1 | The following changes since commit ba29883206d92a29ad5a466e679ccfc2ee6132ef: | 1 | The following changes since commit ac793156f650ae2d77834932d72224175ee69086: |
---|---|---|---|
2 | 2 | ||
3 | Merge remote-tracking branch 'remotes/borntraeger/tags/s390x-20200310' into staging (2020-03-10 16:50:28 +0000) | 3 | Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20201020-1' into staging (2020-10-20 21:11:35 +0100) |
4 | 4 | ||
5 | are available in the Git repository at: | 5 | are available in the Git repository at: |
6 | 6 | ||
7 | https://github.com/XanClic/qemu.git tags/pull-block-2020-03-11 | 7 | https://gitlab.com/stefanha/qemu.git tags/block-pull-request |
8 | 8 | ||
9 | for you to fetch changes up to 397f4e9d83e9c0000905f0a988ba1aeda162571c: | 9 | for you to fetch changes up to 32a3fd65e7e3551337fd26bfc0e2f899d70c028c: |
10 | 10 | ||
11 | block/block-copy: hide structure definitions (2020-03-11 12:42:30 +0100) | 11 | iotests: add commit top->base cases to 274 (2020-10-22 09:55:39 +0100) |
12 | 12 | ||
13 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
14 | Block patches for the 5.0 softfreeze: | 14 | Pull request |
15 | - qemu-img measure for LUKS | 15 | |
16 | - Improve block-copy's performance by reducing inter-request | 16 | v2: |
17 | dependencies | 17 | * Fix format string issues on 32-bit hosts [Peter] |
18 | - Make curl's detection of accept-ranges more robust | 18 | * Fix qemu-nbd.c CONFIG_POSIX ifdef issue [Eric] |
19 | - Memleak fixes | 19 | * Fix missing eventfd.h header on macOS [Peter] |
20 | - iotest fix | 20 | * Drop unreliable vhost-user-blk test (will send a new patch when ready) [Peter] |
21 | |||
22 | This pull request contains the vhost-user-blk server by Coiby Xu along with my | ||
23 | additions, block/nvme.c alignment and hardware error statistics by Philippe | ||
24 | Mathieu-Daudé, and bdrv_co_block_status_above() fixes by Vladimir | ||
25 | Sementsov-Ogievskiy. | ||
21 | 26 | ||
22 | ---------------------------------------------------------------- | 27 | ---------------------------------------------------------------- |
23 | David Edmondson (2): | ||
24 | block/curl: HTTP header fields allow whitespace around values | ||
25 | block/curl: HTTP header field names are case insensitive | ||
26 | 28 | ||
27 | Eric Blake (1): | 29 | Coiby Xu (6): |
28 | iotests: Fix nonportable use of od --endian | 30 | libvhost-user: Allow vu_message_read to be replaced |
31 | libvhost-user: remove watch for kick_fd when de-initialize vu-dev | ||
32 | util/vhost-user-server: generic vhost user server | ||
33 | block: move logical block size check function to a common utility | ||
34 | function | ||
35 | block/export: vhost-user block device backend server | ||
36 | MAINTAINERS: Add vhost-user block device backend server maintainer | ||
29 | 37 | ||
30 | Pan Nengyuan (2): | 38 | Philippe Mathieu-Daudé (1): |
31 | block/qcow2: do free crypto_opts in qcow2_close() | 39 | block/nvme: Add driver statistics for access alignment and hw errors |
32 | qemu-img: free memory before re-assign | ||
33 | 40 | ||
34 | Stefan Hajnoczi (4): | 41 | Stefan Hajnoczi (16): |
35 | luks: extract qcrypto_block_calculate_payload_offset() | 42 | util/vhost-user-server: s/fileds/fields/ typo fix |
36 | luks: implement .bdrv_measure() | 43 | util/vhost-user-server: drop unnecessary QOM cast |
37 | qemu-img: allow qemu-img measure --object without a filename | 44 | util/vhost-user-server: drop unnecessary watch deletion |
38 | iotests: add 288 luks qemu-img measure test | 45 | block/export: consolidate request structs into VuBlockReq |
46 | util/vhost-user-server: drop unused DevicePanicNotifier | ||
47 | util/vhost-user-server: fix memory leak in vu_message_read() | ||
48 | util/vhost-user-server: check EOF when reading payload | ||
49 | util/vhost-user-server: rework vu_client_trip() coroutine lifecycle | ||
50 | block/export: report flush errors | ||
51 | block/export: convert vhost-user-blk server to block export API | ||
52 | util/vhost-user-server: move header to include/ | ||
53 | util/vhost-user-server: use static library in meson.build | ||
54 | qemu-storage-daemon: avoid compiling blockdev_ss twice | ||
55 | block: move block exports to libblockdev | ||
56 | block/export: add iothread and fixed-iothread options | ||
57 | block/export: add vhost-user-blk multi-queue support | ||
39 | 58 | ||
40 | Vladimir Sementsov-Ogievskiy (10): | 59 | Vladimir Sementsov-Ogievskiy (5): |
41 | block/qcow2-threads: fix qcow2_decompress | 60 | block/io: fix bdrv_co_block_status_above |
42 | job: refactor progress to separate object | 61 | block/io: bdrv_common_block_status_above: support include_base |
43 | block/block-copy: fix progress calculation | 62 | block/io: bdrv_common_block_status_above: support bs == base |
44 | block/block-copy: specialcase first copy_range request | 63 | block/io: fix bdrv_is_allocated_above |
45 | block/block-copy: use block_status | 64 | iotests: add commit top->base cases to 274 |
46 | block/block-copy: factor out find_conflicting_inflight_req | ||
47 | block/block-copy: refactor interfaces to use bytes instead of end | ||
48 | block/block-copy: rename start to offset in interfaces | ||
49 | block/block-copy: reduce intersecting request lock | ||
50 | block/block-copy: hide structure definitions | ||
51 | 65 | ||
52 | block/backup-top.c | 6 +- | 66 | MAINTAINERS | 9 + |
53 | block/backup.c | 38 ++- | 67 | qapi/block-core.json | 24 +- |
54 | block/block-copy.c | 405 ++++++++++++++++++++++++------- | 68 | qapi/block-export.json | 36 +- |
55 | block/crypto.c | 62 +++++ | 69 | block/coroutines.h | 2 + |
56 | block/curl.c | 32 ++- | 70 | block/export/vhost-user-blk-server.h | 19 + |
57 | block/qcow2-threads.c | 12 +- | 71 | contrib/libvhost-user/libvhost-user.h | 21 + |
58 | block/qcow2.c | 75 ++---- | 72 | include/qemu/vhost-user-server.h | 65 +++ |
59 | block/trace-events | 1 + | 73 | util/block-helpers.h | 19 + |
60 | blockjob.c | 16 +- | 74 | block/export/export.c | 37 +- |
61 | crypto/block.c | 36 +++ | 75 | block/export/vhost-user-blk-server.c | 431 ++++++++++++++++++++ |
62 | include/block/block-copy.h | 65 +---- | 76 | block/io.c | 132 +++--- |
63 | include/crypto/block.h | 22 ++ | 77 | block/nvme.c | 27 ++ |
64 | include/qemu/job.h | 11 +- | 78 | block/qcow2.c | 16 +- |
65 | include/qemu/progress_meter.h | 58 +++++ | 79 | contrib/libvhost-user/libvhost-user-glib.c | 2 +- |
66 | job-qmp.c | 4 +- | 80 | contrib/libvhost-user/libvhost-user.c | 15 +- |
67 | job.c | 6 +- | 81 | hw/core/qdev-properties-system.c | 31 +- |
68 | qemu-img.c | 14 +- | 82 | nbd/server.c | 2 - |
69 | tests/qemu-iotests/178 | 2 +- | 83 | qemu-nbd.c | 21 +- |
70 | tests/qemu-iotests/178.out.qcow2 | 8 +- | 84 | softmmu/vl.c | 4 + |
71 | tests/qemu-iotests/178.out.raw | 8 +- | 85 | stubs/blk-exp-close-all.c | 7 + |
72 | tests/qemu-iotests/288 | 93 +++++++ | 86 | tests/vhost-user-bridge.c | 2 + |
73 | tests/qemu-iotests/288.out | 30 +++ | 87 | tools/virtiofsd/fuse_virtio.c | 4 +- |
74 | tests/qemu-iotests/common.rc | 22 +- | 88 | util/block-helpers.c | 46 +++ |
75 | tests/qemu-iotests/group | 1 + | 89 | util/vhost-user-server.c | 446 +++++++++++++++++++++ |
76 | 24 files changed, 749 insertions(+), 278 deletions(-) | 90 | block/export/meson.build | 3 +- |
77 | create mode 100644 include/qemu/progress_meter.h | 91 | contrib/libvhost-user/meson.build | 1 + |
78 | create mode 100755 tests/qemu-iotests/288 | 92 | meson.build | 22 +- |
79 | create mode 100644 tests/qemu-iotests/288.out | 93 | nbd/meson.build | 2 + |
94 | storage-daemon/meson.build | 3 +- | ||
95 | stubs/meson.build | 1 + | ||
96 | tests/qemu-iotests/274 | 20 + | ||
97 | tests/qemu-iotests/274.out | 68 ++++ | ||
98 | util/meson.build | 4 + | ||
99 | 33 files changed, 1420 insertions(+), 122 deletions(-) | ||
100 | create mode 100644 block/export/vhost-user-blk-server.h | ||
101 | create mode 100644 include/qemu/vhost-user-server.h | ||
102 | create mode 100644 util/block-helpers.h | ||
103 | create mode 100644 block/export/vhost-user-blk-server.c | ||
104 | create mode 100644 stubs/blk-exp-close-all.c | ||
105 | create mode 100644 util/block-helpers.c | ||
106 | create mode 100644 util/vhost-user-server.c | ||
80 | 107 | ||
81 | -- | 108 | -- |
82 | 2.24.1 | 109 | 2.26.2 |
83 | 110 | ||
84 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Philippe Mathieu-Daudé <philmd@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | In block_copy_do_copy we fallback to read+write if copy_range failed. | 3 | Keep statistics of some hardware errors, and number of |
4 | In this case copy_size is larger than defined for buffered IO, and | 4 | aligned/unaligned I/O accesses. |
5 | there is corresponding commit. Still, backup copies data cluster by | ||
6 | cluster, and most of requests are limited to one cluster anyway, so the | ||
7 | only source of this one bad-limited request is copy-before-write | ||
8 | operation. | ||
9 | 5 | ||
10 | Further patch will move backup to use block_copy directly, than for | 6 | QMP example booting a full RHEL 8.3 aarch64 guest: |
11 | cases where copy_range is not supported, first request will be | ||
12 | oversized in each backup. It's not good, let's change it now. | ||
13 | 7 | ||
14 | Fix is simple: just limit first copy_range request like buffer-based | 8 | { "execute": "query-blockstats" } |
15 | request. If it succeed, set larger copy_range limit. | 9 | { |
10 | "return": [ | ||
11 | { | ||
12 | "device": "", | ||
13 | "node-name": "drive0", | ||
14 | "stats": { | ||
15 | "flush_total_time_ns": 6026948, | ||
16 | "wr_highest_offset": 3383991230464, | ||
17 | "wr_total_time_ns": 807450995, | ||
18 | "failed_wr_operations": 0, | ||
19 | "failed_rd_operations": 0, | ||
20 | "wr_merged": 3, | ||
21 | "wr_bytes": 50133504, | ||
22 | "failed_unmap_operations": 0, | ||
23 | "failed_flush_operations": 0, | ||
24 | "account_invalid": false, | ||
25 | "rd_total_time_ns": 1846979900, | ||
26 | "flush_operations": 130, | ||
27 | "wr_operations": 659, | ||
28 | "rd_merged": 1192, | ||
29 | "rd_bytes": 218244096, | ||
30 | "account_failed": false, | ||
31 | "idle_time_ns": 2678641497, | ||
32 | "rd_operations": 7406, | ||
33 | }, | ||
34 | "driver-specific": { | ||
35 | "driver": "nvme", | ||
36 | "completion-errors": 0, | ||
37 | "unaligned-accesses": 2959, | ||
38 | "aligned-accesses": 4477 | ||
39 | }, | ||
40 | "qdev": "/machine/peripheral-anon/device[0]/virtio-backend" | ||
41 | } | ||
42 | ] | ||
43 | } | ||
16 | 44 | ||
17 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 45 | Suggested-by: Stefan Hajnoczi <stefanha@gmail.com> |
18 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 46 | Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
19 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 47 | Acked-by: Markus Armbruster <armbru@redhat.com> |
20 | Message-Id: <20200311103004.7649-4-vsementsov@virtuozzo.com> | 48 | Message-id: 20201001162939.1567915-1-philmd@redhat.com |
21 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 49 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
22 | --- | 50 | --- |
23 | block/block-copy.c | 41 +++++++++++++++++++++++++++++++---------- | 51 | qapi/block-core.json | 24 +++++++++++++++++++++++- |
24 | 1 file changed, 31 insertions(+), 10 deletions(-) | 52 | block/nvme.c | 27 +++++++++++++++++++++++++++ |
53 | 2 files changed, 50 insertions(+), 1 deletion(-) | ||
25 | 54 | ||
26 | diff --git a/block/block-copy.c b/block/block-copy.c | 55 | diff --git a/qapi/block-core.json b/qapi/block-core.json |
27 | index XXXXXXX..XXXXXXX 100644 | 56 | index XXXXXXX..XXXXXXX 100644 |
28 | --- a/block/block-copy.c | 57 | --- a/qapi/block-core.json |
29 | +++ b/block/block-copy.c | 58 | +++ b/qapi/block-core.json |
30 | @@ -XXX,XX +XXX,XX @@ void block_copy_state_free(BlockCopyState *s) | 59 | @@ -XXX,XX +XXX,XX @@ |
31 | g_free(s); | 60 | 'discard-nb-failed': 'uint64', |
61 | 'discard-bytes-ok': 'uint64' } } | ||
62 | |||
63 | +## | ||
64 | +# @BlockStatsSpecificNvme: | ||
65 | +# | ||
66 | +# NVMe driver statistics | ||
67 | +# | ||
68 | +# @completion-errors: The number of completion errors. | ||
69 | +# | ||
70 | +# @aligned-accesses: The number of aligned accesses performed by | ||
71 | +# the driver. | ||
72 | +# | ||
73 | +# @unaligned-accesses: The number of unaligned accesses performed by | ||
74 | +# the driver. | ||
75 | +# | ||
76 | +# Since: 5.2 | ||
77 | +## | ||
78 | +{ 'struct': 'BlockStatsSpecificNvme', | ||
79 | + 'data': { | ||
80 | + 'completion-errors': 'uint64', | ||
81 | + 'aligned-accesses': 'uint64', | ||
82 | + 'unaligned-accesses': 'uint64' } } | ||
83 | + | ||
84 | ## | ||
85 | # @BlockStatsSpecific: | ||
86 | # | ||
87 | @@ -XXX,XX +XXX,XX @@ | ||
88 | 'discriminator': 'driver', | ||
89 | 'data': { | ||
90 | 'file': 'BlockStatsSpecificFile', | ||
91 | - 'host_device': 'BlockStatsSpecificFile' } } | ||
92 | + 'host_device': 'BlockStatsSpecificFile', | ||
93 | + 'nvme': 'BlockStatsSpecificNvme' } } | ||
94 | |||
95 | ## | ||
96 | # @BlockStats: | ||
97 | diff --git a/block/nvme.c b/block/nvme.c | ||
98 | index XXXXXXX..XXXXXXX 100644 | ||
99 | --- a/block/nvme.c | ||
100 | +++ b/block/nvme.c | ||
101 | @@ -XXX,XX +XXX,XX @@ struct BDRVNVMeState { | ||
102 | |||
103 | /* PCI address (required for nvme_refresh_filename()) */ | ||
104 | char *device; | ||
105 | + | ||
106 | + struct { | ||
107 | + uint64_t completion_errors; | ||
108 | + uint64_t aligned_accesses; | ||
109 | + uint64_t unaligned_accesses; | ||
110 | + } stats; | ||
111 | }; | ||
112 | |||
113 | #define NVME_BLOCK_OPT_DEVICE "device" | ||
114 | @@ -XXX,XX +XXX,XX @@ static bool nvme_process_completion(NVMeQueuePair *q) | ||
115 | break; | ||
116 | } | ||
117 | ret = nvme_translate_error(c); | ||
118 | + if (ret) { | ||
119 | + s->stats.completion_errors++; | ||
120 | + } | ||
121 | q->cq.head = (q->cq.head + 1) % NVME_QUEUE_SIZE; | ||
122 | if (!q->cq.head) { | ||
123 | q->cq_phase = !q->cq_phase; | ||
124 | @@ -XXX,XX +XXX,XX @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes, | ||
125 | assert(QEMU_IS_ALIGNED(bytes, s->page_size)); | ||
126 | assert(bytes <= s->max_transfer); | ||
127 | if (nvme_qiov_aligned(bs, qiov)) { | ||
128 | + s->stats.aligned_accesses++; | ||
129 | return nvme_co_prw_aligned(bs, offset, bytes, qiov, is_write, flags); | ||
130 | } | ||
131 | + s->stats.unaligned_accesses++; | ||
132 | trace_nvme_prw_buffered(s, offset, bytes, qiov->niov, is_write); | ||
133 | buf = qemu_try_memalign(s->page_size, bytes); | ||
134 | |||
135 | @@ -XXX,XX +XXX,XX @@ static void nvme_unregister_buf(BlockDriverState *bs, void *host) | ||
136 | qemu_vfio_dma_unmap(s->vfio, host); | ||
32 | } | 137 | } |
33 | 138 | ||
34 | +static uint32_t block_copy_max_transfer(BdrvChild *source, BdrvChild *target) | 139 | +static BlockStatsSpecific *nvme_get_specific_stats(BlockDriverState *bs) |
35 | +{ | 140 | +{ |
36 | + return MIN_NON_ZERO(INT_MAX, | 141 | + BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1); |
37 | + MIN_NON_ZERO(source->bs->bl.max_transfer, | 142 | + BDRVNVMeState *s = bs->opaque; |
38 | + target->bs->bl.max_transfer)); | 143 | + |
144 | + stats->driver = BLOCKDEV_DRIVER_NVME; | ||
145 | + stats->u.nvme = (BlockStatsSpecificNvme) { | ||
146 | + .completion_errors = s->stats.completion_errors, | ||
147 | + .aligned_accesses = s->stats.aligned_accesses, | ||
148 | + .unaligned_accesses = s->stats.unaligned_accesses, | ||
149 | + }; | ||
150 | + | ||
151 | + return stats; | ||
39 | +} | 152 | +} |
40 | + | 153 | + |
41 | BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, | 154 | static const char *const nvme_strong_runtime_opts[] = { |
42 | int64_t cluster_size, | 155 | NVME_BLOCK_OPT_DEVICE, |
43 | BdrvRequestFlags write_flags, Error **errp) | 156 | NVME_BLOCK_OPT_NAMESPACE, |
44 | { | 157 | @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = { |
45 | BlockCopyState *s; | 158 | .bdrv_refresh_filename = nvme_refresh_filename, |
46 | BdrvDirtyBitmap *copy_bitmap; | 159 | .bdrv_refresh_limits = nvme_refresh_limits, |
47 | - uint32_t max_transfer = | 160 | .strong_runtime_opts = nvme_strong_runtime_opts, |
48 | - MIN_NON_ZERO(INT_MAX, | 161 | + .bdrv_get_specific_stats = nvme_get_specific_stats, |
49 | - MIN_NON_ZERO(source->bs->bl.max_transfer, | 162 | |
50 | - target->bs->bl.max_transfer)); | 163 | .bdrv_detach_aio_context = nvme_detach_aio_context, |
51 | 164 | .bdrv_attach_aio_context = nvme_attach_aio_context, | |
52 | copy_bitmap = bdrv_create_dirty_bitmap(source->bs, cluster_size, NULL, | ||
53 | errp); | ||
54 | @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, | ||
55 | .mem = shres_create(BLOCK_COPY_MAX_MEM), | ||
56 | }; | ||
57 | |||
58 | - if (max_transfer < cluster_size) { | ||
59 | + if (block_copy_max_transfer(source, target) < cluster_size) { | ||
60 | /* | ||
61 | * copy_range does not respect max_transfer. We don't want to bother | ||
62 | * with requests smaller than block-copy cluster size, so fallback to | ||
63 | @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, | ||
64 | s->copy_size = cluster_size; | ||
65 | } else { | ||
66 | /* | ||
67 | - * copy_range does not respect max_transfer (it's a TODO), so we factor | ||
68 | - * that in here. | ||
69 | + * We enable copy-range, but keep small copy_size, until first | ||
70 | + * successful copy_range (look at block_copy_do_copy). | ||
71 | */ | ||
72 | s->use_copy_range = true; | ||
73 | - s->copy_size = MIN(MAX(cluster_size, BLOCK_COPY_MAX_COPY_RANGE), | ||
74 | - QEMU_ALIGN_DOWN(max_transfer, cluster_size)); | ||
75 | + s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); | ||
76 | } | ||
77 | |||
78 | QLIST_INIT(&s->inflight_reqs); | ||
79 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | ||
80 | s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); | ||
81 | /* Fallback to read+write with allocated buffer */ | ||
82 | } else { | ||
83 | + if (s->use_copy_range) { | ||
84 | + /* | ||
85 | + * Successful copy-range. Now increase copy_size. copy_range | ||
86 | + * does not respect max_transfer (it's a TODO), so we factor | ||
87 | + * that in here. | ||
88 | + * | ||
89 | + * Note: we double-check s->use_copy_range for the case when | ||
90 | + * parallel block-copy request unsets it during previous | ||
91 | + * bdrv_co_copy_range call. | ||
92 | + */ | ||
93 | + s->copy_size = | ||
94 | + MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE), | ||
95 | + QEMU_ALIGN_DOWN(block_copy_max_transfer(s->source, | ||
96 | + s->target), | ||
97 | + s->cluster_size)); | ||
98 | + } | ||
99 | goto out; | ||
100 | } | ||
101 | } | ||
102 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | ||
103 | /* | ||
104 | * In case of failed copy_range request above, we may proceed with buffered | ||
105 | * request larger than BLOCK_COPY_MAX_BUFFER. Still, further requests will | ||
106 | - * be properly limited, so don't care too much. | ||
107 | + * be properly limited, so don't care too much. Moreover the most likely | ||
108 | + * case (copy_range is unsupported for the configuration, so the very first | ||
109 | + * copy_range request fails) is handled by setting large copy_size only | ||
110 | + * after first successful copy_range. | ||
111 | */ | ||
112 | |||
113 | bounce_buffer = qemu_blockalign(s->source->bs, nbytes); | ||
114 | -- | 165 | -- |
115 | 2.24.1 | 166 | 2.26.2 |
116 | 167 | ||
117 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Coiby Xu <coiby.xu@gmail.com> |
---|---|---|---|
2 | 2 | ||
3 | Hide structure definitions and add explicit API instead, to keep an | 3 | Allow vu_message_read to be replaced by one which will make use of the |
4 | eye on the scope of the shared fields. | 4 | QIOChannel functions. Thus reading vhost-user message won't stall the |
5 | guest. For slave channel, we still use the default vu_message_read. | ||
5 | 6 | ||
6 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 7 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> |
7 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 8 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> |
8 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 9 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> |
9 | Message-Id: <20200311103004.7649-10-vsementsov@virtuozzo.com> | 10 | Message-id: 20200918080912.321299-2-coiby.xu@gmail.com |
10 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
11 | --- | 12 | --- |
12 | block/backup-top.c | 6 ++-- | 13 | contrib/libvhost-user/libvhost-user.h | 21 +++++++++++++++++++++ |
13 | block/backup.c | 25 ++++++++-------- | 14 | contrib/libvhost-user/libvhost-user-glib.c | 2 +- |
14 | block/block-copy.c | 59 ++++++++++++++++++++++++++++++++++++++ | 15 | contrib/libvhost-user/libvhost-user.c | 14 +++++++------- |
15 | include/block/block-copy.h | 52 +++------------------------------ | 16 | tests/vhost-user-bridge.c | 2 ++ |
16 | 4 files changed, 80 insertions(+), 62 deletions(-) | 17 | tools/virtiofsd/fuse_virtio.c | 4 ++-- |
18 | 5 files changed, 33 insertions(+), 10 deletions(-) | ||
17 | 19 | ||
18 | diff --git a/block/backup-top.c b/block/backup-top.c | 20 | diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h |
19 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/block/backup-top.c | 22 | --- a/contrib/libvhost-user/libvhost-user.h |
21 | +++ b/block/backup-top.c | 23 | +++ b/contrib/libvhost-user/libvhost-user.h |
22 | @@ -XXX,XX +XXX,XX @@ typedef struct BDRVBackupTopState { | 24 | @@ -XXX,XX +XXX,XX @@ |
23 | BlockCopyState *bcs; | 25 | */ |
24 | BdrvChild *target; | 26 | #define VHOST_USER_MAX_RAM_SLOTS 32 |
25 | bool active; | 27 | |
26 | + int64_t cluster_size; | 28 | +#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) |
27 | } BDRVBackupTopState; | 29 | + |
28 | 30 | typedef enum VhostSetConfigType { | |
29 | static coroutine_fn int backup_top_co_preadv( | 31 | VHOST_SET_CONFIG_TYPE_MASTER = 0, |
30 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset, | 32 | VHOST_SET_CONFIG_TYPE_MIGRATION = 1, |
31 | return 0; | 33 | @@ -XXX,XX +XXX,XX @@ typedef uint64_t (*vu_get_features_cb) (VuDev *dev); |
34 | typedef void (*vu_set_features_cb) (VuDev *dev, uint64_t features); | ||
35 | typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg, | ||
36 | int *do_reply); | ||
37 | +typedef bool (*vu_read_msg_cb) (VuDev *dev, int sock, VhostUserMsg *vmsg); | ||
38 | typedef void (*vu_queue_set_started_cb) (VuDev *dev, int qidx, bool started); | ||
39 | typedef bool (*vu_queue_is_processed_in_order_cb) (VuDev *dev, int qidx); | ||
40 | typedef int (*vu_get_config_cb) (VuDev *dev, uint8_t *config, uint32_t len); | ||
41 | @@ -XXX,XX +XXX,XX @@ struct VuDev { | ||
42 | bool broken; | ||
43 | uint16_t max_queues; | ||
44 | |||
45 | + /* @read_msg: custom method to read vhost-user message | ||
46 | + * | ||
47 | + * Read data from vhost_user socket fd and fill up | ||
48 | + * the passed VhostUserMsg *vmsg struct. | ||
49 | + * | ||
50 | + * If reading fails, it should close the received set of file | ||
51 | + * descriptors as socket message's auxiliary data. | ||
52 | + * | ||
53 | + * For the details, please refer to vu_message_read in libvhost-user.c | ||
54 | + * which will be used by default if not custom method is provided when | ||
55 | + * calling vu_init | ||
56 | + * | ||
57 | + * Returns: true if vhost-user message successfully received, | ||
58 | + * otherwise return false. | ||
59 | + * | ||
60 | + */ | ||
61 | + vu_read_msg_cb read_msg; | ||
62 | /* @set_watch: add or update the given fd to the watch set, | ||
63 | * call cb when condition is met */ | ||
64 | vu_set_watch_cb set_watch; | ||
65 | @@ -XXX,XX +XXX,XX @@ bool vu_init(VuDev *dev, | ||
66 | uint16_t max_queues, | ||
67 | int socket, | ||
68 | vu_panic_cb panic, | ||
69 | + vu_read_msg_cb read_msg, | ||
70 | vu_set_watch_cb set_watch, | ||
71 | vu_remove_watch_cb remove_watch, | ||
72 | const VuDevIface *iface); | ||
73 | diff --git a/contrib/libvhost-user/libvhost-user-glib.c b/contrib/libvhost-user/libvhost-user-glib.c | ||
74 | index XXXXXXX..XXXXXXX 100644 | ||
75 | --- a/contrib/libvhost-user/libvhost-user-glib.c | ||
76 | +++ b/contrib/libvhost-user/libvhost-user-glib.c | ||
77 | @@ -XXX,XX +XXX,XX @@ vug_init(VugDev *dev, uint16_t max_queues, int socket, | ||
78 | g_assert(dev); | ||
79 | g_assert(iface); | ||
80 | |||
81 | - if (!vu_init(&dev->parent, max_queues, socket, panic, set_watch, | ||
82 | + if (!vu_init(&dev->parent, max_queues, socket, panic, NULL, set_watch, | ||
83 | remove_watch, iface)) { | ||
84 | return false; | ||
32 | } | 85 | } |
33 | 86 | diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c | |
34 | - off = QEMU_ALIGN_DOWN(offset, s->bcs->cluster_size); | 87 | index XXXXXXX..XXXXXXX 100644 |
35 | - end = QEMU_ALIGN_UP(offset + bytes, s->bcs->cluster_size); | 88 | --- a/contrib/libvhost-user/libvhost-user.c |
36 | + off = QEMU_ALIGN_DOWN(offset, s->cluster_size); | 89 | +++ b/contrib/libvhost-user/libvhost-user.c |
37 | + end = QEMU_ALIGN_UP(offset + bytes, s->cluster_size); | 90 | @@ -XXX,XX +XXX,XX @@ |
38 | 91 | /* The version of inflight buffer */ | |
39 | return block_copy(s->bcs, off, end - off, NULL); | 92 | #define INFLIGHT_VERSION 1 |
93 | |||
94 | -#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) | ||
95 | - | ||
96 | /* The version of the protocol we support */ | ||
97 | #define VHOST_USER_VERSION 1 | ||
98 | #define LIBVHOST_USER_DEBUG 0 | ||
99 | @@ -XXX,XX +XXX,XX @@ have_userfault(void) | ||
40 | } | 100 | } |
41 | @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, | 101 | |
42 | goto fail; | 102 | static bool |
103 | -vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) | ||
104 | +vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) | ||
105 | { | ||
106 | char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {}; | ||
107 | struct iovec iov = { | ||
108 | @@ -XXX,XX +XXX,XX @@ vu_process_message_reply(VuDev *dev, const VhostUserMsg *vmsg) | ||
109 | goto out; | ||
43 | } | 110 | } |
44 | 111 | ||
45 | + state->cluster_size = cluster_size; | 112 | - if (!vu_message_read(dev, dev->slave_fd, &msg_reply)) { |
46 | state->bcs = block_copy_state_new(top->backing, state->target, | 113 | + if (!vu_message_read_default(dev, dev->slave_fd, &msg_reply)) { |
47 | cluster_size, write_flags, &local_err); | 114 | goto out; |
48 | if (local_err) { | ||
49 | diff --git a/block/backup.c b/block/backup.c | ||
50 | index XXXXXXX..XXXXXXX 100644 | ||
51 | --- a/block/backup.c | ||
52 | +++ b/block/backup.c | ||
53 | @@ -XXX,XX +XXX,XX @@ static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret) | ||
54 | |||
55 | if (ret < 0 && job->bitmap_mode == BITMAP_SYNC_MODE_ALWAYS) { | ||
56 | /* If we failed and synced, merge in the bits we didn't copy: */ | ||
57 | - bdrv_dirty_bitmap_merge_internal(bm, job->bcs->copy_bitmap, | ||
58 | + bdrv_dirty_bitmap_merge_internal(bm, block_copy_dirty_bitmap(job->bcs), | ||
59 | NULL, true); | ||
60 | } | 115 | } |
61 | } | 116 | |
62 | @@ -XXX,XX +XXX,XX @@ void backup_do_checkpoint(BlockJob *job, Error **errp) | 117 | @@ -XXX,XX +XXX,XX @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) |
118 | /* Wait for QEMU to confirm that it's registered the handler for the | ||
119 | * faults. | ||
120 | */ | ||
121 | - if (!vu_message_read(dev, dev->sock, vmsg) || | ||
122 | + if (!dev->read_msg(dev, dev->sock, vmsg) || | ||
123 | vmsg->size != sizeof(vmsg->payload.u64) || | ||
124 | vmsg->payload.u64 != 0) { | ||
125 | vu_panic(dev, "failed to receive valid ack for postcopy set-mem-table"); | ||
126 | @@ -XXX,XX +XXX,XX @@ vu_dispatch(VuDev *dev) | ||
127 | int reply_requested; | ||
128 | bool need_reply, success = false; | ||
129 | |||
130 | - if (!vu_message_read(dev, dev->sock, &vmsg)) { | ||
131 | + if (!dev->read_msg(dev, dev->sock, &vmsg)) { | ||
132 | goto end; | ||
133 | } | ||
134 | |||
135 | @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, | ||
136 | uint16_t max_queues, | ||
137 | int socket, | ||
138 | vu_panic_cb panic, | ||
139 | + vu_read_msg_cb read_msg, | ||
140 | vu_set_watch_cb set_watch, | ||
141 | vu_remove_watch_cb remove_watch, | ||
142 | const VuDevIface *iface) | ||
143 | @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, | ||
144 | |||
145 | dev->sock = socket; | ||
146 | dev->panic = panic; | ||
147 | + dev->read_msg = read_msg ? read_msg : vu_message_read_default; | ||
148 | dev->set_watch = set_watch; | ||
149 | dev->remove_watch = remove_watch; | ||
150 | dev->iface = iface; | ||
151 | @@ -XXX,XX +XXX,XX @@ static void _vu_queue_notify(VuDev *dev, VuVirtq *vq, bool sync) | ||
152 | |||
153 | vu_message_write(dev, dev->slave_fd, &vmsg); | ||
154 | if (ack) { | ||
155 | - vu_message_read(dev, dev->slave_fd, &vmsg); | ||
156 | + vu_message_read_default(dev, dev->slave_fd, &vmsg); | ||
157 | } | ||
63 | return; | 158 | return; |
64 | } | 159 | } |
65 | 160 | diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c | |
66 | - bdrv_set_dirty_bitmap(backup_job->bcs->copy_bitmap, 0, backup_job->len); | 161 | index XXXXXXX..XXXXXXX 100644 |
67 | + bdrv_set_dirty_bitmap(block_copy_dirty_bitmap(backup_job->bcs), 0, | 162 | --- a/tests/vhost-user-bridge.c |
68 | + backup_job->len); | 163 | +++ b/tests/vhost-user-bridge.c |
164 | @@ -XXX,XX +XXX,XX @@ vubr_accept_cb(int sock, void *ctx) | ||
165 | VHOST_USER_BRIDGE_MAX_QUEUES, | ||
166 | conn_fd, | ||
167 | vubr_panic, | ||
168 | + NULL, | ||
169 | vubr_set_watch, | ||
170 | vubr_remove_watch, | ||
171 | &vuiface)) { | ||
172 | @@ -XXX,XX +XXX,XX @@ vubr_new(const char *path, bool client) | ||
173 | VHOST_USER_BRIDGE_MAX_QUEUES, | ||
174 | dev->sock, | ||
175 | vubr_panic, | ||
176 | + NULL, | ||
177 | vubr_set_watch, | ||
178 | vubr_remove_watch, | ||
179 | &vuiface)) { | ||
180 | diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c | ||
181 | index XXXXXXX..XXXXXXX 100644 | ||
182 | --- a/tools/virtiofsd/fuse_virtio.c | ||
183 | +++ b/tools/virtiofsd/fuse_virtio.c | ||
184 | @@ -XXX,XX +XXX,XX @@ int virtio_session_mount(struct fuse_session *se) | ||
185 | se->vu_socketfd = data_sock; | ||
186 | se->virtio_dev->se = se; | ||
187 | pthread_rwlock_init(&se->virtio_dev->vu_dispatch_rwlock, NULL); | ||
188 | - vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, fv_set_watch, | ||
189 | - fv_remove_watch, &fv_iface); | ||
190 | + vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, NULL, | ||
191 | + fv_set_watch, fv_remove_watch, &fv_iface); | ||
192 | |||
193 | return 0; | ||
69 | } | 194 | } |
70 | |||
71 | static BlockErrorAction backup_error_action(BackupBlockJob *job, | ||
72 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_loop(BackupBlockJob *job) | ||
73 | BdrvDirtyBitmapIter *bdbi; | ||
74 | int ret = 0; | ||
75 | |||
76 | - bdbi = bdrv_dirty_iter_new(job->bcs->copy_bitmap); | ||
77 | + bdbi = bdrv_dirty_iter_new(block_copy_dirty_bitmap(job->bcs)); | ||
78 | while ((offset = bdrv_dirty_iter_next(bdbi)) != -1) { | ||
79 | do { | ||
80 | if (yield_and_check(job)) { | ||
81 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_loop(BackupBlockJob *job) | ||
82 | return ret; | ||
83 | } | ||
84 | |||
85 | -static void backup_init_copy_bitmap(BackupBlockJob *job) | ||
86 | +static void backup_init_bcs_bitmap(BackupBlockJob *job) | ||
87 | { | ||
88 | bool ret; | ||
89 | uint64_t estimate; | ||
90 | + BdrvDirtyBitmap *bcs_bitmap = block_copy_dirty_bitmap(job->bcs); | ||
91 | |||
92 | if (job->sync_mode == MIRROR_SYNC_MODE_BITMAP) { | ||
93 | - ret = bdrv_dirty_bitmap_merge_internal(job->bcs->copy_bitmap, | ||
94 | - job->sync_bitmap, | ||
95 | + ret = bdrv_dirty_bitmap_merge_internal(bcs_bitmap, job->sync_bitmap, | ||
96 | NULL, true); | ||
97 | assert(ret); | ||
98 | } else { | ||
99 | @@ -XXX,XX +XXX,XX @@ static void backup_init_copy_bitmap(BackupBlockJob *job) | ||
100 | * We can't hog the coroutine to initialize this thoroughly. | ||
101 | * Set a flag and resume work when we are able to yield safely. | ||
102 | */ | ||
103 | - job->bcs->skip_unallocated = true; | ||
104 | + block_copy_set_skip_unallocated(job->bcs, true); | ||
105 | } | ||
106 | - bdrv_set_dirty_bitmap(job->bcs->copy_bitmap, 0, job->len); | ||
107 | + bdrv_set_dirty_bitmap(bcs_bitmap, 0, job->len); | ||
108 | } | ||
109 | |||
110 | - estimate = bdrv_get_dirty_count(job->bcs->copy_bitmap); | ||
111 | + estimate = bdrv_get_dirty_count(bcs_bitmap); | ||
112 | job_progress_set_remaining(&job->common.job, estimate); | ||
113 | } | ||
114 | |||
115 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) | ||
116 | BackupBlockJob *s = container_of(job, BackupBlockJob, common.job); | ||
117 | int ret = 0; | ||
118 | |||
119 | - backup_init_copy_bitmap(s); | ||
120 | + backup_init_bcs_bitmap(s); | ||
121 | |||
122 | if (s->sync_mode == MIRROR_SYNC_MODE_TOP) { | ||
123 | int64_t offset = 0; | ||
124 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) | ||
125 | |||
126 | offset += count; | ||
127 | } | ||
128 | - s->bcs->skip_unallocated = false; | ||
129 | + block_copy_set_skip_unallocated(s->bcs, false); | ||
130 | } | ||
131 | |||
132 | if (s->sync_mode == MIRROR_SYNC_MODE_NONE) { | ||
133 | /* | ||
134 | - * All bits are set in copy_bitmap to allow any cluster to be copied. | ||
135 | + * All bits are set in bcs bitmap to allow any cluster to be copied. | ||
136 | * This does not actually require them to be copied. | ||
137 | */ | ||
138 | while (!job_is_cancelled(job)) { | ||
139 | diff --git a/block/block-copy.c b/block/block-copy.c | ||
140 | index XXXXXXX..XXXXXXX 100644 | ||
141 | --- a/block/block-copy.c | ||
142 | +++ b/block/block-copy.c | ||
143 | @@ -XXX,XX +XXX,XX @@ | ||
144 | #define BLOCK_COPY_MAX_BUFFER (1 * MiB) | ||
145 | #define BLOCK_COPY_MAX_MEM (128 * MiB) | ||
146 | |||
147 | +typedef struct BlockCopyInFlightReq { | ||
148 | + int64_t offset; | ||
149 | + int64_t bytes; | ||
150 | + QLIST_ENTRY(BlockCopyInFlightReq) list; | ||
151 | + CoQueue wait_queue; /* coroutines blocked on this request */ | ||
152 | +} BlockCopyInFlightReq; | ||
153 | + | ||
154 | +typedef struct BlockCopyState { | ||
155 | + /* | ||
156 | + * BdrvChild objects are not owned or managed by block-copy. They are | ||
157 | + * provided by block-copy user and user is responsible for appropriate | ||
158 | + * permissions on these children. | ||
159 | + */ | ||
160 | + BdrvChild *source; | ||
161 | + BdrvChild *target; | ||
162 | + BdrvDirtyBitmap *copy_bitmap; | ||
163 | + int64_t in_flight_bytes; | ||
164 | + int64_t cluster_size; | ||
165 | + bool use_copy_range; | ||
166 | + int64_t copy_size; | ||
167 | + uint64_t len; | ||
168 | + QLIST_HEAD(, BlockCopyInFlightReq) inflight_reqs; | ||
169 | + | ||
170 | + BdrvRequestFlags write_flags; | ||
171 | + | ||
172 | + /* | ||
173 | + * skip_unallocated: | ||
174 | + * | ||
175 | + * Used by sync=top jobs, which first scan the source node for unallocated | ||
176 | + * areas and clear them in the copy_bitmap. During this process, the bitmap | ||
177 | + * is thus not fully initialized: It may still have bits set for areas that | ||
178 | + * are unallocated and should actually not be copied. | ||
179 | + * | ||
180 | + * This is indicated by skip_unallocated. | ||
181 | + * | ||
182 | + * In this case, block_copy() will query the source’s allocation status, | ||
183 | + * skip unallocated regions, clear them in the copy_bitmap, and invoke | ||
184 | + * block_copy_reset_unallocated() every time it does. | ||
185 | + */ | ||
186 | + bool skip_unallocated; | ||
187 | + | ||
188 | + ProgressMeter *progress; | ||
189 | + /* progress_bytes_callback: called when some copying progress is done. */ | ||
190 | + ProgressBytesCallbackFunc progress_bytes_callback; | ||
191 | + void *progress_opaque; | ||
192 | + | ||
193 | + SharedResource *mem; | ||
194 | +} BlockCopyState; | ||
195 | + | ||
196 | static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s, | ||
197 | int64_t offset, | ||
198 | int64_t bytes) | ||
199 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, | ||
200 | |||
201 | return ret; | ||
202 | } | ||
203 | + | ||
204 | +BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s) | ||
205 | +{ | ||
206 | + return s->copy_bitmap; | ||
207 | +} | ||
208 | + | ||
209 | +void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip) | ||
210 | +{ | ||
211 | + s->skip_unallocated = skip; | ||
212 | +} | ||
213 | diff --git a/include/block/block-copy.h b/include/block/block-copy.h | ||
214 | index XXXXXXX..XXXXXXX 100644 | ||
215 | --- a/include/block/block-copy.h | ||
216 | +++ b/include/block/block-copy.h | ||
217 | @@ -XXX,XX +XXX,XX @@ | ||
218 | #include "block/block.h" | ||
219 | #include "qemu/co-shared-resource.h" | ||
220 | |||
221 | -typedef struct BlockCopyInFlightReq { | ||
222 | - int64_t offset; | ||
223 | - int64_t bytes; | ||
224 | - QLIST_ENTRY(BlockCopyInFlightReq) list; | ||
225 | - CoQueue wait_queue; /* coroutines blocked on this request */ | ||
226 | -} BlockCopyInFlightReq; | ||
227 | - | ||
228 | typedef void (*ProgressBytesCallbackFunc)(int64_t bytes, void *opaque); | ||
229 | -typedef struct BlockCopyState { | ||
230 | - /* | ||
231 | - * BdrvChild objects are not owned or managed by block-copy. They are | ||
232 | - * provided by block-copy user and user is responsible for appropriate | ||
233 | - * permissions on these children. | ||
234 | - */ | ||
235 | - BdrvChild *source; | ||
236 | - BdrvChild *target; | ||
237 | - BdrvDirtyBitmap *copy_bitmap; | ||
238 | - int64_t in_flight_bytes; | ||
239 | - int64_t cluster_size; | ||
240 | - bool use_copy_range; | ||
241 | - int64_t copy_size; | ||
