addr, 528, false, true); | ||
502 | + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); | ||
503 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
504 | + | ||
505 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
506 | + QVIRTIO_BLK_TIMEOUT_US); | ||
507 | + status = readb(req_addr + 528); | ||
508 | + g_assert_cmpint(status, ==, 0); | ||
509 | + | ||
510 | + guest_free(alloc, req_addr); | ||
511 | + | ||
512 | + /* Read request */ | ||
513 | + req.type = VIRTIO_BLK_T_IN; | ||
514 | + req.ioprio = 1; | ||
515 | + req.sector = 1; | ||
516 | + req.data = g_malloc0(512); | ||
517 | + | ||
518 | + req_addr = virtio_blk_request(alloc, dev, &req, 512); | ||
519 | + | ||
520 | + g_free(req.data); | ||
521 | + | ||
522 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
523 | + qvirtqueue_add(qts, vq, req_addr + 16, 513, true, false); | ||
524 | + | ||
525 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
526 | + | ||
527 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
528 | + QVIRTIO_BLK_TIMEOUT_US); | ||
529 | + status = readb(req_addr + 528); | ||
530 | + g_assert_cmpint(status, ==, 0); | ||
531 | + | ||
532 | + data = g_malloc0(512); | ||
533 | + qtest_memread(qts, req_addr + 16, data, 512); | ||
534 | + g_assert_cmpstr(data, ==, "TEST"); | ||
535 | + g_free(data); | ||
536 | + | ||
537 | + guest_free(alloc, req_addr); | ||
538 | + } | ||
539 | + | ||
540 | + return vq; | ||
541 | +} | ||
542 | + | ||
543 | +static void basic(void *obj, void *data, QGuestAllocator *t_alloc) | ||
544 | +{ | ||
545 | + QVhostUserBlk *blk_if = obj; | ||
546 | + QVirtQueue *vq; | ||
547 | + | ||
548 | + vq = test_basic(blk_if->vdev, t_alloc); | ||
549 | + qvirtqueue_cleanup(blk_if->vdev->bus, vq, t_alloc); | ||
550 | + | ||
551 | +} | ||
552 | + | ||
553 | +static void indirect(void *obj, void *u_data, QGuestAllocator *t_alloc) | ||
554 | +{ | ||
555 | + QVirtQueue *vq; | ||
556 | + QVhostUserBlk *blk_if = obj; | ||
557 | + QVirtioDevice *dev = blk_if->vdev; | ||
558 | + QVirtioBlkReq req; | ||
559 | + QVRingIndirectDesc *indirect; | ||
560 | + uint64_t req_addr; | ||
561 | + uint64_t capacity; | ||
562 | + uint64_t features; | ||
563 | + uint32_t free_head; | ||
564 | + uint8_t status; | ||
565 | + char *data; | ||
566 | + QTestState *qts = global_qtest; | ||
567 | + | ||
568 | + features = qvirtio_get_features(dev); | ||
569 | + g_assert_cmphex(features & (1u << VIRTIO_RING_F_INDIRECT_DESC), !=, 0); | ||
570 | + features = features & ~(QVIRTIO_F_BAD_FEATURE | | ||
571 | + (1u << VIRTIO_RING_F_EVENT_IDX) | | ||
572 | + (1u << VIRTIO_BLK_F_SCSI)); | ||
573 | + qvirtio_set_features(dev, features); | ||
574 | + | ||
575 | + capacity = qvirtio_config_readq(dev, 0); | ||
576 | + g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512); | ||
577 | + | ||
578 | + vq = qvirtqueue_setup(dev, t_alloc, 0); | ||
579 | + qvirtio_set_driver_ok(dev); | ||
580 | + | ||
581 | + /* Write request */ | ||
582 | + req.type = VIRTIO_BLK_T_OUT; | ||
583 | + req.ioprio = 1; | ||
584 | + req.sector = 0; | ||
585 | + req.data = g_malloc0(512); | ||
586 | + strcpy(req.data, "TEST"); | ||
587 | + | ||
588 | + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); | ||
589 | + | ||
590 | + g_free(req.data); | ||
591 | + | ||
592 | + indirect = qvring_indirect_desc_setup(qts, dev, t_alloc, 2); | ||
593 | + qvring_indirect_desc_add(dev, qts, indirect, req_addr, 528, false); | ||
594 | + qvring_indirect_desc_add(dev, qts, indirect, req_addr + 528, 1, true); | ||
595 | + free_head = qvirtqueue_add_indirect(qts, vq, indirect); | ||
596 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
597 | + | ||
598 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
599 | + QVIRTIO_BLK_TIMEOUT_US); | ||
600 | + status = readb(req_addr + 528); | ||
601 | + g_assert_cmpint(status, ==, 0); | ||
602 | + | ||
603 | + g_free(indirect); | ||
604 | + guest_free(t_alloc, req_addr); | ||
605 | + | ||
606 | + /* Read request */ | ||
607 | + req.type = VIRTIO_BLK_T_IN; | ||
608 | + req.ioprio = 1; | ||
609 | + req.sector = 0; | ||
610 | + req.data = g_malloc0(512); | ||
611 | + strcpy(req.data, "TEST"); | ||
612 | + | ||
613 | + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); | ||
614 | + | ||
615 | + g_free(req.data); | ||
616 | + | ||
617 | + indirect = qvring_indirect_desc_setup(qts, dev, t_alloc, 2); | ||
618 | + qvring_indirect_desc_add(dev, qts, indirect, req_addr, 16, false); | ||
619 | + qvring_indirect_desc_add(dev, qts, indirect, req_addr + 16, 513, true); | ||
620 | + free_head = qvirtqueue_add_indirect(qts, vq, indirect); | ||
621 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
622 | + | ||
623 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
624 | + QVIRTIO_BLK_TIMEOUT_US); | ||
625 | + status = readb(req_addr + 528); | ||
626 | + g_assert_cmpint(status, ==, 0); | ||
627 | + | ||
628 | + data = g_malloc0(512); | ||
629 | + qtest_memread(qts, req_addr + 16, data, 512); | ||
630 | + g_assert_cmpstr(data, ==, "TEST"); | ||
631 | + g_free(data); | ||
632 | + | ||
633 | + g_free(indirect); | ||
634 | + guest_free(t_alloc, req_addr); | ||
635 | + qvirtqueue_cleanup(dev->bus, vq, t_alloc); | ||
636 | +} | ||
637 | + | ||
638 | +static void idx(void *obj, void *u_data, QGuestAllocator *t_alloc) | ||
639 | +{ | ||
640 | + QVirtQueue *vq; | ||
641 | + QVhostUserBlkPCI *blk = obj; | ||
642 | + QVirtioPCIDevice *pdev = &blk->pci_vdev; | ||
643 | + QVirtioDevice *dev = &pdev->vdev; | ||
644 | + QVirtioBlkReq req; | ||
645 | + uint64_t req_addr; | ||
646 | + uint64_t capacity; | ||
647 | + uint64_t features; | ||
648 | + uint32_t free_head; | ||
649 | + uint32_t write_head; | ||
650 | + uint32_t desc_idx; | ||
651 | + uint8_t status; | ||
652 | + char *data; | ||
653 | + QOSGraphObject *blk_object = obj; | ||
654 | + QPCIDevice *pci_dev = blk_object->get_driver(blk_object, "pci-device"); | ||
655 | + QTestState *qts = global_qtest; | ||
656 | + | ||
657 | + if (qpci_check_buggy_msi(pci_dev)) { | ||
658 | + return; | ||
659 | + } | ||
660 | + | ||
661 | + qpci_msix_enable(pdev->pdev); | ||
662 | + qvirtio_pci_set_msix_configuration_vector(pdev, t_alloc, 0); | ||
663 | + | ||
664 | + features = qvirtio_get_features(dev); | ||
665 | + features = features & ~(QVIRTIO_F_BAD_FEATURE | | ||
666 | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | | ||
667 | + (1u << VIRTIO_F_NOTIFY_ON_EMPTY) | | ||
668 | + (1u << VIRTIO_BLK_F_SCSI)); | ||
669 | + qvirtio_set_features(dev, features); | ||
670 | + | ||
671 | + capacity = qvirtio_config_readq(dev, 0); | ||
672 | + g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512); | ||
673 | + | ||
674 | + vq = qvirtqueue_setup(dev, t_alloc, 0); | ||
675 | + qvirtqueue_pci_msix_setup(pdev, (QVirtQueuePCI *)vq, t_alloc, 1); | ||
676 | + | ||
677 | + qvirtio_set_driver_ok(dev); | ||
678 | + | ||
679 | + /* Write request */ | ||
680 | + req.type = VIRTIO_BLK_T_OUT; | ||
681 | + req.ioprio = 1; | ||
682 | + req.sector = 0; | ||
683 | + req.data = g_malloc0(512); | ||
684 | + strcpy(req.data, "TEST"); | ||
685 | + | ||
686 | + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); | ||
687 | + | ||
688 | + g_free(req.data); | ||
689 | + | ||
690 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
691 | + qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true); | ||
692 | + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); | ||
693 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
694 | + | ||
695 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
696 | + QVIRTIO_BLK_TIMEOUT_US); | ||
697 | + | ||
698 | + /* Write request */ | ||
699 | + req.type = VIRTIO_BLK_T_OUT; | ||
700 | + req.ioprio = 1; | ||
701 | + req.sector = 1; | ||
702 | + req.data = g_malloc0(512); | ||
703 | + strcpy(req.data, "TEST"); | ||
704 | + | ||
705 | + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); | ||
706 | + | ||
707 | + g_free(req.data); | ||
708 | + | ||
709 | + /* Notify after processing the third request */ | ||
710 | + qvirtqueue_set_used_event(qts, vq, 2); | ||
711 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
712 | + qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true); | ||
713 | + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); | ||
714 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
715 | + write_head = free_head; | ||
716 | + | ||
717 | + /* No notification expected */ | ||
718 | + status = qvirtio_wait_status_byte_no_isr(qts, dev, | ||
719 | + vq, req_addr + 528, | ||
720 | + QVIRTIO_BLK_TIMEOUT_US); | ||
721 | + g_assert_cmpint(status, ==, 0); | ||
722 | + | ||
723 | + guest_free(t_alloc, req_addr); | ||
724 | + | ||
725 | + /* Read request */ | ||
726 | + req.type = VIRTIO_BLK_T_IN; | ||
727 | + req.ioprio = 1; | ||
728 | + req.sector = 1; | ||
729 | + req.data = g_malloc0(512); | ||
730 | + | ||
731 | + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); | ||
732 | + | ||
733 | + g_free(req.data); | ||
734 | + | ||
735 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
736 | + qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true); | ||
737 | + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); | ||
738 | + | ||
739 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
740 | + | ||
741 | + /* We get just one notification for both requests */ | ||
742 | + qvirtio_wait_used_elem(qts, dev, vq, write_head, NULL, | ||
743 | + QVIRTIO_BLK_TIMEOUT_US); | ||
744 | + g_assert(qvirtqueue_get_buf(qts, vq, &desc_idx, NULL)); | ||
745 | + g_assert_cmpint(desc_idx, ==, free_head); | ||
746 | + | ||
747 | + status = readb(req_addr + 528); | ||
748 | + g_assert_cmpint(status, ==, 0); | ||
749 | + | ||
750 | + data = g_malloc0(512); | ||
751 | + qtest_memread(qts, req_addr + 16, data, 512); | ||
752 | + g_assert_cmpstr(data, ==, "TEST"); | ||
753 | + g_free(data); | ||
754 | + | ||
755 | + guest_free(t_alloc, req_addr); | ||
756 | + | ||
757 | + /* End test */ | ||
758 | + qpci_msix_disable(pdev->pdev); | ||
759 | + | ||
760 | + qvirtqueue_cleanup(dev->bus, vq, t_alloc); | ||
761 | +} | ||
762 | + | ||
763 | +static void pci_hotplug(void *obj, void *data, QGuestAllocator *t_alloc) | ||
764 | +{ | ||
765 | + QVirtioPCIDevice *dev1 = obj; | ||
766 | + QVirtioPCIDevice *dev; | ||
767 | + QTestState *qts = dev1->pdev->bus->qts; | ||
768 | + | ||
769 | + /* plug secondary disk */ | ||
770 | + qtest_qmp_device_add(qts, "vhost-user-blk-pci", "drv1", | ||
771 | + "{'addr': %s, 'chardev': 'char2'}", | ||
772 | + stringify(PCI_SLOT_HP) ".0"); | ||
773 | + | ||
774 | + dev = virtio_pci_new(dev1->pdev->bus, | ||
775 | + &(QPCIAddress) { .devfn = QPCI_DEVFN(PCI_SLOT_HP, 0) | ||
776 | + }); | ||
777 | + g_assert_nonnull(dev); | ||
778 | + g_assert_cmpint(dev->vdev.device_type, ==, VIRTIO_ID_BLOCK); | ||
779 | + qvirtio_pci_device_disable(dev); | ||
780 | + qos_object_destroy((QOSGraphObject *)dev); | ||
781 | + | ||
782 | + /* unplug secondary disk */ | ||
783 | + qpci_unplug_acpi_device_test(qts, "drv1", PCI_SLOT_HP); | ||
784 | +} | ||
785 | + | ||
786 | +/* | ||
787 | + * Check that setting the vring addr on a non-existent virtqueue does | ||
788 | + * not crash. | ||
789 | + */ | ||
790 | +static void test_nonexistent_virtqueue(void *obj, void *data, | ||
791 | + QGuestAllocator *t_alloc) | ||
792 | +{ | ||
793 | + QVhostUserBlkPCI *blk = obj; | ||
794 | + QVirtioPCIDevice *pdev = &blk->pci_vdev; | ||
795 | + QPCIBar bar0; | ||
796 | + QPCIDevice *dev; | ||
797 | + | ||
798 | + dev = qpci_device_find(pdev->pdev->bus, QPCI_DEVFN(4, 0)); | ||
799 | + g_assert(dev != NULL); | ||
800 | + qpci_device_enable(dev); | ||
801 | + | ||
802 | + bar0 = qpci_iomap(dev, 0, NULL); | ||
803 | + | ||
804 | + qpci_io_writeb(dev, bar0, VIRTIO_PCI_QUEUE_SEL, 2); | ||
805 | + qpci_io_writel(dev, bar0, VIRTIO_PCI_QUEUE_PFN, 1); | ||
806 | + | ||
807 | + g_free(dev); | ||
808 | +} | ||
809 | + | ||
810 | +static const char *qtest_qemu_storage_daemon_binary(void) | ||
811 | +{ | ||
812 | + const char *qemu_storage_daemon_bin; | ||
813 | + | ||
814 | + qemu_storage_daemon_bin = getenv("QTEST_QEMU_STORAGE_DAEMON_BINARY"); | ||
815 | + if (!qemu_storage_daemon_bin) { | ||
816 | + fprintf(stderr, "Environment variable " | ||
817 | + "QTEST_QEMU_STORAGE_DAEMON_BINARY required\n"); | ||
818 | + exit(0); | ||
819 | + } | ||
820 | + | ||
821 | + return qemu_storage_daemon_bin; | ||
822 | +} | ||
823 | + | ||
824 | +/* g_test_queue_destroy() cleanup function for files */ | ||
825 | +static void destroy_file(void *path) | ||
826 | +{ | ||
827 | + unlink(path); | ||
828 | + g_free(path); | ||
829 | + qos_invalidate_command_line(); | ||
830 | +} | ||
831 | + | ||
832 | +static char *drive_create(void) | ||
833 | +{ | ||
834 | + int fd, ret; | ||
835 | + /** vhost-user-blk won't recognize drive located in /tmp */ | ||
836 | + char *t_path = g_strdup("qtest.XXXXXX"); | ||
837 | + | ||
838 | + /** Create a temporary raw image */ | ||
839 | + fd = mkstemp(t_path); | ||
840 | + g_assert_cmpint(fd, >=, 0); | ||
841 | + ret = ftruncate(fd, TEST_IMAGE_SIZE); | ||
842 | + g_assert_cmpint(ret, ==, 0); | ||
843 | + close(fd); | ||
844 | + | ||
845 | + g_test_queue_destroy(destroy_file, t_path); | ||
846 | + return t_path; | ||
847 | +} | ||
848 | + | ||
849 | +static char *create_listen_socket(int *fd) | ||
850 | +{ | ||
851 | + int tmp_fd; | ||
852 | + char *path; | ||
853 | + | ||
854 | + /* No race because our pid makes the path unique */ | ||
855 | + path = g_strdup_printf("/tmp/qtest-%d-sock.XXXXXX", getpid()); | ||
856 | + tmp_fd = mkstemp(path); | ||
857 | + g_assert_cmpint(tmp_fd, >=, 0); | ||
858 | + close(tmp_fd); | ||
859 | + unlink(path); | ||
860 | + | ||
861 | + *fd = qtest_socket_server(path); | ||
862 | + g_test_queue_destroy(destroy_file, path); | ||
863 | + return path; | ||
864 | +} | ||
865 | + | ||
866 | +/* | ||
867 | + * g_test_queue_destroy() and qtest_add_abrt_handler() cleanup function for | ||
868 | + * qemu-storage-daemon. | ||
869 | + */ | ||
870 | +static void quit_storage_daemon(void *data) | ||
871 | +{ | ||
872 | + QemuStorageDaemonState *qsd = data; | ||
873 | + int wstatus; | ||
874 | + pid_t pid; | ||
875 | + | ||
876 | + /* | ||
877 | + * If we were invoked as a g_test_queue_destroy() cleanup function we need | ||
878 | + * to remove the abrt handler to avoid being called again if the code below | ||
879 | + * aborts. Also, we must not leave the abrt handler installed after | ||
880 | + * cleanup. | ||
881 | + */ | ||
882 | + qtest_remove_abrt_handler(data); | ||
883 | + | ||
884 | + /* Before quitting storage-daemon, quit qemu to avoid dubious messages */ | ||
885 | + qtest_kill_qemu(global_qtest); | ||
886 | + | ||
887 | + kill(qsd->pid, SIGTERM); | ||
888 | + pid = waitpid(qsd->pid, &wstatus, 0); | ||
889 | + g_assert_cmpint(pid, ==, qsd->pid); | ||
890 | + if (!WIFEXITED(wstatus)) { | ||
891 | + fprintf(stderr, "%s: expected qemu-storage-daemon to exit\n", | ||
892 | + __func__); | ||
893 | + abort(); | ||
894 | + } | ||
895 | + if (WEXITSTATUS(wstatus) != 0) { | ||
896 | + fprintf(stderr, "%s: expected qemu-storage-daemon to exit " | ||
897 | + "successfully, got %d\n", | ||
898 | + __func__, WEXITSTATUS(wstatus)); | ||
899 | + abort(); | ||
900 | + } | ||
901 | + | ||
902 | + g_free(data); | ||
903 | +} | ||
904 | + | ||
905 | +static void start_vhost_user_blk(GString *cmd_line, int vus_instances) | ||
906 | +{ | ||
907 | + const char *vhost_user_blk_bin = qtest_qemu_storage_daemon_binary(); | ||
908 | + int i; | ||
909 | + gchar *img_path; | ||
910 | + GString *storage_daemon_command = g_string_new(NULL); | ||
911 | + QemuStorageDaemonState *qsd; | ||
912 | + | ||
913 | + g_string_append_printf(storage_daemon_command, | ||
914 | + "exec %s ", | ||
915 | + vhost_user_blk_bin); | ||
916 | + | ||
917 | + g_string_append_printf(cmd_line, | ||
918 | + " -object memory-backend-memfd,id=mem,size=256M,share=on " | ||
919 | + " -M memory-backend=mem -m 256M "); | ||
920 | + | ||
921 | + for (i = 0; i < vus_instances; i++) { | ||
922 | + int fd; | ||
923 | + char *sock_path = create_listen_socket(&fd); | ||
924 | + | ||
925 | + /* create image file */ | ||
926 | + img_path = drive_create(); | ||
927 | + g_string_append_printf(storage_daemon_command, | ||
928 | + "--blockdev driver=file,node-name=disk%d,filename=%s " | ||
929 | + "--export type=vhost-user-blk,id=disk%d,addr.type=unix,addr.path=%s," | ||
930 | + "node-name=disk%i,writable=on ", | ||
931 | + i, img_path, i, sock_path, i); | ||
932 | + | ||
933 | + g_string_append_printf(cmd_line, "-chardev socket,id=char%d,path=%s ", | ||
934 | + i + 1, sock_path); | ||
935 | + } | ||
936 | + | ||
937 | + g_test_message("starting vhost-user backend: %s", | ||
938 | + storage_daemon_command->str); | ||
939 | + pid_t pid = fork(); | ||
940 | + if (pid == 0) { | ||
941 | + /* | ||
942 | + * Close standard file descriptors so tap-driver.pl pipe detects when | ||
943 | + * our parent terminates. | ||
944 | + */ | ||
945 | + close(0); | ||
946 | + close(1); | ||
947 | + open("/dev/null", O_RDONLY); | ||
948 | + open("/dev/null", O_WRONLY); | ||
949 | + | ||
950 | + execlp("/bin/sh", "sh", "-c", storage_daemon_command->str, NULL); | ||
951 | + exit(1); | ||
952 | + } | ||
953 | + g_string_free(storage_daemon_command, true); | ||
954 | + | ||
955 | + qsd = g_new(QemuStorageDaemonState, 1); | ||
956 | + qsd->pid = pid; | ||
957 | + | ||
958 | + /* Make sure qemu-storage-daemon is stopped */ | ||
959 | + qtest_add_abrt_handler(quit_storage_daemon, qsd); | ||
960 | + g_test_queue_destroy(quit_storage_daemon, qsd); | ||
961 | +} | ||
962 | + | ||
963 | +static void *vhost_user_blk_test_setup(GString *cmd_line, void *arg) | ||
964 | +{ | ||
965 | + start_vhost_user_blk(cmd_line, 1); | ||
966 | + return arg; | ||
967 | +} | ||
968 | + | ||
969 | +/* | ||
970 | + * Setup for hotplug. | ||
971 | + * | ||
972 | + * Since vhost-user server only serves one vhost-user client one time, | ||
973 | + * another exprot | ||
974 | + * | ||
975 | + */ | ||
976 | +static void *vhost_user_blk_hotplug_test_setup(GString *cmd_line, void *arg) | ||
977 | +{ | ||
978 | + /* "-chardev socket,id=char2" is used for pci_hotplug*/ | ||
979 | + start_vhost_user_blk(cmd_line, 2); | ||
980 | + return arg; | ||
981 | +} | ||
982 | + | ||
983 | +static void register_vhost_user_blk_test(void) | ||
984 | +{ | ||
985 | + QOSGraphTestOptions opts = { | ||
986 | + .before = vhost_user_blk_test_setup, | ||
987 | + }; | ||
988 | + | ||
989 | + /* | ||
990 | + * tests for vhost-user-blk and vhost-user-blk-pci | ||
991 | + * The tests are borrowed from tests/virtio-blk-test.c. But some tests | ||
992 | + * regarding block_resize don't work for vhost-user-blk. | ||
993 | + * vhost-user-blk device doesn't have -drive, so tests containing | ||
994 | + * block_resize are also abandoned, | ||
995 | + * - config | ||
996 | + * - resize | ||
997 | + */ | ||
998 | + qos_add_test("basic", "vhost-user-blk", basic, &opts); | ||
999 | + qos_add_test("indirect", "vhost-user-blk", indirect, &opts); | ||
1000 | + qos_add_test("idx", "vhost-user-blk-pci", idx, &opts); | ||
1001 | + qos_add_test("nxvirtq", "vhost-user-blk-pci", | ||
1002 | + test_nonexistent_virtqueue, &opts); | ||
1003 | + | ||
1004 | + opts.before = vhost_user_blk_hotplug_test_setup; | ||
1005 | + qos_add_test("hotplug", "vhost-user-blk-pci", pci_hotplug, &opts); | ||
1006 | +} | ||
1007 | + | ||
1008 | +libqos_init(register_vhost_user_blk_test); | ||
1009 | diff --git a/MAINTAINERS b/MAINTAINERS | ||
14 | index XXXXXXX..XXXXXXX 100644 | 1010 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/block/qed-cluster.c | 1011 | --- a/MAINTAINERS |
16 | +++ b/block/qed-cluster.c | 1012 | +++ b/MAINTAINERS |
17 | @@ -XXX,XX +XXX,XX @@ static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s, | 1013 | @@ -XXX,XX +XXX,XX @@ F: block/export/vhost-user-blk-server.c |
18 | * On failure QED_CLUSTER_L2 or QED_CLUSTER_L1 is returned for missing L2 or L1 | 1014 | F: block/export/vhost-user-blk-server.h |
19 | * table offset, respectively. len is number of contiguous unallocated bytes. | 1015 | F: include/qemu/vhost-user-server.h |
20 | */ | 1016 | F: tests/qtest/libqos/vhost-user-blk.c |
21 | -int qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | 1017 | +F: tests/qtest/libqos/vhost-user-blk.h |
22 | - size_t *len, uint64_t *img_offset) | 1018 | +F: tests/qtest/vhost-user-blk-test.c |
23 | +int coroutine_fn qed_find_cluster(BDRVQEDState *s, QEDRequest *request, | 1019 | F: util/vhost-user-server.c |
24 | + uint64_t pos, size_t *len, | 1020 | |
25 | + uint64_t *img_offset) | 1021 | FUSE block device exports |
26 | { | 1022 | diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build |
27 | uint64_t l2_offset; | ||
28 | uint64_t offset = 0; | ||
29 | diff --git a/block/qed.c b/block/qed.c | ||
30 | index XXXXXXX..XXXXXXX 100644 | 1023 | index XXXXXXX..XXXXXXX 100644 |
31 | --- a/block/qed.c | 1024 | --- a/tests/qtest/libqos/meson.build |
32 | +++ b/block/qed.c | 1025 | +++ b/tests/qtest/libqos/meson.build |
33 | @@ -XXX,XX +XXX,XX @@ int qed_write_header_sync(BDRVQEDState *s) | 1026 | @@ -XXX,XX +XXX,XX @@ libqos_srcs = files('../libqtest.c', |
34 | * This function only updates known header fields in-place and does not affect | 1027 | 'virtio-9p.c', |
35 | * extra data after the QED header. | 1028 | 'virtio-balloon.c', |
36 | */ | 1029 | 'virtio-blk.c', |
37 | -static int qed_write_header(BDRVQEDState *s) | 1030 | + 'vhost-user-blk.c', |
38 | +static int coroutine_fn qed_write_header(BDRVQEDState *s) | 1031 | 'virtio-mmio.c', |
39 | { | 1032 | 'virtio-net.c', |
40 | /* We must write full sectors for O_DIRECT but cannot necessarily generate | 1033 | 'virtio-pci.c', |
41 | * the data following the header if an unrecognized compat feature is | 1034 | diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build |
42 | @@ -XXX,XX +XXX,XX @@ static void qed_unplug_allocating_write_reqs(BDRVQEDState *s) | ||
43 | qemu_co_enter_next(&s->allocating_write_reqs); | ||
44 | } | ||
45 | |||
46 | -static void qed_need_check_timer_entry(void *opaque) | ||
47 | +static void coroutine_fn qed_need_check_timer_entry(void *opaque) | ||
48 | { | ||
49 | BDRVQEDState *s = opaque; | ||
50 | int ret; | ||
51 | @@ -XXX,XX +XXX,XX @@ static BDRVQEDState *acb_to_s(QEDAIOCB *acb) | ||
52 | * This function reads qiov->size bytes starting at pos from the backing file. | ||
53 | * If there is no backing file then zeroes are read. | ||
54 | */ | ||
55 | -static int qed_read_backing_file(BDRVQEDState *s, uint64_t pos, | ||
56 | - QEMUIOVector *qiov, | ||
57 | - QEMUIOVector **backing_qiov) | ||
58 | +static int coroutine_fn qed_read_backing_file(BDRVQEDState *s, uint64_t pos, | ||
59 | + QEMUIOVector *qiov, | ||
60 | + QEMUIOVector **backing_qiov) | ||
61 | { | ||
62 | uint64_t backing_length = 0; | ||
63 | size_t size; | ||
64 | @@ -XXX,XX +XXX,XX @@ static int qed_read_backing_file(BDRVQEDState *s, uint64_t pos, | ||
65 | * @len: Number of bytes | ||
66 | * @offset: Byte offset in image file | ||
67 | */ | ||
68 | -static int qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos, | ||
69 | - uint64_t len, uint64_t offset) | ||
70 | +static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s, | ||
71 | + uint64_t pos, uint64_t len, | ||
72 | + uint64_t offset) | ||
73 | { | ||
74 | QEMUIOVector qiov; | ||
75 | QEMUIOVector *backing_qiov = NULL; | ||
76 | @@ -XXX,XX +XXX,XX @@ out: | ||
77 | * The cluster offset may be an allocated byte offset in the image file, the | ||
78 | * zero cluster marker, or the unallocated cluster marker. | ||
79 | */ | ||
80 | -static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index, | ||
81 | - unsigned int n, uint64_t cluster) | ||
82 | +static void coroutine_fn qed_update_l2_table(BDRVQEDState *s, QEDTable *table, | ||
83 | + int index, unsigned int n, | ||
84 | + uint64_t cluster) | ||
85 | { | ||
86 | int i; | ||
87 | for (i = index; i < index + n; i++) { | ||
88 | @@ -XXX,XX +XXX,XX @@ static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index, | ||
89 | } | ||
90 | } | ||
91 | |||
92 | -static void qed_aio_complete(QEDAIOCB *acb) | ||
93 | +static void coroutine_fn qed_aio_complete(QEDAIOCB *acb) | ||
94 | { | ||
95 | BDRVQEDState *s = acb_to_s(acb); | ||
96 | |||
97 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete(QEDAIOCB *acb) | ||
98 | /** | ||
99 | * Update L1 table with new L2 table offset and write it out | ||
100 | */ | ||
101 | -static int qed_aio_write_l1_update(QEDAIOCB *acb) | ||
102 | +static int coroutine_fn qed_aio_write_l1_update(QEDAIOCB *acb) | ||
103 | { | ||
104 | BDRVQEDState *s = acb_to_s(acb); | ||
105 | CachedL2Table *l2_table = acb->request.l2_table; | ||
106 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_l1_update(QEDAIOCB *acb) | ||
107 | /** | ||
108 | * Update L2 table with new cluster offsets and write them out | ||
109 | */ | ||
110 | -static int qed_aio_write_l2_update(QEDAIOCB *acb, uint64_t offset) | ||
111 | +static int coroutine_fn qed_aio_write_l2_update(QEDAIOCB *acb, uint64_t offset) | ||
112 | { | ||
113 | BDRVQEDState *s = acb_to_s(acb); | ||
114 | bool need_alloc = acb->find_cluster_ret == QED_CLUSTER_L1; | ||
115 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_l2_update(QEDAIOCB *acb, uint64_t offset) | ||
116 | /** | ||
117 | * Write data to the image file | ||
118 | */ | ||
119 | -static int qed_aio_write_main(QEDAIOCB *acb) | ||
120 | +static int coroutine_fn qed_aio_write_main(QEDAIOCB *acb) | ||
121 | { | ||
122 | BDRVQEDState *s = acb_to_s(acb); | ||
123 | uint64_t offset = acb->cur_cluster + | ||
124 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_main(QEDAIOCB *acb) | ||
125 | /** | ||
126 | * Populate untouched regions of new data cluster | ||
127 | */ | ||
128 | -static int qed_aio_write_cow(QEDAIOCB *acb) | ||
129 | +static int coroutine_fn qed_aio_write_cow(QEDAIOCB *acb) | ||
130 | { | ||
131 | BDRVQEDState *s = acb_to_s(acb); | ||
132 | uint64_t start, len, offset; | ||
133 | @@ -XXX,XX +XXX,XX @@ static bool qed_should_set_need_check(BDRVQEDState *s) | ||
134 | * | ||
135 | * This path is taken when writing to previously unallocated clusters. | ||
136 | */ | ||
137 | -static int qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
138 | +static int coroutine_fn qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
139 | { | ||
140 | BDRVQEDState *s = acb_to_s(acb); | ||
141 | int ret; | ||
142 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
143 | * | ||
144 | * This path is taken when writing to already allocated clusters. | ||
145 | */ | ||
146 | -static int qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | ||
147 | +static int coroutine_fn qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, | ||
148 | + size_t len) | ||
149 | { | ||
150 | /* Allocate buffer for zero writes */ | ||
151 | if (acb->flags & QED_AIOCB_ZERO) { | ||
