1 | The following changes since commit b4fbe1f65a4769c09e6bf2d79fc84360f840f40e: | 1 | The following changes since commit ac793156f650ae2d77834932d72224175ee69086: |
---|---|---|---|
2 | 2 | ||
3 | Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20190129' into staging (2019-01-29 12:00:19 +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://git.xanclic.moe/XanClic/qemu.git tags/pull-block-2019-01-31 | 7 | https://gitlab.com/stefanha/qemu.git tags/block-pull-request |
8 | 8 | ||
9 | for you to fetch changes up to 908b30164bbffad7430d551b2a03a8fbcaa631ef: | 9 | for you to fetch changes up to 32a3fd65e7e3551337fd26bfc0e2f899d70c028c: |
10 | 10 | ||
11 | iotests: Allow 147 to be run concurrently (2019-01-31 00:44:55 +0100) | 11 | iotests: add commit top->base cases to 274 (2020-10-22 09:55:39 +0100) |
12 | 12 | ||
13 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
14 | Block patches: | 14 | Pull request |
15 | - New debugging QMP command to explore block graphs | 15 | |
16 | - Converted DPRINTF()s to trace events | 16 | v2: |
17 | - Fixed qemu-io's use of getopt() for systems with optreset | 17 | * Fix format string issues on 32-bit hosts [Peter] |
18 | - Minor NVMe emulation fixes | 18 | * Fix qemu-nbd.c CONFIG_POSIX ifdef issue [Eric] |
19 | - An iotest fix | 19 | * Fix missing eventfd.h header on macOS [Peter] |
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. | ||
20 | 26 | ||
21 | ---------------------------------------------------------------- | 27 | ---------------------------------------------------------------- |
22 | Laurent Vivier (4): | ||
23 | block/ssh: Convert from DPRINTF() macro to trace events | ||
24 | block/curl: Convert from DPRINTF() macro to trace events | ||
25 | block/file-posix: Convert from DPRINTF() macro to trace events | ||
26 | block/sheepdog: Convert from DPRINTF() macro to trace events | ||
27 | 28 | ||
28 | Li Qiang (3): | 29 | Coiby Xu (6): |
29 | nvme: use TYPE_NVME instead of constant string | 30 | libvhost-user: Allow vu_message_read to be replaced |
30 | nvme: ensure the num_queues is not zero | 31 | libvhost-user: remove watch for kick_fd when de-initialize vu-dev |
31 | nvme: use pci_dev directly in nvme_realize | 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 | ||
32 | 37 | ||
33 | Max Reitz (3): | 38 | Philippe Mathieu-Daudé (1): |
34 | iotests.py: Add qemu_nbd_pipe() | 39 | block/nvme: Add driver statistics for access alignment and hw errors |
35 | iotests: Bind qemu-nbd to localhost in 147 | ||
36 | iotests: Allow 147 to be run concurrently | ||
37 | 40 | ||
38 | Richard W.M. Jones (1): | 41 | Stefan Hajnoczi (16): |
39 | qemu-io: Add generic function for reinitializing optind. | 42 | util/vhost-user-server: s/fileds/fields/ typo fix |
43 | util/vhost-user-server: drop unnecessary QOM cast | ||
44 | util/vhost-user-server: drop unnecessary watch deletion | ||
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 | ||
40 | 58 | ||
41 | Vladimir Sementsov-Ogievskiy (2): | 59 | Vladimir Sementsov-Ogievskiy (5): |
42 | qapi: add x-debug-query-block-graph | 60 | block/io: fix bdrv_co_block_status_above |
43 | scripts: add render_block_graph function for QEMUMachine | 61 | block/io: bdrv_common_block_status_above: support include_base |
62 | block/io: bdrv_common_block_status_above: support bs == base | ||
63 | block/io: fix bdrv_is_allocated_above | ||
64 | iotests: add commit top->base cases to 274 | ||
44 | 65 | ||
45 | configure | 14 ++++ | 66 | MAINTAINERS | 9 + |
46 | qapi/block-core.json | 108 ++++++++++++++++++++++++ | 67 | qapi/block-core.json | 24 +- |
47 | include/block/block.h | 1 + | 68 | qapi/block-export.json | 36 +- |
48 | include/qemu/osdep.h | 16 ++++ | 69 | block/coroutines.h | 2 + |
49 | include/sysemu/block-backend.h | 2 + | 70 | block/export/vhost-user-blk-server.h | 19 + |
50 | block.c | 148 +++++++++++++++++++++++++++++++++ | 71 | contrib/libvhost-user/libvhost-user.h | 21 + |
51 | block/block-backend.c | 5 ++ | 72 | include/qemu/vhost-user-server.h | 65 +++ |
52 | block/curl.c | 29 ++----- | 73 | util/block-helpers.h | 19 + |
53 | block/file-posix.c | 25 ++---- | 74 | block/export/export.c | 37 +- |
54 | block/sheepdog.c | 47 ++++------- | 75 | block/export/vhost-user-blk-server.c | 431 ++++++++++++++++++++ |
55 | block/ssh.c | 46 ++++------ | 76 | block/io.c | 132 +++--- |
56 | blockdev.c | 5 ++ | 77 | block/nvme.c | 27 ++ |
57 | hw/block/nvme.c | 15 ++-- | 78 | block/qcow2.c | 16 +- |
58 | qemu-img.c | 2 +- | 79 | contrib/libvhost-user/libvhost-user-glib.c | 2 +- |
59 | qemu-io-cmds.c | 2 +- | 80 | contrib/libvhost-user/libvhost-user.c | 15 +- |
60 | block/trace-events | 47 +++++++++++ | 81 | hw/core/qdev-properties-system.c | 31 +- |
61 | scripts/render_block_graph.py | 120 ++++++++++++++++++++++++++ | 82 | nbd/server.c | 2 - |
62 | tests/qemu-iotests/147 | 98 +++++++++++++++------- | 83 | qemu-nbd.c | 21 +- |
63 | tests/qemu-iotests/iotests.py | 14 ++++ | 84 | softmmu/vl.c | 4 + |
64 | 19 files changed, 608 insertions(+), 136 deletions(-) | 85 | stubs/blk-exp-close-all.c | 7 + |
65 | create mode 100755 scripts/render_block_graph.py | 86 | tests/vhost-user-bridge.c | 2 + |
87 | tools/virtiofsd/fuse_virtio.c | 4 +- | ||
88 | util/block-helpers.c | 46 +++ | ||
89 | util/vhost-user-server.c | 446 +++++++++++++++++++++ | ||
90 | block/export/meson.build | 3 +- | ||
91 | contrib/libvhost-user/meson.build | 1 + | ||
92 | meson.build | 22 +- | ||
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 | ||
66 | 107 | ||
67 | -- | 108 | -- |
68 | 2.20.1 | 109 | 2.26.2 |
69 | 110 | ||
70 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Philippe Mathieu-Daudé <philmd@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Add a new command, returning block nodes (and their users) graph. | 3 | Keep statistics of some hardware errors, and number of |
4 | aligned/unaligned I/O accesses. | ||
4 | 5 | ||
5 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 6 | QMP example booting a full RHEL 8.3 aarch64 guest: |
6 | Message-id: 20181221170909.25584-2-vsementsov@virtuozzo.com | 7 | |
7 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 8 | { "execute": "query-blockstats" } |
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 | } | ||
44 | |||
45 | Suggested-by: Stefan Hajnoczi <stefanha@gmail.com> | ||
46 | Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
47 | Acked-by: Markus Armbruster <armbru@redhat.com> | ||
48 | Message-id: 20201001162939.1567915-1-philmd@redhat.com | ||
49 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | --- | 50 | --- |
9 | qapi/block-core.json | 108 ++++++++++++++++++++++++ | 51 | qapi/block-core.json | 24 +++++++++++++++++++++++- |
10 | include/block/block.h | 1 + | 52 | block/nvme.c | 27 +++++++++++++++++++++++++++ |
11 | include/sysemu/block-backend.h | 2 + | 53 | 2 files changed, 50 insertions(+), 1 deletion(-) |
12 | block.c | 148 +++++++++++++++++++++++++++++++++ | ||
13 | block/block-backend.c | 5 ++ | ||
14 | blockdev.c | 5 ++ | ||
15 | 6 files changed, 269 insertions(+) | ||
16 | 54 | ||
17 | diff --git a/qapi/block-core.json b/qapi/block-core.json | 55 | diff --git a/qapi/block-core.json b/qapi/block-core.json |
18 | index XXXXXXX..XXXXXXX 100644 | 56 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/qapi/block-core.json | 57 | --- a/qapi/block-core.json |
20 | +++ b/qapi/block-core.json | 58 | +++ b/qapi/block-core.json |
21 | @@ -XXX,XX +XXX,XX @@ | 59 | @@ -XXX,XX +XXX,XX @@ |
22 | ## | 60 | 'discard-nb-failed': 'uint64', |
23 | { 'command': 'query-named-block-nodes', 'returns': [ 'BlockDeviceInfo' ] } | 61 | 'discard-bytes-ok': 'uint64' } } |
24 | 62 | ||
25 | +## | 63 | +## |
26 | +# @XDbgBlockGraphNodeType: | 64 | +# @BlockStatsSpecificNvme: |
27 | +# | 65 | +# |
28 | +# @block-backend: corresponds to BlockBackend | 66 | +# NVMe driver statistics |
29 | +# | 67 | +# |
30 | +# @block-job: corresonds to BlockJob | 68 | +# @completion-errors: The number of completion errors. |
31 | +# | 69 | +# |
32 | +# @block-driver: corresponds to BlockDriverState | 70 | +# @aligned-accesses: The number of aligned accesses performed by |
71 | +# the driver. | ||
33 | +# | 72 | +# |
34 | +# Since: 4.0 | 73 | +# @unaligned-accesses: The number of unaligned accesses performed by |
74 | +# the driver. | ||
75 | +# | ||
76 | +# Since: 5.2 | ||
35 | +## | 77 | +## |
36 | +{ 'enum': 'XDbgBlockGraphNodeType', | 78 | +{ 'struct': 'BlockStatsSpecificNvme', |
37 | + 'data': [ 'block-backend', 'block-job', 'block-driver' ] } | 79 | + 'data': { |
38 | + | 80 | + 'completion-errors': 'uint64', |
39 | +## | 81 | + 'aligned-accesses': 'uint64', |
40 | +# @XDbgBlockGraphNode: | 82 | + 'unaligned-accesses': 'uint64' } } |
41 | +# | ||
42 | +# @id: Block graph node identifier. This @id is generated only for | ||
43 | +# x-debug-query-block-graph and does not relate to any other identifiers in | ||
44 | +# Qemu. | ||
45 | +# | ||
46 | +# @type: Type of graph node. Can be one of block-backend, block-job or | ||
47 | +# block-driver-state. | ||
48 | +# | ||
49 | +# @name: Human readable name of the node. Corresponds to node-name for | ||
50 | +# block-driver-state nodes; is not guaranteed to be unique in the whole | ||
51 | +# graph (with block-jobs and block-backends). | ||
52 | +# | ||
53 | +# Since: 4.0 | ||
54 | +## | ||
55 | +{ 'struct': 'XDbgBlockGraphNode', | ||
56 | + 'data': { 'id': 'uint64', 'type': 'XDbgBlockGraphNodeType', 'name': 'str' } } | ||
57 | + | ||
58 | +## | ||
59 | +# @BlockPermission: | ||
60 | +# | ||
61 | +# Enum of base block permissions. | ||
62 | +# | ||
63 | +# @consistent-read: A user that has the "permission" of consistent reads is | ||
64 | +# guaranteed that their view of the contents of the block | ||
65 | +# device is complete and self-consistent, representing the | ||
66 | +# contents of a disk at a specific point. | ||
67 | +# For most block devices (including their backing files) this | ||
68 | +# is true, but the property cannot be maintained in a few | ||
69 | +# situations like for intermediate nodes of a commit block | ||
70 | +# job. | ||
71 | +# | ||
72 | +# @write: This permission is required to change the visible disk contents. | ||
73 | +# | ||
74 | +# @write-unchanged: This permission (which is weaker than BLK_PERM_WRITE) is | ||
75 | +# both enough and required for writes to the block node when | ||
76 | +# the caller promises that the visible disk content doesn't | ||
77 | +# change. | ||
78 | +# As the BLK_PERM_WRITE permission is strictly stronger, | ||
79 | +# either is sufficient to perform an unchanging write. | ||
80 | +# | ||
81 | +# @resize: This permission is required to change the size of a block node. | ||
82 | +# | ||
83 | +# @graph-mod: This permission is required to change the node that this | ||
84 | +# BdrvChild points to. | ||
85 | +# | ||
86 | +# Since: 4.0 | ||
87 | +## | ||
88 | + { 'enum': 'BlockPermission', | ||
89 | + 'data': [ 'consistent-read', 'write', 'write-unchanged', 'resize', | ||
90 | + 'graph-mod' ] } | ||
91 | +## | ||
92 | +# @XDbgBlockGraphEdge: | ||
93 | +# | ||
94 | +# Block Graph edge description for x-debug-query-block-graph. | ||
95 | +# | ||
96 | +# @parent: parent id | ||
97 | +# | ||
98 | +# @child: child id | ||
99 | +# | ||
100 | +# @name: name of the relation (examples are 'file' and 'backing') | ||
101 | +# | ||
102 | +# @perm: granted permissions for the parent operating on the child | ||
103 | +# | ||
104 | +# @shared-perm: permissions that can still be granted to other users of the | ||
105 | +# child while it is still attached to this parent | ||
106 | +# | ||
107 | +# Since: 4.0 | ||
108 | +## | ||
109 | +{ 'struct': 'XDbgBlockGraphEdge', | ||
110 | + 'data': { 'parent': 'uint64', 'child': 'uint64', | ||
111 | + 'name': 'str', 'perm': [ 'BlockPermission' ], | ||
112 | + 'shared-perm': [ 'BlockPermission' ] } } | ||
113 | + | ||
114 | +## | ||
115 | +# @XDbgBlockGraph: | ||
116 | +# | ||
117 | +# Block Graph - list of nodes and list of edges. | ||
118 | +# | ||
119 | +# Since: 4.0 | ||
120 | +## | ||
121 | +{ 'struct': 'XDbgBlockGraph', | ||
122 | + 'data': { 'nodes': ['XDbgBlockGraphNode'], 'edges': ['XDbgBlockGraphEdge'] } } | ||
123 | + | ||
124 | +## | ||
125 | +# @x-debug-query-block-graph: | ||
126 | +# | ||
127 | +# Get the block graph. | ||
128 | +# | ||
129 | +# Since: 4.0 | ||
130 | +## | ||
131 | +{ 'command': 'x-debug-query-block-graph', 'returns': 'XDbgBlockGraph' } | ||
132 | + | 83 | + |
133 | ## | 84 | ## |
134 | # @drive-mirror: | 85 | # @BlockStatsSpecific: |
135 | # | 86 | # |
136 | diff --git a/include/block/block.h b/include/block/block.h | 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 | ||
137 | index XXXXXXX..XXXXXXX 100644 | 98 | index XXXXXXX..XXXXXXX 100644 |
138 | --- a/include/block/block.h | 99 | --- a/block/nvme.c |
139 | +++ b/include/block/block.h | 100 | +++ b/block/nvme.c |
140 | @@ -XXX,XX +XXX,XX @@ void bdrv_eject(BlockDriverState *bs, bool eject_flag); | 101 | @@ -XXX,XX +XXX,XX @@ struct BDRVNVMeState { |
141 | const char *bdrv_get_format_name(BlockDriverState *bs); | 102 | |
142 | BlockDriverState *bdrv_find_node(const char *node_name); | 103 | /* PCI address (required for nvme_refresh_filename()) */ |
143 | BlockDeviceInfoList *bdrv_named_nodes_list(Error **errp); | 104 | char *device; |
144 | +XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp); | ||
145 | BlockDriverState *bdrv_lookup_bs(const char *device, | ||
146 | const char *node_name, | ||
147 | Error **errp); | ||
148 | diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h | ||
149 | index XXXXXXX..XXXXXXX 100644 | ||
150 | --- a/include/sysemu/block-backend.h | ||
151 | +++ b/include/sysemu/block-backend.h | ||
152 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, | ||
153 | int bytes, BdrvRequestFlags read_flags, | ||
154 | BdrvRequestFlags write_flags); | ||
155 | |||
156 | +const BdrvChild *blk_root(BlockBackend *blk); | ||
157 | + | 105 | + |
158 | #endif | 106 | + struct { |
159 | diff --git a/block.c b/block.c | 107 | + uint64_t completion_errors; |
160 | index XXXXXXX..XXXXXXX 100644 | 108 | + uint64_t aligned_accesses; |
161 | --- a/block.c | 109 | + uint64_t unaligned_accesses; |
162 | +++ b/block.c | 110 | + } stats; |
163 | @@ -XXX,XX +XXX,XX @@ BlockDeviceInfoList *bdrv_named_nodes_list(Error **errp) | 111 | }; |
164 | return list; | 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); | ||
165 | } | 137 | } |
166 | 138 | ||
167 | +#define QAPI_LIST_ADD(list, element) do { \ | 139 | +static BlockStatsSpecific *nvme_get_specific_stats(BlockDriverState *bs) |
168 | + typeof(list) _tmp = g_new(typeof(*(list)), 1); \ | 140 | +{ |
169 | + _tmp->value = (element); \ | 141 | + BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1); |
170 | + _tmp->next = (list); \ | 142 | + BDRVNVMeState *s = bs->opaque; |
171 | + (list) = _tmp; \ | ||
172 | +} while (0) | ||
173 | + | 143 | + |
174 | +typedef struct XDbgBlockGraphConstructor { | 144 | + stats->driver = BLOCKDEV_DRIVER_NVME; |
175 | + XDbgBlockGraph *graph; | 145 | + stats->u.nvme = (BlockStatsSpecificNvme) { |
176 | + GHashTable *graph_nodes; | 146 | + .completion_errors = s->stats.completion_errors, |
177 | +} XDbgBlockGraphConstructor; | 147 | + .aligned_accesses = s->stats.aligned_accesses, |
148 | + .unaligned_accesses = s->stats.unaligned_accesses, | ||
149 | + }; | ||
178 | + | 150 | + |
179 | +static XDbgBlockGraphConstructor *xdbg_graph_new(void) | 151 | + return stats; |
180 | +{ | ||
181 | + XDbgBlockGraphConstructor *gr = g_new(XDbgBlockGraphConstructor, 1); | ||
182 | + | ||
183 | + gr->graph = g_new0(XDbgBlockGraph, 1); | ||
184 | + gr->graph_nodes = g_hash_table_new(NULL, NULL); | ||
185 | + | ||
186 | + return gr; | ||
187 | +} | 152 | +} |
188 | + | 153 | + |
189 | +static XDbgBlockGraph *xdbg_graph_finalize(XDbgBlockGraphConstructor *gr) | 154 | static const char *const nvme_strong_runtime_opts[] = { |
190 | +{ | 155 | NVME_BLOCK_OPT_DEVICE, |
191 | + XDbgBlockGraph *graph = gr->graph; | 156 | NVME_BLOCK_OPT_NAMESPACE, |
192 | + | 157 | @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = { |
193 | + g_hash_table_destroy(gr->graph_nodes); | 158 | .bdrv_refresh_filename = nvme_refresh_filename, |
194 | + g_free(gr); | 159 | .bdrv_refresh_limits = nvme_refresh_limits, |
195 | + | 160 | .strong_runtime_opts = nvme_strong_runtime_opts, |
196 | + return graph; | 161 | + .bdrv_get_specific_stats = nvme_get_specific_stats, |
197 | +} | 162 | |
198 | + | 163 | .bdrv_detach_aio_context = nvme_detach_aio_context, |
199 | +static uintptr_t xdbg_graph_node_num(XDbgBlockGraphConstructor *gr, void *node) | 164 | .bdrv_attach_aio_context = nvme_attach_aio_context, |