242 | - uint64_t len; | ||
243 | - QLIST_HEAD(, BlockCopyInFlightReq) inflight_reqs; | ||
244 | - | ||
245 | - BdrvRequestFlags write_flags; | ||
246 | - | ||
247 | - /* | ||
248 | - * skip_unallocated: | ||
249 | - * | ||
250 | - * Used by sync=top jobs, which first scan the source node for unallocated | ||
251 | - * areas and clear them in the copy_bitmap. During this process, the bitmap | ||
252 | - * is thus not fully initialized: It may still have bits set for areas that | ||
253 | - * are unallocated and should actually not be copied. | ||
254 | - * | ||
255 | - * This is indicated by skip_unallocated. | ||
256 | - * | ||
257 | - * In this case, block_copy() will query the source’s allocation status, | ||
258 | - * skip unallocated regions, clear them in the copy_bitmap, and invoke | ||
259 | - * block_copy_reset_unallocated() every time it does. | ||
260 | - */ | ||
261 | - bool skip_unallocated; | ||
262 | - | ||
263 | - ProgressMeter *progress; | ||
264 | - /* progress_bytes_callback: called when some copying progress is done. */ | ||
265 | - ProgressBytesCallbackFunc progress_bytes_callback; | ||
266 | - void *progress_opaque; | ||
267 | - | ||
268 | - SharedResource *mem; | ||
269 | -} BlockCopyState; | ||
270 | +typedef struct BlockCopyState BlockCopyState; | ||
271 | |||
272 | BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, | ||
273 | int64_t cluster_size, | ||
274 | @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, | ||
275 | int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, | ||
276 | bool *error_is_read); | ||
277 | |||
278 | +BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s); | ||
279 | +void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip); | ||
280 | + | ||
281 | #endif /* BLOCK_COPY_H */ | ||
282 | -- | 195 | -- |
283 | 2.24.1 | 196 | 2.26.2 |
284 | 197 | ||
285 | diff view generated by jsdifflib |
1 | From: Pan Nengyuan <pannengyuan@huawei.com> | 1 | From: Coiby Xu <coiby.xu@gmail.com> |
---|---|---|---|
2 | 2 | ||
3 | collect_image_check() is called twice in img_check(), the filename/format will be alloced without free the original memory. | 3 | When the client is running in gdb and quit command is run in gdb, |
4 | It is not a big deal since the process will exit anyway, but seems like a clean code and it will remove the warning spotted by asan. | 4 | QEMU will still dispatch the event which will cause segment fault in |
5 | the callback function. | ||
5 | 6 | ||
6 | Reported-by: Euler Robot <euler.robot@huawei.com> | 7 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> |
7 | Signed-off-by: Pan Nengyuan <pannengyuan@huawei.com> | 8 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> |
8 | Message-Id: <20200227012950.12256-3-pannengyuan@huawei.com> | 9 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> |
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 10 | Message-id: 20200918080912.321299-3-coiby.xu@gmail.com |
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | --- | 12 | --- |
11 | qemu-img.c | 2 ++ | 13 | contrib/libvhost-user/libvhost-user.c | 1 + |
12 | 1 file changed, 2 insertions(+) | 14 | 1 file changed, 1 insertion(+) |
13 | 15 | ||
14 | diff --git a/qemu-img.c b/qemu-img.c | 16 | diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c |
15 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/qemu-img.c | 18 | --- a/contrib/libvhost-user/libvhost-user.c |
17 | +++ b/qemu-img.c | 19 | +++ b/contrib/libvhost-user/libvhost-user.c |
18 | @@ -XXX,XX +XXX,XX @@ static int img_check(int argc, char **argv) | 20 | @@ -XXX,XX +XXX,XX @@ vu_deinit(VuDev *dev) |
19 | check->corruptions_fixed); | ||
20 | } | 21 | } |
21 | 22 | ||
22 | + qapi_free_ImageCheck(check); | 23 | if (vq->kick_fd != -1) { |
23 | + check = g_new0(ImageCheck, 1); | 24 | + dev->remove_watch(dev, vq->kick_fd); |
24 | ret = collect_image_check(bs, check, filename, fmt, 0); | 25 | close(vq->kick_fd); |
25 | 26 | vq->kick_fd = -1; | |
26 | check->leaks_fixed = leaks_fixed; | 27 | } |
27 | -- | 28 | -- |
28 | 2.24.1 | 29 | 2.26.2 |
29 | 30 | ||
30 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Coiby Xu <coiby.xu@gmail.com> | ||
1 | 2 | ||
3 | Sharing QEMU devices via vhost-user protocol. | ||
4 | |||
5 | Only one vhost-user client can connect to the server one time. | ||
6 | |||
7 | Suggested-by: Kevin Wolf <kwolf@redhat.com> | ||
8 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
9 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> | ||
10 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
11 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> | ||
12 | Message-id: 20200918080912.321299-4-coiby.xu@gmail.com | ||
13 | [Fixed size_t %lu -> %zu format string compiler error. | ||
14 | --Stefan] | ||
15 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
16 | --- | ||
17 | util/vhost-user-server.h | 65 ++++++ | ||
18 | util/vhost-user-server.c | 428 +++++++++++++++++++++++++++++++++++++++ | ||
19 | util/meson.build | 1 + | ||
20 | 3 files changed, 494 insertions(+) | ||
21 | create mode 100644 util/vhost-user-server.h | ||
22 | create mode 100644 util/vhost-user-server.c | ||
23 | |||
24 | diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h | ||
25 | new file mode 100644 | ||
26 | index XXXXXXX..XXXXXXX | ||
27 | --- /dev/null | ||
28 | +++ b/util/vhost-user-server.h | ||
29 | @@ -XXX,XX +XXX,XX @@ | ||
30 | +/* | ||
31 | + * Sharing QEMU devices via vhost-user protocol | ||
32 | + * | ||
33 | + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. | ||
34 | + * Copyright (c) 2020 Red Hat, Inc. | ||
35 | + * | ||
36 | + * This work is licensed under the terms of the GNU GPL, version 2 or | ||
37 | + * later. See the COPYING file in the top-level directory. | ||
38 | + */ | ||
39 | + | ||
40 | +#ifndef VHOST_USER_SERVER_H | ||
41 | +#define VHOST_USER_SERVER_H | ||
42 | + | ||
43 | +#include "contrib/libvhost-user/libvhost-user.h" | ||
44 | +#include "io/channel-socket.h" | ||
45 | +#include "io/channel-file.h" | ||
46 | +#include "io/net-listener.h" | ||
47 | +#include "qemu/error-report.h" | ||
48 | +#include "qapi/error.h" | ||
49 | +#include "standard-headers/linux/virtio_blk.h" | ||
50 | + | ||
51 | +typedef struct VuFdWatch { | ||
52 | + VuDev *vu_dev; | ||
53 | + int fd; /*kick fd*/ | ||
54 | + void *pvt; | ||
55 | + vu_watch_cb cb; | ||
56 | + bool processing; | ||
57 | + QTAILQ_ENTRY(VuFdWatch) next; | ||
58 | +} VuFdWatch; | ||
59 | + | ||
60 | +typedef struct VuServer VuServer; | ||
61 | +typedef void DevicePanicNotifierFn(VuServer *server); | ||
62 | + | ||
63 | +struct VuServer { | ||
64 | + QIONetListener *listener; | ||
65 | + AioContext *ctx; | ||
66 | + DevicePanicNotifierFn *device_panic_notifier; | ||
67 | + int max_queues; | ||
68 | + const VuDevIface *vu_iface; | ||
69 | + VuDev vu_dev; | ||
70 | + QIOChannel *ioc; /* The I/O channel with the client */ | ||
71 | + QIOChannelSocket *sioc; /* The underlying data channel with the client */ | ||
72 | + /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ | ||
73 | + QIOChannel *ioc_slave; | ||
74 | + QIOChannelSocket *sioc_slave; | ||
75 | + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ | ||
76 | + QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; | ||
77 | + /* restart coroutine co_trip if AIOContext is changed */ | ||
78 | + bool aio_context_changed; | ||
79 | + bool processing_msg; | ||
80 | +}; | ||
81 | + | ||
82 | +bool vhost_user_server_start(VuServer *server, | ||
83 | + SocketAddress *unix_socket, | ||
84 | + AioContext *ctx, | ||
85 | + uint16_t max_queues, | ||
86 | + DevicePanicNotifierFn *device_panic_notifier, | ||
87 | + const VuDevIface *vu_iface, | ||
88 | + Error **errp); | ||
89 | + | ||
90 | +void vhost_user_server_stop(VuServer *server); | ||
91 | + | ||
92 | +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); | ||
93 | + | ||
94 | +#endif /* VHOST_USER_SERVER_H */ | ||
95 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
96 | new file mode 100644 | ||
97 | index XXXXXXX..XXXXXXX | ||
98 | --- /dev/null | ||
99 | +++ b/util/vhost-user-server.c | ||
100 | @@ -XXX,XX +XXX,XX @@ | ||
101 | +/* | ||
102 | + * Sharing QEMU devices via vhost-user protocol | ||
103 | + * | ||
104 | + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. | ||
105 | + * Copyright (c) 2020 Red Hat, Inc. | ||
106 | + * | ||
107 | + * This work is licensed under the terms of the GNU GPL, version 2 or | ||
108 | + * later. See the COPYING file in the top-level directory. | ||
109 | + */ | ||
110 | +#include "qemu/osdep.h" | ||
111 | +#include "qemu/main-loop.h" | ||
112 | +#include "vhost-user-server.h" | ||
113 | + | ||
114 | +static void vmsg_close_fds(VhostUserMsg *vmsg) | ||
115 | +{ | ||
116 | + int i; | ||
117 | + for (i = 0; i < vmsg->fd_num; i++) { | ||
118 | + close(vmsg->fds[i]); | ||
119 | + } | ||
120 | +} | ||
121 | + | ||
122 | +static void vmsg_unblock_fds(VhostUserMsg *vmsg) | ||
123 | +{ | ||
124 | + int i; | ||
125 | + for (i = 0; i < vmsg->fd_num; i++) { | ||
126 | + qemu_set_nonblock(vmsg->fds[i]); | ||
127 | + } | ||
128 | +} | ||
129 | + | ||
130 | +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, | ||
131 | + gpointer opaque); | ||
132 | + | ||
133 | +static void close_client(VuServer *server) | ||
134 | +{ | ||
135 | + /* | ||
136 | + * Before closing the client | ||
137 | + * | ||
138 | + * 1. Let vu_client_trip stop processing new vhost-user msg | ||
139 | + * | ||
140 | + * 2. remove kick_handler | ||
141 | + * | ||
142 | + * 3. wait for the kick handler to be finished | ||
143 | + * | ||
144 | + * 4. wait for the current vhost-user msg to be finished processing | ||
145 | + */ | ||
146 | + | ||
147 | + QIOChannelSocket *sioc = server->sioc; | ||
148 | + /* When this is set vu_client_trip will stop new processing vhost-user message */ | ||
149 | + server->sioc = NULL; | ||
150 | + | ||
151 | + VuFdWatch *vu_fd_watch, *next; | ||
152 | + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { | ||
153 | + aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, | ||
154 | + NULL, NULL, NULL); | ||
155 | + } | ||
156 | + | ||
157 | + while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { | ||
158 | + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { | ||
159 | + if (!vu_fd_watch->processing) { | ||
160 | + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); | ||
161 | + g_free(vu_fd_watch); | ||
162 | + } | ||
163 | + } | ||
164 | + } | ||
165 | + | ||
166 | + while (server->processing_msg) { | ||
167 | + if (server->ioc->read_coroutine) { | ||
168 | + server->ioc->read_coroutine = NULL; | ||
169 | + qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, | ||
170 | + NULL, server->ioc); | ||
171 | + server->processing_msg = false; | ||
172 | + } | ||
173 | + } | ||
174 | + | ||
175 | + vu_deinit(&server->vu_dev); | ||
176 | + object_unref(OBJECT(sioc)); | ||
177 | + object_unref(OBJECT(server->ioc)); | ||
178 | +} | ||
179 | + | ||
180 | +static void panic_cb(VuDev *vu_dev, const char *buf) | ||
181 | +{ | ||
182 | + VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
183 | + | ||
184 | + /* avoid while loop in close_client */ | ||
185 | + server->processing_msg = false; | ||
186 | + | ||
187 | + if (buf) { | ||
188 | + error_report("vu_panic: %s", buf); | ||
189 | + } | ||
190 | + | ||
191 | + if (server->sioc) { | ||
192 | + close_client(server); | ||
193 | + } | ||
194 | + | ||
195 | + if (server->device_panic_notifier) { | ||
196 | + server->device_panic_notifier(server); | ||
197 | + } | ||
198 | + | ||
199 | + /* | ||
200 | + * Set the callback function for network listener so another | ||
201 | + * vhost-user client can connect to this server | ||
202 | + */ | ||
203 | + qio_net_listener_set_client_func(server->listener, | ||
204 | + vu_accept, | ||
205 | + server, | ||
206 | + NULL); | ||
207 | +} | ||
208 | + | ||
209 | +static bool coroutine_fn | ||
210 | +vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) | ||
211 | +{ | ||
212 | + struct iovec iov = { | ||
213 | + .iov_base = (char *)vmsg, | ||
214 | + .iov_len = VHOST_USER_HDR_SIZE, | ||
215 | + }; | ||
216 | + int rc, read_bytes = 0; | ||
217 | + Error *local_err = NULL; | ||
218 | + /* | ||
219 | + * Store fds/nfds returned from qio_channel_readv_full into | ||
220 | + * temporary variables. | ||
221 | + * | ||
222 | + * VhostUserMsg is a packed structure, gcc will complain about passing | ||
223 | + * pointer to a packed structure member if we pass &VhostUserMsg.fd_num | ||
224 | + * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, | ||
225 | + * thus two temporary variables nfds and fds are used here. | ||
226 | + */ | ||
227 | + size_t nfds = 0, nfds_t = 0; | ||
228 | + const size_t max_fds = G_N_ELEMENTS(vmsg->fds); | ||
229 | + int *fds_t = NULL; | ||
230 | + VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
231 | + QIOChannel *ioc = server->ioc; | ||
232 | + | ||
233 | + if (!ioc) { | ||
234 | + error_report_err(local_err); | ||
235 | + goto fail; | ||
236 | + } | ||
237 | + | ||
238 | + assert(qemu_in_coroutine()); | ||
239 | + do { | ||
240 | + /* | ||
241 | + * qio_channel_readv_full may have short reads, keeping calling it | ||
242 | + * until getting VHOST_USER_HDR_SIZE or 0 bytes in total | ||
243 | + */ | ||
244 | + rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); | ||
245 | + if (rc < 0) { | ||
246 | + if (rc == QIO_CHANNEL_ERR_BLOCK) { | ||
247 | + qio_channel_yield(ioc, G_IO_IN); | ||
248 | + continue; | ||
249 | + } else { | ||
250 | + error_report_err(local_err); | ||
251 | + return false; | ||
252 | + } | ||
253 | + } | ||
254 | + read_bytes += rc; | ||
255 | + if (nfds_t > 0) { | ||
256 | + if (nfds + nfds_t > max_fds) { | ||
257 | + error_report("A maximum of %zu fds are allowed, " | ||
258 | + "however got %zu fds now", | ||
259 | + max_fds, nfds + nfds_t); | ||
260 | + goto fail; | ||
261 | + } | ||
262 | + memcpy(vmsg->fds + nfds, fds_t, | ||
263 | + nfds_t *sizeof(vmsg->fds[0])); | ||
264 | + nfds += nfds_t; | ||
265 | + g_free(fds_t); | ||
266 | + } | ||
267 | + if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { | ||
268 | + break; | ||
269 | + } | ||
270 | + iov.iov_base = (char *)vmsg + read_bytes; | ||
271 | + iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; | ||
272 | + } while (true); | ||
273 | + | ||
274 | + vmsg->fd_num = nfds; | ||
275 | + /* qio_channel_readv_full will make socket fds blocking, unblock them */ | ||
276 | + vmsg_unblock_fds(vmsg); | ||
277 | + if (vmsg->size > sizeof(vmsg->payload)) { | ||
278 | + error_report("Error: too big message request: %d, " | ||
279 | + "size: vmsg->size: %u, " | ||
280 | + "while sizeof(vmsg->payload) = %zu", | ||
281 | + vmsg->request, vmsg->size, sizeof(vmsg->payload)); | ||
282 | + goto fail; | ||
283 | + } | ||
284 | + | ||
285 | + struct iovec iov_payload = { | ||
286 | + .iov_base = (char *)&vmsg->payload, | ||
287 | + .iov_len = vmsg->size, | ||
288 | + }; | ||
289 | + if (vmsg->size) { | ||
290 | + rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); | ||
291 | + if (rc == -1) { | ||
292 | + error_report_err(local_err); | ||
293 | + goto fail; | ||
294 | + } | ||
295 | + } | ||
296 | + | ||
297 | + return true; | ||
298 | + | ||
299 | +fail: | ||
300 | + vmsg_close_fds(vmsg); | ||
301 | + | ||
302 | + return false; | ||
303 | +} | ||
304 | + | ||
305 | + | ||
306 | +static void vu_client_start(VuServer *server); | ||
307 | +static coroutine_fn void vu_client_trip(void *opaque) | ||
308 | +{ | ||
309 | + VuServer *server = opaque; | ||
310 | + | ||
311 | + while (!server->aio_context_changed && server->sioc) { | ||
312 | + server->processing_msg = true; | ||
313 | + vu_dispatch(&server->vu_dev); | ||
314 | + server->processing_msg = false; | ||
315 | + } | ||
316 | + | ||
317 | + if (server->aio_context_changed && server->sioc) { | ||
318 | + server->aio_context_changed = false; | ||
319 | + vu_client_start(server); | ||
320 | + } | ||
321 | +} | ||
322 | + | ||
323 | +static void vu_client_start(VuServer *server) | ||
324 | +{ | ||
325 | + server->co_trip = qemu_coroutine_create(vu_client_trip, server); | ||
326 | + aio_co_enter(server->ctx, server->co_trip); | ||
327 | +} | ||
328 | + | ||
329 | +/* | ||
330 | + * a wrapper for vu_kick_cb | ||
331 | + * | ||
332 | + * since aio_dispatch can only pass one user data pointer to the | ||
333 | + * callback function, pack VuDev and pvt into a struct. Then unpack it | ||
334 | + * and pass them to vu_kick_cb | ||
335 | + */ | ||
336 | +static void kick_handler(void *opaque) | ||
337 | +{ | ||
338 | + VuFdWatch *vu_fd_watch = opaque; | ||
339 | + vu_fd_watch->processing = true; | ||
340 | + vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); | ||
341 | + vu_fd_watch->processing = false; | ||
342 | +} | ||
343 | + | ||
344 | + | ||
345 | +static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) | ||
346 | +{ | ||
347 | + | ||
348 | + VuFdWatch *vu_fd_watch, *next; | ||
349 | + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { | ||
350 | + if (vu_fd_watch->fd == fd) { | ||
351 | + return vu_fd_watch; | ||
352 | + } | ||
353 | + } | ||
354 | + return NULL; | ||
355 | +} | ||
356 | + | ||
357 | +static void | ||
358 | +set_watch(VuDev *vu_dev, int fd, int vu_evt, | ||
359 | + vu_watch_cb cb, void *pvt) | ||
360 | +{ | ||
361 | + | ||
362 | + VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
363 | + g_assert(vu_dev); | ||
364 | + g_assert(fd >= 0); | ||
365 | + g_assert(cb); | ||
366 | + | ||
367 | + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); | ||
368 | + | ||
369 | + if (!vu_fd_watch) { | ||
370 | + VuFdWatch *vu_fd_watch = g_new0(VuFdWatch, 1); | ||
371 | + | ||
372 | + QTAILQ_INSERT_TAIL(&server->vu_fd_watches, vu_fd_watch, next); | ||
373 | + | ||
374 | + vu_fd_watch->fd = fd; | ||
375 | + vu_fd_watch->cb = cb; | ||
376 | + qemu_set_nonblock(fd); | ||
377 | + aio_set_fd_handler(server->ioc->ctx, fd, true, kick_handler, | ||
378 | + NULL, NULL, vu_fd_watch); | ||
379 | + vu_fd_watch->vu_dev = vu_dev; | ||
380 | + vu_fd_watch->pvt = pvt; | ||
381 | + } | ||
382 | +} | ||
383 | + | ||
384 | + | ||
385 | +static void remove_watch(VuDev *vu_dev, int fd) | ||
386 | +{ | ||
387 | + VuServer *server; | ||
388 | + g_assert(vu_dev); | ||
389 | + g_assert(fd >= 0); | ||
390 | + | ||
391 | + server = container_of(vu_dev, VuServer, vu_dev); | ||
392 | + | ||
393 | + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); | ||
394 | + | ||
395 | + if (!vu_fd_watch) { | ||
396 | + return; | ||
397 | + } | ||
398 | + aio_set_fd_handler(server->ioc->ctx, fd, true, NULL, NULL, NULL, NULL); | ||
399 | + | ||
400 | + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); | ||
401 | + g_free(vu_fd_watch); | ||
402 | +} | ||
403 | + | ||
404 | + | ||
405 | +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, | ||
406 | + gpointer opaque) | ||
407 | +{ | ||
408 | + VuServer *server = opaque; | ||
409 | + | ||
410 | + if (server->sioc) { | ||
411 | + warn_report("Only one vhost-user client is allowed to " | ||
412 | + "connect the server one time"); | ||
413 | + return; | ||
414 | + } | ||
415 | + | ||
416 | + if (!vu_init(&server->vu_dev, server->max_queues, sioc->fd, panic_cb, | ||
417 | + vu_message_read, set_watch, remove_watch, server->vu_iface)) { | ||
418 | + error_report("Failed to initialize libvhost-user"); | ||
419 | + return; | ||
420 | + } | ||
421 | + | ||
422 | + /* | ||
423 | + * Unset the callback function for network listener to make another | ||
424 | + * vhost-user client keeping waiting until this client disconnects | ||
425 | + */ | ||
426 | + qio_net_listener_set_client_func(server->listener, | ||
427 | + NULL, | ||
428 | + NULL, | ||
429 | + NULL); | ||
430 | + server->sioc = sioc; | ||
431 | + /* | ||
432 | + * Increase the object reference, so sioc will not freed by | ||
433 | + * qio_net_listener_channel_func which will call object_unref(OBJECT(sioc)) | ||
434 | + */ | ||
435 | + object_ref(OBJECT(server->sioc)); | ||
436 | + qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); | ||
437 | + server->ioc = QIO_CHANNEL(sioc); | ||
438 | + object_ref(OBJECT(server->ioc)); | ||
439 | + qio_channel_attach_aio_context(server->ioc, server->ctx); | ||
440 | + qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); | ||
441 | + vu_client_start(server); | ||
442 | +} | ||
443 | + | ||
444 | + | ||
445 | +void vhost_user_server_stop(VuServer *server) | ||
446 | +{ | ||
447 | + if (server->sioc) { | ||
448 | + close_client(server); | ||
449 | + } | ||
450 | + | ||
451 | + if (server->listener) { | ||
452 | + qio_net_listener_disconnect(server->listener); | ||
453 | + object_unref(OBJECT(server->listener)); | ||
454 | + } | ||
455 | + | ||
456 | +} | ||
457 | + | ||
458 | +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) | ||
459 | +{ | ||
460 | + VuFdWatch *vu_fd_watch, *next; | ||
461 | + void *opaque = NULL; | ||
462 | + IOHandler *io_read = NULL; | ||
463 | + bool attach; | ||
464 | + | ||
465 | + server->ctx = ctx ? ctx : qemu_get_aio_context(); | ||
466 | + | ||
467 | + if (!server->sioc) { | ||
468 | + /* not yet serving any client*/ | ||
469 | + return; | ||
470 | + } | ||
471 | + | ||
472 | + if (ctx) { | ||
473 | + qio_channel_attach_aio_context(server->ioc, ctx); | ||
474 | + server->aio_context_changed = true; | ||
475 | + io_read = kick_handler; | ||
476 | + attach = true; | ||
477 | + } else { | ||
478 | + qio_channel_detach_aio_context(server->ioc); | ||
479 | + /* server->ioc->ctx keeps the old AioConext */ | ||
480 | + ctx = server->ioc->ctx; | ||
481 | + attach = false; | ||
482 | + } | ||
483 | + | ||
484 | + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { | ||
485 | + if (vu_fd_watch->cb) { | ||
486 | + opaque = attach ? vu_fd_watch : NULL; | ||
487 | + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, | ||
488 | + io_read, NULL, NULL, | ||
489 | + opaque); | ||
490 | + } | ||
491 | + } | ||
492 | +} | ||
493 | + | ||
494 | + | ||
495 | +bool vhost_user_server_start(VuServer *server, | ||
496 | + SocketAddress *socket_addr, | ||
497 | + AioContext *ctx, | ||
498 | + uint16_t max_queues, | ||
499 | + DevicePanicNotifierFn *device_panic_notifier, | ||
500 | + const VuDevIface *vu_iface, | ||
501 | + Error **errp) | ||
502 | +{ | ||
503 | + QIONetListener *listener = qio_net_listener_new(); | ||
504 | + if (qio_net_listener_open_sync(listener, socket_addr, 1, | ||
505 | + errp) < 0) { | ||
506 | + object_unref(OBJECT(listener)); | ||
507 | + return false; | ||
508 | + } | ||
509 | + | ||
510 | + /* zero out unspecified fileds */ | ||
511 | + *server = (VuServer) { | ||
512 | + .listener = listener, | ||
513 | + .vu_iface = vu_iface, | ||
514 | + .max_queues = max_queues, | ||
515 | + .ctx = ctx, | ||
516 | + .device_panic_notifier = device_panic_notifier, | ||
517 | + }; | ||
518 | + | ||
519 | + qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); | ||
520 | + | ||
521 | + qio_net_listener_set_client_func(server->listener, | ||
522 | + vu_accept, | ||
523 | + server, | ||
524 | + NULL); | ||
525 | + | ||
526 | + QTAILQ_INIT(&server->vu_fd_watches); | ||
527 | + return true; | ||
528 | +} | ||
529 | diff --git a/util/meson.build b/util/meson.build | ||
530 | index XXXXXXX..XXXXXXX 100644 | ||
531 | --- a/util/meson.build | ||
532 | +++ b/util/meson.build | ||
533 | @@ -XXX,XX +XXX,XX @@ if have_block | ||
534 | util_ss.add(files('main-loop.c')) | ||
535 | util_ss.add(files('nvdimm-utils.c')) | ||
536 | util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) | ||
537 | + util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) | ||
538 | util_ss.add(files('qemu-coroutine-sleep.c')) | ||
539 | util_ss.add(files('qemu-co-shared-resource.c')) | ||
540 | util_ss.add(files('thread-pool.c', 'qemu-timer.c')) | ||
541 | -- | ||
542 | 2.26.2 | ||
543 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Coiby Xu <coiby.xu@gmail.com> |
---|---|---|---|
2 | 2 | ||
3 | We need it in separate to pass to the block-copy object in the next | 3 | Move the constants from hw/core/qdev-properties.c to |
4 | commit. | 4 | util/block-helpers.h so that knowledge of the min/max values is |
5 | 5 | ||
6 | Cc: qemu-stable@nongnu.org | 6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
7 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 7 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> |
8 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 8 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> |
9 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 9 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> |
10 | Message-Id: <20200311103004.7649-2-vsementsov@virtuozzo.com> | 10 | Acked-by: Eduardo Habkost <ehabkost@redhat.com> |
11 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 11 | Message-id: 20200918080912.321299-5-coiby.xu@gmail.com |
12 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
12 | --- | 13 | --- |
13 | blockjob.c | 16 +++++----- | 14 | util/block-helpers.h | 19 +++++++++++++ |
14 | include/qemu/job.h | 11 ++----- | 15 | hw/core/qdev-properties-system.c | 31 ++++----------------- |
15 | include/qemu/progress_meter.h | 58 +++++++++++++++++++++++++++++++++++ | 16 | util/block-helpers.c | 46 ++++++++++++++++++++++++++++++++ |
16 | job-qmp.c | 4 +-- | 17 | util/meson.build | 1 + |
17 | job.c | 6 ++-- | 18 | 4 files changed, 71 insertions(+), 26 deletions(-) |
18 | qemu-img.c | 6 ++-- | 19 | create mode 100644 util/block-helpers.h |
19 | 6 files changed, 76 insertions(+), 25 deletions(-) | 20 | create mode 100644 util/block-helpers.c |
20 | create mode 100644 include/qemu/progress_meter.h | ||
21 | 21 | ||
22 | diff --git a/blockjob.c b/blockjob.c | 22 | diff --git a/util/block-helpers.h b/util/block-helpers.h |
23 | index XXXXXXX..XXXXXXX 100644 | ||
24 | --- a/blockjob.c | ||
25 | +++ b/blockjob.c | ||
26 | @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp) | ||
27 | info->device = g_strdup(job->job.id); | ||
28 | info->busy = atomic_read(&job->job.busy); | ||
29 | info->paused = job->job.pause_count > 0; | ||
30 | - info->offset = job->job.progress_current; | ||
31 | - info->len = job->job.progress_total; | ||
32 | + info->offset = job->job.progress.current; | ||
33 | + info->len = job->job.progress.total; | ||
34 | info->speed = job->speed; | ||
35 | info->io_status = job->iostatus; | ||
36 | info->ready = job_is_ready(&job->job), | ||
37 | @@ -XXX,XX +XXX,XX @@ static void block_job_event_cancelled(Notifier *n, void *opaque) | ||
38 | |||
39 | qapi_event_send_block_job_cancelled(job_type(&job->job), | ||
40 | job->job.id, | ||
41 | - job->job.progress_total, | ||
42 | - job->job.progress_current, | ||
43 | + job->job.progress.total, | ||
44 | + job->job.progress.current, | ||
45 | job->speed); | ||
46 | } | ||
47 | |||
48 | @@ -XXX,XX +XXX,XX @@ static void block_job_event_completed(Notifier *n, void *opaque) | ||
49 | |||
50 | qapi_event_send_block_job_completed(job_type(&job->job), | ||
51 | job->job.id, | ||
52 | - job->job.progress_total, | ||
53 | - job->job.progress_current, | ||
54 | + job->job.progress.total, | ||
55 | + job->job.progress.current, | ||
56 | job->speed, | ||
57 | !!msg, | ||
58 | msg); | ||
59 | @@ -XXX,XX +XXX,XX @@ static void block_job_event_ready(Notifier *n, void *opaque) | ||
60 | |||
61 | qapi_event_send_block_job_ready(job_type(&job->job), | ||
62 | job->job.id, | ||
63 | - job->job.progress_total, | ||
64 | - job->job.progress_current, | ||
65 | + job->job.progress.total, | ||
66 | + job->job.progress.current, | ||
67 | job->speed); | ||
68 | } | ||
69 | |||
70 | diff --git a/include/qemu/job.h b/include/qemu/job.h | ||
71 | index XXXXXXX..XXXXXXX 100644 | ||
72 | --- a/include/qemu/job.h | ||
73 | +++ b/include/qemu/job.h | ||
74 | @@ -XXX,XX +XXX,XX @@ | ||
75 | |||
76 | #include "qapi/qapi-types-job.h" | ||
77 | #include "qemu/queue.h" | ||
78 | +#include "qemu/progress_meter.h" | ||
79 | #include "qemu/coroutine.h" | ||
80 | #include "block/aio.h" | ||
81 | |||
82 | @@ -XXX,XX +XXX,XX @@ typedef struct Job { | ||
83 | /** True if this job should automatically dismiss itself */ | ||
84 | bool auto_dismiss; | ||
85 | |||
86 | - /** | ||
87 | - * Current progress. The unit is arbitrary as long as the ratio between | ||
88 | - * progress_current and progress_total represents the estimated percentage | ||
89 | - * of work already done. | ||
90 | - */ | ||
91 | - int64_t progress_current; | ||
92 | - | ||
93 | - /** Estimated progress_current value at the completion of the job */ | ||
94 | - int64_t progress_total; | ||
95 | + ProgressMeter progress; | ||
96 | |||
97 | /** | ||
98 | * Return code from @run and/or @prepare callback(s). | ||
99 | diff --git a/include/qemu/progress_meter.h b/include/qemu/progress_meter.h | ||
100 | new file mode 100644 | 23 | new file mode 100644 |
101 | index XXXXXXX..XXXXXXX | 24 | index XXXXXXX..XXXXXXX |
102 | --- /dev/null | 25 | --- /dev/null |
103 | +++ b/include/qemu/progress_meter.h | 26 | +++ b/util/block-helpers.h |
27 | @@ -XXX,XX +XXX,XX @@ | ||
28 | +#ifndef BLOCK_HELPERS_H | ||
29 | +#define BLOCK_HELPERS_H | ||
30 | + | ||
31 | +#include "qemu/units.h" | ||
32 | + | ||
33 | +/* lower limit is sector size */ | ||
34 | +#define MIN_BLOCK_SIZE INT64_C(512) | ||
35 | +#define MIN_BLOCK_SIZE_STR "512 B" | ||
36 | +/* | ||
37 | + * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and | ||
38 | + * matches qcow2 cluster size limit | ||
39 | + */ | ||
40 | +#define MAX_BLOCK_SIZE (2 * MiB) | ||
41 | +#define MAX_BLOCK_SIZE_STR "2 MiB" | ||
42 | + | ||
43 | +void check_block_size(const char *id, const char *name, int64_t value, | ||
44 | + Error **errp); | ||
45 | + | ||
46 | +#endif /* BLOCK_HELPERS_H */ | ||
47 | diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c | ||
48 | index XXXXXXX..XXXXXXX 100644 | ||
49 | --- a/hw/core/qdev-properties-system.c | ||
50 | +++ b/hw/core/qdev-properties-system.c | ||
51 | @@ -XXX,XX +XXX,XX @@ | ||
52 | #include "sysemu/blockdev.h" | ||
53 | #include "net/net.h" | ||
54 | #include "hw/pci/pci.h" | ||
55 | +#include "util/block-helpers.h" | ||
56 | |||
57 | static bool check_prop_still_unset(DeviceState *dev, const char *name, | ||
58 | const void *old_val, const char *new_val, | ||
59 | @@ -XXX,XX +XXX,XX @@ const PropertyInfo qdev_prop_losttickpolicy = { | ||
60 | |||
61 | /* --- blocksize --- */ | ||
62 | |||
63 | -/* lower limit is sector size */ | ||
64 | -#define MIN_BLOCK_SIZE 512 | ||
65 | -#define MIN_BLOCK_SIZE_STR "512 B" | ||
66 | -/* | ||
67 | - * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and | ||
68 | - * matches qcow2 cluster size limit | ||
69 | - */ | ||
70 | -#define MAX_BLOCK_SIZE (2 * MiB) | ||
71 | -#define MAX_BLOCK_SIZE_STR "2 MiB" | ||
72 | - | ||
73 | static void set_blocksize(Object *obj, Visitor *v, const char *name, | ||
74 | void *opaque, Error **errp) | ||
75 | { | ||
76 | @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, | ||
77 | Property *prop = opaque; | ||
78 | uint32_t *ptr = qdev_get_prop_ptr(dev, prop); | ||
79 | uint64_t value; | ||
80 | + Error *local_err = NULL; | ||
81 | |||
82 | if (dev->realized) { | ||
83 | qdev_prop_set_after_realize(dev, name, errp); | ||
84 | @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, | ||
85 | if (!visit_type_size(v, name, &value, errp)) { | ||
86 | return; | ||
87 | } | ||
88 | - /* value of 0 means "unset" */ | ||
89 | - if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { | ||
90 | - error_setg(errp, | ||
91 | - "Property %s.%s doesn't take value %" PRIu64 | ||
92 | - " (minimum: " MIN_BLOCK_SIZE_STR | ||
93 | - ", maximum: " MAX_BLOCK_SIZE_STR ")", | ||
94 | - dev->id ? : "", name, value); | ||
95 | + check_block_size(dev->id ? : "", name, value, &local_err); | ||
96 | + if (local_err) { | ||
97 | + error_propagate(errp, local_err); | ||
98 | return; | ||
99 | } | ||
100 | - | ||
101 | - /* We rely on power-of-2 blocksizes for bitmasks */ | ||
102 | - if ((value & (value - 1)) != 0) { | ||
103 | - error_setg(errp, | ||
104 | - "Property %s.%s doesn't take value '%" PRId64 "', " | ||
105 | - "it's not a power of 2", dev->id ?: "", name, (int64_t)value); | ||
106 | - return; | ||
107 | - } | ||
108 | - | ||
109 | *ptr = value; | ||
110 | } | ||
111 | |||
112 | diff --git a/util/block-helpers.c b/util/block-helpers.c | ||
113 | new file mode 100644 | ||
114 | index XXXXXXX..XXXXXXX | ||
115 | --- /dev/null | ||
116 | +++ b/util/block-helpers.c | ||
104 | @@ -XXX,XX +XXX,XX @@ | 117 | @@ -XXX,XX +XXX,XX @@ |
105 | +/* | 118 | +/* |
106 | + * Helper functionality for some process progress tracking. | 119 | + * Block utility functions |
107 | + * | 120 | + * |
108 | + * Copyright (c) 2011 IBM Corp. | 121 | + * Copyright IBM, Corp. 2011 |
109 | + * Copyright (c) 2012, 2018 Red Hat, Inc. | 122 | + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> |
110 | + * Copyright (c) 2020 Virtuozzo International GmbH | ||
111 | + * | 123 | + * |
112 | + * Permission is hereby granted, free of charge, to any person obtaining a copy | 124 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. |
113 | + * of this software and associated documentation files (the "Software"), to deal | 125 | + * See the COPYING file in the top-level directory. |
114 | + * in the Software without restriction, including without limitation the rights | ||
115 | + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | ||
116 | + * copies of the Software, and to permit persons to whom the Software is | ||
117 | + * furnished to do so, subject to the following conditions: | ||
118 | + * | ||
119 | + * The above copyright notice and this permission notice shall be included in | ||
120 | + * all copies or substantial portions of the Software. | ||
121 | + * | ||
122 | + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | ||
123 | + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, | ||
124 | + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL | ||
125 | + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER | ||
126 | + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, | ||
127 | + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN | ||
128 | + * THE SOFTWARE. | ||
129 | + */ | 126 | + */ |
130 | + | 127 | + |
131 | +#ifndef QEMU_PROGRESS_METER_H | 128 | +#include "qemu/osdep.h" |
132 | +#define QEMU_PROGRESS_METER_H | 129 | +#include "qapi/error.h" |
130 | +#include "qapi/qmp/qerror.h" | ||
131 | +#include "block-helpers.h" | ||
133 | + | 132 | + |
134 | +typedef struct ProgressMeter { | 133 | +/** |
135 | + /** | 134 | + * check_block_size: |
136 | + * Current progress. The unit is arbitrary as long as the ratio between | 135 | + * @id: The unique ID of the object |
137 | + * current and total represents the estimated percentage | 136 | + * @name: The name of the property being validated |
138 | + * of work already done. | 137 | + * @value: The block size in bytes |
139 | + */ | 138 | + * @errp: A pointer to an area to store an error |
140 | + uint64_t current; | 139 | + * |
140 | + * This function checks that the block size meets the following conditions: | ||
141 | + * 1. At least MIN_BLOCK_SIZE | ||
142 | + * 2. No larger than MAX_BLOCK_SIZE | ||
143 | + * 3. A power of 2 | ||
144 | + */ | ||
145 | +void check_block_size(const char *id, const char *name, int64_t value, | ||
146 | + Error **errp) | ||
147 | +{ | ||
148 | + /* value of 0 means "unset" */ | ||
149 | + if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { | ||
150 | + error_setg(errp, QERR_PROPERTY_VALUE_OUT_OF_RANGE, | ||
151 | + id, name, value, MIN_BLOCK_SIZE, MAX_BLOCK_SIZE); | ||
152 | + return; | ||
153 | + } | ||
141 | + | 154 | + |
142 | + /** Estimated current value at the completion of the process */ | 155 | + /* We rely on power-of-2 blocksizes for bitmasks */ |
143 | + uint64_t total; | 156 | + if ((value & (value - 1)) != 0) { |
144 | +} ProgressMeter; | 157 | + error_setg(errp, |
145 | + | 158 | + "Property %s.%s doesn't take value '%" PRId64 |
146 | +static inline void progress_work_done(ProgressMeter *pm, uint64_t done) | 159 | + "', it's not a power of 2", |
147 | +{ | 160 | + id, name, value); |
148 | + pm->current += done; | 161 | + return; |
162 | + } | ||
149 | +} | 163 | +} |
150 | + | 164 | diff --git a/util/meson.build b/util/meson.build |
151 | +static inline void progress_set_remaining(ProgressMeter *pm, uint64_t remaining) | ||
152 | +{ | ||
153 | + pm->total = pm->current + remaining; | ||
154 | +} | ||
155 | + | ||
156 | +static inline void progress_increase_remaining(ProgressMeter *pm, | ||
157 | + uint64_t delta) | ||
158 | +{ | ||
159 | + pm->total += delta; | ||
160 | +} | ||
161 | + | ||
162 | +#endif /* QEMU_PROGRESS_METER_H */ | ||
163 | diff --git a/job-qmp.c b/job-qmp.c | ||
164 | index XXXXXXX..XXXXXXX 100644 | 165 | index XXXXXXX..XXXXXXX 100644 |
165 | --- a/job-qmp.c | 166 | --- a/util/meson.build |
166 | +++ b/job-qmp.c | 167 | +++ b/util/meson.build |
167 | @@ -XXX,XX +XXX,XX @@ static JobInfo *job_query_single(Job *job, Error **errp) | 168 | @@ -XXX,XX +XXX,XX @@ if have_block |
168 | .id = g_strdup(job->id), | 169 | util_ss.add(files('nvdimm-utils.c')) |
169 | .type = job_type(job), | 170 | util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) |
170 | .status = job->status, | 171 | util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) |
171 | - .current_progress = job->progress_current, | 172 | + util_ss.add(files('block-helpers.c')) |
172 | - .total_progress = job->progress_total, | 173 | util_ss.add(files('qemu-coroutine-sleep.c')) |
173 | + .current_progress = job->progress.current, | 174 | util_ss.add(files('qemu-co-shared-resource.c')) |