152 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | ||
153 | * @offset: Cluster offset in bytes | ||
154 | * @len: Length in bytes | ||
155 | */ | ||
156 | -static int qed_aio_write_data(void *opaque, int ret, | ||
157 | - uint64_t offset, size_t len) | ||
158 | +static int coroutine_fn qed_aio_write_data(void *opaque, int ret, | ||
159 | + uint64_t offset, size_t len) | ||
160 | { | ||
161 | QEDAIOCB *acb = opaque; | ||
162 | |||
163 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_data(void *opaque, int ret, | ||
164 | * @offset: Cluster offset in bytes | ||
165 | * @len: Length in bytes | ||
166 | */ | ||
167 | -static int qed_aio_read_data(void *opaque, int ret, uint64_t offset, size_t len) | ||
168 | +static int coroutine_fn qed_aio_read_data(void *opaque, int ret, | ||
169 | + uint64_t offset, size_t len) | ||
170 | { | ||
171 | QEDAIOCB *acb = opaque; | ||
172 | BDRVQEDState *s = acb_to_s(acb); | ||
173 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_read_data(void *opaque, int ret, uint64_t offset, size_t len) | ||
174 | /** | ||
175 | * Begin next I/O or complete the request | ||
176 | */ | ||
177 | -static int qed_aio_next_io(QEDAIOCB *acb) | ||
178 | +static int coroutine_fn qed_aio_next_io(QEDAIOCB *acb) | ||
179 | { | ||
180 | BDRVQEDState *s = acb_to_s(acb); | ||
181 | uint64_t offset; | ||
182 | diff --git a/block/qed.h b/block/qed.h | ||
183 | index XXXXXXX..XXXXXXX 100644 | 1035 | index XXXXXXX..XXXXXXX 100644 |
184 | --- a/block/qed.h | 1036 | --- a/tests/qtest/meson.build |
185 | +++ b/block/qed.h | 1037 | +++ b/tests/qtest/meson.build |
186 | @@ -XXX,XX +XXX,XX @@ int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request, | 1038 | @@ -XXX,XX +XXX,XX @@ if have_virtfs |
187 | /** | 1039 | qos_test_ss.add(files('virtio-9p-test.c')) |
188 | * Cluster functions | 1040 | endif |
189 | */ | 1041 | qos_test_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-test.c')) |
190 | -int qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | 1042 | +if have_vhost_user_blk_server |
191 | - size_t *len, uint64_t *img_offset); | 1043 | + qos_test_ss.add(files('vhost-user-blk-test.c')) |
192 | +int coroutine_fn qed_find_cluster(BDRVQEDState *s, QEDRequest *request, | 1044 | +endif |
193 | + uint64_t pos, size_t *len, | 1045 | |
194 | + uint64_t *img_offset); | 1046 | tpmemu_files = ['tpm-emu.c', 'tpm-util.c', 'tpm-tests.c'] |
195 | 1047 | ||
196 | /** | 1048 | @@ -XXX,XX +XXX,XX @@ foreach dir : target_dirs |
197 | * Consistency check | 1049 | endif |
1050 | qtest_env.set('G_TEST_DBUS_DAEMON', meson.source_root() / 'tests/dbus-vmstate-daemon.sh') | ||
1051 | qtest_env.set('QTEST_QEMU_BINARY', './qemu-system-' + target_base) | ||
1052 | + qtest_env.set('QTEST_QEMU_STORAGE_DAEMON_BINARY', './storage-daemon/qemu-storage-daemon') | ||
1053 | |||
1054 | foreach test : target_qtests | ||
1055 | # Executables are shared across targets, declare them only the first time we | ||
198 | -- | 1056 | -- |
199 | 1.8.3.1 | 1057 | 2.29.2 |
200 | 1058 | ||
201 | 1059 | diff view generated by jsdifflib |
1 | Don't recurse into qed_aio_next_io() and qed_aio_complete() here, but | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | just return an error code and let the caller handle it. | ||
3 | 2 | ||
3 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
4 | Message-Id: <20210223144653.811468-7-stefanha@redhat.com> | ||
4 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
5 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | --- | 6 | --- |
7 | block/qed.c | 43 ++++++++++++++++++++----------------------- | 7 | tests/qtest/vhost-user-blk-test.c | 81 +++++++++++++++++++++++++++++-- |
8 | 1 file changed, 20 insertions(+), 23 deletions(-) | 8 | 1 file changed, 76 insertions(+), 5 deletions(-) |
9 | 9 | ||
10 | diff --git a/block/qed.c b/block/qed.c | 10 | diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c |
11 | index XXXXXXX..XXXXXXX 100644 | 11 | index XXXXXXX..XXXXXXX 100644 |
12 | --- a/block/qed.c | 12 | --- a/tests/qtest/vhost-user-blk-test.c |
13 | +++ b/block/qed.c | 13 | +++ b/tests/qtest/vhost-user-blk-test.c |
14 | @@ -XXX,XX +XXX,XX @@ static bool qed_should_set_need_check(BDRVQEDState *s) | 14 | @@ -XXX,XX +XXX,XX @@ static void pci_hotplug(void *obj, void *data, QGuestAllocator *t_alloc) |
15 | * | 15 | qpci_unplug_acpi_device_test(qts, "drv1", PCI_SLOT_HP); |
16 | * This path is taken when writing to previously unallocated clusters. | 16 | } |
17 | */ | 17 | |
18 | -static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | 18 | +static void multiqueue(void *obj, void *data, QGuestAllocator *t_alloc) |
19 | +static int qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | 19 | +{ |
20 | + QVirtioPCIDevice *pdev1 = obj; | ||
21 | + QVirtioDevice *dev1 = &pdev1->vdev; | ||
22 | + QVirtioPCIDevice *pdev8; | ||
23 | + QVirtioDevice *dev8; | ||
24 | + QTestState *qts = pdev1->pdev->bus->qts; | ||
25 | + uint64_t features; | ||
26 | + uint16_t num_queues; | ||
27 | + | ||
28 | + /* | ||
29 | + * The primary device has 1 queue and VIRTIO_BLK_F_MQ is not enabled. The | ||
30 | + * VIRTIO specification allows VIRTIO_BLK_F_MQ to be enabled when there is | ||
31 | + * only 1 virtqueue, but --device vhost-user-blk-pci doesn't do this (which | ||
32 | + * is also spec-compliant). | ||
33 | + */ | ||
34 | + features = qvirtio_get_features(dev1); | ||
35 | + g_assert_cmpint(features & (1u << VIRTIO_BLK_F_MQ), ==, 0); | ||
36 | + features = features & ~(QVIRTIO_F_BAD_FEATURE | | ||
37 | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | | ||
38 | + (1u << VIRTIO_F_NOTIFY_ON_EMPTY) | | ||
39 | + (1u << VIRTIO_BLK_F_SCSI)); | ||
40 | + qvirtio_set_features(dev1, features); | ||
41 | + | ||
42 | + /* Hotplug a secondary device with 8 queues */ | ||
43 | + qtest_qmp_device_add(qts, "vhost-user-blk-pci", "drv1", | ||
44 | + "{'addr': %s, 'chardev': 'char2', 'num-queues': 8}", | ||
45 | + stringify(PCI_SLOT_HP) ".0"); | ||
46 | + | ||
47 | + pdev8 = virtio_pci_new(pdev1->pdev->bus, | ||
48 | + &(QPCIAddress) { | ||
49 | + .devfn = QPCI_DEVFN(PCI_SLOT_HP, 0) | ||
50 | + }); | ||
51 | + g_assert_nonnull(pdev8); | ||
52 | + g_assert_cmpint(pdev8->vdev.device_type, ==, VIRTIO_ID_BLOCK); | ||
53 | + | ||
54 | + qos_object_start_hw(&pdev8->obj); | ||
55 | + | ||
56 | + dev8 = &pdev8->vdev; | ||
57 | + features = qvirtio_get_features(dev8); | ||
58 | + g_assert_cmpint(features & (1u << VIRTIO_BLK_F_MQ), | ||
59 | + ==, | ||
60 | + (1u << VIRTIO_BLK_F_MQ)); | ||
61 | + features = features & ~(QVIRTIO_F_BAD_FEATURE | | ||
62 | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | | ||
63 | + (1u << VIRTIO_F_NOTIFY_ON_EMPTY) | | ||
64 | + (1u << VIRTIO_BLK_F_SCSI) | | ||
65 | + (1u << VIRTIO_BLK_F_MQ)); | ||
66 | + qvirtio_set_features(dev8, features); | ||
67 | + | ||
68 | + num_queues = qvirtio_config_readw(dev8, | ||
69 | + offsetof(struct virtio_blk_config, num_queues)); | ||
70 | + g_assert_cmpint(num_queues, ==, 8); | ||
71 | + | ||
72 | + qvirtio_pci_device_disable(pdev8); | ||
73 | + qos_object_destroy(&pdev8->obj); | ||
74 | + | ||
75 | + /* unplug secondary disk */ | ||
76 | + qpci_unplug_acpi_device_test(qts, "drv1", PCI_SLOT_HP); | ||
77 | +} | ||
78 | + | ||
79 | /* | ||
80 | * Check that setting the vring addr on a non-existent virtqueue does | ||
81 | * not crash. | ||
82 | @@ -XXX,XX +XXX,XX @@ static void quit_storage_daemon(void *data) | ||
83 | g_free(data); | ||
84 | } | ||
85 | |||
86 | -static void start_vhost_user_blk(GString *cmd_line, int vus_instances) | ||
87 | +static void start_vhost_user_blk(GString *cmd_line, int vus_instances, | ||
88 | + int num_queues) | ||
20 | { | 89 | { |
21 | BDRVQEDState *s = acb_to_s(acb); | 90 | const char *vhost_user_blk_bin = qtest_qemu_storage_daemon_binary(); |
22 | int ret; | 91 | int i; |
23 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | 92 | @@ -XXX,XX +XXX,XX @@ static void start_vhost_user_blk(GString *cmd_line, int vus_instances) |
24 | } | 93 | g_string_append_printf(storage_daemon_command, |
25 | if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs) || | 94 | "--blockdev driver=file,node-name=disk%d,filename=%s " |
26 | s->allocating_write_reqs_plugged) { | 95 | "--export type=vhost-user-blk,id=disk%d,addr.type=unix,addr.path=%s," |
27 | - return; /* wait for existing request to finish */ | 96 | - "node-name=disk%i,writable=on ", |
28 | + return -EINPROGRESS; /* wait for existing request to finish */ | 97 | - i, img_path, i, sock_path, i); |
29 | } | 98 | + "node-name=disk%i,writable=on,num-queues=%d ", |
30 | 99 | + i, img_path, i, sock_path, i, num_queues); | |
31 | acb->cur_nclusters = qed_bytes_to_clusters(s, | 100 | |
32 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | 101 | g_string_append_printf(cmd_line, "-chardev socket,id=char%d,path=%s ", |
33 | if (acb->flags & QED_AIOCB_ZERO) { | 102 | i + 1, sock_path); |
34 | /* Skip ahead if the clusters are already zero */ | 103 | @@ -XXX,XX +XXX,XX @@ static void start_vhost_user_blk(GString *cmd_line, int vus_instances) |
35 | if (acb->find_cluster_ret == QED_CLUSTER_ZERO) { | 104 | |
36 | - qed_aio_start_io(acb); | 105 | static void *vhost_user_blk_test_setup(GString *cmd_line, void *arg) |
37 | - return; | 106 | { |
38 | + return 0; | 107 | - start_vhost_user_blk(cmd_line, 1); |
39 | } | 108 | + start_vhost_user_blk(cmd_line, 1, 1); |
40 | } else { | 109 | return arg; |
41 | acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters); | ||
42 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
43 | s->header.features |= QED_F_NEED_CHECK; | ||
44 | ret = qed_write_header(s); | ||
45 | if (ret < 0) { | ||
46 | - qed_aio_complete(acb, ret); | ||
47 | - return; | ||
48 | + return ret; | ||
49 | } | ||
50 | } | ||
51 | |||
52 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
53 | ret = qed_aio_write_cow(acb); | ||
54 | } | ||
55 | if (ret < 0) { | ||
56 | - qed_aio_complete(acb, ret); | ||
57 | - return; | ||
58 | + return ret; | ||
59 | } | ||
60 | - qed_aio_next_io(acb, 0); | ||
61 | + return 0; | ||
62 | } | 110 | } |
63 | 111 | ||
64 | /** | 112 | @@ -XXX,XX +XXX,XX @@ static void *vhost_user_blk_test_setup(GString *cmd_line, void *arg) |
65 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | 113 | static void *vhost_user_blk_hotplug_test_setup(GString *cmd_line, void *arg) |
66 | * | ||
67 | * This path is taken when writing to already allocated clusters. | ||
68 | */ | ||
69 | -static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | ||
70 | +static int qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | ||
71 | { | 114 | { |
72 | - int ret; | 115 | /* "-chardev socket,id=char2" is used for pci_hotplug*/ |
73 | - | 116 | - start_vhost_user_blk(cmd_line, 2); |
74 | /* Allocate buffer for zero writes */ | 117 | + start_vhost_user_blk(cmd_line, 2, 1); |
75 | if (acb->flags & QED_AIOCB_ZERO) { | 118 | + return arg; |
76 | struct iovec *iov = acb->qiov->iov; | 119 | +} |
77 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | 120 | + |
78 | if (!iov->iov_base) { | 121 | +static void *vhost_user_blk_multiqueue_test_setup(GString *cmd_line, void *arg) |
79 | iov->iov_base = qemu_try_blockalign(acb->common.bs, iov->iov_len); | 122 | +{ |
80 | if (iov->iov_base == NULL) { | 123 | + start_vhost_user_blk(cmd_line, 2, 8); |
81 | - qed_aio_complete(acb, -ENOMEM); | 124 | return arg; |
82 | - return; | ||
83 | + return -ENOMEM; | ||
84 | } | ||
85 | memset(iov->iov_base, 0, iov->iov_len); | ||
86 | } | ||
87 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | ||
88 | qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len); | ||
89 | |||
90 | /* Do the actual write */ | ||
91 | - ret = qed_aio_write_main(acb); | ||
92 | - if (ret < 0) { | ||
93 | - qed_aio_complete(acb, ret); | ||
94 | - return; | ||
95 | - } | ||
96 | - qed_aio_next_io(acb, 0); | ||
97 | + return qed_aio_write_main(acb); | ||
98 | } | 125 | } |
99 | 126 | ||
100 | /** | 127 | @@ -XXX,XX +XXX,XX @@ static void register_vhost_user_blk_test(void) |
101 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_data(void *opaque, int ret, | 128 | |
102 | 129 | opts.before = vhost_user_blk_hotplug_test_setup; | |
103 | switch (ret) { | 130 | qos_add_test("hotplug", "vhost-user-blk-pci", pci_hotplug, &opts); |
104 | case QED_CLUSTER_FOUND: | ||
105 | - qed_aio_write_inplace(acb, offset, len); | ||
106 | + ret = qed_aio_write_inplace(acb, offset, len); | ||
107 | break; | ||
108 | |||
109 | case QED_CLUSTER_L2: | ||
110 | case QED_CLUSTER_L1: | ||
111 | case QED_CLUSTER_ZERO: | ||
112 | - qed_aio_write_alloc(acb, len); | ||
113 | + ret = qed_aio_write_alloc(acb, len); | ||
114 | break; | ||
115 | |||
116 | default: | ||
117 | - qed_aio_complete(acb, ret); | ||
118 | + assert(ret < 0); | ||
119 | break; | ||
120 | } | ||
121 | + | 131 | + |
122 | + if (ret < 0) { | 132 | + opts.before = vhost_user_blk_multiqueue_test_setup; |
123 | + if (ret != -EINPROGRESS) { | 133 | + qos_add_test("multiqueue", "vhost-user-blk-pci", multiqueue, &opts); |
124 | + qed_aio_complete(acb, ret); | ||
125 | + } | ||
126 | + return; | ||
127 | + } | ||
128 | + qed_aio_next_io(acb, 0); | ||
129 | } | 134 | } |
130 | 135 | ||
131 | /** | 136 | libqos_init(register_vhost_user_blk_test); |
132 | -- | 137 | -- |
133 | 1.8.3.1 | 138 | 2.29.2 |
134 | 139 | ||
135 | 140 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Calling aio_poll() directly may have been fine previously, but this is | 3 | The config->blk_size field is little-endian. Use the native-endian |
4 | the future, man! The difference between an aio_poll() loop and | 4 | blk_size variable to avoid double byteswapping. |
5 | BDRV_POLL_WHILE() is that BDRV_POLL_WHILE() releases the AioContext | ||
6 | around aio_poll(). | ||
7 | 5 | ||
8 | This allows the IOThread to run fd handlers or BHs to complete the | 6 | Fixes: 11f60f7eaee2630dd6fa0c3a8c49f792e46c4cf1 ("block/export: make vhost-user-blk config space little-endian") |
9 | request. Failure to release the AioContext causes deadlocks. | ||
10 | |||
11 | Using BDRV_POLL_WHILE() partially fixes a 'savevm' hang with -object | ||
12 | iothread. | ||
13 | |||
14 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
15 | Reviewed-by: Eric Blake <eblake@redhat.com> | 8 | Message-Id: <20210223144653.811468-8-stefanha@redhat.com> |
16 | Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> | ||
17 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 9 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
18 | --- | 10 | --- |
19 | block/io.c | 4 +--- | 11 | block/export/vhost-user-blk-server.c | 2 +- |
20 | 1 file changed, 1 insertion(+), 3 deletions(-) | 12 | 1 file changed, 1 insertion(+), 1 deletion(-) |
21 | 13 | ||
22 | diff --git a/block/io.c b/block/io.c | 14 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
23 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
24 | --- a/block/io.c | 16 | --- a/block/export/vhost-user-blk-server.c |
25 | +++ b/block/io.c | 17 | +++ b/block/export/vhost-user-blk-server.c |
26 | @@ -XXX,XX +XXX,XX @@ bdrv_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos, | 18 | @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, |
27 | Coroutine *co = qemu_coroutine_create(bdrv_co_rw_vmstate_entry, &data); | 19 | config->num_queues = cpu_to_le16(num_queues); |
28 | 20 | config->max_discard_sectors = cpu_to_le32(32768); | |
29 | bdrv_coroutine_enter(bs, co); | 21 | config->max_discard_seg = cpu_to_le32(1); |
30 | - while (data.ret == -EINPROGRESS) { | 22 | - config->discard_sector_alignment = cpu_to_le32(config->blk_size >> 9); |
31 | - aio_poll(bdrv_get_aio_context(bs), true); | 23 | + config->discard_sector_alignment = cpu_to_le32(blk_size >> 9); |
32 | - } | 24 | config->max_write_zeroes_sectors = cpu_to_le32(32768); |
33 | + BDRV_POLL_WHILE(bs, data.ret == -EINPROGRESS); | 25 | config->max_write_zeroes_seg = cpu_to_le32(1); |
34 | return data.ret; | ||
35 | } | ||
36 | } | 26 | } |
37 | -- | 27 | -- |
38 | 1.8.3.1 | 28 | 2.29.2 |
39 | 29 | ||
40 | 30 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | blk/bdrv_drain_all() only takes effect for a single instant and then | 3 | Use VIRTIO_BLK_SECTOR_BITS and VIRTIO_BLK_SECTOR_SIZE when dealing with |
4 | resumes block jobs, guest devices, and other external clients like the | 4 | virtio-blk sector numbers. Although the values happen to be the same as |
5 | NBD server. This can be handy when performing a synchronous drain | 5 | BDRV_SECTOR_BITS and BDRV_SECTOR_SIZE, they are conceptually different. |
6 | before terminating the program, for example. | 6 | This makes it clearer when we are dealing with virtio-blk sector units. |
7 | 7 | ||
8 | Monitor commands usually need to quiesce I/O across an entire code | 8 | Use VIRTIO_BLK_SECTOR_BITS in vu_blk_initialize_config(). Later patches |
9 | region so blk/bdrv_drain_all() is not suitable. They must use | 9 | will use it the new constants the virtqueue request processing code |
10 | bdrv_drain_all_begin/end() to mark the region. This prevents new I/O | 10 | path. |
11 | requests from slipping in or worse - block jobs completing and modifying | ||
12 | the graph. | ||
13 | 11 | ||
14 | I audited other blk/bdrv_drain_all() callers but did not find anything | 12 | Suggested-by: Max Reitz <mreitz@redhat.com> |
15 | that needs a similar fix. This patch fixes the savevm/loadvm commands. | ||
16 | Although I haven't encountered a read world issue this makes the code | ||
17 | safer. | ||
18 | |||
19 | Suggested-by: Kevin Wolf <kwolf@redhat.com> | ||
20 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 13 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
21 | Reviewed-by: Eric Blake <eblake@redhat.com> | 14 | Message-Id: <20210223144653.811468-9-stefanha@redhat.com> |
22 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 15 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
23 | --- | 16 | --- |
24 | migration/savevm.c | 18 +++++++++++++++--- | 17 | block/export/vhost-user-blk-server.c | 15 ++++++++++++--- |
25 | 1 file changed, 15 insertions(+), 3 deletions(-) | 18 | 1 file changed, 12 insertions(+), 3 deletions(-) |
26 | 19 | ||
27 | diff --git a/migration/savevm.c b/migration/savevm.c | 20 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
28 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
29 | --- a/migration/savevm.c | 22 | --- a/block/export/vhost-user-blk-server.c |
30 | +++ b/migration/savevm.c | 23 | +++ b/block/export/vhost-user-blk-server.c |
31 | @@ -XXX,XX +XXX,XX @@ int save_snapshot(const char *name, Error **errp) | 24 | @@ -XXX,XX +XXX,XX @@ |
25 | #include "sysemu/block-backend.h" | ||
26 | #include "util/block-helpers.h" | ||
27 | |||
28 | +/* | ||
29 | + * Sector units are 512 bytes regardless of the | ||
30 | + * virtio_blk_config->blk_size value. | ||
31 | + */ | ||
32 | +#define VIRTIO_BLK_SECTOR_BITS 9 | ||
33 | +#define VIRTIO_BLK_SECTOR_SIZE (1ull << VIRTIO_BLK_SECTOR_BITS) | ||
34 | + | ||
35 | enum { | ||
36 | VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1, | ||
37 | }; | ||
38 | @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, | ||
39 | uint32_t blk_size, | ||
40 | uint16_t num_queues) | ||
41 | { | ||
42 | - config->capacity = cpu_to_le64(bdrv_getlength(bs) >> BDRV_SECTOR_BITS); | ||
43 | + config->capacity = | ||
44 | + cpu_to_le64(bdrv_getlength(bs) >> VIRTIO_BLK_SECTOR_BITS); | ||
45 | config->blk_size = cpu_to_le32(blk_size); | ||
46 | config->size_max = cpu_to_le32(0); | ||
47 | config->seg_max = cpu_to_le32(128 - 2); | ||
48 | @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, | ||
49 | config->num_queues = cpu_to_le16(num_queues); | ||
50 | config->max_discard_sectors = cpu_to_le32(32768); | ||
51 | config->max_discard_seg = cpu_to_le32(1); | ||
52 | - config->discard_sector_alignment = cpu_to_le32(blk_size >> 9); | ||
53 | + config->discard_sector_alignment = | ||
54 | + cpu_to_le32(blk_size >> VIRTIO_BLK_SECTOR_BITS); | ||
55 | config->max_write_zeroes_sectors = cpu_to_le32(32768); | ||
56 | config->max_write_zeroes_seg = cpu_to_le32(1); | ||
57 | } | ||
58 | @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, | ||
59 | if (vu_opts->has_logical_block_size) { | ||
60 | logical_block_size = vu_opts->logical_block_size; | ||
61 | } else { | ||
62 | - logical_block_size = BDRV_SECTOR_SIZE; | ||
63 | + logical_block_size = VIRTIO_BLK_SECTOR_SIZE; | ||
32 | } | 64 | } |
33 | vm_stop(RUN_STATE_SAVE_VM); | 65 | check_block_size(exp->id, "logical-block-size", logical_block_size, |
34 | 66 | &local_err); | |
35 | + bdrv_drain_all_begin(); | ||
36 | + | ||
37 | aio_context_acquire(aio_context); | ||
38 | |||
39 | memset(sn, 0, sizeof(*sn)); | ||
40 | @@ -XXX,XX +XXX,XX @@ int save_snapshot(const char *name, Error **errp) | ||
41 | if (aio_context) { | ||
42 | aio_context_release(aio_context); | ||
43 | } | ||
44 | + | ||
45 | + bdrv_drain_all_end(); | ||
46 | + | ||
47 | if (saved_vm_running) { | ||
48 | vm_start(); | ||
49 | } | ||
50 | @@ -XXX,XX +XXX,XX @@ int load_snapshot(const char *name, Error **errp) | ||
51 | } | ||
52 | |||
53 | /* Flush all IO requests so they don't interfere with the new state. */ | ||
54 | - bdrv_drain_all(); | ||
55 | + bdrv_drain_all_begin(); | ||
56 | |||
57 | ret = bdrv_all_goto_snapshot(name, &bs); | ||
58 | if (ret < 0) { | ||
59 | error_setg(errp, "Error %d while activating snapshot '%s' on '%s'", | ||
60 | ret, name, bdrv_get_device_name(bs)); | ||
61 | - return ret; | ||
62 | + goto err_drain; | ||
63 | } | ||
64 | |||
65 | /* restore the VM state */ | ||
66 | f = qemu_fopen_bdrv(bs_vm_state, 0); | ||
67 | if (!f) { | ||
68 | error_setg(errp, "Could not open VM state file"); | ||
69 | - return -EINVAL; | ||
70 | + ret = -EINVAL; | ||
71 | + goto err_drain; | ||
72 | } | ||
73 | |||
74 | qemu_system_reset(SHUTDOWN_CAUSE_NONE); | ||
75 | @@ -XXX,XX +XXX,XX @@ int load_snapshot(const char *name, Error **errp) | ||
76 | ret = qemu_loadvm_state(f); | ||
77 | aio_context_release(aio_context); | ||
78 | |||
79 | + bdrv_drain_all_end(); | ||
80 | + | ||
81 | migration_incoming_state_destroy(); | ||
82 | if (ret < 0) { | ||
83 | error_setg(errp, "Error %d while loading VM state", ret); | ||
84 | @@ -XXX,XX +XXX,XX @@ int load_snapshot(const char *name, Error **errp) | ||
85 | } | ||
86 | |||
87 | return 0; | ||
88 | + | ||
89 | +err_drain: | ||
90 | + bdrv_drain_all_end(); | ||
91 | + return ret; | ||
92 | } | ||
93 | |||
94 | void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev) | ||
95 | -- | 67 | -- |
96 | 1.8.3.1 | 68 | 2.29.2 |
97 | 69 | ||
98 | 70 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | migration_incoming_state_destroy() uses qemu_fclose() on the vmstate | 3 | The driver is supposed to honor the blk_size field but the protocol |
4 | file. Make sure to call it inside an AioContext acquire/release region. | 4 | still uses 512-byte sector numbers. It is incorrect to multiply |
5 | req->sector_num by blk_size. | ||
5 | 6 | ||
6 | This fixes an 'qemu: qemu_mutex_unlock: Operation not permitted' abort | 7 | VIRTIO 1.1 5.2.5 Device Initialization says: |
7 | in loadvm. | ||
8 | 8 | ||
9 | This patch closes the vmstate file before ending the drained region. | 9 | blk_size can be read to determine the optimal sector size for the |
10 | Previously we closed the vmstate file after ending the drained region. | 10 | driver to use. This does not affect the units used in the protocol |
11 | The order does not matter. | 11 | (always 512 bytes), but awareness of the correct value can affect |
12 | performance. | ||
12 | 13 | ||
14 | Fixes: 3578389bcf76c824a5d82e6586a6f0c71e56f2aa ("block/export: vhost-user block device backend server") | ||
13 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 15 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
16 | Message-Id: <20210223144653.811468-10-stefanha@redhat.com> | ||
14 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 17 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
15 | --- | 18 | --- |
16 | migration/savevm.c | 2 +- | 19 | block/export/vhost-user-blk-server.c | 2 +- |
17 | 1 file changed, 1 insertion(+), 1 deletion(-) | 20 | 1 file changed, 1 insertion(+), 1 deletion(-) |
18 | 21 | ||
19 | diff --git a/migration/savevm.c b/migration/savevm.c | 22 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
20 | index XXXXXXX..XXXXXXX 100644 | 23 | index XXXXXXX..XXXXXXX 100644 |
21 | --- a/migration/savevm.c | 24 | --- a/block/export/vhost-user-blk-server.c |
22 | +++ b/migration/savevm.c | 25 | +++ b/block/export/vhost-user-blk-server.c |
23 | @@ -XXX,XX +XXX,XX @@ int load_snapshot(const char *name, Error **errp) | 26 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_blk_virtio_process_req(void *opaque) |
24 | 27 | break; | |
25 | aio_context_acquire(aio_context); | 28 | } |
26 | ret = qemu_loadvm_state(f); | 29 | |
27 | + migration_incoming_state_destroy(); | 30 | - int64_t offset = req->sector_num * vexp->blk_size; |
28 | aio_context_release(aio_context); | 31 | + int64_t offset = req->sector_num << VIRTIO_BLK_SECTOR_BITS; |
29 | 32 | QEMUIOVector qiov; | |
30 | bdrv_drain_all_end(); | 33 | if (is_write) { |
31 | 34 | qemu_iovec_init_external(&qiov, out_iov, out_num); | |
32 | - migration_incoming_state_destroy(); | ||
33 | if (ret < 0) { | ||
34 | error_setg(errp, "Error %d while loading VM state", ret); | ||
35 | return ret; | ||
36 | -- | 35 | -- |
37 | 1.8.3.1 | 36 | 2.29.2 |
38 | 37 | ||
39 | 38 | diff view generated by jsdifflib |
1 | Most of the qed code is now synchronous and matches the coroutine model. | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | One notable exception is the serialisation between requests which can | ||
3 | still schedule a callback. Before we can replace this with coroutine | ||
4 | locks, let's convert the driver's external interfaces to the coroutine | ||
5 | versions. | ||
6 | 2 | ||
7 | We need to be careful to handle both requests that call the completion | 3 | Validate discard/write zeroes the same way we do for virtio-blk. Some of |
8 | callback directly from the calling coroutine (i.e. fully synchronous | 4 | these checks are mandated by the VIRTIO specification, others are |
9 | code) and requests that involve some callback, so that we need to yield | 5 | internal to QEMU. |
10 | and wait for the completion callback coming from outside the coroutine. | ||
11 | 6 | ||
7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | Message-Id: <20210223144653.811468-11-stefanha@redhat.com> | ||
12 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 9 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
13 | Reviewed-by: Manos Pitsidianakis <el13635@mail.ntua.gr> | ||
14 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
15 | --- | 10 | --- |
16 | block/qed.c | 97 ++++++++++++++++++++++++++----------------------------------- | 11 | block/export/vhost-user-blk-server.c | 116 +++++++++++++++++++++------ |