200 | +{ | ||
201 | + uintptr_t ret = (uintptr_t)g_hash_table_lookup(gr->graph_nodes, node); | ||
202 | + | ||
203 | + if (ret != 0) { | ||
204 | + return ret; | ||
205 | + } | ||
206 | + | ||
207 | + /* | ||
208 | + * Start counting from 1, not 0, because 0 interferes with not-found (NULL) | ||
209 | + * answer of g_hash_table_lookup. | ||
210 | + */ | ||
211 | + ret = g_hash_table_size(gr->graph_nodes) + 1; | ||
212 | + g_hash_table_insert(gr->graph_nodes, node, (void *)ret); | ||
213 | + | ||
214 | + return ret; | ||
215 | +} | ||
216 | + | ||
217 | +static void xdbg_graph_add_node(XDbgBlockGraphConstructor *gr, void *node, | ||
218 | + XDbgBlockGraphNodeType type, const char *name) | ||
219 | +{ | ||
220 | + XDbgBlockGraphNode *n; | ||
221 | + | ||
222 | + n = g_new0(XDbgBlockGraphNode, 1); | ||
223 | + | ||
224 | + n->id = xdbg_graph_node_num(gr, node); | ||
225 | + n->type = type; | ||
226 | + n->name = g_strdup(name); | ||
227 | + | ||
228 | + QAPI_LIST_ADD(gr->graph->nodes, n); | ||
229 | +} | ||
230 | + | ||
231 | +static void xdbg_graph_add_edge(XDbgBlockGraphConstructor *gr, void *parent, | ||
232 | + const BdrvChild *child) | ||
233 | +{ | ||
234 | + typedef struct { | ||
235 | + unsigned int flag; | ||
236 | + BlockPermission num; | ||
237 | + } PermissionMap; | ||
238 | + | ||
239 | + static const PermissionMap permissions[] = { | ||
240 | + { BLK_PERM_CONSISTENT_READ, BLOCK_PERMISSION_CONSISTENT_READ }, | ||
241 | + { BLK_PERM_WRITE, BLOCK_PERMISSION_WRITE }, | ||
242 | + { BLK_PERM_WRITE_UNCHANGED, BLOCK_PERMISSION_WRITE_UNCHANGED }, | ||
243 | + { BLK_PERM_RESIZE, BLOCK_PERMISSION_RESIZE }, | ||
244 | + { BLK_PERM_GRAPH_MOD, BLOCK_PERMISSION_GRAPH_MOD }, | ||
245 | + { 0, 0 } | ||
246 | + }; | ||
247 | + const PermissionMap *p; | ||
248 | + XDbgBlockGraphEdge *edge; | ||
249 | + | ||
250 | + QEMU_BUILD_BUG_ON(1UL << (ARRAY_SIZE(permissions) - 1) != BLK_PERM_ALL + 1); | ||
251 | + | ||
252 | + edge = g_new0(XDbgBlockGraphEdge, 1); | ||
253 | + | ||
254 | + edge->parent = xdbg_graph_node_num(gr, parent); | ||
255 | + edge->child = xdbg_graph_node_num(gr, child->bs); | ||
256 | + edge->name = g_strdup(child->name); | ||
257 | + | ||
258 | + for (p = permissions; p->flag; p++) { | ||
259 | + if (p->flag & child->perm) { | ||
260 | + QAPI_LIST_ADD(edge->perm, p->num); | ||
261 | + } | ||
262 | + if (p->flag & child->shared_perm) { | ||
263 | + QAPI_LIST_ADD(edge->shared_perm, p->num); | ||
264 | + } | ||
265 | + } | ||
266 | + | ||
267 | + QAPI_LIST_ADD(gr->graph->edges, edge); | ||
268 | +} | ||
269 | + | ||
270 | + | ||
271 | +XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp) | ||
272 | +{ | ||
273 | + BlockBackend *blk; | ||
274 | + BlockJob *job; | ||
275 | + BlockDriverState *bs; | ||
276 | + BdrvChild *child; | ||
277 | + XDbgBlockGraphConstructor *gr = xdbg_graph_new(); | ||
278 | + | ||
279 | + for (blk = blk_all_next(NULL); blk; blk = blk_all_next(blk)) { | ||
280 | + char *allocated_name = NULL; | ||
281 | + const char *name = blk_name(blk); | ||
282 | + | ||
283 | + if (!*name) { | ||
284 | + name = allocated_name = blk_get_attached_dev_id(blk); | ||
285 | + } | ||
286 | + xdbg_graph_add_node(gr, blk, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_BACKEND, | ||
287 | + name); | ||
288 | + g_free(allocated_name); | ||
289 | + if (blk_root(blk)) { | ||
290 | + xdbg_graph_add_edge(gr, blk, blk_root(blk)); | ||
291 | + } | ||
292 | + } | ||
293 | + | ||
294 | + for (job = block_job_next(NULL); job; job = block_job_next(job)) { | ||
295 | + GSList *el; | ||
296 | + | ||
297 | + xdbg_graph_add_node(gr, job, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_JOB, | ||
298 | + job->job.id); | ||
299 | + for (el = job->nodes; el; el = el->next) { | ||
300 | + xdbg_graph_add_edge(gr, job, (BdrvChild *)el->data); | ||
301 | + } | ||
302 | + } | ||
303 | + | ||
304 | + QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) { | ||
305 | + xdbg_graph_add_node(gr, bs, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_DRIVER, | ||
306 | + bs->node_name); | ||
307 | + QLIST_FOREACH(child, &bs->children, next) { | ||
308 | + xdbg_graph_add_edge(gr, bs, child); | ||
309 | + } | ||
310 | + } | ||
311 | + | ||
312 | + return xdbg_graph_finalize(gr); | ||
313 | +} | ||
314 | + | ||
315 | BlockDriverState *bdrv_lookup_bs(const char *device, | ||
316 | const char *node_name, | ||
317 | Error **errp) | ||
318 | diff --git a/block/block-backend.c b/block/block-backend.c | ||
319 | index XXXXXXX..XXXXXXX 100644 | ||
320 | --- a/block/block-backend.c | ||
321 | +++ b/block/block-backend.c | ||
322 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in, | ||
323 | blk_out->root, off_out, | ||
324 | bytes, read_flags, write_flags); | ||
325 | } | ||
326 | + | ||
327 | +const BdrvChild *blk_root(BlockBackend *blk) | ||
328 | +{ | ||
329 | + return blk->root; | ||
330 | +} | ||
331 | diff --git a/blockdev.c b/blockdev.c | ||
332 | index XXXXXXX..XXXXXXX 100644 | ||
333 | --- a/blockdev.c | ||
334 | +++ b/blockdev.c | ||
335 | @@ -XXX,XX +XXX,XX @@ BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp) | ||
336 | return bdrv_named_nodes_list(errp); | ||
337 | } | ||
338 | |||
339 | +XDbgBlockGraph *qmp_x_debug_query_block_graph(Error **errp) | ||
340 | +{ | ||
341 | + return bdrv_get_xdbg_block_graph(errp); | ||
342 | +} | ||
343 | + | ||
344 | BlockJob *do_blockdev_backup(BlockdevBackup *backup, JobTxn *txn, | ||
345 | Error **errp) | ||
346 | { | ||
347 | -- | 165 | -- |
348 | 2.20.1 | 166 | 2.26.2 |
349 | 167 | ||
350 | diff view generated by jsdifflib |
1 | From: Laurent Vivier <lvivier@redhat.com> | 1 | From: Coiby Xu <coiby.xu@gmail.com> |
---|---|---|---|
2 | 2 | ||
3 | Signed-off-by: Laurent Vivier <lvivier@redhat.com> | 3 | Allow vu_message_read to be replaced by one which will make use of the |
4 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 4 | QIOChannel functions. Thus reading vhost-user message won't stall the |
5 | Message-id: 20181213162727.17438-5-lvivier@redhat.com | 5 | guest. For slave channel, we still use the default vu_message_read. |
6 | [mreitz: Fixed sheepdog_snapshot_create_inode's format string to use | 6 | |
7 | PRIx32 for uint32_ts] | 7 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> |
8 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 8 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> |
9 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | Message-id: 20200918080912.321299-2-coiby.xu@gmail.com | ||
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
9 | --- | 12 | --- |
10 | block/sheepdog.c | 47 +++++++++++++++++----------------------------- | 13 | contrib/libvhost-user/libvhost-user.h | 21 +++++++++++++++++++++ |
11 | block/trace-events | 14 ++++++++++++++ | 14 | contrib/libvhost-user/libvhost-user-glib.c | 2 +- |
12 | 2 files changed, 31 insertions(+), 30 deletions(-) | 15 | contrib/libvhost-user/libvhost-user.c | 14 +++++++------- |
16 | tests/vhost-user-bridge.c | 2 ++ | ||
17 | tools/virtiofsd/fuse_virtio.c | 4 ++-- | ||
18 | 5 files changed, 33 insertions(+), 10 deletions(-) | ||
13 | 19 | ||
14 | diff --git a/block/sheepdog.c b/block/sheepdog.c | 20 | diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h |
15 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/block/sheepdog.c | 22 | --- a/contrib/libvhost-user/libvhost-user.h |
17 | +++ b/block/sheepdog.c | 23 | +++ b/contrib/libvhost-user/libvhost-user.h |
18 | @@ -XXX,XX +XXX,XX @@ | 24 | @@ -XXX,XX +XXX,XX @@ |
19 | #include "sysemu/block-backend.h" | 25 | */ |
20 | #include "qemu/bitops.h" | 26 | #define VHOST_USER_MAX_RAM_SLOTS 32 |
21 | #include "qemu/cutils.h" | 27 | |
22 | +#include "trace.h" | 28 | +#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) |
23 | 29 | + | |
24 | #define SD_PROTO_VER 0x01 | 30 | typedef enum VhostSetConfigType { |
25 | 31 | VHOST_SET_CONFIG_TYPE_MASTER = 0, | |
26 | @@ -XXX,XX +XXX,XX @@ static inline size_t count_data_objs(const struct SheepdogInode *inode) | 32 | VHOST_SET_CONFIG_TYPE_MIGRATION = 1, |
27 | (1UL << inode->block_size_shift)); | 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; | ||
85 | } | ||
86 | diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c | ||
87 | index XXXXXXX..XXXXXXX 100644 | ||
88 | --- a/contrib/libvhost-user/libvhost-user.c | ||
89 | +++ b/contrib/libvhost-user/libvhost-user.c | ||
90 | @@ -XXX,XX +XXX,XX @@ | ||
91 | /* The version of inflight buffer */ | ||
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) | ||
28 | } | 100 | } |
29 | 101 | ||
30 | -#undef DPRINTF | 102 | static bool |
31 | -#ifdef DEBUG_SDOG | 103 | -vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) |
32 | -#define DEBUG_SDOG_PRINT 1 | 104 | +vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) |
33 | -#else | 105 | { |
34 | -#define DEBUG_SDOG_PRINT 0 | 106 | char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {}; |
35 | -#endif | 107 | struct iovec iov = { |
36 | -#define DPRINTF(fmt, args...) \ | 108 | @@ -XXX,XX +XXX,XX @@ vu_process_message_reply(VuDev *dev, const VhostUserMsg *vmsg) |
37 | - do { \ | ||
38 | - if (DEBUG_SDOG_PRINT) { \ | ||
39 | - fprintf(stderr, "%s %d: " fmt, __func__, __LINE__, ##args); \ | ||
40 | - } \ | ||
41 | - } while (0) | ||
42 | - | ||
43 | typedef struct SheepdogAIOCB SheepdogAIOCB; | ||
44 | typedef struct BDRVSheepdogState BDRVSheepdogState; | ||
45 | |||
46 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn void reconnect_to_sdog(void *opaque) | ||
47 | Error *local_err = NULL; | ||
48 | s->fd = get_sheep_fd(s, &local_err); | ||
49 | if (s->fd < 0) { | ||
50 | - DPRINTF("Wait for connection to be established\n"); | ||
51 | + trace_sheepdog_reconnect_to_sdog(); | ||
52 | error_report_err(local_err); | ||
53 | qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000000ULL); | ||
54 | } | ||
55 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn aio_read_response(void *opaque) | ||
56 | break; | ||
57 | case AIOCB_FLUSH_CACHE: | ||
58 | if (rsp.result == SD_RES_INVALID_PARMS) { | ||
59 | - DPRINTF("disable cache since the server doesn't support it\n"); | ||
60 | + trace_sheepdog_aio_read_response(); | ||
61 | s->cache_flags = SD_FLAG_CMD_DIRECT; | ||
62 | rsp.result = SD_RES_SUCCESS; | ||
63 | } | ||
64 | @@ -XXX,XX +XXX,XX @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags, | ||
65 | s->discard_supported = true; | ||
66 | |||
67 | if (snap_id || tag[0]) { | ||
68 | - DPRINTF("%" PRIx32 " snapshot inode was open.\n", vid); | ||
69 | + trace_sheepdog_open(vid); | ||
70 | s->is_snapshot = true; | ||
71 | } | ||
72 | |||
73 | @@ -XXX,XX +XXX,XX @@ static void sd_close(BlockDriverState *bs) | ||
74 | unsigned int wlen, rlen = 0; | ||
75 | int fd, ret; | ||
76 | |||
77 | - DPRINTF("%s\n", s->name); | ||
78 | + trace_sheepdog_close(s->name); | ||
79 | |||
80 | fd = connect_to_sdog(s, &local_err); | ||
81 | if (fd < 0) { | ||
82 | @@ -XXX,XX +XXX,XX @@ static int sd_create_branch(BDRVSheepdogState *s) | ||
83 | char *buf; | ||
84 | bool deleted; | ||
85 | |||
86 | - DPRINTF("%" PRIx32 " is snapshot.\n", s->inode.vdi_id); | ||
87 | + trace_sheepdog_create_branch_snapshot(s->inode.vdi_id); | ||
88 | |||
89 | buf = g_malloc(SD_INODE_SIZE); | ||
90 | |||
91 | @@ -XXX,XX +XXX,XX @@ static int sd_create_branch(BDRVSheepdogState *s) | ||
92 | goto out; | 109 | goto out; |
93 | } | 110 | } |
94 | 111 | ||
95 | - DPRINTF("%" PRIx32 " is created.\n", vid); | 112 | - if (!vu_message_read(dev, dev->slave_fd, &msg_reply)) { |
96 | + trace_sheepdog_create_branch_created(vid); | 113 | + if (!vu_message_read_default(dev, dev->slave_fd, &msg_reply)) { |
97 | 114 | goto out; | |
98 | fd = connect_to_sdog(s, &local_err); | 115 | } |
99 | if (fd < 0) { | 116 | |
100 | @@ -XXX,XX +XXX,XX @@ static int sd_create_branch(BDRVSheepdogState *s) | 117 | @@ -XXX,XX +XXX,XX @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) |
101 | 118 | /* Wait for QEMU to confirm that it's registered the handler for the | |
102 | s->is_snapshot = false; | 119 | * faults. |
103 | ret = 0; | 120 | */ |
104 | - DPRINTF("%" PRIx32 " was newly created.\n", s->inode.vdi_id); | 121 | - if (!vu_message_read(dev, dev->sock, vmsg) || |
105 | + trace_sheepdog_create_branch_new(s->inode.vdi_id); | 122 | + if (!dev->read_msg(dev, dev->sock, vmsg) || |
106 | 123 | vmsg->size != sizeof(vmsg->payload.u64) || | |
107 | out: | 124 | vmsg->payload.u64 != 0) { |
108 | g_free(buf); | 125 | vu_panic(dev, "failed to receive valid ack for postcopy set-mem-table"); |
109 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn sd_co_rw_vector(SheepdogAIOCB *acb) | 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); | ||
110 | } | 157 | } |
111 | 158 | return; | |
112 | if (create) { | ||
113 | - DPRINTF("update ino (%" PRIu32 ") %" PRIu64 " %" PRIu64 " %ld\n", | ||
114 | - inode->vdi_id, oid, | ||
115 | - vid_to_data_oid(inode->data_vdi_id[idx], idx), idx); | ||
116 | + trace_sheepdog_co_rw_vector_update(inode->vdi_id, oid, | ||
117 | + vid_to_data_oid(inode->data_vdi_id[idx], idx), | ||
118 | + idx); | ||
119 | oid = vid_to_data_oid(inode->vdi_id, idx); | ||
120 | - DPRINTF("new oid %" PRIx64 "\n", oid); | ||
121 | + trace_sheepdog_co_rw_vector_new(oid); | ||
122 | } | ||
123 | |||
124 | aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, create, | ||
125 | @@ -XXX,XX +XXX,XX @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) | ||
126 | SheepdogInode *inode; | ||
127 | unsigned int datalen; | ||
128 | |||
129 | - DPRINTF("sn_info: name %s id_str %s s: name %s vm_state_size %" PRId64 " " | ||
130 | - "is_snapshot %d\n", sn_info->name, sn_info->id_str, | ||
131 | - s->name, sn_info->vm_state_size, s->is_snapshot); | ||
132 | + trace_sheepdog_snapshot_create_info(sn_info->name, sn_info->id_str, s->name, | ||
133 | + sn_info->vm_state_size, s->is_snapshot); | ||
134 | |||
135 | if (s->is_snapshot) { | ||
136 | error_report("You can't create a snapshot of a snapshot VDI, " | ||
137 | @@ -XXX,XX +XXX,XX @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) | ||
138 | return -EINVAL; | ||
139 | } | 159 | } |
140 | 160 | diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c | |
141 | - DPRINTF("%s %s\n", sn_info->name, sn_info->id_str); | ||
142 | + trace_sheepdog_snapshot_create(sn_info->name, sn_info->id_str); | ||
143 | |||
144 | s->inode.vm_state_size = sn_info->vm_state_size; | ||
145 | s->inode.vm_clock_nsec = sn_info->vm_clock_nsec; | ||
146 | @@ -XXX,XX +XXX,XX @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) | ||
147 | } | ||
148 | |||
149 | memcpy(&s->inode, inode, datalen); | ||
150 | - DPRINTF("s->inode: name %s snap_id %x oid %x\n", | ||
151 | - s->inode.name, s->inode.snap_id, s->inode.vdi_id); | ||
152 | + trace_sheepdog_snapshot_create_inode(s->inode.name, s->inode.snap_id, | ||
153 | + s->inode.vdi_id); | ||
154 | |||
155 | cleanup: | ||
156 | g_free(inode); | ||
157 | diff --git a/block/trace-events b/block/trace-events | ||
158 | index XXXXXXX..XXXXXXX 100644 | 161 | index XXXXXXX..XXXXXXX 100644 |
159 | --- a/block/trace-events | 162 | --- a/tests/vhost-user-bridge.c |
160 | +++ b/block/trace-events | 163 | +++ b/tests/vhost-user-bridge.c |
161 | @@ -XXX,XX +XXX,XX @@ file_xfs_discard(const char *error) "cannot punch hole (%s)" | 164 | @@ -XXX,XX +XXX,XX @@ vubr_accept_cb(int sock, void *ctx) |
162 | file_FindEjectableOpticalMedia(const char *media) "Matching using %s" | 165 | VHOST_USER_BRIDGE_MAX_QUEUES, |
163 | file_setup_cdrom(const char *partition) "Using %s as optical disc" | 166 | conn_fd, |
164 | file_hdev_is_sg(int type, int version) "SG device found: type=%d, version=%d" | 167 | vubr_panic, |
165 | + | 168 | + NULL, |
166 | +# block/sheepdog.c | 169 | vubr_set_watch, |
167 | +sheepdog_reconnect_to_sdog(void) "Wait for connection to be established" | 170 | vubr_remove_watch, |
168 | +sheepdog_aio_read_response(void) "disable cache since the server doesn't support it" | 171 | &vuiface)) { |
169 | +sheepdog_open(uint32_t vid) "0x%" PRIx32 " snapshot inode was open" | 172 | @@ -XXX,XX +XXX,XX @@ vubr_new(const char *path, bool client) |
170 | +sheepdog_close(const char *name) "%s" | 173 | VHOST_USER_BRIDGE_MAX_QUEUES, |
171 | +sheepdog_create_branch_snapshot(uint32_t vdi) "0x%" PRIx32 " is snapshot" | 174 | dev->sock, |
172 | +sheepdog_create_branch_created(uint32_t vdi) "0x%" PRIx32 " is created" | 175 | vubr_panic, |
173 | +sheepdog_create_branch_new(uint32_t vdi) "0x%" PRIx32 " was newly created" | 176 | + NULL, |
174 | +sheepdog_co_rw_vector_update(uint32_t vdi, uint64_t oid, uint64_t data, long idx) "update ino (%" PRIu32 ") %" PRIu64 " %" PRIu64 " %ld" | 177 | vubr_set_watch, |