174 | + .total_progress = job->progress.total, | 175 | util_ss.add(files('thread-pool.c', 'qemu-timer.c')) |
175 | .has_error = !!job->err, | ||
176 | .error = job->err ? \ | ||
177 | g_strdup(error_get_pretty(job->err)) : NULL, | ||
178 | diff --git a/job.c b/job.c | ||
179 | index XXXXXXX..XXXXXXX 100644 | ||
180 | --- a/job.c | ||
181 | +++ b/job.c | ||
182 | @@ -XXX,XX +XXX,XX @@ void job_unref(Job *job) | ||
183 | |||
184 | void job_progress_update(Job *job, uint64_t done) | ||
185 | { | ||
186 | - job->progress_current += done; | ||
187 | + progress_work_done(&job->progress, done); | ||
188 | } | ||
189 | |||
190 | void job_progress_set_remaining(Job *job, uint64_t remaining) | ||
191 | { | ||
192 | - job->progress_total = job->progress_current + remaining; | ||
193 | + progress_set_remaining(&job->progress, remaining); | ||
194 | } | ||
195 | |||
196 | void job_progress_increase_remaining(Job *job, uint64_t delta) | ||
197 | { | ||
198 | - job->progress_total += delta; | ||
199 | + progress_increase_remaining(&job->progress, delta); | ||
200 | } | ||
201 | |||
202 | void job_event_cancelled(Job *job) | ||
203 | diff --git a/qemu-img.c b/qemu-img.c | ||
204 | index XXXXXXX..XXXXXXX 100644 | ||
205 | --- a/qemu-img.c | ||
206 | +++ b/qemu-img.c | ||
207 | @@ -XXX,XX +XXX,XX @@ static void run_block_job(BlockJob *job, Error **errp) | ||
208 | do { | ||
209 | float progress = 0.0f; | ||
210 | aio_poll(aio_context, true); | ||
211 | - if (job->job.progress_total) { | ||
212 | - progress = (float)job->job.progress_current / | ||
213 | - job->job.progress_total * 100.f; | ||
214 | + if (job->job.progress.total) { | ||
215 | + progress = (float)job->job.progress.current / | ||
216 | + job->job.progress.total * 100.f; | ||
217 | } | ||
218 | qemu_progress_print(progress, 0); | ||
219 | } while (!job_is_ready(&job->job) && !job_is_completed(&job->job)); | ||
220 | -- | 176 | -- |
221 | 2.24.1 | 177 | 2.26.2 |
222 | 178 | ||
223 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Coiby Xu <coiby.xu@gmail.com> | ||
1 | 2 | ||
3 | By making use of libvhost-user, block device drive can be shared to | ||
4 | the connected vhost-user client. Only one client can connect to the | ||
5 | server one time. | ||
6 | |||
7 | Since vhost-user-server needs a block drive to be created first, delay | ||
8 | the creation of this object. | ||
9 | |||
10 | Suggested-by: Kevin Wolf <kwolf@redhat.com> | ||
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
12 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> | ||
13 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
14 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> | ||
15 | Message-id: 20200918080912.321299-6-coiby.xu@gmail.com | ||
16 | [Shorten "vhost_user_blk_server" string to "vhost_user_blk" to avoid the | ||
17 | following compiler warning: | ||
18 | ../block/export/vhost-user-blk-server.c:178:50: error: ‘%s’ directive output truncated writing 21 bytes into a region of size 20 [-Werror=format-truncation=] | ||
19 | and fix "Invalid size %ld ..." ssize_t format string arguments for | ||
20 | 32-bit hosts. | ||
21 | --Stefan] | ||
22 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
23 | --- | ||
24 | block/export/vhost-user-blk-server.h | 36 ++ | ||
25 | block/export/vhost-user-blk-server.c | 661 +++++++++++++++++++++++++++ | ||
26 | softmmu/vl.c | 4 + | ||
27 | block/meson.build | 1 + | ||
28 | 4 files changed, 702 insertions(+) | ||
29 | create mode 100644 block/export/vhost-user-blk-server.h | ||
30 | create mode 100644 block/export/vhost-user-blk-server.c | ||
31 | |||
32 | diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h | ||
33 | new file mode 100644 | ||
34 | index XXXXXXX..XXXXXXX | ||
35 | --- /dev/null | ||
36 | +++ b/block/export/vhost-user-blk-server.h | ||
37 | @@ -XXX,XX +XXX,XX @@ | ||
38 | +/* | ||
39 | + * Sharing QEMU block devices via vhost-user protocal | ||
40 | + * | ||
41 | + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. | ||
42 | + * Copyright (c) 2020 Red Hat, Inc. | ||
43 | + * | ||
44 | + * This work is licensed under the terms of the GNU GPL, version 2 or | ||
45 | + * later. See the COPYING file in the top-level directory. | ||
46 | + */ | ||
47 | + | ||
48 | +#ifndef VHOST_USER_BLK_SERVER_H | ||
49 | +#define VHOST_USER_BLK_SERVER_H | ||
50 | +#include "util/vhost-user-server.h" | ||
51 | + | ||
52 | +typedef struct VuBlockDev VuBlockDev; | ||
53 | +#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" | ||
54 | +#define VHOST_USER_BLK_SERVER(obj) \ | ||
55 | + OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) | ||
56 | + | ||
57 | +/* vhost user block device */ | ||
58 | +struct VuBlockDev { | ||
59 | + Object parent_obj; | ||
60 | + char *node_name; | ||
61 | + SocketAddress *addr; | ||
62 | + AioContext *ctx; | ||
63 | + VuServer vu_server; | ||
64 | + bool running; | ||
65 | + uint32_t blk_size; | ||
66 | + BlockBackend *backend; | ||
67 | + QIOChannelSocket *sioc; | ||
68 | + QTAILQ_ENTRY(VuBlockDev) next; | ||
69 | + struct virtio_blk_config blkcfg; | ||
70 | + bool writable; | ||
71 | +}; | ||
72 | + | ||
73 | +#endif /* VHOST_USER_BLK_SERVER_H */ | ||
74 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c | ||
75 | new file mode 100644 | ||
76 | index XXXXXXX..XXXXXXX | ||
77 | --- /dev/null | ||
78 | +++ b/block/export/vhost-user-blk-server.c | ||
79 | @@ -XXX,XX +XXX,XX @@ | ||
80 | +/* | ||
81 | + * Sharing QEMU block devices via vhost-user protocal | ||
82 | + * | ||
83 | + * Parts of the code based on nbd/server.c. | ||
84 | + * | ||
85 | + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. | ||
86 | + * Copyright (c) 2020 Red Hat, Inc. | ||
87 | + * | ||
88 | + * This work is licensed under the terms of the GNU GPL, version 2 or | ||
89 | + * later. See the COPYING file in the top-level directory. | ||
90 | + */ | ||
91 | +#include "qemu/osdep.h" | ||
92 | +#include "block/block.h" | ||
93 | +#include "vhost-user-blk-server.h" | ||
94 | +#include "qapi/error.h" | ||
95 | +#include "qom/object_interfaces.h" | ||
96 | +#include "sysemu/block-backend.h" | ||
97 | +#include "util/block-helpers.h" | ||
98 | + | ||
99 | +enum { | ||
100 | + VHOST_USER_BLK_MAX_QUEUES = 1, | ||
101 | +}; | ||
102 | +struct virtio_blk_inhdr { | ||
103 | + unsigned char status; | ||
104 | +}; | ||
105 | + | ||
106 | +typedef struct VuBlockReq { | ||
107 | + VuVirtqElement *elem; | ||
108 | + int64_t sector_num; | ||
109 | + size_t size; | ||
110 | + struct virtio_blk_inhdr *in; | ||
111 | + struct virtio_blk_outhdr out; | ||
112 | + VuServer *server; | ||
113 | + struct VuVirtq *vq; | ||
114 | +} VuBlockReq; | ||
115 | + | ||
116 | +static void vu_block_req_complete(VuBlockReq *req) | ||
117 | +{ | ||
118 | + VuDev *vu_dev = &req->server->vu_dev; | ||
119 | + | ||
120 | + /* IO size with 1 extra status byte */ | ||
121 | + vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); | ||
122 | + vu_queue_notify(vu_dev, req->vq); | ||
123 | + | ||
124 | + if (req->elem) { | ||
125 | + free(req->elem); | ||
126 | + } | ||
127 | + | ||
128 | + g_free(req); | ||
129 | +} | ||
130 | + | ||
131 | +static VuBlockDev *get_vu_block_device_by_server(VuServer *server) | ||
132 | +{ | ||
133 | + return container_of(server, VuBlockDev, vu_server); | ||
134 | +} | ||
135 | + | ||
136 | +static int coroutine_fn | ||
137 | +vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, | ||
138 | + uint32_t iovcnt, uint32_t type) | ||
139 | +{ | ||
140 | + struct virtio_blk_discard_write_zeroes desc; | ||
141 | + ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); | ||
142 | + if (unlikely(size != sizeof(desc))) { | ||
143 | + error_report("Invalid size %zd, expect %zu", size, sizeof(desc)); | ||
144 | + return -EINVAL; | ||
145 | + } | ||
146 | + | ||
147 | + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); | ||
148 | + uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, | ||
149 | + le32_to_cpu(desc.num_sectors) << 9 }; | ||
150 | + if (type == VIRTIO_BLK_T_DISCARD) { | ||
151 | + if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { | ||
152 | + return 0; | ||
153 | + } | ||
154 | + } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { | ||
155 | + if (blk_co_pwrite_zeroes(vdev_blk->backend, | ||
156 | + range[0], range[1], 0) == 0) { | ||
157 | + return 0; | ||
158 | + } | ||
159 | + } | ||
160 | + | ||
161 | + return -EINVAL; | ||
162 | +} | ||
163 | + | ||
164 | +static void coroutine_fn vu_block_flush(VuBlockReq *req) | ||
165 | +{ | ||
166 | + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); | ||
167 | + BlockBackend *backend = vdev_blk->backend; | ||
168 | + blk_co_flush(backend); | ||
169 | +} | ||
170 | + | ||
171 | +struct req_data { | ||
172 | + VuServer *server; | ||
173 | + VuVirtq *vq; | ||
174 | + VuVirtqElement *elem; | ||
175 | +}; | ||
176 | + | ||
177 | +static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
178 | +{ | ||
179 | + struct req_data *data = opaque; | ||
180 | + VuServer *server = data->server; | ||
181 | + VuVirtq *vq = data->vq; | ||
182 | + VuVirtqElement *elem = data->elem; | ||
183 | + uint32_t type; | ||
184 | + VuBlockReq *req; | ||
185 | + | ||
186 | + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
187 | + BlockBackend *backend = vdev_blk->backend; | ||
188 | + | ||
189 | + struct iovec *in_iov = elem->in_sg; | ||
190 | + struct iovec *out_iov = elem->out_sg; | ||
191 | + unsigned in_num = elem->in_num; | ||
192 | + unsigned out_num = elem->out_num; | ||
193 | + /* refer to hw/block/virtio_blk.c */ | ||
194 | + if (elem->out_num < 1 || elem->in_num < 1) { | ||
195 | + error_report("virtio-blk request missing headers"); | ||
196 | + free(elem); | ||
197 | + return; | ||
198 | + } | ||
199 | + | ||
200 | + req = g_new0(VuBlockReq, 1); | ||
201 | + req->server = server; | ||
202 | + req->vq = vq; | ||
203 | + req->elem = elem; | ||
204 | + | ||
205 | + if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, | ||
206 | + sizeof(req->out)) != sizeof(req->out))) { | ||
207 | + error_report("virtio-blk request outhdr too short"); | ||
208 | + goto err; | ||
209 | + } | ||
210 | + | ||
211 | + iov_discard_front(&out_iov, &out_num, sizeof(req->out)); | ||
212 | + | ||
213 | + if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) { | ||
214 | + error_report("virtio-blk request inhdr too short"); | ||
215 | + goto err; | ||
216 | + } | ||
217 | + | ||
218 | + /* We always touch the last byte, so just see how big in_iov is. */ | ||
219 | + req->in = (void *)in_iov[in_num - 1].iov_base | ||
220 | + + in_iov[in_num - 1].iov_len | ||
221 | + - sizeof(struct virtio_blk_inhdr); | ||
222 | + iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr)); | ||
223 | + | ||
224 | + type = le32_to_cpu(req->out.type); | ||
225 | + switch (type & ~VIRTIO_BLK_T_BARRIER) { | ||
226 | + case VIRTIO_BLK_T_IN: | ||
227 | + case VIRTIO_BLK_T_OUT: { | ||
228 | + ssize_t ret = 0; | ||
229 | + bool is_write = type & VIRTIO_BLK_T_OUT; | ||
230 | + req->sector_num = le64_to_cpu(req->out.sector); | ||
231 | + | ||
232 | + int64_t offset = req->sector_num * vdev_blk->blk_size; | ||
233 | + QEMUIOVector qiov; | ||
234 | + if (is_write) { | ||
235 | + qemu_iovec_init_external(&qiov, out_iov, out_num); | ||
236 | + ret = blk_co_pwritev(backend, offset, qiov.size, | ||
237 | + &qiov, 0); | ||
238 | + } else { | ||
239 | + qemu_iovec_init_external(&qiov, in_iov, in_num); | ||
240 | + ret = blk_co_preadv(backend, offset, qiov.size, | ||
241 | + &qiov, 0); | ||
242 | + } | ||
243 | + if (ret >= 0) { | ||
244 | + req->in->status = VIRTIO_BLK_S_OK; | ||
245 | + } else { | ||
246 | + req->in->status = VIRTIO_BLK_S_IOERR; | ||
247 | + } | ||
248 | + break; | ||
249 | + } | ||
250 | + case VIRTIO_BLK_T_FLUSH: | ||
251 | + vu_block_flush(req); | ||
252 | + req->in->status = VIRTIO_BLK_S_OK; | ||
253 | + break; | ||
254 | + case VIRTIO_BLK_T_GET_ID: { | ||
255 | + size_t size = MIN(iov_size(&elem->in_sg[0], in_num), | ||
256 | + VIRTIO_BLK_ID_BYTES); | ||
257 | + snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk"); | ||
258 | + req->in->status = VIRTIO_BLK_S_OK; | ||
259 | + req->size = elem->in_sg[0].iov_len; | ||
260 | + break; | ||
261 | + } | ||
262 | + case VIRTIO_BLK_T_DISCARD: | ||
263 | + case VIRTIO_BLK_T_WRITE_ZEROES: { | ||
264 | + int rc; | ||
265 | + rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], | ||
266 | + out_num, type); | ||
267 | + if (rc == 0) { | ||
268 | + req->in->status = VIRTIO_BLK_S_OK; | ||
269 | + } else { | ||
270 | + req->in->status = VIRTIO_BLK_S_IOERR; | ||
271 | + } | ||
272 | + break; | ||
273 | + } | ||
274 | + default: | ||
275 | + req->in->status = VIRTIO_BLK_S_UNSUPP; | ||
276 | + break; | ||
277 | + } | ||
278 | + | ||
279 | + vu_block_req_complete(req); | ||
280 | + return; | ||
281 | + | ||
282 | +err: | ||
283 | + free(elem); | ||
284 | + g_free(req); | ||
285 | + return; | ||
286 | +} | ||
287 | + | ||
288 | +static void vu_block_process_vq(VuDev *vu_dev, int idx) | ||
289 | +{ | ||
290 | + VuServer *server; | ||
291 | + VuVirtq *vq; | ||
292 | + struct req_data *req_data; | ||
293 | + | ||
294 | + server = container_of(vu_dev, VuServer, vu_dev); | ||
295 | + assert(server); | ||
296 | + | ||
297 | + vq = vu_get_queue(vu_dev, idx); | ||
298 | + assert(vq); | ||
299 | + VuVirtqElement *elem; | ||
300 | + while (1) { | ||
301 | + elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + | ||
302 | + sizeof(VuBlockReq)); | ||
303 | + if (elem) { | ||
304 | + req_data = g_new0(struct req_data, 1); | ||
305 | + req_data->server = server; | ||
306 | + req_data->vq = vq; | ||
307 | + req_data->elem = elem; | ||
308 | + Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, | ||
309 | + req_data); | ||
310 | + aio_co_enter(server->ioc->ctx, co); | ||
311 | + } else { | ||
312 | + break; | ||
313 | + } | ||
314 | + } | ||
315 | +} | ||
316 | + | ||
317 | +static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) | ||
318 | +{ | ||
319 | + VuVirtq *vq; | ||
320 | + | ||
321 | + assert(vu_dev); | ||
322 | + | ||
323 | + vq = vu_get_queue(vu_dev, idx); | ||
324 | + vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); | ||
325 | +} | ||
326 | + | ||
327 | +static uint64_t vu_block_get_features(VuDev *dev) | ||
328 | +{ | ||
329 | + uint64_t features; | ||
330 | + VuServer *server = container_of(dev, VuServer, vu_dev); | ||
331 | + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
332 | + features = 1ull << VIRTIO_BLK_F_SIZE_MAX | | ||
333 | + 1ull << VIRTIO_BLK_F_SEG_MAX | | ||
334 | + 1ull << VIRTIO_BLK_F_TOPOLOGY | | ||
335 | + 1ull << VIRTIO_BLK_F_BLK_SIZE | | ||
336 | + 1ull << VIRTIO_BLK_F_FLUSH | | ||
337 | + 1ull << VIRTIO_BLK_F_DISCARD | | ||
338 | + 1ull << VIRTIO_BLK_F_WRITE_ZEROES | | ||
339 | + 1ull << VIRTIO_BLK_F_CONFIG_WCE | | ||
340 | + 1ull << VIRTIO_F_VERSION_1 | | ||
341 | + 1ull << VIRTIO_RING_F_INDIRECT_DESC | | ||
342 | + 1ull << VIRTIO_RING_F_EVENT_IDX | | ||
343 | + 1ull << VHOST_USER_F_PROTOCOL_FEATURES; | ||
344 | + | ||
345 | + if (!vdev_blk->writable) { | ||
346 | + features |= 1ull << VIRTIO_BLK_F_RO; | ||
347 | + } | ||
348 | + | ||
349 | + return features; | ||
350 | +} | ||
351 | + | ||
352 | +static uint64_t vu_block_get_protocol_features(VuDev *dev) | ||
353 | +{ | ||
354 | + return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | | ||
355 | + 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; | ||
356 | +} | ||
357 | + | ||
358 | +static int | ||
359 | +vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) | ||
360 | +{ | ||
361 | + VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
362 | + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
363 | + memcpy(config, &vdev_blk->blkcfg, len); | ||
364 | + | ||
365 | + return 0; | ||
366 | +} | ||
367 | + | ||
368 | +static int | ||
369 | +vu_block_set_config(VuDev *vu_dev, const uint8_t *data, | ||
370 | + uint32_t offset, uint32_t size, uint32_t flags) | ||
371 | +{ | ||
372 | + VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
373 | + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
374 | + uint8_t wce; | ||
375 | + | ||
376 | + /* don't support live migration */ | ||
377 | + if (flags != VHOST_SET_CONFIG_TYPE_MASTER) { | ||
378 | + return -EINVAL; | ||
379 | + } | ||
380 | + | ||
381 | + if (offset != offsetof(struct virtio_blk_config, wce) || | ||
382 | + size != 1) { | ||
383 | + return -EINVAL; | ||
384 | + } | ||
385 | + | ||
386 | + wce = *data; | ||
387 | + vdev_blk->blkcfg.wce = wce; | ||
388 | + blk_set_enable_write_cache(vdev_blk->backend, wce); | ||
389 | + return 0; | ||
390 | +} | ||
391 | + | ||
392 | +/* | ||
393 | + * When the client disconnects, it sends a VHOST_USER_NONE request | ||
394 | + * and vu_process_message will simple call exit which cause the VM | ||
395 | + * to exit abruptly. | ||
396 | + * To avoid this issue, process VHOST_USER_NONE request ahead | ||
397 | + * of vu_process_message. | ||
398 | + * | ||
399 | + */ | ||
400 | +static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) | ||
401 | +{ | ||
402 | + if (vmsg->request == VHOST_USER_NONE) { | ||
403 | + dev->panic(dev, "disconnect"); | ||
404 | + return true; | ||
405 | + } | ||
406 | + return false; | ||
407 | +} | ||
408 | + | ||
409 | +static const VuDevIface vu_block_iface = { | ||
410 | + .get_features = vu_block_get_features, | ||
411 | + .queue_set_started = vu_block_queue_set_started, | ||
412 | + .get_protocol_features = vu_block_get_protocol_features, | ||
413 | + .get_config = vu_block_get_config, | ||
414 | + .set_config = vu_block_set_config, | ||
415 | + .process_msg = vu_block_process_msg, | ||
416 | +}; | ||
417 | + | ||
418 | +static void blk_aio_attached(AioContext *ctx, void *opaque) | ||
419 | +{ | ||
420 | + VuBlockDev *vub_dev = opaque; | ||
421 | + aio_context_acquire(ctx); | ||
422 | + vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); | ||
423 | + aio_context_release(ctx); | ||
424 | +} | ||
425 | + | ||
426 | +static void blk_aio_detach(void *opaque) | ||
427 | +{ | ||
428 | + VuBlockDev *vub_dev = opaque; | ||
429 | + AioContext *ctx = vub_dev->vu_server.ctx; | ||
430 | + aio_context_acquire(ctx); | ||
431 | + vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); | ||
432 | + aio_context_release(ctx); | ||
433 | +} | ||
434 | + | ||
435 | +static void | ||
436 | +vu_block_initialize_config(BlockDriverState *bs, | ||
437 | + struct virtio_blk_config *config, uint32_t blk_size) | ||
438 | +{ | ||
439 | + config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; | ||
440 | + config->blk_size = blk_size; | ||
441 | + config->size_max = 0; | ||
442 | + config->seg_max = 128 - 2; | ||
443 | + config->min_io_size = 1; | ||
444 | + config->opt_io_size = 1; | ||
445 | + config->num_queues = VHOST_USER_BLK_MAX_QUEUES; | ||
446 | + config->max_discard_sectors = 32768; | ||
447 | + config->max_discard_seg = 1; | ||
448 | + config->discard_sector_alignment = config->blk_size >> 9; | ||
449 | + config->max_write_zeroes_sectors = 32768; | ||
450 | + config->max_write_zeroes_seg = 1; | ||
451 | +} | ||
452 | + | ||
453 | +static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) | ||
454 | +{ | ||
455 | + | ||
456 | + BlockBackend *blk; | ||
457 | + Error *local_error = NULL; | ||
458 | + const char *node_name = vu_block_device->node_name; | ||
459 | + bool writable = vu_block_device->writable; | ||
460 | + uint64_t perm = BLK_PERM_CONSISTENT_READ; | ||
461 | + int ret; | ||
462 | + | ||
463 | + AioContext *ctx; | ||
464 | + | ||
465 | + BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); | ||
466 | + | ||
467 | + if (!bs) { | ||
468 | + error_propagate(errp, local_error); | ||
469 | + return NULL; | ||
470 | + } | ||
471 | + | ||
472 | + if (bdrv_is_read_only(bs)) { | ||
473 | + writable = false; | ||
474 | + } | ||
475 | + | ||
476 | + if (writable) { | ||
477 | + perm |= BLK_PERM_WRITE; | ||
478 | + } | ||
479 | + | ||
480 | + ctx = bdrv_get_aio_context(bs); | ||
481 | + aio_context_acquire(ctx); | ||
482 | + bdrv_invalidate_cache(bs, NULL); | ||
483 | + aio_context_release(ctx); | ||
484 | + | ||
485 | + /* | ||
486 | + * Don't allow resize while the vhost user server is running, | ||
487 | + * otherwise we don't care what happens with the node. | ||
488 | + */ | ||
489 | + blk = blk_new(bdrv_get_aio_context(bs), perm, | ||
490 | + BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | | ||
491 | + BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); | ||
492 | + ret = blk_insert_bs(blk, bs, errp); | ||
493 | + | ||
494 | + if (ret < 0) { | ||
495 | + goto fail; | ||
496 | + } | ||
497 | + | ||
498 | + blk_set_enable_write_cache(blk, false); | ||
499 | + | ||
500 | + blk_set_allow_aio_context_change(blk, true); | ||
501 | + | ||
502 | + vu_block_device->blkcfg.wce = 0; | ||
503 | + vu_block_device->backend = blk; | ||
504 | + if (!vu_block_device->blk_size) { | ||
505 | + vu_block_device->blk_size = BDRV_SECTOR_SIZE; | ||
506 | + } | ||
507 | + vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; | ||
508 | + blk_set_guest_block_size(blk, vu_block_device->blk_size); | ||
509 | + vu_block_initialize_config(bs, &vu_block_device->blkcfg, | ||
510 | + vu_block_device->blk_size); | ||
511 | + return vu_block_device; | ||
512 | + | ||
513 | +fail: | ||
514 | + blk_unref(blk); | ||
515 | + return NULL; | ||
516 | +} | ||
517 | + | ||
518 | +static void vu_block_deinit(VuBlockDev *vu_block_device) | ||
519 | +{ | ||
520 | + if (vu_block_device->backend) { | ||
521 | + blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, | ||
522 | + blk_aio_detach, vu_block_device); | ||
523 | + } | ||
524 | + | ||
525 | + blk_unref(vu_block_device->backend); | ||
526 | +} | ||
527 | + | ||
528 | +static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) | ||
529 | +{ | ||
530 | + vhost_user_server_stop(&vu_block_device->vu_server); | ||
531 | + vu_block_deinit(vu_block_device); | ||
532 | +} | ||
533 | + | ||
534 | +static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, | ||
535 | + Error **errp) | ||
536 | +{ | ||
537 | + AioContext *ctx; | ||
538 | + SocketAddress *addr = vu_block_device->addr; | ||
539 | + | ||
540 | + if (!vu_block_init(vu_block_device, errp)) { | ||
541 | + return; | ||
542 | + } | ||
543 | + | ||
544 | + ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); | ||
545 | + | ||
546 | + if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, | ||
547 | + VHOST_USER_BLK_MAX_QUEUES, | ||
548 | + NULL, &vu_block_iface, | ||
549 | + errp)) { | ||
550 | + goto error; | ||
551 | + } | ||
552 | + | ||
553 | + blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, | ||
554 | + blk_aio_detach, vu_block_device); | ||
555 | + vu_block_device->running = true; | ||
556 | + return; | ||
557 | + | ||
558 | + error: | ||
559 | + vu_block_deinit(vu_block_device); | ||
560 | +} | ||
561 | + | ||
562 | +static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) | ||
563 | +{ | ||
564 | + if (vus->running) { | ||
565 | + error_setg(errp, "The property can't be modified " | ||
566 | + "while the server is running"); | ||
567 | + return false; | ||
568 | + } | ||
569 | + return true; | ||
570 | +} | ||
571 | + | ||
572 | +static void vu_set_node_name(Object *obj, const char *value, Error **errp) | ||
573 | +{ | ||
574 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
575 | + | ||
576 | + if (!vu_prop_modifiable(vus, errp)) { | ||
577 | + return; | ||
578 | + } | ||
579 | + | ||
580 | + if (vus->node_name) { | ||
581 | + g_free(vus->node_name); | ||
582 | + } | ||
583 | + | ||
584 | + vus->node_name = g_strdup(value); | ||
585 | +} | ||
586 | + | ||
587 | +static char *vu_get_node_name(Object *obj, Error **errp) | ||
588 | +{ | ||
589 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
590 | + return g_strdup(vus->node_name); | ||
591 | +} | ||
592 | + | ||
593 | +static void free_socket_addr(SocketAddress *addr) | ||
594 | +{ | ||
595 | + g_free(addr->u.q_unix.path); | ||
596 | + g_free(addr); | ||
597 | +} | ||
598 | + | ||
599 | +static void vu_set_unix_socket(Object *obj, const char *value, | ||
600 | + Error **errp) | ||
601 | +{ | ||
602 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
603 | + | ||
604 | + if (!vu_prop_modifiable(vus, errp)) { | ||
605 | + return; | ||
606 | + } | ||
607 | + | ||
608 | + if (vus->addr) { | ||
609 | + free_socket_addr(vus->addr); | ||
610 | + } | ||
611 | + | ||
612 | + SocketAddress *addr = g_new0(SocketAddress, 1); | ||
613 | + addr->type = SOCKET_ADDRESS_TYPE_UNIX; | ||
614 | + addr->u.q_unix.path = g_strdup(value); | ||
615 | + vus->addr = addr; | ||
616 | +} | ||
617 | + | ||
618 | +static char *vu_get_unix_socket(Object *obj, Error **errp) | ||
619 | +{ | ||
620 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
621 | + return g_strdup(vus->addr->u.q_unix.path); | ||
622 | +} | ||
623 | + | ||
624 | +static bool vu_get_block_writable(Object *obj, Error **errp) | ||
625 | +{ | ||
626 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
627 | + return vus->writable; | ||
628 | +} | ||
629 | + | ||
630 | +static void vu_set_block_writable(Object *obj, bool value, Error **errp) | ||
631 | +{ | ||
632 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
633 | + | ||
634 | + if (!vu_prop_modifiable(vus, errp)) { | ||
635 | + return; | ||
636 | + } | ||
637 | + | ||
638 | + vus->writable = value; | ||
639 | +} | ||
640 | + | ||
641 | +static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, | ||
642 | + void *opaque, Error **errp) | ||
643 | +{ | ||
644 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
645 | + uint32_t value = vus->blk_size; | ||
646 | + | ||
647 | + visit_type_uint32(v, name, &value, errp); | ||
648 | +} | ||
649 | + | ||
650 | +static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, | ||
651 | + void *opaque, Error **errp) | ||
652 | +{ | ||
653 | + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
654 | + | ||
655 | + Error *local_err = NULL; | ||
656 | + uint32_t value; | ||
657 | + | ||
658 | + if (!vu_prop_modifiable(vus, errp)) { | ||
659 | + return; | ||
660 | + } | ||
661 | + | ||
662 | + visit_type_uint32(v, name, &value, &local_err); | ||
663 | + if (local_err) { | ||
664 | + goto out; | ||
665 | + } | ||
666 | + | ||
667 | + check_block_size(object_get_typename(obj), name, value, &local_err); | ||
668 | + if (local_err) { | ||
669 | + goto out; | ||
670 | + } | ||
671 | + | ||
672 | + vus->blk_size = value; | ||
673 | + | ||
674 | +out: | ||
675 | + error_propagate(errp, local_err); | ||
676 | +} | ||
677 | + | ||
678 | +static void vhost_user_blk_server_instance_finalize(Object *obj) | ||
679 | +{ | ||
680 | + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); | ||
681 | + | ||
682 | + vhost_user_blk_server_stop(vub); | ||
683 | + | ||
684 | + /* | ||
685 | + * Unlike object_property_add_str, object_class_property_add_str | ||
686 | + * doesn't have a release method. Thus manual memory freeing is | ||
687 | + * needed. | ||
688 | + */ | ||
689 | + free_socket_addr(vub->addr); | ||
690 | + g_free(vub->node_name); | ||
691 | +} | ||
692 | + | ||
693 | +static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) | ||
694 | +{ | ||
695 | + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); | ||
696 | + | ||
697 | + vhost_user_blk_server_start(vub, errp); | ||
698 | +} | ||
699 | + | ||
700 | +static void vhost_user_blk_server_class_init(ObjectClass *klass, | ||
701 | + void *class_data) | ||
702 | +{ | ||
703 | + UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); | ||
704 | + ucc->complete = vhost_user_blk_server_complete; | ||
705 | + | ||
706 | + object_class_property_add_bool(klass, "writable", | ||
707 | + vu_get_block_writable, | ||
708 | + vu_set_block_writable); | ||
709 | + | ||
710 | + object_class_property_add_str(klass, "node-name", | ||
711 | + vu_get_node_name, | ||
712 | + vu_set_node_name); | ||
713 | + | ||
714 | + object_class_property_add_str(klass, "unix-socket", | ||
715 | + vu_get_unix_socket, | ||
716 | + vu_set_unix_socket); | ||
717 | + | ||
718 | + object_class_property_add(klass, "logical-block-size", "uint32", | ||
719 | + vu_get_blk_size, vu_set_blk_size, | ||
720 | + NULL, NULL); | ||
721 | +} | ||
722 | + | ||
723 | +static const TypeInfo vhost_user_blk_server_info = { | ||
724 | + .name = TYPE_VHOST_USER_BLK_SERVER, | ||
725 | + .parent = TYPE_OBJECT, | ||
726 | + .instance_size = sizeof(VuBlockDev), | ||
727 | + .instance_finalize = vhost_user_blk_server_instance_finalize, | ||
728 | + .class_init = vhost_user_blk_server_class_init, | ||
729 | + .interfaces = (InterfaceInfo[]) { | ||
730 | + {TYPE_USER_CREATABLE}, | ||
731 | + {} | ||
732 | + }, | ||
733 | +}; | ||
734 | + | ||
735 | +static void vhost_user_blk_server_register_types(void) | ||
736 | +{ | ||
737 | + type_register_static(&vhost_user_blk_server_info); | ||
738 | +} | ||
739 | + | ||
740 | +type_init(vhost_user_blk_server_register_types) | ||
741 | diff --git a/softmmu/vl.c b/softmmu/vl.c | ||
742 | index XXXXXXX..XXXXXXX 100644 | ||
743 | --- a/softmmu/vl.c | ||
744 | +++ b/softmmu/vl.c | ||
745 | @@ -XXX,XX +XXX,XX @@ static bool object_create_initial(const char *type, QemuOpts *opts) | ||
746 | } | ||
747 | #endif | ||
748 | |||
749 | + /* Reason: vhost-user-blk-server property "node-name" */ | ||
750 | + if (g_str_equal(type, "vhost-user-blk-server")) { | ||
751 | + return false; | ||
752 | + } | ||
753 | /* | ||
754 | * Reason: filter-* property "netdev" etc. | ||
755 | */ | ||
756 | diff --git a/block/meson.build b/block/meson.build | ||
757 | index XXXXXXX..XXXXXXX 100644 | ||
758 | --- a/block/meson.build | ||
759 | +++ b/block/meson.build | ||
760 | @@ -XXX,XX +XXX,XX @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') | ||
761 | block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) | ||
762 | block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) | ||
763 | block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) | ||
764 | +block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) | ||
765 | block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) | ||
766 | block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) | ||
767 | block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) | ||
768 | -- | ||
769 | 2.26.2 | ||
770 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Coiby Xu <coiby.xu@gmail.com> | ||
1 | 2 | ||
3 | Suggested-by: Stefano Garzarella <sgarzare@redhat.com> | ||
4 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> | ||
5 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> | ||
7 | Message-id: 20200918080912.321299-8-coiby.xu@gmail.com | ||
8 | [Removed reference to vhost-user-blk-test.c, it will be sent in a | ||
9 | separate pull request. | ||
10 | --Stefan] | ||
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
12 | --- | ||
13 | MAINTAINERS | 7 +++++++ | ||
14 | 1 file changed, 7 insertions(+) | ||
15 | |||
16 | diff --git a/MAINTAINERS b/MAINTAINERS | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/MAINTAINERS | ||
19 | +++ b/MAINTAINERS | ||
20 | @@ -XXX,XX +XXX,XX @@ L: qemu-block@nongnu.org | ||
21 | S: Supported | ||
22 | F: tests/image-fuzzer/ | ||
23 | |||
24 | +Vhost-user block device backend server | ||
25 | +M: Coiby Xu <Coiby.Xu@gmail.com> | ||
26 | +S: Maintained | ||
27 | +F: block/export/vhost-user-blk-server.c | ||
28 | +F: util/vhost-user-server.c | ||
29 | +F: tests/qtest/libqos/vhost-user-blk.c | ||
30 | + | ||
31 | Replication | ||
32 | M: Wen Congyang <wencongyang2@huawei.com> | ||
33 | M: Xie Changlong <xiechanglong.d@gmail.com> | ||
34 | -- | ||
35 | 2.26.2 | ||
36 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
2 | Message-id: 20200924151549.913737-3-stefanha@redhat.com | ||
3 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
4 | --- | ||
5 | util/vhost-user-server.c | 2 +- | ||
6 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
1 | 7 | ||
8 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
9 | index XXXXXXX..XXXXXXX 100644 | ||
10 | --- a/util/vhost-user-server.c | ||
11 | +++ b/util/vhost-user-server.c | ||
12 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, | ||
13 | return false; | ||
14 | } | ||
15 | |||
16 | - /* zero out unspecified fileds */ | ||
17 | + /* zero out unspecified fields */ | ||
18 | *server = (VuServer) { | ||
19 | .listener = listener, | ||
20 | .vu_iface = vu_iface, | ||
21 | -- | ||
22 | 2.26.2 | ||
23 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | We already have access to the value with the correct type (ioc and sioc | ||
2 | are the same QIOChannel). | ||
1 | 3 | ||
4 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
5 | Message-id: 20200924151549.913737-4-stefanha@redhat.com | ||
6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
7 | --- | ||
8 | util/vhost-user-server.c | 2 +- | ||
9 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
10 | |||
11 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
12 | index XXXXXXX..XXXXXXX 100644 | ||
13 | --- a/util/vhost-user-server.c | ||
14 | +++ b/util/vhost-user-server.c | ||
15 | @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, | ||
16 | server->ioc = QIO_CHANNEL(sioc); | ||
17 | object_ref(OBJECT(server->ioc)); | ||
18 | qio_channel_attach_aio_context(server->ioc, server->ctx); | ||
19 | - qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); | ||
20 | + qio_channel_set_blocking(server->ioc, false, NULL); | ||
21 | vu_client_start(server); | ||
22 | } | ||
23 | |||
24 | -- | ||
25 | 2.26.2 | ||
26 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | Explicitly deleting watches is not necessary since libvhost-user calls |
---|---|---|---|
2 | 2 | remove_watch() during vu_deinit(). Add an assertion to check this | |
3 | The qcow2 .bdrv_measure() code calculates the crypto payload offset. | 3 | though. |
4 | This logic really belongs in crypto/block.c where it can be reused by | ||
5 | other image formats. | ||
6 | |||
7 | The "luks" block driver will need this same logic in order to implement | ||
8 | .bdrv_measure(), so extract the qcrypto_block_calculate_payload_offset() | ||
9 | function now. | ||
10 | 4 | ||
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
12 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 6 | Message-id: 20200924151549.913737-5-stefanha@redhat.com |
13 | Message-Id: <20200221112522.1497712-2-stefanha@redhat.com> | 7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
14 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
15 | --- | 8 | --- |
16 | block/qcow2.c | 74 +++++++++++------------------------------- | 9 | util/vhost-user-server.c | 19 ++++--------------- |
17 | crypto/block.c | 36 ++++++++++++++++++++ | 10 | 1 file changed, 4 insertions(+), 15 deletions(-) |
18 | include/crypto/block.h | 22 +++++++++++++ | ||
19 | 3 files changed, 77 insertions(+), 55 deletions(-) | ||
20 | 11 | ||
21 | diff --git a/block/qcow2.c b/block/qcow2.c | 12 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c |
22 | index XXXXXXX..XXXXXXX 100644 | 13 | index XXXXXXX..XXXXXXX 100644 |
23 | --- a/block/qcow2.c | 14 | --- a/util/vhost-user-server.c |
24 | +++ b/block/qcow2.c | 15 | +++ b/util/vhost-user-server.c |
25 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs) | 16 | @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) |
26 | return ret; | 17 | /* When this is set vu_client_trip will stop new processing vhost-user message */ |
27 | } | 18 | server->sioc = NULL; |
28 | 19 | ||
29 | -static ssize_t qcow2_measure_crypto_hdr_init_func(QCryptoBlock *block, | 20 | - VuFdWatch *vu_fd_watch, *next; |
30 | - size_t headerlen, void *opaque, Error **errp) | 21 | - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { |
31 | -{ | 22 | - aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, |
32 | - size_t *headerlenp = opaque; | 23 | - NULL, NULL, NULL); |
33 | - | ||
34 | - /* Stash away the payload size */ | ||
35 | - *headerlenp = headerlen; | ||
36 | - return 0; | ||
37 | -} | ||
38 | - | ||
39 | -static ssize_t qcow2_measure_crypto_hdr_write_func(QCryptoBlock *block, | ||
40 | - size_t offset, const uint8_t *buf, size_t buflen, | ||
41 | - void *opaque, Error **errp) | ||
42 | -{ | ||
43 | - /* Discard the bytes, we're not actually writing to an image */ | ||
44 | - return buflen; | ||
45 | -} | ||
46 | - | ||
47 | -/* Determine the number of bytes for the LUKS payload */ | ||
48 | -static bool qcow2_measure_luks_headerlen(QemuOpts *opts, size_t *len, | ||
49 | - Error **errp) | ||
50 | -{ | ||
51 | - QDict *opts_qdict; | ||
52 | - QDict *cryptoopts_qdict; | ||
53 | - QCryptoBlockCreateOptions *cryptoopts; | ||
54 | - QCryptoBlock *crypto; | ||
55 | - | ||
56 | - /* Extract "encrypt." options into a qdict */ | ||
57 | - opts_qdict = qemu_opts_to_qdict(opts, NULL); | ||
58 | - qdict_extract_subqdict(opts_qdict, &cryptoopts_qdict, "encrypt."); | ||
59 | - qobject_unref(opts_qdict); | ||
60 | - | ||
61 | - /* Build QCryptoBlockCreateOptions object from qdict */ | ||
62 | - qdict_put_str(cryptoopts_qdict, "format", "luks"); | ||
63 | - cryptoopts = block_crypto_create_opts_init(cryptoopts_qdict, errp); | ||
64 | - qobject_unref(cryptoopts_qdict); | ||
65 | - if (!cryptoopts) { | ||
66 | - return false; | ||
67 | - } | 24 | - } |
68 | - | 25 | - |
69 | - /* Fake LUKS creation in order to determine the payload size */ | 26 | - while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { |
70 | - crypto = qcrypto_block_create(cryptoopts, "encrypt.", | 27 | - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { |
71 | - qcow2_measure_crypto_hdr_init_func, | 28 | - if (!vu_fd_watch->processing) { |
72 | - qcow2_measure_crypto_hdr_write_func, | 29 | - QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); |
73 | - len, errp); | 30 | - g_free(vu_fd_watch); |
74 | - qapi_free_QCryptoBlockCreateOptions(cryptoopts); | 31 | - } |
75 | - if (!crypto) { | 32 | - } |
76 | - return false; | ||
77 | - } | 33 | - } |
78 | - | 34 | - |
79 | - qcrypto_block_free(crypto); | 35 | while (server->processing_msg) { |
80 | - return true; | 36 | if (server->ioc->read_coroutine) { |
81 | -} | 37 | server->ioc->read_coroutine = NULL; |
82 | - | 38 | @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) |
83 | static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, | 39 | } |
84 | Error **errp) | 40 | |
85 | { | 41 | vu_deinit(&server->vu_dev); |
86 | @@ -XXX,XX +XXX,XX @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, | ||
87 | g_free(optstr); | ||
88 | |||
89 | if (has_luks) { | ||
90 | + g_autoptr(QCryptoBlockCreateOptions) create_opts = NULL; | ||
91 | + QDict *opts_qdict; | ||
92 | + QDict *cryptoopts; | ||
93 | size_t headerlen; | ||
94 | |||
95 | - if (!qcow2_measure_luks_headerlen(opts, &headerlen, &local_err)) { | ||
96 | + opts_qdict = qemu_opts_to_qdict(opts, NULL); | ||
97 | + qdict_extract_subqdict(opts_qdict, &cryptoopts, "encrypt."); | ||
98 | + qobject_unref(opts_qdict); | ||
99 | + | 42 | + |
100 | + qdict_put_str(cryptoopts, "format", "luks"); | 43 | + /* vu_deinit() should have called remove_watch() */ |
44 | + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); | ||
101 | + | 45 | + |
102 | + create_opts = block_crypto_create_opts_init(cryptoopts, errp); | 46 | object_unref(OBJECT(sioc)); |
103 | + qobject_unref(cryptoopts); | 47 | object_unref(OBJECT(server->ioc)); |
104 | + if (!create_opts) { | ||
105 | + goto err; | ||
106 | + } | ||
107 | + | ||
108 | + if (!qcrypto_block_calculate_payload_offset(create_opts, | ||
109 | + "encrypt.", | ||
110 | + &headerlen, | ||
111 | + &local_err)) { | ||
112 | goto err; | ||
113 | } | ||
114 | |||
115 | diff --git a/crypto/block.c b/crypto/block.c | ||
116 | index XXXXXXX..XXXXXXX 100644 | ||
117 | --- a/crypto/block.c | ||
118 | +++ b/crypto/block.c | ||
119 | @@ -XXX,XX +XXX,XX @@ QCryptoBlock *qcrypto_block_create(QCryptoBlockCreateOptions *options, | ||
120 | } | 48 | } |
121 | |||
122 | |||
123 | +static ssize_t qcrypto_block_headerlen_hdr_init_func(QCryptoBlock *block, | ||
124 | + size_t headerlen, void *opaque, Error **errp) | ||
125 | +{ | ||
126 | + size_t *headerlenp = opaque; | ||
127 | + | ||
128 | + /* Stash away the payload size */ | ||
129 | + *headerlenp = headerlen; | ||
130 | + return 0; | ||
131 | +} | ||
132 | + | ||
133 | + | ||
134 | +static ssize_t qcrypto_block_headerlen_hdr_write_func(QCryptoBlock *block, | ||
135 | + size_t offset, const uint8_t *buf, size_t buflen, | ||
136 | + void *opaque, Error **errp) | ||
137 | +{ | ||
138 | + /* Discard the bytes, we're not actually writing to an image */ | ||
139 | + return buflen; | ||
140 | +} | ||
141 | + | ||
142 | + | ||
143 | +bool | ||
144 | +qcrypto_block_calculate_payload_offset(QCryptoBlockCreateOptions *create_opts, | ||
145 | + const char *optprefix, | ||
146 | + size_t *len, | ||
147 | + Error **errp) | ||
148 | +{ | ||
149 | + /* Fake LUKS creation in order to determine the payload size */ | ||
150 | + g_autoptr(QCryptoBlock) crypto = | ||
151 | + qcrypto_block_create(create_opts, optprefix, | ||
152 | + qcrypto_block_headerlen_hdr_init_func, | ||
153 | + qcrypto_block_headerlen_hdr_write_func, | ||
154 | + len, errp); | ||
155 | + return crypto != NULL; | ||
156 | +} | ||
157 | + | ||
158 | + | ||
159 | QCryptoBlockInfo *qcrypto_block_get_info(QCryptoBlock *block, | ||
160 | Error **errp) | ||
161 | { | ||
162 | diff --git a/include/crypto/block.h b/include/crypto/block.h | ||
163 | index XXXXXXX..XXXXXXX 100644 | ||
164 | --- a/include/crypto/block.h | ||
165 | +++ b/include/crypto/block.h | ||
166 | @@ -XXX,XX +XXX,XX @@ QCryptoBlock *qcrypto_block_create(QCryptoBlockCreateOptions *options, | ||
167 | Error **errp); | ||
168 | |||
169 | |||
170 | +/** | ||
171 | + * qcrypto_block_calculate_payload_offset: | ||
172 | + * @create_opts: the encryption options | ||
173 | + * @optprefix: name prefix for options | ||
174 | + * @len: output for number of header bytes before payload | ||
175 | + * @errp: pointer to a NULL-initialized error object | ||
176 | + * | ||
177 | + * Calculate the number of header bytes before the payload in an encrypted | ||
178 | + * storage volume. The header is an area before the payload that is reserved | ||
179 | + * for encryption metadata. | ||
180 | + * | ||
181 | + * Returns: true on success, false on error | ||
182 | + */ | ||
183 | +bool | ||
184 | +qcrypto_block_calculate_payload_offset(QCryptoBlockCreateOptions *create_opts, | ||
185 | + const char *optprefix, | ||
186 | + size_t *len, | ||
187 | + Error **errp); | ||
188 | + | ||
189 | + | ||
190 | /** | ||
191 | * qcrypto_block_get_info: | ||
192 | * @block: the block encryption object | ||
193 | @@ -XXX,XX +XXX,XX @@ uint64_t qcrypto_block_get_sector_size(QCryptoBlock *block); | ||
194 | void qcrypto_block_free(QCryptoBlock *block); | ||
195 | |||
196 | G_DEFINE_AUTOPTR_CLEANUP_FUNC(QCryptoBlock, qcrypto_block_free) | ||
197 | +G_DEFINE_AUTOPTR_CLEANUP_FUNC(QCryptoBlockCreateOptions, | ||
198 | + qapi_free_QCryptoBlockCreateOptions) | ||
199 | |||
200 | #endif /* QCRYPTO_BLOCK_H */ | ||
201 | -- | 49 | -- |
202 | 2.24.1 | 50 | 2.26.2 |
203 | 51 | ||
204 | diff view generated by jsdifflib |
1 | From: Eric Blake <eblake@redhat.com> | 1 | Only one struct is needed per request. Drop req_data and the separate |
---|---|---|---|
2 | VuBlockReq instance. Instead let vu_queue_pop() allocate everything at | ||
3 | once. | ||
2 | 4 | ||
3 | Tests 261 and 272 fail on RHEL 7 with coreutils 8.22, since od | 5 | This fixes the req_data memory leak in vu_block_virtio_process_req(). |
4 | --endian was not added until coreutils 8.23. Fix this by manually | ||
5 | constructing the final value one byte at a time. | ||
6 | 6 | ||
7 | Fixes: fc8ba423 | 7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
8 | Reported-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 8 | Message-id: 20200924151549.913737-6-stefanha@redhat.com |
9 | Signed-off-by: Eric Blake <eblake@redhat.com> | 9 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
10 | Reviewed-by: Max Reitz <mreitz@redhat.com> | ||
11 | Message-Id: <20200226125424.481840-1-eblake@redhat.com> | ||
12 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
13 | --- | 10 | --- |
14 | tests/qemu-iotests/common.rc | 22 +++++++++++++++++----- | 11 | block/export/vhost-user-blk-server.c | 68 +++++++++------------------- |
15 | 1 file changed, 17 insertions(+), 5 deletions(-) | 12 | 1 file changed, 21 insertions(+), 47 deletions(-) |
16 | 13 | ||
17 | diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc | 14 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
18 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/tests/qemu-iotests/common.rc | 16 | --- a/block/export/vhost-user-blk-server.c |
20 | +++ b/tests/qemu-iotests/common.rc | 17 | +++ b/block/export/vhost-user-blk-server.c |
21 | @@ -XXX,XX +XXX,XX @@ poke_file() | 18 | @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { |
22 | # peek_file_le 'test.img' 512 2 => 65534 | 19 | }; |
23 | peek_file_le() | 20 | |
21 | typedef struct VuBlockReq { | ||
22 | - VuVirtqElement *elem; | ||
23 | + VuVirtqElement elem; | ||
24 | int64_t sector_num; | ||
25 | size_t size; | ||
26 | struct virtio_blk_inhdr *in; | ||
27 | @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) | ||
28 | VuDev *vu_dev = &req->server->vu_dev; | ||
29 | |||
30 | /* IO size with 1 extra status byte */ | ||
31 | - vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); | ||
32 | + vu_queue_push(vu_dev, req->vq, &req->elem, req->size + 1); | ||
33 | vu_queue_notify(vu_dev, req->vq); | ||
34 | |||
35 | - if (req->elem) { | ||
36 | - free(req->elem); | ||
37 | - } | ||
38 | - | ||
39 | - g_free(req); | ||
40 | + free(req); | ||
41 | } | ||
42 | |||
43 | static VuBlockDev *get_vu_block_device_by_server(VuServer *server) | ||
44 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_flush(VuBlockReq *req) | ||
45 | blk_co_flush(backend); | ||
46 | } | ||
47 | |||
48 | -struct req_data { | ||
49 | - VuServer *server; | ||
50 | - VuVirtq *vq; | ||
51 | - VuVirtqElement *elem; | ||
52 | -}; | ||
53 | - | ||
54 | static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
24 | { | 55 | { |
25 | - # Wrap in echo $() to strip spaces | 56 | - struct req_data *data = opaque; |
26 | - echo $(od -j"$2" -N"$3" --endian=little -An -vtu"$3" "$1") | 57 | - VuServer *server = data->server; |
27 | + local val=0 shift=0 byte | 58 | - VuVirtq *vq = data->vq; |
59 | - VuVirtqElement *elem = data->elem; | ||
60 | + VuBlockReq *req = opaque; | ||
61 | + VuServer *server = req->server; | ||
62 | + VuVirtqElement *elem = &req->elem; | ||
63 | uint32_t type; | ||
64 | - VuBlockReq *req; | ||
65 | |||
66 | VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
67 | BlockBackend *backend = vdev_blk->backend; | ||
68 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
69 | struct iovec *out_iov = elem->out_sg; | ||
70 | unsigned in_num = elem->in_num; | ||
71 | unsigned out_num = elem->out_num; | ||
28 | + | 72 | + |
29 | + # coreutils' od --endian is not portable, so manually assemble bytes. | 73 | /* refer to hw/block/virtio_blk.c */ |
30 | + for byte in $(od -j"$2" -N"$3" -An -v -tu1 "$1"); do | 74 | if (elem->out_num < 1 || elem->in_num < 1) { |
31 | + val=$(( val | (byte << shift) )) | 75 | error_report("virtio-blk request missing headers"); |
32 | + shift=$((shift + 8)) | 76 | - free(elem); |
33 | + done | 77 | - return; |
34 | + printf %llu $val | 78 | + goto err; |
79 | } | ||
80 | |||
81 | - req = g_new0(VuBlockReq, 1); | ||
82 | - req->server = server; | ||
83 | - req->vq = vq; | ||
84 | - req->elem = elem; | ||
85 | - | ||
86 | if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, | ||
87 | sizeof(req->out)) != sizeof(req->out))) { | ||
88 | error_report("virtio-blk request outhdr too short"); | ||
89 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
90 | |||
91 | err: | ||
92 | free(elem); | ||
93 | - g_free(req); | ||
94 | - return; | ||
35 | } | 95 | } |
36 | 96 | ||
37 | # peek_file_be 'test.img' 512 2 => 65279 | 97 | static void vu_block_process_vq(VuDev *vu_dev, int idx) |
38 | peek_file_be() | ||
39 | { | 98 | { |
40 | - # Wrap in echo $() to strip spaces | 99 | - VuServer *server; |
41 | - echo $(od -j"$2" -N"$3" --endian=big -An -vtu"$3" "$1") | 100 | - VuVirtq *vq; |
42 | + local val=0 byte | 101 | - struct req_data *req_data; |
102 | + VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
103 | + VuVirtq *vq = vu_get_queue(vu_dev, idx); | ||
104 | |||
105 | - server = container_of(vu_dev, VuServer, vu_dev); | ||
106 | - assert(server); | ||
107 | - | ||
108 | - vq = vu_get_queue(vu_dev, idx); | ||
109 | - assert(vq); | ||
110 | - VuVirtqElement *elem; | ||
111 | while (1) { | ||
112 | - elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + | ||
113 | - sizeof(VuBlockReq)); | ||
114 | - if (elem) { | ||
115 | - req_data = g_new0(struct req_data, 1); | ||
116 | - req_data->server = server; | ||
117 | - req_data->vq = vq; | ||
118 | - req_data->elem = elem; | ||
119 | - Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, | ||
120 | - req_data); | ||
121 | - aio_co_enter(server->ioc->ctx, co); | ||
122 | - } else { | ||
123 | + VuBlockReq *req; | ||
43 | + | 124 | + |
44 | + # coreutils' od --endian is not portable, so manually assemble bytes. | 125 | + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); |
45 | + for byte in $(od -j"$2" -N"$3" -An -v -tu1 "$1"); do | 126 | + if (!req) { |
46 | + val=$(( (val << 8) | byte )) | 127 | break; |
47 | + done | 128 | } |
48 | + printf %llu $val | 129 | + |
130 | + req->server = server; | ||
131 | + req->vq = vq; | ||
132 | + | ||
133 | + Coroutine *co = | ||
134 | + qemu_coroutine_create(vu_block_virtio_process_req, req); | ||
135 | + qemu_coroutine_enter(co); | ||
136 | } | ||
49 | } | 137 | } |
50 | 138 | ||
51 | -# peek_file_raw 'test.img' 512 2 => '\xff\xfe' | ||
52 | +# peek_file_raw 'test.img' 512 2 => '\xff\xfe'. Do not use if the raw data | ||
53 | +# is likely to contain \0 or trailing \n. | ||
54 | peek_file_raw() | ||
55 | { | ||
56 | dd if="$1" bs=1 skip="$2" count="$3" status=none | ||
57 | -- | 139 | -- |
58 | 2.24.1 | 140 | 2.26.2 |
59 | 141 | ||
60 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | The device panic notifier callback is not used. Drop it. | ||
1 | 2 | ||
3 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
4 | Message-id: 20200924151549.913737-7-stefanha@redhat.com | ||
5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | --- | ||
7 | util/vhost-user-server.h | 3 --- | ||
8 | block/export/vhost-user-blk-server.c | 3 +-- | ||
9 | util/vhost-user-server.c | 6 ------ | ||
10 | 3 files changed, 1 insertion(+), 11 deletions(-) | ||
11 | |||
12 | diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/util/vhost-user-server.h | ||
15 | +++ b/util/vhost-user-server.h | ||
16 | @@ -XXX,XX +XXX,XX @@ typedef struct VuFdWatch { | ||
17 | } VuFdWatch; | ||
18 | |||
19 | typedef struct VuServer VuServer; | ||
20 | -typedef void DevicePanicNotifierFn(VuServer *server); | ||
21 | |||
22 | struct VuServer { | ||
23 | QIONetListener *listener; | ||
24 | AioContext *ctx; | ||
25 | - DevicePanicNotifierFn *device_panic_notifier; | ||
26 | int max_queues; | ||
27 | const VuDevIface *vu_iface; | ||
28 | VuDev vu_dev; | ||
29 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, | ||
30 | SocketAddress *unix_socket, | ||
31 | AioContext *ctx, | ||
32 | uint16_t max_queues, | ||
33 | - DevicePanicNotifierFn *device_panic_notifier, | ||
34 | const VuDevIface *vu_iface, | ||
35 | Error **errp); | ||
36 | |||
37 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c | ||
38 | index XXXXXXX..XXXXXXX 100644 | ||
39 | --- a/block/export/vhost-user-blk-server.c | ||
40 | +++ b/block/export/vhost-user-blk-server.c | ||
41 | @@ -XXX,XX +XXX,XX @@ static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, | ||
42 | ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); | ||
43 | |||
44 | if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, | ||
45 | - VHOST_USER_BLK_MAX_QUEUES, | ||
46 | - NULL, &vu_block_iface, | ||
47 | + VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, | ||
48 | errp)) { | ||
49 | goto error; | ||
50 | } | ||
51 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
52 | index XXXXXXX..XXXXXXX 100644 | ||
53 | --- a/util/vhost-user-server.c | ||
54 | +++ b/util/vhost-user-server.c | ||
55 | @@ -XXX,XX +XXX,XX @@ static void panic_cb(VuDev *vu_dev, const char *buf) | ||
56 | close_client(server); | ||
57 | } | ||
58 | |||
59 | - if (server->device_panic_notifier) { | ||
60 | - server->device_panic_notifier(server); | ||
61 | - } | ||
62 | - | ||
63 | /* | ||
64 | * Set the callback function for network listener so another | ||
65 | * vhost-user client can connect to this server | ||
66 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, | ||
67 | SocketAddress *socket_addr, | ||
68 | AioContext *ctx, | ||
69 | uint16_t max_queues, | ||
70 | - DevicePanicNotifierFn *device_panic_notifier, | ||
71 | const VuDevIface *vu_iface, | ||
72 | Error **errp) | ||
73 | { | ||
74 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, | ||
75 | .vu_iface = vu_iface, | ||
76 | .max_queues = max_queues, | ||
77 | .ctx = ctx, | ||
78 | - .device_panic_notifier = device_panic_notifier, | ||
79 | }; | ||
80 | |||
81 | qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); | ||
82 | -- | ||
83 | 2.26.2 | ||
84 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | fds[] is leaked when qio_channel_readv_full() fails. | ||
1 | 2 | ||
3 | Use vmsg->fds[] instead of keeping a local fds[] array. Then we can | ||
4 | reuse goto fail to clean up fds. vmsg->fd_num must be zeroed before the | ||
5 | loop to make this safe. | ||
6 | |||
7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | Message-id: 20200924151549.913737-8-stefanha@redhat.com | ||
9 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | --- | ||
11 | util/vhost-user-server.c | 50 ++++++++++++++++++---------------------- | ||
12 | 1 file changed, 23 insertions(+), 27 deletions(-) | ||
13 | |||
14 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/util/vhost-user-server.c | ||
17 | +++ b/util/vhost-user-server.c | ||
18 | @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) | ||
19 | }; | ||
20 | int rc, read_bytes = 0; | ||
21 | Error *local_err = NULL; | ||
22 | - /* | ||
23 | - * Store fds/nfds returned from qio_channel_readv_full into | ||
24 | - * temporary variables. | ||
25 | - * | ||
26 | - * VhostUserMsg is a packed structure, gcc will complain about passing | ||
27 | - * pointer to a packed structure member if we pass &VhostUserMsg.fd_num | ||
28 | - * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, | ||
29 | - * thus two temporary variables nfds and fds are used here. | ||
30 | - */ | ||
31 | - size_t nfds = 0, nfds_t = 0; | ||
32 | const size_t max_fds = G_N_ELEMENTS(vmsg->fds); | ||
33 | - int *fds_t = NULL; | ||
34 | VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
35 | QIOChannel *ioc = server->ioc; | ||
36 | |||
37 | + vmsg->fd_num = 0; | ||
38 | if (!ioc) { | ||
39 | error_report_err(local_err); | ||
40 | goto fail; | ||
41 | @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) | ||
42 | |||
43 | assert(qemu_in_coroutine()); | ||
44 | do { | ||
45 | + size_t nfds = 0; | ||
46 | + int *fds = NULL; | ||
47 | + | ||
48 | /* | ||
49 | * qio_channel_readv_full may have short reads, keeping calling it | ||
50 | * until getting VHOST_USER_HDR_SIZE or 0 bytes in total | ||
51 | */ | ||
52 | - rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); | ||
53 | + rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err); | ||
54 | if (rc < 0) { | ||
55 | if (rc == QIO_CHANNEL_ERR_BLOCK) { | ||
56 | + assert(local_err == NULL); | ||
57 | qio_channel_yield(ioc, G_IO_IN); | ||
58 | continue; | ||
59 | } else { | ||
60 | error_report_err(local_err); | ||
61 | - return false; | ||
62 | + goto fail; | ||
63 | } | ||
64 | } | ||
65 | - read_bytes += rc; | ||
66 | - if (nfds_t > 0) { | ||
67 | - if (nfds + nfds_t > max_fds) { | ||
68 | + | ||
69 | + if (nfds > 0) { | ||
70 | + if (vmsg->fd_num + nfds > max_fds) { | ||
71 | error_report("A maximum of %zu fds are allowed, " | ||
72 | "however got %zu fds now", | ||
73 | - max_fds, nfds + nfds_t); | ||
74 | + max_fds, vmsg->fd_num + nfds); | ||
75 | + g_free(fds); | ||
76 | goto fail; | ||
77 | } | ||
78 | - memcpy(vmsg->fds + nfds, fds_t, | ||
79 | - nfds_t *sizeof(vmsg->fds[0])); | ||
80 | - nfds += nfds_t; | ||
81 | - g_free(fds_t); | ||
82 | + memcpy(vmsg->fds + vmsg->fd_num, fds, nfds * sizeof(vmsg->fds[0])); | ||
83 | + vmsg->fd_num += nfds; | ||
84 | + g_free(fds); | ||
85 | } | ||
86 | - if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { | ||
87 | - break; | ||
88 | + | ||
89 | + if (rc == 0) { /* socket closed */ | ||
90 | + goto fail; | ||
91 | } | ||
92 | - iov.iov_base = (char *)vmsg + read_bytes; | ||
93 | - iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; | ||
94 | - } while (true); | ||
95 | |||
96 | - vmsg->fd_num = nfds; | ||
97 | + iov.iov_base += rc; | ||
98 | + iov.iov_len -= rc; | ||
99 | + read_bytes += rc; | ||
100 | + } while (read_bytes != VHOST_USER_HDR_SIZE); | ||
101 | + | ||
102 | /* qio_channel_readv_full will make socket fds blocking, unblock them */ | ||
103 | vmsg_unblock_fds(vmsg); | ||
104 | if (vmsg->size > sizeof(vmsg->payload)) { | ||
105 | -- | ||
106 | 2.26.2 | ||
107 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Unexpected EOF is an error that must be reported. | ||
1 | 2 | ||
3 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
4 | Message-id: 20200924151549.913737-9-stefanha@redhat.com | ||
5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | --- | ||
7 | util/vhost-user-server.c | 6 ++++-- | ||
8 | 1 file changed, 4 insertions(+), 2 deletions(-) | ||
9 | |||
10 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
11 | index XXXXXXX..XXXXXXX 100644 | ||
12 | --- a/util/vhost-user-server.c | ||
13 | +++ b/util/vhost-user-server.c | ||
14 | @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) | ||
15 | }; | ||
16 | if (vmsg->size) { | ||
17 | rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); | ||
18 | - if (rc == -1) { | ||
19 | - error_report_err(local_err); | ||
20 | + if (rc != 1) { | ||
21 | + if (local_err) { | ||
22 | + error_report_err(local_err); | ||
23 | + } | ||
24 | goto fail; | ||
25 | } | ||
26 | } | ||
27 | -- | ||
28 | 2.26.2 | ||
29 | diff view generated by jsdifflib |
1 | From: David Edmondson <david.edmondson@oracle.com> | 1 | The vu_client_trip() coroutine is leaked during AioContext switching. It |
---|---|---|---|
2 | is also unsafe to destroy the vu_dev in panic_cb() since its callers | ||
3 | still access it in some cases. | ||
2 | 4 | ||
3 | RFC 7230 section 3.2 indicates that whitespace is permitted between | 5 | Rework the lifecycle to solve these safety issues. |
4 | the field name and field value and after the field value. | ||
5 | 6 | ||
6 | Signed-off-by: David Edmondson <david.edmondson@oracle.com> | 7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
7 | Message-Id: <20200224101310.101169-2-david.edmondson@oracle.com> | 8 | Message-id: 20200924151549.913737-10-stefanha@redhat.com |
8 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 9 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
10 | --- | 10 | --- |
11 | block/curl.c | 31 +++++++++++++++++++++++++++---- | 11 | util/vhost-user-server.h | 29 ++-- |
12 | 1 file changed, 27 insertions(+), 4 deletions(-) | 12 | block/export/vhost-user-blk-server.c | 9 +- |
13 | util/vhost-user-server.c | 245 +++++++++++++++------------ | ||
14 | 3 files changed, 155 insertions(+), 128 deletions(-) | ||
13 | 15 | ||
14 | diff --git a/block/curl.c b/block/curl.c | 16 | diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h |
15 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/block/curl.c | 18 | --- a/util/vhost-user-server.h |
17 | +++ b/block/curl.c | 19 | +++ b/util/vhost-user-server.h |
18 | @@ -XXX,XX +XXX,XX @@ static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque) | 20 | @@ -XXX,XX +XXX,XX @@ |
19 | { | 21 | #include "qapi/error.h" |
20 | BDRVCURLState *s = opaque; | 22 | #include "standard-headers/linux/virtio_blk.h" |
21 | size_t realsize = size * nmemb; | 23 | |
22 | - const char *accept_line = "Accept-Ranges: bytes"; | 24 | +/* A kick fd that we monitor on behalf of libvhost-user */ |
23 | + const char *header = (char *)ptr; | 25 | typedef struct VuFdWatch { |
24 | + const char *end = header + realsize; | 26 | VuDev *vu_dev; |
25 | + const char *accept_ranges = "Accept-Ranges:"; | 27 | int fd; /*kick fd*/ |
26 | + const char *bytes = "bytes"; | 28 | void *pvt; |
27 | 29 | vu_watch_cb cb; | |
28 | - if (realsize >= strlen(accept_line) | 30 | - bool processing; |
29 | - && strncmp((char *)ptr, accept_line, strlen(accept_line)) == 0) { | 31 | QTAILQ_ENTRY(VuFdWatch) next; |
30 | - s->accept_range = true; | 32 | } VuFdWatch; |
31 | + if (realsize >= strlen(accept_ranges) | 33 | |
32 | + && strncmp(header, accept_ranges, strlen(accept_ranges)) == 0) { | 34 | -typedef struct VuServer VuServer; |
33 | + | 35 | - |
34 | + char *p = strchr(header, ':') + 1; | 36 | -struct VuServer { |
35 | + | 37 | +/** |
36 | + /* Skip whitespace between the header name and value. */ | 38 | + * VuServer: |
37 | + while (p < end && *p && g_ascii_isspace(*p)) { | 39 | + * A vhost-user server instance with user-defined VuDevIface callbacks. |
38 | + p++; | 40 | + * Vhost-user device backends can be implemented using VuServer. VuDevIface |
41 | + * callbacks and virtqueue kicks run in the given AioContext. | ||
42 | + */ | ||
43 | +typedef struct { | ||
44 | QIONetListener *listener; | ||
45 | + QEMUBH *restart_listener_bh; | ||
46 | AioContext *ctx; | ||
47 | int max_queues; | ||
48 | const VuDevIface *vu_iface; | ||
49 | + | ||
50 | + /* Protected by ctx lock */ | ||
51 | VuDev vu_dev; | ||
52 | QIOChannel *ioc; /* The I/O channel with the client */ | ||
53 | QIOChannelSocket *sioc; /* The underlying data channel with the client */ | ||
54 | - /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ | ||
55 | - QIOChannel *ioc_slave; | ||
56 | - QIOChannelSocket *sioc_slave; | ||
57 | - Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ | ||
58 | QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; | ||
59 | - /* restart coroutine co_trip if AIOContext is changed */ | ||
60 | - bool aio_context_changed; | ||
61 | - bool processing_msg; | ||
62 | -}; | ||
63 | + | ||
64 | + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ | ||
65 | +} VuServer; | ||
66 | |||
67 | bool vhost_user_server_start(VuServer *server, | ||
68 | SocketAddress *unix_socket, | ||
69 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, | ||
70 | |||
71 | void vhost_user_server_stop(VuServer *server); | ||
72 | |||
73 | -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); | ||
74 | +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx); | ||
75 | +void vhost_user_server_detach_aio_context(VuServer *server); | ||
76 | |||
77 | #endif /* VHOST_USER_SERVER_H */ | ||
78 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c | ||
79 | index XXXXXXX..XXXXXXX 100644 | ||
80 | --- a/block/export/vhost-user-blk-server.c | ||
81 | +++ b/block/export/vhost-user-blk-server.c | ||
82 | @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_block_iface = { | ||
83 | static void blk_aio_attached(AioContext *ctx, void *opaque) | ||
84 | { | ||
85 | VuBlockDev *vub_dev = opaque; | ||
86 | - aio_context_acquire(ctx); | ||
87 | - vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); | ||
88 | - aio_context_release(ctx); | ||
89 | + vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); | ||
90 | } | ||
91 | |||
92 | static void blk_aio_detach(void *opaque) | ||
93 | { | ||
94 | VuBlockDev *vub_dev = opaque; | ||
95 | - AioContext *ctx = vub_dev->vu_server.ctx; | ||
96 | - aio_context_acquire(ctx); | ||
97 | - vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); | ||
98 | - aio_context_release(ctx); | ||
99 | + vhost_user_server_detach_aio_context(&vub_dev->vu_server); | ||
100 | } | ||
101 | |||
102 | static void | ||
103 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
104 | index XXXXXXX..XXXXXXX 100644 | ||
105 | --- a/util/vhost-user-server.c | ||
106 | +++ b/util/vhost-user-server.c | ||
107 | @@ -XXX,XX +XXX,XX @@ | ||
108 | */ | ||
109 | #include "qemu/osdep.h" | ||
110 | #include "qemu/main-loop.h" | ||
111 | +#include "block/aio-wait.h" | ||
112 | #include "vhost-user-server.h" | ||
113 | |||
114 | +/* | ||
115 | + * Theory of operation: | ||
116 | + * | ||
117 | + * VuServer is started and stopped by vhost_user_server_start() and | ||
118 | + * vhost_user_server_stop() from the main loop thread. Starting the server | ||
119 | + * opens a vhost-user UNIX domain socket and listens for incoming connections. | ||
120 | + * Only one connection is allowed at a time. | ||
121 | + * | ||
122 | + * The connection is handled by the vu_client_trip() coroutine in the | ||
123 | + * VuServer->ctx AioContext. The coroutine consists of a vu_dispatch() loop | ||
124 | + * where libvhost-user calls vu_message_read() to receive the next vhost-user | ||
125 | + * protocol messages over the UNIX domain socket. | ||
126 | + * | ||
127 | + * When virtqueues are set up libvhost-user calls set_watch() to monitor kick | ||
128 | + * fds. These fds are also handled in the VuServer->ctx AioContext. | ||
129 | + * | ||
130 | + * Both vu_client_trip() and kick fd monitoring can be stopped by shutting down | ||
131 | + * the socket connection. Shutting down the socket connection causes | ||
132 | + * vu_message_read() to fail since no more data can be received from the socket. | ||
133 | + * After vu_dispatch() fails, vu_client_trip() calls vu_deinit() to stop | ||
134 | + * libvhost-user before terminating the coroutine. vu_deinit() calls | ||
135 | + * remove_watch() to stop monitoring kick fds and this stops virtqueue | ||
136 | + * processing. | ||
137 | + * | ||
138 | + * When vu_client_trip() has finished cleaning up it schedules a BH in the main | ||
139 | + * loop thread to accept the next client connection. | ||
140 | + * | ||
141 | + * When libvhost-user detects an error it calls panic_cb() and sets the | ||
142 | + * dev->broken flag. Both vu_client_trip() and kick fd processing stop when | ||
143 | + * the dev->broken flag is set. | ||
144 | + * | ||
145 | + * It is possible to switch AioContexts using | ||
146 | + * vhost_user_server_detach_aio_context() and | ||
147 | + * vhost_user_server_attach_aio_context(). They stop monitoring fds in the old | ||
148 | + * AioContext and resume monitoring in the new AioContext. The vu_client_trip() | ||
149 | + * coroutine remains in a yielded state during the switch. This is made | ||
150 | + * possible by QIOChannel's support for spurious coroutine re-entry in | ||
151 | + * qio_channel_yield(). The coroutine will restart I/O when re-entered from the | ||
152 | + * new AioContext. | ||
153 | + */ | ||
154 | + | ||
155 | static void vmsg_close_fds(VhostUserMsg *vmsg) | ||
156 | { | ||
157 | int i; | ||
158 | @@ -XXX,XX +XXX,XX @@ static void vmsg_unblock_fds(VhostUserMsg *vmsg) | ||
159 | } | ||
160 | } | ||
161 | |||
162 | -static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, | ||
163 | - gpointer opaque); | ||
164 | - | ||
165 | -static void close_client(VuServer *server) | ||
166 | -{ | ||
167 | - /* | ||
168 | - * Before closing the client | ||
169 | - * | ||
170 | - * 1. Let vu_client_trip stop processing new vhost-user msg | ||
171 | - * | ||
172 | - * 2. remove kick_handler | ||
173 | - * | ||
174 | - * 3. wait for the kick handler to be finished | ||
175 | - * | ||
176 | - * 4. wait for the current vhost-user msg to be finished processing | ||
177 | - */ | ||
178 | - | ||
179 | - QIOChannelSocket *sioc = server->sioc; | ||
180 | - /* When this is set vu_client_trip will stop new processing vhost-user message */ | ||
181 | - server->sioc = NULL; | ||
182 | - | ||
183 | - while (server->processing_msg) { | ||
184 | - if (server->ioc->read_coroutine) { | ||
185 | - server->ioc->read_coroutine = NULL; | ||
186 | - qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, | ||
187 | - NULL, server->ioc); | ||
188 | - server->processing_msg = false; | ||
189 | - } | ||
190 | - } | ||
191 | - | ||
192 | - vu_deinit(&server->vu_dev); | ||
193 | - | ||
194 | - /* vu_deinit() should have called remove_watch() */ | ||
195 | - assert(QTAILQ_EMPTY(&server->vu_fd_watches)); | ||
196 | - | ||
197 | - object_unref(OBJECT(sioc)); | ||
198 | - object_unref(OBJECT(server->ioc)); | ||
199 | -} | ||
200 | - | ||
201 | static void panic_cb(VuDev *vu_dev, const char *buf) | ||
202 | { | ||
203 | - VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
204 | - | ||
205 | - /* avoid while loop in close_client */ | ||
206 | - server->processing_msg = false; | ||
207 | - | ||
208 | - if (buf) { | ||
209 | - error_report("vu_panic: %s", buf); | ||
210 | - } | ||
211 | - | ||
212 | - if (server->sioc) { | ||
213 | - close_client(server); | ||
214 | - } | ||
215 | - | ||
216 | - /* | ||
217 | - * Set the callback function for network listener so another | ||
218 | - * vhost-user client can connect to this server | ||
219 | - */ | ||
220 | - qio_net_listener_set_client_func(server->listener, | ||
221 | - vu_accept, | ||
222 | - server, | ||
223 | - NULL); | ||
224 | + error_report("vu_panic: %s", buf); | ||
225 | } | ||
226 | |||
227 | static bool coroutine_fn | ||
228 | @@ -XXX,XX +XXX,XX @@ fail: | ||
229 | return false; | ||
230 | } | ||
231 | |||
232 | - | ||
233 | -static void vu_client_start(VuServer *server); | ||
234 | static coroutine_fn void vu_client_trip(void *opaque) | ||
235 | { | ||
236 | VuServer *server = opaque; | ||
237 | + VuDev *vu_dev = &server->vu_dev; | ||
238 | |||
239 | - while (!server->aio_context_changed && server->sioc) { | ||
240 | - server->processing_msg = true; | ||
241 | - vu_dispatch(&server->vu_dev); | ||
242 | - server->processing_msg = false; | ||
243 | + while (!vu_dev->broken && vu_dispatch(vu_dev)) { | ||
244 | + /* Keep running */ | ||
245 | } | ||
246 | |||
247 | - if (server->aio_context_changed && server->sioc) { | ||
248 | - server->aio_context_changed = false; | ||
249 | - vu_client_start(server); | ||
250 | - } | ||
251 | -} | ||
252 | + vu_deinit(vu_dev); | ||
253 | + | ||
254 | + /* vu_deinit() should have called remove_watch() */ | ||
255 | + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); | ||
256 | + | ||
257 | + object_unref(OBJECT(server->sioc)); | ||
258 | + server->sioc = NULL; | ||
259 | |||
260 | -static void vu_client_start(VuServer *server) | ||
261 | -{ | ||
262 | - server->co_trip = qemu_coroutine_create(vu_client_trip, server); | ||
263 | - aio_co_enter(server->ctx, server->co_trip); | ||
264 | + object_unref(OBJECT(server->ioc)); | ||
265 | + server->ioc = NULL; | ||
266 | + | ||
267 | + server->co_trip = NULL; | ||
268 | + if (server->restart_listener_bh) { | ||
269 | + qemu_bh_schedule(server->restart_listener_bh); | ||
270 | + } | ||
271 | + aio_wait_kick(); | ||
272 | } | ||
273 | |||
274 | /* | ||
275 | @@ -XXX,XX +XXX,XX @@ static void vu_client_start(VuServer *server) | ||
276 | static void kick_handler(void *opaque) | ||
277 | { | ||
278 | VuFdWatch *vu_fd_watch = opaque; | ||
279 | - vu_fd_watch->processing = true; | ||
280 | - vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); | ||
281 | - vu_fd_watch->processing = false; | ||
282 | + VuDev *vu_dev = vu_fd_watch->vu_dev; | ||
283 | + | ||
284 | + vu_fd_watch->cb(vu_dev, 0, vu_fd_watch->pvt); | ||
285 | + | ||
286 | + /* Stop vu_client_trip() if an error occurred in vu_fd_watch->cb() */ | ||
287 | + if (vu_dev->broken) { | ||
288 | + VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
289 | + | ||
290 | + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); | ||
291 | + } | ||
292 | } | ||
293 | |||
294 | - | ||
295 | static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) | ||
296 | { | ||
297 | |||
298 | @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, | ||
299 | qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); | ||
300 | server->ioc = QIO_CHANNEL(sioc); | ||
301 | object_ref(OBJECT(server->ioc)); | ||
302 | - qio_channel_attach_aio_context(server->ioc, server->ctx); | ||
303 | + | ||
304 | + /* TODO vu_message_write() spins if non-blocking! */ | ||
305 | qio_channel_set_blocking(server->ioc, false, NULL); | ||
306 | - vu_client_start(server); | ||
307 | + | ||
308 | + server->co_trip = qemu_coroutine_create(vu_client_trip, server); | ||
309 | + | ||
310 | + aio_context_acquire(server->ctx); | ||
311 | + vhost_user_server_attach_aio_context(server, server->ctx); | ||
312 | + aio_context_release(server->ctx); | ||
313 | } | ||
314 | |||
315 | - | ||
316 | void vhost_user_server_stop(VuServer *server) | ||
317 | { | ||
318 | + aio_context_acquire(server->ctx); | ||
319 | + | ||
320 | + qemu_bh_delete(server->restart_listener_bh); | ||
321 | + server->restart_listener_bh = NULL; | ||
322 | + | ||
323 | if (server->sioc) { | ||
324 | - close_client(server); | ||
325 | + VuFdWatch *vu_fd_watch; | ||
326 | + | ||
327 | + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { | ||
328 | + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, | ||
329 | + NULL, NULL, NULL, vu_fd_watch); | ||
39 | + } | 330 | + } |
40 | + | 331 | + |
41 | + if (end - p >= strlen(bytes) | 332 | + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); |
42 | + && strncmp(p, bytes, strlen(bytes)) == 0) { | 333 | + |
43 | + | 334 | + AIO_WAIT_WHILE(server->ctx, server->co_trip); |
44 | + /* Check that there is nothing but whitespace after the value. */ | 335 | } |
45 | + p += strlen(bytes); | 336 | |
46 | + while (p < end && *p && g_ascii_isspace(*p)) { | 337 | + aio_context_release(server->ctx); |
47 | + p++; | 338 | + |
48 | + } | 339 | if (server->listener) { |
49 | + | 340 | qio_net_listener_disconnect(server->listener); |
50 | + if (p == end || !*p) { | 341 | object_unref(OBJECT(server->listener)); |
51 | + s->accept_range = true; | 342 | } |
52 | + } | 343 | +} |
344 | + | ||
345 | +/* | ||
346 | + * Allow the next client to connect to the server. Called from a BH in the main | ||
347 | + * loop. | ||
348 | + */ | ||
349 | +static void restart_listener_bh(void *opaque) | ||
350 | +{ | ||
351 | + VuServer *server = opaque; | ||
352 | |||
353 | + qio_net_listener_set_client_func(server->listener, vu_accept, server, | ||
354 | + NULL); | ||
355 | } | ||
356 | |||
357 | -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) | ||
358 | +/* Called with ctx acquired */ | ||
359 | +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx) | ||
360 | { | ||
361 | - VuFdWatch *vu_fd_watch, *next; | ||
362 | - void *opaque = NULL; | ||
363 | - IOHandler *io_read = NULL; | ||
364 | - bool attach; | ||
365 | + VuFdWatch *vu_fd_watch; | ||
366 | |||
367 | - server->ctx = ctx ? ctx : qemu_get_aio_context(); | ||
368 | + server->ctx = ctx; | ||
369 | |||
370 | if (!server->sioc) { | ||
371 | - /* not yet serving any client*/ | ||