17 | 1 file changed, 42 insertions(+), 55 deletions(-) | 12 | 1 file changed, 93 insertions(+), 23 deletions(-) |
18 | 13 | ||
19 | diff --git a/block/qed.c b/block/qed.c | 14 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
20 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
21 | --- a/block/qed.c | 16 | --- a/block/export/vhost-user-blk-server.c |
22 | +++ b/block/qed.c | 17 | +++ b/block/export/vhost-user-blk-server.c |
23 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb) | 18 | @@ -XXX,XX +XXX,XX @@ |
24 | } | 19 | |
20 | enum { | ||
21 | VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1, | ||
22 | + VHOST_USER_BLK_MAX_DISCARD_SECTORS = 32768, | ||
23 | + VHOST_USER_BLK_MAX_WRITE_ZEROES_SECTORS = 32768, | ||
24 | }; | ||
25 | struct virtio_blk_inhdr { | ||
26 | unsigned char status; | ||
27 | @@ -XXX,XX +XXX,XX @@ static void vu_blk_req_complete(VuBlkReq *req) | ||
28 | free(req); | ||
25 | } | 29 | } |
26 | 30 | ||
27 | -static BlockAIOCB *qed_aio_setup(BlockDriverState *bs, | 31 | +static bool vu_blk_sect_range_ok(VuBlkExport *vexp, uint64_t sector, |
28 | - int64_t sector_num, | 32 | + size_t size) |
29 | - QEMUIOVector *qiov, int nb_sectors, | 33 | +{ |
30 | - BlockCompletionFunc *cb, | 34 | + uint64_t nb_sectors = size >> BDRV_SECTOR_BITS; |
31 | - void *opaque, int flags) | 35 | + uint64_t total_sectors; |
32 | +typedef struct QEDRequestCo { | ||
33 | + Coroutine *co; | ||
34 | + bool done; | ||
35 | + int ret; | ||
36 | +} QEDRequestCo; | ||
37 | + | 36 | + |
38 | +static void qed_co_request_cb(void *opaque, int ret) | 37 | + if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) { |
39 | { | 38 | + return false; |
40 | - QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, cb, opaque); | 39 | + } |
41 | + QEDRequestCo *co = opaque; | 40 | + if ((sector << VIRTIO_BLK_SECTOR_BITS) % vexp->blk_size) { |
42 | 41 | + return false; | |
43 | - trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors, | 42 | + } |
44 | - opaque, flags); | 43 | + blk_get_geometry(vexp->export.blk, &total_sectors); |
45 | + co->done = true; | 44 | + if (sector > total_sectors || nb_sectors > total_sectors - sector) { |
46 | + co->ret = ret; | 45 | + return false; |
47 | + qemu_coroutine_enter_if_inactive(co->co); | 46 | + } |
47 | + return true; | ||
48 | +} | 48 | +} |
49 | + | 49 | + |
50 | +static int coroutine_fn qed_co_request(BlockDriverState *bs, int64_t sector_num, | 50 | static int coroutine_fn |
51 | + QEMUIOVector *qiov, int nb_sectors, | 51 | -vu_blk_discard_write_zeroes(BlockBackend *blk, struct iovec *iov, |
52 | + int flags) | 52 | +vu_blk_discard_write_zeroes(VuBlkExport *vexp, struct iovec *iov, |
53 | +{ | 53 | uint32_t iovcnt, uint32_t type) |
54 | + QEDRequestCo co = { | 54 | { |
55 | + .co = qemu_coroutine_self(), | 55 | + BlockBackend *blk = vexp->export.blk; |
56 | + .done = false, | 56 | struct virtio_blk_discard_write_zeroes desc; |
57 | + }; | 57 | - ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); |
58 | + QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, qed_co_request_cb, &co); | 58 | + ssize_t size; |
59 | + uint64_t sector; | ||
60 | + uint32_t num_sectors; | ||
61 | + uint32_t max_sectors; | ||
62 | + uint32_t flags; | ||
63 | + int bytes; | ||
59 | + | 64 | + |
60 | + trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors, &co, flags); | 65 | + /* Only one desc is currently supported */ |
61 | 66 | + if (unlikely(iov_size(iov, iovcnt) > sizeof(desc))) { | |
62 | acb->flags = flags; | 67 | + return VIRTIO_BLK_S_UNSUPP; |
63 | acb->qiov = qiov; | ||
64 | @@ -XXX,XX +XXX,XX @@ static BlockAIOCB *qed_aio_setup(BlockDriverState *bs, | ||
65 | |||
66 | /* Start request */ | ||
67 | qed_aio_start_io(acb); | ||
68 | - return &acb->common; | ||
69 | -} | ||
70 | |||
71 | -static BlockAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs, | ||
72 | - int64_t sector_num, | ||
73 | - QEMUIOVector *qiov, int nb_sectors, | ||
74 | - BlockCompletionFunc *cb, | ||
75 | - void *opaque) | ||
76 | -{ | ||
77 | - return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0); | ||
78 | + if (!co.done) { | ||
79 | + qemu_coroutine_yield(); | ||
80 | + } | 68 | + } |
81 | + | 69 | + |
82 | + return co.ret; | 70 | + size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); |
71 | if (unlikely(size != sizeof(desc))) { | ||
72 | - error_report("Invalid size %zd, expect %zu", size, sizeof(desc)); | ||
73 | - return -EINVAL; | ||
74 | + error_report("Invalid size %zd, expected %zu", size, sizeof(desc)); | ||
75 | + return VIRTIO_BLK_S_IOERR; | ||
76 | } | ||
77 | |||
78 | - uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, | ||
79 | - le32_to_cpu(desc.num_sectors) << 9 }; | ||
80 | - if (type == VIRTIO_BLK_T_DISCARD) { | ||
81 | - if (blk_co_pdiscard(blk, range[0], range[1]) == 0) { | ||
82 | - return 0; | ||
83 | + sector = le64_to_cpu(desc.sector); | ||
84 | + num_sectors = le32_to_cpu(desc.num_sectors); | ||
85 | + flags = le32_to_cpu(desc.flags); | ||
86 | + max_sectors = (type == VIRTIO_BLK_T_WRITE_ZEROES) ? | ||
87 | + VHOST_USER_BLK_MAX_WRITE_ZEROES_SECTORS : | ||
88 | + VHOST_USER_BLK_MAX_DISCARD_SECTORS; | ||
89 | + | ||
90 | + /* This check ensures that 'bytes' fits in an int */ | ||
91 | + if (unlikely(num_sectors > max_sectors)) { | ||
92 | + return VIRTIO_BLK_S_IOERR; | ||
93 | + } | ||
94 | + | ||
95 | + bytes = num_sectors << VIRTIO_BLK_SECTOR_BITS; | ||
96 | + | ||
97 | + if (unlikely(!vu_blk_sect_range_ok(vexp, sector, bytes))) { | ||
98 | + return VIRTIO_BLK_S_IOERR; | ||
99 | + } | ||
100 | + | ||
101 | + /* | ||
102 | + * The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for discard | ||
103 | + * and write zeroes commands if any unknown flag is set. | ||
104 | + */ | ||
105 | + if (unlikely(flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) { | ||
106 | + return VIRTIO_BLK_S_UNSUPP; | ||
107 | + } | ||
108 | + | ||
109 | + if (type == VIRTIO_BLK_T_WRITE_ZEROES) { | ||
110 | + int blk_flags = 0; | ||
111 | + | ||
112 | + if (flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) { | ||
113 | + blk_flags |= BDRV_REQ_MAY_UNMAP; | ||
114 | + } | ||
115 | + | ||
116 | + if (blk_co_pwrite_zeroes(blk, sector << VIRTIO_BLK_SECTOR_BITS, | ||
117 | + bytes, blk_flags) == 0) { | ||
118 | + return VIRTIO_BLK_S_OK; | ||
119 | } | ||
120 | - } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { | ||
121 | - if (blk_co_pwrite_zeroes(blk, range[0], range[1], 0) == 0) { | ||
122 | - return 0; | ||
123 | + } else if (type == VIRTIO_BLK_T_DISCARD) { | ||
124 | + /* | ||
125 | + * The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for | ||
126 | + * discard commands if the unmap flag is set. | ||
127 | + */ | ||
128 | + if (unlikely(flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) { | ||
129 | + return VIRTIO_BLK_S_UNSUPP; | ||
130 | + } | ||
131 | + | ||
132 | + if (blk_co_pdiscard(blk, sector << VIRTIO_BLK_SECTOR_BITS, | ||
133 | + bytes) == 0) { | ||
134 | + return VIRTIO_BLK_S_OK; | ||
135 | } | ||
136 | } | ||
137 | |||
138 | - return -EINVAL; | ||
139 | + return VIRTIO_BLK_S_IOERR; | ||
83 | } | 140 | } |
84 | 141 | ||
85 | -static BlockAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs, | 142 | static void coroutine_fn vu_blk_virtio_process_req(void *opaque) |
86 | - int64_t sector_num, | 143 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_blk_virtio_process_req(void *opaque) |
87 | - QEMUIOVector *qiov, int nb_sectors, | 144 | } |
88 | - BlockCompletionFunc *cb, | 145 | case VIRTIO_BLK_T_DISCARD: |
89 | - void *opaque) | 146 | case VIRTIO_BLK_T_WRITE_ZEROES: { |
90 | +static int coroutine_fn bdrv_qed_co_readv(BlockDriverState *bs, | 147 | - int rc; |
91 | + int64_t sector_num, int nb_sectors, | 148 | - |
92 | + QEMUIOVector *qiov) | 149 | if (!vexp->writable) { |
93 | { | 150 | req->in->status = VIRTIO_BLK_S_IOERR; |
94 | - return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, | 151 | break; |
95 | - opaque, QED_AIOCB_WRITE); | 152 | } |
96 | + return qed_co_request(bs, sector_num, qiov, nb_sectors, 0); | 153 | |
154 | - rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type); | ||
155 | - if (rc == 0) { | ||
156 | - req->in->status = VIRTIO_BLK_S_OK; | ||
157 | - } else { | ||
158 | - req->in->status = VIRTIO_BLK_S_IOERR; | ||
159 | - } | ||
160 | + req->in->status = vu_blk_discard_write_zeroes(vexp, out_iov, out_num, | ||
161 | + type); | ||
162 | break; | ||
163 | } | ||
164 | default: | ||
165 | @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, | ||
166 | config->min_io_size = cpu_to_le16(1); | ||
167 | config->opt_io_size = cpu_to_le32(1); | ||
168 | config->num_queues = cpu_to_le16(num_queues); | ||
169 | - config->max_discard_sectors = cpu_to_le32(32768); | ||
170 | + config->max_discard_sectors = | ||
171 | + cpu_to_le32(VHOST_USER_BLK_MAX_DISCARD_SECTORS); | ||
172 | config->max_discard_seg = cpu_to_le32(1); | ||
173 | config->discard_sector_alignment = | ||
174 | cpu_to_le32(blk_size >> VIRTIO_BLK_SECTOR_BITS); | ||
175 | - config->max_write_zeroes_sectors = cpu_to_le32(32768); | ||
176 | + config->max_write_zeroes_sectors | ||
177 | + = cpu_to_le32(VHOST_USER_BLK_MAX_WRITE_ZEROES_SECTORS); | ||
178 | config->max_write_zeroes_seg = cpu_to_le32(1); | ||
97 | } | 179 | } |
98 | 180 | ||
99 | -typedef struct { | ||
100 | - Coroutine *co; | ||
101 | - int ret; | ||
102 | - bool done; | ||
103 | -} QEDWriteZeroesCB; | ||
104 | - | ||
105 | -static void coroutine_fn qed_co_pwrite_zeroes_cb(void *opaque, int ret) | ||
106 | +static int coroutine_fn bdrv_qed_co_writev(BlockDriverState *bs, | ||
107 | + int64_t sector_num, int nb_sectors, | ||
108 | + QEMUIOVector *qiov) | ||
109 | { | ||
110 | - QEDWriteZeroesCB *cb = opaque; | ||
111 | - | ||
112 | - cb->done = true; | ||
113 | - cb->ret = ret; | ||
114 | - if (cb->co) { | ||
115 | - aio_co_wake(cb->co); | ||
116 | - } | ||
117 | + return qed_co_request(bs, sector_num, qiov, nb_sectors, QED_AIOCB_WRITE); | ||
118 | } | ||
119 | |||
120 | static int coroutine_fn bdrv_qed_co_pwrite_zeroes(BlockDriverState *bs, | ||
121 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_pwrite_zeroes(BlockDriverState *bs, | ||
122 | int count, | ||
123 | BdrvRequestFlags flags) | ||
124 | { | ||
125 | - BlockAIOCB *blockacb; | ||
126 | BDRVQEDState *s = bs->opaque; | ||
127 | - QEDWriteZeroesCB cb = { .done = false }; | ||
128 | QEMUIOVector qiov; | ||
129 | struct iovec iov; | ||
130 | |||
131 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_pwrite_zeroes(BlockDriverState *bs, | ||
132 | iov.iov_len = count; | ||
133 | |||
134 | qemu_iovec_init_external(&qiov, &iov, 1); | ||
135 | - blockacb = qed_aio_setup(bs, offset >> BDRV_SECTOR_BITS, &qiov, | ||
136 | - count >> BDRV_SECTOR_BITS, | ||
137 | - qed_co_pwrite_zeroes_cb, &cb, | ||
138 | - QED_AIOCB_WRITE | QED_AIOCB_ZERO); | ||
139 | - if (!blockacb) { | ||
140 | - return -EIO; | ||
141 | - } | ||
142 | - if (!cb.done) { | ||
143 | - cb.co = qemu_coroutine_self(); | ||
144 | - qemu_coroutine_yield(); | ||
145 | - } | ||
146 | - assert(cb.done); | ||
147 | - return cb.ret; | ||
148 | + return qed_co_request(bs, offset >> BDRV_SECTOR_BITS, &qiov, | ||
149 | + count >> BDRV_SECTOR_BITS, | ||
150 | + QED_AIOCB_WRITE | QED_AIOCB_ZERO); | ||
151 | } | ||
152 | |||
153 | static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset, Error **errp) | ||
154 | @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_qed = { | ||
155 | .bdrv_create = bdrv_qed_create, | ||
156 | .bdrv_has_zero_init = bdrv_has_zero_init_1, | ||
157 | .bdrv_co_get_block_status = bdrv_qed_co_get_block_status, | ||
158 | - .bdrv_aio_readv = bdrv_qed_aio_readv, | ||
159 | - .bdrv_aio_writev = bdrv_qed_aio_writev, | ||
160 | + .bdrv_co_readv = bdrv_qed_co_readv, | ||
161 | + .bdrv_co_writev = bdrv_qed_co_writev, | ||
162 | .bdrv_co_pwrite_zeroes = bdrv_qed_co_pwrite_zeroes, | ||
163 | .bdrv_truncate = bdrv_qed_truncate, | ||
164 | .bdrv_getlength = bdrv_qed_getlength, | ||
165 | -- | 181 | -- |
166 | 1.8.3.1 | 182 | 2.29.2 |
167 | 183 | ||
168 | 184 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | ||
---|---|---|---|
2 | |||
3 | Exercise input validation code paths in | ||
4 | block/export/vhost-user-blk-server.c. | ||
5 | |||
6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
7 | Message-Id: <20210223144653.811468-12-stefanha@redhat.com> | ||
1 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
2 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
3 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
4 | --- | 9 | --- |
5 | block/qed-cluster.c | 94 ++++++++++++++++++----------------------------------- | 10 | tests/qtest/vhost-user-blk-test.c | 124 ++++++++++++++++++++++++++++++ |
6 | block/qed-table.c | 15 +++------ | 11 | 1 file changed, 124 insertions(+) |
7 | block/qed.h | 3 +- | ||
8 | 3 files changed, 36 insertions(+), 76 deletions(-) | ||
9 | 12 | ||
10 | diff --git a/block/qed-cluster.c b/block/qed-cluster.c | 13 | diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c |
11 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
12 | --- a/block/qed-cluster.c | 15 | --- a/tests/qtest/vhost-user-blk-test.c |
13 | +++ b/block/qed-cluster.c | 16 | +++ b/tests/qtest/vhost-user-blk-test.c |
14 | @@ -XXX,XX +XXX,XX @@ static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s, | 17 | @@ -XXX,XX +XXX,XX @@ static uint64_t virtio_blk_request(QGuestAllocator *alloc, QVirtioDevice *d, |
15 | return i - index; | 18 | return addr; |
16 | } | 19 | } |
17 | 20 | ||
18 | -typedef struct { | 21 | +static void test_invalid_discard_write_zeroes(QVirtioDevice *dev, |
19 | - BDRVQEDState *s; | 22 | + QGuestAllocator *alloc, |
20 | - uint64_t pos; | 23 | + QTestState *qts, |
21 | - size_t len; | 24 | + QVirtQueue *vq, |
22 | - | 25 | + uint32_t type) |
23 | - QEDRequest *request; | 26 | +{ |
24 | - | 27 | + QVirtioBlkReq req; |
25 | - /* User callback */ | 28 | + struct virtio_blk_discard_write_zeroes dwz_hdr; |
26 | - QEDFindClusterFunc *cb; | 29 | + struct virtio_blk_discard_write_zeroes dwz_hdr2[2]; |
27 | - void *opaque; | 30 | + uint64_t req_addr; |
28 | -} QEDFindClusterCB; | 31 | + uint32_t free_head; |
29 | - | 32 | + uint8_t status; |
30 | -static void qed_find_cluster_cb(void *opaque, int ret) | 33 | + |
31 | -{ | 34 | + /* More than one dwz is not supported */ |
32 | - QEDFindClusterCB *find_cluster_cb = opaque; | 35 | + req.type = type; |
33 | - BDRVQEDState *s = find_cluster_cb->s; | 36 | + req.data = (char *) dwz_hdr2; |
34 | - QEDRequest *request = find_cluster_cb->request; | 37 | + dwz_hdr2[0].sector = 0; |
35 | - uint64_t offset = 0; | 38 | + dwz_hdr2[0].num_sectors = 1; |
36 | - size_t len = 0; | 39 | + dwz_hdr2[0].flags = 0; |
37 | - unsigned int index; | 40 | + dwz_hdr2[1].sector = 1; |
38 | - unsigned int n; | 41 | + dwz_hdr2[1].num_sectors = 1; |
39 | - | 42 | + dwz_hdr2[1].flags = 0; |
40 | - qed_acquire(s); | 43 | + |
41 | - if (ret) { | 44 | + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr2[0]); |
42 | - goto out; | 45 | + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr2[1]); |
43 | - } | 46 | + |
44 | - | 47 | + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr2)); |
45 | - index = qed_l2_index(s, find_cluster_cb->pos); | 48 | + |
46 | - n = qed_bytes_to_clusters(s, | 49 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); |
47 | - qed_offset_into_cluster(s, find_cluster_cb->pos) + | 50 | + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr2), false, true); |
48 | - find_cluster_cb->len); | 51 | + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr2), 1, true, |
49 | - n = qed_count_contiguous_clusters(s, request->l2_table->table, | 52 | + false); |
50 | - index, n, &offset); | 53 | + |
51 | - | 54 | + qvirtqueue_kick(qts, dev, vq, free_head); |
52 | - if (qed_offset_is_unalloc_cluster(offset)) { | 55 | + |
53 | - ret = QED_CLUSTER_L2; | 56 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, |
54 | - } else if (qed_offset_is_zero_cluster(offset)) { | 57 | + QVIRTIO_BLK_TIMEOUT_US); |
55 | - ret = QED_CLUSTER_ZERO; | 58 | + status = readb(req_addr + 16 + sizeof(dwz_hdr2)); |
56 | - } else if (qed_check_cluster_offset(s, offset)) { | 59 | + g_assert_cmpint(status, ==, VIRTIO_BLK_S_UNSUPP); |
57 | - ret = QED_CLUSTER_FOUND; | 60 | + |
58 | - } else { | 61 | + guest_free(alloc, req_addr); |
59 | - ret = -EINVAL; | 62 | + |
60 | - } | 63 | + /* num_sectors must be less than config->max_write_zeroes_sectors */ |
61 | - | 64 | + req.type = type; |
62 | - len = MIN(find_cluster_cb->len, n * s->header.cluster_size - | 65 | + req.data = (char *) &dwz_hdr; |
63 | - qed_offset_into_cluster(s, find_cluster_cb->pos)); | 66 | + dwz_hdr.sector = 0; |
64 | - | 67 | + dwz_hdr.num_sectors = 0xffffffff; |
65 | -out: | 68 | + dwz_hdr.flags = 0; |
66 | - find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len); | 69 | + |
67 | - qed_release(s); | 70 | + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); |
68 | - g_free(find_cluster_cb); | 71 | + |
69 | -} | 72 | + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); |
70 | - | 73 | + |
71 | /** | 74 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); |
72 | * Find the offset of a data cluster | 75 | + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true); |
73 | * | 76 | + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), 1, true, |
74 | @@ -XXX,XX +XXX,XX @@ out: | 77 | + false); |
75 | void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | 78 | + |
76 | size_t len, QEDFindClusterFunc *cb, void *opaque) | 79 | + qvirtqueue_kick(qts, dev, vq, free_head); |
80 | + | ||
81 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
82 | + QVIRTIO_BLK_TIMEOUT_US); | ||
83 | + status = readb(req_addr + 16 + sizeof(dwz_hdr)); | ||
84 | + g_assert_cmpint(status, ==, VIRTIO_BLK_S_IOERR); | ||
85 | + | ||
86 | + guest_free(alloc, req_addr); | ||
87 | + | ||
88 | + /* sector must be less than the device capacity */ | ||
89 | + req.type = type; | ||
90 | + req.data = (char *) &dwz_hdr; | ||
91 | + dwz_hdr.sector = TEST_IMAGE_SIZE / 512 + 1; | ||
92 | + dwz_hdr.num_sectors = 1; | ||
93 | + dwz_hdr.flags = 0; | ||
94 | + | ||
95 | + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); | ||
96 | + | ||
97 | + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); | ||
98 | + | ||
99 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
100 | + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true); | ||
101 | + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), 1, true, | ||
102 | + false); | ||
103 | + | ||
104 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
105 | + | ||
106 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
107 | + QVIRTIO_BLK_TIMEOUT_US); | ||
108 | + status = readb(req_addr + 16 + sizeof(dwz_hdr)); | ||
109 | + g_assert_cmpint(status, ==, VIRTIO_BLK_S_IOERR); | ||
110 | + | ||
111 | + guest_free(alloc, req_addr); | ||
112 | + | ||
113 | + /* reserved flag bits must be zero */ | ||
114 | + req.type = type; | ||
115 | + req.data = (char *) &dwz_hdr; | ||
116 | + dwz_hdr.sector = 0; | ||
117 | + dwz_hdr.num_sectors = 1; | ||
118 | + dwz_hdr.flags = ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP; | ||
119 | + | ||
120 | + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); | ||
121 | + | ||
122 | + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); | ||
123 | + | ||
124 | + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); | ||
125 | + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true); | ||
126 | + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), 1, true, | ||
127 | + false); | ||
128 | + | ||
129 | + qvirtqueue_kick(qts, dev, vq, free_head); | ||
130 | + | ||
131 | + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, | ||
132 | + QVIRTIO_BLK_TIMEOUT_US); | ||
133 | + status = readb(req_addr + 16 + sizeof(dwz_hdr)); | ||
134 | + g_assert_cmpint(status, ==, VIRTIO_BLK_S_UNSUPP); | ||
135 | + | ||
136 | + guest_free(alloc, req_addr); | ||
137 | +} | ||
138 | + | ||
139 | /* Returns the request virtqueue so the caller can perform further tests */ | ||
140 | static QVirtQueue *test_basic(QVirtioDevice *dev, QGuestAllocator *alloc) | ||
77 | { | 141 | { |
78 | - QEDFindClusterCB *find_cluster_cb; | 142 | @@ -XXX,XX +XXX,XX @@ static QVirtQueue *test_basic(QVirtioDevice *dev, QGuestAllocator *alloc) |
79 | uint64_t l2_offset; | 143 | g_free(data); |
80 | + uint64_t offset = 0; | 144 | |
81 | + unsigned int index; | 145 | guest_free(alloc, req_addr); |
82 | + unsigned int n; | 146 | + |
83 | + int ret; | 147 | + test_invalid_discard_write_zeroes(dev, alloc, qts, vq, |
84 | 148 | + VIRTIO_BLK_T_WRITE_ZEROES); | |
85 | /* Limit length to L2 boundary. Requests are broken up at the L2 boundary | ||
86 | * so that a request acts on one L2 table at a time. | ||
87 | @@ -XXX,XX +XXX,XX @@ void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
88 | return; | ||
89 | } | 149 | } |
90 | 150 | ||
91 | - find_cluster_cb = g_malloc(sizeof(*find_cluster_cb)); | 151 | if (features & (1u << VIRTIO_BLK_F_DISCARD)) { |
92 | - find_cluster_cb->s = s; | 152 | @@ -XXX,XX +XXX,XX @@ static QVirtQueue *test_basic(QVirtioDevice *dev, QGuestAllocator *alloc) |
93 | - find_cluster_cb->pos = pos; | 153 | g_assert_cmpint(status, ==, 0); |
94 | - find_cluster_cb->len = len; | 154 | |
95 | - find_cluster_cb->cb = cb; | 155 | guest_free(alloc, req_addr); |
96 | - find_cluster_cb->opaque = opaque; | ||
97 | - find_cluster_cb->request = request; | ||
98 | + ret = qed_read_l2_table(s, request, l2_offset); | ||
99 | + qed_acquire(s); | ||
100 | + if (ret) { | ||
101 | + goto out; | ||
102 | + } | ||
103 | + | 156 | + |
104 | + index = qed_l2_index(s, pos); | 157 | + test_invalid_discard_write_zeroes(dev, alloc, qts, vq, |
105 | + n = qed_bytes_to_clusters(s, | 158 | + VIRTIO_BLK_T_DISCARD); |
106 | + qed_offset_into_cluster(s, pos) + len); | ||
107 | + n = qed_count_contiguous_clusters(s, request->l2_table->table, | ||
108 | + index, n, &offset); | ||
109 | + | ||
110 | + if (qed_offset_is_unalloc_cluster(offset)) { | ||
111 | + ret = QED_CLUSTER_L2; | ||
112 | + } else if (qed_offset_is_zero_cluster(offset)) { | ||
113 | + ret = QED_CLUSTER_ZERO; | ||
114 | + } else if (qed_check_cluster_offset(s, offset)) { | ||
115 | + ret = QED_CLUSTER_FOUND; | ||
116 | + } else { | ||
117 | + ret = -EINVAL; | ||
118 | + } | ||
119 | + | ||
120 | + len = MIN(len, | ||
121 | + n * s->header.cluster_size - qed_offset_into_cluster(s, pos)); | ||
122 | |||
123 | - qed_read_l2_table(s, request, l2_offset, | ||
124 | - qed_find_cluster_cb, find_cluster_cb); | ||
125 | +out: | ||
126 | + cb(opaque, ret, offset, len); | ||
127 | + qed_release(s); | ||
128 | } | ||
129 | diff --git a/block/qed-table.c b/block/qed-table.c | ||
130 | index XXXXXXX..XXXXXXX 100644 | ||
131 | --- a/block/qed-table.c | ||
132 | +++ b/block/qed-table.c | ||
133 | @@ -XXX,XX +XXX,XX @@ int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index, | ||
134 | return ret; | ||
135 | } | ||
136 | |||
137 | -void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset, | ||
138 | - BlockCompletionFunc *cb, void *opaque) | ||
139 | +int qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset) | ||
140 | { | ||
141 | int ret; | ||
142 | |||
143 | @@ -XXX,XX +XXX,XX @@ void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset, | ||
144 | /* Check for cached L2 entry */ | ||
145 | request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset); | ||
146 | if (request->l2_table) { | ||
147 | - cb(opaque, 0); | ||
148 | - return; | ||
149 | + return 0; | ||
150 | } | 159 | } |
151 | 160 | ||
152 | request->l2_table = qed_alloc_l2_cache_entry(&s->l2_cache); | 161 | if (features & (1u << VIRTIO_F_ANY_LAYOUT)) { |
153 | @@ -XXX,XX +XXX,XX @@ void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset, | ||
154 | } | ||
155 | qed_release(s); | ||
156 | |||
157 | - cb(opaque, ret); | ||
158 | + return ret; | ||
159 | } | ||
160 | |||
161 | int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset) | ||
162 | { | ||
163 | - int ret = -EINPROGRESS; | ||
164 | - | ||
165 | - qed_read_l2_table(s, request, offset, qed_sync_cb, &ret); | ||
166 | - BDRV_POLL_WHILE(s->bs, ret == -EINPROGRESS); | ||
167 | - | ||
168 | - return ret; | ||
169 | + return qed_read_l2_table(s, request, offset); | ||
170 | } | ||
171 | |||
172 | void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, | ||
173 | diff --git a/block/qed.h b/block/qed.h | ||
174 | index XXXXXXX..XXXXXXX 100644 | ||
175 | --- a/block/qed.h | ||
176 | +++ b/block/qed.h | ||
177 | @@ -XXX,XX +XXX,XX @@ int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index, | ||
178 | unsigned int n); | ||
179 | int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, | ||
180 | uint64_t offset); | ||
181 | -void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset, | ||
182 | - BlockCompletionFunc *cb, void *opaque); | ||
183 | +int qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset); | ||
184 | void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, | ||
185 | unsigned int index, unsigned int n, bool flush, | ||
186 | BlockCompletionFunc *cb, void *opaque); | ||
187 | -- | 162 | -- |
188 | 1.8.3.1 | 163 | 2.29.2 |
189 | 164 | ||
190 | 165 | diff view generated by jsdifflib |
1 | From: Alberto Garcia <berto@igalia.com> | 1 | From: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | If the guest tries to write data that results on the allocation of a | 3 | Check that the sector number and byte count are valid. |
4 | new cluster, instead of writing the guest data first and then the data | ||
5 | from the COW regions, write everything together using one single I/O | ||
6 | operation. | ||
7 | 4 | ||
8 | This can improve the write performance by 25% or more, depending on | 5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
9 | several factors such as the media type, the cluster size and the I/O | 6 | Message-Id: <20210223144653.811468-13-stefanha@redhat.com> |
10 | request size. | ||
11 | |||
12 | Signed-off-by: Alberto Garcia <berto@igalia.com> | ||
13 | Reviewed-by: Kevin Wolf <kwolf@redhat.com> | ||
14 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 7 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
15 | --- | 8 | --- |
16 | block/qcow2-cluster.c | 40 ++++++++++++++++++++++++-------- | 9 | block/export/vhost-user-blk-server.c | 19 ++++++++++++++++--- |
17 | block/qcow2.c | 64 +++++++++++++++++++++++++++++++++++++++++++-------- | 10 | 1 file changed, 16 insertions(+), 3 deletions(-) |
18 | block/qcow2.h | 7 ++++++ | ||
19 | 3 files changed, 91 insertions(+), 20 deletions(-) | ||
20 | 11 | ||
21 | diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c | 12 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
22 | index XXXXXXX..XXXXXXX 100644 | 13 | index XXXXXXX..XXXXXXX 100644 |