175 | +sheepdog_co_rw_vector_new(uint64_t oid) "new oid 0x%" PRIx64 | 178 | vubr_remove_watch, |
176 | +sheepdog_snapshot_create_info(const char *sn_name, const char *id, const char *name, int64_t size, int is_snapshot) "sn_info: name %s id_str %s s: name %s vm_state_size %" PRId64 " " "is_snapshot %d" | 179 | &vuiface)) { |
177 | +sheepdog_snapshot_create(const char *sn_name, const char *id) "%s %s" | 180 | diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c |
178 | +sheepdog_snapshot_create_inode(const char *name, uint32_t snap, uint32_t vdi) "s->inode: name %s snap_id 0x%" PRIx32 " vdi 0x%" PRIx32 | 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; | ||
194 | } | ||
179 | -- | 195 | -- |
180 | 2.20.1 | 196 | 2.26.2 |
181 | 197 | ||
182 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Coiby Xu <coiby.xu@gmail.com> | ||
1 | 2 | ||
3 | When the client is running in gdb and quit command is run in gdb, | ||
4 | QEMU will still dispatch the event which will cause segment fault in | ||
5 | the callback function. | ||
6 | |||
7 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> | ||
8 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
9 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> | ||
10 | Message-id: 20200918080912.321299-3-coiby.xu@gmail.com | ||
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
12 | --- | ||
13 | contrib/libvhost-user/libvhost-user.c | 1 + | ||
14 | 1 file changed, 1 insertion(+) | ||
15 | |||
16 | diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/contrib/libvhost-user/libvhost-user.c | ||
19 | +++ b/contrib/libvhost-user/libvhost-user.c | ||
20 | @@ -XXX,XX +XXX,XX @@ vu_deinit(VuDev *dev) | ||
21 | } | ||
22 | |||
23 | if (vq->kick_fd != -1) { | ||
24 | + dev->remove_watch(dev, vq->kick_fd); | ||
25 | close(vq->kick_fd); | ||
26 | vq->kick_fd = -1; | ||
27 | } | ||
28 | -- | ||
29 | 2.26.2 | ||
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: Li Qiang <liq3ea@163.com> | 1 | From: Coiby Xu <coiby.xu@gmail.com> |
---|---|---|---|
2 | 2 | ||
3 | When it is zero, it causes segv. | 3 | Move the constants from hw/core/qdev-properties.c to |
4 | Using following command: | 4 | util/block-helpers.h so that knowledge of the min/max values is |
5 | 5 | ||
6 | "-drive file=//home/test/test1.img,if=none,id=id0 | 6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
7 | -device nvme,drive=id0,serial=test,num_queues=0" | 7 | Signed-off-by: Coiby Xu <coiby.xu@gmail.com> |
8 | causes following Backtrack: | 8 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> |
9 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> | ||
10 | Acked-by: Eduardo Habkost <ehabkost@redhat.com> | ||
11 | Message-id: 20200918080912.321299-5-coiby.xu@gmail.com | ||
12 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
13 | --- | ||
14 | util/block-helpers.h | 19 +++++++++++++ | ||
15 | hw/core/qdev-properties-system.c | 31 ++++----------------- | ||
16 | util/block-helpers.c | 46 ++++++++++++++++++++++++++++++++ | ||
17 | util/meson.build | 1 + | ||
18 | 4 files changed, 71 insertions(+), 26 deletions(-) | ||
19 | create mode 100644 util/block-helpers.h | ||
20 | create mode 100644 util/block-helpers.c | ||
9 | 21 | ||
10 | Thread 4 "qemu-system-x86" received signal SIGSEGV, Segmentation fault. | 22 | diff --git a/util/block-helpers.h b/util/block-helpers.h |
11 | [Switching to Thread 0x7fffe9735700 (LWP 30952)] | 23 | new file mode 100644 |
12 | 0x0000555555a7a77c in nvme_start_ctrl (n=0x5555577473f0) at hw/block/nvme.c:825 | 24 | index XXXXXXX..XXXXXXX |
13 | 825 if (unlikely(n->cq[0])) { | 25 | --- /dev/null |
14 | (gdb) bt | 26 | +++ b/util/block-helpers.h |
15 | 0 0x0000555555a7a77c in nvme_start_ctrl (n=0x5555577473f0) | 27 | @@ -XXX,XX +XXX,XX @@ |
16 | at hw/block/nvme.c:825 | 28 | +#ifndef BLOCK_HELPERS_H |
17 | 1 0x0000555555a7af7f in nvme_write_bar (n=0x5555577473f0, offset=20, | 29 | +#define BLOCK_HELPERS_H |
18 | data=4587521, size=4) at hw/block/nvme.c:969 | 30 | + |
19 | 2 0x0000555555a7b81a in nvme_mmio_write (opaque=0x5555577473f0, addr=20, | 31 | +#include "qemu/units.h" |
20 | data=4587521, size=4) at hw/block/nvme.c:1163 | 32 | + |
21 | 3 0x0000555555869236 in memory_region_write_accessor (mr=0x555557747cd0, | 33 | +/* lower limit is sector size */ |
22 | addr=20, value=0x7fffe97320f8, size=4, shift=0, mask=4294967295, attrs=...) | 34 | +#define MIN_BLOCK_SIZE INT64_C(512) |
23 | at /home/test/qemu1/qemu/memory.c:502 | 35 | +#define MIN_BLOCK_SIZE_STR "512 B" |
24 | 4 0x0000555555869446 in access_with_adjusted_size (addr=20, | 36 | +/* |
25 | value=0x7fffe97320f8, size=4, access_size_min=2, access_size_max=8, | 37 | + * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and |
26 | access_fn=0x55555586914d <memory_region_write_accessor>, | 38 | + * matches qcow2 cluster size limit |
27 | mr=0x555557747cd0, attrs=...) at /home/test/qemu1/qemu/memory.c:568 | 39 | + */ |
28 | 5 0x000055555586c479 in memory_region_dispatch_write (mr=0x555557747cd0, | 40 | +#define MAX_BLOCK_SIZE (2 * MiB) |
29 | addr=20, data=4587521, size=4, attrs=...) | 41 | +#define MAX_BLOCK_SIZE_STR "2 MiB" |
30 | at /home/test/qemu1/qemu/memory.c:1499 | 42 | + |
31 | 6 0x00005555558030af in flatview_write_continue (fv=0x7fffe0061130, | 43 | +void check_block_size(const char *id, const char *name, int64_t value, |
32 | addr=4273930260, attrs=..., buf=0x7ffff7ff0028 "\001", len=4, addr1=20, | 44 | + Error **errp); |
33 | l=4, mr=0x555557747cd0) at /home/test/qemu1/qemu/exec.c:3234 | 45 | + |
34 | 7 0x00005555558031f9 in flatview_write (fv=0x7fffe0061130, addr=4273930260, | 46 | +#endif /* BLOCK_HELPERS_H */ |
35 | attrs=..., buf=0x7ffff7ff0028 "\001", len=4) | 47 | diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c |
36 | at /home/test/qemu1/qemu/exec.c:3273 | ||
37 | 8 0x00005555558034ff in address_space_write ( | ||
38 | ---Type <return> to continue, or q <return> to quit--- | ||
39 | as=0x555556758480 <address_space_memory>, addr=4273930260, attrs=..., | ||
40 | buf=0x7ffff7ff0028 "\001", len=4) at /home/test/qemu1/qemu/exec.c:3363 | ||
41 | 9 0x0000555555803550 in address_space_rw ( | ||
42 | as=0x555556758480 <address_space_memory>, addr=4273930260, attrs=..., | ||
43 | buf=0x7ffff7ff0028 "\001", len=4, is_write=true) | ||
44 | at /home/test/qemu1/qemu/exec.c:3374 | ||
45 | 10 0x00005555558884a1 in kvm_cpu_exec (cpu=0x555556920e40) | ||
46 | at /home/test/qemu1/qemu/accel/kvm/kvm-all.c:2031 | ||
47 | 11 0x000055555584cd9d in qemu_kvm_cpu_thread_fn (arg=0x555556920e40) | ||
48 | at /home/test/qemu1/qemu/cpus.c:1281 | ||
49 | 12 0x0000555555dbaf6d in qemu_thread_start (args=0x5555569438a0) | ||
50 | at util/qemu-thread-posix.c:502 | ||
51 | 13 0x00007ffff5dc86db in start_thread (arg=0x7fffe9735700) | ||
52 | at pthread_create.c:463 | ||
53 | 14 0x00007ffff5af188f in clone () | ||
54 | at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | ||
55 | |||
56 | Signed-off-by: Li Qiang <liq3ea@163.com> | ||
57 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
58 | Message-id: 20190120055558.32984-3-liq3ea@163.com | ||
59 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
60 | --- | ||
61 | hw/block/nvme.c | 5 +++++ | ||
62 | 1 file changed, 5 insertions(+) | ||
63 | |||
64 | diff --git a/hw/block/nvme.c b/hw/block/nvme.c | ||
65 | index XXXXXXX..XXXXXXX 100644 | 48 | index XXXXXXX..XXXXXXX 100644 |
66 | --- a/hw/block/nvme.c | 49 | --- a/hw/core/qdev-properties-system.c |
67 | +++ b/hw/block/nvme.c | 50 | +++ b/hw/core/qdev-properties-system.c |
68 | @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) | 51 | @@ -XXX,XX +XXX,XX @@ |
69 | int64_t bs_size; | 52 | #include "sysemu/blockdev.h" |
70 | uint8_t *pci_conf; | 53 | #include "net/net.h" |
71 | 54 | #include "hw/pci/pci.h" | |
72 | + if (!n->num_queues) { | 55 | +#include "util/block-helpers.h" |
73 | + error_setg(errp, "num_queues can't be zero"); | 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 | ||
117 | @@ -XXX,XX +XXX,XX @@ | ||
118 | +/* | ||
119 | + * Block utility functions | ||
120 | + * | ||
121 | + * Copyright IBM, Corp. 2011 | ||
122 | + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> | ||
123 | + * | ||
124 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. | ||
125 | + * See the COPYING file in the top-level directory. | ||
126 | + */ | ||
127 | + | ||
128 | +#include "qemu/osdep.h" | ||
129 | +#include "qapi/error.h" | ||
130 | +#include "qapi/qmp/qerror.h" | ||
131 | +#include "block-helpers.h" | ||
132 | + | ||
133 | +/** | ||
134 | + * check_block_size: | ||
135 | + * @id: The unique ID of the object | ||
136 | + * @name: The name of the property being validated | ||
137 | + * @value: The block size in bytes | ||
138 | + * @errp: A pointer to an area to store an error | ||
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); | ||
74 | + return; | 152 | + return; |
75 | + } | 153 | + } |
76 | + | 154 | + |
77 | if (!n->conf.blk) { | 155 | + /* We rely on power-of-2 blocksizes for bitmasks */ |
78 | error_setg(errp, "drive property not set"); | 156 | + if ((value & (value - 1)) != 0) { |
79 | return; | 157 | + error_setg(errp, |
158 | + "Property %s.%s doesn't take value '%" PRId64 | ||
159 | + "', it's not a power of 2", | ||
160 | + id, name, value); | ||
161 | + return; | ||
162 | + } | ||
163 | +} | ||
164 | diff --git a/util/meson.build b/util/meson.build | ||
165 | index XXXXXXX..XXXXXXX 100644 | ||
166 | --- a/util/meson.build | ||
167 | +++ b/util/meson.build | ||
168 | @@ -XXX,XX +XXX,XX @@ if have_block | ||
169 | util_ss.add(files('nvdimm-utils.c')) | ||
170 | util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) | ||
171 | util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) | ||
172 | + util_ss.add(files('block-helpers.c')) | ||
173 | util_ss.add(files('qemu-coroutine-sleep.c')) | ||
174 | util_ss.add(files('qemu-co-shared-resource.c')) | ||
175 | util_ss.add(files('thread-pool.c', 'qemu-timer.c')) | ||
80 | -- | 176 | -- |
81 | 2.20.1 | 177 | 2.26.2 |
82 | 178 | ||
83 | 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 |
1 | By default, qemu-nbd binds to 0.0.0.0. However, we then proceed to | 1 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
---|---|---|---|
2 | connect to "localhost". Usually, this works out fine; but if this test | 2 | Message-id: 20200924151549.913737-3-stefanha@redhat.com |
3 | is run concurrently, some other test function may have bound a different | 3 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
4 | server to ::1 (on the same port -- you can bind different serves to the | ||
5 | same port, as long as one is on IPv4 and the other on IPv6). | ||
6 | |||
7 | So running qemu-nbd works, it can bind to 0.0.0.0:NBD_PORT. But | ||
8 | potentially a concurrent test has successfully taken [::1]:NBD_PORT. In | ||
9 | this case, trying to connect to "localhost" will lead us to the IPv6 | ||
10 | instance, where we do not want to end up. | ||
11 | |||
12 | Fix this by just binding to "localhost". This will make qemu-nbd error | ||
13 | out immediately and not give us cryptic errors later. | ||
14 | |||
15 | (Also, it will allow us to just try a different port as of a future | ||
16 | patch.) | ||
17 | |||
18 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
19 | Message-id: 20181221234750.23577-3-mreitz@redhat.com | ||
20 | Reviewed-by: John Snow <jsnow@redhat.com> | ||
21 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
22 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
23 | --- | 4 | --- |
24 | tests/qemu-iotests/147 | 2 +- | 5 | util/vhost-user-server.c | 2 +- |
25 | 1 file changed, 1 insertion(+), 1 deletion(-) | 6 | 1 file changed, 1 insertion(+), 1 deletion(-) |
26 | 7 | ||
27 | diff --git a/tests/qemu-iotests/147 b/tests/qemu-iotests/147 | 8 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c |
28 | index XXXXXXX..XXXXXXX 100755 | 9 | index XXXXXXX..XXXXXXX 100644 |
29 | --- a/tests/qemu-iotests/147 | 10 | --- a/util/vhost-user-server.c |
30 | +++ b/tests/qemu-iotests/147 | 11 | +++ b/util/vhost-user-server.c |
31 | @@ -XXX,XX +XXX,XX @@ class QemuNBD(NBDBlockdevAddBase): | 12 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, |
32 | self.assertEqual(qemu_nbd('-f', imgfmt, test_img, *args), 0) | 13 | return false; |
33 | 14 | } | |
34 | def test_inet(self): | 15 | |
35 | - self._server_up('-p', str(NBD_PORT)) | 16 | - /* zero out unspecified fileds */ |
36 | + self._server_up('-b', 'localhost', '-p', str(NBD_PORT)) | 17 | + /* zero out unspecified fields */ |
37 | address = { 'type': 'inet', | 18 | *server = (VuServer) { |
38 | 'data': { | 19 | .listener = listener, |
39 | 'host': 'localhost', | 20 | .vu_iface = vu_iface, |
40 | -- | 21 | -- |
41 | 2.20.1 | 22 | 2.26.2 |
42 | 23 | ||
43 | diff view generated by jsdifflib |
1 | From: Li Qiang <liq3ea@163.com> | 1 | We already have access to the value with the correct type (ioc and sioc |
---|---|---|---|
2 | are the same QIOChannel). | ||
2 | 3 | ||
3 | Signed-off-by: Li Qiang <liq3ea@163.com> | 4 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
4 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 5 | Message-id: 20200924151549.913737-4-stefanha@redhat.com |
5 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 6 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
6 | Message-id: 20190120055558.32984-2-liq3ea@163.com | ||
7 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
8 | --- | 7 | --- |
9 | hw/block/nvme.c | 2 +- | 8 | util/vhost-user-server.c | 2 +- |
10 | 1 file changed, 1 insertion(+), 1 deletion(-) | 9 | 1 file changed, 1 insertion(+), 1 deletion(-) |
11 | 10 | ||
12 | diff --git a/hw/block/nvme.c b/hw/block/nvme.c | 11 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c |
13 | index XXXXXXX..XXXXXXX 100644 | 12 | index XXXXXXX..XXXXXXX 100644 |
14 | --- a/hw/block/nvme.c | 13 | --- a/util/vhost-user-server.c |
15 | +++ b/hw/block/nvme.c | 14 | +++ b/util/vhost-user-server.c |
16 | @@ -XXX,XX +XXX,XX @@ static void nvme_instance_init(Object *obj) | 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); | ||
17 | } | 22 | } |
18 | 23 | ||
19 | static const TypeInfo nvme_info = { | ||
20 | - .name = "nvme", | ||
21 | + .name = TYPE_NVME, | ||
22 | .parent = TYPE_PCI_DEVICE, | ||
23 | .instance_size = sizeof(NvmeCtrl), | ||
24 | .class_init = nvme_class_init, | ||
25 | -- | 24 | -- |
26 | 2.20.1 | 25 | 2.26.2 |
27 | 26 | ||
28 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Explicitly deleting watches is not necessary since libvhost-user calls | ||
2 | remove_watch() during vu_deinit(). Add an assertion to check this | ||
3 | though. | ||
1 | 4 | ||
5 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
6 | Message-id: 20200924151549.913737-5-stefanha@redhat.com | ||
7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | --- | ||
9 | util/vhost-user-server.c | 19 ++++--------------- | ||
10 | 1 file changed, 4 insertions(+), 15 deletions(-) | ||
11 | |||
12 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/util/vhost-user-server.c | ||
15 | +++ b/util/vhost-user-server.c | ||
16 | @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) | ||
17 | /* When this is set vu_client_trip will stop new processing vhost-user message */ | ||
18 | server->sioc = NULL; | ||
19 | |||
20 | - VuFdWatch *vu_fd_watch, *next; | ||
21 | - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { | ||
22 | - aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, | ||
23 | - NULL, NULL, NULL); | ||
24 | - } | ||
25 | - | ||
26 | - while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { | ||
27 | - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { | ||
28 | - if (!vu_fd_watch->processing) { | ||
29 | - QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); | ||
30 | - g_free(vu_fd_watch); | ||
31 | - } | ||
32 | - } | ||
33 | - } | ||
34 | - | ||
35 | while (server->processing_msg) { | ||
36 | if (server->ioc->read_coroutine) { | ||
37 | server->ioc->read_coroutine = NULL; | ||
38 | @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) | ||
39 | } | ||
40 | |||
41 | vu_deinit(&server->vu_dev); | ||
42 | + | ||
43 | + /* vu_deinit() should have called remove_watch() */ | ||
44 | + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); | ||
45 | + | ||
46 | object_unref(OBJECT(sioc)); | ||
47 | object_unref(OBJECT(server->ioc)); | ||
48 | } | ||
49 | -- | ||
50 | 2.26.2 | ||
51 | diff view generated by jsdifflib |
1 | From: Li Qiang <liq3ea@163.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 | There is no need to make another reference. | 5 | This fixes the req_data memory leak in vu_block_virtio_process_req(). |
