The following changes since commit 23919ddfd56135cad3cb468a8f54d5a595f024f4: Merge remote-tracking branch 'remotes/aperard/tags/pull-xen-20190827' into staging (2019-08-27 15:52:36 +0100) are available in the Git repository at: https://github.com/XanClic/qemu.git tags/pull-block-2019-08-27 for you to fetch changes up to bb043c056cffcc2f3ce88bfdaf2e76e455c09e2c: iotests: Unify cache mode quoting (2019-08-27 19:48:44 +0200) ---------------------------------------------------------------- Block patches: - qemu-io now accepts a file to read a write pattern from - Ensure that raw files have their first block allocated so we can probe the O_DIRECT alignment if necessary - Various fixes ---------------------------------------------------------------- Denis Plotnikov (1): qemu-io: add pattern file for write command Max Reitz (7): iotests: Fix _filter_img_create() vmdk: Use bdrv_dirname() for relative extent paths iotests: Keep testing broken relative extent paths vmdk: Reject invalid compressed writes iotests: Disable broken streamOptimized tests iotests: Disable 110 for vmdk.twoGbMaxExtentSparse iotests: Disable 126 for flat vmdk subformats Nir Soffer (3): block: posix: Always allocate the first block iotests: Test allocate_first_block() with O_DIRECT iotests: Unify cache mode quoting Stefan Hajnoczi (1): file-posix: fix request_alignment typo Thomas Huth (2): iotests: Check for enabled drivers before testing them tests/check-block: Skip iotests when sanitizers are enabled Vladimir Sementsov-Ogievskiy (1): block: fix permission update in bdrv_replace_node block.c | 5 +- block/file-posix.c | 53 +++++++++- block/vmdk.c | 64 ++++++++---- qemu-io-cmds.c | 99 +++++++++++++++++-- tests/check-block.sh | 5 + tests/qemu-iotests/002 | 1 + tests/qemu-iotests/003 | 1 + tests/qemu-iotests/005 | 3 +- tests/qemu-iotests/009 | 1 + tests/qemu-iotests/010 | 1 + tests/qemu-iotests/011 | 1 + tests/qemu-iotests/017 | 3 +- tests/qemu-iotests/018 | 3 +- tests/qemu-iotests/019 | 3 +- tests/qemu-iotests/020 | 3 +- tests/qemu-iotests/026 | 4 +- tests/qemu-iotests/027 | 1 + tests/qemu-iotests/032 | 1 + tests/qemu-iotests/033 | 1 + tests/qemu-iotests/034 | 3 +- tests/qemu-iotests/037 | 3 +- tests/qemu-iotests/039 | 4 +- tests/qemu-iotests/052 | 2 +- tests/qemu-iotests/059 | 34 ++++++- tests/qemu-iotests/059.out | 26 +++-- tests/qemu-iotests/063 | 3 +- tests/qemu-iotests/071 | 1 + tests/qemu-iotests/072 | 1 + tests/qemu-iotests/081 | 4 +- tests/qemu-iotests/091 | 4 +- tests/qemu-iotests/099 | 1 + tests/qemu-iotests/105 | 3 +- tests/qemu-iotests/110 | 3 +- tests/qemu-iotests/120 | 1 + tests/qemu-iotests/126 | 2 + tests/qemu-iotests/{150.out => 150.out.qcow2} | 0 tests/qemu-iotests/150.out.raw | 12 +++ tests/qemu-iotests/162 | 4 +- tests/qemu-iotests/175 | 47 +++++++-- tests/qemu-iotests/175.out | 16 ++- tests/qemu-iotests/178.out.qcow2 | 4 +- tests/qemu-iotests/184 | 1 + tests/qemu-iotests/186 | 1 + tests/qemu-iotests/197 | 1 + tests/qemu-iotests/215 | 1 + tests/qemu-iotests/221.out | 12 ++- tests/qemu-iotests/251 | 1 + tests/qemu-iotests/253.out | 12 ++- tests/qemu-iotests/common.filter | 4 +- tests/qemu-iotests/common.rc | 14 +++ 50 files changed, 391 insertions(+), 87 deletions(-) rename tests/qemu-iotests/{150.out => 150.out.qcow2} (100%) create mode 100644 tests/qemu-iotests/150.out.raw -- 2.21.0 From: Denis Plotnikov <dplotnikov@virtuozzo.com> The patch allows to provide a pattern file for write command. There was no similar ability before. Signed-off-by: Denis Plotnikov <dplotnikov@virtuozzo.com> Message-id: 20190820164616.4072-1-dplotnikov@virtuozzo.com Reviewed-by: Eric Blake <eblake@redhat.com> [mreitz: Keep optstring in alphabetical order] Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-io-cmds.c | 99 +++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 93 insertions(+), 6 deletions(-) diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static void qemu_io_free(void *p) qemu_vfree(p); } +/* + * qemu_io_alloc_from_file() + * + * Allocates the buffer and populates