372 | return; | ||
373 | } | ||
374 | |||
375 | - if (ctx) { | ||
376 | - qio_channel_attach_aio_context(server->ioc, ctx); | ||
377 | - server->aio_context_changed = true; | ||
378 | - io_read = kick_handler; | ||
379 | - attach = true; | ||
380 | - } else { | ||
381 | + qio_channel_attach_aio_context(server->ioc, ctx); | ||
382 | + | ||
383 | + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { | ||
384 | + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, kick_handler, NULL, | ||
385 | + NULL, vu_fd_watch); | ||
386 | + } | ||
387 | + | ||
388 | + aio_co_schedule(ctx, server->co_trip); | ||
389 | +} | ||
390 | + | ||
391 | +/* Called with server->ctx acquired */ | ||
392 | +void vhost_user_server_detach_aio_context(VuServer *server) | ||
393 | +{ | ||
394 | + if (server->sioc) { | ||
395 | + VuFdWatch *vu_fd_watch; | ||
396 | + | ||
397 | + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { | ||
398 | + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, | ||
399 | + NULL, NULL, NULL, vu_fd_watch); | ||
53 | + } | 400 | + } |
54 | } | 401 | + |
55 | 402 | qio_channel_detach_aio_context(server->ioc); | |
56 | return realsize; | 403 | - /* server->ioc->ctx keeps the old AioConext */ |
404 | - ctx = server->ioc->ctx; | ||
405 | - attach = false; | ||
406 | } | ||
407 | |||
408 | - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { | ||
409 | - if (vu_fd_watch->cb) { | ||
410 | - opaque = attach ? vu_fd_watch : NULL; | ||
411 | - aio_set_fd_handler(ctx, vu_fd_watch->fd, true, | ||
412 | - io_read, NULL, NULL, | ||
413 | - opaque); | ||
414 | - } | ||
415 | - } | ||
416 | + server->ctx = NULL; | ||
417 | } | ||
418 | |||
419 | - | ||
420 | bool vhost_user_server_start(VuServer *server, | ||
421 | SocketAddress *socket_addr, | ||
422 | AioContext *ctx, | ||
423 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, | ||
424 | const VuDevIface *vu_iface, | ||
425 | Error **errp) | ||
426 | { | ||
427 | + QEMUBH *bh; | ||
428 | QIONetListener *listener = qio_net_listener_new(); | ||
429 | if (qio_net_listener_open_sync(listener, socket_addr, 1, | ||
430 | errp) < 0) { | ||
431 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, | ||
432 | return false; | ||
433 | } | ||
434 | |||
435 | + bh = qemu_bh_new(restart_listener_bh, server); | ||
436 | + | ||
437 | /* zero out unspecified fields */ | ||
438 | *server = (VuServer) { | ||
439 | .listener = listener, | ||
440 | + .restart_listener_bh = bh, | ||
441 | .vu_iface = vu_iface, | ||
442 | .max_queues = max_queues, | ||
443 | .ctx = ctx, | ||
57 | -- | 444 | -- |
58 | 2.24.1 | 445 | 2.26.2 |
59 | 446 | ||
60 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Propagate the flush return value since errors are possible. | ||
1 | 2 | ||
3 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
4 | Message-id: 20200924151549.913737-11-stefanha@redhat.com | ||
5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | --- | ||
7 | block/export/vhost-user-blk-server.c | 11 +++++++---- | ||
8 | 1 file changed, 7 insertions(+), 4 deletions(-) | ||
9 | |||
10 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c | ||
11 | index XXXXXXX..XXXXXXX 100644 | ||
12 | --- a/block/export/vhost-user-blk-server.c | ||
13 | +++ b/block/export/vhost-user-blk-server.c | ||
14 | @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, | ||
15 | return -EINVAL; | ||
16 | } | ||
17 | |||
18 | -static void coroutine_fn vu_block_flush(VuBlockReq *req) | ||
19 | +static int coroutine_fn vu_block_flush(VuBlockReq *req) | ||
20 | { | ||
21 | VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); | ||
22 | BlockBackend *backend = vdev_blk->backend; | ||
23 | - blk_co_flush(backend); | ||
24 | + return blk_co_flush(backend); | ||
25 | } | ||
26 | |||
27 | static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
28 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
29 | break; | ||
30 | } | ||
31 | case VIRTIO_BLK_T_FLUSH: | ||
32 | - vu_block_flush(req); | ||
33 | - req->in->status = VIRTIO_BLK_S_OK; | ||
34 | + if (vu_block_flush(req) == 0) { | ||
35 | + req->in->status = VIRTIO_BLK_S_OK; | ||
36 | + } else { | ||
37 | + req->in->status = VIRTIO_BLK_S_IOERR; | ||
38 | + } | ||
39 | break; | ||
40 | case VIRTIO_BLK_T_GET_ID: { | ||
41 | size_t size = MIN(iov_size(&elem->in_sg[0], in_num), | ||
42 | -- | ||
43 | 2.26.2 | ||
44 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | Use the new QAPI block exports API instead of defining our own QOM |
---|---|---|---|
2 | 2 | objects. | |
3 | offset/bytes pair is more usual naming in block layer, let's use it. | 3 | |
4 | 4 | This is a large change because the lifecycle of VuBlockDev needs to | |
5 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 5 | follow BlockExportDriver. QOM properties are replaced by QAPI options |
6 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 6 | objects. |
7 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 7 | |
8 | Message-Id: <20200311103004.7649-8-vsementsov@virtuozzo.com> | 8 | VuBlockDev is renamed VuBlkExport and contains a BlockExport field. |
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 9 | Several fields can be dropped since BlockExport already has equivalents. |
10 | |||
11 | The file names and meson build integration will be adjusted in a future | ||
12 | patch. libvhost-user should probably be built as a static library that | ||
13 | is linked into QEMU instead of as a .c file that results in duplicate | ||
14 | compilation. | ||
15 | |||
16 | The new command-line syntax is: | ||
17 | |||
18 | $ qemu-storage-daemon \ | ||
19 | --blockdev file,node-name=drive0,filename=test.img \ | ||
20 | --export vhost-user-blk,node-name=drive0,id=export0,unix-socket=/tmp/vhost-user-blk.sock | ||
21 | |||
22 | Note that unix-socket is optional because we may wish to accept chardevs | ||
23 | too in the future. | ||
24 | |||
25 | Markus noted that supported address families are not explicit in the | ||
26 | QAPI schema. It is unlikely that support for more address families will | ||
27 | be added since file descriptor passing is required and few address | ||
28 | families support it. If a new address family needs to be added, then the | ||
29 | QAPI 'features' syntax can be used to advertize them. | ||
30 | |||
31 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
32 | Acked-by: Markus Armbruster <armbru@redhat.com> | ||
33 | Message-id: 20200924151549.913737-12-stefanha@redhat.com | ||
34 | [Skip test on big-endian host architectures because this device doesn't | ||
35 | support them yet (as already mentioned in a code comment). | ||
36 | --Stefan] | ||
37 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | --- | 38 | --- |
11 | block/block-copy.c | 82 +++++++++++++++++++------------------- | 39 | qapi/block-export.json | 21 +- |
12 | include/block/block-copy.h | 4 +- | 40 | block/export/vhost-user-blk-server.h | 23 +- |
13 | 2 files changed, 43 insertions(+), 43 deletions(-) | 41 | block/export/export.c | 6 + |
14 | 42 | block/export/vhost-user-blk-server.c | 452 +++++++-------------------- | |
15 | diff --git a/block/block-copy.c b/block/block-copy.c | 43 | util/vhost-user-server.c | 10 +- |
44 | block/export/meson.build | 1 + | ||
45 | block/meson.build | 1 - | ||
46 | 7 files changed, 156 insertions(+), 358 deletions(-) | ||
47 | |||
48 | diff --git a/qapi/block-export.json b/qapi/block-export.json | ||
16 | index XXXXXXX..XXXXXXX 100644 | 49 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/block/block-copy.c | 50 | --- a/qapi/block-export.json |
18 | +++ b/block/block-copy.c | 51 | +++ b/qapi/block-export.json |
19 | @@ -XXX,XX +XXX,XX @@ | 52 | @@ -XXX,XX +XXX,XX @@ |
20 | #define BLOCK_COPY_MAX_MEM (128 * MiB) | 53 | 'data': { '*name': 'str', '*description': 'str', |
21 | 54 | '*bitmap': 'str' } } | |
22 | static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s, | 55 | |
23 | - int64_t start, | 56 | +## |
24 | + int64_t offset, | 57 | +# @BlockExportOptionsVhostUserBlk: |
25 | int64_t bytes) | 58 | +# |
26 | { | 59 | +# A vhost-user-blk block export. |
27 | BlockCopyInFlightReq *req; | 60 | +# |
28 | 61 | +# @addr: The vhost-user socket on which to listen. Both 'unix' and 'fd' | |
29 | QLIST_FOREACH(req, &s->inflight_reqs, list) { | 62 | +# SocketAddress types are supported. Passed fds must be UNIX domain |
30 | - if (start + bytes > req->start && start < req->start + req->bytes) { | 63 | +# sockets. |
31 | + if (offset + bytes > req->offset && offset < req->offset + req->bytes) { | 64 | +# @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. |
32 | return req; | 65 | +# |
66 | +# Since: 5.2 | ||
67 | +## | ||
68 | +{ 'struct': 'BlockExportOptionsVhostUserBlk', | ||
69 | + 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } | ||
70 | + | ||
71 | ## | ||
72 | # @NbdServerAddOptions: | ||
73 | # | ||
74 | @@ -XXX,XX +XXX,XX @@ | ||
75 | # An enumeration of block export types | ||
76 | # | ||
77 | # @nbd: NBD export | ||
78 | +# @vhost-user-blk: vhost-user-blk export (since 5.2) | ||
79 | # | ||
80 | # Since: 4.2 | ||
81 | ## | ||
82 | { 'enum': 'BlockExportType', | ||
83 | - 'data': [ 'nbd' ] } | ||
84 | + 'data': [ 'nbd', 'vhost-user-blk' ] } | ||
85 | |||
86 | ## | ||
87 | # @BlockExportOptions: | ||
88 | @@ -XXX,XX +XXX,XX @@ | ||
89 | '*writethrough': 'bool' }, | ||
90 | 'discriminator': 'type', | ||
91 | 'data': { | ||
92 | - 'nbd': 'BlockExportOptionsNbd' | ||
93 | + 'nbd': 'BlockExportOptionsNbd', | ||
94 | + 'vhost-user-blk': 'BlockExportOptionsVhostUserBlk' | ||
95 | } } | ||
96 | |||
97 | ## | ||
98 | diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h | ||
99 | index XXXXXXX..XXXXXXX 100644 | ||
100 | --- a/block/export/vhost-user-blk-server.h | ||
101 | +++ b/block/export/vhost-user-blk-server.h | ||
102 | @@ -XXX,XX +XXX,XX @@ | ||
103 | |||
104 | #ifndef VHOST_USER_BLK_SERVER_H | ||
105 | #define VHOST_USER_BLK_SERVER_H | ||
106 | -#include "util/vhost-user-server.h" | ||
107 | |||
108 | -typedef struct VuBlockDev VuBlockDev; | ||
109 | -#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" | ||
110 | -#define VHOST_USER_BLK_SERVER(obj) \ | ||
111 | - OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) | ||
112 | +#include "block/export.h" | ||
113 | |||
114 | -/* vhost user block device */ | ||
115 | -struct VuBlockDev { | ||
116 | - Object parent_obj; | ||
117 | - char *node_name; | ||
118 | - SocketAddress *addr; | ||
119 | - AioContext *ctx; | ||
120 | - VuServer vu_server; | ||
121 | - bool running; | ||
122 | - uint32_t blk_size; | ||
123 | - BlockBackend *backend; | ||
124 | - QIOChannelSocket *sioc; | ||
125 | - QTAILQ_ENTRY(VuBlockDev) next; | ||
126 | - struct virtio_blk_config blkcfg; | ||
127 | - bool writable; | ||
128 | -}; | ||
129 | +/* For block/export/export.c */ | ||
130 | +extern const BlockExportDriver blk_exp_vhost_user_blk; | ||
131 | |||
132 | #endif /* VHOST_USER_BLK_SERVER_H */ | ||
133 | diff --git a/block/export/export.c b/block/export/export.c | ||
134 | index XXXXXXX..XXXXXXX 100644 | ||
135 | --- a/block/export/export.c | ||
136 | +++ b/block/export/export.c | ||
137 | @@ -XXX,XX +XXX,XX @@ | ||
138 | #include "sysemu/block-backend.h" | ||
139 | #include "block/export.h" | ||
140 | #include "block/nbd.h" | ||
141 | +#if CONFIG_LINUX | ||
142 | +#include "block/export/vhost-user-blk-server.h" | ||
143 | +#endif | ||
144 | #include "qapi/error.h" | ||
145 | #include "qapi/qapi-commands-block-export.h" | ||
146 | #include "qapi/qapi-events-block-export.h" | ||
147 | @@ -XXX,XX +XXX,XX @@ | ||
148 | |||
149 | static const BlockExportDriver *blk_exp_drivers[] = { | ||
150 | &blk_exp_nbd, | ||
151 | +#if CONFIG_LINUX | ||
152 | + &blk_exp_vhost_user_blk, | ||
153 | +#endif | ||
154 | }; | ||
155 | |||
156 | /* Only accessed from the main thread */ | ||
157 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c | ||
158 | index XXXXXXX..XXXXXXX 100644 | ||
159 | --- a/block/export/vhost-user-blk-server.c | ||
160 | +++ b/block/export/vhost-user-blk-server.c | ||
161 | @@ -XXX,XX +XXX,XX @@ | ||
162 | */ | ||
163 | #include "qemu/osdep.h" | ||
164 | #include "block/block.h" | ||
165 | +#include "contrib/libvhost-user/libvhost-user.h" | ||
166 | +#include "standard-headers/linux/virtio_blk.h" | ||
167 | +#include "util/vhost-user-server.h" | ||
168 | #include "vhost-user-blk-server.h" | ||
169 | #include "qapi/error.h" | ||
170 | #include "qom/object_interfaces.h" | ||
171 | @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { | ||
172 | unsigned char status; | ||
173 | }; | ||
174 | |||
175 | -typedef struct VuBlockReq { | ||
176 | +typedef struct VuBlkReq { | ||
177 | VuVirtqElement elem; | ||
178 | int64_t sector_num; | ||
179 | size_t size; | ||
180 | @@ -XXX,XX +XXX,XX @@ typedef struct VuBlockReq { | ||
181 | struct virtio_blk_outhdr out; | ||
182 | VuServer *server; | ||
183 | struct VuVirtq *vq; | ||
184 | -} VuBlockReq; | ||
185 | +} VuBlkReq; | ||
186 | |||
187 | -static void vu_block_req_complete(VuBlockReq *req) | ||
188 | +/* vhost user block device */ | ||
189 | +typedef struct { | ||
190 | + BlockExport export; | ||
191 | + VuServer vu_server; | ||
192 | + uint32_t blk_size; | ||
193 | + QIOChannelSocket *sioc; | ||
194 | + struct virtio_blk_config blkcfg; | ||
195 | + bool writable; | ||
196 | +} VuBlkExport; | ||
197 | + | ||
198 | +static void vu_blk_req_complete(VuBlkReq *req) | ||
199 | { | ||
200 | VuDev *vu_dev = &req->server->vu_dev; | ||
201 | |||
202 | @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) | ||
203 | free(req); | ||
204 | } | ||
205 | |||
206 | -static VuBlockDev *get_vu_block_device_by_server(VuServer *server) | ||
207 | -{ | ||
208 | - return container_of(server, VuBlockDev, vu_server); | ||
209 | -} | ||
210 | - | ||
211 | static int coroutine_fn | ||
212 | -vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, | ||
213 | - uint32_t iovcnt, uint32_t type) | ||
214 | +vu_blk_discard_write_zeroes(BlockBackend *blk, struct iovec *iov, | ||
215 | + uint32_t iovcnt, uint32_t type) | ||
216 | { | ||
217 | struct virtio_blk_discard_write_zeroes desc; | ||
218 | ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); | ||
219 | @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, | ||
220 | return -EINVAL; | ||
221 | } | ||
222 | |||
223 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); | ||
224 | uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, | ||
225 | le32_to_cpu(desc.num_sectors) << 9 }; | ||
226 | if (type == VIRTIO_BLK_T_DISCARD) { | ||
227 | - if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { | ||
228 | + if (blk_co_pdiscard(blk, range[0], range[1]) == 0) { | ||
229 | return 0; | ||
230 | } | ||
231 | } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { | ||
232 | - if (blk_co_pwrite_zeroes(vdev_blk->backend, | ||
233 | - range[0], range[1], 0) == 0) { | ||
234 | + if (blk_co_pwrite_zeroes(blk, range[0], range[1], 0) == 0) { | ||
235 | return 0; | ||
33 | } | 236 | } |
34 | } | 237 | } |
35 | @@ -XXX,XX +XXX,XX @@ static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s, | 238 | @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, |
36 | } | 239 | return -EINVAL; |
37 | 240 | } | |
38 | static void coroutine_fn block_copy_wait_inflight_reqs(BlockCopyState *s, | 241 | |
39 | - int64_t start, | 242 | -static int coroutine_fn vu_block_flush(VuBlockReq *req) |
40 | + int64_t offset, | 243 | +static void coroutine_fn vu_blk_virtio_process_req(void *opaque) |
41 | int64_t bytes) | 244 | { |
42 | { | 245 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); |
43 | BlockCopyInFlightReq *req; | 246 | - BlockBackend *backend = vdev_blk->backend; |
44 | 247 | - return blk_co_flush(backend); | |
45 | - while ((req = find_conflicting_inflight_req(s, start, bytes))) { | 248 | -} |
46 | + while ((req = find_conflicting_inflight_req(s, offset, bytes))) { | 249 | - |
47 | qemu_co_queue_wait(&req->wait_queue, NULL); | 250 | -static void coroutine_fn vu_block_virtio_process_req(void *opaque) |
251 | -{ | ||
252 | - VuBlockReq *req = opaque; | ||
253 | + VuBlkReq *req = opaque; | ||
254 | VuServer *server = req->server; | ||
255 | VuVirtqElement *elem = &req->elem; | ||
256 | uint32_t type; | ||
257 | |||
258 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
259 | - BlockBackend *backend = vdev_blk->backend; | ||
260 | + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); | ||
261 | + BlockBackend *blk = vexp->export.blk; | ||
262 | |||
263 | struct iovec *in_iov = elem->in_sg; | ||
264 | struct iovec *out_iov = elem->out_sg; | ||
265 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
266 | bool is_write = type & VIRTIO_BLK_T_OUT; | ||
267 | req->sector_num = le64_to_cpu(req->out.sector); | ||
268 | |||
269 | - int64_t offset = req->sector_num * vdev_blk->blk_size; | ||
270 | + if (is_write && !vexp->writable) { | ||
271 | + req->in->status = VIRTIO_BLK_S_IOERR; | ||
272 | + break; | ||
273 | + } | ||
274 | + | ||
275 | + int64_t offset = req->sector_num * vexp->blk_size; | ||
276 | QEMUIOVector qiov; | ||
277 | if (is_write) { | ||
278 | qemu_iovec_init_external(&qiov, out_iov, out_num); | ||
279 | - ret = blk_co_pwritev(backend, offset, qiov.size, | ||
280 | - &qiov, 0); | ||
281 | + ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0); | ||
282 | } else { | ||
283 | qemu_iovec_init_external(&qiov, in_iov, in_num); | ||
284 | - ret = blk_co_preadv(backend, offset, qiov.size, | ||
285 | - &qiov, 0); | ||
286 | + ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0); | ||
287 | } | ||
288 | if (ret >= 0) { | ||
289 | req->in->status = VIRTIO_BLK_S_OK; | ||
290 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
291 | break; | ||
48 | } | 292 | } |
49 | } | 293 | case VIRTIO_BLK_T_FLUSH: |
50 | 294 | - if (vu_block_flush(req) == 0) { | |
51 | static void block_copy_inflight_req_begin(BlockCopyState *s, | 295 | + if (blk_co_flush(blk) == 0) { |
52 | BlockCopyInFlightReq *req, | 296 | req->in->status = VIRTIO_BLK_S_OK; |
53 | - int64_t start, int64_t bytes) | 297 | } else { |
54 | + int64_t offset, int64_t bytes) | 298 | req->in->status = VIRTIO_BLK_S_IOERR; |
55 | { | 299 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) |
56 | - req->start = start; | 300 | case VIRTIO_BLK_T_DISCARD: |
57 | + req->offset = offset; | 301 | case VIRTIO_BLK_T_WRITE_ZEROES: { |
58 | req->bytes = bytes; | 302 | int rc; |
59 | qemu_co_queue_init(&req->wait_queue); | 303 | - rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], |
60 | QLIST_INSERT_HEAD(&s->inflight_reqs, req, list); | 304 | - out_num, type); |
61 | @@ -XXX,XX +XXX,XX @@ void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm) | 305 | + |
62 | * Returns 0 on success. | 306 | + if (!vexp->writable) { |
63 | */ | 307 | + req->in->status = VIRTIO_BLK_S_IOERR; |
64 | static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | 308 | + break; |
65 | - int64_t start, int64_t bytes, | 309 | + } |
66 | + int64_t offset, int64_t bytes, | 310 | + |
67 | bool zeroes, bool *error_is_read) | 311 | + rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type); |
68 | { | 312 | if (rc == 0) { |
69 | int ret; | 313 | req->in->status = VIRTIO_BLK_S_OK; |
70 | - int64_t nbytes = MIN(start + bytes, s->len) - start; | 314 | } else { |
71 | + int64_t nbytes = MIN(offset + bytes, s->len) - offset; | 315 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) |
72 | void *bounce_buffer = NULL; | 316 | break; |
73 | |||
74 | - assert(start >= 0 && bytes > 0 && INT64_MAX - start >= bytes); | ||
75 | - assert(QEMU_IS_ALIGNED(start, s->cluster_size)); | ||
76 | + assert(offset >= 0 && bytes > 0 && INT64_MAX - offset >= bytes); | ||
77 | + assert(QEMU_IS_ALIGNED(offset, s->cluster_size)); | ||
78 | assert(QEMU_IS_ALIGNED(bytes, s->cluster_size)); | ||
79 | - assert(start < s->len); | ||
80 | - assert(start + bytes <= s->len || | ||
81 | - start + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size)); | ||
82 | + assert(offset < s->len); | ||
83 | + assert(offset + bytes <= s->len || | ||
84 | + offset + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size)); | ||
85 | assert(nbytes < INT_MAX); | ||
86 | |||
87 | if (zeroes) { | ||
88 | - ret = bdrv_co_pwrite_zeroes(s->target, start, nbytes, s->write_flags & | ||
89 | + ret = bdrv_co_pwrite_zeroes(s->target, offset, nbytes, s->write_flags & | ||
90 | ~BDRV_REQ_WRITE_COMPRESSED); | ||
91 | if (ret < 0) { | ||
92 | - trace_block_copy_write_zeroes_fail(s, start, ret); | ||
93 | + trace_block_copy_write_zeroes_fail(s, offset, ret); | ||
94 | if (error_is_read) { | ||
95 | *error_is_read = false; | ||
96 | } | ||
97 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | ||
98 | } | 317 | } |
99 | 318 | ||
100 | if (s->use_copy_range) { | 319 | - vu_block_req_complete(req); |
101 | - ret = bdrv_co_copy_range(s->source, start, s->target, start, nbytes, | 320 | + vu_blk_req_complete(req); |
102 | + ret = bdrv_co_copy_range(s->source, offset, s->target, offset, nbytes, | 321 | return; |
103 | 0, s->write_flags); | 322 | |
104 | if (ret < 0) { | 323 | err: |
105 | - trace_block_copy_copy_range_fail(s, start, ret); | 324 | - free(elem); |
106 | + trace_block_copy_copy_range_fail(s, offset, ret); | 325 | + free(req); |
107 | s->use_copy_range = false; | 326 | } |
108 | s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); | 327 | |
109 | /* Fallback to read+write with allocated buffer */ | 328 | -static void vu_block_process_vq(VuDev *vu_dev, int idx) |
110 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | 329 | +static void vu_blk_process_vq(VuDev *vu_dev, int idx) |
111 | 330 | { | |
112 | bounce_buffer = qemu_blockalign(s->source->bs, nbytes); | 331 | VuServer *server = container_of(vu_dev, VuServer, vu_dev); |
113 | 332 | VuVirtq *vq = vu_get_queue(vu_dev, idx); | |
114 | - ret = bdrv_co_pread(s->source, start, nbytes, bounce_buffer, 0); | 333 | |
115 | + ret = bdrv_co_pread(s->source, offset, nbytes, bounce_buffer, 0); | 334 | while (1) { |
116 | if (ret < 0) { | 335 | - VuBlockReq *req; |
117 | - trace_block_copy_read_fail(s, start, ret); | 336 | + VuBlkReq *req; |
118 | + trace_block_copy_read_fail(s, offset, ret); | 337 | |
119 | if (error_is_read) { | 338 | - req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); |
120 | *error_is_read = true; | 339 | + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlkReq)); |
121 | } | 340 | if (!req) { |
122 | goto out; | ||
123 | } | ||
124 | |||
125 | - ret = bdrv_co_pwrite(s->target, start, nbytes, bounce_buffer, | ||
126 | + ret = bdrv_co_pwrite(s->target, offset, nbytes, bounce_buffer, | ||
127 | s->write_flags); | ||
128 | if (ret < 0) { | ||
129 | - trace_block_copy_write_fail(s, start, ret); | ||
130 | + trace_block_copy_write_fail(s, offset, ret); | ||
131 | if (error_is_read) { | ||
132 | *error_is_read = false; | ||
133 | } | ||
134 | @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, | ||
135 | } | ||
136 | |||
137 | int coroutine_fn block_copy(BlockCopyState *s, | ||
138 | - int64_t start, int64_t bytes, | ||
139 | + int64_t offset, int64_t bytes, | ||
140 | bool *error_is_read) | ||
141 | { | ||
142 | int ret = 0; | ||
143 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
144 | assert(bdrv_get_aio_context(s->source->bs) == | ||
145 | bdrv_get_aio_context(s->target->bs)); | ||
146 | |||
147 | - assert(QEMU_IS_ALIGNED(start, s->cluster_size)); | ||
148 | + assert(QEMU_IS_ALIGNED(offset, s->cluster_size)); | ||
149 | assert(QEMU_IS_ALIGNED(bytes, s->cluster_size)); | ||
150 | |||
151 | - block_copy_wait_inflight_reqs(s, start, bytes); | ||
152 | - block_copy_inflight_req_begin(s, &req, start, bytes); | ||
153 | + block_copy_wait_inflight_reqs(s, offset, bytes); | ||
154 | + block_copy_inflight_req_begin(s, &req, offset, bytes); | ||
155 | |||
156 | while (bytes) { | ||
157 | int64_t next_zero, cur_bytes, status_bytes; | ||
158 | |||
159 | - if (!bdrv_dirty_bitmap_get(s->copy_bitmap, start)) { | ||
160 | - trace_block_copy_skip(s, start); | ||
161 | - start += s->cluster_size; | ||
162 | + if (!bdrv_dirty_bitmap_get(s->copy_bitmap, offset)) { | ||
163 | + trace_block_copy_skip(s, offset); | ||
164 | + offset += s->cluster_size; | ||
165 | bytes -= s->cluster_size; | ||
166 | continue; /* already copied */ | ||
167 | } | ||
168 | |||
169 | cur_bytes = MIN(bytes, s->copy_size); | ||
170 | |||
171 | - next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, start, | ||
172 | + next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, offset, | ||
173 | cur_bytes); | ||
174 | if (next_zero >= 0) { | ||
175 | - assert(next_zero > start); /* start is dirty */ | ||
176 | - assert(next_zero < start + cur_bytes); /* no need to do MIN() */ | ||
177 | - cur_bytes = next_zero - start; | ||
178 | + assert(next_zero > offset); /* offset is dirty */ | ||
179 | + assert(next_zero < offset + cur_bytes); /* no need to do MIN() */ | ||
180 | + cur_bytes = next_zero - offset; | ||
181 | } | ||
182 | |||
183 | - ret = block_copy_block_status(s, start, cur_bytes, &status_bytes); | ||
184 | + ret = block_copy_block_status(s, offset, cur_bytes, &status_bytes); | ||
185 | if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) { | ||
186 | - bdrv_reset_dirty_bitmap(s->copy_bitmap, start, status_bytes); | ||
187 | + bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, status_bytes); | ||
188 | progress_set_remaining(s->progress, | ||
189 | bdrv_get_dirty_count(s->copy_bitmap) + | ||
190 | s->in_flight_bytes); | ||
191 | - trace_block_copy_skip_range(s, start, status_bytes); | ||
192 | - start += status_bytes; | ||
193 | + trace_block_copy_skip_range(s, offset, status_bytes); | ||
194 | + offset += status_bytes; | ||
195 | bytes -= status_bytes; | ||
196 | continue; | ||
197 | } | ||
198 | |||
199 | cur_bytes = MIN(cur_bytes, status_bytes); | ||
200 | |||
201 | - trace_block_copy_process(s, start); | ||
202 | + trace_block_copy_process(s, offset); | ||
203 | |||
204 | - bdrv_reset_dirty_bitmap(s->copy_bitmap, start, cur_bytes); | ||
205 | + bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, cur_bytes); | ||
206 | s->in_flight_bytes += cur_bytes; | ||
207 | |||
208 | co_get_from_shres(s->mem, cur_bytes); | ||
209 | - ret = block_copy_do_copy(s, start, cur_bytes, ret & BDRV_BLOCK_ZERO, | ||
210 | + ret = block_copy_do_copy(s, offset, cur_bytes, ret & BDRV_BLOCK_ZERO, | ||
211 | error_is_read); | ||
212 | co_put_to_shres(s->mem, cur_bytes); | ||
213 | s->in_flight_bytes -= cur_bytes; | ||
214 | if (ret < 0) { | ||
215 | - bdrv_set_dirty_bitmap(s->copy_bitmap, start, cur_bytes); | ||
216 | + bdrv_set_dirty_bitmap(s->copy_bitmap, offset, cur_bytes); | ||
217 | break; | 341 | break; |
218 | } | 342 | } |
219 | 343 | @@ -XXX,XX +XXX,XX @@ static void vu_block_process_vq(VuDev *vu_dev, int idx) | |
220 | progress_work_done(s->progress, cur_bytes); | 344 | req->vq = vq; |
221 | s->progress_bytes_callback(cur_bytes, s->progress_opaque); | 345 | |
222 | - start += cur_bytes; | 346 | Coroutine *co = |
223 | + offset += cur_bytes; | 347 | - qemu_coroutine_create(vu_block_virtio_process_req, req); |
224 | bytes -= cur_bytes; | 348 | + qemu_coroutine_create(vu_blk_virtio_process_req, req); |
349 | qemu_coroutine_enter(co); | ||
225 | } | 350 | } |
226 | 351 | } | |
227 | diff --git a/include/block/block-copy.h b/include/block/block-copy.h | 352 | |
353 | -static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) | ||
354 | +static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started) | ||
355 | { | ||
356 | VuVirtq *vq; | ||
357 | |||
358 | assert(vu_dev); | ||
359 | |||
360 | vq = vu_get_queue(vu_dev, idx); | ||
361 | - vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); | ||
362 | + vu_set_queue_handler(vu_dev, vq, started ? vu_blk_process_vq : NULL); | ||
363 | } | ||
364 | |||
365 | -static uint64_t vu_block_get_features(VuDev *dev) | ||
366 | +static uint64_t vu_blk_get_features(VuDev *dev) | ||
367 | { | ||
368 | uint64_t features; | ||
369 | VuServer *server = container_of(dev, VuServer, vu_dev); | ||
370 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
371 | + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); | ||
372 | features = 1ull << VIRTIO_BLK_F_SIZE_MAX | | ||
373 | 1ull << VIRTIO_BLK_F_SEG_MAX | | ||
374 | 1ull << VIRTIO_BLK_F_TOPOLOGY | | ||
375 | @@ -XXX,XX +XXX,XX @@ static uint64_t vu_block_get_features(VuDev *dev) | ||
376 | 1ull << VIRTIO_RING_F_EVENT_IDX | | ||
377 | 1ull << VHOST_USER_F_PROTOCOL_FEATURES; | ||
378 | |||
379 | - if (!vdev_blk->writable) { | ||
380 | + if (!vexp->writable) { | ||
381 | features |= 1ull << VIRTIO_BLK_F_RO; | ||
382 | } | ||
383 | |||
384 | return features; | ||
385 | } | ||
386 | |||
387 | -static uint64_t vu_block_get_protocol_features(VuDev *dev) | ||
388 | +static uint64_t vu_blk_get_protocol_features(VuDev *dev) | ||
389 | { | ||
390 | return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | | ||
391 | 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; | ||
392 | } | ||
393 | |||
394 | static int | ||
395 | -vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) | ||
396 | +vu_blk_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) | ||
397 | { | ||
398 | + /* TODO blkcfg must be little-endian for VIRTIO 1.0 */ | ||
399 | VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
400 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
401 | - memcpy(config, &vdev_blk->blkcfg, len); | ||
402 | - | ||
403 | + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); | ||
404 | + memcpy(config, &vexp->blkcfg, len); | ||
405 | return 0; | ||
406 | } | ||
407 | |||
408 | static int | ||
409 | -vu_block_set_config(VuDev *vu_dev, const uint8_t *data, | ||
410 | +vu_blk_set_config(VuDev *vu_dev, const uint8_t *data, | ||
411 | uint32_t offset, uint32_t size, uint32_t flags) | ||
412 | { | ||
413 | VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
414 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); | ||
415 | + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); | ||
416 | uint8_t wce; | ||
417 | |||
418 | /* don't support live migration */ | ||
419 | @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, | ||
420 | } | ||
421 | |||
422 | wce = *data; | ||
423 | - vdev_blk->blkcfg.wce = wce; | ||
424 | - blk_set_enable_write_cache(vdev_blk->backend, wce); | ||
425 | + vexp->blkcfg.wce = wce; | ||
426 | + blk_set_enable_write_cache(vexp->export.blk, wce); | ||
427 | return 0; | ||
428 | } | ||
429 | |||
430 | @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, | ||
431 | * of vu_process_message. | ||
432 | * | ||
433 | */ | ||
434 | -static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) | ||
435 | +static int vu_blk_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) | ||
436 | { | ||
437 | if (vmsg->request == VHOST_USER_NONE) { | ||
438 | dev->panic(dev, "disconnect"); | ||
439 | @@ -XXX,XX +XXX,XX @@ static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) | ||
440 | return false; | ||
441 | } | ||
442 | |||
443 | -static const VuDevIface vu_block_iface = { | ||
444 | - .get_features = vu_block_get_features, | ||
445 | - .queue_set_started = vu_block_queue_set_started, | ||
446 | - .get_protocol_features = vu_block_get_protocol_features, | ||
447 | - .get_config = vu_block_get_config, | ||
448 | - .set_config = vu_block_set_config, | ||
449 | - .process_msg = vu_block_process_msg, | ||
450 | +static const VuDevIface vu_blk_iface = { | ||
451 | + .get_features = vu_blk_get_features, | ||
452 | + .queue_set_started = vu_blk_queue_set_started, | ||
453 | + .get_protocol_features = vu_blk_get_protocol_features, | ||
454 | + .get_config = vu_blk_get_config, | ||
455 | + .set_config = vu_blk_set_config, | ||
456 | + .process_msg = vu_blk_process_msg, | ||
457 | }; | ||
458 | |||
459 | static void blk_aio_attached(AioContext *ctx, void *opaque) | ||
460 | { | ||
461 | - VuBlockDev *vub_dev = opaque; | ||
462 | - vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); | ||
463 | + VuBlkExport *vexp = opaque; | ||
464 | + vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); | ||
465 | } | ||
466 | |||
467 | static void blk_aio_detach(void *opaque) | ||
468 | { | ||
469 | - VuBlockDev *vub_dev = opaque; | ||
470 | - vhost_user_server_detach_aio_context(&vub_dev->vu_server); | ||
471 | + VuBlkExport *vexp = opaque; | ||
472 | + vhost_user_server_detach_aio_context(&vexp->vu_server); | ||
473 | } | ||
474 | |||
475 | static void | ||
476 | -vu_block_initialize_config(BlockDriverState *bs, | ||
477 | +vu_blk_initialize_config(BlockDriverState *bs, | ||
478 | struct virtio_blk_config *config, uint32_t blk_size) | ||
479 | { | ||
480 | config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; | ||
481 | @@ -XXX,XX +XXX,XX @@ vu_block_initialize_config(BlockDriverState *bs, | ||
482 | config->max_write_zeroes_seg = 1; | ||
483 | } | ||
484 | |||
485 | -static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) | ||
486 | +static void vu_blk_exp_request_shutdown(BlockExport *exp) | ||
487 | { | ||
488 | + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); | ||
489 | |||
490 | - BlockBackend *blk; | ||
491 | - Error *local_error = NULL; | ||
492 | - const char *node_name = vu_block_device->node_name; | ||
493 | - bool writable = vu_block_device->writable; | ||
494 | - uint64_t perm = BLK_PERM_CONSISTENT_READ; | ||
495 | - int ret; | ||
496 | - | ||
497 | - AioContext *ctx; | ||
498 | - | ||
499 | - BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); | ||
500 | - | ||
501 | - if (!bs) { | ||
502 | - error_propagate(errp, local_error); | ||
503 | - return NULL; | ||
504 | - } | ||
505 | - | ||
506 | - if (bdrv_is_read_only(bs)) { | ||
507 | - writable = false; | ||
508 | - } | ||
509 | - | ||
510 | - if (writable) { | ||
511 | - perm |= BLK_PERM_WRITE; | ||
512 | - } | ||
513 | - | ||
514 | - ctx = bdrv_get_aio_context(bs); | ||
515 | - aio_context_acquire(ctx); | ||
516 | - bdrv_invalidate_cache(bs, NULL); | ||
517 | - aio_context_release(ctx); | ||
518 | - | ||
519 | - /* | ||
520 | - * Don't allow resize while the vhost user server is running, | ||
521 | - * otherwise we don't care what happens with the node. | ||
522 | - */ | ||
523 | - blk = blk_new(bdrv_get_aio_context(bs), perm, | ||
524 | - BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | | ||
525 | - BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); | ||
526 | - ret = blk_insert_bs(blk, bs, errp); | ||
527 | - | ||
528 | - if (ret < 0) { | ||
529 | - goto fail; | ||
530 | - } | ||
531 | - | ||
532 | - blk_set_enable_write_cache(blk, false); | ||
533 | - | ||
534 | - blk_set_allow_aio_context_change(blk, true); | ||
535 | - | ||
536 | - vu_block_device->blkcfg.wce = 0; | ||
537 | - vu_block_device->backend = blk; | ||
538 | - if (!vu_block_device->blk_size) { | ||
539 | - vu_block_device->blk_size = BDRV_SECTOR_SIZE; | ||
540 | - } | ||
541 | - vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; | ||
542 | - blk_set_guest_block_size(blk, vu_block_device->blk_size); | ||
543 | - vu_block_initialize_config(bs, &vu_block_device->blkcfg, | ||
544 | - vu_block_device->blk_size); | ||
545 | - return vu_block_device; | ||
546 | - | ||
547 | -fail: | ||
548 | - blk_unref(blk); | ||
549 | - return NULL; | ||
550 | -} | ||
551 | - | ||
552 | -static void vu_block_deinit(VuBlockDev *vu_block_device) | ||
553 | -{ | ||
554 | - if (vu_block_device->backend) { | ||
555 | - blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, | ||
556 | - blk_aio_detach, vu_block_device); | ||
557 | - } | ||
558 | - | ||
559 | - blk_unref(vu_block_device->backend); | ||
560 | -} | ||
561 | - | ||
562 | -static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) | ||
563 | -{ | ||
564 | - vhost_user_server_stop(&vu_block_device->vu_server); | ||
565 | - vu_block_deinit(vu_block_device); | ||
566 | -} | ||
567 | - | ||
568 | -static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, | ||
569 | - Error **errp) | ||
570 | -{ | ||
571 | - AioContext *ctx; | ||
572 | - SocketAddress *addr = vu_block_device->addr; | ||
573 | - | ||
574 | - if (!vu_block_init(vu_block_device, errp)) { | ||
575 | - return; | ||
576 | - } | ||
577 | - | ||
578 | - ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); | ||
579 | - | ||
580 | - if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, | ||
581 | - VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, | ||
582 | - errp)) { | ||
583 | - goto error; | ||
584 | - } | ||
585 | - | ||
586 | - blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, | ||
587 | - blk_aio_detach, vu_block_device); | ||
588 | - vu_block_device->running = true; | ||
589 | - return; | ||
590 | - | ||
591 | - error: | ||
592 | - vu_block_deinit(vu_block_device); | ||
593 | -} | ||
594 | - | ||
595 | -static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) | ||
596 | -{ | ||
597 | - if (vus->running) { | ||
598 | - error_setg(errp, "The property can't be modified " | ||
599 | - "while the server is running"); | ||
600 | - return false; | ||
601 | - } | ||
602 | - return true; | ||
603 | -} | ||
604 | - | ||
605 | -static void vu_set_node_name(Object *obj, const char *value, Error **errp) | ||
606 | -{ | ||
607 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
608 | - | ||
609 | - if (!vu_prop_modifiable(vus, errp)) { | ||
610 | - return; | ||
611 | - } | ||
612 | - | ||
613 | - if (vus->node_name) { | ||
614 | - g_free(vus->node_name); | ||
615 | - } | ||
616 | - | ||
617 | - vus->node_name = g_strdup(value); | ||
618 | -} | ||
619 | - | ||
620 | -static char *vu_get_node_name(Object *obj, Error **errp) | ||
621 | -{ | ||