23 | --- a/block/qcow2-cluster.c | 14 | --- a/block/export/vhost-user-blk-server.c |
24 | +++ b/block/qcow2-cluster.c | 15 | +++ b/block/export/vhost-user-blk-server.c |
25 | @@ -XXX,XX +XXX,XX @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | 16 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_blk_virtio_process_req(void *opaque) |
26 | assert(start->nb_bytes <= UINT_MAX - end->nb_bytes); | 17 | switch (type & ~VIRTIO_BLK_T_BARRIER) { |
27 | assert(start->nb_bytes + end->nb_bytes <= UINT_MAX - data_bytes); | 18 | case VIRTIO_BLK_T_IN: |
28 | assert(start->offset + start->nb_bytes <= end->offset); | 19 | case VIRTIO_BLK_T_OUT: { |
29 | + assert(!m->data_qiov || m->data_qiov->size == data_bytes); | 20 | + QEMUIOVector qiov; |
30 | 21 | + int64_t offset; | |
31 | if (start->nb_bytes == 0 && end->nb_bytes == 0) { | 22 | ssize_t ret = 0; |
32 | return 0; | 23 | bool is_write = type & VIRTIO_BLK_T_OUT; |
33 | @@ -XXX,XX +XXX,XX @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | 24 | req->sector_num = le64_to_cpu(req->out.sector); |
34 | /* The part of the buffer where the end region is located */ | 25 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_blk_virtio_process_req(void *opaque) |
35 | end_buffer = start_buffer + buffer_size - end->nb_bytes; | 26 | break; |
36 | |||
37 | - qemu_iovec_init(&qiov, 1); | ||
38 | + qemu_iovec_init(&qiov, 2 + (m->data_qiov ? m->data_qiov->niov : 0)); | ||
39 | |||
40 | qemu_co_mutex_unlock(&s->lock); | ||
41 | /* First we read the existing data from both COW regions. We | ||
42 | @@ -XXX,XX +XXX,XX @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | ||
43 | } | 27 | } |
44 | } | 28 | |
45 | 29 | - int64_t offset = req->sector_num << VIRTIO_BLK_SECTOR_BITS; | |
46 | - /* And now we can write everything */ | 30 | - QEMUIOVector qiov; |
47 | - qemu_iovec_reset(&qiov); | 31 | if (is_write) { |
48 | - qemu_iovec_add(&qiov, start_buffer, start->nb_bytes); | 32 | qemu_iovec_init_external(&qiov, out_iov, out_num); |
49 | - ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov); | 33 | - ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0); |
50 | - if (ret < 0) { | 34 | } else { |
51 | - goto fail; | 35 | qemu_iovec_init_external(&qiov, in_iov, in_num); |
52 | + /* And now we can write everything. If we have the guest data we | ||
53 | + * can write everything in one single operation */ | ||
54 | + if (m->data_qiov) { | ||
55 | + qemu_iovec_reset(&qiov); | ||
56 | + if (start->nb_bytes) { | ||
57 | + qemu_iovec_add(&qiov, start_buffer, start->nb_bytes); | ||
58 | + } | ||
59 | + qemu_iovec_concat(&qiov, m->data_qiov, 0, data_bytes); | ||
60 | + if (end->nb_bytes) { | ||
61 | + qemu_iovec_add(&qiov, end_buffer, end->nb_bytes); | ||
62 | + } | ||
63 | + /* NOTE: we have a write_aio blkdebug event here followed by | ||
64 | + * a cow_write one in do_perform_cow_write(), but there's only | ||
65 | + * one single I/O operation */ | ||
66 | + BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); | ||
67 | + ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov); | ||
68 | + } else { | ||
69 | + /* If there's no guest data then write both COW regions separately */ | ||
70 | + qemu_iovec_reset(&qiov); | ||
71 | + qemu_iovec_add(&qiov, start_buffer, start->nb_bytes); | ||
72 | + ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov); | ||
73 | + if (ret < 0) { | ||
74 | + goto fail; | ||
75 | + } | 36 | + } |
76 | + | 37 | + |
77 | + qemu_iovec_reset(&qiov); | 38 | + if (unlikely(!vu_blk_sect_range_ok(vexp, |
78 | + qemu_iovec_add(&qiov, end_buffer, end->nb_bytes); | 39 | + req->sector_num, |
79 | + ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, &qiov); | 40 | + qiov.size))) { |
80 | } | 41 | + req->in->status = VIRTIO_BLK_S_IOERR; |
81 | 42 | + break; | |
82 | - qemu_iovec_reset(&qiov); | ||
83 | - qemu_iovec_add(&qiov, end_buffer, end->nb_bytes); | ||
84 | - ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, &qiov); | ||
85 | fail: | ||
86 | qemu_co_mutex_lock(&s->lock); | ||
87 | |||
88 | diff --git a/block/qcow2.c b/block/qcow2.c | ||
89 | index XXXXXXX..XXXXXXX 100644 | ||
90 | --- a/block/qcow2.c | ||
91 | +++ b/block/qcow2.c | ||
92 | @@ -XXX,XX +XXX,XX @@ fail: | ||
93 | return ret; | ||
94 | } | ||
95 | |||
96 | +/* Check if it's possible to merge a write request with the writing of | ||
97 | + * the data from the COW regions */ | ||
98 | +static bool merge_cow(uint64_t offset, unsigned bytes, | ||
99 | + QEMUIOVector *hd_qiov, QCowL2Meta *l2meta) | ||
100 | +{ | ||
101 | + QCowL2Meta *m; | ||
102 | + | ||
103 | + for (m = l2meta; m != NULL; m = m->next) { | ||
104 | + /* If both COW regions are empty then there's nothing to merge */ | ||
105 | + if (m->cow_start.nb_bytes == 0 && m->cow_end.nb_bytes == 0) { | ||
106 | + continue; | ||
107 | + } | 43 | + } |
108 | + | 44 | + |
109 | + /* The data (middle) region must be immediately after the | 45 | + offset = req->sector_num << VIRTIO_BLK_SECTOR_BITS; |
110 | + * start region */ | ||
111 | + if (l2meta_cow_start(m) + m->cow_start.nb_bytes != offset) { | ||
112 | + continue; | ||
113 | + } | ||
114 | + | 46 | + |
115 | + /* The end region must be immediately after the data (middle) | 47 | + if (is_write) { |
116 | + * region */ | 48 | + ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0); |
117 | + if (m->offset + m->cow_end.offset != offset + bytes) { | 49 | + } else { |
118 | + continue; | 50 | ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0); |
119 | + } | ||
120 | + | ||
121 | + /* Make sure that adding both COW regions to the QEMUIOVector | ||
122 | + * does not exceed IOV_MAX */ | ||
123 | + if (hd_qiov->niov > IOV_MAX - 2) { | ||
124 | + continue; | ||
125 | + } | ||
126 | + | ||
127 | + m->data_qiov = hd_qiov; | ||
128 | + return true; | ||
129 | + } | ||
130 | + | ||
131 | + return false; | ||
132 | +} | ||
133 | + | ||
134 | static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, | ||
135 | uint64_t bytes, QEMUIOVector *qiov, | ||
136 | int flags) | ||
137 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, | ||
138 | goto fail; | ||
139 | } | 51 | } |
140 | 52 | if (ret >= 0) { | |
141 | - qemu_co_mutex_unlock(&s->lock); | ||
142 | - BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); | ||
143 | - trace_qcow2_writev_data(qemu_coroutine_self(), | ||
144 | - cluster_offset + offset_in_cluster); | ||
145 | - ret = bdrv_co_pwritev(bs->file, | ||
146 | - cluster_offset + offset_in_cluster, | ||
147 | - cur_bytes, &hd_qiov, 0); | ||
148 | - qemu_co_mutex_lock(&s->lock); | ||
149 | - if (ret < 0) { | ||
150 | - goto fail; | ||
151 | + /* If we need to do COW, check if it's possible to merge the | ||
152 | + * writing of the guest data together with that of the COW regions. | ||
153 | + * If it's not possible (or not necessary) then write the | ||
154 | + * guest data now. */ | ||
155 | + if (!merge_cow(offset, cur_bytes, &hd_qiov, l2meta)) { | ||
156 | + qemu_co_mutex_unlock(&s->lock); | ||
157 | + BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); | ||
158 | + trace_qcow2_writev_data(qemu_coroutine_self(), | ||
159 | + cluster_offset + offset_in_cluster); | ||
160 | + ret = bdrv_co_pwritev(bs->file, | ||
161 | + cluster_offset + offset_in_cluster, | ||
162 | + cur_bytes, &hd_qiov, 0); | ||
163 | + qemu_co_mutex_lock(&s->lock); | ||
164 | + if (ret < 0) { | ||
165 | + goto fail; | ||
166 | + } | ||
167 | } | ||
168 | |||
169 | while (l2meta != NULL) { | ||
170 | diff --git a/block/qcow2.h b/block/qcow2.h | ||
171 | index XXXXXXX..XXXXXXX 100644 | ||
172 | --- a/block/qcow2.h | ||
173 | +++ b/block/qcow2.h | ||
174 | @@ -XXX,XX +XXX,XX @@ typedef struct QCowL2Meta | ||
175 | */ | ||
176 | Qcow2COWRegion cow_end; | ||
177 | |||
178 | + /** | ||
179 | + * The I/O vector with the data from the actual guest write request. | ||
180 | + * If non-NULL, this is meant to be merged together with the data | ||
181 | + * from @cow_start and @cow_end into one single write operation. | ||
182 | + */ | ||
183 | + QEMUIOVector *data_qiov; | ||
184 | + | ||
185 | /** Pointer to next L2Meta of the same write request */ | ||
186 | struct QCowL2Meta *next; | ||
187 | |||
188 | -- | 53 | -- |
189 | 1.8.3.1 | 54 | 2.29.2 |
190 | 55 | ||
191 | 56 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
---|---|---|---|
2 | |||
3 | Rename bytes_covered_by_bitmap_cluster() to | ||
4 | bdrv_dirty_bitmap_serialization_coverage() and make it public. | ||
5 | It is needed as we are going to share it with bitmap loading in | ||
6 | parallels format. | ||
7 | |||
8 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
9 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
10 | Reviewed-by: Denis V. Lunev <den@openvz.org> | ||
11 | Message-Id: <20210224104707.88430-2-vsementsov@virtuozzo.com> | ||
1 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 12 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
2 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
3 | --- | 13 | --- |
4 | block/qed.c | 32 ++++++++++++-------------------- | 14 | include/block/dirty-bitmap.h | 2 ++ |
5 | 1 file changed, 12 insertions(+), 20 deletions(-) | 15 | block/dirty-bitmap.c | 13 +++++++++++++ |
16 | block/qcow2-bitmap.c | 16 ++-------------- | ||
17 | 3 files changed, 17 insertions(+), 14 deletions(-) | ||
6 | 18 | ||
7 | diff --git a/block/qed.c b/block/qed.c | 19 | diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h |
8 | index XXXXXXX..XXXXXXX 100644 | 20 | index XXXXXXX..XXXXXXX 100644 |
9 | --- a/block/qed.c | 21 | --- a/include/block/dirty-bitmap.h |
10 | +++ b/block/qed.c | 22 | +++ b/include/block/dirty-bitmap.h |
11 | @@ -XXX,XX +XXX,XX @@ int qed_write_header_sync(BDRVQEDState *s) | 23 | @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter); |
12 | * This function only updates known header fields in-place and does not affect | 24 | uint64_t bdrv_dirty_bitmap_serialization_size(const BdrvDirtyBitmap *bitmap, |
13 | * extra data after the QED header. | 25 | uint64_t offset, uint64_t bytes); |
14 | */ | 26 | uint64_t bdrv_dirty_bitmap_serialization_align(const BdrvDirtyBitmap *bitmap); |
15 | -static void qed_write_header(BDRVQEDState *s, BlockCompletionFunc cb, | 27 | +uint64_t bdrv_dirty_bitmap_serialization_coverage(int serialized_chunk_size, |
16 | - void *opaque) | 28 | + const BdrvDirtyBitmap *bitmap); |
17 | +static int qed_write_header(BDRVQEDState *s) | 29 | void bdrv_dirty_bitmap_serialize_part(const BdrvDirtyBitmap *bitmap, |
18 | { | 30 | uint8_t *buf, uint64_t offset, |
19 | /* We must write full sectors for O_DIRECT but cannot necessarily generate | 31 | uint64_t bytes); |
20 | * the data following the header if an unrecognized compat feature is | 32 | diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c |
21 | @@ -XXX,XX +XXX,XX @@ static void qed_write_header(BDRVQEDState *s, BlockCompletionFunc cb, | 33 | index XXXXXXX..XXXXXXX 100644 |
22 | ret = 0; | 34 | --- a/block/dirty-bitmap.c |
23 | out: | 35 | +++ b/block/dirty-bitmap.c |
24 | qemu_vfree(buf); | 36 | @@ -XXX,XX +XXX,XX @@ uint64_t bdrv_dirty_bitmap_serialization_align(const BdrvDirtyBitmap *bitmap) |
25 | - cb(opaque, ret); | 37 | return hbitmap_serialization_align(bitmap->bitmap); |
26 | + return ret; | ||
27 | } | 38 | } |
28 | 39 | ||
29 | static uint64_t qed_max_image_size(uint32_t cluster_size, uint32_t table_size) | 40 | +/* Return the disk size covered by a chunk of serialized bitmap data. */ |
30 | @@ -XXX,XX +XXX,XX @@ static void qed_unplug_allocating_write_reqs(BDRVQEDState *s) | 41 | +uint64_t bdrv_dirty_bitmap_serialization_coverage(int serialized_chunk_size, |
31 | } | 42 | + const BdrvDirtyBitmap *bitmap) |
43 | +{ | ||
44 | + uint64_t granularity = bdrv_dirty_bitmap_granularity(bitmap); | ||
45 | + uint64_t limit = granularity * (serialized_chunk_size << 3); | ||
46 | + | ||
47 | + assert(QEMU_IS_ALIGNED(limit, | ||
48 | + bdrv_dirty_bitmap_serialization_align(bitmap))); | ||
49 | + return limit; | ||
50 | +} | ||
51 | + | ||
52 | + | ||
53 | void bdrv_dirty_bitmap_serialize_part(const BdrvDirtyBitmap *bitmap, | ||
54 | uint8_t *buf, uint64_t offset, | ||
55 | uint64_t bytes) | ||
56 | diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c | ||
57 | index XXXXXXX..XXXXXXX 100644 | ||
58 | --- a/block/qcow2-bitmap.c | ||
59 | +++ b/block/qcow2-bitmap.c | ||
60 | @@ -XXX,XX +XXX,XX @@ static int free_bitmap_clusters(BlockDriverState *bs, Qcow2BitmapTable *tb) | ||
61 | return 0; | ||
32 | } | 62 | } |
33 | 63 | ||
34 | -static void qed_finish_clear_need_check(void *opaque, int ret) | 64 | -/* Return the disk size covered by a single qcow2 cluster of bitmap data. */ |
65 | -static uint64_t bytes_covered_by_bitmap_cluster(const BDRVQcow2State *s, | ||
66 | - const BdrvDirtyBitmap *bitmap) | ||
35 | -{ | 67 | -{ |
36 | - /* Do nothing */ | 68 | - uint64_t granularity = bdrv_dirty_bitmap_granularity(bitmap); |
69 | - uint64_t limit = granularity * (s->cluster_size << 3); | ||
70 | - | ||
71 | - assert(QEMU_IS_ALIGNED(limit, | ||
72 | - bdrv_dirty_bitmap_serialization_align(bitmap))); | ||
73 | - return limit; | ||
37 | -} | 74 | -} |
38 | - | 75 | - |
39 | -static void qed_flush_after_clear_need_check(void *opaque, int ret) | 76 | /* load_bitmap_data |
40 | -{ | 77 | * @bitmap_table entries must satisfy specification constraints. |
41 | - BDRVQEDState *s = opaque; | 78 | * @bitmap must be cleared */ |
42 | - | 79 | @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, |
43 | - bdrv_aio_flush(s->bs, qed_finish_clear_need_check, s); | ||
44 | - | ||
45 | - /* No need to wait until flush completes */ | ||
46 | - qed_unplug_allocating_write_reqs(s); | ||
47 | -} | ||
48 | - | ||
49 | static void qed_clear_need_check(void *opaque, int ret) | ||
50 | { | ||
51 | BDRVQEDState *s = opaque; | ||
52 | @@ -XXX,XX +XXX,XX @@ static void qed_clear_need_check(void *opaque, int ret) | ||
53 | } | 80 | } |
54 | 81 | ||
55 | s->header.features &= ~QED_F_NEED_CHECK; | 82 | buf = g_malloc(s->cluster_size); |
56 | - qed_write_header(s, qed_flush_after_clear_need_check, s); | 83 | - limit = bytes_covered_by_bitmap_cluster(s, bitmap); |
57 | + ret = qed_write_header(s); | 84 | + limit = bdrv_dirty_bitmap_serialization_coverage(s->cluster_size, bitmap); |
58 | + (void) ret; | 85 | for (i = 0, offset = 0; i < tab_size; ++i, offset += limit) { |
59 | + | 86 | uint64_t count = MIN(bm_size - offset, limit); |
60 | + qed_unplug_allocating_write_reqs(s); | 87 | uint64_t entry = bitmap_table[i]; |
61 | + | 88 | @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, |
62 | + ret = bdrv_flush(s->bs); | ||
63 | + (void) ret; | ||
64 | } | ||
65 | |||
66 | static void qed_need_check_timer_cb(void *opaque) | ||
67 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
68 | { | ||
69 | BDRVQEDState *s = acb_to_s(acb); | ||
70 | BlockCompletionFunc *cb; | ||
71 | + int ret; | ||
72 | |||
73 | /* Cancel timer when the first allocating request comes in */ | ||
74 | if (QSIMPLEQ_EMPTY(&s->allocating_write_reqs)) { | ||
75 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
76 | |||
77 | if (qed_should_set_need_check(s)) { | ||
78 | s->header.features |= QED_F_NEED_CHECK; | ||
79 | - qed_write_header(s, cb, acb); | ||
80 | + ret = qed_write_header(s); | ||
81 | + cb(acb, ret); | ||
82 | } else { | ||
83 | cb(acb, 0); | ||
84 | } | 89 | } |
90 | |||
91 | buf = g_malloc(s->cluster_size); | ||
92 | - limit = bytes_covered_by_bitmap_cluster(s, bitmap); | ||
93 | + limit = bdrv_dirty_bitmap_serialization_coverage(s->cluster_size, bitmap); | ||
94 | assert(DIV_ROUND_UP(bm_size, limit) == tb_size); | ||
95 | |||
96 | offset = 0; | ||
85 | -- | 97 | -- |
86 | 1.8.3.1 | 98 | 2.29.2 |
87 | 99 | ||
88 | 100 | diff view generated by jsdifflib |
1 | From: Alberto Garcia <berto@igalia.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Qcow2COWRegion has two attributes: | 3 | Actually L1 table entry offset is in 512 bytes sectors. Fix the spec. |
4 | 4 | ||
5 | - The offset of the COW region from the start of the first cluster | 5 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
6 | touched by the I/O request. Since it's always going to be positive | 6 | Message-Id: <20210224104707.88430-3-vsementsov@virtuozzo.com> |
7 | and the maximum request size is at most INT_MAX, we can use a | 7 | Reviewed-by: Denis V. Lunev <den@openvz.org> |
8 | regular unsigned int to store this offset. | ||
9 | |||
10 | - The size of the COW region in bytes. This is guaranteed to be >= 0, | ||
11 | so we should use an unsigned type instead. | ||
12 | |||
13 | In x86_64 this reduces the size of Qcow2COWRegion from 16 to 8 bytes. | ||
14 | It will also help keep some assertions simpler now that we know that | ||
15 | there are no negative numbers. | ||
16 | |||
17 | The prototype of do_perform_cow() is also updated to reflect these | ||
18 | changes. | ||
19 | |||
20 | Signed-off-by: Alberto Garcia <berto@igalia.com> | ||
21 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
22 | Reviewed-by: Kevin Wolf <kwolf@redhat.com> | ||
23 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
24 | --- | 9 | --- |
25 | block/qcow2-cluster.c | 4 ++-- | 10 | docs/interop/parallels.txt | 28 ++++++++++++++++------------ |
26 | block/qcow2.h | 4 ++-- | 11 | 1 file changed, 16 insertions(+), 12 deletions(-) |
27 | 2 files changed, 4 insertions(+), 4 deletions(-) | ||
28 | 12 | ||
29 | diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c | 13 | diff --git a/docs/interop/parallels.txt b/docs/interop/parallels.txt |
30 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
31 | --- a/block/qcow2-cluster.c | 15 | --- a/docs/interop/parallels.txt |
32 | +++ b/block/qcow2-cluster.c | 16 | +++ b/docs/interop/parallels.txt |
33 | @@ -XXX,XX +XXX,XX @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num, | 17 | @@ -XXX,XX +XXX,XX @@ of its data area are: |
34 | static int coroutine_fn do_perform_cow(BlockDriverState *bs, | 18 | 28 - 31: l1_size |
35 | uint64_t src_cluster_offset, | 19 | The number of entries in the L1 table of the bitmap. |
36 | uint64_t cluster_offset, | 20 | |
37 | - int offset_in_cluster, | 21 | - variable: l1_table (8 * l1_size bytes) |
38 | - int bytes) | 22 | - L1 offset table (in bytes) |
39 | + unsigned offset_in_cluster, | 23 | + variable: L1 offset table (l1_table), size: 8 * l1_size bytes |
40 | + unsigned bytes) | 24 | |
41 | { | 25 | -A dirty bitmap is stored using a one-level structure for the mapping to host |
42 | BDRVQcow2State *s = bs->opaque; | 26 | -clusters - an L1 table. |
43 | QEMUIOVector qiov; | 27 | +The dirty bitmap described by this feature extension is stored in a set of |
44 | diff --git a/block/qcow2.h b/block/qcow2.h | 28 | +clusters inside the Parallels image file. The offsets of these clusters are |
45 | index XXXXXXX..XXXXXXX 100644 | 29 | +saved in the L1 offset table specified by the feature extension. Each L1 table |
46 | --- a/block/qcow2.h | 30 | +entry is a 64 bit integer as described below: |
47 | +++ b/block/qcow2.h | 31 | |
48 | @@ -XXX,XX +XXX,XX @@ typedef struct Qcow2COWRegion { | 32 | -Given an offset in bytes into the bitmap data, the offset in bytes into the |
49 | * Offset of the COW region in bytes from the start of the first cluster | 33 | -image file can be obtained as follows: |
50 | * touched by the request. | 34 | +Given an offset in bytes into the bitmap data, corresponding L1 entry is |
51 | */ | 35 | |
52 | - uint64_t offset; | 36 | - offset = l1_table[offset / cluster_size] + (offset % cluster_size) |
53 | + unsigned offset; | 37 | + l1_table[offset / cluster_size] |
54 | 38 | ||
55 | /** Number of bytes to copy */ | 39 | -If an L1 table entry is 0, the corresponding cluster of the bitmap is assumed |
56 | - int nb_bytes; | 40 | -to be zero. |
57 | + unsigned nb_bytes; | 41 | +If an L1 table entry is 0, all bits in the corresponding cluster of the bitmap |
58 | } Qcow2COWRegion; | 42 | +are assumed to be 0. |
59 | 43 | ||
60 | /** | 44 | -If an L1 table entry is 1, the corresponding cluster of the bitmap is assumed |
45 | -to have all bits set. | ||
46 | +If an L1 table entry is 1, all bits in the corresponding cluster of the bitmap | ||
47 | +are assumed to be 1. | ||
48 | |||
49 | -If an L1 table entry is not 0 or 1, it allocates a cluster from the data area. | ||
50 | +If an L1 table entry is not 0 or 1, it contains the corresponding cluster | ||
51 | +offset (in 512b sectors). Given an offset in bytes into the bitmap data the | ||
52 | +offset in bytes into the image file can be obtained as follows: | ||
53 | + | ||
54 | + offset = l1_table[offset / cluster_size] * 512 + (offset % cluster_size) | ||
61 | -- | 55 | -- |
62 | 1.8.3.1 | 56 | 2.29.2 |
63 | 57 | ||
64 | 58 | diff view generated by jsdifflib |
1 | From: Alberto Garcia <berto@igalia.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Instead of passing a single buffer pointer to do_perform_cow_write(), | 3 | We are going to use it in more places, calculating |
4 | pass a QEMUIOVector. This will allow us to merge the write requests | 4 | "s->tracks << BDRV_SECTOR_BITS" doesn't look good. |
5 | for the COW regions and the actual data into a single one. | ||
6 | 5 | ||
7 | Although do_perform_cow_read() does not strictly need to change its | 6 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
8 | API, we're doing it here as well for consistency. | 7 | Message-Id: <20210224104707.88430-4-vsementsov@virtuozzo.com> |
9 | 8 | Reviewed-by: Denis V. Lunev <den@openvz.org> | |
10 | Signed-off-by: Alberto Garcia <berto@igalia.com> | ||
11 | Reviewed-by: Kevin Wolf <kwolf@redhat.com> | ||
12 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 9 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
13 | --- | 10 | --- |
14 | block/qcow2-cluster.c | 51 ++++++++++++++++++++++++--------------------------- | 11 | block/parallels.h | 1 + |
15 | 1 file changed, 24 insertions(+), 27 deletions(-) | 12 | block/parallels.c | 8 ++++---- |
13 | 2 files changed, 5 insertions(+), 4 deletions(-) | ||
16 | 14 | ||
17 | diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c | 15 | diff --git a/block/parallels.h b/block/parallels.h |
18 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/block/qcow2-cluster.c | 17 | --- a/block/parallels.h |
20 | +++ b/block/qcow2-cluster.c | 18 | +++ b/block/parallels.h |
21 | @@ -XXX,XX +XXX,XX @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num, | 19 | @@ -XXX,XX +XXX,XX @@ typedef struct BDRVParallelsState { |
22 | static int coroutine_fn do_perform_cow_read(BlockDriverState *bs, | 20 | ParallelsPreallocMode prealloc_mode; |
23 | uint64_t src_cluster_offset, | 21 | |
24 | unsigned offset_in_cluster, | 22 | unsigned int tracks; |
25 | - uint8_t *buffer, | 23 | + unsigned int cluster_size; |
26 | - unsigned bytes) | 24 | |
27 | + QEMUIOVector *qiov) | 25 | unsigned int off_multiplier; |
28 | { | 26 | Error *migration_blocker; |
29 | - QEMUIOVector qiov; | 27 | diff --git a/block/parallels.c b/block/parallels.c |
30 | - struct iovec iov = { .iov_base = buffer, .iov_len = bytes }; | 28 | index XXXXXXX..XXXXXXX 100644 |
29 | --- a/block/parallels.c | ||
30 | +++ b/block/parallels.c | ||
31 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, | ||
31 | int ret; | 32 | int ret; |
32 | 33 | uint32_t i; | |
33 | - if (bytes == 0) { | 34 | bool flush_bat = false; |
34 | + if (qiov->size == 0) { | 35 | - int cluster_size = s->tracks << BDRV_SECTOR_BITS; |
35 | return 0; | 36 | |
37 | size = bdrv_getlength(bs->file->bs); | ||
38 | if (size < 0) { | ||
39 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, | ||
40 | high_off = off; | ||
41 | } | ||
42 | |||
43 | - if (prev_off != 0 && (prev_off + cluster_size) != off) { | ||
44 | + if (prev_off != 0 && (prev_off + s->cluster_size) != off) { | ||
45 | res->bfi.fragmented_clusters++; | ||
46 | } | ||
47 | prev_off = off; | ||
48 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, | ||
49 | } | ||
36 | } | 50 | } |
37 | 51 | ||
38 | - qemu_iovec_init_external(&qiov, &iov, 1); | 52 | - res->image_end_offset = high_off + cluster_size; |
39 | - | 53 | + res->image_end_offset = high_off + s->cluster_size; |
40 | BLKDBG_EVENT(bs->file, BLKDBG_COW_READ); | 54 | if (size > res->image_end_offset) { |
41 | 55 | int64_t count; | |
42 | if (!bs->drv) { | 56 | - count = DIV_ROUND_UP(size - res->image_end_offset, cluster_size); |
43 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn do_perform_cow_read(BlockDriverState *bs, | 57 | + count = DIV_ROUND_UP(size - res->image_end_offset, s->cluster_size); |
44 | * which can lead to deadlock when block layer copy-on-read is enabled. | 58 | fprintf(stderr, "%s space leaked at the end of the image %" PRId64 "\n", |
45 | */ | 59 | fix & BDRV_FIX_LEAKS ? "Repairing" : "ERROR", |
46 | ret = bs->drv->bdrv_co_preadv(bs, src_cluster_offset + offset_in_cluster, | 60 | size - res->image_end_offset); |
47 | - bytes, &qiov, 0); | 61 | @@ -XXX,XX +XXX,XX @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, |
48 | + qiov->size, qiov, 0); | 62 | ret = -EFBIG; |
49 | if (ret < 0) { | ||
50 | return ret; | ||
51 | } | ||
52 | @@ -XXX,XX +XXX,XX @@ static bool coroutine_fn do_perform_cow_encrypt(BlockDriverState *bs, | ||
53 | static int coroutine_fn do_perform_cow_write(BlockDriverState *bs, | ||
54 | uint64_t cluster_offset, | ||
55 | unsigned offset_in_cluster, | ||
56 | - uint8_t *buffer, | ||
57 | - unsigned bytes) | ||
58 | + QEMUIOVector *qiov) | ||
59 | { | ||
60 | - QEMUIOVector qiov; | ||
61 | - struct iovec iov = { .iov_base = buffer, .iov_len = bytes }; | ||
62 | int ret; | ||
63 | |||
64 | - if (bytes == 0) { | ||
65 | + if (qiov->size == 0) { | ||
66 | return 0; | ||
67 | } | ||
68 | |||
69 | - qemu_iovec_init_external(&qiov, &iov, 1); | ||
70 | - | ||
71 | ret = qcow2_pre_write_overlap_check(bs, 0, | ||
72 | - cluster_offset + offset_in_cluster, bytes); | ||
73 | + cluster_offset + offset_in_cluster, qiov->size); | ||
74 | if (ret < 0) { | ||
75 | return ret; | ||
76 | } | ||
77 | |||
78 | BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE); | ||
79 | ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster, | ||
80 | - bytes, &qiov, 0); | ||
81 | + qiov->size, qiov, 0); | ||
82 | if (ret < 0) { | ||
83 | return ret; | ||
84 | } | ||
85 | @@ -XXX,XX +XXX,XX @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | ||
86 | unsigned data_bytes = end->offset - (start->offset + start->nb_bytes); | ||
87 | bool merge_reads; | ||
88 | uint8_t *start_buffer, *end_buffer; | ||
89 | + QEMUIOVector qiov; | ||
90 | int ret; | ||
91 | |||
92 | assert(start->nb_bytes <= UINT_MAX - end->nb_bytes); | ||
93 | @@ -XXX,XX +XXX,XX @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | ||
94 | /* The part of the buffer where the end region is located */ | ||
95 | end_buffer = start_buffer + buffer_size - end->nb_bytes; | ||
96 | |||
97 | + qemu_iovec_init(&qiov, 1); | ||
98 | + | ||