it with the content of the given file + * up to @len bytes. If the file length is less than @len, then the buffer + * is populated with the file content cyclically. + * + * @blk - the block backend where the buffer content is going to be written to + * @len - the buffer length + * @file_name - the file to read the content from + * + * Returns: the buffer pointer on success + * NULL on error + */ +static void *qemu_io_alloc_from_file(BlockBackend *blk, size_t len, + const char *file_name) +{ + char *buf, *buf_origin; + FILE *f = fopen(file_name, "r"); + int pattern_len; + + if (!f) { + perror(file_name); + return NULL; + } + + if (qemuio_misalign) { + len += MISALIGN_OFFSET; + } + + buf_origin = buf = blk_blockalign(blk, len); + + if (qemuio_misalign) { + buf_origin += MISALIGN_OFFSET; + buf += MISALIGN_OFFSET; + len -= MISALIGN_OFFSET; + } + + pattern_len = fread(buf_origin, 1, len, f); + + if (ferror(f)) { + perror(file_name); + goto error; + } + + if (pattern_len == 0) { + fprintf(stderr, "%s: file is empty\n", file_name); + goto error; + } + + fclose(f); + + if (len > pattern_len) { + len -= pattern_len; + buf += pattern_len; + + while (len > 0) { + size_t len_to_copy = MIN(pattern_len, len); + + memcpy(buf, buf_origin, len_to_copy); + + len -= len_to_copy; + buf += len_to_copy; + } + } + + return buf_origin; + +error: + qemu_io_free(buf_origin); + return NULL; +} + static void dump_buffer(const void *buffer, int64_t offset, int64_t len) { uint64_t i; @@ -XXX,XX +XXX,XX @@ static void write_help(void) " -n, -- with -z, don't allow slow fallback\n" " -p, -- ignored for backwards compatibility\n" " -P, -- use different pattern to fill file\n" +" -s, -- use a pattern file to fill the write buffer\n" " -C, -- report statistics in a machine parsable format\n" " -q, -- quiet mode, do not show I/O statistics\n" " -u, -- with -z, allow unmapping\n" @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t write_cmd = { .perm = BLK_PERM_WRITE, .argmin = 2, .argmax = -1, - .args = "[-bcCfnquz] [-P pattern] off len", + .args = "[-bcCfnquz] [-P pattern | -s source_file] off len", .oneline = "writes a number of bytes at a specified offset", .help = write_help, }; @@ -XXX,XX +XXX,XX @@ static int write_f(BlockBackend *blk, int argc, char **argv) { struct timespec t1, t2; bool Cflag = false, qflag = false, bflag = false; - bool Pflag = false, zflag = false, cflag = false; + bool Pflag = false, zflag = false, cflag = false, sflag = false; int flags = 0; int c, cnt, ret; char *buf = NULL; @@ -XXX,XX +XXX,XX @@ static int write_f(BlockBackend *blk, int argc, char **argv) /* Some compilers get confused and warn if this is not initialized. */ int64_t total = 0; int pattern = 0xcd; + const char *file_name = NULL; - while ((c = getopt(argc, argv, "bcCfnpP:quz")) != -1) { + while ((c = getopt(argc, argv, "bcCfnpP:qs:uz")) != -1) { switch (c) { case 'b': bflag = true; @@ -XXX,XX +XXX,XX @@ static int write_f(BlockBackend *blk, int argc, char **argv) case 'q': qflag = true; break; + case 's': + sflag = true; + file_name = optarg; + break; case 'u': flags |= BDRV_REQ_MAY_UNMAP; break; @@ -XXX,XX +XXX,XX @@ static int write_f(BlockBackend *blk, int argc, char **argv) return -EINVAL; } - if (zflag && Pflag) { - printf("-z and -P cannot be specified at the same time\n"); + if (zflag + Pflag + sflag > 1) { + printf("Only one of -z, -P, and -s " + "can be specified at the same time\n"); return -EINVAL; } @@ -XXX,XX +XXX,XX @@ static int write_f(BlockBackend *blk, int argc, char **argv) } if (!zflag) { - buf = qemu_io_alloc(blk, count, pattern); + if (sflag) { + buf = qemu_io_alloc_from_file(blk, count, file_name); + if (!buf) { + return -EINVAL; + } + } else { + buf = qemu_io_alloc(blk, count, pattern); + } } clock_gettime(CLOCK_MONOTONIC, &t1); -- 2.21.0 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> It's wrong to OR shared permissions. It may lead to crash on further permission updates. Also, no needs to consider previously calculated permissions, as at this point we already bind all new parents and bdrv_get_cumulative_perm result is enough. So fix the bug by just set permissions by bdrv_get_cumulative_perm result. Bug was introduced in long ago 234ac1a9025, in 2.9. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20190824100740.61635-1-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, { BdrvChild *c, *next; GSList *list = NULL, *p; - uint64_t old_perm, old_shared; uint64_t perm = 0, shared = BLK_PERM_ALL; int ret; @@ -XXX,XX +XXX,XX @@ void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, bdrv_unref(from); } - bdrv_get_cumulative_perm(to, &old_perm, &old_shared); - bdrv_set_perm(to, old_perm | perm, old_shared | shared); + bdrv_get_cumulative_perm(to, &perm, &shared); + bdrv_set_perm(to, perm, shared); out: g_slist_free(list); -- 2.21.0 From: Nir Soffer <nirsof@gmail.com> When creating an image with preallocation "off" or "falloc", the first block of the image is typically not allocated. When using Gluster storage backed by XFS filesystem, reading this block using direct I/O succeeds regardless of request length, fooling alignment detection. In this case we fallback to a safe value (4096) instead of the optimal value (512), which may lead to unneeded data copying when aligning requests. Allocating the first block avoids the fallback. Since we allocate the first block even with preallocation=off, we no longer create images with zero disk size: $ ./qemu-img create -f raw test.raw 1g Formatting 'test.raw', fmt=raw size=1073741824 $ ls -lhs test.raw 4.0K -rw-r--r--. 1 nsoffer nsoffer 1.0G Aug 16 23:48 test.raw And converting the image requires additional cluster: $ ./qemu-img measure -f raw -O qcow2 test.raw required size: 458752 fully allocated size: 1074135040 When using format like vmdk with multiple files per image, we allocate one block per file: $ ./qemu-img create -f vmdk -o subformat=twoGbMaxExtentFlat test.vmdk 4g Formatting 'test.vmdk', fmt=vmdk size=4294967296 compat6=off hwversion=undefined subformat=twoGbMaxExtentFlat $ ls -lhs test*.vmdk 4.0K -rw-r--r--. 1 nsoffer nsoffer 2.0G Aug 27 03:23 test-f001.vmdk 4.0K -rw-r--r--. 1 nsoffer nsoffer 2.0G Aug 27 03:23 test-f002.vmdk 4.0K -rw-r--r--. 1 nsoffer nsoffer 353 Aug 27 03:23 test.vmdk I did quick performance test for copying disks with qemu-img convert to new raw target image to Gluster storage with sector size of 512 bytes: for i in $(seq 10); do rm -f dst.raw sleep 10 time ./qemu-img convert -f raw -O raw -t none -T none src.raw dst.raw done Here is a table comparing the total time spent: Type Before(s) After(s) Diff(%) --------------------------------------- real 530.028 469.123 -11.4 user 17.204 10.768 -37.4 sys 17.881 7.011 -60.7 We can see very clear improvement in CPU usage. Signed-off-by: Nir Soffer <nsoffer@redhat.com> Message-id: 20190827010528.8818-2-nsoffer@redhat.com Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/file-posix.c | 51 +++++++++++++++++++ tests/qemu-iotests/059.out | 2 +- tests/qemu-iotests/{150.out => 150.out.qcow2} | 0 tests/qemu-iotests/150.out.raw | 12 +++++ tests/qemu-iotests/175 | 19 ++++--- tests/qemu-iotests/175.out | 8 +-- tests/qemu-iotests/178.out.qcow2 | 4 +- tests/qemu-iotests/221.out | 12 +++-- tests/qemu-iotests/253.out | 12 +++-- 9 files changed, 99 insertions(+), 21 deletions(-) rename tests/qemu-iotests/{150.out => 150.out.qcow2} (100%) create mode 100644 tests/qemu-iotests/150.out.raw diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ static int handle_aiocb_discard(void *opaque) return ret; } +/* + * Help alignment probing by allocating the first block. + * + * When reading with direct I/O from unallocated area on Gluster backed by XFS, + * reading succeeds regardless of request length. In this case we fallback to + * safe alignment which is not optimal. Allocating the first block avoids this + * fallback. + * + * fd may be opened with O_DIRECT, but we don't know the buffer alignment or + * request alignment, so we use safe values. + * + * Returns: 0 on success, -errno on failure. Since