622 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
623 | - return g_strdup(vus->node_name); | ||
624 | -} | ||
625 | - | ||
626 | -static void free_socket_addr(SocketAddress *addr) | ||
627 | -{ | ||
628 | - g_free(addr->u.q_unix.path); | ||
629 | - g_free(addr); | ||
630 | -} | ||
631 | - | ||
632 | -static void vu_set_unix_socket(Object *obj, const char *value, | ||
633 | - Error **errp) | ||
634 | -{ | ||
635 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
636 | - | ||
637 | - if (!vu_prop_modifiable(vus, errp)) { | ||
638 | - return; | ||
639 | - } | ||
640 | - | ||
641 | - if (vus->addr) { | ||
642 | - free_socket_addr(vus->addr); | ||
643 | - } | ||
644 | - | ||
645 | - SocketAddress *addr = g_new0(SocketAddress, 1); | ||
646 | - addr->type = SOCKET_ADDRESS_TYPE_UNIX; | ||
647 | - addr->u.q_unix.path = g_strdup(value); | ||
648 | - vus->addr = addr; | ||
649 | + vhost_user_server_stop(&vexp->vu_server); | ||
650 | } | ||
651 | |||
652 | -static char *vu_get_unix_socket(Object *obj, Error **errp) | ||
653 | +static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, | ||
654 | + Error **errp) | ||
655 | { | ||
656 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
657 | - return g_strdup(vus->addr->u.q_unix.path); | ||
658 | -} | ||
659 | - | ||
660 | -static bool vu_get_block_writable(Object *obj, Error **errp) | ||
661 | -{ | ||
662 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
663 | - return vus->writable; | ||
664 | -} | ||
665 | - | ||
666 | -static void vu_set_block_writable(Object *obj, bool value, Error **errp) | ||
667 | -{ | ||
668 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
669 | - | ||
670 | - if (!vu_prop_modifiable(vus, errp)) { | ||
671 | - return; | ||
672 | - } | ||
673 | - | ||
674 | - vus->writable = value; | ||
675 | -} | ||
676 | - | ||
677 | -static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, | ||
678 | - void *opaque, Error **errp) | ||
679 | -{ | ||
680 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
681 | - uint32_t value = vus->blk_size; | ||
682 | - | ||
683 | - visit_type_uint32(v, name, &value, errp); | ||
684 | -} | ||
685 | - | ||
686 | -static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, | ||
687 | - void *opaque, Error **errp) | ||
688 | -{ | ||
689 | - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); | ||
690 | - | ||
691 | + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); | ||
692 | + BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; | ||
693 | Error *local_err = NULL; | ||
694 | - uint32_t value; | ||
695 | + uint64_t logical_block_size; | ||
696 | |||
697 | - if (!vu_prop_modifiable(vus, errp)) { | ||
698 | - return; | ||
699 | - } | ||
700 | + vexp->writable = opts->writable; | ||
701 | + vexp->blkcfg.wce = 0; | ||
702 | |||
703 | - visit_type_uint32(v, name, &value, &local_err); | ||
704 | - if (local_err) { | ||
705 | - goto out; | ||
706 | + if (vu_opts->has_logical_block_size) { | ||
707 | + logical_block_size = vu_opts->logical_block_size; | ||
708 | + } else { | ||
709 | + logical_block_size = BDRV_SECTOR_SIZE; | ||
710 | } | ||
711 | - | ||
712 | - check_block_size(object_get_typename(obj), name, value, &local_err); | ||
713 | + check_block_size(exp->id, "logical-block-size", logical_block_size, | ||
714 | + &local_err); | ||
715 | if (local_err) { | ||
716 | - goto out; | ||
717 | + error_propagate(errp, local_err); | ||
718 | + return -EINVAL; | ||
719 | + } | ||
720 | + vexp->blk_size = logical_block_size; | ||
721 | + blk_set_guest_block_size(exp->blk, logical_block_size); | ||
722 | + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, | ||
723 | + logical_block_size); | ||
724 | + | ||
725 | + blk_set_allow_aio_context_change(exp->blk, true); | ||
726 | + blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, | ||
727 | + vexp); | ||
728 | + | ||
729 | + if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, | ||
730 | + VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, | ||
731 | + errp)) { | ||
732 | + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, | ||
733 | + blk_aio_detach, vexp); | ||
734 | + return -EADDRNOTAVAIL; | ||
735 | } | ||
736 | |||
737 | - vus->blk_size = value; | ||
738 | - | ||
739 | -out: | ||
740 | - error_propagate(errp, local_err); | ||
741 | -} | ||
742 | - | ||
743 | -static void vhost_user_blk_server_instance_finalize(Object *obj) | ||
744 | -{ | ||
745 | - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); | ||
746 | - | ||
747 | - vhost_user_blk_server_stop(vub); | ||
748 | - | ||
749 | - /* | ||
750 | - * Unlike object_property_add_str, object_class_property_add_str | ||
751 | - * doesn't have a release method. Thus manual memory freeing is | ||
752 | - * needed. | ||
753 | - */ | ||
754 | - free_socket_addr(vub->addr); | ||
755 | - g_free(vub->node_name); | ||
756 | -} | ||
757 | - | ||
758 | -static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) | ||
759 | -{ | ||
760 | - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); | ||
761 | - | ||
762 | - vhost_user_blk_server_start(vub, errp); | ||
763 | + return 0; | ||
764 | } | ||
765 | |||
766 | -static void vhost_user_blk_server_class_init(ObjectClass *klass, | ||
767 | - void *class_data) | ||
768 | +static void vu_blk_exp_delete(BlockExport *exp) | ||
769 | { | ||
770 | - UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); | ||
771 | - ucc->complete = vhost_user_blk_server_complete; | ||
772 | - | ||
773 | - object_class_property_add_bool(klass, "writable", | ||
774 | - vu_get_block_writable, | ||
775 | - vu_set_block_writable); | ||
776 | - | ||
777 | - object_class_property_add_str(klass, "node-name", | ||
778 | - vu_get_node_name, | ||
779 | - vu_set_node_name); | ||
780 | - | ||
781 | - object_class_property_add_str(klass, "unix-socket", | ||
782 | - vu_get_unix_socket, | ||
783 | - vu_set_unix_socket); | ||
784 | + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); | ||
785 | |||
786 | - object_class_property_add(klass, "logical-block-size", "uint32", | ||
787 | - vu_get_blk_size, vu_set_blk_size, | ||
788 | - NULL, NULL); | ||
789 | + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, | ||
790 | + vexp); | ||
791 | } | ||
792 | |||
793 | -static const TypeInfo vhost_user_blk_server_info = { | ||
794 | - .name = TYPE_VHOST_USER_BLK_SERVER, | ||
795 | - .parent = TYPE_OBJECT, | ||
796 | - .instance_size = sizeof(VuBlockDev), | ||
797 | - .instance_finalize = vhost_user_blk_server_instance_finalize, | ||
798 | - .class_init = vhost_user_blk_server_class_init, | ||
799 | - .interfaces = (InterfaceInfo[]) { | ||
800 | - {TYPE_USER_CREATABLE}, | ||
801 | - {} | ||
802 | - }, | ||
803 | +const BlockExportDriver blk_exp_vhost_user_blk = { | ||
804 | + .type = BLOCK_EXPORT_TYPE_VHOST_USER_BLK, | ||
805 | + .instance_size = sizeof(VuBlkExport), | ||
806 | + .create = vu_blk_exp_create, | ||
807 | + .delete = vu_blk_exp_delete, | ||
808 | + .request_shutdown = vu_blk_exp_request_shutdown, | ||
809 | }; | ||
810 | - | ||
811 | -static void vhost_user_blk_server_register_types(void) | ||
812 | -{ | ||
813 | - type_register_static(&vhost_user_blk_server_info); | ||
814 | -} | ||
815 | - | ||
816 | -type_init(vhost_user_blk_server_register_types) | ||
817 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
228 | index XXXXXXX..XXXXXXX 100644 | 818 | index XXXXXXX..XXXXXXX 100644 |
229 | --- a/include/block/block-copy.h | 819 | --- a/util/vhost-user-server.c |
230 | +++ b/include/block/block-copy.h | 820 | +++ b/util/vhost-user-server.c |
231 | @@ -XXX,XX +XXX,XX @@ | 821 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, |
232 | #include "qemu/co-shared-resource.h" | 822 | Error **errp) |
233 | 823 | { | |
234 | typedef struct BlockCopyInFlightReq { | 824 | QEMUBH *bh; |
235 | - int64_t start; | 825 | - QIONetListener *listener = qio_net_listener_new(); |
236 | + int64_t offset; | 826 | + QIONetListener *listener; |
237 | int64_t bytes; | 827 | + |
238 | QLIST_ENTRY(BlockCopyInFlightReq) list; | 828 | + if (socket_addr->type != SOCKET_ADDRESS_TYPE_UNIX && |
239 | CoQueue wait_queue; /* coroutines blocked on this request */ | 829 | + socket_addr->type != SOCKET_ADDRESS_TYPE_FD) { |
240 | @@ -XXX,XX +XXX,XX @@ void block_copy_state_free(BlockCopyState *s); | 830 | + error_setg(errp, "Only socket address types 'unix' and 'fd' are supported"); |
241 | int64_t block_copy_reset_unallocated(BlockCopyState *s, | 831 | + return false; |
242 | int64_t offset, int64_t *count); | 832 | + } |
243 | 833 | + | |
244 | -int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, | 834 | + listener = qio_net_listener_new(); |
245 | +int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, | 835 | if (qio_net_listener_open_sync(listener, socket_addr, 1, |
246 | bool *error_is_read); | 836 | errp) < 0) { |
247 | 837 | object_unref(OBJECT(listener)); | |
248 | #endif /* BLOCK_COPY_H */ | 838 | diff --git a/block/export/meson.build b/block/export/meson.build |
839 | index XXXXXXX..XXXXXXX 100644 | ||
840 | --- a/block/export/meson.build | ||
841 | +++ b/block/export/meson.build | ||
842 | @@ -1 +1,2 @@ | ||
843 | block_ss.add(files('export.c')) | ||
844 | +block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) | ||
845 | diff --git a/block/meson.build b/block/meson.build | ||
846 | index XXXXXXX..XXXXXXX 100644 | ||
847 | --- a/block/meson.build | ||
848 | +++ b/block/meson.build | ||
849 | @@ -XXX,XX +XXX,XX @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') | ||
850 | block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) | ||
851 | block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) | ||
852 | block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) | ||
853 | -block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) | ||
854 | block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) | ||
855 | block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) | ||
856 | block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) | ||
249 | -- | 857 | -- |
250 | 2.24.1 | 858 | 2.26.2 |
251 | 859 | ||
252 | diff view generated by jsdifflib |
1 | From: Pan Nengyuan <pannengyuan@huawei.com> | 1 | Headers used by other subsystems are located in include/. Also add the |
---|---|---|---|
2 | vhost-user-server and vhost-user-blk-server headers to MAINTAINERS. | ||
2 | 3 | ||
3 | 'crypto_opts' forgot to free in qcow2_close(), this patch fix the bellow leak stack: | 4 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
5 | Message-id: 20200924151549.913737-13-stefanha@redhat.com | ||
6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
7 | --- | ||
8 | MAINTAINERS | 4 +++- | ||
9 | {util => include/qemu}/vhost-user-server.h | 0 | ||
10 | block/export/vhost-user-blk-server.c | 2 +- | ||
11 | util/vhost-user-server.c | 2 +- | ||
12 | 4 files changed, 5 insertions(+), 3 deletions(-) | ||
13 | rename {util => include/qemu}/vhost-user-server.h (100%) | ||
4 | 14 | ||
5 | Direct leak of 24 byte(s) in 1 object(s) allocated from: | 15 | diff --git a/MAINTAINERS b/MAINTAINERS |
6 | #0 0x7f0edd81f970 in __interceptor_calloc (/lib64/libasan.so.5+0xef970) | 16 | index XXXXXXX..XXXXXXX 100644 |
7 | #1 0x7f0edc6d149d in g_malloc0 (/lib64/libglib-2.0.so.0+0x5249d) | 17 | --- a/MAINTAINERS |
8 | #2 0x55d7eaede63d in qobject_input_start_struct /mnt/sdb/qemu-new/qemu_test/qemu/qapi/qobject-input-visitor.c:295 | 18 | +++ b/MAINTAINERS |
9 | #3 0x55d7eaed78b8 in visit_start_struct /mnt/sdb/qemu-new/qemu_test/qemu/qapi/qapi-visit-core.c:49 | 19 | @@ -XXX,XX +XXX,XX @@ Vhost-user block device backend server |
10 | #4 0x55d7eaf5140b in visit_type_QCryptoBlockOpenOptions qapi/qapi-visit-crypto.c:290 | 20 | M: Coiby Xu <Coiby.Xu@gmail.com> |
11 | #5 0x55d7eae43af3 in block_crypto_open_opts_init /mnt/sdb/qemu-new/qemu_test/qemu/block/crypto.c:163 | 21 | S: Maintained |
12 | #6 0x55d7eacd2924 in qcow2_update_options_prepare /mnt/sdb/qemu-new/qemu_test/qemu/block/qcow2.c:1148 | 22 | F: block/export/vhost-user-blk-server.c |
13 | #7 0x55d7eacd33f7 in qcow2_update_options /mnt/sdb/qemu-new/qemu_test/qemu/block/qcow2.c:1232 | 23 | -F: util/vhost-user-server.c |
14 | #8 0x55d7eacd9680 in qcow2_do_open /mnt/sdb/qemu-new/qemu_test/qemu/block/qcow2.c:1512 | 24 | +F: block/export/vhost-user-blk-server.h |
15 | #9 0x55d7eacdc55e in qcow2_open_entry /mnt/sdb/qemu-new/qemu_test/qemu/block/qcow2.c:1792 | 25 | +F: include/qemu/vhost-user-server.h |
16 | #10 0x55d7eacdc8fe in qcow2_open /mnt/sdb/qemu-new/qemu_test/qemu/block/qcow2.c:1819 | 26 | F: tests/qtest/libqos/vhost-user-blk.c |
17 | #11 0x55d7eac3742d in bdrv_open_driver /mnt/sdb/qemu-new/qemu_test/qemu/block.c:1317 | 27 | +F: util/vhost-user-server.c |
18 | #12 0x55d7eac3e990 in bdrv_open_common /mnt/sdb/qemu-new/qemu_test/qemu/block.c:1575 | 28 | |
19 | #13 0x55d7eac4442c in bdrv_open_inherit /mnt/sdb/qemu-new/qemu_test/qemu/block.c:3126 | 29 | Replication |
20 | #14 0x55d7eac45c3f in bdrv_open /mnt/sdb/qemu-new/qemu_test/qemu/block.c:3219 | 30 | M: Wen Congyang <wencongyang2@huawei.com> |
21 | #15 0x55d7ead8e8a4 in blk_new_open /mnt/sdb/qemu-new/qemu_test/qemu/block/block-backend.c:397 | 31 | diff --git a/util/vhost-user-server.h b/include/qemu/vhost-user-server.h |
22 | #16 0x55d7eacde74c in qcow2_co_create /mnt/sdb/qemu-new/qemu_test/qemu/block/qcow2.c:3534 | 32 | similarity index 100% |
23 | #17 0x55d7eacdfa6d in qcow2_co_create_opts /mnt/sdb/qemu-new/qemu_test/qemu/block/qcow2.c:3668 | 33 | rename from util/vhost-user-server.h |
24 | #18 0x55d7eac1c678 in bdrv_create_co_entry /mnt/sdb/qemu-new/qemu_test/qemu/block.c:485 | 34 | rename to include/qemu/vhost-user-server.h |
25 | #19 0x55d7eb0024d2 in coroutine_trampoline /mnt/sdb/qemu-new/qemu_test/qemu/util/coroutine-ucontext.c:115 | 35 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
36 | index XXXXXXX..XXXXXXX 100644 | ||
37 | --- a/block/export/vhost-user-blk-server.c | ||
38 | +++ b/block/export/vhost-user-blk-server.c | ||
39 | @@ -XXX,XX +XXX,XX @@ | ||
40 | #include "block/block.h" | ||
41 | #include "contrib/libvhost-user/libvhost-user.h" | ||
42 | #include "standard-headers/linux/virtio_blk.h" | ||
43 | -#include "util/vhost-user-server.h" | ||
44 | +#include "qemu/vhost-user-server.h" | ||
45 | #include "vhost-user-blk-server.h" | ||
46 | #include "qapi/error.h" | ||
47 | #include "qom/object_interfaces.h" | ||
48 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
49 | index XXXXXXX..XXXXXXX 100644 | ||
50 | --- a/util/vhost-user-server.c | ||
51 | +++ b/util/vhost-user-server.c | ||
52 | @@ -XXX,XX +XXX,XX @@ | ||
53 | */ | ||
54 | #include "qemu/osdep.h" | ||
55 | #include "qemu/main-loop.h" | ||
56 | +#include "qemu/vhost-user-server.h" | ||
57 | #include "block/aio-wait.h" | ||
58 | -#include "vhost-user-server.h" | ||
59 | |||
60 | /* | ||
61 | * Theory of operation: | ||
62 | -- | ||
63 | 2.26.2 | ||
26 | 64 | ||
27 | Reported-by: Euler Robot <euler.robot@huawei.com> | ||
28 | Signed-off-by: Pan Nengyuan <pannengyuan@huawei.com> | ||
29 | Reviewed-by: Max Reitz <mreitz@redhat.com> | ||
30 | Message-Id: <20200227012950.12256-2-pannengyuan@huawei.com> | ||
31 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
32 | --- | ||
33 | block/qcow2.c | 1 + | ||
34 | 1 file changed, 1 insertion(+) | ||
35 | |||
36 | diff --git a/block/qcow2.c b/block/qcow2.c | ||
37 | index XXXXXXX..XXXXXXX 100644 | ||
38 | --- a/block/qcow2.c | ||
39 | +++ b/block/qcow2.c | ||
40 | @@ -XXX,XX +XXX,XX @@ static void qcow2_close(BlockDriverState *bs) | ||
41 | |||
42 | qcrypto_block_free(s->crypto); | ||
43 | s->crypto = NULL; | ||
44 | + qapi_free_QCryptoBlockOpenOptions(s->crypto_opts); | ||
45 | |||
46 | g_free(s->unknown_header_fields); | ||
47 | cleanup_unknown_header_ext(bs); | ||
48 | -- | ||
49 | 2.24.1 | ||
50 | |||
51 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | Don't compile contrib/libvhost-user/libvhost-user.c again. Instead build |
---|---|---|---|
2 | the static library once and then reuse it throughout QEMU. | ||
2 | 3 | ||
3 | In most qemu-img sub-commands the --object option only makes sense when | 4 | Also switch from CONFIG_LINUX to CONFIG_VHOST_USER, which is what the |
4 | there is a filename. qemu-img measure is an exception because objects | 5 | vhost-user tools (vhost-user-gpu, etc) do. |
5 | may be referenced from the image creation options instead of an existing | ||
6 | image file. Allow --object without a filename. | ||
7 | 6 | ||
8 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
9 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 8 | Message-id: 20200924151549.913737-14-stefanha@redhat.com |
10 | Message-Id: <20200221112522.1497712-4-stefanha@redhat.com> | 9 | [Added CONFIG_LINUX again because libvhost-user doesn't build on macOS. |
11 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 10 | --Stefan] |
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
12 | --- | 12 | --- |
13 | qemu-img.c | 6 ++---- | 13 | block/export/export.c | 8 ++++---- |
14 | tests/qemu-iotests/178 | 2 +- | 14 | block/export/meson.build | 2 +- |
15 | tests/qemu-iotests/178.out.qcow2 | 8 ++++---- | 15 | contrib/libvhost-user/meson.build | 1 + |
16 | tests/qemu-iotests/178.out.raw | 8 ++++---- | 16 | meson.build | 6 +++++- |
17 | 4 files changed, 11 insertions(+), 13 deletions(-) | 17 | util/meson.build | 4 +++- |
18 | 5 files changed, 14 insertions(+), 7 deletions(-) | ||
18 | 19 | ||
19 | diff --git a/qemu-img.c b/qemu-img.c | 20 | diff --git a/block/export/export.c b/block/export/export.c |
20 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
21 | --- a/qemu-img.c | 22 | --- a/block/export/export.c |
22 | +++ b/qemu-img.c | 23 | +++ b/block/export/export.c |
23 | @@ -XXX,XX +XXX,XX @@ static int img_measure(int argc, char **argv) | 24 | @@ -XXX,XX +XXX,XX @@ |
24 | filename = argv[optind]; | 25 | #include "sysemu/block-backend.h" |
25 | } | 26 | #include "block/export.h" |
26 | 27 | #include "block/nbd.h" | |
27 | - if (!filename && | 28 | -#if CONFIG_LINUX |
28 | - (object_opts || image_opts || fmt || snapshot_name || sn_opts)) { | 29 | -#include "block/export/vhost-user-blk-server.h" |
29 | - error_report("--object, --image-opts, -f, and -l " | 30 | -#endif |
30 | - "require a filename argument."); | 31 | #include "qapi/error.h" |
31 | + if (!filename && (image_opts || fmt || snapshot_name || sn_opts)) { | 32 | #include "qapi/qapi-commands-block-export.h" |
32 | + error_report("--image-opts, -f, and -l require a filename argument."); | 33 | #include "qapi/qapi-events-block-export.h" |
33 | goto out; | 34 | #include "qemu/id.h" |
34 | } | 35 | +#ifdef CONFIG_VHOST_USER |
35 | if (filename && img_size != UINT64_MAX) { | 36 | +#include "vhost-user-blk-server.h" |
36 | diff --git a/tests/qemu-iotests/178 b/tests/qemu-iotests/178 | 37 | +#endif |
37 | index XXXXXXX..XXXXXXX 100755 | 38 | |
38 | --- a/tests/qemu-iotests/178 | 39 | static const BlockExportDriver *blk_exp_drivers[] = { |
39 | +++ b/tests/qemu-iotests/178 | 40 | &blk_exp_nbd, |
40 | @@ -XXX,XX +XXX,XX @@ _make_test_img 1G | 41 | -#if CONFIG_LINUX |
41 | $QEMU_IMG measure # missing arguments | 42 | +#ifdef CONFIG_VHOST_USER |
42 | $QEMU_IMG measure --size 2G "$TEST_IMG" # only one allowed | 43 | &blk_exp_vhost_user_blk, |
43 | $QEMU_IMG measure "$TEST_IMG" a # only one filename allowed | 44 | #endif |
44 | -$QEMU_IMG measure --object secret,id=sec0,data=MTIzNDU2,format=base64 # missing filename | 45 | }; |
45 | +$QEMU_IMG measure --object secret,id=sec0,data=MTIzNDU2,format=base64 # size or filename needed | 46 | diff --git a/block/export/meson.build b/block/export/meson.build |
46 | $QEMU_IMG measure --image-opts # missing filename | ||
47 | $QEMU_IMG measure -f qcow2 # missing filename | ||
48 | $QEMU_IMG measure -l snap1 # missing filename | ||
49 | diff --git a/tests/qemu-iotests/178.out.qcow2 b/tests/qemu-iotests/178.out.qcow2 | ||
50 | index XXXXXXX..XXXXXXX 100644 | 47 | index XXXXXXX..XXXXXXX 100644 |
51 | --- a/tests/qemu-iotests/178.out.qcow2 | 48 | --- a/block/export/meson.build |
52 | +++ b/tests/qemu-iotests/178.out.qcow2 | 49 | +++ b/block/export/meson.build |
53 | @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 | 50 | @@ -XXX,XX +XXX,XX @@ |
54 | qemu-img: Either --size N or one filename must be specified. | 51 | block_ss.add(files('export.c')) |
55 | qemu-img: --size N cannot be used together with a filename. | 52 | -block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) |
56 | qemu-img: At most one filename argument is allowed. | 53 | +block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) |
57 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | 54 | diff --git a/contrib/libvhost-user/meson.build b/contrib/libvhost-user/meson.build |
58 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | ||
59 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | ||
60 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | ||
61 | +qemu-img: Either --size N or one filename must be specified. | ||
62 | +qemu-img: --image-opts, -f, and -l require a filename argument. | ||
63 | +qemu-img: --image-opts, -f, and -l require a filename argument. | ||
64 | +qemu-img: --image-opts, -f, and -l require a filename argument. | ||
65 | qemu-img: Invalid option list: , | ||
66 | qemu-img: Invalid parameter 'snapshot.foo' | ||
67 | qemu-img: Failed in parsing snapshot param 'snapshot.foo' | ||
68 | diff --git a/tests/qemu-iotests/178.out.raw b/tests/qemu-iotests/178.out.raw | ||
69 | index XXXXXXX..XXXXXXX 100644 | 55 | index XXXXXXX..XXXXXXX 100644 |
70 | --- a/tests/qemu-iotests/178.out.raw | 56 | --- a/contrib/libvhost-user/meson.build |
71 | +++ b/tests/qemu-iotests/178.out.raw | 57 | +++ b/contrib/libvhost-user/meson.build |
72 | @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 | 58 | @@ -XXX,XX +XXX,XX @@ |
73 | qemu-img: Either --size N or one filename must be specified. | 59 | libvhost_user = static_library('vhost-user', |
74 | qemu-img: --size N cannot be used together with a filename. | 60 | files('libvhost-user.c', 'libvhost-user-glib.c'), |
75 | qemu-img: At most one filename argument is allowed. | 61 | build_by_default: false) |
76 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | 62 | +vhost_user = declare_dependency(link_with: libvhost_user) |
77 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | 63 | diff --git a/meson.build b/meson.build |
78 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | 64 | index XXXXXXX..XXXXXXX 100644 |
79 | -qemu-img: --object, --image-opts, -f, and -l require a filename argument. | 65 | --- a/meson.build |
80 | +qemu-img: Either --size N or one filename must be specified. | 66 | +++ b/meson.build |
81 | +qemu-img: --image-opts, -f, and -l require a filename argument. | 67 | @@ -XXX,XX +XXX,XX @@ trace_events_subdirs += [ |
82 | +qemu-img: --image-opts, -f, and -l require a filename argument. | 68 | 'util', |
83 | +qemu-img: --image-opts, -f, and -l require a filename argument. | 69 | ] |
84 | qemu-img: Invalid option list: , | 70 | |
85 | qemu-img: Invalid parameter 'snapshot.foo' | 71 | +vhost_user = not_found |
86 | qemu-img: Failed in parsing snapshot param 'snapshot.foo' | 72 | +if 'CONFIG_VHOST_USER' in config_host |
73 | + subdir('contrib/libvhost-user') | ||
74 | +endif | ||
75 | + | ||
76 | subdir('qapi') | ||
77 | subdir('qobject') | ||
78 | subdir('stubs') | ||
79 | @@ -XXX,XX +XXX,XX @@ if have_tools | ||
80 | install: true) | ||
81 | |||
82 | if 'CONFIG_VHOST_USER' in config_host | ||
83 | - subdir('contrib/libvhost-user') | ||
84 | subdir('contrib/vhost-user-blk') | ||
85 | subdir('contrib/vhost-user-gpu') | ||
86 | subdir('contrib/vhost-user-input') | ||
87 | diff --git a/util/meson.build b/util/meson.build | ||
88 | index XXXXXXX..XXXXXXX 100644 | ||
89 | --- a/util/meson.build | ||
90 | +++ b/util/meson.build | ||
91 | @@ -XXX,XX +XXX,XX @@ if have_block | ||
92 | util_ss.add(files('main-loop.c')) | ||
93 | util_ss.add(files('nvdimm-utils.c')) | ||
94 | util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) | ||
95 | - util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) | ||
96 | + util_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: [ | ||
97 | + files('vhost-user-server.c'), vhost_user | ||
98 | + ]) | ||
99 | util_ss.add(files('block-helpers.c')) | ||
100 | util_ss.add(files('qemu-coroutine-sleep.c')) | ||
101 | util_ss.add(files('qemu-co-shared-resource.c')) | ||
87 | -- | 102 | -- |
88 | 2.24.1 | 103 | 2.26.2 |
89 | 104 | ||
90 | diff view generated by jsdifflib |
1 | From: David Edmondson <david.edmondson@oracle.com> | 1 | Introduce libblkdev.fa to avoid recompiling blockdev_ss twice. |
---|---|---|---|
2 | 2 | ||
3 | RFC 7230 section 3.2 indicates that HTTP header field names are case | 3 | Suggested-by: Paolo Bonzini <pbonzini@redhat.com> |
4 | insensitive. | 4 | Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> |
5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | Message-id: 20200929125516.186715-3-stefanha@redhat.com | ||
7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | --- | ||
9 | meson.build | 12 ++++++++++-- | ||
10 | storage-daemon/meson.build | 3 +-- | ||
11 | 2 files changed, 11 insertions(+), 4 deletions(-) | ||
5 | 12 | ||
6 | Signed-off-by: David Edmondson <david.edmondson@oracle.com> | 13 | diff --git a/meson.build b/meson.build |
7 | Message-Id: <20200224101310.101169-3-david.edmondson@oracle.com> | 14 | index XXXXXXX..XXXXXXX 100644 |
8 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 15 | --- a/meson.build |
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 16 | +++ b/meson.build |
10 | --- | 17 | @@ -XXX,XX +XXX,XX @@ blockdev_ss.add(files( |
11 | block/curl.c | 5 +++-- | 18 | # os-win32.c does not |
12 | 1 file changed, 3 insertions(+), 2 deletions(-) | 19 | blockdev_ss.add(when: 'CONFIG_POSIX', if_true: files('os-posix.c')) |
20 | softmmu_ss.add(when: 'CONFIG_WIN32', if_true: [files('os-win32.c')]) | ||
21 | -softmmu_ss.add_all(blockdev_ss) | ||
22 | |||
23 | common_ss.add(files('cpus-common.c')) | ||
24 | |||
25 | @@ -XXX,XX +XXX,XX @@ block = declare_dependency(link_whole: [libblock], | ||
26 | link_args: '@block.syms', | ||
27 | dependencies: [crypto, io]) | ||
28 | |||
29 | +blockdev_ss = blockdev_ss.apply(config_host, strict: false) | ||
30 | +libblockdev = static_library('blockdev', blockdev_ss.sources() + genh, | ||
31 | + dependencies: blockdev_ss.dependencies(), | ||
32 | + name_suffix: 'fa', | ||
33 | + build_by_default: false) | ||
34 | + | ||
35 | +blockdev = declare_dependency(link_whole: [libblockdev], | ||
36 | + dependencies: [block]) | ||
37 | + | ||
38 | qmp_ss = qmp_ss.apply(config_host, strict: false) | ||
39 | libqmp = static_library('qmp', qmp_ss.sources() + genh, | ||
40 | dependencies: qmp_ss.dependencies(), | ||
41 | @@ -XXX,XX +XXX,XX @@ foreach m : block_mods + softmmu_mods | ||
42 | install_dir: config_host['qemu_moddir']) | ||
43 | endforeach | ||
44 | |||
45 | -softmmu_ss.add(authz, block, chardev, crypto, io, qmp) | ||
46 | +softmmu_ss.add(authz, blockdev, chardev, crypto, io, qmp) | ||
47 | common_ss.add(qom, qemuutil) | ||
48 | |||
49 | common_ss.add_all(when: 'CONFIG_SOFTMMU', if_true: [softmmu_ss]) | ||
50 | diff --git a/storage-daemon/meson.build b/storage-daemon/meson.build | ||
51 | index XXXXXXX..XXXXXXX 100644 | ||
52 | --- a/storage-daemon/meson.build | ||
53 | +++ b/storage-daemon/meson.build | ||
54 | @@ -XXX,XX +XXX,XX @@ | ||
55 | qsd_ss = ss.source_set() | ||
56 | qsd_ss.add(files('qemu-storage-daemon.c')) | ||
57 | -qsd_ss.add(block, chardev, qmp, qom, qemuutil) | ||
58 | -qsd_ss.add_all(blockdev_ss) | ||
59 | +qsd_ss.add(blockdev, chardev, qmp, qom, qemuutil) | ||
60 | |||
61 | subdir('qapi') | ||
62 | |||
63 | -- | ||
64 | 2.26.2 | ||
13 | 65 | ||
14 | diff --git a/block/curl.c b/block/curl.c | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/block/curl.c | ||
17 | +++ b/block/curl.c | ||
18 | @@ -XXX,XX +XXX,XX @@ static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque) | ||
19 | size_t realsize = size * nmemb; | ||
20 | const char *header = (char *)ptr; | ||
21 | const char *end = header + realsize; | ||
22 | - const char *accept_ranges = "Accept-Ranges:"; | ||
23 | + const char *accept_ranges = "accept-ranges:"; | ||
24 | const char *bytes = "bytes"; | ||
25 | |||
26 | if (realsize >= strlen(accept_ranges) | ||
27 | - && strncmp(header, accept_ranges, strlen(accept_ranges)) == 0) { | ||
28 | + && g_ascii_strncasecmp(header, accept_ranges, | ||
29 | + strlen(accept_ranges)) == 0) { | ||
30 | |||
31 | char *p = strchr(header, ':') + 1; | ||
32 | |||
33 | -- | ||
34 | 2.24.1 | ||
35 | |||
36 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | Block exports are used by softmmu, qemu-storage-daemon, and qemu-nbd. |
---|---|---|---|
2 | They are not used by other programs and are not otherwise needed in | ||
3 | libblock. | ||
2 | 4 | ||
3 | This test exercises the block/crypto.c "luks" block driver | 5 | Undo the recent move of blockdev-nbd.c from blockdev_ss into block_ss. |
4 | .bdrv_measure() code. | 6 | Since bdrv_close_all() (libblock) calls blk_exp_close_all() |
7 | (libblockdev) a stub function is required.. | ||
8 | |||
9 | Make qemu-nbd.c use signal handling utility functions instead of | ||
10 | duplicating the code. This helps because os-posix.c is in libblockdev | ||
11 | and it depends on a qemu_system_killed() symbol that qemu-nbd.c lacks. | ||
12 | Once we use the signal handling utility functions we also end up | ||
13 | providing the necessary symbol. | ||
5 | 14 | ||
6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 15 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
7 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 16 | Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> |
8 | Message-Id: <20200221112522.1497712-5-stefanha@redhat.com> | 17 | Reviewed-by: Eric Blake <eblake@redhat.com> |
9 | [mreitz: Renamed test from 282 to 288] | 18 | Message-id: 20200929125516.186715-4-stefanha@redhat.com |
10 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 19 | [Fixed s/ndb/nbd/ typo in commit description as suggested by Eric Blake |
20 | --Stefan] | ||
21 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
11 | --- | 22 | --- |
12 | tests/qemu-iotests/288 | 93 ++++++++++++++++++++++++++++++++++++++ | 23 | qemu-nbd.c | 21 ++++++++------------- |
13 | tests/qemu-iotests/288.out | 30 ++++++++++++ | 24 | stubs/blk-exp-close-all.c | 7 +++++++ |
14 | tests/qemu-iotests/group | 1 + | 25 | block/export/meson.build | 4 ++-- |
15 | 3 files changed, 124 insertions(+) | 26 | meson.build | 4 ++-- |
16 | create mode 100755 tests/qemu-iotests/288 | 27 | nbd/meson.build | 2 ++ |
17 | create mode 100644 tests/qemu-iotests/288.out | 28 | stubs/meson.build | 1 + |
29 | 6 files changed, 22 insertions(+), 17 deletions(-) | ||
30 | create mode 100644 stubs/blk-exp-close-all.c | ||
18 | 31 | ||
19 | diff --git a/tests/qemu-iotests/288 b/tests/qemu-iotests/288 | 32 | diff --git a/qemu-nbd.c b/qemu-nbd.c |
20 | new file mode 100755 | 33 | index XXXXXXX..XXXXXXX 100644 |
21 | index XXXXXXX..XXXXXXX | 34 | --- a/qemu-nbd.c |
22 | --- /dev/null | 35 | +++ b/qemu-nbd.c |
23 | +++ b/tests/qemu-iotests/288 | ||
24 | @@ -XXX,XX +XXX,XX @@ | 36 | @@ -XXX,XX +XXX,XX @@ |
25 | +#!/usr/bin/env bash | 37 | #include "qapi/error.h" |
26 | +# | 38 | #include "qemu/cutils.h" |
27 | +# qemu-img measure tests for LUKS images | 39 | #include "sysemu/block-backend.h" |
28 | +# | 40 | +#include "sysemu/runstate.h" /* for qemu_system_killed() prototype */ |
29 | +# Copyright (C) 2020 Red Hat, Inc. | 41 | #include "block/block_int.h" |
30 | +# | 42 | #include "block/nbd.h" |
31 | +# This program is free software; you can redistribute it and/or modify | 43 | #include "qemu/main-loop.h" |
32 | +# it under the terms of the GNU General Public License as published by | 44 | @@ -XXX,XX +XXX,XX @@ QEMU_COPYRIGHT "\n" |
33 | +# the Free Software Foundation; either version 2 of the License, or | 45 | } |
34 | +# (at your option) any later version. | 46 | |
35 | +# | 47 | #ifdef CONFIG_POSIX |
36 | +# This program is distributed in the hope that it will be useful, | 48 | -static void termsig_handler(int signum) |
37 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of | 49 | +/* |
38 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 50 | + * The client thread uses SIGTERM to interrupt the server. A signal |
39 | +# GNU General Public License for more details. | 51 | + * handler ensures that "qemu-nbd -v -c" exits with a nice status code. |
40 | +# | 52 | + */ |
41 | +# You should have received a copy of the GNU General Public License | 53 | +void qemu_system_killed(int signum, pid_t pid) |
42 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. | 54 | { |
43 | +# | 55 | qatomic_cmpxchg(&state, RUNNING, TERMINATE); |
44 | + | 56 | qemu_notify_event(); |
45 | +# creator | 57 | @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) |
46 | +owner=stefanha@redhat.com | 58 | BlockExportOptions *export_opts; |
47 | + | 59 | |
48 | +seq=`basename $0` | 60 | #ifdef CONFIG_POSIX |
49 | +echo "QA output created by $seq" | 61 | - /* |
50 | + | 62 | - * Exit gracefully on various signals, which includes SIGTERM used |
51 | +status=1 # failure is the default! | 63 | - * by 'qemu-nbd -v -c'. |
52 | + | 64 | - */ |
53 | +_cleanup() | 65 | - struct sigaction sa_sigterm; |
54 | +{ | 66 | - memset(&sa_sigterm, 0, sizeof(sa_sigterm)); |
55 | + _cleanup_test_img | 67 | - sa_sigterm.sa_handler = termsig_handler; |
56 | + rm -f "$TEST_IMG.converted" | 68 | - sigaction(SIGTERM, &sa_sigterm, NULL); |
57 | +} | 69 | - sigaction(SIGINT, &sa_sigterm, NULL); |
58 | +trap "_cleanup; exit \$status" 0 1 2 3 15 | 70 | - sigaction(SIGHUP, &sa_sigterm, NULL); |
59 | + | 71 | - |
60 | +# get standard environment, filters and checks | 72 | - signal(SIGPIPE, SIG_IGN); |
61 | +. ./common.rc | 73 | + os_setup_early_signal_handling(); |
62 | +. ./common.filter | 74 | + os_setup_signal_handling(); |
63 | +. ./common.pattern | 75 | #endif |
64 | + | 76 | |
65 | +_supported_fmt luks | 77 | socket_init(); |
66 | +_supported_proto file | 78 | diff --git a/stubs/blk-exp-close-all.c b/stubs/blk-exp-close-all.c |
67 | +_supported_os Linux | ||
68 | + | ||
69 | +SECRET=secret,id=sec0,data=passphrase | ||
70 | + | ||
71 | +echo "== measure 1G image file ==" | ||
72 | +echo | ||
73 | + | ||
74 | +$QEMU_IMG measure --object "$SECRET" \ | ||
75 | + -O "$IMGFMT" \ | ||
76 | + -o key-secret=sec0,iter-time=10 \ | ||
77 | + --size 1G | ||
78 | + | ||
79 | +echo | ||
80 | +echo "== create 1G image file (size should be no greater than measured) ==" | ||
81 | +echo | ||
82 | + | ||
83 | +_make_test_img 1G | ||
84 | +stat -c "image file size in bytes: %s" "$TEST_IMG_FILE" | ||
85 | + | ||
86 | +echo | ||
87 | +echo "== modified 1G image file (size should be no greater than measured) ==" | ||
88 | +echo | ||
89 | + | ||
90 | +$QEMU_IO --object "$SECRET" --image-opts "$TEST_IMG" -c "write -P 0x51 0x10000 0x400" | _filter_qemu_io | _filter_testdir | ||
91 | +stat -c "image file size in bytes: %s" "$TEST_IMG_FILE" | ||
92 | + | ||
93 | +echo | ||
94 | +echo "== measure preallocation=falloc 1G image file ==" | ||
95 | +echo | ||
96 | + | ||
97 | +$QEMU_IMG measure --object "$SECRET" \ | ||
98 | + -O "$IMGFMT" \ | ||
99 | + -o key-secret=sec0,iter-time=10,preallocation=falloc \ | ||
100 | + --size 1G | ||
101 | + | ||
102 | +echo | ||
103 | +echo "== measure with input image file ==" | ||
104 | +echo | ||
105 | + | ||
106 | +IMGFMT=raw IMGKEYSECRET= IMGOPTS= _make_test_img 1G | _filter_imgfmt | ||
107 | +QEMU_IO_OPTIONS= IMGOPTSSYNTAX= $QEMU_IO -f raw -c "write -P 0x51 0x10000 0x400" "$TEST_IMG_FILE" | _filter_qemu_io | _filter_testdir | ||
108 | +$QEMU_IMG measure --object "$SECRET" \ | ||
109 | + -O "$IMGFMT" \ | ||
110 | + -o key-secret=sec0,iter-time=10 \ | ||
111 | + -f raw \ | ||
112 | + "$TEST_IMG_FILE" | ||
113 | + | ||
114 | +# success, all done | ||
115 | +echo "*** done" | ||
116 | +rm -f $seq.full | ||
117 | +status=0 | ||
118 | diff --git a/tests/qemu-iotests/288.out b/tests/qemu-iotests/288.out | ||
119 | new file mode 100644 | 79 | new file mode 100644 |
120 | index XXXXXXX..XXXXXXX | 80 | index XXXXXXX..XXXXXXX |
121 | --- /dev/null | 81 | --- /dev/null |
122 | +++ b/tests/qemu-iotests/288.out | 82 | +++ b/stubs/blk-exp-close-all.c |
123 | @@ -XXX,XX +XXX,XX @@ | 83 | @@ -XXX,XX +XXX,XX @@ |
124 | +QA output created by 288 | 84 | +#include "qemu/osdep.h" |
125 | +== measure 1G image file == | 85 | +#include "block/export.h" |
126 | + | 86 | + |
127 | +required size: 1075810304 | 87 | +/* Only used in programs that support block exports (libblockdev.fa) */ |
128 | +fully allocated size: 1075810304 | 88 | +void blk_exp_close_all(void) |
129 | + | 89 | +{ |
130 | +== create 1G image file (size should be no greater than measured) == | 90 | +} |
131 | + | 91 | diff --git a/block/export/meson.build b/block/export/meson.build |
132 | +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 | ||
133 | +image file size in bytes: 1075810304 | ||
134 | + | ||
135 | +== modified 1G image file (size should be no greater than measured) == | ||
136 | + | ||
137 | +wrote 1024/1024 bytes at offset 65536 | ||
138 | +1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
139 | +image file size in bytes: 1075810304 | ||
140 | + | ||
141 | +== measure preallocation=falloc 1G image file == | ||
142 | + | ||
143 | +required size: 1075810304 | ||
144 | +fully allocated size: 1075810304 | ||
145 | + | ||
146 | +== measure with input image file == | ||
147 | + | ||