99 | qemu_co_mutex_unlock(&s->lock); | ||
100 | /* First we read the existing data from both COW regions. We | ||
101 | * either read the whole region in one go, or the start and end | ||
102 | * regions separately. */ | ||
103 | if (merge_reads) { | ||
104 | - ret = do_perform_cow_read(bs, m->offset, start->offset, | ||
105 | - start_buffer, buffer_size); | ||
106 | + qemu_iovec_add(&qiov, start_buffer, buffer_size); | ||
107 | + ret = do_perform_cow_read(bs, m->offset, start->offset, &qiov); | ||
108 | } else { | ||
109 | - ret = do_perform_cow_read(bs, m->offset, start->offset, | ||
110 | - start_buffer, start->nb_bytes); | ||
111 | + qemu_iovec_add(&qiov, start_buffer, start->nb_bytes); | ||
112 | + ret = do_perform_cow_read(bs, m->offset, start->offset, &qiov); | ||
113 | if (ret < 0) { | ||
114 | goto fail; | ||
115 | } | ||
116 | |||
117 | - ret = do_perform_cow_read(bs, m->offset, end->offset, | ||
118 | - end_buffer, end->nb_bytes); | ||
119 | + qemu_iovec_reset(&qiov); | ||
120 | + qemu_iovec_add(&qiov, end_buffer, end->nb_bytes); | ||
121 | + ret = do_perform_cow_read(bs, m->offset, end->offset, &qiov); | ||
122 | } | ||
123 | if (ret < 0) { | ||
124 | goto fail; | ||
125 | @@ -XXX,XX +XXX,XX @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | ||
126 | } | ||
127 | |||
128 | /* And now we can write everything */ | ||
129 | - ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, | ||
130 | - start_buffer, start->nb_bytes); | ||
131 | + qemu_iovec_reset(&qiov); | ||
132 | + qemu_iovec_add(&qiov, start_buffer, start->nb_bytes); | ||
133 | + ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov); | ||
134 | if (ret < 0) { | ||
135 | goto fail; | 63 | goto fail; |
136 | } | 64 | } |
137 | 65 | + s->cluster_size = s->tracks << BDRV_SECTOR_BITS; | |
138 | - ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, | 66 | |
139 | - end_buffer, end->nb_bytes); | 67 | s->bat_size = le32_to_cpu(ph.bat_entries); |
140 | + qemu_iovec_reset(&qiov); | 68 | if (s->bat_size > INT_MAX / sizeof(uint32_t)) { |
141 | + qemu_iovec_add(&qiov, end_buffer, end->nb_bytes); | ||
142 | + ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, &qiov); | ||
143 | fail: | ||
144 | qemu_co_mutex_lock(&s->lock); | ||
145 | |||
146 | @@ -XXX,XX +XXX,XX @@ fail: | ||
147 | } | ||
148 | |||
149 | qemu_vfree(start_buffer); | ||
150 | + qemu_iovec_destroy(&qiov); | ||
151 | return ret; | ||
152 | } | ||
153 | |||
154 | -- | 69 | -- |
155 | 1.8.3.1 | 70 | 2.29.2 |
156 | 71 | ||
157 | 72 | diff view generated by jsdifflib |
1 | From: Alberto Garcia <berto@igalia.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | This patch splits do_perform_cow() into three separate functions to | 3 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
4 | read, encrypt and write the COW regions. | 4 | Message-Id: <20210224104707.88430-5-vsementsov@virtuozzo.com> |
5 | 5 | Reviewed-by: Denis V. Lunev <den@openvz.org> | |
6 | perform_cow() can now read both regions first, then encrypt them and | ||
7 | finally write them to disk. The memory allocation is also done in | ||
8 | this function now, using one single buffer large enough to hold both | ||
9 | regions. | ||
10 | |||
11 | Signed-off-by: Alberto Garcia <berto@igalia.com> | ||
12 | Reviewed-by: Kevin Wolf <kwolf@redhat.com> | ||
13 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 6 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
14 | --- | 7 | --- |
15 | block/qcow2-cluster.c | 117 +++++++++++++++++++++++++++++++++++++------------- | 8 | block/parallels.h | 6 +- |
16 | 1 file changed, 87 insertions(+), 30 deletions(-) | 9 | block/parallels-ext.c | 300 ++++++++++++++++++++++++++++++++++++++++++ |
10 | block/parallels.c | 18 +++ | ||
11 | block/meson.build | 3 +- | ||
12 | 4 files changed, 325 insertions(+), 2 deletions(-) | ||
13 | create mode 100644 block/parallels-ext.c | ||
17 | 14 | ||
18 | diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c | 15 | diff --git a/block/parallels.h b/block/parallels.h |
19 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/block/qcow2-cluster.c | 17 | --- a/block/parallels.h |
21 | +++ b/block/qcow2-cluster.c | 18 | +++ b/block/parallels.h |
22 | @@ -XXX,XX +XXX,XX @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num, | 19 | @@ -XXX,XX +XXX,XX @@ typedef struct ParallelsHeader { |
23 | return 0; | 20 | uint64_t nb_sectors; |
24 | } | 21 | uint32_t inuse; |
25 | 22 | uint32_t data_off; | |
26 | -static int coroutine_fn do_perform_cow(BlockDriverState *bs, | 23 | - char padding[12]; |
27 | - uint64_t src_cluster_offset, | 24 | + uint32_t flags; |
28 | - uint64_t cluster_offset, | 25 | + uint64_t ext_off; |
29 | - unsigned offset_in_cluster, | 26 | } QEMU_PACKED ParallelsHeader; |
30 | - unsigned bytes) | 27 | |
31 | +static int coroutine_fn do_perform_cow_read(BlockDriverState *bs, | 28 | typedef enum ParallelsPreallocMode { |
32 | + uint64_t src_cluster_offset, | 29 | @@ -XXX,XX +XXX,XX @@ typedef struct BDRVParallelsState { |
33 | + unsigned offset_in_cluster, | 30 | Error *migration_blocker; |
34 | + uint8_t *buffer, | 31 | } BDRVParallelsState; |
35 | + unsigned bytes) | 32 | |
36 | { | 33 | +int parallels_read_format_extension(BlockDriverState *bs, |
37 | - BDRVQcow2State *s = bs->opaque; | 34 | + int64_t ext_off, Error **errp); |
38 | QEMUIOVector qiov; | 35 | + |
39 | - struct iovec iov; | 36 | #endif |
40 | + struct iovec iov = { .iov_base = buffer, .iov_len = bytes }; | 37 | diff --git a/block/parallels-ext.c b/block/parallels-ext.c |
41 | int ret; | 38 | new file mode 100644 |
42 | 39 | index XXXXXXX..XXXXXXX | |
43 | if (bytes == 0) { | 40 | --- /dev/null |
44 | return 0; | 41 | +++ b/block/parallels-ext.c |
45 | } | 42 | @@ -XXX,XX +XXX,XX @@ |
46 | 43 | +/* | |
47 | - iov.iov_len = bytes; | 44 | + * Support of Parallels Format Extension. It's a part of Parallels format |
48 | - iov.iov_base = qemu_try_blockalign(bs, iov.iov_len); | 45 | + * driver. |
49 | - if (iov.iov_base == NULL) { | 46 | + * |
50 | - return -ENOMEM; | 47 | + * Copyright (c) 2021 Virtuozzo International GmbH |
51 | - } | 48 | + * |
52 | - | 49 | + * Permission is hereby granted, free of charge, to any person obtaining a copy |
53 | qemu_iovec_init_external(&qiov, &iov, 1); | 50 | + * of this software and associated documentation files (the "Software"), to deal |
54 | 51 | + * in the Software without restriction, including without limitation the rights | |
55 | BLKDBG_EVENT(bs->file, BLKDBG_COW_READ); | 52 | + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
56 | 53 | + * copies of the Software, and to permit persons to whom the Software is | |
57 | if (!bs->drv) { | 54 | + * furnished to do so, subject to the following conditions: |
58 | - ret = -ENOMEDIUM; | 55 | + * |
59 | - goto out; | 56 | + * The above copyright notice and this permission notice shall be included in |
60 | + return -ENOMEDIUM; | 57 | + * all copies or substantial portions of the Software. |
61 | } | 58 | + * |
62 | 59 | + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | |
63 | /* Call .bdrv_co_readv() directly instead of using the public block-layer | 60 | + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
64 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn do_perform_cow(BlockDriverState *bs, | 61 | + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL |
65 | ret = bs->drv->bdrv_co_preadv(bs, src_cluster_offset + offset_in_cluster, | 62 | + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
66 | bytes, &qiov, 0); | 63 | + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
67 | if (ret < 0) { | 64 | + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
68 | - goto out; | 65 | + * THE SOFTWARE. |
69 | + return ret; | 66 | + */ |
70 | } | 67 | + |
71 | 68 | +#include "qemu/osdep.h" | |
72 | - if (bs->encrypted) { | 69 | +#include "qapi/error.h" |
73 | + return 0; | 70 | +#include "block/block_int.h" |
71 | +#include "parallels.h" | ||
72 | +#include "crypto/hash.h" | ||
73 | +#include "qemu/uuid.h" | ||
74 | + | ||
75 | +#define PARALLELS_FORMAT_EXTENSION_MAGIC 0xAB234CEF23DCEA87ULL | ||
76 | + | ||
77 | +#define PARALLELS_END_OF_FEATURES_MAGIC 0x0ULL | ||
78 | +#define PARALLELS_DIRTY_BITMAP_FEATURE_MAGIC 0x20385FAE252CB34AULL | ||
79 | + | ||
80 | +typedef struct ParallelsFormatExtensionHeader { | ||
81 | + uint64_t magic; /* PARALLELS_FORMAT_EXTENSION_MAGIC */ | ||
82 | + uint8_t check_sum[16]; | ||
83 | +} QEMU_PACKED ParallelsFormatExtensionHeader; | ||
84 | + | ||
85 | +typedef struct ParallelsFeatureHeader { | ||
86 | + uint64_t magic; | ||
87 | + uint64_t flags; | ||
88 | + uint32_t data_size; | ||
89 | + uint32_t _unused; | ||
90 | +} QEMU_PACKED ParallelsFeatureHeader; | ||
91 | + | ||
92 | +typedef struct ParallelsDirtyBitmapFeature { | ||
93 | + uint64_t size; | ||
94 | + uint8_t id[16]; | ||
95 | + uint32_t granularity; | ||
96 | + uint32_t l1_size; | ||
97 | + /* L1 table follows */ | ||
98 | +} QEMU_PACKED ParallelsDirtyBitmapFeature; | ||
99 | + | ||
100 | +/* Given L1 table read bitmap data from the image and populate @bitmap */ | ||
101 | +static int parallels_load_bitmap_data(BlockDriverState *bs, | ||
102 | + const uint64_t *l1_table, | ||
103 | + uint32_t l1_size, | ||
104 | + BdrvDirtyBitmap *bitmap, | ||
105 | + Error **errp) | ||
106 | +{ | ||
107 | + BDRVParallelsState *s = bs->opaque; | ||
108 | + int ret = 0; | ||
109 | + uint64_t offset, limit; | ||
110 | + uint64_t bm_size = bdrv_dirty_bitmap_size(bitmap); | ||
111 | + uint8_t *buf = NULL; | ||
112 | + uint64_t i, tab_size = | ||
113 | + DIV_ROUND_UP(bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_size), | ||
114 | + s->cluster_size); | ||
115 | + | ||
116 | + if (tab_size != l1_size) { | ||
117 | + error_setg(errp, "Bitmap table size %" PRIu32 " does not correspond " | ||
118 | + "to bitmap size and cluster size. Expected %" PRIu64, | ||
119 | + l1_size, tab_size); | ||
120 | + return -EINVAL; | ||
121 | + } | ||
122 | + | ||
123 | + buf = qemu_blockalign(bs, s->cluster_size); | ||
124 | + limit = bdrv_dirty_bitmap_serialization_coverage(s->cluster_size, bitmap); | ||
125 | + for (i = 0, offset = 0; i < tab_size; ++i, offset += limit) { | ||
126 | + uint64_t count = MIN(bm_size - offset, limit); | ||
127 | + uint64_t entry = l1_table[i]; | ||
128 | + | ||
129 | + if (entry == 0) { | ||
130 | + /* No need to deserialize zeros because @bitmap is cleared. */ | ||
131 | + continue; | ||
132 | + } | ||
133 | + | ||
134 | + if (entry == 1) { | ||
135 | + bdrv_dirty_bitmap_deserialize_ones(bitmap, offset, count, false); | ||
136 | + } else { | ||
137 | + ret = bdrv_pread(bs->file, entry << BDRV_SECTOR_BITS, buf, | ||
138 | + s->cluster_size); | ||
139 | + if (ret < 0) { | ||
140 | + error_setg_errno(errp, -ret, | ||
141 | + "Failed to read bitmap data cluster"); | ||
142 | + goto finish; | ||
143 | + } | ||
144 | + bdrv_dirty_bitmap_deserialize_part(bitmap, buf, offset, count, | ||
145 | + false); | ||
146 | + } | ||
147 | + } | ||
148 | + ret = 0; | ||
149 | + | ||
150 | + bdrv_dirty_bitmap_deserialize_finish(bitmap); | ||
151 | + | ||
152 | +finish: | ||
153 | + qemu_vfree(buf); | ||
154 | + | ||
155 | + return ret; | ||
74 | +} | 156 | +} |
75 | + | 157 | + |
76 | +static bool coroutine_fn do_perform_cow_encrypt(BlockDriverState *bs, | 158 | +/* |
77 | + uint64_t src_cluster_offset, | 159 | + * @data buffer (of @data_size size) is the Dirty bitmaps feature which |
78 | + unsigned offset_in_cluster, | 160 | + * consists of ParallelsDirtyBitmapFeature followed by L1 table. |
79 | + uint8_t *buffer, | 161 | + */ |
80 | + unsigned bytes) | 162 | +static BdrvDirtyBitmap *parallels_load_bitmap(BlockDriverState *bs, |
163 | + uint8_t *data, | ||
164 | + size_t data_size, | ||
165 | + Error **errp) | ||
81 | +{ | 166 | +{ |
82 | + if (bytes && bs->encrypted) { | 167 | + int ret; |
83 | + BDRVQcow2State *s = bs->opaque; | 168 | + ParallelsDirtyBitmapFeature bf; |
84 | int64_t sector = (src_cluster_offset + offset_in_cluster) | 169 | + g_autofree uint64_t *l1_table = NULL; |
85 | >> BDRV_SECTOR_BITS; | 170 | + BdrvDirtyBitmap *bitmap; |
86 | assert(s->cipher); | 171 | + QemuUUID uuid; |
87 | assert((offset_in_cluster & ~BDRV_SECTOR_MASK) == 0); | 172 | + char uuidstr[UUID_FMT_LEN + 1]; |
88 | assert((bytes & ~BDRV_SECTOR_MASK) == 0); | 173 | + int i; |
89 | - if (qcow2_encrypt_sectors(s, sector, iov.iov_base, iov.iov_base, | 174 | + |
90 | + if (qcow2_encrypt_sectors(s, sector, buffer, buffer, | 175 | + if (data_size < sizeof(bf)) { |
91 | bytes >> BDRV_SECTOR_BITS, true, NULL) < 0) { | 176 | + error_setg(errp, "Too small Bitmap Feature area in Parallels Format " |
92 | - ret = -EIO; | 177 | + "Extension: %zu bytes, expected at least %zu bytes", |
93 | - goto out; | 178 | + data_size, sizeof(bf)); |
94 | + return false; | 179 | + return NULL; |
95 | } | 180 | + } |
96 | } | 181 | + memcpy(&bf, data, sizeof(bf)); |
97 | + return true; | 182 | + bf.size = le64_to_cpu(bf.size); |
183 | + bf.granularity = le32_to_cpu(bf.granularity) << BDRV_SECTOR_BITS; | ||
184 | + bf.l1_size = le32_to_cpu(bf.l1_size); | ||
185 | + data += sizeof(bf); | ||
186 | + data_size -= sizeof(bf); | ||
187 | + | ||
188 | + if (bf.size != bs->total_sectors) { | ||
189 | + error_setg(errp, "Bitmap size (in sectors) %" PRId64 " differs from " | ||
190 | + "disk size in sectors %" PRId64, bf.size, bs->total_sectors); | ||
191 | + return NULL; | ||
192 | + } | ||
193 | + | ||
194 | + if (bf.l1_size * sizeof(uint64_t) > data_size) { | ||
195 | + error_setg(errp, "Bitmaps feature corrupted: l1 table exceeds " | ||
196 | + "extension data_size"); | ||
197 | + return NULL; | ||
198 | + } | ||
199 | + | ||
200 | + memcpy(&uuid, bf.id, sizeof(uuid)); | ||
201 | + qemu_uuid_unparse(&uuid, uuidstr); | ||
202 | + bitmap = bdrv_create_dirty_bitmap(bs, bf.granularity, uuidstr, errp); | ||
203 | + if (!bitmap) { | ||
204 | + return NULL; | ||
205 | + } | ||
206 | + | ||
207 | + l1_table = g_new(uint64_t, bf.l1_size); | ||
208 | + for (i = 0; i < bf.l1_size; i++, data += sizeof(uint64_t)) { | ||
209 | + l1_table[i] = ldq_le_p(data); | ||
210 | + } | ||
211 | + | ||
212 | + ret = parallels_load_bitmap_data(bs, l1_table, bf.l1_size, bitmap, errp); | ||
213 | + if (ret < 0) { | ||
214 | + bdrv_release_dirty_bitmap(bitmap); | ||
215 | + return NULL; | ||
216 | + } | ||
217 | + | ||
218 | + /* We support format extension only for RO parallels images. */ | ||
219 | + assert(!(bs->open_flags & BDRV_O_RDWR)); | ||
220 | + bdrv_dirty_bitmap_set_readonly(bitmap, true); | ||
221 | + | ||
222 | + return bitmap; | ||
98 | +} | 223 | +} |
99 | + | 224 | + |
100 | +static int coroutine_fn do_perform_cow_write(BlockDriverState *bs, | 225 | +static int parallels_parse_format_extension(BlockDriverState *bs, |
101 | + uint64_t cluster_offset, | 226 | + uint8_t *ext_cluster, Error **errp) |
102 | + unsigned offset_in_cluster, | ||
103 | + uint8_t *buffer, | ||
104 | + unsigned bytes) | ||
105 | +{ | 227 | +{ |
106 | + QEMUIOVector qiov; | 228 | + BDRVParallelsState *s = bs->opaque; |
107 | + struct iovec iov = { .iov_base = buffer, .iov_len = bytes }; | ||
108 | + int ret; | 229 | + int ret; |
109 | + | 230 | + int remaining = s->cluster_size; |
110 | + if (bytes == 0) { | 231 | + uint8_t *pos = ext_cluster; |
111 | + return 0; | 232 | + ParallelsFormatExtensionHeader eh; |
112 | + } | 233 | + g_autofree uint8_t *hash = NULL; |
113 | + | 234 | + size_t hash_len = 0; |
114 | + qemu_iovec_init_external(&qiov, &iov, 1); | 235 | + GSList *bitmaps = NULL, *el; |
115 | 236 | + | |
116 | ret = qcow2_pre_write_overlap_check(bs, 0, | 237 | + memcpy(&eh, pos, sizeof(eh)); |
117 | cluster_offset + offset_in_cluster, bytes); | 238 | + eh.magic = le64_to_cpu(eh.magic); |
118 | if (ret < 0) { | 239 | + pos += sizeof(eh); |
119 | - goto out; | 240 | + remaining -= sizeof(eh); |
120 | + return ret; | 241 | + |
121 | } | 242 | + if (eh.magic != PARALLELS_FORMAT_EXTENSION_MAGIC) { |
122 | 243 | + error_setg(errp, "Wrong parallels Format Extension magic: 0x%" PRIx64 | |
123 | BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE); | 244 | + ", expected: 0x%llx", eh.magic, |
124 | ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster, | 245 | + PARALLELS_FORMAT_EXTENSION_MAGIC); |
125 | bytes, &qiov, 0); | 246 | + goto fail; |
126 | if (ret < 0) { | 247 | + } |
127 | - goto out; | 248 | + |
128 | + return ret; | 249 | + ret = qcrypto_hash_bytes(QCRYPTO_HASH_ALG_MD5, (char *)pos, remaining, |
129 | } | 250 | + &hash, &hash_len, errp); |
130 | |||
131 | - ret = 0; | ||
132 | -out: | ||
133 | - qemu_vfree(iov.iov_base); | ||
134 | - return ret; | ||
135 | + return 0; | ||
136 | } | ||
137 | |||
138 | |||
139 | @@ -XXX,XX +XXX,XX @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) | ||
140 | BDRVQcow2State *s = bs->opaque; | ||
141 | Qcow2COWRegion *start = &m->cow_start; | ||
142 | Qcow2COWRegion *end = &m->cow_end; | ||
143 | + unsigned buffer_size; | ||
144 | + uint8_t *start_buffer, *end_buffer; | ||
145 | int ret; | ||
146 | |||
147 | + assert(start->nb_bytes <= UINT_MAX - end->nb_bytes); | ||
148 | + | ||
149 | if (start->nb_bytes == 0 && end->nb_bytes == 0) { | ||
150 | return 0; | ||
151 | } | ||
152 | |||
153 | + /* Reserve a buffer large enough to store the data from both the | ||
154 | + * start and end COW regions. Add some padding in the middle if | ||
155 | + * necessary to make sure that the end region is optimally aligned */ | ||
156 | + buffer_size = QEMU_ALIGN_UP(start->nb_bytes, bdrv_opt_mem_align(bs)) + | ||
157 | + end->nb_bytes; | ||
158 | + start_buffer = qemu_try_blockalign(bs, buffer_size); | ||
159 | + if (start_buffer == NULL) { | ||
160 | + return -ENOMEM; | ||
161 | + } | ||
162 | + /* The part of the buffer where the end region is located */ | ||
163 | + end_buffer = start_buffer + buffer_size - end->nb_bytes; | ||
164 | + | ||
165 | qemu_co_mutex_unlock(&s->lock); | ||
166 | - ret = do_perform_cow(bs, m->offset, m->alloc_offset, | ||
167 | - start->offset, start->nb_bytes); | ||
168 | + /* First we read the existing data from both COW regions */ | ||
169 | + ret = do_perform_cow_read(bs, m->offset, start->offset, | ||
170 | + start_buffer, start->nb_bytes); | ||
171 | if (ret < 0) { | ||
172 | goto fail; | ||
173 | } | ||
174 | |||
175 | - ret = do_perform_cow(bs, m->offset, m->alloc_offset, | ||
176 | - end->offset, end->nb_bytes); | ||
177 | + ret = do_perform_cow_read(bs, m->offset, end->offset, | ||
178 | + end_buffer, end->nb_bytes); | ||
179 | + if (ret < 0) { | 251 | + if (ret < 0) { |
180 | + goto fail; | 252 | + goto fail; |
181 | + } | 253 | + } |
182 | + | 254 | + |
183 | + /* Encrypt the data if necessary before writing it */ | 255 | + if (hash_len != sizeof(eh.check_sum) || |
184 | + if (bs->encrypted) { | 256 | + memcmp(hash, eh.check_sum, sizeof(eh.check_sum)) != 0) { |
185 | + if (!do_perform_cow_encrypt(bs, m->offset, start->offset, | 257 | + error_setg(errp, "Wrong checksum in Format Extension header. Format " |
186 | + start_buffer, start->nb_bytes) || | 258 | + "extension is corrupted."); |
187 | + !do_perform_cow_encrypt(bs, m->offset, end->offset, | 259 | + goto fail; |
188 | + end_buffer, end->nb_bytes)) { | 260 | + } |
189 | + ret = -EIO; | 261 | + |
262 | + while (true) { | ||
263 | + ParallelsFeatureHeader fh; | ||
264 | + BdrvDirtyBitmap *bitmap; | ||
265 | + | ||
266 | + if (remaining < sizeof(fh)) { | ||
267 | + error_setg(errp, "Can not read feature header, as remaining bytes " | ||
268 | + "(%d) in Format Extension is less than Feature header " | ||
269 | + "size (%zu)", remaining, sizeof(fh)); | ||
190 | + goto fail; | 270 | + goto fail; |
191 | + } | 271 | + } |
192 | + } | 272 | + |
193 | + | 273 | + memcpy(&fh, pos, sizeof(fh)); |
194 | + /* And now we can write everything */ | 274 | + pos += sizeof(fh); |
195 | + ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, | 275 | + remaining -= sizeof(fh); |
196 | + start_buffer, start->nb_bytes); | 276 | + |
277 | + fh.magic = le64_to_cpu(fh.magic); | ||
278 | + fh.flags = le64_to_cpu(fh.flags); | ||
279 | + fh.data_size = le32_to_cpu(fh.data_size); | ||
280 | + | ||
281 | + if (fh.flags) { | ||
282 | + error_setg(errp, "Flags for extension feature are unsupported"); | ||
283 | + goto fail; | ||
284 | + } | ||
285 | + | ||
286 | + if (fh.data_size > remaining) { | ||
287 | + error_setg(errp, "Feature data_size exceedes Format Extension " | ||
288 | + "cluster"); | ||
289 | + goto fail; | ||
290 | + } | ||
291 | + | ||
292 | + switch (fh.magic) { | ||
293 | + case PARALLELS_END_OF_FEATURES_MAGIC: | ||
294 | + return 0; | ||
295 | + | ||
296 | + case PARALLELS_DIRTY_BITMAP_FEATURE_MAGIC: | ||
297 | + bitmap = parallels_load_bitmap(bs, pos, fh.data_size, errp); | ||
298 | + if (!bitmap) { | ||
299 | + goto fail; | ||
300 | + } | ||
301 | + bitmaps = g_slist_append(bitmaps, bitmap); | ||
302 | + break; | ||
303 | + | ||
304 | + default: | ||
305 | + error_setg(errp, "Unknown feature: 0x%" PRIu64, fh.magic); | ||
306 | + goto fail; | ||
307 | + } | ||
308 | + | ||
309 | + pos = ext_cluster + QEMU_ALIGN_UP(pos + fh.data_size - ext_cluster, 8); | ||
310 | + } | ||
311 | + | ||
312 | +fail: | ||
313 | + for (el = bitmaps; el; el = el->next) { | ||
314 | + bdrv_release_dirty_bitmap(el->data); | ||
315 | + } | ||
316 | + g_slist_free(bitmaps); | ||
317 | + | ||
318 | + return -EINVAL; | ||
319 | +} | ||
320 | + | ||
321 | +int parallels_read_format_extension(BlockDriverState *bs, | ||
322 | + int64_t ext_off, Error **errp) | ||
323 | +{ | ||
324 | + BDRVParallelsState *s = bs->opaque; | ||
325 | + int ret; | ||
326 | + uint8_t *ext_cluster = qemu_blockalign(bs, s->cluster_size); | ||
327 | + | ||
328 | + assert(ext_off > 0); | ||
329 | + | ||
330 | + ret = bdrv_pread(bs->file, ext_off, ext_cluster, s->cluster_size); | ||
197 | + if (ret < 0) { | 331 | + if (ret < 0) { |
198 | + goto fail; | 332 | + error_setg_errno(errp, -ret, "Failed to read Format Extension cluster"); |
199 | + } | 333 | + goto out; |
200 | 334 | + } | |
201 | + ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, | 335 | + |
202 | + end_buffer, end->nb_bytes); | 336 | + ret = parallels_parse_format_extension(bs, ext_cluster, errp); |
203 | fail: | 337 | + |
204 | qemu_co_mutex_lock(&s->lock); | 338 | +out: |
205 | 339 | + qemu_vfree(ext_cluster); | |
206 | @@ -XXX,XX +XXX,XX @@ fail: | 340 | + |
207 | qcow2_cache_depends_on_flush(s->l2_table_cache); | 341 | + return ret; |
342 | +} | ||
343 | diff --git a/block/parallels.c b/block/parallels.c | ||
344 | index XXXXXXX..XXXXXXX 100644 | ||
345 | --- a/block/parallels.c | ||
346 | +++ b/block/parallels.c | ||
347 | @@ -XXX,XX +XXX,XX @@ | ||
348 | */ | ||
349 | |||
350 | #include "qemu/osdep.h" | ||
351 | +#include "qemu/error-report.h" | ||
352 | #include "qapi/error.h" | ||
353 | #include "block/block_int.h" | ||
354 | #include "block/qdict.h" | ||
355 | @@ -XXX,XX +XXX,XX @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, | ||
356 | goto fail_options; | ||
208 | } | 357 | } |
209 | 358 | ||
210 | + qemu_vfree(start_buffer); | 359 | + if (ph.ext_off) { |
211 | return ret; | 360 | + if (flags & BDRV_O_RDWR) { |
212 | } | 361 | + /* |
213 | 362 | + * It's unsafe to open image RW if there is an extension (as we | |
363 | + * don't support it). But parallels driver in QEMU historically | ||
364 | + * ignores the extension, so print warning and don't care. | ||
365 | + */ | ||
366 | + warn_report("Format Extension ignored in RW mode"); | ||
367 | + } else { | ||
368 | + ret = parallels_read_format_extension( | ||
369 | + bs, le64_to_cpu(ph.ext_off) << BDRV_SECTOR_BITS, errp); | ||
370 | + if (ret < 0) { | ||
371 | + goto fail; | ||
372 | + } | ||
373 | + } | ||
374 | + } | ||
375 | + | ||
376 | if ((flags & BDRV_O_RDWR) && !(flags & BDRV_O_INACTIVE)) { | ||
377 | s->header->inuse = cpu_to_le32(HEADER_INUSE_MAGIC); | ||
378 | ret = parallels_update_header(bs); | ||
379 | diff --git a/block/meson.build b/block/meson.build | ||
380 | index XXXXXXX..XXXXXXX 100644 | ||
381 | --- a/block/meson.build | ||
382 | +++ b/block/meson.build | ||
383 | @@ -XXX,XX +XXX,XX @@ block_ss.add(when: 'CONFIG_QED', if_true: files( | ||
384 | 'qed-table.c', | ||
385 | 'qed.c', | ||
386 | )) | ||
387 | -block_ss.add(when: [libxml2, 'CONFIG_PARALLELS'], if_true: files('parallels.c')) | ||
388 | +block_ss.add(when: [libxml2, 'CONFIG_PARALLELS'], | ||
389 | + if_true: files('parallels.c', 'parallels-ext.c')) | ||
390 | block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c')) | ||
391 | block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) | ||
392 | block_ss.add(when: libiscsi, if_true: files('iscsi-opts.c')) | ||
214 | -- | 393 | -- |
215 | 1.8.3.1 | 394 | 2.29.2 |
216 | 395 | ||
217 | 396 | diff view generated by jsdifflib |
1 | From: Alberto Garcia <berto@igalia.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | There used to be throttle_timers_{detach,attach}_aio_context() calls | 3 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
4 | in bdrv_set_aio_context(), but since 7ca7f0f6db1fedd28d490795d778cf239 | 4 | Message-Id: <20210224104707.88430-6-vsementsov@virtuozzo.com> |
5 | they are now in blk_set_aio_context(). | 5 | Reviewed-by: Denis V. Lunev <den@openvz.org> |
6 | |||
7 | Signed-off-by: Alberto Garcia <berto@igalia.com> | ||
8 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
9 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 6 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
10 | --- | 7 | --- |
11 | block/throttle-groups.c | 2 +- | 8 | tests/qemu-iotests/iotests.py | 10 ++++++++++ |
12 | 1 file changed, 1 insertion(+), 1 deletion(-) | 9 | 1 file changed, 10 insertions(+) |
13 | 10 | ||
14 | diff --git a/block/throttle-groups.c b/block/throttle-groups.c | 11 | diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py |
15 | index XXXXXXX..XXXXXXX 100644 | 12 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/block/throttle-groups.c | 13 | --- a/tests/qemu-iotests/iotests.py |
17 | +++ b/block/throttle-groups.c | 14 | +++ b/tests/qemu-iotests/iotests.py |
18 | @@ -XXX,XX +XXX,XX @@ | 15 | @@ -XXX,XX +XXX,XX @@ |
19 | * Again, all this is handled internally and is mostly transparent to | 16 | # |
20 | * the outside. The 'throttle_timers' field however has an additional | 17 | |
21 | * constraint because it may be temporarily invalid (see for example | 18 | import atexit |
22 | - * bdrv_set_aio_context()). Therefore in this file a thread will | 19 | +import bz2 |
23 | + * blk_set_aio_context()). Therefore in this file a thread will | 20 | from collections import OrderedDict |
24 | * access some other BlockBackend's timers only after verifying that | 21 | import faulthandler |
25 | * that BlockBackend has throttled requests in the queue. | 22 | import io |
26 | */ | 23 | @@ -XXX,XX +XXX,XX @@ |
24 | import logging | ||
25 | import os | ||
26 | import re | ||