4 | 6 | ||
5 | Signed-off-by: Li Qiang <liq3ea@163.com> | 7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
6 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 8 | Message-id: 20200924151549.913737-6-stefanha@redhat.com |
7 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 9 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
8 | Message-id: 20190120055558.32984-4-liq3ea@163.com | ||
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
10 | --- | 10 | --- |
11 | hw/block/nvme.c | 8 ++++---- | 11 | block/export/vhost-user-blk-server.c | 68 +++++++++------------------- |
12 | 1 file changed, 4 insertions(+), 4 deletions(-) | 12 | 1 file changed, 21 insertions(+), 47 deletions(-) |
13 | 13 | ||
14 | diff --git a/hw/block/nvme.c b/hw/block/nvme.c | 14 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c |
15 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/hw/block/nvme.c | 16 | --- a/block/export/vhost-user-blk-server.c |
17 | +++ b/hw/block/nvme.c | 17 | +++ b/block/export/vhost-user-blk-server.c |
18 | @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) | 18 | @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { |
19 | pci_conf[PCI_INTERRUPT_PIN] = 1; | 19 | }; |
20 | pci_config_set_prog_interface(pci_dev->config, 0x2); | 20 | |
21 | pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS); | 21 | typedef struct VuBlockReq { |
22 | - pcie_endpoint_cap_init(&n->parent_obj, 0x80); | 22 | - VuVirtqElement *elem; |
23 | + pcie_endpoint_cap_init(pci_dev, 0x80); | 23 | + VuVirtqElement elem; |
24 | 24 | int64_t sector_num; | |
25 | n->num_namespaces = 1; | 25 | size_t size; |
26 | n->reg_size = pow2ceil(0x1004 + 2 * (n->num_queues + 1) * 4); | 26 | struct virtio_blk_inhdr *in; |
27 | @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) | 27 | @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) |
28 | 28 | VuDev *vu_dev = &req->server->vu_dev; | |
29 | memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, | 29 | |
30 | "nvme", n->reg_size); | 30 | /* IO size with 1 extra status byte */ |
31 | - pci_register_bar(&n->parent_obj, 0, | 31 | - vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); |
32 | + pci_register_bar(pci_dev, 0, | 32 | + vu_queue_push(vu_dev, req->vq, &req->elem, req->size + 1); |
33 | PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64, | 33 | vu_queue_notify(vu_dev, req->vq); |
34 | &n->iomem); | 34 | |
35 | - msix_init_exclusive_bar(&n->parent_obj, n->num_queues, 4, NULL); | 35 | - if (req->elem) { |
36 | + msix_init_exclusive_bar(pci_dev, n->num_queues, 4, NULL); | 36 | - free(req->elem); |
37 | 37 | - } | |
38 | id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID)); | 38 | - |
39 | id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID)); | 39 | - g_free(req); |
40 | @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) | 40 | + free(req); |
41 | n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz)); | 41 | } |
42 | memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n, | 42 | |
43 | "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz)); | 43 | static VuBlockDev *get_vu_block_device_by_server(VuServer *server) |
44 | - pci_register_bar(&n->parent_obj, NVME_CMBLOC_BIR(n->bar.cmbloc), | 44 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_flush(VuBlockReq *req) |
45 | + pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc), | 45 | blk_co_flush(backend); |
46 | PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 | | 46 | } |
47 | PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem); | 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) | ||
55 | { | ||
56 | - struct req_data *data = opaque; | ||
57 | - VuServer *server = data->server; | ||
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; | ||
72 | + | ||
73 | /* refer to hw/block/virtio_blk.c */ | ||
74 | if (elem->out_num < 1 || elem->in_num < 1) { | ||
75 | error_report("virtio-blk request missing headers"); | ||
76 | - free(elem); | ||
77 | - return; | ||
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; | ||
95 | } | ||
96 | |||
97 | static void vu_block_process_vq(VuDev *vu_dev, int idx) | ||
98 | { | ||
99 | - VuServer *server; | ||
100 | - VuVirtq *vq; | ||
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; | ||
124 | + | ||
125 | + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); | ||
126 | + if (!req) { | ||
127 | break; | ||
128 | } | ||
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 | } | ||
137 | } | ||
48 | 138 | ||
49 | -- | 139 | -- |
50 | 2.20.1 | 140 | 2.26.2 |
51 | 141 | ||
52 | 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 |
1 | From: "Richard W.M. Jones" <rjones@redhat.com> | 1 | Unexpected EOF is an error that must be reported. |
---|---|---|---|
2 | 2 | ||
3 | On FreeBSD 11.2: | 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(-) | ||
4 | 9 | ||
5 | $ nbdkit memory size=1M --run './qemu-io -f raw -c "aio_write 0 512" $nbd' | 10 | diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c |
6 | Parsing error: non-numeric argument, or extraneous/unrecognized suffix -- aio_write | ||
7 | |||
8 | After main option parsing, we reinitialize optind so we can parse each | ||
9 | command. However reinitializing optind to 0 does not work on FreeBSD. | ||
10 | What happens when you do this is optind remains 0 after the option | ||
11 | parsing loop, and the result is we try to parse argv[optind] == | ||
12 | argv[0] == "aio_write" as if it was the first parameter. | ||
13 | |||
14 | The FreeBSD manual page says: | ||
15 | |||
16 | In order to use getopt() to evaluate multiple sets of arguments, or to | ||
17 | evaluate a single set of arguments multiple times, the variable optreset | ||
18 | must be set to 1 before the second and each additional set of calls to | ||
19 | getopt(), and the variable optind must be reinitialized. | ||
20 | |||
21 | (From the rest of the man page it is clear that optind must be | ||
22 | reinitialized to 1). | ||
23 | |||
24 | The glibc man page says: | ||
25 | |||
26 | A program that scans multiple argument vectors, or rescans the same | ||
27 | vector more than once, and wants to make use of GNU extensions such as | ||
28 | '+' and '-' at the start of optstring, or changes the value of | ||
29 | POSIXLY_CORRECT between scans, must reinitialize getopt() by resetting | ||
30 | optind to 0, rather than the traditional value of 1. (Resetting to 0 | ||
31 | forces the invocation of an internal initialization routine that | ||
32 | rechecks POSIXLY_CORRECT and checks for GNU extensions in optstring.) | ||
33 | |||
34 | This commit introduces an OS-portability function called | ||
35 | qemu_reset_optind which provides a way of resetting optind that works | ||
36 | on FreeBSD and platforms that use optreset, while keeping it the same | ||
37 | as now on other platforms. | ||
38 | |||
39 | Note that the qemu codebase sets optind in many other places, but in | ||
40 | those other places it's setting a local variable and not using getopt. | ||
41 | This change is only needed in places where we are using getopt and the | ||
42 | associated global variable optind. | ||
43 | |||
44 | Signed-off-by: Richard W.M. Jones <rjones@redhat.com> | ||
45 | Message-id: 20190118101114.11759-2-rjones@redhat.com | ||
46 | Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> | ||
47 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
48 | Signed-off-by: Max Reitz <mreitz@redhat.com> | ||
49 | --- | ||
50 | configure | 14 ++++++++++++++ | ||
51 | include/qemu/osdep.h | 16 ++++++++++++++++ | ||
52 | qemu-img.c | 2 +- | ||
53 | qemu-io-cmds.c | 2 +- | ||
54 | 4 files changed, 32 insertions(+), 2 deletions(-) | ||
55 | |||
56 | diff --git a/configure b/configure | ||
57 | index XXXXXXX..XXXXXXX 100755 | ||
58 | --- a/configure | ||
59 | +++ b/configure | ||
60 | @@ -XXX,XX +XXX,XX @@ if compile_prog "" "" ; then | ||
61 | signalfd=yes | ||
62 | fi | ||
63 | |||
64 | +# check if optreset global is declared by <getopt.h> | ||
65 | +optreset="no" | ||
66 | +cat > $TMPC << EOF | ||
67 | +#include <getopt.h> | ||
68 | +int main(void) { return optreset; } | ||
69 | +EOF | ||
70 | + | ||
71 | +if compile_prog "" "" ; then | ||
72 | + optreset=yes | ||
73 | +fi | ||
74 | + | ||
75 | # check if eventfd is supported | ||
76 | eventfd=no | ||
77 | cat > $TMPC << EOF | ||
78 | @@ -XXX,XX +XXX,XX @@ fi | ||
79 | if test "$signalfd" = "yes" ; then | ||
80 | echo "CONFIG_SIGNALFD=y" >> $config_host_mak | ||
81 | fi | ||
82 | +if test "$optreset" = "yes" ; then | ||
83 | + echo "HAVE_OPTRESET=y" >> $config_host_mak | ||
84 | +fi | ||
85 | if test "$tcg" = "yes"; then | ||
86 | echo "CONFIG_TCG=y" >> $config_host_mak | ||
87 | if test "$tcg_interpreter" = "yes" ; then | ||
88 | diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h | ||
89 | index XXXXXXX..XXXXXXX 100644 | 11 | index XXXXXXX..XXXXXXX 100644 |
90 | --- a/include/qemu/osdep.h | 12 | --- a/util/vhost-user-server.c |
91 | +++ b/include/qemu/osdep.h | 13 | +++ b/util/vhost-user-server.c |
92 | @@ -XXX,XX +XXX,XX @@ extern int daemon(int, int); | 14 | @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) |
93 | #include <ctype.h> | 15 | }; |
94 | #include <errno.h> | 16 | if (vmsg->size) { |
95 | #include <fcntl.h> | 17 | rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); |
96 | +#include <getopt.h> | 18 | - if (rc == -1) { |
97 | #include <sys/stat.h> | 19 | - error_report_err(local_err); |
98 | #include <sys/time.h> | 20 | + if (rc != 1) { |
99 | #include <assert.h> | 21 | + if (local_err) { |
100 | @@ -XXX,XX +XXX,XX @@ extern int qemu_icache_linesize_log; | 22 | + error_report_err(local_err); |
101 | extern int qemu_dcache_linesize; | 23 | + } |
102 | extern int qemu_dcache_linesize_log; | 24 | goto fail; |
103 | |||
104 | +/* | ||
105 | + * After using getopt or getopt_long, if you need to parse another set | ||
106 | + * of options, then you must reset optind. Unfortunately the way to | ||
107 | + * do this varies between implementations of getopt. | ||
108 | + */ | ||
109 | +static inline void qemu_reset_optind(void) | ||
110 | +{ | ||
111 | +#ifdef HAVE_OPTRESET | ||
112 | + optind = 1; | ||
113 | + optreset = 1; | ||
114 | +#else | ||
115 | + optind = 0; | ||
116 | +#endif | ||
117 | +} | ||
118 | + | ||
119 | #endif | ||
120 | diff --git a/qemu-img.c b/qemu-img.c | ||
121 | index XXXXXXX..XXXXXXX 100644 | ||
122 | --- a/qemu-img.c | ||
123 | +++ b/qemu-img.c | ||
124 | @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) | ||
125 | return 0; | ||
126 | } | ||
127 | argv += optind; | ||
128 | - optind = 0; | ||
129 | + qemu_reset_optind(); | ||
130 | |||
131 | if (!trace_init_backends()) { | ||
132 | exit(1); | ||
133 | diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c | ||
134 | index XXXXXXX..XXXXXXX 100644 | ||
135 | --- a/qemu-io-cmds.c | ||
136 | +++ b/qemu-io-cmds.c | ||
137 | @@ -XXX,XX +XXX,XX @@ static int command(BlockBackend *blk, const cmdinfo_t *ct, int argc, | ||
138 | } | 25 | } |
139 | } | 26 | } |
140 | |||
141 | - optind = 0; | ||
142 | + qemu_reset_optind(); | ||
143 | return ct->cfunc(blk, argc, argv); | ||
144 | } | ||
145 | |||
146 | -- | 27 | -- |
147 | 2.20.1 | 28 | 2.26.2 |
148 | 29 | ||
149 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
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. | ||
1 | 4 | ||
5 | Rework the lifecycle to solve these safety issues. | ||
6 | |||
7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | Message-id: 20200924151549.913737-10-stefanha@redhat.com | ||
9 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
10 | --- | ||
11 | util/vhost-user-server.h | 29 ++-- | ||
12 | block/export/vhost-user-blk-server.c | 9 +- | ||
13 | util/vhost-user-server.c | 245 +++++++++++++++------------ | ||
14 | 3 files changed, 155 insertions(+), 128 deletions(-) | ||
15 | |||
16 | diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/util/vhost-user-server.h | ||
19 | +++ b/util/vhost-user-server.h | ||
20 | @@ -XXX,XX +XXX,XX @@ | ||
21 | #include "qapi/error.h" | ||
22 | #include "standard-headers/linux/virtio_blk.h" | ||
23 | |||
24 | +/* A kick fd that we monitor on behalf of libvhost-user */ | ||
25 | typedef struct VuFdWatch { | ||
26 | VuDev *vu_dev; | ||
27 | int fd; /*kick fd*/ | ||
28 | void *pvt; | ||
29 | vu_watch_cb cb; | ||
30 | - bool processing; | ||
31 | QTAILQ_ENTRY(VuFdWatch) next; | ||
32 | } VuFdWatch; | ||
33 | |||
34 | -typedef struct VuServer VuServer; | ||
35 | - | ||
36 | -struct VuServer { | ||
37 | +/** | ||
38 | + * VuServer: | ||
39 | + * A vhost-user server instance with user-defined VuDevIface callbacks. | ||
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); | ||
330 | + } | ||
331 | + | ||
332 | + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); | ||
333 | + | ||
334 | + AIO_WAIT_WHILE(server->ctx, server->co_trip); | ||
335 | } | ||
336 | |||
337 | + aio_context_release(server->ctx); | ||
338 | + | ||
339 | if (server->listener) { | ||
340 | qio_net_listener_disconnect(server->listener); | ||
341 | object_unref(OBJECT(server->listener)); | ||
342 | } | ||
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); | ||
400 | + } | ||
401 | + | ||
402 | qio_channel_detach_aio_context(server->ioc); | ||
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, | ||
444 | -- | ||
445 | 2.26.2 | ||
446 | 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: Laurent Vivier <lvivier@redhat.com> | 1 | Use the new QAPI block exports API instead of defining our own QOM |
---|---|---|---|
2 | 2 | objects. | |
3 | Signed-off-by: Laurent Vivier <lvivier@redhat.com> | 3 | |
4 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 4 | This is a large change because the lifecycle of VuBlockDev needs to |
5 | Message-id: 20181213162727.17438-4-lvivier@redhat.com | 5 | follow BlockExportDriver. QOM properties are replaced by QAPI options |
6 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 6 | objects. |
7 | |||
8 | VuBlockDev is renamed VuBlkExport and contains a BlockExport field. | ||
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> | ||
7 | --- | 38 | --- |
8 | block/file-posix.c | 25 ++++++------------------- | 39 | qapi/block-export.json | 21 +- |
9 | block/trace-events | 7 +++++++ | 40 | block/export/vhost-user-blk-server.h | 23 +- |
10 | 2 files changed, 13 insertions(+), 19 deletions(-) | 41 | block/export/export.c | 6 + |
11 | 42 | block/export/vhost-user-blk-server.c | 452 +++++++-------------------- | |
12 | diff --git a/block/file-posix.c b/block/file-posix.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 | ||
13 | index XXXXXXX..XXXXXXX 100644 | 49 | index XXXXXXX..XXXXXXX 100644 |
14 | --- a/block/file-posix.c | 50 | --- a/qapi/block-export.json |
15 | +++ b/block/file-posix.c | 51 | +++ b/qapi/block-export.json |
16 | @@ -XXX,XX +XXX,XX @@ | 52 | @@ -XXX,XX +XXX,XX @@ |
17 | #include <xfs/xfs.h> | 53 | 'data': { '*name': 'str', '*description': 'str', |
18 | #endif | 54 | '*bitmap': 'str' } } |
19 | 55 | ||
20 | -//#define DEBUG_BLOCK | 56 | +## |
21 | - | 57 | +# @BlockExportOptionsVhostUserBlk: |
22 | -#ifdef DEBUG_BLOCK | 58 | +# |
23 | -# define DEBUG_BLOCK_PRINT 1 | 59 | +# A vhost-user-blk block export. |
24 | -#else | 60 | +# |
25 | -# define DEBUG_BLOCK_PRINT 0 | 61 | +# @addr: The vhost-user socket on which to listen. Both 'unix' and 'fd' |
26 | -#endif | 62 | +# SocketAddress types are supported. Passed fds must be UNIX domain |
27 | -#define DPRINTF(fmt, ...) \ | 63 | +# sockets. |
28 | -do { \ | 64 | +# @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. |
29 | - if (DEBUG_BLOCK_PRINT) { \ | 65 | +# |
30 | - printf(fmt, ## __VA_ARGS__); \ | 66 | +# Since: 5.2 |
31 | - } \ | 67 | +## |
32 | -} while (0) | 68 | +{ 'struct': 'BlockExportOptionsVhostUserBlk', |
33 | +#include "trace.h" | 69 | + 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } |
34 | 70 | + | |
35 | /* OS X does not have O_DSYNC */ | 71 | ## |
36 | #ifndef O_DSYNC | 72 | # @NbdServerAddOptions: |
37 | @@ -XXX,XX +XXX,XX @@ static int xfs_write_zeroes(BDRVRawState *s, int64_t offset, uint64_t bytes) | 73 | # |
38 | 74 | @@ -XXX,XX +XXX,XX @@ | |
39 | if (xfsctl(NULL, s->fd, XFS_IOC_ZERO_RANGE, &fl) < 0) { | 75 | # An enumeration of block export types |
40 | err = errno; | 76 | # |
41 | - DPRINTF("cannot write zero range (%s)\n", strerror(errno)); | 77 | # @nbd: NBD export |
42 | + trace_file_xfs_write_zeroes(strerror(errno)); | 78 | +# @vhost-user-blk: vhost-user-blk export (since 5.2) |
43 | return -err; | 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; | ||
44 | } | 221 | } |
45 | 222 | ||