148 | +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 | ||
149 | +wrote 1024/1024 bytes at offset 65536 | ||
150 | +1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
151 | +required size: 1075810304 | ||
152 | +fully allocated size: 1075810304 | ||
153 | +*** done | ||
154 | diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group | ||
155 | index XXXXXXX..XXXXXXX 100644 | 92 | index XXXXXXX..XXXXXXX 100644 |
156 | --- a/tests/qemu-iotests/group | 93 | --- a/block/export/meson.build |
157 | +++ b/tests/qemu-iotests/group | 94 | +++ b/block/export/meson.build |
158 | @@ -XXX,XX +XXX,XX @@ | 95 | @@ -XXX,XX +XXX,XX @@ |
159 | 283 auto quick | 96 | -block_ss.add(files('export.c')) |
160 | 284 rw | 97 | -block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) |
161 | 286 rw quick | 98 | +blockdev_ss.add(files('export.c')) |
162 | +288 quick | 99 | +blockdev_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) |
100 | diff --git a/meson.build b/meson.build | ||
101 | index XXXXXXX..XXXXXXX 100644 | ||
102 | --- a/meson.build | ||
103 | +++ b/meson.build | ||
104 | @@ -XXX,XX +XXX,XX @@ subdir('dump') | ||
105 | |||
106 | block_ss.add(files( | ||
107 | 'block.c', | ||
108 | - 'blockdev-nbd.c', | ||
109 | 'blockjob.c', | ||
110 | 'job.c', | ||
111 | 'qemu-io-cmds.c', | ||
112 | @@ -XXX,XX +XXX,XX @@ subdir('block') | ||
113 | |||
114 | blockdev_ss.add(files( | ||
115 | 'blockdev.c', | ||
116 | + 'blockdev-nbd.c', | ||
117 | 'iothread.c', | ||
118 | 'job-qmp.c', | ||
119 | )) | ||
120 | @@ -XXX,XX +XXX,XX @@ if have_tools | ||
121 | qemu_io = executable('qemu-io', files('qemu-io.c'), | ||
122 | dependencies: [block, qemuutil], install: true) | ||
123 | qemu_nbd = executable('qemu-nbd', files('qemu-nbd.c'), | ||
124 | - dependencies: [block, qemuutil], install: true) | ||
125 | + dependencies: [blockdev, qemuutil], install: true) | ||
126 | |||
127 | subdir('storage-daemon') | ||
128 | subdir('contrib/rdmacm-mux') | ||
129 | diff --git a/nbd/meson.build b/nbd/meson.build | ||
130 | index XXXXXXX..XXXXXXX 100644 | ||
131 | --- a/nbd/meson.build | ||
132 | +++ b/nbd/meson.build | ||
133 | @@ -XXX,XX +XXX,XX @@ | ||
134 | block_ss.add(files( | ||
135 | 'client.c', | ||
136 | 'common.c', | ||
137 | +)) | ||
138 | +blockdev_ss.add(files( | ||
139 | 'server.c', | ||
140 | )) | ||
141 | diff --git a/stubs/meson.build b/stubs/meson.build | ||
142 | index XXXXXXX..XXXXXXX 100644 | ||
143 | --- a/stubs/meson.build | ||
144 | +++ b/stubs/meson.build | ||
145 | @@ -XXX,XX +XXX,XX @@ | ||
146 | stub_ss.add(files('arch_type.c')) | ||
147 | stub_ss.add(files('bdrv-next-monitor-owned.c')) | ||
148 | stub_ss.add(files('blk-commit-all.c')) | ||
149 | +stub_ss.add(files('blk-exp-close-all.c')) | ||
150 | stub_ss.add(files('blockdev-close-all-bdrv-states.c')) | ||
151 | stub_ss.add(files('change-state-handler.c')) | ||
152 | stub_ss.add(files('cmos.c')) | ||
163 | -- | 153 | -- |
164 | 2.24.1 | 154 | 2.26.2 |
165 | 155 | ||
166 | diff view generated by jsdifflib |
1 | From: Stefan Hajnoczi <stefanha@redhat.com> | 1 | Make it possible to specify the iothread where the export will run. By |
---|---|---|---|
2 | 2 | default the block node can be moved to other AioContexts later and the | |
3 | Add qemu-img measure support in the "luks" block driver. | 3 | export will follow. The fixed-iothread option forces strict behavior |
4 | that prevents changing AioContext while the export is active. See the | ||
5 | QAPI docs for details. | ||
4 | 6 | ||
5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | 7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
6 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 8 | Message-id: 20200929125516.186715-5-stefanha@redhat.com |
7 | Message-Id: <20200221112522.1497712-3-stefanha@redhat.com> | 9 | [Fix stray '#' character in block-export.json and add missing "(since: |
8 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 10 | 5.2)" as suggested by Eric Blake. |
11 | --Stefan] | ||
12 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
9 | --- | 13 | --- |
10 | block/crypto.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++ | 14 | qapi/block-export.json | 11 ++++++++++ |
11 | 1 file changed, 62 insertions(+) | 15 | block/export/export.c | 31 +++++++++++++++++++++++++++- |
16 | block/export/vhost-user-blk-server.c | 5 ++++- | ||
17 | nbd/server.c | 2 -- | ||
18 | 4 files changed, 45 insertions(+), 4 deletions(-) | ||
12 | 19 | ||
13 | diff --git a/block/crypto.c b/block/crypto.c | 20 | diff --git a/qapi/block-export.json b/qapi/block-export.json |
14 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/block/crypto.c | 22 | --- a/qapi/block-export.json |
16 | +++ b/block/crypto.c | 23 | +++ b/qapi/block-export.json |
17 | @@ -XXX,XX +XXX,XX @@ static int64_t block_crypto_getlength(BlockDriverState *bs) | 24 | @@ -XXX,XX +XXX,XX @@ |
18 | } | 25 | # export before completion is signalled. (since: 5.2; |
19 | 26 | # default: false) | |
20 | 27 | # | |
21 | +static BlockMeasureInfo *block_crypto_measure(QemuOpts *opts, | 28 | +# @iothread: The name of the iothread object where the export will run. The |
22 | + BlockDriverState *in_bs, | 29 | +# default is to use the thread currently associated with the |
23 | + Error **errp) | 30 | +# block node. (since: 5.2) |
24 | +{ | 31 | +# |
25 | + g_autoptr(QCryptoBlockCreateOptions) create_opts = NULL; | 32 | +# @fixed-iothread: True prevents the block node from being moved to another |
26 | + Error *local_err = NULL; | 33 | +# thread while the export is active. If true and @iothread is |
27 | + BlockMeasureInfo *info; | 34 | +# given, export creation fails if the block node cannot be |
28 | + uint64_t size; | 35 | +# moved to the iothread. The default is false. (since: 5.2) |
29 | + size_t luks_payload_size; | 36 | +# |
30 | + QDict *cryptoopts; | 37 | # Since: 4.2 |
38 | ## | ||
39 | { 'union': 'BlockExportOptions', | ||
40 | 'base': { 'type': 'BlockExportType', | ||
41 | 'id': 'str', | ||
42 | + '*fixed-iothread': 'bool', | ||
43 | + '*iothread': 'str', | ||
44 | 'node-name': 'str', | ||
45 | '*writable': 'bool', | ||
46 | '*writethrough': 'bool' }, | ||
47 | diff --git a/block/export/export.c b/block/export/export.c | ||
48 | index XXXXXXX..XXXXXXX 100644 | ||
49 | --- a/block/export/export.c | ||
50 | +++ b/block/export/export.c | ||
51 | @@ -XXX,XX +XXX,XX @@ | ||
52 | |||
53 | #include "block/block.h" | ||
54 | #include "sysemu/block-backend.h" | ||
55 | +#include "sysemu/iothread.h" | ||
56 | #include "block/export.h" | ||
57 | #include "block/nbd.h" | ||
58 | #include "qapi/error.h" | ||
59 | @@ -XXX,XX +XXX,XX @@ static const BlockExportDriver *blk_exp_find_driver(BlockExportType type) | ||
60 | |||
61 | BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) | ||
62 | { | ||
63 | + bool fixed_iothread = export->has_fixed_iothread && export->fixed_iothread; | ||
64 | const BlockExportDriver *drv; | ||
65 | BlockExport *exp = NULL; | ||
66 | BlockDriverState *bs; | ||
67 | - BlockBackend *blk; | ||
68 | + BlockBackend *blk = NULL; | ||
69 | AioContext *ctx; | ||
70 | uint64_t perm; | ||
71 | int ret; | ||
72 | @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) | ||
73 | ctx = bdrv_get_aio_context(bs); | ||
74 | aio_context_acquire(ctx); | ||
75 | |||
76 | + if (export->has_iothread) { | ||
77 | + IOThread *iothread; | ||
78 | + AioContext *new_ctx; | ||
31 | + | 79 | + |
32 | + /* | 80 | + iothread = iothread_by_id(export->iothread); |
33 | + * Preallocation mode doesn't affect size requirements but we must consume | 81 | + if (!iothread) { |
34 | + * the option. | 82 | + error_setg(errp, "iothread \"%s\" not found", export->iothread); |
35 | + */ | 83 | + goto fail; |
36 | + g_free(qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC)); | ||
37 | + | ||
38 | + size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0); | ||
39 | + | ||
40 | + if (in_bs) { | ||
41 | + int64_t ssize = bdrv_getlength(in_bs); | ||
42 | + | ||
43 | + if (ssize < 0) { | ||
44 | + error_setg_errno(&local_err, -ssize, | ||
45 | + "Unable to get image virtual_size"); | ||
46 | + goto err; | ||
47 | + } | 84 | + } |
48 | + | 85 | + |
49 | + size = ssize; | 86 | + new_ctx = iothread_get_aio_context(iothread); |
87 | + | ||
88 | + ret = bdrv_try_set_aio_context(bs, new_ctx, errp); | ||
89 | + if (ret == 0) { | ||
90 | + aio_context_release(ctx); | ||
91 | + aio_context_acquire(new_ctx); | ||
92 | + ctx = new_ctx; | ||
93 | + } else if (fixed_iothread) { | ||
94 | + goto fail; | ||
95 | + } | ||
50 | + } | 96 | + } |
51 | + | 97 | + |
52 | + cryptoopts = qemu_opts_to_qdict_filtered(opts, NULL, | 98 | /* |
53 | + &block_crypto_create_opts_luks, true); | 99 | * Block exports are used for non-shared storage migration. Make sure |
54 | + qdict_put_str(cryptoopts, "format", "luks"); | 100 | * that BDRV_O_INACTIVE is cleared and the image is ready for write |
55 | + create_opts = block_crypto_create_opts_init(cryptoopts, &local_err); | 101 | @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) |
56 | + qobject_unref(cryptoopts); | 102 | } |
57 | + if (!create_opts) { | 103 | |
58 | + goto err; | 104 | blk = blk_new(ctx, perm, BLK_PERM_ALL); |
105 | + | ||
106 | + if (!fixed_iothread) { | ||
107 | + blk_set_allow_aio_context_change(blk, true); | ||
59 | + } | 108 | + } |
60 | + | 109 | + |
61 | + if (!qcrypto_block_calculate_payload_offset(create_opts, NULL, | 110 | ret = blk_insert_bs(blk, bs, errp); |
62 | + &luks_payload_size, | 111 | if (ret < 0) { |
63 | + &local_err)) { | 112 | goto fail; |
64 | + goto err; | 113 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
65 | + } | 114 | index XXXXXXX..XXXXXXX 100644 |
115 | --- a/block/export/vhost-user-blk-server.c | ||
116 | +++ b/block/export/vhost-user-blk-server.c | ||
117 | @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_blk_iface = { | ||
118 | static void blk_aio_attached(AioContext *ctx, void *opaque) | ||
119 | { | ||
120 | VuBlkExport *vexp = opaque; | ||
66 | + | 121 | + |
67 | + /* | 122 | + vexp->export.ctx = ctx; |
68 | + * Unallocated blocks are still encrypted so allocation status makes no | 123 | vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); |
69 | + * difference to the file size. | 124 | } |
70 | + */ | 125 | |
71 | + info = g_new(BlockMeasureInfo, 1); | 126 | static void blk_aio_detach(void *opaque) |
72 | + info->fully_allocated = luks_payload_size + size; | 127 | { |
73 | + info->required = luks_payload_size + size; | 128 | VuBlkExport *vexp = opaque; |
74 | + return info; | ||
75 | + | 129 | + |
76 | +err: | 130 | vhost_user_server_detach_aio_context(&vexp->vu_server); |
77 | + error_propagate(errp, local_err); | 131 | + vexp->export.ctx = NULL; |
78 | + return NULL; | 132 | } |
79 | +} | 133 | |
80 | + | 134 | static void |
81 | + | 135 | @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, |
82 | static int block_crypto_probe_luks(const uint8_t *buf, | 136 | vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, |
83 | int buf_size, | 137 | logical_block_size); |
84 | const char *filename) { | 138 | |
85 | @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_crypto_luks = { | 139 | - blk_set_allow_aio_context_change(exp->blk, true); |
86 | .bdrv_co_preadv = block_crypto_co_preadv, | 140 | blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, |
87 | .bdrv_co_pwritev = block_crypto_co_pwritev, | 141 | vexp); |
88 | .bdrv_getlength = block_crypto_getlength, | 142 | |
89 | + .bdrv_measure = block_crypto_measure, | 143 | diff --git a/nbd/server.c b/nbd/server.c |
90 | .bdrv_get_info = block_crypto_get_info_luks, | 144 | index XXXXXXX..XXXXXXX 100644 |
91 | .bdrv_get_specific_info = block_crypto_get_specific_info_luks, | 145 | --- a/nbd/server.c |
92 | 146 | +++ b/nbd/server.c | |
147 | @@ -XXX,XX +XXX,XX @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, | ||
148 | return ret; | ||
149 | } | ||
150 | |||
151 | - blk_set_allow_aio_context_change(blk, true); | ||
152 | - | ||
153 | QTAILQ_INIT(&exp->clients); | ||
154 | exp->name = g_strdup(arg->name); | ||
155 | exp->description = g_strdup(arg->description); | ||
93 | -- | 156 | -- |
94 | 2.24.1 | 157 | 2.26.2 |
95 | 158 | ||
96 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | Allow the number of queues to be configured using --export |
---|---|---|---|
2 | vhost-user-blk,num-queues=N. This setting should match the QEMU --device | ||
3 | vhost-user-blk-pci,num-queues=N setting but QEMU vhost-user-blk.c lowers | ||
4 | its own value if the vhost-user-blk backend offers fewer queues than | ||
5 | QEMU. | ||
2 | 6 | ||
3 | Use bdrv_block_status_above to chose effective chunk size and to handle | 7 | The vhost-user-blk-server.c code is already capable of multi-queue. All |
4 | zeroes effectively. | 8 | virtqueue processing runs in the same AioContext. No new locking is |
9 | needed. | ||
5 | 10 | ||
6 | This substitutes checking for just being allocated or not, and drops | 11 | Add the num-queues=N option and set the VIRTIO_BLK_F_MQ feature bit. |
7 | old code path for it. Assistance by backup job is dropped too, as | 12 | Note that the feature bit only announces the presence of the num_queues |
8 | caching block-status information is more difficult than just caching | 13 | configuration space field. It does not promise that there is more than 1 |
9 | is-allocated information in our dirty bitmap, and backup job is not | 14 | virtqueue, so we can set it unconditionally. |
10 | good place for this caching anyway. | ||
11 | 15 | ||
12 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 16 | I tested multi-queue by running a random read fio test with numjobs=4 on |
13 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 17 | an -smp 4 guest. After the benchmark finished the guest /proc/interrupts |
14 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 18 | file showed activity on all 4 virtio-blk MSI-X. The /sys/block/vda/mq/ |
15 | Message-Id: <20200311103004.7649-5-vsementsov@virtuozzo.com> | 19 | directory shows that Linux blk-mq has 4 queues configured. |
16 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 20 | |
21 | An automated test is included in the next commit. | ||
22 | |||
23 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
24 | Acked-by: Markus Armbruster <armbru@redhat.com> | ||
25 | Message-id: 20201001144604.559733-2-stefanha@redhat.com | ||
26 | [Fixed accidental tab characters as suggested by Markus Armbruster | ||
27 | --Stefan] | ||
28 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
17 | --- | 29 | --- |
18 | block/block-copy.c | 73 +++++++++++++++++++++++++++++++++++++--------- | 30 | qapi/block-export.json | 10 +++++++--- |
19 | block/trace-events | 1 + | 31 | block/export/vhost-user-blk-server.c | 24 ++++++++++++++++++------ |
20 | 2 files changed, 61 insertions(+), 13 deletions(-) | 32 | 2 files changed, 25 insertions(+), 9 deletions(-) |
21 | 33 | ||
22 | diff --git a/block/block-copy.c b/block/block-copy.c | 34 | diff --git a/qapi/block-export.json b/qapi/block-export.json |
23 | index XXXXXXX..XXXXXXX 100644 | 35 | index XXXXXXX..XXXXXXX 100644 |
24 | --- a/block/block-copy.c | 36 | --- a/qapi/block-export.json |
25 | +++ b/block/block-copy.c | 37 | +++ b/qapi/block-export.json |
26 | @@ -XXX,XX +XXX,XX @@ void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm) | 38 | @@ -XXX,XX +XXX,XX @@ |
27 | */ | 39 | # SocketAddress types are supported. Passed fds must be UNIX domain |
28 | static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | 40 | # sockets. |
29 | int64_t start, int64_t end, | 41 | # @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. |
30 | - bool *error_is_read) | 42 | +# @num-queues: Number of request virtqueues. Must be greater than 0. Defaults |
31 | + bool zeroes, bool *error_is_read) | 43 | +# to 1. |
44 | # | ||
45 | # Since: 5.2 | ||
46 | ## | ||
47 | { 'struct': 'BlockExportOptionsVhostUserBlk', | ||
48 | - 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } | ||
49 | + 'data': { 'addr': 'SocketAddress', | ||
50 | + '*logical-block-size': 'size', | ||
51 | + '*num-queues': 'uint16'} } | ||
52 | |||
53 | ## | ||
54 | # @NbdServerAddOptions: | ||
55 | @@ -XXX,XX +XXX,XX @@ | ||
56 | { 'union': 'BlockExportOptions', | ||
57 | 'base': { 'type': 'BlockExportType', | ||
58 | 'id': 'str', | ||
59 | - '*fixed-iothread': 'bool', | ||
60 | - '*iothread': 'str', | ||
61 | + '*fixed-iothread': 'bool', | ||
62 | + '*iothread': 'str', | ||
63 | 'node-name': 'str', | ||
64 | '*writable': 'bool', | ||
65 | '*writethrough': 'bool' }, | ||
66 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c | ||
67 | index XXXXXXX..XXXXXXX 100644 | ||
68 | --- a/block/export/vhost-user-blk-server.c | ||
69 | +++ b/block/export/vhost-user-blk-server.c | ||
70 | @@ -XXX,XX +XXX,XX @@ | ||
71 | #include "util/block-helpers.h" | ||
72 | |||
73 | enum { | ||
74 | - VHOST_USER_BLK_MAX_QUEUES = 1, | ||
75 | + VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1, | ||
76 | }; | ||
77 | struct virtio_blk_inhdr { | ||
78 | unsigned char status; | ||
79 | @@ -XXX,XX +XXX,XX @@ static uint64_t vu_blk_get_features(VuDev *dev) | ||
80 | 1ull << VIRTIO_BLK_F_DISCARD | | ||
81 | 1ull << VIRTIO_BLK_F_WRITE_ZEROES | | ||
82 | 1ull << VIRTIO_BLK_F_CONFIG_WCE | | ||
83 | + 1ull << VIRTIO_BLK_F_MQ | | ||
84 | 1ull << VIRTIO_F_VERSION_1 | | ||
85 | 1ull << VIRTIO_RING_F_INDIRECT_DESC | | ||
86 | 1ull << VIRTIO_RING_F_EVENT_IDX | | ||
87 | @@ -XXX,XX +XXX,XX @@ static void blk_aio_detach(void *opaque) | ||
88 | |||
89 | static void | ||
90 | vu_blk_initialize_config(BlockDriverState *bs, | ||
91 | - struct virtio_blk_config *config, uint32_t blk_size) | ||
92 | + struct virtio_blk_config *config, | ||
93 | + uint32_t blk_size, | ||
94 | + uint16_t num_queues) | ||
32 | { | 95 | { |
33 | int ret; | 96 | config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; |
34 | int nbytes = MIN(end, s->len) - start; | 97 | config->blk_size = blk_size; |
35 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | 98 | @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, |
36 | assert(QEMU_IS_ALIGNED(end, s->cluster_size)); | 99 | config->seg_max = 128 - 2; |
37 | assert(end < s->len || end == QEMU_ALIGN_UP(s->len, s->cluster_size)); | 100 | config->min_io_size = 1; |
38 | 101 | config->opt_io_size = 1; | |
39 | + if (zeroes) { | 102 | - config->num_queues = VHOST_USER_BLK_MAX_QUEUES; |
40 | + ret = bdrv_co_pwrite_zeroes(s->target, start, nbytes, s->write_flags & | 103 | + config->num_queues = num_queues; |
41 | + ~BDRV_REQ_WRITE_COMPRESSED); | 104 | config->max_discard_sectors = 32768; |
42 | + if (ret < 0) { | 105 | config->max_discard_seg = 1; |
43 | + trace_block_copy_write_zeroes_fail(s, start, ret); | 106 | config->discard_sector_alignment = config->blk_size >> 9; |
44 | + if (error_is_read) { | 107 | @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, |
45 | + *error_is_read = false; | 108 | BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; |
46 | + } | 109 | Error *local_err = NULL; |
47 | + } | 110 | uint64_t logical_block_size; |
48 | + return ret; | 111 | + uint16_t num_queues = VHOST_USER_BLK_NUM_QUEUES_DEFAULT; |
112 | |||
113 | vexp->writable = opts->writable; | ||
114 | vexp->blkcfg.wce = 0; | ||
115 | @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, | ||
116 | } | ||
117 | vexp->blk_size = logical_block_size; | ||
118 | blk_set_guest_block_size(exp->blk, logical_block_size); | ||
119 | + | ||
120 | + if (vu_opts->has_num_queues) { | ||
121 | + num_queues = vu_opts->num_queues; | ||
122 | + } | ||
123 | + if (num_queues == 0) { | ||
124 | + error_setg(errp, "num-queues must be greater than 0"); | ||
125 | + return -EINVAL; | ||
49 | + } | 126 | + } |
50 | + | 127 | + |
51 | if (s->use_copy_range) { | 128 | vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, |
52 | ret = bdrv_co_copy_range(s->source, start, s->target, start, nbytes, | 129 | - logical_block_size); |
53 | 0, s->write_flags); | 130 | + logical_block_size, num_queues); |
54 | @@ -XXX,XX +XXX,XX @@ out: | 131 | |
55 | return ret; | 132 | blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, |
56 | } | 133 | vexp); |
57 | 134 | ||
58 | +static int block_copy_block_status(BlockCopyState *s, int64_t offset, | 135 | if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, |
59 | + int64_t bytes, int64_t *pnum) | 136 | - VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, |
60 | +{ | 137 | - errp)) { |
61 | + int64_t num; | 138 | + num_queues, &vu_blk_iface, errp)) { |
62 | + BlockDriverState *base; | 139 | blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, |
63 | + int ret; | 140 | blk_aio_detach, vexp); |
64 | + | 141 | return -EADDRNOTAVAIL; |
65 | + if (s->skip_unallocated && s->source->bs->backing) { | ||
66 | + base = s->source->bs->backing->bs; | ||
67 | + } else { | ||
68 | + base = NULL; | ||
69 | + } | ||
70 | + | ||
71 | + ret = bdrv_block_status_above(s->source->bs, base, offset, bytes, &num, | ||
72 | + NULL, NULL); | ||
73 | + if (ret < 0 || num < s->cluster_size) { | ||
74 | + /* | ||
75 | + * On error or if failed to obtain large enough chunk just fallback to | ||
76 | + * copy one cluster. | ||
77 | + */ | ||
78 | + num = s->cluster_size; | ||
79 | + ret = BDRV_BLOCK_ALLOCATED | BDRV_BLOCK_DATA; | ||
80 | + } else if (offset + num == s->len) { | ||
81 | + num = QEMU_ALIGN_UP(num, s->cluster_size); | ||
82 | + } else { | ||
83 | + num = QEMU_ALIGN_DOWN(num, s->cluster_size); | ||
84 | + } | ||
85 | + | ||
86 | + *pnum = num; | ||
87 | + return ret; | ||
88 | +} | ||
89 | + | ||
90 | /* | ||
91 | * Check if the cluster starting at offset is allocated or not. | ||
92 | * return via pnum the number of contiguous clusters sharing this allocation. | ||
93 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
94 | { | ||
95 | int ret = 0; | ||
96 | int64_t end = bytes + start; /* bytes */ | ||
97 | - int64_t status_bytes; | ||
98 | BlockCopyInFlightReq req; | ||
99 | |||
100 | /* | ||
101 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
102 | block_copy_inflight_req_begin(s, &req, start, end); | ||
103 | |||
104 | while (start < end) { | ||
105 | - int64_t next_zero, chunk_end; | ||
106 | + int64_t next_zero, chunk_end, status_bytes; | ||
107 | |||
108 | if (!bdrv_dirty_bitmap_get(s->copy_bitmap, start)) { | ||
109 | trace_block_copy_skip(s, start); | ||
110 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
111 | chunk_end = next_zero; | ||
112 | } | ||
113 | |||
114 | - if (s->skip_unallocated) { | ||
115 | - ret = block_copy_reset_unallocated(s, start, &status_bytes); | ||
116 | - if (ret == 0) { | ||
117 | - trace_block_copy_skip_range(s, start, status_bytes); | ||
118 | - start += status_bytes; | ||
119 | - continue; | ||
120 | - } | ||
121 | - /* Clamp to known allocated region */ | ||
122 | - chunk_end = MIN(chunk_end, start + status_bytes); | ||
123 | + ret = block_copy_block_status(s, start, chunk_end - start, | ||
124 | + &status_bytes); | ||
125 | + if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) { | ||
126 | + bdrv_reset_dirty_bitmap(s->copy_bitmap, start, status_bytes); | ||
127 | + progress_set_remaining(s->progress, | ||
128 | + bdrv_get_dirty_count(s->copy_bitmap) + | ||
129 | + s->in_flight_bytes); | ||
130 | + trace_block_copy_skip_range(s, start, status_bytes); | ||
131 | + start += status_bytes; | ||
132 | + continue; | ||
133 | } | ||
134 | |||
135 | + chunk_end = MIN(chunk_end, start + status_bytes); | ||
136 | + | ||
137 | trace_block_copy_process(s, start); | ||
138 | |||
139 | bdrv_reset_dirty_bitmap(s->copy_bitmap, start, chunk_end - start); | ||
140 | s->in_flight_bytes += chunk_end - start; | ||
141 | |||
142 | co_get_from_shres(s->mem, chunk_end - start); | ||
143 | - ret = block_copy_do_copy(s, start, chunk_end, error_is_read); | ||
144 | + ret = block_copy_do_copy(s, start, chunk_end, ret & BDRV_BLOCK_ZERO, | ||
145 | + error_is_read); | ||
146 | co_put_to_shres(s->mem, chunk_end - start); | ||
147 | s->in_flight_bytes -= chunk_end - start; | ||
148 | if (ret < 0) { | ||
149 | diff --git a/block/trace-events b/block/trace-events | ||
150 | index XXXXXXX..XXXXXXX 100644 | ||
151 | --- a/block/trace-events | ||
152 | +++ b/block/trace-events | ||
153 | @@ -XXX,XX +XXX,XX @@ block_copy_process(void *bcs, int64_t start) "bcs %p start %"PRId64 | ||
154 | block_copy_copy_range_fail(void *bcs, int64_t start, int ret) "bcs %p start %"PRId64" ret %d" | ||
155 | block_copy_read_fail(void *bcs, int64_t start, int ret) "bcs %p start %"PRId64" ret %d" | ||
156 | block_copy_write_fail(void *bcs, int64_t start, int ret) "bcs %p start %"PRId64" ret %d" | ||
157 | +block_copy_write_zeroes_fail(void *bcs, int64_t start, int ret) "bcs %p start %"PRId64" ret %d" | ||
158 | |||
159 | # ../blockdev.c | ||
160 | qmp_block_job_cancel(void *job) "job %p" | ||
161 | -- | 142 | -- |
162 | 2.24.1 | 143 | 2.26.2 |
163 | 144 | ||
164 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Currently, block_copy operation lock the whole requested region. But | 3 | bdrv_co_block_status_above has several design problems with handling |
4 | there is no reason to lock clusters, which are already copied, it will | 4 | short backing files: |
5 | disturb other parallel block_copy requests for no reason. | ||
6 | 5 | ||
7 | Let's instead do the following: | 6 | 1. With want_zeros=true, it may return ret with BDRV_BLOCK_ZERO but |
7 | without BDRV_BLOCK_ALLOCATED flag, when actually short backing file | ||
8 | which produces these after-EOF zeros is inside requested backing | ||
9 | sequence. | ||
8 | 10 | ||
9 | Lock only sub-region, which we are going to operate on. Then, after | 11 | 2. With want_zero=false, it may return pnum=0 prior to actual EOF, |
10 | copying all dirty sub-regions, we should wait for intersecting | 12 | because of EOF of short backing file. |
11 | requests block-copy, if they failed, we should retry these new dirty | 13 | |
12 | clusters. | 14 | Fix these things, making logic about short backing files clearer. |
15 | |||
16 | With fixed bdrv_block_status_above we also have to improve is_zero in | ||
17 | qcow2 code, otherwise iotest 154 will fail, because with this patch we | ||
18 | stop to merge zeros of different types (produced by fully unallocated | ||
19 | in the whole backing chain regions vs produced by short backing files). | ||
20 | |||
21 | Note also, that this patch leaves for another day the general problem | ||
22 | around block-status: misuse of BDRV_BLOCK_ALLOCATED as is-fs-allocated | ||
23 | vs go-to-backing. | ||
13 | 24 | ||
14 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 25 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
15 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 26 | Reviewed-by: Alberto Garcia <berto@igalia.com> |
16 | Message-Id: <20200311103004.7649-9-vsementsov@virtuozzo.com> | 27 | Reviewed-by: Eric Blake <eblake@redhat.com> |
17 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 28 | Message-id: 20200924194003.22080-2-vsementsov@virtuozzo.com |
29 | [Fix s/comes/come/ as suggested by Eric Blake | ||
30 | --Stefan] | ||
31 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
18 | --- | 32 | --- |
19 | block/block-copy.c | 129 ++++++++++++++++++++++++++++++++++++--------- | 33 | block/io.c | 68 ++++++++++++++++++++++++++++++++++++++++----------- |
20 | 1 file changed, 105 insertions(+), 24 deletions(-) | 34 | block/qcow2.c | 16 ++++++++++-- |
35 | 2 files changed, 68 insertions(+), 16 deletions(-) | ||
21 | 36 | ||
22 | diff --git a/block/block-copy.c b/block/block-copy.c | 37 | diff --git a/block/io.c b/block/io.c |
23 | index XXXXXXX..XXXXXXX 100644 | 38 | index XXXXXXX..XXXXXXX 100644 |
24 | --- a/block/block-copy.c | 39 | --- a/block/io.c |
25 | +++ b/block/block-copy.c | 40 | +++ b/block/io.c |
26 | @@ -XXX,XX +XXX,XX @@ static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s, | 41 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
27 | return NULL; | 42 | int64_t *map, |
28 | } | 43 | BlockDriverState **file) |
29 | |||
30 | -static void coroutine_fn block_copy_wait_inflight_reqs(BlockCopyState *s, | ||
31 | - int64_t offset, | ||
32 | - int64_t bytes) | ||
33 | +/* | ||
34 | + * If there are no intersecting requests return false. Otherwise, wait for the | ||
35 | + * first found intersecting request to finish and return true. | ||
36 | + */ | ||
37 | +static bool coroutine_fn block_copy_wait_one(BlockCopyState *s, int64_t offset, | ||
38 | + int64_t bytes) | ||
39 | { | 44 | { |
40 | - BlockCopyInFlightReq *req; | 45 | + int ret; |
41 | + BlockCopyInFlightReq *req = find_conflicting_inflight_req(s, offset, bytes); | 46 | BlockDriverState *p; |
42 | 47 | - int ret = 0; | |
43 | - while ((req = find_conflicting_inflight_req(s, offset, bytes))) { | 48 | - bool first = true; |
44 | - qemu_co_queue_wait(&req->wait_queue, NULL); | 49 | + int64_t eof = 0; |
45 | + if (!req) { | 50 | |
46 | + return false; | 51 | assert(bs != base); |
47 | } | 52 | - for (p = bs; p != base; p = bdrv_filter_or_cow_bs(p)) { |
48 | + | 53 | + |
49 | + qemu_co_queue_wait(&req->wait_queue, NULL); | 54 | + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); |
50 | + | 55 | + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { |
51 | + return true; | 56 | + return ret; |
52 | } | ||
53 | |||
54 | +/* Called only on full-dirty region */ | ||
55 | static void block_copy_inflight_req_begin(BlockCopyState *s, | ||
56 | BlockCopyInFlightReq *req, | ||
57 | int64_t offset, int64_t bytes) | ||
58 | { | ||
59 | + assert(!find_conflicting_inflight_req(s, offset, bytes)); | ||
60 | + | ||
61 | + bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes); | ||
62 | + s->in_flight_bytes += bytes; | ||
63 | + | ||
64 | req->offset = offset; | ||
65 | req->bytes = bytes; | ||
66 | qemu_co_queue_init(&req->wait_queue); | ||
67 | QLIST_INSERT_HEAD(&s->inflight_reqs, req, list); | ||
68 | } | ||
69 | |||
70 | -static void coroutine_fn block_copy_inflight_req_end(BlockCopyInFlightReq *req) | ||
71 | +/* | ||
72 | + * block_copy_inflight_req_shrink | ||
73 | + * | ||
74 | + * Drop the tail of the request to be handled later. Set dirty bits back and | ||
75 | + * wake up all requests waiting for us (may be some of them are not intersecting | ||
76 | + * with shrunk request) | ||
77 | + */ | ||
78 | +static void coroutine_fn block_copy_inflight_req_shrink(BlockCopyState *s, | ||
79 | + BlockCopyInFlightReq *req, int64_t new_bytes) | ||
80 | { | ||
81 | + if (new_bytes == req->bytes) { | ||
82 | + return; | ||
83 | + } | 57 | + } |
84 | + | 58 | + |
85 | + assert(new_bytes > 0 && new_bytes < req->bytes); | 59 | + if (ret & BDRV_BLOCK_EOF) { |
60 | + eof = offset + *pnum; | ||
61 | + } | ||
86 | + | 62 | + |
87 | + s->in_flight_bytes -= req->bytes - new_bytes; | 63 | + assert(*pnum <= bytes); |
88 | + bdrv_set_dirty_bitmap(s->copy_bitmap, | 64 | + bytes = *pnum; |
89 | + req->offset + new_bytes, req->bytes - new_bytes); | ||
90 | + | 65 | + |
91 | + req->bytes = new_bytes; | 66 | + for (p = bdrv_filter_or_cow_bs(bs); p != base; |
92 | + qemu_co_queue_restart_all(&req->wait_queue); | 67 | + p = bdrv_filter_or_cow_bs(p)) |
93 | +} | 68 | + { |
94 | + | 69 | ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, |
95 | +static void coroutine_fn block_copy_inflight_req_end(BlockCopyState *s, | 70 | file); |
96 | + BlockCopyInFlightReq *req, | ||
97 | + int ret) | ||
98 | +{ | ||
99 | + s->in_flight_bytes -= req->bytes; | ||
100 | + if (ret < 0) { | ||
101 | + bdrv_set_dirty_bitmap(s->copy_bitmap, req->offset, req->bytes); | ||
102 | + } | ||
103 | QLIST_REMOVE(req, list); | ||
104 | qemu_co_queue_restart_all(&req->wait_queue); | ||
105 | } | ||
106 | @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, | ||
107 | return ret; | ||
108 | } | ||
109 | |||
110 | -int coroutine_fn block_copy(BlockCopyState *s, | ||
111 | - int64_t offset, int64_t bytes, | ||
112 | - bool *error_is_read) | ||
113 | +/* | ||
114 | + * block_copy_dirty_clusters | ||
115 | + * | ||
116 | + * Copy dirty clusters in @offset/@bytes range. | ||
117 | + * Returns 1 if dirty clusters found and successfully copied, 0 if no dirty | ||
118 | + * clusters found and -errno on failure. | ||
119 | + */ | ||
120 | +static int coroutine_fn block_copy_dirty_clusters(BlockCopyState *s, | ||
121 | + int64_t offset, int64_t bytes, | ||
122 | + bool *error_is_read) | ||
123 | { | ||
124 | int ret = 0; | ||
125 | - BlockCopyInFlightReq req; | ||
126 | + bool found_dirty = false; | ||
127 | |||
128 | /* | ||
129 | * block_copy() user is responsible for keeping source and target in same | ||
130 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
131 | assert(QEMU_IS_ALIGNED(offset, s->cluster_size)); | ||
132 | assert(QEMU_IS_ALIGNED(bytes, s->cluster_size)); | ||
133 | |||
134 | - block_copy_wait_inflight_reqs(s, offset, bytes); | ||
135 | - block_copy_inflight_req_begin(s, &req, offset, bytes); | ||
136 | - | ||
137 | while (bytes) { | ||
138 | + BlockCopyInFlightReq req; | ||
139 | int64_t next_zero, cur_bytes, status_bytes; | ||
140 | |||
141 | if (!bdrv_dirty_bitmap_get(s->copy_bitmap, offset)) { | ||
142 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
143 | continue; /* already copied */ | ||
144 | } | ||
145 | |||
146 | + found_dirty = true; | ||
147 | + | ||
148 | cur_bytes = MIN(bytes, s->copy_size); | ||
149 | |||
150 | next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, offset, | ||
151 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
152 | assert(next_zero < offset + cur_bytes); /* no need to do MIN() */ | ||
153 | cur_bytes = next_zero - offset; | ||
154 | } | ||
155 | + block_copy_inflight_req_begin(s, &req, offset, cur_bytes); | ||
156 | |||
157 | ret = block_copy_block_status(s, offset, cur_bytes, &status_bytes); | ||
158 | + assert(ret >= 0); /* never fail */ | ||
159 | + cur_bytes = MIN(cur_bytes, status_bytes); | ||
160 | + block_copy_inflight_req_shrink(s, &req, cur_bytes); | ||
161 | if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) { | ||
162 | - bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, status_bytes); | ||
163 | + block_copy_inflight_req_end(s, &req, 0); | ||
164 | progress_set_remaining(s->progress, | ||
165 | bdrv_get_dirty_count(s->copy_bitmap) + | ||
166 | s->in_flight_bytes); | ||
167 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
168 | continue; | ||
169 | } | ||
170 | |||
171 | - cur_bytes = MIN(cur_bytes, status_bytes); | ||
172 | - | ||
173 | trace_block_copy_process(s, offset); | ||
174 | |||
175 | - bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, cur_bytes); | ||
176 | - s->in_flight_bytes += cur_bytes; | ||
177 | - | ||
178 | co_get_from_shres(s->mem, cur_bytes); | ||
179 | ret = block_copy_do_copy(s, offset, cur_bytes, ret & BDRV_BLOCK_ZERO, | ||
180 | error_is_read); | ||
181 | co_put_to_shres(s->mem, cur_bytes); | ||
182 | - s->in_flight_bytes -= cur_bytes; | ||
183 | + block_copy_inflight_req_end(s, &req, ret); | ||
184 | if (ret < 0) { | 71 | if (ret < 0) { |
185 | - bdrv_set_dirty_bitmap(s->copy_bitmap, offset, cur_bytes); | ||
186 | - break; | 72 | - break; |
187 | + return ret; | 73 | + return ret; |
188 | } | 74 | } |
189 | 75 | - if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { | |
190 | progress_work_done(s->progress, cur_bytes); | 76 | + if (*pnum == 0) { |
191 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | 77 | /* |
192 | bytes -= cur_bytes; | 78 | - * Reading beyond the end of the file continues to read |
193 | } | 79 | - * zeroes, but we can only widen the result to the |
194 | 80 | - * unallocated length we learned from an earlier | |
195 | - block_copy_inflight_req_end(&req); | 81 | - * iteration. |
196 | + return found_dirty; | 82 | + * The top layer deferred to this layer, and because this layer is |
197 | +} | 83 | + * short, any zeroes that we synthesize beyond EOF behave as if they |
198 | + | 84 | + * were allocated at this layer. |
199 | +/* | 85 | + * |
200 | + * block_copy | 86 | + * We don't include BDRV_BLOCK_EOF into ret, as upper layer may be |
201 | + * | 87 | + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see |
202 | + * Copy requested region, accordingly to dirty bitmap. | 88 | + * below. |
203 | + * Collaborate with parallel block_copy requests: if they succeed it will help | 89 | */ |
204 | + * us. If they fail, we will retry not-copied regions. So, if we return error, | 90 | + assert(ret & BDRV_BLOCK_EOF); |
205 | + * it means that some I/O operation failed in context of _this_ block_copy call, | 91 | *pnum = bytes; |
206 | + * not some parallel operation. | 92 | + if (file) { |
207 | + */ | 93 | + *file = p; |
208 | +int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, | 94 | + } |
209 | + bool *error_is_read) | 95 | + ret = BDRV_BLOCK_ZERO | BDRV_BLOCK_ALLOCATED; |
210 | +{ | 96 | + break; |
211 | + int ret; | 97 | } |
212 | + | 98 | - if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { |
213 | + do { | 99 | + if (ret & BDRV_BLOCK_ALLOCATED) { |
214 | + ret = block_copy_dirty_clusters(s, offset, bytes, error_is_read); | 100 | + /* |
215 | + | 101 | + * We've found the node and the status, we must break. |
216 | + if (ret == 0) { | 102 | + * |
217 | + ret = block_copy_wait_one(s, offset, bytes); | 103 | + * Drop BDRV_BLOCK_EOF, as it's not for upper layer, which may be |
218 | + } | 104 | + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see |
105 | + * below. | ||
106 | + */ | ||
107 | + ret &= ~BDRV_BLOCK_EOF; | ||
108 | break; | ||
109 | } | ||
110 | - /* [offset, pnum] unallocated on this layer, which could be only | ||