27 | +import shutil | ||
28 | import signal | ||
29 | import struct | ||
30 | import subprocess | ||
31 | @@ -XXX,XX +XXX,XX @@ | ||
32 | os.environ.get('IMGKEYSECRET', '') | ||
33 | luks_default_key_secret_opt = 'key-secret=keysec0' | ||
34 | |||
35 | +sample_img_dir = os.environ['SAMPLE_IMG_DIR'] | ||
36 | + | ||
37 | + | ||
38 | +def unarchive_sample_image(sample, fname): | ||
39 | + sample_fname = os.path.join(sample_img_dir, sample + '.bz2') | ||
40 | + with bz2.open(sample_fname) as f_in, open(fname, 'wb') as f_out: | ||
41 | + shutil.copyfileobj(f_in, f_out) | ||
42 | + | ||
43 | |||
44 | def qemu_tool_pipe_and_status(tool: str, args: Sequence[str], | ||
45 | connect_stderr: bool = True) -> Tuple[str, int]: | ||
27 | -- | 46 | -- |
28 | 1.8.3.1 | 47 | 2.29.2 |
29 | 48 | ||
30 | 49 | diff view generated by jsdifflib |
1 | When qemu is exited, all running jobs should be cancelled successfully. | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | This adds a test for this for all types of block jobs that currently | ||
3 | exist in qemu. | ||
4 | 2 | ||
3 | Test support for reading bitmap from parallels image format. | ||
4 | parallels-with-bitmap.bz2 is generated on Virtuozzo by | ||
5 | parallels-with-bitmap.sh | ||
6 | |||
7 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
8 | Message-Id: <20210224104707.88430-7-vsementsov@virtuozzo.com> | ||
9 | Reviewed-by: Denis V. Lunev <den@openvz.org> | ||
5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 10 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
6 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
7 | --- | 11 | --- |
8 | tests/qemu-iotests/185 | 206 +++++++++++++++++++++++++++++++++++++++++++++ | 12 | .../sample_images/parallels-with-bitmap.bz2 | Bin 0 -> 203 bytes |
9 | tests/qemu-iotests/185.out | 59 +++++++++++++ | 13 | .../sample_images/parallels-with-bitmap.sh | 51 ++++++++++++++++ |
10 | tests/qemu-iotests/group | 1 + | 14 | .../qemu-iotests/tests/parallels-read-bitmap | 55 ++++++++++++++++++ |
11 | 3 files changed, 266 insertions(+) | 15 | .../tests/parallels-read-bitmap.out | 6 ++ |
12 | create mode 100755 tests/qemu-iotests/185 | 16 | 4 files changed, 112 insertions(+) |
13 | create mode 100644 tests/qemu-iotests/185.out | 17 | create mode 100644 tests/qemu-iotests/sample_images/parallels-with-bitmap.bz2 |
18 | create mode 100755 tests/qemu-iotests/sample_images/parallels-with-bitmap.sh | ||
19 | create mode 100755 tests/qemu-iotests/tests/parallels-read-bitmap | ||
20 | create mode 100644 tests/qemu-iotests/tests/parallels-read-bitmap.out | ||
14 | 21 | ||
15 | diff --git a/tests/qemu-iotests/185 b/tests/qemu-iotests/185 | 22 | diff --git a/tests/qemu-iotests/sample_images/parallels-with-bitmap.bz2 b/tests/qemu-iotests/sample_images/parallels-with-bitmap.bz2 |
23 | new file mode 100644 | ||
24 | index XXXXXXX..XXXXXXX | ||
25 | GIT binary patch | ||
26 | literal 203 | ||
27 | zcmV;+05tzXT4*^jL0KkKS@=;0bpT+Hf7|^?Km<xfFyKQJ7=Y^F-%vt;00~Ysa6|-= | ||
28 | zk&7Szk`SoS002EkfMftPG<ipnsiCK}K_sNmm}me3FiZr%Oaf_u5F8kD;mB_~cxD-r | ||
29 | z5P$(X{&Tq5C`<xK02D?NNdN+t$~z$m00O|zFh^ynq*yaCtkn+NZzWom<#OEoF`?zb | ||
30 | zv(i3x^K~wt!aLPcRBP+PckUsIh6*LgjYSh0`}#7hMC9NR5D)+W0d&8Mxgwk>NPH-R | ||
31 | Fx`3oHQ9u9y | ||
32 | |||
33 | literal 0 | ||
34 | HcmV?d00001 | ||
35 | |||
36 | diff --git a/tests/qemu-iotests/sample_images/parallels-with-bitmap.sh b/tests/qemu-iotests/sample_images/parallels-with-bitmap.sh | ||
16 | new file mode 100755 | 37 | new file mode 100755 |
17 | index XXXXXXX..XXXXXXX | 38 | index XXXXXXX..XXXXXXX |
18 | --- /dev/null | 39 | --- /dev/null |
19 | +++ b/tests/qemu-iotests/185 | 40 | +++ b/tests/qemu-iotests/sample_images/parallels-with-bitmap.sh |
20 | @@ -XXX,XX +XXX,XX @@ | 41 | @@ -XXX,XX +XXX,XX @@ |
21 | +#!/bin/bash | 42 | +#!/bin/bash |
22 | +# | 43 | +# |
23 | +# Test exiting qemu while jobs are still running | 44 | +# Test parallels load bitmap |
24 | +# | 45 | +# |
25 | +# Copyright (C) 2017 Red Hat, Inc. | 46 | +# Copyright (c) 2021 Virtuozzo International GmbH. |
26 | +# | 47 | +# |
27 | +# This program is free software; you can redistribute it and/or modify | 48 | +# This program is free software; you can redistribute it and/or modify |
28 | +# it under the terms of the GNU General Public License as published by | 49 | +# it under the terms of the GNU General Public License as published by |
29 | +# the Free Software Foundation; either version 2 of the License, or | 50 | +# the Free Software Foundation; either version 2 of the License, or |
30 | +# (at your option) any later version. | 51 | +# (at your option) any later version. |
... | ... | ||
36 | +# | 57 | +# |
37 | +# You should have received a copy of the GNU General Public License | 58 | +# You should have received a copy of the GNU General Public License |
38 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. | 59 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. |
39 | +# | 60 | +# |
40 | + | 61 | + |
41 | +# creator | 62 | +CT=parallels-with-bitmap-ct |
42 | +owner=kwolf@redhat.com | 63 | +DIR=$PWD/parallels-with-bitmap-dir |
64 | +IMG=$DIR/root.hds | ||
65 | +XML=$DIR/DiskDescriptor.xml | ||
66 | +TARGET=parallels-with-bitmap.bz2 | ||
43 | + | 67 | + |
44 | +seq=`basename $0` | 68 | +rm -rf $DIR |
45 | +echo "QA output created by $seq" | ||
46 | + | 69 | + |
47 | +here=`pwd` | 70 | +prlctl create $CT --vmtype ct |
48 | +status=1 # failure is the default! | 71 | +prlctl set $CT --device-add hdd --image $DIR --recreate --size 2G |
49 | + | 72 | + |
50 | +MIG_SOCKET="${TEST_DIR}/migrate" | 73 | +# cleanup the image |
74 | +qemu-img create -f parallels $IMG 64G | ||
51 | + | 75 | + |
52 | +_cleanup() | 76 | +# create bitmap |
53 | +{ | 77 | +prlctl backup $CT |
54 | + rm -f "${TEST_IMG}.mid" | ||
55 | + rm -f "${TEST_IMG}.copy" | ||
56 | + _cleanup_test_img | ||
57 | + _cleanup_qemu | ||
58 | +} | ||
59 | +trap "_cleanup; exit \$status" 0 1 2 3 15 | ||
60 | + | 78 | + |
61 | +# get standard environment, filters and checks | 79 | +prlctl set $CT --device-del hdd1 |
62 | +. ./common.rc | 80 | +prlctl destroy $CT |
63 | +. ./common.filter | ||
64 | +. ./common.qemu | ||
65 | + | 81 | + |
66 | +_supported_fmt qcow2 | 82 | +dev=$(ploop mount $XML | sed -n 's/^Adding delta dev=\(\/dev\/ploop[0-9]\+\).*/\1/p') |
67 | +_supported_proto file | 83 | +dd if=/dev/zero of=$dev bs=64K seek=5 count=2 oflag=direct |
68 | +_supported_os Linux | 84 | +dd if=/dev/zero of=$dev bs=64K seek=30 count=1 oflag=direct |
85 | +dd if=/dev/zero of=$dev bs=64K seek=10 count=3 oflag=direct | ||
86 | +ploop umount $XML # bitmap name will be in the output | ||
69 | + | 87 | + |
70 | +size=64M | 88 | +bzip2 -z $IMG |
71 | +TEST_IMG="${TEST_IMG}.base" _make_test_img $size | ||
72 | + | 89 | + |
73 | +echo | 90 | +mv $IMG.bz2 $TARGET |
74 | +echo === Starting VM === | ||
75 | +echo | ||
76 | + | 91 | + |
77 | +qemu_comm_method="qmp" | 92 | +rm -rf $DIR |
93 | diff --git a/tests/qemu-iotests/tests/parallels-read-bitmap b/tests/qemu-iotests/tests/parallels-read-bitmap | ||
94 | new file mode 100755 | ||
95 | index XXXXXXX..XXXXXXX | ||
96 | --- /dev/null | ||
97 | +++ b/tests/qemu-iotests/tests/parallels-read-bitmap | ||
98 | @@ -XXX,XX +XXX,XX @@ | ||
99 | +#!/usr/bin/env python3 | ||
100 | +# | ||
101 | +# Test parallels load bitmap | ||
102 | +# | ||
103 | +# Copyright (c) 2021 Virtuozzo International GmbH. | ||
104 | +# | ||
105 | +# This program is free software; you can redistribute it and/or modify | ||
106 | +# it under the terms of the GNU General Public License as published by | ||
107 | +# the Free Software Foundation; either version 2 of the License, or | ||
108 | +# (at your option) any later version. | ||
109 | +# | ||
110 | +# This program is distributed in the hope that it will be useful, | ||
111 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
112 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
113 | +# GNU General Public License for more details. | ||
114 | +# | ||
115 | +# You should have received a copy of the GNU General Public License | ||
116 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. | ||
117 | +# | ||
78 | + | 118 | + |
79 | +_launch_qemu \ | 119 | +import json |
80 | + -drive file="${TEST_IMG}.base",cache=$CACHEMODE,driver=$IMGFMT,id=disk | 120 | +import iotests |
81 | +h=$QEMU_HANDLE | 121 | +from iotests import qemu_nbd_popen, qemu_img_pipe, log, file_path |
82 | +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' | ||
83 | + | 122 | + |
84 | +echo | 123 | +iotests.script_initialize(supported_fmts=['parallels']) |
85 | +echo === Creating backing chain === | ||
86 | +echo | ||
87 | + | 124 | + |
88 | +_send_qemu_cmd $h \ | 125 | +nbd_sock = file_path('nbd-sock', base_dir=iotests.sock_dir) |
89 | + "{ 'execute': 'blockdev-snapshot-sync', | 126 | +disk = iotests.file_path('disk') |
90 | + 'arguments': { 'device': 'disk', | 127 | +bitmap = 'e4f2eed0-37fe-4539-b50b-85d2e7fd235f' |
91 | + 'snapshot-file': '$TEST_IMG.mid', | 128 | +nbd_opts = f'driver=nbd,server.type=unix,server.path={nbd_sock}' \ |
92 | + 'format': '$IMGFMT', | 129 | + f',x-dirty-bitmap=qemu:dirty-bitmap:{bitmap}' |
93 | + 'mode': 'absolute-paths' } }" \ | ||
94 | + "return" | ||
95 | + | 130 | + |
96 | +_send_qemu_cmd $h \ | ||
97 | + "{ 'execute': 'human-monitor-command', | ||
98 | + 'arguments': { 'command-line': | ||
99 | + 'qemu-io disk \"write 0 4M\"' } }" \ | ||
100 | + "return" | ||
101 | + | 131 | + |
102 | +_send_qemu_cmd $h \ | 132 | +iotests.unarchive_sample_image('parallels-with-bitmap', disk) |
103 | + "{ 'execute': 'blockdev-snapshot-sync', | ||
104 | + 'arguments': { 'device': 'disk', | ||
105 | + 'snapshot-file': '$TEST_IMG', | ||
106 | + 'format': '$IMGFMT', | ||
107 | + 'mode': 'absolute-paths' } }" \ | ||
108 | + "return" | ||
109 | + | 133 | + |
110 | +echo | ||
111 | +echo === Start commit job and exit qemu === | ||
112 | +echo | ||
113 | + | 134 | + |
114 | +# Note that the reference output intentionally includes the 'offset' field in | 135 | +with qemu_nbd_popen('--read-only', f'--socket={nbd_sock}', |
115 | +# BLOCK_JOB_CANCELLED events for all of the following block jobs. They are | 136 | + f'--bitmap={bitmap}', '-f', iotests.imgfmt, disk): |
116 | +# predictable and any change in the offsets would hint at a bug in the job | 137 | + out = qemu_img_pipe('map', '--output=json', '--image-opts', nbd_opts) |
117 | +# throttling code. | 138 | + chunks = json.loads(out) |
118 | +# | 139 | + cluster = 64 * 1024 |
119 | +# In order to achieve these predictable offsets, all of the following tests | ||
120 | +# use speed=65536. Each job will perform exactly one iteration before it has | ||
121 | +# to sleep at least for a second, which is plenty of time for the 'quit' QMP | ||
122 | +# command to be received (after receiving the command, the rest runs | ||
123 | +# synchronously, so jobs can arbitrarily continue or complete). | ||
124 | +# | ||
125 | +# The buffer size for commit and streaming is 512k (waiting for 8 seconds after | ||
126 | +# the first request), for active commit and mirror it's large enough to cover | ||
127 | +# the full 4M, and for backup it's the qcow2 cluster size, which we know is | ||
128 | +# 64k. As all of these are at least as large as the speed, we are sure that the | ||
129 | +# offset doesn't advance after the first iteration before qemu exits. | ||
130 | + | 140 | + |
131 | +_send_qemu_cmd $h \ | 141 | + log('dirty clusters (cluster size is 64K):') |
132 | + "{ 'execute': 'block-commit', | 142 | + for c in chunks: |
133 | + 'arguments': { 'device': 'disk', | 143 | + assert c['start'] % cluster == 0 |
134 | + 'base':'$TEST_IMG.base', | 144 | + assert c['length'] % cluster == 0 |
135 | + 'top': '$TEST_IMG.mid', | 145 | + if c['data']: |
136 | + 'speed': 65536 } }" \ | 146 | + continue |
137 | + "return" | ||
138 | + | 147 | + |
139 | +_send_qemu_cmd $h "{ 'execute': 'quit' }" "return" | 148 | + a = c['start'] // cluster |
140 | +wait=1 _cleanup_qemu | 149 | + b = (c['start'] + c['length']) // cluster |
141 | + | 150 | + if b - a > 1: |
142 | +echo | 151 | + log(f'{a}-{b-1}') |
143 | +echo === Start active commit job and exit qemu === | 152 | + else: |
144 | +echo | 153 | + log(a) |
145 | + | 154 | diff --git a/tests/qemu-iotests/tests/parallels-read-bitmap.out b/tests/qemu-iotests/tests/parallels-read-bitmap.out |
146 | +_launch_qemu \ | ||
147 | + -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk | ||
148 | +h=$QEMU_HANDLE | ||
149 | +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' | ||
150 | + | ||
151 | +_send_qemu_cmd $h \ | ||
152 | + "{ 'execute': 'block-commit', | ||
153 | + 'arguments': { 'device': 'disk', | ||
154 | + 'base':'$TEST_IMG.base', | ||
155 | + 'speed': 65536 } }" \ | ||
156 | + "return" | ||
157 | + | ||
158 | +_send_qemu_cmd $h "{ 'execute': 'quit' }" "return" | ||
159 | +wait=1 _cleanup_qemu | ||
160 | + | ||
161 | +echo | ||
162 | +echo === Start mirror job and exit qemu === | ||
163 | +echo | ||
164 | + | ||
165 | +_launch_qemu \ | ||
166 | + -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk | ||
167 | +h=$QEMU_HANDLE | ||
168 | +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' | ||
169 | + | ||
170 | +_send_qemu_cmd $h \ | ||
171 | + "{ 'execute': 'drive-mirror', | ||
172 | + 'arguments': { 'device': 'disk', | ||
173 | + 'target': '$TEST_IMG.copy', | ||
174 | + 'format': '$IMGFMT', | ||
175 | + 'sync': 'full', | ||
176 | + 'speed': 65536 } }" \ | ||
177 | + "return" | ||
178 | + | ||
179 | +_send_qemu_cmd $h "{ 'execute': 'quit' }" "return" | ||
180 | +wait=1 _cleanup_qemu | ||
181 | + | ||
182 | +echo | ||
183 | +echo === Start backup job and exit qemu === | ||
184 | +echo | ||
185 | + | ||
186 | +_launch_qemu \ | ||
187 | + -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk | ||
188 | +h=$QEMU_HANDLE | ||
189 | +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' | ||
190 | + | ||
191 | +_send_qemu_cmd $h \ | ||
192 | + "{ 'execute': 'drive-backup', | ||
193 | + 'arguments': { 'device': 'disk', | ||
194 | + 'target': '$TEST_IMG.copy', | ||
195 | + 'format': '$IMGFMT', | ||
196 | + 'sync': 'full', | ||
197 | + 'speed': 65536 } }" \ | ||
198 | + "return" | ||
199 | + | ||
200 | +_send_qemu_cmd $h "{ 'execute': 'quit' }" "return" | ||
201 | +wait=1 _cleanup_qemu | ||
202 | + | ||
203 | +echo | ||
204 | +echo === Start streaming job and exit qemu === | ||
205 | +echo | ||
206 | + | ||
207 | +_launch_qemu \ | ||
208 | + -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk | ||
209 | +h=$QEMU_HANDLE | ||
210 | +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' | ||
211 | + | ||
212 | +_send_qemu_cmd $h \ | ||
213 | + "{ 'execute': 'block-stream', | ||
214 | + 'arguments': { 'device': 'disk', | ||
215 | + 'speed': 65536 } }" \ | ||
216 | + "return" | ||
217 | + | ||
218 | +_send_qemu_cmd $h "{ 'execute': 'quit' }" "return" | ||
219 | +wait=1 _cleanup_qemu | ||
220 | + | ||
221 | +_check_test_img | ||
222 | + | ||
223 | +# success, all done | ||
224 | +echo "*** done" | ||
225 | +rm -f $seq.full | ||
226 | +status=0 | ||
227 | diff --git a/tests/qemu-iotests/185.out b/tests/qemu-iotests/185.out | ||
228 | new file mode 100644 | 155 | new file mode 100644 |
229 | index XXXXXXX..XXXXXXX | 156 | index XXXXXXX..XXXXXXX |
230 | --- /dev/null | 157 | --- /dev/null |
231 | +++ b/tests/qemu-iotests/185.out | 158 | +++ b/tests/qemu-iotests/tests/parallels-read-bitmap.out |
232 | @@ -XXX,XX +XXX,XX @@ | 159 | @@ -XXX,XX +XXX,XX @@ |
233 | +QA output created by 185 | 160 | +Start NBD server |
234 | +Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864 | 161 | +dirty clusters (cluster size is 64K): |
235 | + | 162 | +5-6 |
236 | +=== Starting VM === | 163 | +10-12 |
237 | + | 164 | +30 |
238 | +{"return": {}} | 165 | +Kill NBD server |
239 | + | ||
240 | +=== Creating backing chain === | ||
241 | + | ||
242 | +Formatting 'TEST_DIR/t.qcow2.mid', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.base backing_fmt=qcow2 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16 | ||
243 | +{"return": {}} | ||
244 | +wrote 4194304/4194304 bytes at offset 0 | ||
245 | +4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
246 | +{"return": ""} | ||
247 | +Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.qcow2.mid backing_fmt=qcow2 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16 | ||
248 | +{"return": {}} | ||
249 | + | ||
250 | +=== Start commit job and exit qemu === | ||
251 | + | ||
252 | +{"return": {}} | ||
253 | +{"return": {}} | ||
254 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} | ||
255 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 524288, "speed": 65536, "type": "commit"}} | ||
256 | + | ||
257 | +=== Start active commit job and exit qemu === | ||
258 | + | ||
259 | +{"return": {}} | ||
260 | +{"return": {}} | ||
261 | +{"return": {}} | ||
262 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} | ||
263 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "commit"}} | ||
264 | + | ||
265 | +=== Start mirror job and exit qemu === | ||
266 | + | ||
267 | +{"return": {}} | ||
268 | +Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16 | ||
269 | +{"return": {}} | ||
270 | +{"return": {}} | ||
271 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} | ||
272 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "mirror"}} | ||
273 | + | ||
274 | +=== Start backup job and exit qemu === | ||
275 | + | ||
276 | +{"return": {}} | ||
277 | +Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 encryption=off cluster_size=65536 lazy_refcounts=off refcount_bits=16 | ||
278 | +{"return": {}} | ||
279 | +{"return": {}} | ||
280 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} | ||
281 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 65536, "speed": 65536, "type": "backup"}} | ||
282 | + | ||
283 | +=== Start streaming job and exit qemu === | ||
284 | + | ||
285 | +{"return": {}} | ||
286 | +{"return": {}} | ||
287 | +{"return": {}} | ||
288 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} | ||
289 | +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 524288, "speed": 65536, "type": "stream"}} | ||
290 | +No errors were found on the image. | ||
291 | +*** done | ||
292 | diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group | ||
293 | index XXXXXXX..XXXXXXX 100644 | ||
294 | --- a/tests/qemu-iotests/group | ||
295 | +++ b/tests/qemu-iotests/group | ||
296 | @@ -XXX,XX +XXX,XX @@ | ||
297 | 181 rw auto migration | ||
298 | 182 rw auto quick | ||
299 | 183 rw auto migration | ||
300 | +185 rw auto | ||
301 | -- | 166 | -- |
302 | 1.8.3.1 | 167 | 2.29.2 |
303 | 168 | ||
304 | 169 | diff view generated by jsdifflib |
1 | After _cleanup_qemu(), test cases should be able to start the next qemu | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | process and call _cleanup_qemu() for that one as well. For this to work | ||
3 | cleanly, we need to improve the cleanup so that the second invocation | ||
4 | doesn't try to kill the qemu instances from the first invocation a | ||
5 | second time (which would result in error messages). | ||
6 | 2 | ||
3 | Add new parallels-ext.c and myself as co-maintainer. | ||
4 | |||
5 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
6 | Message-Id: <20210304095151.19358-1-vsementsov@virtuozzo.com> | ||
7 | Reviewed-by: Denis V. Lunev <den@openvz.org> | ||
7 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
8 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
9 | Reviewed-by: Max Reitz <mreitz@redhat.com> | ||
10 | --- | 9 | --- |
11 | tests/qemu-iotests/common.qemu | 3 +++ | 10 | MAINTAINERS | 3 +++ |
12 | 1 file changed, 3 insertions(+) | 11 | 1 file changed, 3 insertions(+) |
13 | 12 | ||
14 | diff --git a/tests/qemu-iotests/common.qemu b/tests/qemu-iotests/common.qemu | 13 | diff --git a/MAINTAINERS b/MAINTAINERS |
15 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/tests/qemu-iotests/common.qemu | 15 | --- a/MAINTAINERS |
17 | +++ b/tests/qemu-iotests/common.qemu | 16 | +++ b/MAINTAINERS |
18 | @@ -XXX,XX +XXX,XX @@ function _cleanup_qemu() | 17 | @@ -XXX,XX +XXX,XX @@ F: block/dmg.c |
19 | rm -f "${QEMU_FIFO_IN}_${i}" "${QEMU_FIFO_OUT}_${i}" | 18 | parallels |
20 | eval "exec ${QEMU_IN[$i]}<&-" # close file descriptors | 19 | M: Stefan Hajnoczi <stefanha@redhat.com> |
21 | eval "exec ${QEMU_OUT[$i]}<&-" | 20 | M: Denis V. Lunev <den@openvz.org> |
22 | + | 21 | +M: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
23 | + unset QEMU_IN[$i] | 22 | L: qemu-block@nongnu.org |
24 | + unset QEMU_OUT[$i] | 23 | S: Supported |
25 | done | 24 | F: block/parallels.c |
26 | } | 25 | +F: block/parallels-ext.c |
26 | F: docs/interop/parallels.txt | ||
27 | +T: git https://src.openvz.org/scm/~vsementsov/qemu.git parallels | ||
28 | |||
29 | qed | ||
30 | M: Stefan Hajnoczi <stefanha@redhat.com> | ||
27 | -- | 31 | -- |
28 | 1.8.3.1 | 32 | 2.29.2 |
29 | 33 | ||
30 | 34 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | This adds documentation for the -blockdev options that apply to all | ||
2 | nodes independent of the block driver used. | ||
3 | 1 | ||
4 | All options that are shared by -blockdev and -drive are now explained in | ||
5 | the section for -blockdev. The documentation of -drive mentions that all | ||
6 | -blockdev options are accepted as well. | ||
7 | |||
8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
9 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
10 | Reviewed-by: Max Reitz <mreitz@redhat.com> | ||
11 | --- | ||
12 | qemu-options.hx | 108 +++++++++++++++++++++++++++++++++++++++++--------------- | ||
13 | 1 file changed, 79 insertions(+), 29 deletions(-) | ||
14 | |||
15 | diff --git a/qemu-options.hx b/qemu-options.hx | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/qemu-options.hx | ||
18 | +++ b/qemu-options.hx | ||
19 | @@ -XXX,XX +XXX,XX @@ DEF("blockdev", HAS_ARG, QEMU_OPTION_blockdev, | ||
20 | " [,read-only=on|off][,detect-zeroes=on|off|unmap]\n" | ||
21 | " [,driver specific parameters...]\n" | ||
22 | " configure a block backend\n", QEMU_ARCH_ALL) | ||
23 | +STEXI | ||
24 | +@item -blockdev @var{option}[,@var{option}[,@var{option}[,...]]] | ||
25 | +@findex -blockdev | ||
26 | + | ||
27 | +Define a new block driver node. | ||
28 | + | ||
29 | +@table @option | ||
30 | +@item Valid options for any block driver node: | ||
31 | + | ||
32 | +@table @code | ||
33 | +@item driver | ||
34 | +Specifies the block driver to use for the given node. | ||
35 | +@item node-name | ||
36 | +This defines the name of the block driver node by which it will be referenced | ||
37 | +later. The name must be unique, i.e. it must not match the name of a different | ||
38 | +block driver node, or (if you use @option{-drive} as well) the ID of a drive. | ||
39 | + | ||
40 | +If no node name is specified, it is automatically generated. The generated node | ||
41 | +name is not intended to be predictable and changes between QEMU invocations. | ||
42 | +For the top level, an explicit node name must be specified. | ||
43 | +@item read-only | ||
44 | +Open the node read-only. Guest write attempts will fail. | ||
45 | +@item cache.direct | ||
46 | +The host page cache can be avoided with @option{cache.direct=on}. This will | ||
47 | +attempt to do disk IO directly to the guest's memory. QEMU may still perform an | ||
48 | +internal copy of the data. | ||
49 | +@item cache.no-flush | ||
50 | +In case you don't care about data integrity over host failures, you can use | ||
51 | +@option{cache.no-flush=on}. This option tells QEMU that it never needs to write | ||
52 | +any data to the disk but can instead keep things in cache. If anything goes | ||
53 | +wrong, like your host losing power, the disk storage getting disconnected | ||
54 | +accidentally, etc. your image will most probably be rendered unusable. | ||
55 | +@item discard=@var{discard} | ||
56 | +@var{discard} is one of "ignore" (or "off") or "unmap" (or "on") and controls | ||
57 | +whether @code{discard} (also known as @code{trim} or @code{unmap}) requests are | ||
58 | +ignored or passed to the filesystem. Some machine types may not support | ||
59 | +discard requests. | ||
60 | +@item detect-zeroes=@var{detect-zeroes} | ||
61 | +@var{detect-zeroes} is "off", "on" or "unmap" and enables the automatic | ||
62 | +conversion of plain zero writes by the OS to driver specific optimized | ||
63 | +zero write commands. You may even choose "unmap" if @var{discard} is set | ||
64 | +to "unmap" to allow a zero write to be converted to an @code{unmap} operation. | ||
65 | +@end table | ||
66 | + | ||
67 | +@end table | ||
68 | + | ||
69 | +ETEXI | ||
70 | |||
71 | DEF("drive", HAS_ARG, QEMU_OPTION_drive, | ||
72 | "-drive [file=file][,if=type][,bus=n][,unit=m][,media=d][,index=i]\n" | ||
73 | @@ -XXX,XX +XXX,XX @@ STEXI | ||
74 | @item -drive @var{option}[,@var{option}[,@var{option}[,...]]] | ||
75 | @findex -drive | ||
76 | |||
77 | -Define a new drive. Valid options are: | ||
78 | +Define a new drive. This includes creating a block driver node (the backend) as | ||
79 | +well as a guest device, and is mostly a shortcut for defining the corresponding | ||
80 | +@option{-blockdev} and @option{-device} options. | ||
81 | + | ||
82 | +@option{-drive} accepts all options that are accepted by @option{-blockdev}. In | ||
83 | +addition, it knows the following options: | ||
84 | |||
85 | @table @option | ||
86 | @item file=@var{file} | ||
87 | @@ -XXX,XX +XXX,XX @@ These options have the same definition as they have in @option{-hdachs}. | ||
88 | @var{snapshot} is "on" or "off" and controls snapshot mode for the given drive | ||
89 | (see @option{-snapshot}). | ||
90 | @item cache=@var{cache} | ||
91 | -@var{cache} is "none", "writeback", "unsafe", "directsync" or "writethrough" and controls how the host cache is used to access block data. | ||
92 | +@var{cache} is "none", "writeback", "unsafe", "directsync" or "writethrough" | ||
93 | +and controls how the host cache is used to access block data. This is a | ||
94 | +shortcut that sets the @option{cache.direct} and @option{cache.no-flush} | ||
95 | +options (as in @option{-blockdev}), and additionally @option{cache.writeback}, | ||
96 | +which provides a default for the @option{write-cache} option of block guest | ||
97 | +devices (as in @option{-device}). The modes correspond to the following | ||
98 | +settings: | ||
99 | + | ||
100 | +@c Our texi2pod.pl script doesn't support @multitable, so fall back to using | ||
101 | +@c plain ASCII art (well, UTF-8 art really). This looks okay both in the manpage | ||
102 | +@c and the HTML output. | ||
103 | +@example | ||
104 | +@ │ cache.writeback cache.direct cache.no-flush | ||
105 | +─────────────┼───────────────────────────────────────────────── | ||
106 | +writeback │ on off off | ||
107 | +none │ on on off | ||