46 | @@ -XXX,XX +XXX,XX @@ static int xfs_discard(BDRVRawState *s, int64_t offset, uint64_t bytes) | 223 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); |
47 | 224 | uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, | |
48 | if (xfsctl(NULL, s->fd, XFS_IOC_UNRESVSP64, &fl) < 0) { | 225 | le32_to_cpu(desc.num_sectors) << 9 }; |
49 | err = errno; | 226 | if (type == VIRTIO_BLK_T_DISCARD) { |
50 | - DPRINTF("cannot punch hole (%s)\n", strerror(errno)); | 227 | - if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { |
51 | + trace_file_xfs_discard(strerror(errno)); | 228 | + if (blk_co_pdiscard(blk, range[0], range[1]) == 0) { |
52 | return -err; | 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; | ||
236 | } | ||
53 | } | 237 | } |
54 | 238 | @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, | |
55 | @@ -XXX,XX +XXX,XX @@ static char *FindEjectableOpticalMedia(io_iterator_t *mediaIterator) | 239 | return -EINVAL; |
56 | 240 | } | |
57 | /* If a match was found, leave the loop */ | 241 | |
58 | if (*mediaIterator != 0) { | 242 | -static int coroutine_fn vu_block_flush(VuBlockReq *req) |
59 | - DPRINTF("Matching using %s\n", matching_array[index]); | 243 | +static void coroutine_fn vu_blk_virtio_process_req(void *opaque) |
60 | + trace_file_FindEjectableOpticalMedia(matching_array[index]); | 244 | { |
61 | mediaType = g_strdup(matching_array[index]); | 245 | - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); |
246 | - BlockBackend *backend = vdev_blk->backend; | ||
247 | - return blk_co_flush(backend); | ||
248 | -} | ||
249 | - | ||
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; | ||
292 | } | ||
293 | case VIRTIO_BLK_T_FLUSH: | ||
294 | - if (vu_block_flush(req) == 0) { | ||
295 | + if (blk_co_flush(blk) == 0) { | ||
296 | req->in->status = VIRTIO_BLK_S_OK; | ||
297 | } else { | ||
298 | req->in->status = VIRTIO_BLK_S_IOERR; | ||
299 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
300 | case VIRTIO_BLK_T_DISCARD: | ||
301 | case VIRTIO_BLK_T_WRITE_ZEROES: { | ||
302 | int rc; | ||
303 | - rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], | ||
304 | - out_num, type); | ||
305 | + | ||
306 | + if (!vexp->writable) { | ||
307 | + req->in->status = VIRTIO_BLK_S_IOERR; | ||
308 | + break; | ||
309 | + } | ||
310 | + | ||
311 | + rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type); | ||
312 | if (rc == 0) { | ||
313 | req->in->status = VIRTIO_BLK_S_OK; | ||
314 | } else { | ||
315 | @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) | ||
316 | break; | ||
317 | } | ||
318 | |||
319 | - vu_block_req_complete(req); | ||
320 | + vu_blk_req_complete(req); | ||
321 | return; | ||
322 | |||
323 | err: | ||
324 | - free(elem); | ||
325 | + free(req); | ||
326 | } | ||
327 | |||
328 | -static void vu_block_process_vq(VuDev *vu_dev, int idx) | ||
329 | +static void vu_blk_process_vq(VuDev *vu_dev, int idx) | ||
330 | { | ||
331 | VuServer *server = container_of(vu_dev, VuServer, vu_dev); | ||
332 | VuVirtq *vq = vu_get_queue(vu_dev, idx); | ||
333 | |||
334 | while (1) { | ||
335 | - VuBlockReq *req; | ||
336 | + VuBlkReq *req; | ||
337 | |||
338 | - req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); | ||
339 | + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlkReq)); | ||
340 | if (!req) { | ||
62 | break; | 341 | break; |
63 | } | 342 | } |
64 | @@ -XXX,XX +XXX,XX @@ static bool setup_cdrom(char *bsd_path, Error **errp) | 343 | @@ -XXX,XX +XXX,XX @@ static void vu_block_process_vq(VuDev *vu_dev, int idx) |
65 | if (partition_found == false) { | 344 | req->vq = vq; |
66 | error_setg(errp, "Failed to find a working partition on disc"); | 345 | |
67 | } else { | 346 | Coroutine *co = |
68 | - DPRINTF("Using %s as optical disc\n", test_partition); | 347 | - qemu_coroutine_create(vu_block_virtio_process_req, req); |
69 | + trace_file_setup_cdrom(test_partition); | 348 | + qemu_coroutine_create(vu_blk_virtio_process_req, req); |
70 | pstrcpy(bsd_path, MAXPATHLEN, test_partition); | 349 | qemu_coroutine_enter(co); |
71 | } | 350 | } |
72 | return partition_found; | 351 | } |
73 | @@ -XXX,XX +XXX,XX @@ static bool hdev_is_sg(BlockDriverState *bs) | 352 | |
74 | 353 | -static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) | |
75 | ret = ioctl(s->fd, SG_GET_SCSI_ID, &scsiid); | 354 | +static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started) |
76 | if (ret >= 0) { | 355 | { |
77 | - DPRINTF("SG device found: type=%d, version=%d\n", | 356 | VuVirtq *vq; |
78 | - scsiid.scsi_type, sg_version); | 357 | |
79 | + trace_file_hdev_is_sg(scsiid.scsi_type, sg_version); | 358 | assert(vu_dev); |
80 | return true; | 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; | ||
81 | } | 382 | } |
82 | 383 | ||
83 | diff --git a/block/trace-events b/block/trace-events | 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 | ||
84 | index XXXXXXX..XXXXXXX 100644 | 818 | index XXXXXXX..XXXXXXX 100644 |
85 | --- a/block/trace-events | 819 | --- a/util/vhost-user-server.c |
86 | +++ b/block/trace-events | 820 | +++ b/util/vhost-user-server.c |
87 | @@ -XXX,XX +XXX,XX @@ curl_open(const char *file) "opening %s" | 821 | @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, |
88 | curl_open_size(uint64_t size) "size = %" PRIu64 | 822 | Error **errp) |
89 | curl_setup_preadv(uint64_t bytes, uint64_t start, const char *range) "reading %" PRIu64 " at %" PRIu64 " (%s)" | 823 | { |
90 | curl_close(void) "close" | 824 | QEMUBH *bh; |
825 | - QIONetListener *listener = qio_net_listener_new(); | ||
826 | + QIONetListener *listener; | ||
91 | + | 827 | + |
92 | +# block/file-posix.c | 828 | + if (socket_addr->type != SOCKET_ADDRESS_TYPE_UNIX && |
93 | +file_xfs_write_zeroes(const char *error) "cannot write zero range (%s)" | 829 | + socket_addr->type != SOCKET_ADDRESS_TYPE_FD) { |
94 | +file_xfs_discard(const char *error) "cannot punch hole (%s)" | 830 | + error_setg(errp, "Only socket address types 'unix' and 'fd' are supported"); |
95 | +file_FindEjectableOpticalMedia(const char *media) "Matching using %s" | 831 | + return false; |
96 | +file_setup_cdrom(const char *partition) "Using %s as optical disc" | 832 | + } |
97 | +file_hdev_is_sg(int type, int version) "SG device found: type=%d, version=%d" | 833 | + |
834 | + listener = qio_net_listener_new(); | ||
835 | if (qio_net_listener_open_sync(listener, socket_addr, 1, | ||
836 | errp) < 0) { | ||
837 | object_unref(OBJECT(listener)); | ||
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')) | ||
98 | -- | 857 | -- |
99 | 2.20.1 | 858 | 2.26.2 |
100 | 859 | ||
101 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
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. | ||
1 | 3 | ||
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%) | ||
14 | |||
15 | diff --git a/MAINTAINERS b/MAINTAINERS | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/MAINTAINERS | ||
18 | +++ b/MAINTAINERS | ||
19 | @@ -XXX,XX +XXX,XX @@ Vhost-user block device backend server | ||
20 | M: Coiby Xu <Coiby.Xu@gmail.com> | ||
21 | S: Maintained | ||
22 | F: block/export/vhost-user-blk-server.c | ||
23 | -F: util/vhost-user-server.c | ||
24 | +F: block/export/vhost-user-blk-server.h | ||
25 | +F: include/qemu/vhost-user-server.h | ||
26 | F: tests/qtest/libqos/vhost-user-blk.c | ||
27 | +F: util/vhost-user-server.c | ||
28 | |||
29 | Replication | ||
30 | M: Wen Congyang <wencongyang2@huawei.com> | ||
31 | diff --git a/util/vhost-user-server.h b/include/qemu/vhost-user-server.h | ||
32 | similarity index 100% | ||
33 | rename from util/vhost-user-server.h | ||
34 | rename to include/qemu/vhost-user-server.h | ||
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 | ||
64 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Don't compile contrib/libvhost-user/libvhost-user.c again. Instead build | ||
2 | the static library once and then reuse it throughout QEMU. | ||
1 | 3 | ||
4 | Also switch from CONFIG_LINUX to CONFIG_VHOST_USER, which is what the | ||
5 | vhost-user tools (vhost-user-gpu, etc) do. | ||
6 | |||
7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | Message-id: 20200924151549.913737-14-stefanha@redhat.com | ||
9 | [Added CONFIG_LINUX again because libvhost-user doesn't build on macOS. | ||
10 | --Stefan] | ||
11 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
12 | --- | ||
13 | block/export/export.c | 8 ++++---- | ||
14 | block/export/meson.build | 2 +- | ||
15 | contrib/libvhost-user/meson.build | 1 + | ||
16 | meson.build | 6 +++++- | ||
17 | util/meson.build | 4 +++- | ||
18 | 5 files changed, 14 insertions(+), 7 deletions(-) | ||
19 | |||
20 | diff --git a/block/export/export.c b/block/export/export.c | ||
21 | index XXXXXXX..XXXXXXX 100644 | ||
22 | --- a/block/export/export.c | ||
23 | +++ b/block/export/export.c | ||
24 | @@ -XXX,XX +XXX,XX @@ | ||
25 | #include "sysemu/block-backend.h" | ||
26 | #include "block/export.h" | ||
27 | #include "block/nbd.h" | ||
28 | -#if CONFIG_LINUX | ||
29 | -#include "block/export/vhost-user-blk-server.h" | ||
30 | -#endif | ||
31 | #include "qapi/error.h" | ||
32 | #include "qapi/qapi-commands-block-export.h" | ||
33 | #include "qapi/qapi-events-block-export.h" | ||
34 | #include "qemu/id.h" | ||
35 | +#ifdef CONFIG_VHOST_USER | ||
36 | +#include "vhost-user-blk-server.h" | ||
37 | +#endif | ||
38 | |||
39 | static const BlockExportDriver *blk_exp_drivers[] = { | ||
40 | &blk_exp_nbd, | ||
41 | -#if CONFIG_LINUX | ||
42 | +#ifdef CONFIG_VHOST_USER | ||
43 | &blk_exp_vhost_user_blk, | ||
44 | #endif | ||
45 | }; | ||
46 | diff --git a/block/export/meson.build b/block/export/meson.build | ||
47 | index XXXXXXX..XXXXXXX 100644 | ||
48 | --- a/block/export/meson.build | ||
49 | +++ b/block/export/meson.build | ||
50 | @@ -XXX,XX +XXX,XX @@ | ||
51 | block_ss.add(files('export.c')) | ||
52 | -block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) | ||
53 | +block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) | ||
54 | diff --git a/contrib/libvhost-user/meson.build b/contrib/libvhost-user/meson.build | ||
55 | index XXXXXXX..XXXXXXX 100644 | ||
56 | --- a/contrib/libvhost-user/meson.build | ||
57 | +++ b/contrib/libvhost-user/meson.build | ||
58 | @@ -XXX,XX +XXX,XX @@ | ||
59 | libvhost_user = static_library('vhost-user', | ||
60 | files('libvhost-user.c', 'libvhost-user-glib.c'), | ||
61 | build_by_default: false) | ||
62 | +vhost_user = declare_dependency(link_with: libvhost_user) | ||
63 | diff --git a/meson.build b/meson.build | ||
64 | index XXXXXXX..XXXXXXX 100644 | ||
65 | --- a/meson.build | ||
66 | +++ b/meson.build | ||
67 | @@ -XXX,XX +XXX,XX @@ trace_events_subdirs += [ | ||
68 | 'util', | ||
69 | ] | ||
70 | |||
71 | +vhost_user = not_found | ||
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')) | ||
102 | -- | ||
103 | 2.26.2 | ||
104 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Introduce libblkdev.fa to avoid recompiling blockdev_ss twice. | ||
1 | 2 | ||
3 | Suggested-by: Paolo Bonzini <pbonzini@redhat.com> | ||
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(-) | ||
12 | |||
13 | diff --git a/meson.build b/meson.build | ||
14 | index XXXXXXX..XXXXXXX 100644 | ||
15 | --- a/meson.build | ||
16 | +++ b/meson.build | ||
17 | @@ -XXX,XX +XXX,XX @@ blockdev_ss.add(files( | ||
18 | # os-win32.c does not | ||
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 | ||
65 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
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. | ||
1 | 4 | ||
5 | Undo the recent move of blockdev-nbd.c from blockdev_ss into block_ss. | ||
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. | ||
14 | |||
15 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
16 | Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> | ||
17 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
18 | Message-id: 20200929125516.186715-4-stefanha@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> | ||
22 | --- | ||
23 | qemu-nbd.c | 21 ++++++++------------- | ||
24 | stubs/blk-exp-close-all.c | 7 +++++++ | ||
25 | block/export/meson.build | 4 ++-- | ||
26 | meson.build | 4 ++-- | ||
27 | nbd/meson.build | 2 ++ | ||
28 | stubs/meson.build | 1 + | ||
29 | 6 files changed, 22 insertions(+), 17 deletions(-) | ||
30 | create mode 100644 stubs/blk-exp-close-all.c | ||
31 | |||
32 | diff --git a/qemu-nbd.c b/qemu-nbd.c | ||
33 | index XXXXXXX..XXXXXXX 100644 | ||
34 | --- a/qemu-nbd.c | ||
35 | +++ b/qemu-nbd.c | ||
36 | @@ -XXX,XX +XXX,XX @@ | ||
37 | #include "qapi/error.h" | ||
38 | #include "qemu/cutils.h" | ||
39 | #include "sysemu/block-backend.h" | ||
40 | +#include "sysemu/runstate.h" /* for qemu_system_killed() prototype */ | ||
41 | #include "block/block_int.h" | ||
42 | #include "block/nbd.h" | ||
43 | #include "qemu/main-loop.h" | ||
44 | @@ -XXX,XX +XXX,XX @@ QEMU_COPYRIGHT "\n" | ||
45 | } | ||
46 | |||
47 | #ifdef CONFIG_POSIX | ||
48 | -static void termsig_handler(int signum) | ||
49 | +/* | ||
50 | + * The client thread uses SIGTERM to interrupt the server. A signal | ||
51 | + * handler ensures that "qemu-nbd -v -c" exits with a nice status code. | ||
52 | + */ | ||
53 | +void qemu_system_killed(int signum, pid_t pid) | ||
54 | { | ||
55 | qatomic_cmpxchg(&state, RUNNING, TERMINATE); | ||
56 | qemu_notify_event(); | ||
57 | @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) | ||
58 | BlockExportOptions *export_opts; | ||
59 | |||
60 | #ifdef CONFIG_POSIX | ||
61 | - /* | ||
62 | - * Exit gracefully on various signals, which includes SIGTERM used | ||
63 | - * by 'qemu-nbd -v -c'. | ||
64 | - */ | ||
65 | - struct sigaction sa_sigterm; | ||
66 | - memset(&sa_sigterm, 0, sizeof(sa_sigterm)); | ||
67 | - sa_sigterm.sa_handler = termsig_handler; | ||
68 | - sigaction(SIGTERM, &sa_sigterm, NULL); | ||
69 | - sigaction(SIGINT, &sa_sigterm, NULL); | ||
70 | - sigaction(SIGHUP, &sa_sigterm, NULL); | ||
71 | - | ||
72 | - signal(SIGPIPE, SIG_IGN); | ||
73 | + os_setup_early_signal_handling(); | ||
74 | + os_setup_signal_handling(); | ||
75 | #endif | ||
76 | |||
77 | socket_init(); | ||
78 | diff --git a/stubs/blk-exp-close-all.c b/stubs/blk-exp-close-all.c | ||
79 | new file mode 100644 | ||
80 | index XXXXXXX..XXXXXXX | ||
81 | --- /dev/null | ||
82 | +++ b/stubs/blk-exp-close-all.c | ||
83 | @@ -XXX,XX +XXX,XX @@ | ||
84 | +#include "qemu/osdep.h" | ||
85 | +#include "block/export.h" | ||
86 | + | ||
87 | +/* Only used in programs that support block exports (libblockdev.fa) */ | ||
88 | +void blk_exp_close_all(void) | ||
89 | +{ | ||
90 | +} | ||
91 | diff --git a/block/export/meson.build b/block/export/meson.build | ||
92 | index XXXXXXX..XXXXXXX 100644 | ||
93 | --- a/block/export/meson.build | ||
94 | +++ b/block/export/meson.build | ||
95 | @@ -XXX,XX +XXX,XX @@ | ||
96 | -block_ss.add(files('export.c')) | ||
97 | -block_ss.add(when: ['CONFIG_LINUX', 'CONFIG_VHOST_USER'], if_true: files('vhost-user-blk-server.c')) | ||
98 | +blockdev_ss.add(files('export.c')) | ||
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')) | ||
153 | -- | ||
154 | 2.26.2 | ||
155 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Make it possible to specify the iothread where the export will run. By | ||
2 | default the block node can be moved to other AioContexts later and the | ||
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. | ||
1 | 6 | ||
7 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | Message-id: 20200929125516.186715-5-stefanha@redhat.com | ||
9 | [Fix stray '#' character in block-export.json and add missing "(since: | ||
10 | 5.2)" as suggested by Eric Blake. | ||
11 | --Stefan] | ||
12 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
13 | --- | ||
14 | qapi/block-export.json | 11 ++++++++++ | ||
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(-) | ||
19 | |||
20 | diff --git a/qapi/block-export.json b/qapi/block-export.json | ||
21 | index XXXXXXX..XXXXXXX 100644 | ||
22 | --- a/qapi/block-export.json | ||
23 | +++ b/qapi/block-export.json | ||
24 | @@ -XXX,XX +XXX,XX @@ | ||
25 | # export before completion is signalled. (since: 5.2; | ||
26 | # default: false) | ||
27 | # | ||
28 | +# @iothread: The name of the iothread object where the export will run. The | ||
29 | +# default is to use the thread currently associated with the | ||
30 | +# block node. (since: 5.2) | ||
31 | +# | ||
32 | +# @fixed-iothread: True prevents the block node from being moved to another | ||
33 | +# thread while the export is active. If true and @iothread is | ||
34 | +# given, export creation fails if the block node cannot be | ||
35 | +# moved to the iothread. The default is false. (since: 5.2) | ||