this is an optimization, + * caller may ignore failures. + */ +static int allocate_first_block(int fd, size_t max_size) +{ + size_t write_size = (max_size < MAX_BLOCKSIZE) + ? BDRV_SECTOR_SIZE + : MAX_BLOCKSIZE; + size_t max_align = MAX(MAX_BLOCKSIZE, getpagesize()); + void *buf; + ssize_t n; + int ret; + + buf = qemu_memalign(max_align, write_size); + memset(buf, 0, write_size); + + do { + n = pwrite(fd, buf, write_size, 0); + } while (n == -1 && errno == EINTR); + + ret = (n == -1) ? -errno : 0; + + qemu_vfree(buf); + return ret; +} + static int handle_aiocb_truncate(void *opaque) { RawPosixAIOData *aiocb = opaque; @@ -XXX,XX +XXX,XX @@ static int handle_aiocb_truncate(void *opaque) /* posix_fallocate() doesn't set errno. */ error_setg_errno(errp, -result, "Could not preallocate new data"); + } else if (current_length == 0) { + /* + * posix_fallocate() uses fallocate() if the filesystem + * supports it, or fallback to manually writing zeroes. If + * fallocate() was used, unaligned reads from the fallocated + * area in raw_probe_alignment() will succeed, hence we need to + * allocate the first block. + * + * Optimize future alignment probing; ignore failures. + */ + allocate_first_block(fd, offset); } } else { result = 0; @@ -XXX,XX +XXX,XX @@ static int handle_aiocb_truncate(void *opaque) if (ftruncate(fd, offset) != 0) { result = -errno; error_setg_errno(errp, -result, "Could not resize file"); + } else if (current_length == 0 && offset > current_length) { + /* Optimize future alignment probing; ignore failures. */ + allocate_first_block(fd, offset); } return result; default: diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/059.out +++ b/tests/qemu-iotests/059.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824000 subformat=twoGbMax image: TEST_DIR/t.vmdk file format: vmdk virtual size: 0.977 TiB (1073741824000 bytes) -disk size: 16 KiB +disk size: 1.97 MiB Format specific information: cid: XXXXXXXX parent cid: XXXXXXXX diff --git a/tests/qemu-iotests/150.out b/tests/qemu-iotests/150.out.qcow2 similarity index 100% rename from tests/qemu-iotests/150.out rename to tests/qemu-iotests/150.out.qcow2 diff --git a/tests/qemu-iotests/150.out.raw b/tests/qemu-iotests/150.out.raw new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/150.out.raw @@ -XXX,XX +XXX,XX @@ +QA output created by 150 + +=== Mapping sparse conversion === + +Offset Length File +0 0x1000 TEST_DIR/t.IMGFMT + +=== Mapping non-sparse conversion === + +Offset Length File +0 0x100000 TEST_DIR/t.IMGFMT +*** done diff --git a/tests/qemu-iotests/175 b/tests/qemu-iotests/175 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/175 +++ b/tests/qemu-iotests/175 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # the file size. This function hides the resulting difference in the # stat -c '%b' output. # Parameter 1: Number of blocks an empty file occupies -# Parameter 2: Image size in bytes +# Parameter 2: Minimal number of blocks in an image +# Parameter 3: Image size in bytes _filter_blocks() { extra_blocks=$1 - img_size=$2 + min_blocks=$2 + img_size=$3 - sed -e "s/blocks=$extra_blocks\\(\$\\|[^0-9]\\)/nothing allocated/" \ - -e "s/blocks=$((extra_blocks + img_size / 512))\\(\$\\|[^0-9]\\)/everything allocated/" + sed -e "s/blocks=$min_blocks\\(\$\\|[^0-9]\\)/min allocation/" \ + -e "s/blocks=$((extra_blocks + img_size / 512))\\(\$\\|[^0-9]\\)/max allocation/" } # get standard environment, filters and checks @@ -XXX,XX +XXX,XX @@ size=$((1 * 1024 * 1024)) touch "$TEST_DIR/empty" extra_blocks=$(stat -c '%b' "$TEST_DIR/empty") +# We always write the first byte; check how many blocks this filesystem +# allocates to match empty image alloation. +printf "\0" > "$TEST_DIR/empty" +min_blocks=$(stat -c '%b' "$TEST_DIR/empty") + echo echo "== creating image with default preallocation ==" _make_test_img $size | _filter_imgfmt -stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $size +stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $size for mode in off full falloc; do echo echo "== creating image with preallocation $mode ==" IMGOPTS=preallocation=$mode _make_test_img $size | _filter_imgfmt - stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $size + stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $size done # success, all done diff --git a/tests/qemu-iotests/175.out b/tests/qemu-iotests/175.