108 | +writethrough │ off off off | ||
109 | +directsync │ off on off | ||
110 | +unsafe │ on off on | ||
111 | +@end example | ||
112 | + | ||
113 | +The default mode is @option{cache=writeback}. | ||
114 | + | ||
115 | @item aio=@var{aio} | ||
116 | @var{aio} is "threads", or "native" and selects between pthread based disk I/O and native Linux AIO. | ||
117 | -@item discard=@var{discard} | ||
118 | -@var{discard} is one of "ignore" (or "off") or "unmap" (or "on") and controls whether @dfn{discard} (also known as @dfn{trim} or @dfn{unmap}) requests are ignored or passed to the filesystem. Some machine types may not support discard requests. | ||
119 | @item format=@var{format} | ||
120 | Specify which disk @var{format} will be used rather than detecting | ||
121 | the format. Can be used to specify format=raw to avoid interpreting | ||
122 | @@ -XXX,XX +XXX,XX @@ Specify which @var{action} to take on write and read errors. Valid actions are: | ||
123 | "report" (report the error to the guest), "enospc" (pause QEMU only if the | ||
124 | host disk is full; report the error to the guest otherwise). | ||
125 | The default setting is @option{werror=enospc} and @option{rerror=report}. | ||
126 | -@item readonly | ||
127 | -Open drive @option{file} as read-only. Guest write attempts will fail. | ||
128 | @item copy-on-read=@var{copy-on-read} | ||
129 | @var{copy-on-read} is "on" or "off" and enables whether to copy read backing | ||
130 | file sectors into the image file. | ||
131 | -@item detect-zeroes=@var{detect-zeroes} | ||
132 | -@var{detect-zeroes} is "off", "on" or "unmap" and enables the automatic | ||
133 | -conversion of plain zero writes by the OS to driver specific optimized | ||
134 | -zero write commands. You may even choose "unmap" if @var{discard} is set | ||
135 | -to "unmap" to allow a zero write to be converted to an UNMAP operation. | ||
136 | @item bps=@var{b},bps_rd=@var{r},bps_wr=@var{w} | ||
137 | Specify bandwidth throttling limits in bytes per second, either for all request | ||
138 | types or for reads or writes only. Small values can lead to timeouts or hangs | ||
139 | @@ -XXX,XX +XXX,XX @@ prevent guests from circumventing throttling limits by using many small disks | ||
140 | instead of a single larger disk. | ||
141 | @end table | ||
142 | |||
143 | -By default, the @option{cache=writeback} mode is used. It will report data | ||
144 | +By default, the @option{cache.writeback=on} mode is used. It will report data | ||
145 | writes as completed as soon as the data is present in the host page cache. | ||
146 | This is safe as long as your guest OS makes sure to correctly flush disk caches | ||
147 | where needed. If your guest OS does not handle volatile disk write caches | ||
148 | correctly and your host crashes or loses power, then the guest may experience | ||
149 | data corruption. | ||
150 | |||
151 | -For such guests, you should consider using @option{cache=writethrough}. This | ||
152 | +For such guests, you should consider using @option{cache.writeback=off}. This | ||
153 | means that the host page cache will be used to read and write data, but write | ||
154 | notification will be sent to the guest only after QEMU has made sure to flush | ||
155 | each write to the disk. Be aware that this has a major impact on performance. | ||
156 | |||
157 | -The host page cache can be avoided entirely with @option{cache=none}. This will | ||
158 | -attempt to do disk IO directly to the guest's memory. QEMU may still perform | ||
159 | -an internal copy of the data. Note that this is considered a writeback mode and | ||
160 | -the guest OS must handle the disk write cache correctly in order to avoid data | ||
161 | -corruption on host crashes. | ||
162 | - | ||
163 | -The host page cache can be avoided while only sending write notifications to | ||
164 | -the guest when the data has been flushed to the disk using | ||
165 | -@option{cache=directsync}. | ||
166 | - | ||
167 | -In case you don't care about data integrity over host failures, use | ||
168 | -@option{cache=unsafe}. This option tells QEMU that it never needs to write any | ||
169 | -data to the disk but can instead keep things in cache. If anything goes wrong, | ||
170 | -like your host losing power, the disk storage getting disconnected accidentally, | ||
171 | -etc. your image will most probably be rendered unusable. When using | ||
172 | -the @option{-snapshot} option, unsafe caching is always used. | ||
173 | +When using the @option{-snapshot} option, unsafe caching is always used. | ||
174 | |||
175 | Copy-on-read avoids accessing the same backing file sectors repeatedly and is | ||
176 | useful when the backing file is over a slow network. By default copy-on-read | ||
177 | -- | ||
178 | 1.8.3.1 | ||
179 | |||
180 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | This documents the driver-specific options for the raw, qcow2 and file | ||
2 | block drivers for the man page. For everything else, we refer to the | ||
3 | QAPI documentation. | ||
4 | 1 | ||
5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
6 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
7 | Reviewed-by: Max Reitz <mreitz@redhat.com> | ||
8 | --- | ||
9 | qemu-options.hx | 115 +++++++++++++++++++++++++++++++++++++++++++++++++++++++- | ||
10 | 1 file changed, 114 insertions(+), 1 deletion(-) | ||
11 | |||
12 | diff --git a/qemu-options.hx b/qemu-options.hx | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/qemu-options.hx | ||
15 | +++ b/qemu-options.hx | ||
16 | @@ -XXX,XX +XXX,XX @@ STEXI | ||
17 | @item -blockdev @var{option}[,@var{option}[,@var{option}[,...]]] | ||
18 | @findex -blockdev | ||
19 | |||
20 | -Define a new block driver node. | ||
21 | +Define a new block driver node. Some of the options apply to all block drivers, | ||
22 | +other options are only accepted for a specific block driver. See below for a | ||
23 | +list of generic options and options for the most common block drivers. | ||
24 | + | ||
25 | +Options that expect a reference to another node (e.g. @code{file}) can be | ||
26 | +given in two ways. Either you specify the node name of an already existing node | ||
27 | +(file=@var{node-name}), or you define a new node inline, adding options | ||
28 | +for the referenced node after a dot (file.filename=@var{path},file.aio=native). | ||
29 | + | ||
30 | +A block driver node created with @option{-blockdev} can be used for a guest | ||
31 | +device by specifying its node name for the @code{drive} property in a | ||
32 | +@option{-device} argument that defines a block device. | ||
33 | |||
34 | @table @option | ||
35 | @item Valid options for any block driver node: | ||
36 | @@ -XXX,XX +XXX,XX @@ zero write commands. You may even choose "unmap" if @var{discard} is set | ||
37 | to "unmap" to allow a zero write to be converted to an @code{unmap} operation. | ||
38 | @end table | ||
39 | |||
40 | +@item Driver-specific options for @code{file} | ||
41 | + | ||
42 | +This is the protocol-level block driver for accessing regular files. | ||
43 | + | ||
44 | +@table @code | ||
45 | +@item filename | ||
46 | +The path to the image file in the local filesystem | ||
47 | +@item aio | ||
48 | +Specifies the AIO backend (threads/native, default: threads) | ||
49 | +@end table | ||
50 | +Example: | ||
51 | +@example | ||
52 | +-blockdev driver=file,node-name=disk,filename=disk.img | ||
53 | +@end example | ||
54 | + | ||
55 | +@item Driver-specific options for @code{raw} | ||
56 | + | ||
57 | +This is the image format block driver for raw images. It is usually | ||
58 | +stacked on top of a protocol level block driver such as @code{file}. | ||
59 | + | ||
60 | +@table @code | ||
61 | +@item file | ||
62 | +Reference to or definition of the data source block driver node | ||
63 | +(e.g. a @code{file} driver node) | ||
64 | +@end table | ||
65 | +Example 1: | ||
66 | +@example | ||
67 | +-blockdev driver=file,node-name=disk_file,filename=disk.img | ||
68 | +-blockdev driver=raw,node-name=disk,file=disk_file | ||
69 | +@end example | ||
70 | +Example 2: | ||
71 | +@example | ||
72 | +-blockdev driver=raw,node-name=disk,file.driver=file,file.filename=disk.img | ||
73 | +@end example | ||
74 | + | ||
75 | +@item Driver-specific options for @code{qcow2} | ||
76 | + | ||
77 | +This is the image format block driver for qcow2 images. It is usually | ||
78 | +stacked on top of a protocol level block driver such as @code{file}. | ||
79 | + | ||
80 | +@table @code | ||
81 | +@item file | ||
82 | +Reference to or definition of the data source block driver node | ||
83 | +(e.g. a @code{file} driver node) | ||
84 | + | ||
85 | +@item backing | ||
86 | +Reference to or definition of the backing file block device (default is taken | ||
87 | +from the image file). It is allowed to pass an empty string here in order to | ||
88 | +disable the default backing file. | ||
89 | + | ||
90 | +@item lazy-refcounts | ||
91 | +Whether to enable the lazy refcounts feature (on/off; default is taken from the | ||
92 | +image file) | ||
93 | + | ||
94 | +@item cache-size | ||
95 | +The maximum total size of the L2 table and refcount block caches in bytes | ||
96 | +(default: 1048576 bytes or 8 clusters, whichever is larger) | ||
97 | + | ||
98 | +@item l2-cache-size | ||
99 | +The maximum size of the L2 table cache in bytes | ||
100 | +(default: 4/5 of the total cache size) | ||
101 | + | ||
102 | +@item refcount-cache-size | ||
103 | +The maximum size of the refcount block cache in bytes | ||
104 | +(default: 1/5 of the total cache size) | ||
105 | + | ||
106 | +@item cache-clean-interval | ||
107 | +Clean unused entries in the L2 and refcount caches. The interval is in seconds. | ||
108 | +The default value is 0 and it disables this feature. | ||
109 | + | ||
110 | +@item pass-discard-request | ||
111 | +Whether discard requests to the qcow2 device should be forwarded to the data | ||
112 | +source (on/off; default: on if discard=unmap is specified, off otherwise) | ||
113 | + | ||
114 | +@item pass-discard-snapshot | ||
115 | +Whether discard requests for the data source should be issued when a snapshot | ||
116 | +operation (e.g. deleting a snapshot) frees clusters in the qcow2 file (on/off; | ||
117 | +default: on) | ||
118 | + | ||
119 | +@item pass-discard-other | ||
120 | +Whether discard requests for the data source should be issued on other | ||
121 | +occasions where a cluster gets freed (on/off; default: off) | ||
122 | + | ||
123 | +@item overlap-check | ||
124 | +Which overlap checks to perform for writes to the image | ||
125 | +(none/constant/cached/all; default: cached). For details or finer | ||
126 | +granularity control refer to the QAPI documentation of @code{blockdev-add}. | ||
127 | +@end table | ||
128 | + | ||
129 | +Example 1: | ||
130 | +@example | ||
131 | +-blockdev driver=file,node-name=my_file,filename=/tmp/disk.qcow2 | ||
132 | +-blockdev driver=qcow2,node-name=hda,file=my_file,overlap-check=none,cache-size=16777216 | ||
133 | +@end example | ||
134 | +Example 2: | ||
135 | +@example | ||
136 | +-blockdev driver=qcow2,node-name=disk,file.driver=http,file.filename=http://example.com/image.qcow2 | ||
137 | +@end example | ||
138 | + | ||
139 | +@item Driver-specific options for other drivers | ||
140 | +Please refer to the QAPI documentation of the @code{blockdev-add} QMP command. | ||
141 | + | ||
142 | @end table | ||
143 | |||
144 | ETEXI | ||
145 | -- | ||
146 | 1.8.3.1 | ||
147 | |||
148 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
2 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
3 | --- | ||
4 | block/qed-cluster.c | 39 ++++++++++++++++++++++----------------- | ||
5 | block/qed.c | 24 +++++++++++------------- | ||
6 | block/qed.h | 4 ++-- | ||
7 | 3 files changed, 35 insertions(+), 32 deletions(-) | ||
8 | 1 | ||
9 | diff --git a/block/qed-cluster.c b/block/qed-cluster.c | ||
10 | index XXXXXXX..XXXXXXX 100644 | ||
11 | --- a/block/qed-cluster.c | ||
12 | +++ b/block/qed-cluster.c | ||
13 | @@ -XXX,XX +XXX,XX @@ static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s, | ||
14 | * @s: QED state | ||
15 | * @request: L2 cache entry | ||
16 | * @pos: Byte position in device | ||
17 | - * @len: Number of bytes | ||
18 | - * @cb: Completion function | ||
19 | - * @opaque: User data for completion function | ||
20 | + * @len: Number of bytes (may be shortened on return) | ||
21 | + * @img_offset: Contains offset in the image file on success | ||
22 | * | ||
23 | * This function translates a position in the block device to an offset in the | ||
24 | - * image file. It invokes the cb completion callback to report back the | ||
25 | - * translated offset or unallocated range in the image file. | ||
26 | + * image file. The translated offset or unallocated range in the image file is | ||
27 | + * reported back in *img_offset and *len. | ||
28 | * | ||
29 | * If the L2 table exists, request->l2_table points to the L2 table cache entry | ||
30 | * and the caller must free the reference when they are finished. The cache | ||
31 | * entry is exposed in this way to avoid callers having to read the L2 table | ||
32 | * again later during request processing. If request->l2_table is non-NULL it | ||
33 | * will be unreferenced before taking on the new cache entry. | ||
34 | + * | ||
35 | + * On success QED_CLUSTER_FOUND is returned and img_offset/len are a contiguous | ||
36 | + * range in the image file. | ||
37 | + * | ||
38 | + * On failure QED_CLUSTER_L2 or QED_CLUSTER_L1 is returned for missing L2 or L1 | ||
39 | + * table offset, respectively. len is number of contiguous unallocated bytes. | ||
40 | */ | ||
41 | -void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
42 | - size_t len, QEDFindClusterFunc *cb, void *opaque) | ||
43 | +int qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
44 | + size_t *len, uint64_t *img_offset) | ||
45 | { | ||
46 | uint64_t l2_offset; | ||
47 | uint64_t offset = 0; | ||
48 | @@ -XXX,XX +XXX,XX @@ void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
49 | /* Limit length to L2 boundary. Requests are broken up at the L2 boundary | ||
50 | * so that a request acts on one L2 table at a time. | ||
51 | */ | ||
52 | - len = MIN(len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos); | ||
53 | + *len = MIN(*len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos); | ||
54 | |||
55 | l2_offset = s->l1_table->offsets[qed_l1_index(s, pos)]; | ||
56 | if (qed_offset_is_unalloc_cluster(l2_offset)) { | ||
57 | - cb(opaque, QED_CLUSTER_L1, 0, len); | ||
58 | - return; | ||
59 | + *img_offset = 0; | ||
60 | + return QED_CLUSTER_L1; | ||
61 | } | ||
62 | if (!qed_check_table_offset(s, l2_offset)) { | ||
63 | - cb(opaque, -EINVAL, 0, 0); | ||
64 | - return; | ||
65 | + *img_offset = *len = 0; | ||
66 | + return -EINVAL; | ||
67 | } | ||
68 | |||
69 | ret = qed_read_l2_table(s, request, l2_offset); | ||
70 | @@ -XXX,XX +XXX,XX @@ void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
71 | } | ||
72 | |||
73 | index = qed_l2_index(s, pos); | ||
74 | - n = qed_bytes_to_clusters(s, | ||
75 | - qed_offset_into_cluster(s, pos) + len); | ||
76 | + n = qed_bytes_to_clusters(s, qed_offset_into_cluster(s, pos) + *len); | ||
77 | n = qed_count_contiguous_clusters(s, request->l2_table->table, | ||
78 | index, n, &offset); | ||
79 | |||
80 | @@ -XXX,XX +XXX,XX @@ void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
81 | ret = -EINVAL; | ||
82 | } | ||
83 | |||
84 | - len = MIN(len, | ||
85 | - n * s->header.cluster_size - qed_offset_into_cluster(s, pos)); | ||
86 | + *len = MIN(*len, | ||
87 | + n * s->header.cluster_size - qed_offset_into_cluster(s, pos)); | ||
88 | |||
89 | out: | ||
90 | - cb(opaque, ret, offset, len); | ||
91 | + *img_offset = offset; | ||
92 | qed_release(s); | ||
93 | + return ret; | ||
94 | } | ||
95 | diff --git a/block/qed.c b/block/qed.c | ||
96 | index XXXXXXX..XXXXXXX 100644 | ||
97 | --- a/block/qed.c | ||
98 | +++ b/block/qed.c | ||
99 | @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs, | ||
100 | .file = file, | ||
101 | }; | ||
102 | QEDRequest request = { .l2_table = NULL }; | ||
103 | + uint64_t offset; | ||
104 | + int ret; | ||
105 | |||
106 | - qed_find_cluster(s, &request, cb.pos, len, qed_is_allocated_cb, &cb); | ||
107 | + ret = qed_find_cluster(s, &request, cb.pos, &len, &offset); | ||
108 | + qed_is_allocated_cb(&cb, ret, offset, len); | ||
109 | |||
110 | - /* Now sleep if the callback wasn't invoked immediately */ | ||
111 | - while (cb.status == BDRV_BLOCK_OFFSET_MASK) { | ||
112 | - cb.co = qemu_coroutine_self(); | ||
113 | - qemu_coroutine_yield(); | ||
114 | - } | ||
115 | + /* The callback was invoked immediately */ | ||
116 | + assert(cb.status != BDRV_BLOCK_OFFSET_MASK); | ||
117 | |||
118 | qed_unref_l2_cache_entry(request.l2_table); | ||
119 | |||
120 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len) | ||
121 | * or -errno | ||
122 | * @offset: Cluster offset in bytes | ||
123 | * @len: Length in bytes | ||
124 | - * | ||
125 | - * Callback from qed_find_cluster(). | ||
126 | */ | ||
127 | static void qed_aio_write_data(void *opaque, int ret, | ||
128 | uint64_t offset, size_t len) | ||
129 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_data(void *opaque, int ret, | ||
130 | * or -errno | ||
131 | * @offset: Cluster offset in bytes | ||
132 | * @len: Length in bytes | ||
133 | - * | ||
134 | - * Callback from qed_find_cluster(). | ||
135 | */ | ||
136 | static void qed_aio_read_data(void *opaque, int ret, | ||
137 | uint64_t offset, size_t len) | ||
138 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb, int ret) | ||
139 | BDRVQEDState *s = acb_to_s(acb); | ||
140 | QEDFindClusterFunc *io_fn = (acb->flags & QED_AIOCB_WRITE) ? | ||
141 | qed_aio_write_data : qed_aio_read_data; | ||
142 | + uint64_t offset; | ||
143 | + size_t len; | ||
144 | |||
145 | trace_qed_aio_next_io(s, acb, ret, acb->cur_pos + acb->cur_qiov.size); | ||
146 | |||
147 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb, int ret) | ||
148 | } | ||
149 | |||
150 | /* Find next cluster and start I/O */ | ||
151 | - qed_find_cluster(s, &acb->request, | ||
152 | - acb->cur_pos, acb->end_pos - acb->cur_pos, | ||
153 | - io_fn, acb); | ||
154 | + len = acb->end_pos - acb->cur_pos; | ||
155 | + ret = qed_find_cluster(s, &acb->request, acb->cur_pos, &len, &offset); | ||
156 | + io_fn(acb, ret, offset, len); | ||
157 | } | ||
158 | |||
159 | static BlockAIOCB *qed_aio_setup(BlockDriverState *bs, | ||
160 | diff --git a/block/qed.h b/block/qed.h | ||
161 | index XXXXXXX..XXXXXXX 100644 | ||
162 | --- a/block/qed.h | ||
163 | +++ b/block/qed.h | ||
164 | @@ -XXX,XX +XXX,XX @@ int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request, | ||
165 | /** | ||
166 | * Cluster functions | ||
167 | */ | ||
168 | -void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
169 | - size_t len, QEDFindClusterFunc *cb, void *opaque); | ||
170 | +int qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos, | ||
171 | + size_t *len, uint64_t *img_offset); | ||
172 | |||
173 | /** | ||
174 | * Consistency check | ||
175 | -- | ||
176 | 1.8.3.1 | ||
177 | |||
178 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | With this change, qed_aio_write_prefill() and qed_aio_write_postfill() | ||
2 | collapse into a single function. This is reflected by a rename of the | ||
3 | combined function to qed_aio_write_cow(). | ||
4 | 1 | ||
5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
6 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
7 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | --- | ||
9 | block/qed.c | 57 +++++++++++++++++++++++---------------------------------- | ||
10 | 1 file changed, 23 insertions(+), 34 deletions(-) | ||
11 | |||
12 | diff --git a/block/qed.c b/block/qed.c | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/block/qed.c | ||
15 | +++ b/block/qed.c | ||
16 | @@ -XXX,XX +XXX,XX @@ static int qed_read_backing_file(BDRVQEDState *s, uint64_t pos, | ||
17 | * @pos: Byte position in device | ||
18 | * @len: Number of bytes | ||
19 | * @offset: Byte offset in image file | ||
20 | - * @cb: Completion function | ||
21 | - * @opaque: User data for completion function | ||
22 | */ | ||
23 | -static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos, | ||
24 | - uint64_t len, uint64_t offset, | ||
25 | - BlockCompletionFunc *cb, | ||
26 | - void *opaque) | ||
27 | +static int qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos, | ||
28 | + uint64_t len, uint64_t offset) | ||
29 | { | ||
30 | QEMUIOVector qiov; | ||
31 | QEMUIOVector *backing_qiov = NULL; | ||
32 | @@ -XXX,XX +XXX,XX @@ static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos, | ||
33 | |||
34 | /* Skip copy entirely if there is no work to do */ | ||
35 | if (len == 0) { | ||
36 | - cb(opaque, 0); | ||
37 | - return; | ||
38 | + return 0; | ||
39 | } | ||
40 | |||
41 | iov = (struct iovec) { | ||
42 | @@ -XXX,XX +XXX,XX @@ static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos, | ||
43 | ret = 0; | ||
44 | out: | ||
45 | qemu_vfree(iov.iov_base); | ||
46 | - cb(opaque, ret); | ||
47 | + return ret; | ||
48 | } | ||
49 | |||
50 | /** | ||
51 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_main(void *opaque, int ret) | ||
52 | } | ||
53 | |||
54 | /** | ||
55 | - * Populate back untouched region of new data cluster | ||
56 | + * Populate untouched regions of new data cluster | ||
57 | */ | ||
58 | -static void qed_aio_write_postfill(void *opaque, int ret) | ||
59 | +static void qed_aio_write_cow(void *opaque, int ret) | ||
60 | { | ||
61 | QEDAIOCB *acb = opaque; | ||
62 | BDRVQEDState *s = acb_to_s(acb); | ||
63 | - uint64_t start = acb->cur_pos + acb->cur_qiov.size; | ||
64 | - uint64_t len = | ||
65 | - qed_start_of_cluster(s, start + s->header.cluster_size - 1) - start; | ||
66 | - uint64_t offset = acb->cur_cluster + | ||
67 | - qed_offset_into_cluster(s, acb->cur_pos) + | ||
68 | - acb->cur_qiov.size; | ||
69 | + uint64_t start, len, offset; | ||
70 | + | ||
71 | + /* Populate front untouched region of new data cluster */ | ||
72 | + start = qed_start_of_cluster(s, acb->cur_pos); | ||
73 | + len = qed_offset_into_cluster(s, acb->cur_pos); | ||
74 | |||
75 | + trace_qed_aio_write_prefill(s, acb, start, len, acb->cur_cluster); | ||
76 | + ret = qed_copy_from_backing_file(s, start, len, acb->cur_cluster); | ||
77 | if (ret) { | ||
78 | qed_aio_complete(acb, ret); | ||
79 | return; | ||
80 | } | ||
81 | |||
82 | - trace_qed_aio_write_postfill(s, acb, start, len, offset); | ||
83 | - qed_copy_from_backing_file(s, start, len, offset, | ||
84 | - qed_aio_write_main, acb); | ||
85 | -} | ||
86 | + /* Populate back untouched region of new data cluster */ | ||
87 | + start = acb->cur_pos + acb->cur_qiov.size; | ||
88 | + len = qed_start_of_cluster(s, start + s->header.cluster_size - 1) - start; | ||
89 | + offset = acb->cur_cluster + | ||
90 | + qed_offset_into_cluster(s, acb->cur_pos) + | ||
91 | + acb->cur_qiov.size; | ||
92 | |||
93 | -/** | ||
94 | - * Populate front untouched region of new data cluster | ||
95 | - */ | ||
96 | -static void qed_aio_write_prefill(void *opaque, int ret) | ||
97 | -{ | ||
98 | - QEDAIOCB *acb = opaque; | ||
99 | - BDRVQEDState *s = acb_to_s(acb); | ||
100 | - uint64_t start = qed_start_of_cluster(s, acb->cur_pos); | ||
101 | - uint64_t len = qed_offset_into_cluster(s, acb->cur_pos); | ||
102 | + trace_qed_aio_write_postfill(s, acb, start, len, offset); | ||
103 | + ret = qed_copy_from_backing_file(s, start, len, offset); | ||
104 | |||
105 | - trace_qed_aio_write_prefill(s, acb, start, len, acb->cur_cluster); | ||
106 | - qed_copy_from_backing_file(s, start, len, acb->cur_cluster, | ||
107 | - qed_aio_write_postfill, acb); | ||
108 | + qed_aio_write_main(acb, ret); | ||
109 | } | ||
110 | |||
111 | /** | ||
112 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
113 | |||
114 | cb = qed_aio_write_zero_cluster; | ||
115 | } else { | ||
116 | - cb = qed_aio_write_prefill; | ||
117 | + cb = qed_aio_write_cow; | ||
118 | acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters); | ||
119 | } | ||
120 | |||
121 | -- | ||
122 | 1.8.3.1 | ||
123 | |||
124 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
2 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
3 | --- | ||
4 | block/qed-table.c | 47 ++++++++++++----------------------------------- | ||
5 | block/qed.c | 12 +++++++----- | ||
6 | block/qed.h | 8 +++----- | ||
7 | 3 files changed, 22 insertions(+), 45 deletions(-) | ||
8 | 1 | ||
9 | diff --git a/block/qed-table.c b/block/qed-table.c | ||
10 | index XXXXXXX..XXXXXXX 100644 | ||
11 | --- a/block/qed-table.c | ||
12 | +++ b/block/qed-table.c | ||
13 | @@ -XXX,XX +XXX,XX @@ out: | ||
14 | * @index: Index of first element | ||
15 | * @n: Number of elements | ||
16 | * @flush: Whether or not to sync to disk | ||
17 | - * @cb: Completion function | ||
18 | - * @opaque: Argument for completion function | ||
19 | */ | ||
20 | -static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, | ||
21 | - unsigned int index, unsigned int n, bool flush, | ||
22 | - BlockCompletionFunc *cb, void *opaque) | ||
23 | +static int qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, | ||
24 | + unsigned int index, unsigned int n, bool flush) | ||
25 | { | ||
26 | unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1; | ||
27 | unsigned int start, end, i; | ||
28 | @@ -XXX,XX +XXX,XX @@ static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, | ||
29 | ret = 0; | ||
30 | out: | ||
31 | qemu_vfree(new_table); | ||
32 | - cb(opaque, ret); | ||
33 | -} | ||
34 | - | ||
35 | -/** | ||
36 | - * Propagate return value from async callback | ||
37 | - */ | ||
38 | -static void qed_sync_cb(void *opaque, int ret) | ||
39 | -{ | ||
40 | - *(int *)opaque = ret; | ||
41 | + return ret; | ||
42 | } | ||
43 | |||
44 | int qed_read_l1_table_sync(BDRVQEDState *s) | ||
45 | @@ -XXX,XX +XXX,XX @@ int qed_read_l1_table_sync(BDRVQEDState *s) | ||
46 | return qed_read_table(s, s->header.l1_table_offset, s->l1_table); | ||
47 | } | ||
48 | |||
49 | -void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n, | ||
50 | - BlockCompletionFunc *cb, void *opaque) | ||
51 | +int qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n) | ||
52 | { | ||
53 | BLKDBG_EVENT(s->bs->file, BLKDBG_L1_UPDATE); | ||
54 | - qed_write_table(s, s->header.l1_table_offset, | ||
55 | - s->l1_table, index, n, false, cb, opaque); | ||
56 | + return qed_write_table(s, s->header.l1_table_offset, | ||
57 | + s->l1_table, index, n, false); | ||
58 | } | ||
59 | |||
60 | int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index, | ||
61 | unsigned int n) | ||
62 | { | ||
63 | - int ret = -EINPROGRESS; | ||
64 | - | ||
65 | - qed_write_l1_table(s, index, n, qed_sync_cb, &ret); | ||