36 | +# | ||
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; | ||
79 | + | ||
80 | + iothread = iothread_by_id(export->iothread); | ||
81 | + if (!iothread) { | ||
82 | + error_setg(errp, "iothread \"%s\" not found", export->iothread); | ||
83 | + goto fail; | ||
84 | + } | ||
85 | + | ||
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 | + } | ||
96 | + } | ||
97 | + | ||
98 | /* | ||
99 | * Block exports are used for non-shared storage migration. Make sure | ||
100 | * that BDRV_O_INACTIVE is cleared and the image is ready for write | ||
101 | @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) | ||
102 | } | ||
103 | |||
104 | blk = blk_new(ctx, perm, BLK_PERM_ALL); | ||
105 | + | ||
106 | + if (!fixed_iothread) { | ||
107 | + blk_set_allow_aio_context_change(blk, true); | ||
108 | + } | ||
109 | + | ||
110 | ret = blk_insert_bs(blk, bs, errp); | ||
111 | if (ret < 0) { | ||
112 | goto fail; | ||
113 | diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c | ||
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; | ||
121 | + | ||
122 | + vexp->export.ctx = ctx; | ||
123 | vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); | ||
124 | } | ||
125 | |||
126 | static void blk_aio_detach(void *opaque) | ||
127 | { | ||
128 | VuBlkExport *vexp = opaque; | ||
129 | + | ||
130 | vhost_user_server_detach_aio_context(&vexp->vu_server); | ||
131 | + vexp->export.ctx = NULL; | ||
132 | } | ||
133 | |||
134 | static void | ||
135 | @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, | ||
136 | vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, | ||
137 | logical_block_size); | ||
138 | |||
139 | - blk_set_allow_aio_context_change(exp->blk, true); | ||
140 | blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, | ||
141 | vexp); | ||
142 | |||
143 | diff --git a/nbd/server.c b/nbd/server.c | ||
144 | index XXXXXXX..XXXXXXX 100644 | ||
145 | --- a/nbd/server.c | ||
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); | ||
156 | -- | ||
157 | 2.26.2 | ||
158 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
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. | ||
1 | 6 | ||
7 | The vhost-user-blk-server.c code is already capable of multi-queue. All | ||
8 | virtqueue processing runs in the same AioContext. No new locking is | ||
9 | needed. | ||
10 | |||
11 | Add the num-queues=N option and set the VIRTIO_BLK_F_MQ feature bit. | ||
12 | Note that the feature bit only announces the presence of the num_queues | ||
13 | configuration space field. It does not promise that there is more than 1 | ||
14 | virtqueue, so we can set it unconditionally. | ||
15 | |||
16 | I tested multi-queue by running a random read fio test with numjobs=4 on | ||
17 | an -smp 4 guest. After the benchmark finished the guest /proc/interrupts | ||
18 | file showed activity on all 4 virtio-blk MSI-X. The /sys/block/vda/mq/ | ||
19 | directory shows that Linux blk-mq has 4 queues configured. | ||
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> | ||
29 | --- | ||
30 | qapi/block-export.json | 10 +++++++--- | ||
31 | block/export/vhost-user-blk-server.c | 24 ++++++++++++++++++------ | ||
32 | 2 files changed, 25 insertions(+), 9 deletions(-) | ||
33 | |||
34 | diff --git a/qapi/block-export.json b/qapi/block-export.json | ||
35 | index XXXXXXX..XXXXXXX 100644 | ||
36 | --- a/qapi/block-export.json | ||
37 | +++ b/qapi/block-export.json | ||
38 | @@ -XXX,XX +XXX,XX @@ | ||
39 | # SocketAddress types are supported. Passed fds must be UNIX domain | ||
40 | # sockets. | ||
41 | # @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. | ||
42 | +# @num-queues: Number of request virtqueues. Must be greater than 0. Defaults | ||
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) | ||
95 | { | ||
96 | config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; | ||
97 | config->blk_size = blk_size; | ||
98 | @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, | ||
99 | config->seg_max = 128 - 2; | ||
100 | config->min_io_size = 1; | ||
101 | config->opt_io_size = 1; | ||
102 | - config->num_queues = VHOST_USER_BLK_MAX_QUEUES; | ||
103 | + config->num_queues = num_queues; | ||
104 | config->max_discard_sectors = 32768; | ||
105 | config->max_discard_seg = 1; | ||
106 | config->discard_sector_alignment = config->blk_size >> 9; | ||
107 | @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, | ||
108 | BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; | ||
109 | Error *local_err = NULL; | ||
110 | uint64_t logical_block_size; | ||
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; | ||
126 | + } | ||
127 | + | ||
128 | vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, | ||
129 | - logical_block_size); | ||
130 | + logical_block_size, num_queues); | ||
131 | |||
132 | blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, | ||
133 | vexp); | ||
134 | |||
135 | if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, | ||
136 | - VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, | ||
137 | - errp)) { | ||
138 | + num_queues, &vu_blk_iface, errp)) { | ||
139 | blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, | ||
140 | blk_aio_detach, vexp); | ||
141 | return -EADDRNOTAVAIL; | ||
142 | -- | ||
143 | 2.26.2 | ||
144 | diff view generated by jsdifflib |
1 | To do this, we need to allow creating the NBD server on various ports | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | instead of a single one (which may not even work if you run just one | ||
3 | instance, because something entirely else might be using that port). | ||
4 | 2 | ||
5 | So we just pick a random port in [32768, 32768 + 1024) and try to create | 3 | bdrv_co_block_status_above has several design problems with handling |
6 | a server there. If that fails, we just retry until something sticks. | 4 | short backing files: |
7 | 5 | ||
8 | For the IPv6 test, we need a different range, though (just above that | 6 | 1. With want_zeros=true, it may return ret with BDRV_BLOCK_ZERO but |
9 | one). This is because "localhost" resolves to both 127.0.0.1 and ::1. | 7 | without BDRV_BLOCK_ALLOCATED flag, when actually short backing file |
10 | This means that if you bind to it, it will bind to both, if possible, or | 8 | which produces these after-EOF zeros is inside requested backing |
11 | just one if the other is already in use. Therefore, if the IPv6 test | 9 | sequence. |
12 | has already taken [::1]:some_port and we then try to take | ||
13 | localhost:some_port, that will work -- only the second server will be | ||
14 | bound to 127.0.0.1:some_port alone and not [::1]:some_port in addition. | ||
15 | So we have two different servers on the same port, one for IPv4 and one | ||
16 | for IPv6. | ||
17 | 10 | ||
18 | But when we then try to connect to the server through | 11 | 2. With want_zero=false, it may return pnum=0 prior to actual EOF, |
19 | localhost:some_port, we will always end up at the IPv6 one (as long as | 12 | because of EOF of short backing file. |
20 | it is up), and this may not be the one we want. | ||
21 | 13 | ||
22 | Thus, we must make sure not to create an IPv6-only NBD server on the | 14 | Fix these things, making logic about short backing files clearer. |
23 | same port as a normal "dual-stack" NBD server -- which is done by using | ||
24 | distinct port ranges, as explained above. | ||
25 | 15 | ||
26 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 16 | With fixed bdrv_block_status_above we also have to improve is_zero in |
27 | Message-id: 20181221234750.23577-4-mreitz@redhat.com | 17 | qcow2 code, otherwise iotest 154 will fail, because with this patch we |
28 | Reviewed-by: John Snow <jsnow@redhat.com> | 18 | stop to merge zeros of different types (produced by fully unallocated |
29 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 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. | ||
24 | |||
25 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
26 | Reviewed-by: Alberto Garcia <berto@igalia.com> | ||
27 | Reviewed-by: Eric Blake <eblake@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> | ||
30 | --- | 32 | --- |
31 | tests/qemu-iotests/147 | 98 +++++++++++++++++++++++++++++------------- | 33 | block/io.c | 68 ++++++++++++++++++++++++++++++++++++++++----------- |
32 | 1 file changed, 68 insertions(+), 30 deletions(-) | 34 | block/qcow2.c | 16 ++++++++++-- |
35 | 2 files changed, 68 insertions(+), 16 deletions(-) | ||
33 | 36 | ||
34 | diff --git a/tests/qemu-iotests/147 b/tests/qemu-iotests/147 | 37 | diff --git a/block/io.c b/block/io.c |
35 | index XXXXXXX..XXXXXXX 100755 | 38 | index XXXXXXX..XXXXXXX 100644 |
36 | --- a/tests/qemu-iotests/147 | 39 | --- a/block/io.c |
37 | +++ b/tests/qemu-iotests/147 | 40 | +++ b/block/io.c |
38 | @@ -XXX,XX +XXX,XX @@ | 41 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
39 | # | 42 | int64_t *map, |
40 | 43 | BlockDriverState **file) | |
41 | import os | 44 | { |
42 | +import random | 45 | + int ret; |
43 | import socket | 46 | BlockDriverState *p; |
44 | import stat | 47 | - int ret = 0; |
45 | import time | 48 | - bool first = true; |
46 | import iotests | 49 | + int64_t eof = 0; |
47 | -from iotests import cachemode, imgfmt, qemu_img, qemu_nbd | 50 | |
48 | +from iotests import cachemode, imgfmt, qemu_img, qemu_nbd, qemu_nbd_pipe | 51 | assert(bs != base); |
49 | 52 | - for (p = bs; p != base; p = bdrv_filter_or_cow_bs(p)) { | |
50 | -NBD_PORT = 10811 | ||
51 | +NBD_PORT_START = 32768 | ||
52 | +NBD_PORT_END = NBD_PORT_START + 1024 | ||
53 | +NBD_IPV6_PORT_START = NBD_PORT_END | ||
54 | +NBD_IPV6_PORT_END = NBD_IPV6_PORT_START + 1024 | ||
55 | |||
56 | test_img = os.path.join(iotests.test_dir, 'test.img') | ||
57 | unix_socket = os.path.join(iotests.test_dir, 'nbd.socket') | ||
58 | @@ -XXX,XX +XXX,XX @@ class QemuNBD(NBDBlockdevAddBase): | ||
59 | except OSError: | ||
60 | pass | ||
61 | |||
62 | + def _try_server_up(self, *args): | ||
63 | + status, msg = qemu_nbd_pipe('-f', imgfmt, test_img, *args) | ||
64 | + if status == 0: | ||
65 | + return True | ||
66 | + if 'Address already in use' in msg: | ||
67 | + return False | ||
68 | + self.fail(msg) | ||
69 | + | 53 | + |
70 | def _server_up(self, *args): | 54 | + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); |
71 | - self.assertEqual(qemu_nbd('-f', imgfmt, test_img, *args), 0) | 55 | + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { |
72 | + self.assertTrue(self._try_server_up(*args)) | 56 | + return ret; |
73 | 57 | + } | |
74 | def test_inet(self): | ||
75 | - self._server_up('-b', 'localhost', '-p', str(NBD_PORT)) | ||
76 | + while True: | ||
77 | + nbd_port = random.randrange(NBD_PORT_START, NBD_PORT_END) | ||
78 | + if self._try_server_up('-b', 'localhost', '-p', str(nbd_port)): | ||
79 | + break | ||
80 | + | 58 | + |
81 | address = { 'type': 'inet', | 59 | + if (ret & BDRV_BLOCK_EOF) { |
82 | 'data': { | 60 | + eof = offset + *pnum; |
83 | 'host': 'localhost', | 61 | + } |
84 | - 'port': str(NBD_PORT) | ||
85 | + 'port': str(nbd_port) | ||
86 | } } | ||
87 | - self.client_test('nbd://localhost:%i' % NBD_PORT, | ||
88 | + self.client_test('nbd://localhost:%i' % nbd_port, | ||
89 | flatten_sock_addr(address)) | ||
90 | |||
91 | def test_unix(self): | ||
92 | @@ -XXX,XX +XXX,XX @@ class BuiltinNBD(NBDBlockdevAddBase): | ||
93 | except OSError: | ||
94 | pass | ||
95 | |||
96 | - def _server_up(self, address, export_name=None, export_name2=None): | ||
97 | + # Returns False on EADDRINUSE; fails an assertion on other errors. | ||
98 | + # Returns True on success. | ||
99 | + def _try_server_up(self, address, export_name=None, export_name2=None): | ||
100 | result = self.server.qmp('nbd-server-start', addr=address) | ||
101 | + if 'error' in result and \ | ||
102 | + 'Address already in use' in result['error']['desc']: | ||
103 | + return False | ||
104 | self.assert_qmp(result, 'return', {}) | ||
105 | |||
106 | if export_name is None: | ||
107 | @@ -XXX,XX +XXX,XX @@ class BuiltinNBD(NBDBlockdevAddBase): | ||
108 | name=export_name2) | ||
109 | self.assert_qmp(result, 'return', {}) | ||
110 | |||
111 | + return True | ||
112 | + | 62 | + |
113 | + def _server_up(self, address, export_name=None, export_name2=None): | 63 | + assert(*pnum <= bytes); |
114 | + self.assertTrue(self._try_server_up(address, export_name, export_name2)) | 64 | + bytes = *pnum; |
115 | |||
116 | def _server_down(self): | ||
117 | result = self.server.qmp('nbd-server-stop') | ||
118 | self.assert_qmp(result, 'return', {}) | ||
119 | |||
120 | def do_test_inet(self, export_name=None): | ||
121 | - address = { 'type': 'inet', | ||
122 | - 'data': { | ||
123 | - 'host': 'localhost', | ||
124 | - 'port': str(NBD_PORT) | ||
125 | - } } | ||
126 | - self._server_up(address, export_name) | ||
127 | + while True: | ||
128 | + nbd_port = random.randrange(NBD_PORT_START, NBD_PORT_END) | ||
129 | + address = { 'type': 'inet', | ||
130 | + 'data': { | ||
131 | + 'host': 'localhost', | ||
132 | + 'port': str(nbd_port) | ||
133 | + } } | ||
134 | + if self._try_server_up(address, export_name): | ||
135 | + break | ||
136 | + | 65 | + |
137 | export_name = export_name or 'nbd-export' | 66 | + for (p = bdrv_filter_or_cow_bs(bs); p != base; |
138 | - self.client_test('nbd://localhost:%i/%s' % (NBD_PORT, export_name), | 67 | + p = bdrv_filter_or_cow_bs(p)) |
139 | + self.client_test('nbd://localhost:%i/%s' % (nbd_port, export_name), | 68 | + { |
140 | flatten_sock_addr(address), export_name) | 69 | ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, |
141 | self._server_down() | 70 | file); |
142 | 71 | if (ret < 0) { | |
143 | @@ -XXX,XX +XXX,XX @@ class BuiltinNBD(NBDBlockdevAddBase): | 72 | - break; |
144 | self.do_test_inet('shadow') | 73 | + return ret; |
145 | 74 | } | |
146 | def test_inet_two_exports(self): | 75 | - if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { |
147 | - address = { 'type': 'inet', | 76 | + if (*pnum == 0) { |
148 | - 'data': { | 77 | /* |
149 | - 'host': 'localhost', | 78 | - * Reading beyond the end of the file continues to read |
150 | - 'port': str(NBD_PORT) | 79 | - * zeroes, but we can only widen the result to the |
151 | - } } | 80 | - * unallocated length we learned from an earlier |
152 | - self._server_up(address, 'exp1', 'exp2') | 81 | - * iteration. |
153 | - self.client_test('nbd://localhost:%i/%s' % (NBD_PORT, 'exp1'), | 82 | + * The top layer deferred to this layer, and because this layer is |
154 | + while True: | 83 | + * short, any zeroes that we synthesize beyond EOF behave as if they |
155 | + nbd_port = random.randrange(NBD_PORT_START, NBD_PORT_END) | 84 | + * were allocated at this layer. |
156 | + address = { 'type': 'inet', | 85 | + * |
157 | + 'data': { | 86 | + * We don't include BDRV_BLOCK_EOF into ret, as upper layer may be |
158 | + 'host': 'localhost', | 87 | + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see |
159 | + 'port': str(nbd_port) | 88 | + * below. |
160 | + } } | 89 | */ |
161 | + if self._try_server_up(address, 'exp1', 'exp2'): | 90 | + assert(ret & BDRV_BLOCK_EOF); |
162 | + break | 91 | *pnum = bytes; |
92 | + if (file) { | ||
93 | + *file = p; | ||
94 | + } | ||
95 | + ret = BDRV_BLOCK_ZERO | BDRV_BLOCK_ALLOCATED; | ||
96 | + break; | ||
97 | } | ||
98 | - if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { | ||
99 | + if (ret & BDRV_BLOCK_ALLOCATED) { | ||
100 | + /* | ||
101 | + * We've found the node and the status, we must break. | ||
102 | + * | ||
103 | + * Drop BDRV_BLOCK_EOF, as it's not for upper layer, which may be | ||
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; | ||
163 | + | 114 | + |
164 | + self.client_test('nbd://localhost:%i/%s' % (nbd_port, 'exp1'), | 115 | + /* |
165 | flatten_sock_addr(address), 'exp1', 'node1', False) | 116 | + * OK, [offset, offset + *pnum) region is unallocated on this layer, |
166 | - self.client_test('nbd://localhost:%i/%s' % (NBD_PORT, 'exp2'), | 117 | + * let's continue the diving. |
167 | + self.client_test('nbd://localhost:%i/%s' % (nbd_port, 'exp2'), | 118 | + */ |
168 | flatten_sock_addr(address), 'exp2', 'node2', False) | 119 | + assert(*pnum <= bytes); |
169 | result = self.vm.qmp('blockdev-del', node_name='node1') | 120 | + bytes = *pnum; |
170 | self.assert_qmp(result, 'return', {}) | 121 | + } |
171 | @@ -XXX,XX +XXX,XX @@ class BuiltinNBD(NBDBlockdevAddBase): | ||
172 | except socket.gaierror: | ||
173 | # IPv6 not available, skip | ||
174 | return | ||
175 | - address = { 'type': 'inet', | ||
176 | - 'data': { | ||
177 | - 'host': '::1', | ||
178 | - 'port': str(NBD_PORT), | ||
179 | - 'ipv4': False, | ||