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/175.out +++ b/tests/qemu-iotests/175.out @@ -XXX,XX +XXX,XX @@ QA output created by 175 == creating image with default preallocation == Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 -size=1048576, nothing allocated +size=1048576, min allocation == creating image with preallocation off == Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=off -size=1048576, nothing allocated +size=1048576, min allocation == creating image with preallocation full == Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=full -size=1048576, everything allocated +size=1048576, max allocation == creating image with preallocation falloc == Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=falloc -size=1048576, everything allocated +size=1048576, max allocation *** done diff --git a/tests/qemu-iotests/178.out.qcow2 b/tests/qemu-iotests/178.out.qcow2 index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/178.out.qcow2 +++ b/tests/qemu-iotests/178.out.qcow2 @@ -XXX,XX +XXX,XX @@ converted image file size in bytes: 196608 == raw input image with data (human) == Formatting 'TEST_DIR/t.qcow2', fmt=IMGFMT size=1073741824 -required size: 393216 +required size: 458752 fully allocated size: 1074135040 wrote 512/512 bytes at offset 512 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ converted image file size in bytes: 196608 Formatting 'TEST_DIR/t.qcow2', fmt=IMGFMT size=1073741824 { - "required": 393216, + "required": 458752, "fully-allocated": 1074135040 } wrote 512/512 bytes at offset 512 diff --git a/tests/qemu-iotests/221.out b/tests/qemu-iotests/221.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/221.out +++ b/tests/qemu-iotests/221.out @@ -XXX,XX +XXX,XX @@ QA output created by 221 === Check mapping of unaligned raw image === Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65537 -[{ "start": 0, "length": 66048, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] -[{ "start": 0, "length": 66048, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 61952, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 61952, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] wrote 1/1 bytes at offset 65536 1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -[{ "start": 0, "length": 65536, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 61440, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, { "start": 65536, "length": 1, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, { "start": 65537, "length": 511, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] -[{ "start": 0, "length": 65536, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 61440, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, { "start": 65536, "length": 1, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, { "start": 65537, "length": 511, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] *** done diff --git a/tests/qemu-iotests/253.out b/tests/qemu-iotests/253.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/253.out +++ b/tests/qemu-iotests/253.out @@ -XXX,XX +XXX,XX @@ QA output created by 253 === Check mapping of unaligned raw image === Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048575 -[{ "start": 0, "length": 1048576, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] -[{ "start": 0, "length": 1048576, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 1044480, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 1044480, "depth": 0, "zero": true, "data": false, "offset": OFFSET}] wrote 65535/65535 bytes at offset 983040 63.999 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -[{ "start": 0, "length": 983040, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 