66 | - BDRV_POLL_WHILE(s->bs, ret == -EINPROGRESS); | ||
67 | - | ||
68 | - return ret; | ||
69 | + return qed_write_l1_table(s, index, n); | ||
70 | } | ||
71 | |||
72 | int qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset) | ||
73 | @@ -XXX,XX +XXX,XX @@ int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset | ||
74 | return qed_read_l2_table(s, request, offset); | ||
75 | } | ||
76 | |||
77 | -void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, | ||
78 | - unsigned int index, unsigned int n, bool flush, | ||
79 | - BlockCompletionFunc *cb, void *opaque) | ||
80 | +int qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, | ||
81 | + unsigned int index, unsigned int n, bool flush) | ||
82 | { | ||
83 | BLKDBG_EVENT(s->bs->file, BLKDBG_L2_UPDATE); | ||
84 | - qed_write_table(s, request->l2_table->offset, | ||
85 | - request->l2_table->table, index, n, flush, cb, opaque); | ||
86 | + return qed_write_table(s, request->l2_table->offset, | ||
87 | + request->l2_table->table, index, n, flush); | ||
88 | } | ||
89 | |||
90 | int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request, | ||
91 | unsigned int index, unsigned int n, bool flush) | ||
92 | { | ||
93 | - int ret = -EINPROGRESS; | ||
94 | - | ||
95 | - qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret); | ||
96 | - BDRV_POLL_WHILE(s->bs, ret == -EINPROGRESS); | ||
97 | - | ||
98 | - return ret; | ||
99 | + return qed_write_l2_table(s, request, index, n, flush); | ||
100 | } | ||
101 | diff --git a/block/qed.c b/block/qed.c | ||
102 | index XXXXXXX..XXXXXXX 100644 | ||
103 | --- a/block/qed.c | ||
104 | +++ b/block/qed.c | ||
105 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_l1_update(void *opaque, int ret) | ||
106 | index = qed_l1_index(s, acb->cur_pos); | ||
107 | s->l1_table->offsets[index] = acb->request.l2_table->offset; | ||
108 | |||
109 | - qed_write_l1_table(s, index, 1, qed_commit_l2_update, acb); | ||
110 | + ret = qed_write_l1_table(s, index, 1); | ||
111 | + qed_commit_l2_update(acb, ret); | ||
112 | } | ||
113 | |||
114 | /** | ||
115 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset) | ||
116 | |||
117 | if (need_alloc) { | ||
118 | /* Write out the whole new L2 table */ | ||
119 | - qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true, | ||
120 | - qed_aio_write_l1_update, acb); | ||
121 | + ret = qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true); | ||
122 | + qed_aio_write_l1_update(acb, ret); | ||
123 | } else { | ||
124 | /* Write out only the updated part of the L2 table */ | ||
125 | - qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, false, | ||
126 | - qed_aio_next_io_cb, acb); | ||
127 | + ret = qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, | ||
128 | + false); | ||
129 | + qed_aio_next_io(acb, ret); | ||
130 | } | ||
131 | return; | ||
132 | |||
133 | diff --git a/block/qed.h b/block/qed.h | ||
134 | index XXXXXXX..XXXXXXX 100644 | ||
135 | --- a/block/qed.h | ||
136 | +++ b/block/qed.h | ||
137 | @@ -XXX,XX +XXX,XX @@ void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table); | ||
138 | * Table I/O functions | ||
139 | */ | ||
140 | int qed_read_l1_table_sync(BDRVQEDState *s); | ||
141 | -void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n, | ||
142 | - BlockCompletionFunc *cb, void *opaque); | ||
143 | +int qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n); | ||
144 | int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index, | ||
145 | unsigned int n); | ||
146 | int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, | ||
147 | uint64_t offset); | ||
148 | int qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset); | ||
149 | -void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, | ||
150 | - unsigned int index, unsigned int n, bool flush, | ||
151 | - BlockCompletionFunc *cb, void *opaque); | ||
152 | +int qed_write_l2_table(BDRVQEDState *s, QEDRequest *request, | ||
153 | + unsigned int index, unsigned int n, bool flush); | ||
154 | int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request, | ||
155 | unsigned int index, unsigned int n, bool flush); | ||
156 | |||
157 | -- | ||
158 | 1.8.3.1 | ||
159 | |||
160 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | Note that this code is generally not running in coroutine context, so | ||
2 | this is an actual blocking synchronous operation. We'll fix this in a | ||
3 | moment. | ||
4 | 1 | ||
5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
6 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
7 | --- | ||
8 | block/qed.c | 61 +++++++++++++++++++------------------------------------------ | ||
9 | 1 file changed, 19 insertions(+), 42 deletions(-) | ||
10 | |||
11 | diff --git a/block/qed.c b/block/qed.c | ||
12 | index XXXXXXX..XXXXXXX 100644 | ||
13 | --- a/block/qed.c | ||
14 | +++ b/block/qed.c | ||
15 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_start_io(QEDAIOCB *acb) | ||
16 | qed_aio_next_io(acb, 0); | ||
17 | } | ||
18 | |||
19 | -static void qed_aio_next_io_cb(void *opaque, int ret) | ||
20 | -{ | ||
21 | - QEDAIOCB *acb = opaque; | ||
22 | - | ||
23 | - qed_aio_next_io(acb, ret); | ||
24 | -} | ||
25 | - | ||
26 | static void qed_plug_allocating_write_reqs(BDRVQEDState *s) | ||
27 | { | ||
28 | assert(!s->allocating_write_reqs_plugged); | ||
29 | @@ -XXX,XX +XXX,XX @@ err: | ||
30 | qed_aio_complete(acb, ret); | ||
31 | } | ||
32 | |||
33 | -static void qed_aio_write_l2_update_cb(void *opaque, int ret) | ||
34 | -{ | ||
35 | - QEDAIOCB *acb = opaque; | ||
36 | - qed_aio_write_l2_update(acb, ret, acb->cur_cluster); | ||
37 | -} | ||
38 | - | ||
39 | -/** | ||
40 | - * Flush new data clusters before updating the L2 table | ||
41 | - * | ||
42 | - * This flush is necessary when a backing file is in use. A crash during an | ||
43 | - * allocating write could result in empty clusters in the image. If the write | ||
44 | - * only touched a subregion of the cluster, then backing image sectors have | ||
45 | - * been lost in the untouched region. The solution is to flush after writing a | ||
46 | - * new data cluster and before updating the L2 table. | ||
47 | - */ | ||
48 | -static void qed_aio_write_flush_before_l2_update(void *opaque, int ret) | ||
49 | -{ | ||
50 | - QEDAIOCB *acb = opaque; | ||
51 | - BDRVQEDState *s = acb_to_s(acb); | ||
52 | - | ||
53 | - if (!bdrv_aio_flush(s->bs->file->bs, qed_aio_write_l2_update_cb, opaque)) { | ||
54 | - qed_aio_complete(acb, -EIO); | ||
55 | - } | ||
56 | -} | ||
57 | - | ||
58 | /** | ||
59 | * Write data to the image file | ||
60 | */ | ||
61 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_main(void *opaque, int ret) | ||
62 | BDRVQEDState *s = acb_to_s(acb); | ||
63 | uint64_t offset = acb->cur_cluster + | ||
64 | qed_offset_into_cluster(s, acb->cur_pos); | ||
65 | - BlockCompletionFunc *next_fn; | ||
66 | |||
67 | trace_qed_aio_write_main(s, acb, ret, offset, acb->cur_qiov.size); | ||
68 | |||
69 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_main(void *opaque, int ret) | ||
70 | return; | ||
71 | } | ||
72 | |||
73 | + BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO); | ||
74 | + ret = bdrv_pwritev(s->bs->file, offset, &acb->cur_qiov); | ||
75 | + if (ret >= 0) { | ||
76 | + ret = 0; | ||
77 | + } | ||
78 | + | ||
79 | if (acb->find_cluster_ret == QED_CLUSTER_FOUND) { | ||
80 | - next_fn = qed_aio_next_io_cb; | ||
81 | + qed_aio_next_io(acb, ret); | ||
82 | } else { | ||
83 | if (s->bs->backing) { | ||
84 | - next_fn = qed_aio_write_flush_before_l2_update; | ||
85 | - } else { | ||
86 | - next_fn = qed_aio_write_l2_update_cb; | ||
87 | + /* | ||
88 | + * Flush new data clusters before updating the L2 table | ||
89 | + * | ||
90 | + * This flush is necessary when a backing file is in use. A crash | ||
91 | + * during an allocating write could result in empty clusters in the | ||
92 | + * image. If the write only touched a subregion of the cluster, | ||
93 | + * then backing image sectors have been lost in the untouched | ||
94 | + * region. The solution is to flush after writing a new data | ||
95 | + * cluster and before updating the L2 table. | ||
96 | + */ | ||
97 | + ret = bdrv_flush(s->bs->file->bs); | ||
98 | } | ||
99 | + qed_aio_write_l2_update(acb, ret, acb->cur_cluster); | ||
100 | } | ||
101 | - | ||
102 | - BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO); | ||
103 | - bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE, | ||
104 | - &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE, | ||
105 | - next_fn, acb); | ||
106 | } | ||
107 | |||
108 | /** | ||
109 | -- | ||
110 | 1.8.3.1 | ||
111 | |||
112 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | qed_commit_l2_update() is unconditionally called at the end of | ||
2 | qed_aio_write_l1_update(). Inline it. | ||
3 | 1 | ||
4 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
5 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | --- | ||
7 | block/qed.c | 36 ++++++++++++++---------------------- | ||
8 | 1 file changed, 14 insertions(+), 22 deletions(-) | ||
9 | |||
10 | diff --git a/block/qed.c b/block/qed.c | ||
11 | index XXXXXXX..XXXXXXX 100644 | ||
12 | --- a/block/qed.c | ||
13 | +++ b/block/qed.c | ||
14 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete(QEDAIOCB *acb, int ret) | ||
15 | } | ||
16 | |||
17 | /** | ||
18 | - * Commit the current L2 table to the cache | ||
19 | + * Update L1 table with new L2 table offset and write it out | ||
20 | */ | ||
21 | -static void qed_commit_l2_update(void *opaque, int ret) | ||
22 | +static void qed_aio_write_l1_update(void *opaque, int ret) | ||
23 | { | ||
24 | QEDAIOCB *acb = opaque; | ||
25 | BDRVQEDState *s = acb_to_s(acb); | ||
26 | CachedL2Table *l2_table = acb->request.l2_table; | ||
27 | uint64_t l2_offset = l2_table->offset; | ||
28 | + int index; | ||
29 | + | ||
30 | + if (ret) { | ||
31 | + qed_aio_complete(acb, ret); | ||
32 | + return; | ||
33 | + } | ||
34 | |||
35 | + index = qed_l1_index(s, acb->cur_pos); | ||
36 | + s->l1_table->offsets[index] = l2_table->offset; | ||
37 | + | ||
38 | + ret = qed_write_l1_table(s, index, 1); | ||
39 | + | ||
40 | + /* Commit the current L2 table to the cache */ | ||
41 | qed_commit_l2_cache_entry(&s->l2_cache, l2_table); | ||
42 | |||
43 | /* This is guaranteed to succeed because we just committed the entry to the | ||
44 | @@ -XXX,XX +XXX,XX @@ static void qed_commit_l2_update(void *opaque, int ret) | ||
45 | qed_aio_next_io(acb, ret); | ||
46 | } | ||
47 | |||
48 | -/** | ||
49 | - * Update L1 table with new L2 table offset and write it out | ||
50 | - */ | ||
51 | -static void qed_aio_write_l1_update(void *opaque, int ret) | ||
52 | -{ | ||
53 | - QEDAIOCB *acb = opaque; | ||
54 | - BDRVQEDState *s = acb_to_s(acb); | ||
55 | - int index; | ||
56 | - | ||
57 | - if (ret) { | ||
58 | - qed_aio_complete(acb, ret); | ||
59 | - return; | ||
60 | - } | ||
61 | - | ||
62 | - index = qed_l1_index(s, acb->cur_pos); | ||
63 | - s->l1_table->offsets[index] = acb->request.l2_table->offset; | ||
64 | - | ||
65 | - ret = qed_write_l1_table(s, index, 1); | ||
66 | - qed_commit_l2_update(acb, ret); | ||
67 | -} | ||
68 | |||
69 | /** | ||
70 | * Update L2 table with new cluster offsets and write them out | ||
71 | -- | ||
72 | 1.8.3.1 | ||
73 | |||
74 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | Don't recurse into qed_aio_next_io() and qed_aio_complete() here, but | ||
2 | just return an error code and let the caller handle it. | ||
3 | 1 | ||
4 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
5 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | --- | ||
7 | block/qed.c | 19 +++++++++---------- | ||
8 | 1 file changed, 9 insertions(+), 10 deletions(-) | ||
9 | |||
10 | diff --git a/block/qed.c b/block/qed.c | ||
11 | index XXXXXXX..XXXXXXX 100644 | ||
12 | --- a/block/qed.c | ||
13 | +++ b/block/qed.c | ||
14 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete(QEDAIOCB *acb, int ret) | ||
15 | /** | ||
16 | * Update L1 table with new L2 table offset and write it out | ||
17 | */ | ||
18 | -static void qed_aio_write_l1_update(void *opaque, int ret) | ||
19 | +static int qed_aio_write_l1_update(QEDAIOCB *acb) | ||
20 | { | ||
21 | - QEDAIOCB *acb = opaque; | ||
22 | BDRVQEDState *s = acb_to_s(acb); | ||
23 | CachedL2Table *l2_table = acb->request.l2_table; | ||
24 | uint64_t l2_offset = l2_table->offset; | ||
25 | - int index; | ||
26 | - | ||
27 | - if (ret) { | ||
28 | - qed_aio_complete(acb, ret); | ||
29 | - return; | ||
30 | - } | ||
31 | + int index, ret; | ||
32 | |||
33 | index = qed_l1_index(s, acb->cur_pos); | ||
34 | s->l1_table->offsets[index] = l2_table->offset; | ||
35 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_l1_update(void *opaque, int ret) | ||
36 | acb->request.l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset); | ||
37 | assert(acb->request.l2_table != NULL); | ||
38 | |||
39 | - qed_aio_next_io(acb, ret); | ||
40 | + return ret; | ||
41 | } | ||
42 | |||
43 | |||
44 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset) | ||
45 | if (need_alloc) { | ||
46 | /* Write out the whole new L2 table */ | ||
47 | ret = qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true); | ||
48 | - qed_aio_write_l1_update(acb, ret); | ||
49 | + if (ret) { | ||
50 | + goto err; | ||
51 | + } | ||
52 | + ret = qed_aio_write_l1_update(acb); | ||
53 | + qed_aio_next_io(acb, ret); | ||
54 | + | ||
55 | } else { | ||
56 | /* Write out only the updated part of the L2 table */ | ||
57 | ret = qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, | ||
58 | -- | ||
59 | 1.8.3.1 | ||
60 | |||
61 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | Don't recurse into qed_aio_next_io() and qed_aio_complete() here, but | ||
2 | just return an error code and let the caller handle it. | ||
3 | 1 | ||
4 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
5 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | --- | ||
7 | block/qed.c | 43 ++++++++++++++++++++++++++----------------- | ||
8 | 1 file changed, 26 insertions(+), 17 deletions(-) | ||
9 | |||
10 | diff --git a/block/qed.c b/block/qed.c | ||
11 | index XXXXXXX..XXXXXXX 100644 | ||
12 | --- a/block/qed.c | ||
13 | +++ b/block/qed.c | ||
14 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_l1_update(QEDAIOCB *acb) | ||
15 | /** | ||
16 | * Update L2 table with new cluster offsets and write them out | ||
17 | */ | ||
18 | -static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset) | ||
19 | +static int qed_aio_write_l2_update(QEDAIOCB *acb, uint64_t offset) | ||
20 | { | ||
21 | BDRVQEDState *s = acb_to_s(acb); | ||
22 | bool need_alloc = acb->find_cluster_ret == QED_CLUSTER_L1; | ||
23 | - int index; | ||
24 | - | ||
25 | - if (ret) { | ||
26 | - goto err; | ||
27 | - } | ||
28 | + int index, ret; | ||
29 | |||
30 | if (need_alloc) { | ||
31 | qed_unref_l2_cache_entry(acb->request.l2_table); | ||
32 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset) | ||
33 | /* Write out the whole new L2 table */ | ||
34 | ret = qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true); | ||
35 | if (ret) { | ||
36 | - goto err; | ||
37 | + return ret; | ||
38 | } | ||
39 | - ret = qed_aio_write_l1_update(acb); | ||
40 | - qed_aio_next_io(acb, ret); | ||
41 | - | ||
42 | + return qed_aio_write_l1_update(acb); | ||
43 | } else { | ||
44 | /* Write out only the updated part of the L2 table */ | ||
45 | ret = qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, | ||
46 | false); | ||
47 | - qed_aio_next_io(acb, ret); | ||
48 | + if (ret) { | ||
49 | + return ret; | ||
50 | + } | ||
51 | } | ||
52 | - return; | ||
53 | - | ||
54 | -err: | ||
55 | - qed_aio_complete(acb, ret); | ||
56 | + return 0; | ||
57 | } | ||
58 | |||
59 | /** | ||
60 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_main(void *opaque, int ret) | ||
61 | */ | ||
62 | ret = bdrv_flush(s->bs->file->bs); | ||
63 | } | ||
64 | - qed_aio_write_l2_update(acb, ret, acb->cur_cluster); | ||
65 | + if (ret) { | ||
66 | + goto err; | ||
67 | + } | ||
68 | + ret = qed_aio_write_l2_update(acb, acb->cur_cluster); | ||
69 | + if (ret) { | ||
70 | + goto err; | ||
71 | + } | ||
72 | + qed_aio_next_io(acb, 0); | ||
73 | } | ||
74 | + return; | ||
75 | + | ||
76 | +err: | ||
77 | + qed_aio_complete(acb, ret); | ||
78 | } | ||
79 | |||
80 | /** | ||
81 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_zero_cluster(void *opaque, int ret) | ||
82 | return; | ||
83 | } | ||
84 | |||
85 | - qed_aio_write_l2_update(acb, 0, 1); | ||
86 | + ret = qed_aio_write_l2_update(acb, 1); | ||
87 | + if (ret < 0) { | ||
88 | + qed_aio_complete(acb, ret); | ||
89 | + return; | ||
90 | + } | ||
91 | + qed_aio_next_io(acb, 0); | ||
92 | } | ||
93 | |||
94 | /** | ||
95 | -- | ||
96 | 1.8.3.1 | ||
97 | |||
98 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | Now that we're running in coroutine context, the ad-hoc serialisation | ||
2 | code (which drops a request that has to wait out of coroutine context) | ||
3 | can be replaced by a CoQueue. | ||
4 | 1 | ||
5 | This means that when we resume a serialised request, it is running in | ||
6 | coroutine context again and its I/O isn't blocking any more. | ||
7 | |||
8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
9 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | --- | ||
11 | block/qed.c | 49 +++++++++++++++++-------------------------------- | ||
12 | block/qed.h | 3 ++- | ||
13 | 2 files changed, 19 insertions(+), 33 deletions(-) | ||
14 | |||
15 | diff --git a/block/qed.c b/block/qed.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/block/qed.c | ||
18 | +++ b/block/qed.c | ||
19 | @@ -XXX,XX +XXX,XX @@ static void qed_plug_allocating_write_reqs(BDRVQEDState *s) | ||
20 | |||
21 | static void qed_unplug_allocating_write_reqs(BDRVQEDState *s) | ||
22 | { | ||
23 | - QEDAIOCB *acb; | ||
24 | - | ||
25 | assert(s->allocating_write_reqs_plugged); | ||
26 | |||
27 | s->allocating_write_reqs_plugged = false; | ||
28 | - | ||
29 | - acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs); | ||
30 | - if (acb) { | ||
31 | - qed_aio_start_io(acb); | ||
32 | - } | ||
33 | + qemu_co_enter_next(&s->allocating_write_reqs); | ||
34 | } | ||
35 | |||
36 | static void qed_clear_need_check(void *opaque, int ret) | ||
37 | @@ -XXX,XX +XXX,XX @@ static void qed_need_check_timer_cb(void *opaque) | ||
38 | BDRVQEDState *s = opaque; | ||
39 | |||
40 | /* The timer should only fire when allocating writes have drained */ | ||
41 | - assert(!QSIMPLEQ_FIRST(&s->allocating_write_reqs)); | ||
42 | + assert(!s->allocating_acb); | ||
43 | |||
44 | trace_qed_need_check_timer_cb(s); | ||
45 | |||
46 | @@ -XXX,XX +XXX,XX @@ static int bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int flags, | ||
47 | int ret; | ||
48 | |||
49 | s->bs = bs; | ||
50 | - QSIMPLEQ_INIT(&s->allocating_write_reqs); | ||
51 | + qemu_co_queue_init(&s->allocating_write_reqs); | ||
52 | |||
53 | ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header)); | ||
54 | if (ret < 0) { | ||
55 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete_bh(void *opaque) | ||
56 | qed_release(s); | ||
57 | } | ||
58 | |||
59 | -static void qed_resume_alloc_bh(void *opaque) | ||
60 | -{ | ||
61 | - qed_aio_start_io(opaque); | ||
62 | -} | ||
63 | - | ||
64 | static void qed_aio_complete(QEDAIOCB *acb, int ret) | ||
65 | { | ||
66 | BDRVQEDState *s = acb_to_s(acb); | ||
67 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete(QEDAIOCB *acb, int ret) | ||
68 | * next request in the queue. This ensures that we don't cycle through | ||
69 | * requests multiple times but rather finish one at a time completely. | ||
70 | */ | ||
71 | - if (acb == QSIMPLEQ_FIRST(&s->allocating_write_reqs)) { | ||
72 | - QEDAIOCB *next_acb; | ||
73 | - QSIMPLEQ_REMOVE_HEAD(&s->allocating_write_reqs, next); | ||
74 | - next_acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs); | ||
75 | - if (next_acb) { | ||
76 | - aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs), | ||
77 | - qed_resume_alloc_bh, next_acb); | ||
78 | + if (acb == s->allocating_acb) { | ||
79 | + s->allocating_acb = NULL; | ||
80 | + if (!qemu_co_queue_empty(&s->allocating_write_reqs)) { | ||
81 | + qemu_co_enter_next(&s->allocating_write_reqs); | ||
82 | } else if (s->header.features & QED_F_NEED_CHECK) { | ||
83 | qed_start_need_check_timer(s); | ||
84 | } | ||
85 | @@ -XXX,XX +XXX,XX @@ static int qed_aio_write_alloc(QEDAIOCB *acb, size_t len) | ||
86 | int ret; | ||
87 | |||
88 | /* Cancel timer when the first allocating request comes in */ | ||
89 | - if (QSIMPLEQ_EMPTY(&s->allocating_write_reqs)) { | ||
90 | + if (s->allocating_acb == NULL) { | ||
91 | qed_cancel_need_check_timer(s); | ||
92 | } | ||
93 | |||
94 | /* Freeze this request if another allocating write is in progress */ | ||
95 | - if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) { | ||
96 | - QSIMPLEQ_INSERT_TAIL(&s->allocating_write_reqs, acb, next); | ||
97 | - } | ||
98 | - if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs) || | ||
99 | - s->allocating_write_reqs_plugged) { | ||
100 | - return -EINPROGRESS; /* wait for existing request to finish */ | ||
101 | + if (s->allocating_acb != acb || s->allocating_write_reqs_plugged) { | ||
102 | + if (s->allocating_acb != NULL) { | ||
103 | + qemu_co_queue_wait(&s->allocating_write_reqs, NULL); | ||
104 | + assert(s->allocating_acb == NULL); | ||
105 | + } | ||
106 | + s->allocating_acb = acb; | ||
107 | + return -EAGAIN; /* start over with looking up table entries */ | ||
108 | } | ||
109 | |||
110 | acb->cur_nclusters = qed_bytes_to_clusters(s, | ||
111 | @@ -XXX,XX +XXX,XX @@ static void qed_aio_next_io(QEDAIOCB *acb) | ||
112 | ret = qed_aio_read_data(acb, ret, offset, len); | ||
113 | } | ||
114 | |||
115 | - if (ret < 0) { | ||
116 | - if (ret != -EINPROGRESS) { | ||
117 | - qed_aio_complete(acb, ret); | ||
118 | - } | ||
119 | + if (ret < 0 && ret != -EAGAIN) { | ||
120 | + qed_aio_complete(acb, ret); | ||
121 | return; | ||
122 | } | ||
123 | } | ||
124 | diff --git a/block/qed.h b/block/qed.h | ||
125 | index XXXXXXX..XXXXXXX 100644 | ||
126 | --- a/block/qed.h | ||
127 | +++ b/block/qed.h | ||
128 | @@ -XXX,XX +XXX,XX @@ typedef struct { | ||
129 | uint32_t l2_mask; | ||
130 | |||
131 | /* Allocating write request queue */ | ||
132 | - QSIMPLEQ_HEAD(, QEDAIOCB) allocating_write_reqs; | ||
133 | + QEDAIOCB *allocating_acb; | ||
134 | + CoQueue allocating_write_reqs; | ||
135 | bool allocating_write_reqs_plugged; | ||
136 | |||
137 | /* Periodic flush and clear need check flag */ | ||
138 | -- | ||
139 | 1.8.3.1 | ||
140 | |||
141 | diff view generated by jsdifflib |
1 | This fixes the last place where we degraded from AIO to actual blocking | 1 | The 'name' option for NBD exports is optional. Add a note that the |
---|---|---|---|
2 | synchronous I/O requests. Putting it into a coroutine means that instead | 2 | default for the option is the node name (people could otherwise expect |
3 | of blocking, the coroutine simply yields while doing I/O. | 3 | that it's the empty string like for qemu-nbd). |
4 | 4 | ||
5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | 5 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> |
6 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | 6 | Message-Id: <20210305094856.18964-1-kwolf@redhat.com> |
7 | Reviewed-by: Max Reitz <mreitz@redhat.com> | ||
8 | Signed-off-by: Kevin Wolf <kwolf@redhat.com> | ||
7 | --- | 9 | --- |
8 | block/qed.c | 33 +++++++++++++++++---------------- | 10 | docs/tools/qemu-storage-daemon.rst | 5 +++-- |
9 | 1 file changed, 17 insertions(+), 16 deletions(-) | 11 | 1 file changed, 3 insertions(+), 2 deletions(-) |
10 | 12 | ||
11 | diff --git a/block/qed.c b/block/qed.c | 13 | diff --git a/docs/tools/qemu-storage-daemon.rst b/docs/tools/qemu-storage-daemon.rst |
12 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
13 | --- a/block/qed.c | 15 | --- a/docs/tools/qemu-storage-daemon.rst |
14 | +++ b/block/qed.c | 16 | +++ b/docs/tools/qemu-storage-daemon.rst |
15 | @@ -XXX,XX +XXX,XX @@ static void qed_unplug_allocating_write_reqs(BDRVQEDState *s) | 17 | @@ -XXX,XX +XXX,XX @@ Standard options: |
16 | qemu_co_enter_next(&s->allocating_write_reqs); | 18 | requests for modifying data (the default is off). |
17 | } | 19 | |
18 | 20 | The ``nbd`` export type requires ``--nbd-server`` (see below). ``name`` is | |
19 | -static void qed_clear_need_check(void *opaque, int ret) | 21 | - the NBD export name. ``bitmap`` is the name of a dirty bitmap reachable from |
20 | +static void qed_need_check_timer_entry(void *opaque) | 22 | - the block node, so the NBD client can use NBD_OPT_SET_META_CONTEXT with the |
21 | { | 23 | + the NBD export name (if not specified, it defaults to the given |
22 | BDRVQEDState *s = opaque; | 24 | + ``node-name``). ``bitmap`` is the name of a dirty bitmap reachable from the |
23 | + int ret; | 25 | + block node, so the NBD client can use NBD_OPT_SET_META_CONTEXT with the |
24 | 26 | metadata context name "qemu:dirty-bitmap:BITMAP" to inspect the bitmap. | |
25 | - if (ret) { | 27 | |
26 | + /* The timer should only fire when allocating writes have drained */ | 28 | The ``vhost-user-blk`` export type takes a vhost-user socket address on which |
27 | + assert(!s->allocating_acb); | ||
28 | + | ||
29 | + trace_qed_need_check_timer_cb(s); | ||
30 | + | ||
31 | + qed_acquire(s); | ||
32 | + qed_plug_allocating_write_reqs(s); | ||
33 | + | ||
34 | + /* Ensure writes are on disk before clearing flag */ | ||
35 | + ret = bdrv_co_flush(s->bs->file->bs); | ||
36 | + qed_release(s); | ||
37 | + if (ret < 0) { | ||
38 | qed_unplug_allocating_write_reqs(s); | ||
39 | return; | ||
40 | } | ||
41 | @@ -XXX,XX +XXX,XX @@ static void qed_clear_need_check(void *opaque, int ret) | ||
42 | |||
43 | qed_unplug_allocating_write_reqs(s); | ||
44 | |||
45 | - ret = bdrv_flush(s->bs); | ||
46 | + ret = bdrv_co_flush(s->bs); | ||
47 | (void) ret; | ||
48 | } | ||
49 | |||
50 | static void qed_need_check_timer_cb(void *opaque) | ||
51 | { | ||
52 | - BDRVQEDState *s = opaque; | ||
53 | - | ||
54 | - /* The timer should only fire when allocating writes have drained */ | ||
55 | - assert(!s->allocating_acb); | ||
56 | - | ||
57 | - trace_qed_need_check_timer_cb(s); | ||
58 | - | ||
59 | - qed_acquire(s); | ||
60 | - qed_plug_allocating_write_reqs(s); | ||
61 | - | ||
62 | - /* Ensure writes are on disk before clearing flag */ | ||
63 | - bdrv_aio_flush(s->bs->file->bs, qed_clear_need_check, s); | ||
64 | - qed_release(s); | ||
65 | + Coroutine *co = qemu_coroutine_create(qed_need_check_timer_entry, opaque); | ||
66 | + qemu_coroutine_enter(co); | ||
67 | } | ||
68 | |||
69 | void qed_acquire(BDRVQEDState *s) | ||
70 | -- | 29 | -- |
71 | 1.8.3.1 | 30 | 2.29.2 |
72 | 31 | ||
73 | 32 | diff view generated by jsdifflib |