180 | - 'ipv6': True | ||
181 | - } } | ||
182 | + | 122 | + |
183 | + while True: | 123 | + if (offset + *pnum == eof) { |
184 | + nbd_port = random.randrange(NBD_IPV6_PORT_START, NBD_IPV6_PORT_END) | 124 | + ret |= BDRV_BLOCK_EOF; |
185 | + address = { 'type': 'inet', | 125 | } |
186 | + 'data': { | ||
187 | + 'host': '::1', | ||
188 | + 'port': str(nbd_port), | ||
189 | + 'ipv4': False, | ||
190 | + 'ipv6': True | ||
191 | + } } | ||
192 | + if self._try_server_up(address): | ||
193 | + break | ||
194 | + | 126 | + |
195 | filename = { 'driver': 'raw', | 127 | return ret; |
196 | 'file': { | 128 | } |
197 | 'driver': 'nbd', | 129 | |
198 | 'export': 'nbd-export', | 130 | diff --git a/block/qcow2.c b/block/qcow2.c |
199 | 'server': flatten_sock_addr(address) | 131 | index XXXXXXX..XXXXXXX 100644 |
200 | } } | 132 | --- a/block/qcow2.c |
201 | - self._server_up(address) | 133 | +++ b/block/qcow2.c |
202 | self.client_test(filename, flatten_sock_addr(address), 'nbd-export') | 134 | @@ -XXX,XX +XXX,XX @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) |
203 | self._server_down() | 135 | if (!bytes) { |
204 | 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, | ||
205 | -- | 157 | -- |
206 | 2.20.1 | 158 | 2.26.2 |
207 | 159 | ||
208 | diff view generated by jsdifflib |
1 | In some cases, we may want to deal with qemu-nbd errors (e.g. by | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | launching it in a different configuration until it no longer throws | ||
3 | any). In that case, we do not want its output ending up in the test | ||
4 | output. | ||
5 | 2 | ||
6 | It may still be useful for handling the error, though, so add a new | 3 | In order to reuse bdrv_common_block_status_above in |
7 | function that works basically like qemu_nbd(), only that it returns the | 4 | bdrv_is_allocated_above, let's support include_base parameter. |
8 | qemu-nbd output instead of making it end up in the log. In contrast to | ||
9 | qemu_img_pipe(), it does still return the exit code as well, though, | ||
10 | because that is even more important for error handling. | ||
11 | 5 | ||
12 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 6 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
13 | Message-id: 20181221234750.23577-2-mreitz@redhat.com | 7 | Reviewed-by: Alberto Garcia <berto@igalia.com> |
14 | Reviewed-by: John Snow <jsnow@redhat.com> | ||
15 | Reviewed-by: Eric Blake <eblake@redhat.com> | 8 | Reviewed-by: Eric Blake <eblake@redhat.com> |
16 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 9 | Message-id: 20200924194003.22080-3-vsementsov@virtuozzo.com |
10 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
17 | --- | 11 | --- |
18 | tests/qemu-iotests/iotests.py | 14 ++++++++++++++ | 12 | block/coroutines.h | 2 ++ |
19 | 1 file changed, 14 insertions(+) | 13 | block/io.c | 21 ++++++++++++++------- |
14 | 2 files changed, 16 insertions(+), 7 deletions(-) | ||
20 | 15 | ||
21 | diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py | 16 | diff --git a/block/coroutines.h b/block/coroutines.h |
22 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
23 | --- a/tests/qemu-iotests/iotests.py | 18 | --- a/block/coroutines.h |
24 | +++ b/tests/qemu-iotests/iotests.py | 19 | +++ b/block/coroutines.h |
25 | @@ -XXX,XX +XXX,XX @@ def qemu_nbd(*args): | 20 | @@ -XXX,XX +XXX,XX @@ bdrv_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, |
26 | '''Run qemu-nbd in daemon mode and return the parent's exit code''' | 21 | int coroutine_fn |
27 | return subprocess.call(qemu_nbd_args + ['--fork'] + list(args)) | 22 | bdrv_co_common_block_status_above(BlockDriverState *bs, |
28 | 23 | BlockDriverState *base, | |
29 | +def qemu_nbd_pipe(*args): | 24 | + bool include_base, |
30 | + '''Run qemu-nbd in daemon mode and return both the parent's exit code | 25 | bool want_zero, |
31 | + and its output''' | 26 | int64_t offset, |
32 | + subp = subprocess.Popen(qemu_nbd_args + ['--fork'] + list(args), | 27 | int64_t bytes, |
33 | + stdout=subprocess.PIPE, | 28 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
34 | + stderr=subprocess.STDOUT, | 29 | int generated_co_wrapper |
35 | + universal_newlines=True) | 30 | bdrv_common_block_status_above(BlockDriverState *bs, |
36 | + exitcode = subp.wait() | 31 | BlockDriverState *base, |
37 | + if exitcode < 0: | 32 | + bool include_base, |
38 | + sys.stderr.write('qemu-nbd received signal %i: %s\n' % | 33 | bool want_zero, |
39 | + (-exitcode, | 34 | int64_t offset, |
40 | + ' '.join(qemu_nbd_args + ['--fork'] + list(args)))) | 35 | int64_t bytes, |
41 | + return exitcode, subp.communicate()[0] | 36 | diff --git a/block/io.c b/block/io.c |
37 | index XXXXXXX..XXXXXXX 100644 | ||
38 | --- a/block/io.c | ||
39 | +++ b/block/io.c | ||
40 | @@ -XXX,XX +XXX,XX @@ early_out: | ||
41 | int coroutine_fn | ||
42 | bdrv_co_common_block_status_above(BlockDriverState *bs, | ||
43 | BlockDriverState *base, | ||
44 | + bool include_base, | ||
45 | bool want_zero, | ||
46 | int64_t offset, | ||
47 | int64_t bytes, | ||
48 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, | ||
49 | BlockDriverState *p; | ||
50 | int64_t eof = 0; | ||
51 | |||
52 | - assert(bs != base); | ||
53 | + assert(include_base || bs != base); | ||
54 | + assert(!include_base || base); /* Can't include NULL base */ | ||
55 | |||
56 | ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); | ||
57 | - if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { | ||
58 | + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { | ||
59 | return ret; | ||
60 | } | ||
61 | |||
62 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, | ||
63 | assert(*pnum <= bytes); | ||
64 | bytes = *pnum; | ||
65 | |||
66 | - for (p = bdrv_filter_or_cow_bs(bs); p != base; | ||
67 | + for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base; | ||
68 | p = bdrv_filter_or_cow_bs(p)) | ||
69 | { | ||
70 | ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, | ||
71 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, | ||
72 | break; | ||
73 | } | ||
74 | |||
75 | + if (p == base) { | ||
76 | + assert(include_base); | ||
77 | + break; | ||
78 | + } | ||
42 | + | 79 | + |
43 | def compare_images(img1, img2, fmt1=imgfmt, fmt2=imgfmt): | 80 | /* |
44 | '''Return True if two image files are identical''' | 81 | * OK, [offset, offset + *pnum) region is unallocated on this layer, |
45 | return qemu_img('compare', '-f', fmt1, | 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 | } | ||
46 | -- | 105 | -- |
47 | 2.20.1 | 106 | 2.26.2 |
48 | 107 | ||
49 | diff view generated by jsdifflib |
1 | From: Laurent Vivier <lvivier@redhat.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Signed-off-by: Laurent Vivier <lvivier@redhat.com> | 3 | We are going to reuse bdrv_common_block_status_above in |
4 | Reviewed-by: Richard W.M. Jones <rjones@redhat.com> | 4 | bdrv_is_allocated_above. bdrv_is_allocated_above may be called with |
5 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 5 | include_base == false and still bs == base (for ex. from img_rebase()). |
6 | Message-id: 20181213162727.17438-3-lvivier@redhat.com | 6 | |
7 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 7 | So, support this corner case. |
8 | |||
9 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
10 | Reviewed-by: Kevin Wolf <kwolf@redhat.com> | ||
11 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
12 | Reviewed-by: Alberto Garcia <berto@igalia.com> | ||
13 | Message-id: 20200924194003.22080-4-vsementsov@virtuozzo.com | ||
14 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
8 | --- | 15 | --- |
9 | block/curl.c | 29 ++++++++--------------------- | 16 | block/io.c | 6 +++++- |
10 | block/trace-events | 9 +++++++++ | 17 | 1 file changed, 5 insertions(+), 1 deletion(-) |
11 | 2 files changed, 17 insertions(+), 21 deletions(-) | ||
12 | 18 | ||
13 | diff --git a/block/curl.c b/block/curl.c | 19 | diff --git a/block/io.c b/block/io.c |
14 | index XXXXXXX..XXXXXXX 100644 | 20 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/block/curl.c | 21 | --- a/block/io.c |
16 | +++ b/block/curl.c | 22 | +++ b/block/io.c |
17 | @@ -XXX,XX +XXX,XX @@ | 23 | @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, |
18 | #include "crypto/secret.h" | 24 | BlockDriverState *p; |
19 | #include <curl/curl.h> | 25 | int64_t eof = 0; |
20 | #include "qemu/cutils.h" | 26 | |
21 | +#include "trace.h" | 27 | - assert(include_base || bs != base); |
22 | 28 | assert(!include_base || base); /* Can't include NULL base */ | |
23 | -// #define DEBUG_CURL | 29 | |
24 | // #define DEBUG_VERBOSE | 30 | + if (!include_base && bs == base) { |
25 | 31 | + *pnum = bytes; | |
26 | -#ifdef DEBUG_CURL | 32 | + return 0; |
27 | -#define DEBUG_CURL_PRINT 1 | 33 | + } |
28 | -#else | ||
29 | -#define DEBUG_CURL_PRINT 0 | ||
30 | -#endif | ||
31 | -#define DPRINTF(fmt, ...) \ | ||
32 | - do { \ | ||
33 | - if (DEBUG_CURL_PRINT) { \ | ||
34 | - fprintf(stderr, fmt, ## __VA_ARGS__); \ | ||
35 | - } \ | ||
36 | - } while (0) | ||
37 | - | ||
38 | #if LIBCURL_VERSION_NUM >= 0x071000 | ||
39 | /* The multi interface timer callback was introduced in 7.16.0 */ | ||
40 | #define NEED_CURL_TIMER_CALLBACK | ||
41 | @@ -XXX,XX +XXX,XX @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque) | ||
42 | { | ||
43 | BDRVCURLState *s = opaque; | ||
44 | |||
45 | - DPRINTF("CURL: timer callback timeout_ms %ld\n", timeout_ms); | ||
46 | + trace_curl_timer_cb(timeout_ms); | ||
47 | if (timeout_ms == -1) { | ||
48 | timer_del(&s->timer); | ||
49 | } else { | ||
50 | @@ -XXX,XX +XXX,XX @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action, | ||
51 | } | ||
52 | socket = NULL; | ||
53 | |||
54 | - DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, (int)fd); | ||
55 | + trace_curl_sock_cb(action, (int)fd); | ||
56 | switch (action) { | ||
57 | case CURL_POLL_IN: | ||
58 | aio_set_fd_handler(s->aio_context, fd, false, | ||
59 | @@ -XXX,XX +XXX,XX @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque) | ||
60 | size_t realsize = size * nmemb; | ||
61 | int i; | ||
62 | |||
63 | - DPRINTF("CURL: Just reading %zd bytes\n", realsize); | ||
64 | + trace_curl_read_cb(realsize); | ||
65 | |||
66 | if (!s || !s->orig_buf) { | ||
67 | goto read_end; | ||
68 | @@ -XXX,XX +XXX,XX @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags, | ||
69 | } | ||
70 | } | ||
71 | |||
72 | - DPRINTF("CURL: Opening %s\n", file); | ||
73 | + trace_curl_open(file); | ||
74 | qemu_co_queue_init(&s->free_state_waitq); | ||
75 | s->aio_context = bdrv_get_aio_context(bs); | ||
76 | s->url = g_strdup(file); | ||
77 | @@ -XXX,XX +XXX,XX @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags, | ||
78 | "Server does not support 'range' (byte ranges)."); | ||
79 | goto out; | ||
80 | } | ||
81 | - DPRINTF("CURL: Size = %" PRIu64 "\n", s->len); | ||
82 | + trace_curl_open_size(s->len); | ||
83 | |||
84 | qemu_mutex_lock(&s->mutex); | ||
85 | curl_clean_state(state); | ||
86 | @@ -XXX,XX +XXX,XX @@ static void curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb) | ||
87 | state->acb[0] = acb; | ||
88 | |||
89 | snprintf(state->range, 127, "%" PRIu64 "-%" PRIu64, start, end); | ||
90 | - DPRINTF("CURL (AIO): Reading %" PRIu64 " at %" PRIu64 " (%s)\n", | ||
91 | - acb->bytes, start, state->range); | ||
92 | + trace_curl_setup_preadv(acb->bytes, start, state->range); | ||
93 | curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range); | ||
94 | |||
95 | curl_multi_add_handle(s->multi, state->curl); | ||
96 | @@ -XXX,XX +XXX,XX @@ static void curl_close(BlockDriverState *bs) | ||
97 | { | ||
98 | BDRVCURLState *s = bs->opaque; | ||
99 | |||
100 | - DPRINTF("CURL: Close\n"); | ||
101 | + trace_curl_close(); | ||
102 | curl_detach_aio_context(bs); | ||
103 | qemu_mutex_destroy(&s->mutex); | ||
104 | |||
105 | diff --git a/block/trace-events b/block/trace-events | ||
106 | index XXXXXXX..XXXXXXX 100644 | ||
107 | --- a/block/trace-events | ||
108 | +++ b/block/trace-events | ||
109 | @@ -XXX,XX +XXX,XX @@ ssh_write(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu" | ||
110 | ssh_write_buf(void *buf, size_t size) "sftp_write buf=%p size=%zu" | ||
111 | ssh_write_return(ssize_t ret) "sftp_write returned %zd" | ||
112 | ssh_seek(int64_t offset) "seeking to offset=%" PRIi64 | ||
113 | + | 34 | + |
114 | +# block/curl.c | 35 | ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); |
115 | +curl_timer_cb(long timeout_ms) "timer callback timeout_ms %ld" | 36 | if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { |
116 | +curl_sock_cb(int action, int fd) "sock action %d on fd %d" | 37 | return ret; |
117 | +curl_read_cb(size_t realsize) "just reading %zu bytes" | ||
118 | +curl_open(const char *file) "opening %s" | ||
119 | +curl_open_size(uint64_t size) "size = %" PRIu64 | ||
120 | +curl_setup_preadv(uint64_t bytes, uint64_t start, const char *range) "reading %" PRIu64 " at %" PRIu64 " (%s)" | ||
121 | +curl_close(void) "close" | ||
122 | -- | 38 | -- |
123 | 2.20.1 | 39 | 2.26.2 |
124 | 40 | ||
125 | diff view generated by jsdifflib |
1 | From: Laurent Vivier <lvivier@redhat.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Signed-off-by: Laurent Vivier <lvivier@redhat.com> | 3 | bdrv_is_allocated_above wrongly handles short backing files: it reports |
4 | Reviewed-by: Richard W.M. Jones <rjones@redhat.com> | 4 | after-EOF space as UNALLOCATED which is wrong, as on read the data is |
5 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 5 | generated on the level of short backing file (if all overlays have |
6 | Message-id: 20181213162727.17438-2-lvivier@redhat.com | 6 | unallocated areas at that place). |
7 | [mreitz: Fixed type of ssh_{read,write}_return's parameter to be ssize_t | 7 | |
8 | instead of size_t] | 8 | Reusing bdrv_common_block_status_above fixes the issue and unifies code |
9 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 9 | path. |
10 | |||
11 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | ||
12 | Reviewed-by: Eric Blake <eblake@redhat.com> | ||
13 | Reviewed-by: Alberto Garcia <berto@igalia.com> | ||
14 | Message-id: 20200924194003.22080-5-vsementsov@virtuozzo.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> | ||
10 | --- | 18 | --- |
11 | block/ssh.c | 46 +++++++++++++++++----------------------------- | 19 | block/io.c | 43 +++++-------------------------------------- |
12 | block/trace-events | 17 +++++++++++++++++ | 20 | 1 file changed, 5 insertions(+), 38 deletions(-) |
13 | 2 files changed, 34 insertions(+), 29 deletions(-) | ||
14 | 21 | ||
15 | diff --git a/block/ssh.c b/block/ssh.c | 22 | diff --git a/block/io.c b/block/io.c |
16 | index XXXXXXX..XXXXXXX 100644 | 23 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/block/ssh.c | 24 | --- a/block/io.c |
18 | +++ b/block/ssh.c | 25 | +++ b/block/io.c |
19 | @@ -XXX,XX +XXX,XX @@ | 26 | @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, |
20 | #include "qapi/qmp/qstring.h" | 27 | * at 'offset + *pnum' may return the same allocation status (in other |
21 | #include "qapi/qobject-input-visitor.h" | 28 | * words, the result is not necessarily the maximum possible range); |
22 | #include "qapi/qobject-output-visitor.h" | 29 | * but 'pnum' will only be 0 when end of file is reached. |
23 | +#include "trace.h" | ||
24 | |||
25 | -/* DEBUG_SSH=1 enables the DPRINTF (debugging printf) statements in | ||
26 | - * this block driver code. | ||
27 | - * | 30 | - * |
28 | +/* | ||
29 | * TRACE_LIBSSH2=<bitmask> enables tracing in libssh2 itself. Note | ||
30 | * that this requires that libssh2 was specially compiled with the | ||
31 | * `./configure --enable-debug' option, so most likely you will have | ||
32 | * to compile it yourself. The meaning of <bitmask> is described | ||
33 | * here: http://www.libssh2.org/libssh2_trace.html | ||
34 | */ | 31 | */ |
35 | -#define DEBUG_SSH 0 | 32 | int bdrv_is_allocated_above(BlockDriverState *top, |
36 | #define TRACE_LIBSSH2 0 /* or try: LIBSSH2_TRACE_SFTP */ | 33 | BlockDriverState *base, |
37 | 34 | bool include_base, int64_t offset, | |
38 | -#define DPRINTF(fmt, ...) \ | 35 | int64_t bytes, int64_t *pnum) |
39 | - do { \ | 36 | { |
40 | - if (DEBUG_SSH) { \ | 37 | - BlockDriverState *intermediate; |
41 | - fprintf(stderr, "ssh: %-15s " fmt "\n", \ | 38 | - int ret; |
42 | - __func__, ##__VA_ARGS__); \ | 39 | - int64_t n = bytes; |
43 | - } \ | ||
44 | - } while (0) | ||
45 | - | 40 | - |
46 | typedef struct BDRVSSHState { | 41 | - assert(base || !include_base); |
47 | /* Coroutine. */ | 42 | - |
48 | CoMutex lock; | 43 | - intermediate = top; |