978944, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, { "start": 983040, "length": 65536, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] -[{ "start": 0, "length": 983040, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, +[{ "start": 0, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": OFFSET}, +{ "start": 4096, "length": 978944, "depth": 0, "zero": true, "data": false, "offset": OFFSET}, { "start": 983040, "length": 65536, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] *** done -- 2.21.0 From: Nir Soffer <nirsof@gmail.com> Using block_resize we can test allocate_first_block() with file descriptor opened with O_DIRECT, ensuring that it works for any size larger than 4096 bytes. Testing smaller sizes is tricky as the result depends on the filesystem used for testing. For example on NFS any size will work since O_DIRECT does not require any alignment. Signed-off-by: Nir Soffer <nsoffer@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20190827010528.8818-3-nsoffer@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/175 | 28 ++++++++++++++++++++++++++++ tests/qemu-iotests/175.out | 8 ++++++++ 2 files changed, 36 insertions(+) diff --git a/tests/qemu-iotests/175 b/tests/qemu-iotests/175 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/175 +++ b/tests/qemu-iotests/175 @@ -XXX,XX +XXX,XX @@ _filter_blocks() -e "s/blocks=$((extra_blocks + img_size / 512))\\(\$\\|[^0-9]\\)/max allocation/" } +# Resize image using block_resize. +# Parameter 1: image path +# Parameter 2: new size +_block_resize() +{ + local path=$1 + local size=$2 + + $QEMU -qmp stdio -nographic -nodefaults \ + -blockdev file,node-name=file,filename=$path,cache.direct=on \ + <<EOF +{'execute': 'qmp_capabilities'} +{'execute': 'block_resize', 'arguments': {'node-name': 'file', 'size': $size}} +{'execute': 'quit'} +EOF +} + # get standard environment, filters and checks . ./common.rc . ./common.filter @@ -XXX,XX +XXX,XX @@ _supported_fmt raw _supported_proto file _supported_os Linux +_default_cache_mode none +_supported_cache_modes none directsync + size=$((1 * 1024 * 1024)) touch "$TEST_DIR/empty" @@ -XXX,XX +XXX,XX @@ for mode in off full falloc; do stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $size done +for new_size in 4096 1048576; do + echo + echo "== resize empty image with block_resize ==" + _make_test_img 0 | _filter_imgfmt + _block_resize $TEST_IMG $new_size >/dev/null + stat -c "size=%s, blocks=%b" $TEST_IMG | _filter_blocks $extra_blocks $min_blocks $new_size +done + # success, all done echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/175.out b/tests/qemu-iotests/175.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/175.out +++ b/tests/qemu-iotests/175.out @@ -XXX,XX +XXX,XX @@ size=1048576, max allocation == creating image with preallocation falloc == Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 preallocation=falloc size=1048576, max allocation + +== resize empty image with block_resize == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=0 +size=4096, min allocation + +== resize empty image with block_resize == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=0 +size=1048576, min allocation *** done -- 2.21.0 fe646693acc changed qemu-img create's output so that it no longer prints single quotes around parameter values. The subformat and adapter_type filters in _filter_img_create() have never been adapted to that change. Fixes: fe646693acc13ac48b98435d14149ab04dc597bc Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Message-id: 20190815153638.4600-2-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/059.out | 16 ++++++++-------- tests/qemu-iotests/common.filter | 4 ++-- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/059.out +++ b/tests/qemu-iotests/059.