111 | - * the first part of [offset, bytes]. */ | ||
112 | - bytes = MIN(bytes, *pnum); | ||
113 | - first = false; | ||
219 | + | 114 | + |
220 | + /* | 115 | + /* |
221 | + * We retry in two cases: | 116 | + * OK, [offset, offset + *pnum) region is unallocated on this layer, |
222 | + * 1. Some progress done | 117 | + * let's continue the diving. |
223 | + * Something was copied, which means that there were yield points | ||
224 | + * and some new dirty bits may have appeared (due to failed parallel | ||
225 | + * block-copy requests). | ||
226 | + * 2. We have waited for some intersecting block-copy request | ||
227 | + * It may have failed and produced new dirty bits. | ||
228 | + */ | 118 | + */ |
229 | + } while (ret > 0); | 119 | + assert(*pnum <= bytes); |
230 | 120 | + bytes = *pnum; | |
121 | + } | ||
122 | + | ||
123 | + if (offset + *pnum == eof) { | ||
124 | + ret |= BDRV_BLOCK_EOF; | ||
125 | } | ||
126 | + | ||
231 | return ret; | 127 | return ret; |
232 | } | 128 | } |
129 | |||
130 | diff --git a/block/qcow2.c b/block/qcow2.c | ||
131 | index XXXXXXX..XXXXXXX 100644 | ||
132 | --- a/block/qcow2.c | ||
133 | +++ b/block/qcow2.c | ||
134 | @@ -XXX,XX +XXX,XX @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) | ||
135 | if (!bytes) { | ||
136 | return true; | ||
137 | } | ||
138 | - res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); | ||
139 | - return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; | ||
140 | + | ||
141 | + /* | ||
142 | + * bdrv_block_status_above doesn't merge different types of zeros, for | ||
143 | + * example, zeros which come from the region which is unallocated in | ||
144 | + * the whole backing chain, and zeros which come because of a short | ||
145 | + * backing file. So, we need a loop. | ||
146 | + */ | ||
147 | + do { | ||
148 | + res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); | ||
149 | + offset += nr; | ||
150 | + bytes -= nr; | ||
151 | + } while (res >= 0 && (res & BDRV_BLOCK_ZERO) && nr && bytes); | ||
152 | + | ||
153 | + return res >= 0 && (res & BDRV_BLOCK_ZERO) && bytes == 0; | ||
154 | } | ||
155 | |||
156 | static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, | ||
233 | -- | 157 | -- |
234 | 2.24.1 | 158 | 2.26.2 |
235 | 159 | ||
236 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Assume we have two regions, A and B, and region B is in-flight now, | 3 | In order to reuse bdrv_common_block_status_above in |
4 | region A is not yet touched, but it is unallocated and should be | 4 | bdrv_is_allocated_above, let's support include_base parameter. |
5 | skipped. | ||
6 | 5 | ||
7 | Correspondingly, as progress we have | 6 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
7 | Reviewed-by: Alberto Garcia <berto@igalia.com> | ||
8 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
9 | Message-id: 20200924194003.22080-3-vsementsov@virtuozzo.com | ||
10 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
11 | --- | ||
12 | block/coroutines.h | 2 ++ | ||
13 | block/io.c | 21 ++++++++++++++------- | ||
14 | 2 files changed, 16 insertions(+), 7 deletions(-) | ||
8 | 15 | ||
9 | total = A + B | 16 | diff --git a/block/coroutines.h b/block/coroutines.h |
10 | current = 0 | ||
11 | |||
12 | If we reset unallocated region A and call progress_reset_callback, | ||
13 | it will calculate 0 bytes dirty in the bitmap and call | ||
14 | job_progress_set_remaining, which will set | ||
15 | |||
16 | total = current + 0 = 0 + 0 = 0 | ||
17 | |||
18 | So, B bytes are actually removed from total accounting. When job | ||
19 | finishes we'll have | ||
20 | |||
21 | total = 0 | ||
22 | current = B | ||
23 | |||
24 | , which doesn't sound good. | ||
25 | |||
26 | This is because we didn't considered in-flight bytes, actually when | ||
27 | calculating remaining, we should have set (in_flight + dirty_bytes) | ||
28 | as remaining, not only dirty_bytes. | ||
29 | |||
30 | To fix it, let's refactor progress calculation, moving it to block-copy | ||
31 | itself instead of fixing callback. And, of course, track in_flight | ||
32 | bytes count. | ||
33 | |||
34 | We still have to keep one callback, to maintain backup job bytes_read | ||
35 | calculation, but it will go on soon, when we turn the whole backup | ||
36 | process into one block_copy call. | ||
37 | |||
38 | Cc: qemu-stable@nongnu.org | ||
39 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
40 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | ||
41 | Message-Id: <20200311103004.7649-3-vsementsov@virtuozzo.com> | ||
42 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
43 | --- | ||
44 | block/backup.c | 13 ++----------- | ||
45 | block/block-copy.c | 16 ++++++++++++---- | ||
46 | include/block/block-copy.h | 15 +++++---------- | ||
47 | 3 files changed, 19 insertions(+), 25 deletions(-) | ||
48 | |||
49 | diff --git a/block/backup.c b/block/backup.c | ||
50 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
51 | --- a/block/backup.c | 18 | --- a/block/coroutines.h |
52 | +++ b/block/backup.c | 19 | +++ b/block/coroutines.h |
53 | @@ -XXX,XX +XXX,XX @@ static void backup_progress_bytes_callback(int64_t bytes, void *opaque) | 20 | @@ -XXX,XX +XXX,XX @@ bdrv_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, |
54 | BackupBlockJob *s = opaque; | 21 | int coroutine_fn |
55 | 22 | bdrv_co_common_block_status_above(BlockDriverState *bs, | |
56 | s->bytes_read += bytes; | 23 | BlockDriverState *base, |
57 | - job_progress_update(&s->common.job, bytes); | 24 | + bool include_base, |
58 | -} | 25 | bool want_zero, |
59 | - | 26 | int64_t offset, |
60 | -static void backup_progress_reset_callback(void *opaque) | 27 | int64_t bytes, |
61 | -{ | 28 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
62 | - BackupBlockJob *s = opaque; | 29 | int generated_co_wrapper |
63 | - uint64_t estimate = bdrv_get_dirty_count(s->bcs->copy_bitmap); | 30 | bdrv_common_block_status_above(BlockDriverState *bs, |
64 | - | 31 | BlockDriverState *base, |
65 | - job_progress_set_remaining(&s->common.job, estimate); | 32 | + bool include_base, |
66 | } | 33 | bool want_zero, |
67 | 34 | int64_t offset, | |
68 | static int coroutine_fn backup_do_cow(BackupBlockJob *job, | 35 | int64_t bytes, |
69 | @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, | 36 | diff --git a/block/io.c b/block/io.c |
70 | job->cluster_size = cluster_size; | ||
71 | job->len = len; | ||
72 | |||
73 | - block_copy_set_callbacks(bcs, backup_progress_bytes_callback, | ||
74 | - backup_progress_reset_callback, job); | ||
75 | + block_copy_set_progress_callback(bcs, backup_progress_bytes_callback, job); | ||
76 | + block_copy_set_progress_meter(bcs, &job->common.job.progress); | ||
77 | |||
78 | /* Required permissions are already taken by backup-top target */ | ||
79 | block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL, | ||
80 | diff --git a/block/block-copy.c b/block/block-copy.c | ||
81 | index XXXXXXX..XXXXXXX 100644 | 37 | index XXXXXXX..XXXXXXX 100644 |
82 | --- a/block/block-copy.c | 38 | --- a/block/io.c |
83 | +++ b/block/block-copy.c | 39 | +++ b/block/io.c |
84 | @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, | 40 | @@ -XXX,XX +XXX,XX @@ early_out: |
85 | return s; | 41 | int coroutine_fn |
86 | } | 42 | bdrv_co_common_block_status_above(BlockDriverState *bs, |
87 | 43 | BlockDriverState *base, | |
88 | -void block_copy_set_callbacks( | 44 | + bool include_base, |
89 | +void block_copy_set_progress_callback( | 45 | bool want_zero, |
90 | BlockCopyState *s, | 46 | int64_t offset, |
91 | ProgressBytesCallbackFunc progress_bytes_callback, | 47 | int64_t bytes, |
92 | - ProgressResetCallbackFunc progress_reset_callback, | 48 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
93 | void *progress_opaque) | 49 | BlockDriverState *p; |
94 | { | 50 | int64_t eof = 0; |
95 | s->progress_bytes_callback = progress_bytes_callback; | 51 | |
96 | - s->progress_reset_callback = progress_reset_callback; | 52 | - assert(bs != base); |
97 | s->progress_opaque = progress_opaque; | 53 | + assert(include_base || bs != base); |
98 | } | 54 | + assert(!include_base || base); /* Can't include NULL base */ |
99 | 55 | ||
100 | +void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm) | 56 | ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); |
101 | +{ | 57 | - if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { |
102 | + s->progress = pm; | 58 | + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { |
103 | +} | 59 | return ret; |
104 | + | ||
105 | /* | ||
106 | * block_copy_do_copy | ||
107 | * | ||
108 | @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, | ||
109 | |||
110 | if (!ret) { | ||
111 | bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes); | ||
112 | - s->progress_reset_callback(s->progress_opaque); | ||
113 | + progress_set_remaining(s->progress, | ||
114 | + bdrv_get_dirty_count(s->copy_bitmap) + | ||
115 | + s->in_flight_bytes); | ||
116 | } | 60 | } |
117 | 61 | ||
118 | *count = bytes; | 62 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
119 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | 63 | assert(*pnum <= bytes); |
120 | trace_block_copy_process(s, start); | 64 | bytes = *pnum; |
121 | 65 | ||
122 | bdrv_reset_dirty_bitmap(s->copy_bitmap, start, chunk_end - start); | 66 | - for (p = bdrv_filter_or_cow_bs(bs); p != base; |
123 | + s->in_flight_bytes += chunk_end - start; | 67 | + for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base; |
124 | 68 | p = bdrv_filter_or_cow_bs(p)) | |
125 | co_get_from_shres(s->mem, chunk_end - start); | 69 | { |
126 | ret = block_copy_do_copy(s, start, chunk_end, error_is_read); | 70 | ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, |
127 | co_put_to_shres(s->mem, chunk_end - start); | 71 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
128 | + s->in_flight_bytes -= chunk_end - start; | ||
129 | if (ret < 0) { | ||
130 | bdrv_set_dirty_bitmap(s->copy_bitmap, start, chunk_end - start); | ||
131 | break; | 72 | break; |
132 | } | 73 | } |
133 | 74 | ||
134 | + progress_work_done(s->progress, chunk_end - start); | 75 | + if (p == base) { |
135 | s->progress_bytes_callback(chunk_end - start, s->progress_opaque); | 76 | + assert(include_base); |
136 | start = chunk_end; | 77 | + break; |
137 | ret = 0; | 78 | + } |
138 | diff --git a/include/block/block-copy.h b/include/block/block-copy.h | ||
139 | index XXXXXXX..XXXXXXX 100644 | ||
140 | --- a/include/block/block-copy.h | ||
141 | +++ b/include/block/block-copy.h | ||
142 | @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyInFlightReq { | ||
143 | } BlockCopyInFlightReq; | ||
144 | |||
145 | typedef void (*ProgressBytesCallbackFunc)(int64_t bytes, void *opaque); | ||
146 | -typedef void (*ProgressResetCallbackFunc)(void *opaque); | ||
147 | typedef struct BlockCopyState { | ||
148 | /* | ||
149 | * BdrvChild objects are not owned or managed by block-copy. They are | ||
150 | @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyState { | ||
151 | BdrvChild *source; | ||
152 | BdrvChild *target; | ||
153 | BdrvDirtyBitmap *copy_bitmap; | ||
154 | + int64_t in_flight_bytes; | ||
155 | int64_t cluster_size; | ||
156 | bool use_copy_range; | ||
157 | int64_t copy_size; | ||
158 | @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyState { | ||
159 | */ | ||
160 | bool skip_unallocated; | ||
161 | |||
162 | + ProgressMeter *progress; | ||
163 | /* progress_bytes_callback: called when some copying progress is done. */ | ||
164 | ProgressBytesCallbackFunc progress_bytes_callback; | ||
165 | - | ||
166 | - /* | ||
167 | - * progress_reset_callback: called when some bytes reset from copy_bitmap | ||
168 | - * (see @skip_unallocated above). The callee is assumed to recalculate how | ||
169 | - * many bytes remain based on the dirty bit count of copy_bitmap. | ||
170 | - */ | ||
171 | - ProgressResetCallbackFunc progress_reset_callback; | ||
172 | void *progress_opaque; | ||
173 | |||
174 | SharedResource *mem; | ||
175 | @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, | ||
176 | BdrvRequestFlags write_flags, | ||
177 | Error **errp); | ||
178 | |||
179 | -void block_copy_set_callbacks( | ||
180 | +void block_copy_set_progress_callback( | ||
181 | BlockCopyState *s, | ||
182 | ProgressBytesCallbackFunc progress_bytes_callback, | ||
183 | - ProgressResetCallbackFunc progress_reset_callback, | ||
184 | void *progress_opaque); | ||
185 | |||
186 | +void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm); | ||
187 | + | 79 | + |
188 | void block_copy_state_free(BlockCopyState *s); | 80 | /* |
189 | 81 | * OK, [offset, offset + *pnum) region is unallocated on this layer, | |
190 | int64_t block_copy_reset_unallocated(BlockCopyState *s, | 82 | * let's continue the diving. |
83 | @@ -XXX,XX +XXX,XX @@ int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, | ||
84 | int64_t offset, int64_t bytes, int64_t *pnum, | ||
85 | int64_t *map, BlockDriverState **file) | ||
86 | { | ||
87 | - return bdrv_common_block_status_above(bs, base, true, offset, bytes, | ||
88 | + return bdrv_common_block_status_above(bs, base, false, true, offset, bytes, | ||
89 | pnum, map, file); | ||
90 | } | ||
91 | |||
92 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, | ||
93 | int ret; | ||
94 | int64_t dummy; | ||
95 | |||
96 | - ret = bdrv_common_block_status_above(bs, bdrv_filter_or_cow_bs(bs), false, | ||
97 | - offset, bytes, pnum ? pnum : &dummy, | ||
98 | - NULL, NULL); | ||
99 | + ret = bdrv_common_block_status_above(bs, bs, true, false, offset, | ||
100 | + bytes, pnum ? pnum : &dummy, NULL, | ||
101 | + NULL); | ||
102 | if (ret < 0) { | ||
103 | return ret; | ||
104 | } | ||
191 | -- | 105 | -- |
192 | 2.24.1 | 106 | 2.26.2 |
193 | 107 | ||
194 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Split find_conflicting_inflight_req to be used separately. | 3 | We are going to reuse bdrv_common_block_status_above in |
4 | bdrv_is_allocated_above. bdrv_is_allocated_above may be called with | ||
5 | include_base == false and still bs == base (for ex. from img_rebase()). | ||
6 | |||
7 | So, support this corner case. | ||
4 | 8 | ||
5 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 9 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
6 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 10 | Reviewed-by: Kevin Wolf <kwolf@redhat.com> |
7 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 11 | Reviewed-by: Eric Blake <eblake@redhat.com> |
8 | Message-Id: <20200311103004.7649-6-vsementsov@virtuozzo.com> | 12 | Reviewed-by: Alberto Garcia <berto@igalia.com> |
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 13 | Message-id: 20200924194003.22080-4-vsementsov@virtuozzo.com |
14 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | --- | 15 | --- |
11 | block/block-copy.c | 31 +++++++++++++++++++------------ | 16 | block/io.c | 6 +++++- |
12 | 1 file changed, 19 insertions(+), 12 deletions(-) | 17 | 1 file changed, 5 insertions(+), 1 deletion(-) |
13 | 18 | ||
14 | diff --git a/block/block-copy.c b/block/block-copy.c | 19 | diff --git a/block/io.c b/block/io.c |
15 | index XXXXXXX..XXXXXXX 100644 | 20 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/block/block-copy.c | 21 | --- a/block/io.c |
17 | +++ b/block/block-copy.c | 22 | +++ b/block/io.c |
18 | @@ -XXX,XX +XXX,XX @@ | 23 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
19 | #define BLOCK_COPY_MAX_BUFFER (1 * MiB) | 24 | BlockDriverState *p; |
20 | #define BLOCK_COPY_MAX_MEM (128 * MiB) | 25 | int64_t eof = 0; |
21 | 26 | ||
22 | +static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s, | 27 | - assert(include_base || bs != base); |
23 | + int64_t start, | 28 | assert(!include_base || base); /* Can't include NULL base */ |
24 | + int64_t end) | 29 | |
25 | +{ | 30 | + if (!include_base && bs == base) { |
26 | + BlockCopyInFlightReq *req; | 31 | + *pnum = bytes; |
27 | + | 32 | + return 0; |
28 | + QLIST_FOREACH(req, &s->inflight_reqs, list) { | ||
29 | + if (end > req->start_byte && start < req->end_byte) { | ||
30 | + return req; | ||
31 | + } | ||
32 | + } | 33 | + } |
33 | + | 34 | + |
34 | + return NULL; | 35 | ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); |
35 | +} | 36 | if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { |
36 | + | 37 | return ret; |
37 | static void coroutine_fn block_copy_wait_inflight_reqs(BlockCopyState *s, | ||
38 | int64_t start, | ||
39 | int64_t end) | ||
40 | { | ||
41 | BlockCopyInFlightReq *req; | ||
42 | - bool waited; | ||
43 | - | ||
44 | - do { | ||
45 | - waited = false; | ||
46 | - QLIST_FOREACH(req, &s->inflight_reqs, list) { | ||
47 | - if (end > req->start_byte && start < req->end_byte) { | ||
48 | - qemu_co_queue_wait(&req->wait_queue, NULL); | ||
49 | - waited = true; | ||
50 | - break; | ||
51 | - } | ||
52 | - } | ||
53 | - } while (waited); | ||
54 | + | ||
55 | + while ((req = find_conflicting_inflight_req(s, start, end))) { | ||
56 | + qemu_co_queue_wait(&req->wait_queue, NULL); | ||
57 | + } | ||
58 | } | ||
59 | |||
60 | static void block_copy_inflight_req_begin(BlockCopyState *s, | ||
61 | -- | 38 | -- |
62 | 2.24.1 | 39 | 2.26.2 |
63 | 40 | ||
64 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | We have a lot of "chunk_end - start" invocations, let's switch to | 3 | bdrv_is_allocated_above wrongly handles short backing files: it reports |
4 | bytes/cur_bytes scheme instead. | 4 | after-EOF space as UNALLOCATED which is wrong, as on read the data is |
5 | generated on the level of short backing file (if all overlays have | ||
6 | unallocated areas at that place). | ||
5 | 7 | ||
6 | While being here, improve check on block_copy_do_copy parameters to not | 8 | Reusing bdrv_common_block_status_above fixes the issue and unifies code |
7 | overflow when calculating nbytes and use int64_t for bytes in | 9 | path. |
8 | block_copy for consistency. | ||
9 | 10 | ||
10 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 11 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
11 | Reviewed-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> | 12 | Reviewed-by: Eric Blake <eblake@redhat.com> |
12 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 13 | Reviewed-by: Alberto Garcia <berto@igalia.com> |
13 | Message-Id: <20200311103004.7649-7-vsementsov@virtuozzo.com> | 14 | Message-id: 20200924194003.22080-5-vsementsov@virtuozzo.com |
14 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 15 | [Fix s/has/have/ as suggested by Eric Blake. Fix s/area/areas/. |
16 | --Stefan] | ||
17 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
15 | --- | 18 | --- |
16 | block/block-copy.c | 78 ++++++++++++++++++++------------------ | 19 | block/io.c | 43 +++++-------------------------------------- |
17 | include/block/block-copy.h | 6 +-- | 20 | 1 file changed, 5 insertions(+), 38 deletions(-) |
18 | 2 files changed, 44 insertions(+), 40 deletions(-) | ||
19 | 21 | ||
20 | diff --git a/block/block-copy.c b/block/block-copy.c | 22 | diff --git a/block/io.c b/block/io.c |
21 | index XXXXXXX..XXXXXXX 100644 | 23 | index XXXXXXX..XXXXXXX 100644 |
22 | --- a/block/block-copy.c | 24 | --- a/block/io.c |
23 | +++ b/block/block-copy.c | 25 | +++ b/block/io.c |
24 | @@ -XXX,XX +XXX,XX @@ | 26 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, |
25 | 27 | * at 'offset + *pnum' may return the same allocation status (in other | |
26 | static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s, | 28 | * words, the result is not necessarily the maximum possible range); |
27 | int64_t start, | 29 | * but 'pnum' will only be 0 when end of file is reached. |
28 | - int64_t end) | 30 | - * |
29 | + int64_t bytes) | 31 | */ |
32 | int bdrv_is_allocated_above(BlockDriverState *top, | ||
33 | BlockDriverState *base, | ||
34 | bool include_base, int64_t offset, | ||
35 | int64_t bytes, int64_t *pnum) | ||
30 | { | 36 | { |
31 | BlockCopyInFlightReq *req; | 37 | - BlockDriverState *intermediate; |
32 | 38 | - int ret; | |
33 | QLIST_FOREACH(req, &s->inflight_reqs, list) { | 39 | - int64_t n = bytes; |
34 | - if (end > req->start_byte && start < req->end_byte) { | 40 | - |
35 | + if (start + bytes > req->start && start < req->start + req->bytes) { | 41 | - assert(base || !include_base); |
36 | return req; | 42 | - |
37 | } | 43 | - intermediate = top; |
44 | - while (include_base || intermediate != base) { | ||
45 | - int64_t pnum_inter; | ||
46 | - int64_t size_inter; | ||
47 | - | ||
48 | - assert(intermediate); | ||
49 | - ret = bdrv_is_allocated(intermediate, offset, bytes, &pnum_inter); | ||
50 | - if (ret < 0) { | ||
51 | - return ret; | ||
52 | - } | ||
53 | - if (ret) { | ||
54 | - *pnum = pnum_inter; | ||
55 | - return 1; | ||
56 | - } | ||
57 | - | ||
58 | - size_inter = bdrv_getlength(intermediate); | ||
59 | - if (size_inter < 0) { | ||
60 | - return size_inter; | ||
61 | - } | ||
62 | - if (n > pnum_inter && | ||
63 | - (intermediate == top || offset + pnum_inter < size_inter)) { | ||
64 | - n = pnum_inter; | ||
65 | - } | ||
66 | - | ||
67 | - if (intermediate == base) { | ||
68 | - break; | ||
69 | - } | ||
70 | - | ||
71 | - intermediate = bdrv_filter_or_cow_bs(intermediate); | ||
72 | + int ret = bdrv_common_block_status_above(top, base, include_base, false, | ||
73 | + offset, bytes, pnum, NULL, NULL); | ||
74 | + if (ret < 0) { | ||
75 | + return ret; | ||
38 | } | 76 | } |
39 | @@ -XXX,XX +XXX,XX @@ static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s, | 77 | |
40 | 78 | - *pnum = n; | |
41 | static void coroutine_fn block_copy_wait_inflight_reqs(BlockCopyState *s, | 79 | - return 0; |
42 | int64_t start, | 80 | + return !!(ret & BDRV_BLOCK_ALLOCATED); |
43 | - int64_t end) | ||
44 | + int64_t bytes) | ||
45 | { | ||
46 | BlockCopyInFlightReq *req; | ||
47 | |||
48 | - while ((req = find_conflicting_inflight_req(s, start, end))) { | ||
49 | + while ((req = find_conflicting_inflight_req(s, start, bytes))) { | ||
50 | qemu_co_queue_wait(&req->wait_queue, NULL); | ||
51 | } | ||
52 | } | 81 | } |
53 | 82 | ||
54 | static void block_copy_inflight_req_begin(BlockCopyState *s, | 83 | int coroutine_fn |
55 | BlockCopyInFlightReq *req, | ||
56 | - int64_t start, int64_t end) | ||
57 | + int64_t start, int64_t bytes) | ||
58 | { | ||
59 | - req->start_byte = start; | ||
60 | - req->end_byte = end; | ||
61 | + req->start = start; | ||
62 | + req->bytes = bytes; | ||
63 | qemu_co_queue_init(&req->wait_queue); | ||
64 | QLIST_INSERT_HEAD(&s->inflight_reqs, req, list); | ||
65 | } | ||
66 | @@ -XXX,XX +XXX,XX @@ void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm) | ||
67 | /* | ||
68 | * block_copy_do_copy | ||
69 | * | ||
70 | - * Do copy of cluser-aligned chunk. @end is allowed to exceed s->len only to | ||
71 | - * cover last cluster when s->len is not aligned to clusters. | ||
72 | + * Do copy of cluster-aligned chunk. Requested region is allowed to exceed | ||
73 | + * s->len only to cover last cluster when s->len is not aligned to clusters. | ||
74 | * | ||
75 | * No sync here: nor bitmap neighter intersecting requests handling, only copy. | ||
76 | * | ||
77 | * Returns 0 on success. | ||
78 | */ | ||
79 | static int coroutine_fn block_copy_do_copy(BlockCopyState *s, | ||
80 | - int64_t start, int64_t end, | ||
81 | + int64_t start, int64_t bytes, | ||
82 | bool zeroes, bool *error_is_read) | ||
83 | { | ||
84 | int ret; | ||
85 | - int nbytes = MIN(end, s->len) - start; | ||
86 | + int64_t nbytes = MIN(start + bytes, s->len) - start; | ||
87 | void *bounce_buffer = NULL; | ||
88 | |||
89 | + assert(start >= 0 && bytes > 0 && INT64_MAX - start >= bytes); | ||
90 | assert(QEMU_IS_ALIGNED(start, s->cluster_size)); | ||
91 | - assert(QEMU_IS_ALIGNED(end, s->cluster_size)); | ||
92 | - assert(end < s->len || end == QEMU_ALIGN_UP(s->len, s->cluster_size)); | ||
93 | + assert(QEMU_IS_ALIGNED(bytes, s->cluster_size)); | ||
94 | + assert(start < s->len); | ||
95 | + assert(start + bytes <= s->len || | ||
96 | + start + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size)); | ||
97 | + assert(nbytes < INT_MAX); | ||
98 | |||
99 | if (zeroes) { | ||
100 | ret = bdrv_co_pwrite_zeroes(s->target, start, nbytes, s->write_flags & | ||
101 | @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, | ||
102 | } | ||
103 | |||
104 | int coroutine_fn block_copy(BlockCopyState *s, | ||
105 | - int64_t start, uint64_t bytes, | ||
106 | + int64_t start, int64_t bytes, | ||
107 | bool *error_is_read) | ||
108 | { | ||
109 | int ret = 0; | ||
110 | - int64_t end = bytes + start; /* bytes */ | ||
111 | BlockCopyInFlightReq req; | ||
112 | |||
113 | /* | ||
114 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
115 | bdrv_get_aio_context(s->target->bs)); | ||
116 | |||
117 | assert(QEMU_IS_ALIGNED(start, s->cluster_size)); | ||
118 | - assert(QEMU_IS_ALIGNED(end, s->cluster_size)); | ||
119 | + assert(QEMU_IS_ALIGNED(bytes, s->cluster_size)); | ||
120 | |||
121 | block_copy_wait_inflight_reqs(s, start, bytes); | ||
122 | - block_copy_inflight_req_begin(s, &req, start, end); | ||
123 | + block_copy_inflight_req_begin(s, &req, start, bytes); | ||
124 | |||
125 | - while (start < end) { | ||
126 | - int64_t next_zero, chunk_end, status_bytes; | ||
127 | + while (bytes) { | ||
128 | + int64_t next_zero, cur_bytes, status_bytes; | ||
129 | |||
130 | if (!bdrv_dirty_bitmap_get(s->copy_bitmap, start)) { | ||
131 | trace_block_copy_skip(s, start); | ||
132 | start += s->cluster_size; | ||
133 | + bytes -= s->cluster_size; | ||
134 | continue; /* already copied */ | ||
135 | } | ||
136 | |||
137 | - chunk_end = MIN(end, start + s->copy_size); | ||
138 | + cur_bytes = MIN(bytes, s->copy_size); | ||
139 | |||
140 | next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, start, | ||
141 | - chunk_end - start); | ||
142 | + cur_bytes); | ||
143 | if (next_zero >= 0) { | ||
144 | assert(next_zero > start); /* start is dirty */ | ||
145 | - assert(next_zero < chunk_end); /* no need to do MIN() */ | ||
146 | - chunk_end = next_zero; | ||
147 | + assert(next_zero < start + cur_bytes); /* no need to do MIN() */ | ||
148 | + cur_bytes = next_zero - start; | ||
149 | } | ||
150 | |||
151 | - ret = block_copy_block_status(s, start, chunk_end - start, | ||
152 | - &status_bytes); | ||
153 | + ret = block_copy_block_status(s, start, cur_bytes, &status_bytes); | ||
154 | if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) { | ||
155 | bdrv_reset_dirty_bitmap(s->copy_bitmap, start, status_bytes); | ||
156 | progress_set_remaining(s->progress, | ||
157 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, | ||
158 | s->in_flight_bytes); | ||
159 | trace_block_copy_skip_range(s, start, status_bytes); | ||
160 | start += status_bytes; | ||
161 | + bytes -= status_bytes; | ||
162 | continue; | ||
163 | } | ||
164 | |||
165 | - chunk_end = MIN(chunk_end, start + status_bytes); | ||
166 | + cur_bytes = MIN(cur_bytes, status_bytes); | ||
167 | |||
168 | trace_block_copy_process(s, start); | ||
169 | |||
170 | - bdrv_reset_dirty_bitmap(s->copy_bitmap, start, chunk_end - start); | ||
171 | - s->in_flight_bytes += chunk_end - start; | ||
172 | + bdrv_reset_dirty_bitmap(s->copy_bitmap, start, cur_bytes); | ||
173 | + s->in_flight_bytes += cur_bytes; | ||
174 | |||
175 | - co_get_from_shres(s->mem, chunk_end - start); | ||
176 | - ret = block_copy_do_copy(s, start, chunk_end, ret & BDRV_BLOCK_ZERO, | ||
177 | + co_get_from_shres(s->mem, cur_bytes); | ||
178 | + ret = block_copy_do_copy(s, start, cur_bytes, ret & BDRV_BLOCK_ZERO, | ||
179 | error_is_read); | ||
180 | - co_put_to_shres(s->mem, chunk_end - start); | ||
181 | - s->in_flight_bytes -= chunk_end - start; | ||
182 | + co_put_to_shres(s->mem, cur_bytes); | ||
183 | + s->in_flight_bytes -= cur_bytes; | ||
184 | if (ret < 0) { | ||
185 | - bdrv_set_dirty_bitmap(s->copy_bitmap, start, chunk_end - start); | ||
186 | + bdrv_set_dirty_bitmap(s->copy_bitmap, start, cur_bytes); | ||
187 | break; | ||
188 | } | ||
189 | |||
190 | - progress_work_done(s->progress, chunk_end - start); | ||
191 | - s->progress_bytes_callback(chunk_end - start, s->progress_opaque); | ||
192 | - start = chunk_end; | ||
193 | - ret = 0; | ||
194 | + progress_work_done(s->progress, cur_bytes); | ||
195 | + s->progress_bytes_callback(cur_bytes, s->progress_opaque); | ||
196 | + start += cur_bytes; | ||
197 | + bytes -= cur_bytes; | ||
198 | } | ||
199 | |||
200 | block_copy_inflight_req_end(&req); | ||
201 | diff --git a/include/block/block-copy.h b/include/block/block-copy.h | ||
202 | index XXXXXXX..XXXXXXX 100644 | ||
203 | --- a/include/block/block-copy.h | ||
204 | +++ b/include/block/block-copy.h | ||
205 | @@ -XXX,XX +XXX,XX @@ | ||
206 | #include "qemu/co-shared-resource.h" | ||
207 | |||
208 | typedef struct BlockCopyInFlightReq { | ||
209 | - int64_t start_byte; | ||
210 | - int64_t end_byte; | ||
211 | + int64_t start; | ||
212 | + int64_t bytes; | ||
213 | QLIST_ENTRY(BlockCopyInFlightReq) list; | ||
214 | CoQueue wait_queue; /* coroutines blocked on this request */ | ||
215 | } BlockCopyInFlightReq; | ||
216 | @@ -XXX,XX +XXX,XX @@ void block_copy_state_free(BlockCopyState *s); | ||
217 | int64_t block_copy_reset_unallocated(BlockCopyState *s, | ||
218 | int64_t offset, int64_t *count); | ||
219 | |||
220 | -int coroutine_fn block_copy(BlockCopyState *s, int64_t start, uint64_t bytes, | ||
221 | +int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, | ||
222 | bool *error_is_read); | ||
223 | |||
224 | #endif /* BLOCK_COPY_H */ | ||
225 | -- | 84 | -- |
226 | 2.24.1 | 85 | 2.26.2 |
227 | 86 | ||
228 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | On success path we return what inflate() returns instead of 0. And it | 3 | These cases are fixed by previous patches around block_status and |
4 | most probably works for Z_STREAM_END as it is positive, but is | 4 | is_allocated. |
5 | definitely broken for Z_BUF_ERROR. | ||
6 | 5 | ||
7 | While being here, switch to errno return code, to be closer to | 6 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
8 | qcow2_compress API (and usual expectations). | 7 | Reviewed-by: Eric Blake <eblake@redhat.com> |
8 | Reviewed-by: Alberto Garcia <berto@igalia.com> | ||
9 | Message-id: 20200924194003.22080-6-vsementsov@virtuozzo.com | ||
10 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
11 | --- | ||
12 | tests/qemu-iotests/274 | 20 +++++++++++ | ||
13 | tests/qemu-iotests/274.out | 68 ++++++++++++++++++++++++++++++++++++++ | ||
14 | 2 files changed, 88 insertions(+) | ||
9 | 15 | ||
10 | Revert condition in if to be more positive. Drop dead initialization of | 16 | diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 |
11 | ret. | 17 | index XXXXXXX..XXXXXXX 100755 |
18 | --- a/tests/qemu-iotests/274 | ||
19 | +++ b/tests/qemu-iotests/274 | ||
20 | @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('base') as base, \ | ||
21 | iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) | ||
22 | iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) | ||
23 | |||
24 | + iotests.log('=== Testing qemu-img commit (top -> base) ===') | ||
25 | + | ||
26 | + create_chain() | ||
27 | + iotests.qemu_img_log('commit', '-b', base, top) | ||
28 | + iotests.img_info_log(base) | ||
29 | + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) | ||
30 | + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) | ||
31 | + | ||
32 | + iotests.log('=== Testing QMP active commit (top -> base) ===') | ||
33 | + | ||
34 | + create_chain() | ||
35 | + with create_vm() as vm: | ||
36 | + vm.launch() | ||
37 | + vm.qmp_log('block-commit', device='top', base_node='base', | ||
38 | + job_id='job0', auto_dismiss=False) | ||
39 | + vm.run_job('job0', wait=5) | ||
40 | + | ||
41 | + iotests.img_info_log(mid) | ||
42 | + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) | ||
43 | + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) | ||
44 | |||
45 | iotests.log('== Resize tests ==') | ||
46 | |||
47 | diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out | ||
48 | index XXXXXXX..XXXXXXX 100644 | ||
49 | --- a/tests/qemu-iotests/274.out | ||
50 | +++ b/tests/qemu-iotests/274.out | ||
51 | @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 0 | ||
52 | read 1048576/1048576 bytes at offset 1048576 | ||
53 | 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
54 | |||
55 | +=== Testing qemu-img commit (top -> base) === | ||
56 | +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 | ||
57 | + | ||
58 | +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 | ||
59 | + | ||
60 | +Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 | ||
61 | + | ||
62 | +wrote 2097152/2097152 bytes at offset 0 | ||
63 | +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
64 | + | ||
65 | +Image committed. | ||
66 | + | ||
67 | +image: TEST_IMG | ||
68 | +file format: IMGFMT | ||
69 | +virtual size: 2 MiB (2097152 bytes) | ||
70 | +cluster_size: 65536 | ||
71 | +Format specific information: | ||
72 | + compat: 1.1 | ||
73 | + compression type: zlib | ||
74 | + lazy refcounts: false | ||
75 | + refcount bits: 16 | ||
76 | + corrupt: false | ||
77 | + extended l2: false | ||
78 | + | ||
79 | +read 1048576/1048576 bytes at offset 0 | ||
80 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
81 | + | ||
82 | +read 1048576/1048576 bytes at offset 1048576 | ||
83 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
84 | + | ||
85 | +=== Testing QMP active commit (top -> base) === | ||
86 | +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 | ||
87 | + | ||
88 | +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=1048576 backing_file=TEST_DIR/PID-base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 | ||
89 | + | ||
90 | +Formatting 'TEST_DIR/PID-top', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 backing_file=TEST_DIR/PID-mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 | ||
91 | + | ||
92 | +wrote 2097152/2097152 bytes at offset 0 | ||
93 | +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
94 | + | ||
95 | +{"execute": "block-commit", "arguments": {"auto-dismiss": false, "base-node": "base", "device": "top", "job-id": "job0"}} | ||
96 | +{"return": {}} | ||
97 | +{"execute": "job-complete", "arguments": {"id": "job0"}} | ||
98 | +{"return": {}} | ||
99 | +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} | ||
100 | +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} | ||
101 | +{"execute": "job-dismiss", "arguments": {"id": "job0"}} | ||
102 | +{"return": {}} | ||
103 | +image: TEST_IMG | ||
104 | +file format: IMGFMT | ||
105 | +virtual size: 1 MiB (1048576 bytes) | ||
106 | +cluster_size: 65536 | ||
107 | +backing file: TEST_DIR/PID-base | ||
108 | +backing file format: IMGFMT | ||
109 | +Format specific information: | ||
110 | + compat: 1.1 | ||
111 | + compression type: zlib | ||
112 | + lazy refcounts: false | ||
113 | + refcount bits: 16 | ||
114 | + corrupt: false | ||
115 | + extended l2: false | ||
116 | + | ||
117 | +read 1048576/1048576 bytes at offset 0 | ||
118 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
119 | + | ||
120 | +read 1048576/1048576 bytes at offset 1048576 | ||
121 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
122 | + | ||
123 | == Resize tests == | ||
124 | === preallocation=off === | ||
125 | Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=6442450944 lazy_refcounts=off refcount_bits=16 | ||
126 | -- | ||
127 | 2.26.2 | ||
12 | 128 | ||
13 | Cc: qemu-stable@nongnu.org # v4.0 | ||
14 | Fixes: 341926ab83e2b | ||
15 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
16 | Message-Id: <20200302150930.16218-1-vsementsov@virtuozzo.com> | ||
17 | Reviewed-by: Alberto Garcia <berto@igalia.com> | ||
18 | Reviewed-by: Ján Tomko <jtomko@redhat.com> | ||
19 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
20 | --- | ||
21 | block/qcow2-threads.c | 12 +++++++----- | ||
22 | 1 file changed, 7 insertions(+), 5 deletions(-) | ||
23 | |||
24 | diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c | ||
25 | index XXXXXXX..XXXXXXX 100644 | ||
26 | --- a/block/qcow2-threads.c | ||
27 | +++ b/block/qcow2-threads.c | ||
28 | @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_compress(void *dest, size_t dest_size, | ||
29 | * @src - source buffer, @src_size bytes | ||
30 | * | ||
31 | * Returns: 0 on success | ||
32 | - * -1 on fail | ||
33 | + * -EIO on fail | ||
34 | */ | ||
35 | static ssize_t qcow2_decompress(void *dest, size_t dest_size, | ||
36 | const void *src, size_t src_size) | ||
37 | { | ||
38 | - int ret = 0; | ||
39 | + int ret; | ||
40 | z_stream strm; | ||
41 | |||
42 | memset(&strm, 0, sizeof(strm)); | ||
43 | @@ -XXX,XX +XXX,XX @@ static ssize_t qcow2_decompress(void *dest, size_t dest_size, | ||
44 | |||
45 | ret = inflateInit2(&strm, -12); | ||
46 | if (ret != Z_OK) { | ||
47 | - return -1; | ||
48 | + return -EIO; | ||
49 | } | ||
50 | |||
51 | ret = inflate(&strm, Z_FINISH); | ||
52 | - if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) || strm.avail_out != 0) { | ||
53 | + if ((ret == Z_STREAM_END || ret == Z_BUF_ERROR) && strm.avail_out == 0) { | ||
54 | /* | ||
55 | * We approve Z_BUF_ERROR because we need @dest buffer to be filled, but | ||
56 | * @src buffer may be processed partly (because in qcow2 we know size of | ||
57 | * compressed data with precision of one sector) | ||
58 | */ | ||
59 | - ret = -1; | ||
60 | + ret = 0; | ||
61 | + } else { | ||
62 | + ret = -EIO; | ||
63 | } | ||
64 | |||
65 | inflateEnd(&strm); | ||
66 | -- | ||
67 | 2.24.1 | ||
68 | |||
69 | diff view generated by jsdifflib |