49 | @@ -XXX,XX +XXX,XX @@ static int check_host_key_knownhosts(BDRVSSHState *s, | 44 | - while (include_base || intermediate != base) { |
50 | switch (r) { | 45 | - int64_t pnum_inter; |
51 | case LIBSSH2_KNOWNHOST_CHECK_MATCH: | 46 | - int64_t size_inter; |
52 | /* OK */ | 47 | - |
53 | - DPRINTF("host key OK: %s", found->key); | 48 | - assert(intermediate); |
54 | + trace_ssh_check_host_key_knownhosts(found->key); | 49 | - ret = bdrv_is_allocated(intermediate, offset, bytes, &pnum_inter); |
55 | break; | 50 | - if (ret < 0) { |
56 | case LIBSSH2_KNOWNHOST_CHECK_MISMATCH: | 51 | - return ret; |
57 | ret = -EINVAL; | 52 | - } |
58 | @@ -XXX,XX +XXX,XX @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts, | 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; | ||
59 | } | 76 | } |
60 | 77 | ||
61 | /* Open the remote file. */ | 78 | - *pnum = n; |
62 | - DPRINTF("opening file %s flags=0x%x creat_mode=0%o", | 79 | - return 0; |
63 | - opts->path, ssh_flags, creat_mode); | 80 | + return !!(ret & BDRV_BLOCK_ALLOCATED); |
64 | + trace_ssh_connect_to_ssh(opts->path, ssh_flags, creat_mode); | ||
65 | s->sftp_handle = libssh2_sftp_open(s->sftp, opts->path, ssh_flags, | ||
66 | creat_mode); | ||
67 | if (!s->sftp_handle) { | ||
68 | @@ -XXX,XX +XXX,XX @@ static int coroutine_fn ssh_co_create_opts(const char *filename, QemuOpts *opts, | ||
69 | /* Get desired file size. */ | ||
70 | ssh_opts->size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), | ||
71 | BDRV_SECTOR_SIZE); | ||
72 | - DPRINTF("total_size=%" PRIi64, ssh_opts->size); | ||
73 | + trace_ssh_co_create_opts(ssh_opts->size); | ||
74 | |||
75 | uri_options = qdict_new(); | ||
76 | ret = parse_uri(filename, uri_options, errp); | ||
77 | @@ -XXX,XX +XXX,XX @@ static void restart_coroutine(void *opaque) | ||
78 | BDRVSSHState *s = bs->opaque; | ||
79 | AioContext *ctx = bdrv_get_aio_context(bs); | ||
80 | |||
81 | - DPRINTF("co=%p", restart->co); | ||
82 | + trace_ssh_restart_coroutine(restart->co); | ||
83 | aio_set_fd_handler(ctx, s->sock, false, NULL, NULL, NULL, NULL); | ||
84 | |||
85 | aio_co_wake(restart->co); | ||
86 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs) | ||
87 | wr_handler = restart_coroutine; | ||
88 | } | ||
89 | |||
90 | - DPRINTF("s->sock=%d rd_handler=%p wr_handler=%p", s->sock, | ||
91 | - rd_handler, wr_handler); | ||
92 | + trace_ssh_co_yield(s->sock, rd_handler, wr_handler); | ||
93 | |||
94 | aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, | ||
95 | false, rd_handler, wr_handler, NULL, &restart); | ||
96 | qemu_coroutine_yield(); | ||
97 | - DPRINTF("s->sock=%d - back", s->sock); | ||
98 | + trace_ssh_co_yield_back(s->sock); | ||
99 | } | 81 | } |
100 | 82 | ||
101 | /* SFTP has a function `libssh2_sftp_seek64' which seeks to a position | 83 | int coroutine_fn |
102 | @@ -XXX,XX +XXX,XX @@ static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags) | ||
103 | bool force = (flags & SSH_SEEK_FORCE) != 0; | ||
104 | |||
105 | if (force || op_read != s->offset_op_read || offset != s->offset) { | ||
106 | - DPRINTF("seeking to offset=%" PRIi64, offset); | ||
107 | + trace_ssh_seek(offset); | ||
108 | libssh2_sftp_seek64(s->sftp_handle, offset); | ||
109 | s->offset = offset; | ||
110 | s->offset_op_read = op_read; | ||
111 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs, | ||
112 | char *buf, *end_of_vec; | ||
113 | struct iovec *i; | ||
114 | |||
115 | - DPRINTF("offset=%" PRIi64 " size=%zu", offset, size); | ||
116 | + trace_ssh_read(offset, size); | ||
117 | |||
118 | ssh_seek(s, offset, SSH_SEEK_READ); | ||
119 | |||
120 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs, | ||
121 | */ | ||
122 | for (got = 0; got < size; ) { | ||
123 | again: | ||
124 | - DPRINTF("sftp_read buf=%p size=%zu", buf, end_of_vec - buf); | ||
125 | + trace_ssh_read_buf(buf, end_of_vec - buf); | ||
126 | r = libssh2_sftp_read(s->sftp_handle, buf, end_of_vec - buf); | ||
127 | - DPRINTF("sftp_read returned %zd", r); | ||
128 | + trace_ssh_read_return(r); | ||
129 | |||
130 | if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) { | ||
131 | co_yield(s, bs); | ||
132 | @@ -XXX,XX +XXX,XX @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs, | ||
133 | char *buf, *end_of_vec; | ||
134 | struct iovec *i; | ||
135 | |||
136 | - DPRINTF("offset=%" PRIi64 " size=%zu", offset, size); | ||
137 | + trace_ssh_write(offset, size); | ||
138 | |||
139 | ssh_seek(s, offset, SSH_SEEK_WRITE); | ||
140 | |||
141 | @@ -XXX,XX +XXX,XX @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs, | ||
142 | |||
143 | for (written = 0; written < size; ) { | ||
144 | again: | ||
145 | - DPRINTF("sftp_write buf=%p size=%zu", buf, end_of_vec - buf); | ||
146 | + trace_ssh_write_buf(buf, end_of_vec - buf); | ||
147 | r = libssh2_sftp_write(s->sftp_handle, buf, end_of_vec - buf); | ||
148 | - DPRINTF("sftp_write returned %zd", r); | ||
149 | + trace_ssh_write_return(r); | ||
150 | |||
151 | if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) { | ||
152 | co_yield(s, bs); | ||
153 | @@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs) | ||
154 | { | ||
155 | int r; | ||
156 | |||
157 | - DPRINTF("fsync"); | ||
158 | + trace_ssh_flush(); | ||
159 | again: | ||
160 | r = libssh2_sftp_fsync(s->sftp_handle); | ||
161 | if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) { | ||
162 | @@ -XXX,XX +XXX,XX @@ static int64_t ssh_getlength(BlockDriverState *bs) | ||
163 | |||
164 | /* Note we cannot make a libssh2 call here. */ | ||
165 | length = (int64_t) s->attrs.filesize; | ||
166 | - DPRINTF("length=%" PRIi64, length); | ||
167 | + trace_ssh_getlength(length); | ||
168 | |||
169 | return length; | ||
170 | } | ||
171 | diff --git a/block/trace-events b/block/trace-events | ||
172 | index XXXXXXX..XXXXXXX 100644 | ||
173 | --- a/block/trace-events | ||
174 | +++ b/block/trace-events | ||
175 | @@ -XXX,XX +XXX,XX @@ iscsi_xcopy(void *src_lun, uint64_t src_off, void *dst_lun, uint64_t dst_off, ui | ||
176 | # block/nbd-client.c | ||
177 | nbd_read_reply_entry_fail(int ret, const char *err) "ret = %d, err: %s" | ||
178 | nbd_co_request_fail(uint64_t from, uint32_t len, uint64_t handle, uint16_t flags, uint16_t type, const char *name, int ret, const char *err) "Request failed { .from = %" PRIu64", .len = %" PRIu32 ", .handle = %" PRIu64 ", .flags = 0x%" PRIx16 ", .type = %" PRIu16 " (%s) } ret = %d, err: %s" | ||
179 | + | ||
180 | +# block/ssh.c | ||
181 | +ssh_restart_coroutine(void *co) "co=%p" | ||
182 | +ssh_flush(void) "fsync" | ||
183 | +ssh_check_host_key_knownhosts(const char *key) "host key OK: %s" | ||
184 | +ssh_connect_to_ssh(char *path, int flags, int mode) "opening file %s flags=0x%x creat_mode=0%o" | ||
185 | +ssh_co_yield(int sock, void *rd_handler, void *wr_handler) "s->sock=%d rd_handler=%p wr_handler=%p" | ||
186 | +ssh_co_yield_back(int sock) "s->sock=%d - back" | ||
187 | +ssh_getlength(int64_t length) "length=%" PRIi64 | ||
188 | +ssh_co_create_opts(uint64_t size) "total_size=%" PRIu64 | ||
189 | +ssh_read(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu" | ||
190 | +ssh_read_buf(void *buf, size_t size) "sftp_read buf=%p size=%zu" | ||
191 | +ssh_read_return(ssize_t ret) "sftp_read returned %zd" | ||
192 | +ssh_write(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu" | ||
193 | +ssh_write_buf(void *buf, size_t size) "sftp_write buf=%p size=%zu" | ||
194 | +ssh_write_return(ssize_t ret) "sftp_write returned %zd" | ||
195 | +ssh_seek(int64_t offset) "seeking to offset=%" PRIi64 | ||
196 | -- | 84 | -- |
197 | 2.20.1 | 85 | 2.26.2 |
198 | 86 | ||
199 | diff view generated by jsdifflib |
1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 1 | From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
---|---|---|---|
2 | 2 | ||
3 | Render block nodes graph with help of graphviz. This new function is | 3 | These cases are fixed by previous patches around block_status and |
4 | for debugging, so there is no sense to put it into qemu.py as a method | 4 | is_allocated. |
5 | of QEMUMachine. Let's instead put it separately. | ||
6 | 5 | ||
7 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> | 6 | Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> |
8 | Acked-by: Eduardo Habkost <ehabkost@redhat.com> | 7 | Reviewed-by: Eric Blake <eblake@redhat.com> |
9 | Reviewed-by: Max Reitz <mreitz@redhat.com> | 8 | Reviewed-by: Alberto Garcia <berto@igalia.com> |
10 | Message-id: 20181221170909.25584-3-vsementsov@virtuozzo.com | 9 | Message-id: 20200924194003.22080-6-vsementsov@virtuozzo.com |
11 | Signed-off-by: Max Reitz <mreitz@redhat.com> | 10 | Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> |
12 | --- | 11 | --- |
13 | scripts/render_block_graph.py | 120 ++++++++++++++++++++++++++++++++++ | 12 | tests/qemu-iotests/274 | 20 +++++++++++ |
14 | 1 file changed, 120 insertions(+) | 13 | tests/qemu-iotests/274.out | 68 ++++++++++++++++++++++++++++++++++++++ |
15 | create mode 100755 scripts/render_block_graph.py | 14 | 2 files changed, 88 insertions(+) |
16 | 15 | ||
17 | diff --git a/scripts/render_block_graph.py b/scripts/render_block_graph.py | 16 | diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 |
18 | new file mode 100755 | 17 | index XXXXXXX..XXXXXXX 100755 |
19 | index XXXXXXX..XXXXXXX | 18 | --- a/tests/qemu-iotests/274 |
20 | --- /dev/null | 19 | +++ b/tests/qemu-iotests/274 |
21 | +++ b/scripts/render_block_graph.py | 20 | @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('base') as base, \ |
22 | @@ -XXX,XX +XXX,XX @@ | 21 | iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) |
23 | +#!/usr/bin/env python | 22 | iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) |
24 | +# | 23 | |
25 | +# Render Qemu Block Graph | 24 | + iotests.log('=== Testing qemu-img commit (top -> base) ===') |
26 | +# | ||
27 | +# Copyright (c) 2018 Virtuozzo International GmbH. All rights reserved. | ||
28 | +# | ||
29 | +# This program is free software; you can redistribute it and/or modify | ||
30 | +# it under the terms of the GNU General Public License as published by | ||
31 | +# the Free Software Foundation; either version 2 of the License, or | ||
32 | +# (at your option) any later version. | ||
33 | +# | ||
34 | +# This program is distributed in the hope that it will be useful, | ||
35 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
36 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
37 | +# GNU General Public License for more details. | ||
38 | +# | ||
39 | +# You should have received a copy of the GNU General Public License | ||
40 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. | ||
41 | +# | ||
42 | + | 25 | + |
43 | +import os | 26 | + create_chain() |
44 | +import sys | 27 | + iotests.qemu_img_log('commit', '-b', base, top) |
45 | +import subprocess | 28 | + iotests.img_info_log(base) |
46 | +import json | 29 | + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) |
47 | +from graphviz import Digraph | 30 | + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) |
48 | +from qemu import MonitorResponseError | ||
49 | + | 31 | + |
32 | + iotests.log('=== Testing QMP active commit (top -> base) ===') | ||
50 | + | 33 | + |
51 | +def perm(arr): | 34 | + create_chain() |
52 | + s = 'w' if 'write' in arr else '_' | 35 | + with create_vm() as vm: |
53 | + s += 'r' if 'consistent-read' in arr else '_' | 36 | + vm.launch() |
54 | + s += 'u' if 'write-unchanged' in arr else '_' | 37 | + vm.qmp_log('block-commit', device='top', base_node='base', |
55 | + s += 'g' if 'graph-mod' in arr else '_' | 38 | + job_id='job0', auto_dismiss=False) |
56 | + s += 's' if 'resize' in arr else '_' | 39 | + vm.run_job('job0', wait=5) |
57 | + return s | ||
58 | + | 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 | ||
59 | + | 57 | + |
60 | +def render_block_graph(qmp, filename, format='png'): | 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 |
61 | + ''' | ||
62 | + Render graph in text (dot) representation into "@filename" and | ||
63 | + representation in @format into "@filename.@format" | ||
64 | + ''' | ||
65 | + | 59 | + |
66 | + bds_nodes = qmp.command('query-named-block-nodes') | 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 |
67 | + bds_nodes = {n['node-name']: n for n in bds_nodes} | ||
68 | + | 61 | + |
69 | + job_nodes = qmp.command('query-block-jobs') | 62 | +wrote 2097152/2097152 bytes at offset 0 |
70 | + job_nodes = {n['device']: n for n in job_nodes} | 63 | +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) |
71 | + | 64 | + |
72 | + block_graph = qmp.command('x-debug-query-block-graph') | 65 | +Image committed. |
73 | + | 66 | + |
74 | + graph = Digraph(comment='Block Nodes Graph') | 67 | +image: TEST_IMG |
75 | + graph.format = format | 68 | +file format: IMGFMT |
76 | + graph.node('permission symbols:\l' | 69 | +virtual size: 2 MiB (2097152 bytes) |
77 | + ' w - Write\l' | 70 | +cluster_size: 65536 |
78 | + ' r - consistent-Read\l' | 71 | +Format specific information: |
79 | + ' u - write - Unchanged\l' | 72 | + compat: 1.1 |
80 | + ' g - Graph-mod\l' | 73 | + compression type: zlib |
81 | + ' s - reSize\l' | 74 | + lazy refcounts: false |
82 | + 'edge label scheme:\l' | 75 | + refcount bits: 16 |
83 | + ' <child type>\l' | 76 | + corrupt: false |
84 | + ' <perm>\l' | 77 | + extended l2: false |
85 | + ' <shared_perm>\l', shape='none') | ||
86 | + | 78 | + |
87 | + for n in block_graph['nodes']: | 79 | +read 1048576/1048576 bytes at offset 0 |
88 | + if n['type'] == 'block-driver': | 80 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) |
89 | + info = bds_nodes[n['name']] | ||
90 | + label = n['name'] + ' [' + info['drv'] + ']' | ||
91 | + if info['drv'] == 'file': | ||
92 | + label += '\n' + os.path.basename(info['file']) | ||
93 | + shape = 'ellipse' | ||
94 | + elif n['type'] == 'block-job': | ||
95 | + info = job_nodes[n['name']] | ||
96 | + label = info['type'] + ' job (' + n['name'] + ')' | ||
97 | + shape = 'box' | ||
98 | + else: | ||
99 | + assert n['type'] == 'block-backend' | ||
100 | + label = n['name'] if n['name'] else 'unnamed blk' | ||
101 | + shape = 'box' | ||
102 | + | 81 | + |
103 | + graph.node(str(n['id']), label, shape=shape) | 82 | +read 1048576/1048576 bytes at offset 1048576 |
83 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
104 | + | 84 | + |
105 | + for e in block_graph['edges']: | 85 | +=== Testing QMP active commit (top -> base) === |
106 | + label = '%s\l%s\l%s\l' % (e['name'], perm(e['perm']), | 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 |
107 | + perm(e['shared-perm'])) | ||
108 | + graph.edge(str(e['parent']), str(e['child']), label=label) | ||
109 | + | 87 | + |
110 | + graph.render(filename) | 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 |
111 | + | 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 | ||
112 | + | 91 | + |
113 | +class LibvirtGuest(): | 92 | +wrote 2097152/2097152 bytes at offset 0 |
114 | + def __init__(self, name): | 93 | +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) |
115 | + self.name = name | ||
116 | + | 94 | + |
117 | + def command(self, cmd): | 95 | +{"execute": "block-commit", "arguments": {"auto-dismiss": false, "base-node": "base", "device": "top", "job-id": "job0"}} |
118 | + # only supports qmp commands without parameters | 96 | +{"return": {}} |
119 | + m = {'execute': cmd} | 97 | +{"execute": "job-complete", "arguments": {"id": "job0"}} |
120 | + ar = ['virsh', 'qemu-monitor-command', self.name, json.dumps(m)] | 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 | ||
121 | + | 116 | + |
122 | + reply = json.loads(subprocess.check_output(ar)) | 117 | +read 1048576/1048576 bytes at offset 0 |
118 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
123 | + | 119 | + |
124 | + if 'error' in reply: | 120 | +read 1048576/1048576 bytes at offset 1048576 |
125 | + raise MonitorResponseError(reply) | 121 | +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) |
126 | + | 122 | + |
127 | + return reply['return'] | 123 | == Resize tests == |
128 | + | 124 | === preallocation=off === |
129 | + | 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 |
130 | +if __name__ == '__main__': | ||
131 | + obj = sys.argv[1] | ||
132 | + out = sys.argv[2] | ||
133 | + | ||
134 | + if os.path.exists(obj): | ||
135 | + # assume unix socket | ||
136 | + qmp = QEMUMonitorProtocol(obj) | ||
137 | + qmp.connect() | ||
138 | + else: | ||
139 | + # assume libvirt guest name | ||
140 | + qmp = LibvirtGuest(obj) | ||
141 | + | ||
142 | + render_block_graph(qmp, out) | ||
143 | -- | 126 | -- |
144 | 2.20.1 | 127 | 2.26.2 |
145 | 128 | ||
146 | diff view generated by jsdifflib |