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 qemu-io: can't open device TEST_DIR/t.vmdk: L1 size too big === Testing monolithicFlat creation and opening === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2147483648 subformat=monolithicFlat +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2147483648 image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 2 GiB (2147483648 bytes) === Testing monolithicFlat with zeroed_grain === qemu-img: TEST_DIR/t.IMGFMT: Flat image can't enable zeroed grain -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2147483648 subformat=monolithicFlat +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2147483648 === Testing big twoGbMaxExtentFlat === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824000 subformat=twoGbMaxExtentFlat +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824000 image: TEST_DIR/t.vmdk file format: vmdk virtual size: 0.977 TiB (1073741824000 bytes) @@ -XXX,XX +XXX,XX @@ Format specific information: qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Invalid extent line: RW 12582912 VMFS "dummy.IMGFMT" 1 === Testing truncated sparse === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=107374182400 subformat=monolithicSparse +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=107374182400 qemu-img: Could not open 'TEST_DIR/t.IMGFMT': File truncated, expecting at least 13172736 bytes === Converting to streamOptimized from image with small cluster size=== @@ -XXX,XX +XXX,XX @@ wrote 512/512 bytes at offset 10240 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing monolithicFlat with internally generated JSON file name === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 subformat=monolithicFlat +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 qemu-io: can't open: Cannot use relative extent paths with VMDK descriptor file 'json:{"image": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, "driver": "blkdebug", "inject-error.0.event": "read_aio"}' === Testing version 3 === @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 64931328 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing 4TB monolithicFlat creation and IO === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=4398046511104 subformat=monolithicFlat +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=4398046511104 image: TEST_DIR/t.IMGFMT file format: IMGFMT virtual size: 4 TiB (4398046511104 bytes) @@ -XXX,XX +XXX,XX @@ read 1024/1024 bytes at offset 966367641600 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing qemu-img map on extents === -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=33285996544 subformat=monolithicSparse +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=33285996544 wrote 1024/1024 bytes at offset 65024 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) wrote 1024/1024 bytes at offset 2147483136 @@ -XXX,XX +XXX,XX @@ Offset Length Mapped to File 0 0x20000 0x3f0000 TEST_DIR/t.vmdk 0x7fff0000 0x20000 0x410000 TEST_DIR/t.vmdk 0x140000000 0x10000 0x430000 TEST_DIR/t.vmdk -Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=33285996544 subformat=twoGbMaxExtentSparse +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=33285996544 wrote 1024/1024 bytes at offset 65024 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) wrote 1024/1024 bytes at offset 2147483136 diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -XXX,XX +XXX,XX @@ _filter_img_create() -e "s# compat6=\\(on\\|off\\)##g" \ -e "s# static=\\(on\\|off\\)##g" \ -e "s# zeroed_grain=\\(on\\|off\\)##g" \ - -e "s# subformat='[^']*'##g" \ - -e "s# adapter_type='[^']*'##g" \ + -e "s# subformat=[^ ]*##g" \ + -e "s# adapter_type=[^ ]*##g" \ -e "s# hwversion=[^ ]*##g" \ -e "s# lazy_refcounts=\\(on\\|off\\)##g" \ -e "s# block_size=[0-9]\\+##g" \ -- 2.21.0 This makes iotest 033 pass with e.g. subformat=monolithicFlat. It also turns a former error in 059 into success. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20190815153638.4600-3-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/vmdk.c | 54 ++++++++++++++++++++++++-------------- tests/qemu-iotests/059 | 7 +++-- tests/qemu-iotests/059.out | 4 ++- 3 files changed, 42 insertions(+), 23 deletions(-) diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static const char *next_line(const char *s) } static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, - const char *desc_file_path, QDict *options, - Error **errp) + QDict *options, Error **errp) { int ret; int matches; @@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, const char *p, *np; int64_t sectors = 0; int64_t flat_offset; + char *desc_file_dir = NULL; char *extent_path; BdrvChild *extent_file; BDRVVmdkState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, continue; } - if (!path_is_absolute(fname) && !path_has_protocol(fname) && - !desc_file_path[0]) - { - bdrv_refresh_filename(bs->file->bs); - error_setg(errp, "Cannot use relative extent paths with VMDK " - "descriptor file '%s'", bs->file->bs->filename); - return -EINVAL; - } + if (path_is_absolute(fname)) { + extent_path = g_strdup(fname); + } else { + if (!desc_file_dir) { + desc_file_dir = bdrv_dirname(bs->file->bs, errp); + if (!desc_file_dir) { + bdrv_refresh_filename(bs->file->bs); + error_prepend(errp, "Cannot use relative paths with VMDK " + "descriptor file '%s': ", + bs->file->bs->filename); + ret = -EINVAL; + goto out; + } + } - extent_path = path_combine(desc_file_path, fname); + extent_path = g_strconcat(desc_file_dir, fname, NULL); + } ret = snprintf(extent_opt_prefix, 32, "extents.%d", s->num_extents); assert(ret < 32); @@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, g_free(extent_path); if (local_err) { error_propagate(errp, local_err); - return -EINVAL; + ret = -EINVAL; + goto out; } /* save to extents array */ @@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, 0, 0, 0, 0, 0, &extent, errp); if (ret < 0) { bdrv_unref_child(bs, extent_file); - return ret; + goto out; } extent->flat_start_offset = flat_offset << 9; } else if (!strcmp(type, "SPARSE") || !strcmp(type, "VMFSSPARSE")) { @@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, g_free(buf); if (ret) { bdrv_unref_child(bs, extent_file); - return ret; + goto out; } extent = &s->extents[s->num_extents - 1]; } else if (!strcmp(type, "SESPARSE")) { ret = vmdk_open_se_sparse(bs, extent_file, bs->open_flags, errp); if (ret) { bdrv_unref_child(bs, extent_file); - return ret; + goto out; } extent = &s->extents[s->num_extents - 1]; } else { error_setg(errp, "Unsupported extent type '%s'", type); bdrv_unref_child(bs, extent_file); - return -ENOTSUP; + ret = -ENOTSUP; + goto out; } extent->type = g_strdup(type); } - return 0; + + ret = 0; + goto out; invalid: np = next_line(p); @@ -XXX,XX +XXX,XX @@ invalid: np--; } error_setg(errp, "Invalid extent line: %.*s", (int)(np - p), p); - return -EINVAL; + ret = -EINVAL; + +out: + g_free(desc_file_dir); + return ret; } static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf, @@ -XXX,XX +XXX,XX @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf, } s->create_type = g_strdup(ct); s->desc_offset = 0; - ret = vmdk_parse_extents(buf, bs, bs->file->bs->exact_filename, options, - errp); + ret = vmdk_parse_extents(buf, bs, options, errp); exit: return ret; } diff --git a/tests/qemu-iotests/059 b/tests/qemu-iotests/059 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/059 +++ b/tests/qemu-iotests/059 @@ -XXX,XX +XXX,XX @@ $QEMU_IMG convert -f qcow2 -O vmdk -o subformat=streamOptimized "$TEST_IMG.qcow2 echo echo "=== Testing monolithicFlat with internally generated JSON file name ===" +# Should work, because bdrv_dirname() works fine with blkdebug IMGOPTS="subformat=monolithicFlat" _make_test_img 64M -$QEMU_IO -c "open -o driver=$IMGFMT,file.driver=blkdebug,file.image.filename=$TEST_IMG,file.inject-error.0.event=read_aio" 2>&1 \ - | _filter_testdir | _filter_imgfmt +$QEMU_IO -c "open -o driver=$IMGFMT,file.driver=blkdebug,file.image.filename=$TEST_IMG,file.inject-error.0.event=read_aio" \ + -c info \ + 2>&1 \ + | _filter_testdir | _filter_imgfmt | _filter_img_info _cleanup_test_img echo diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/059.out +++ b/tests/qemu-iotests/059.out @@ -XXX,XX +XXX,XX @@ wrote 512/512 bytes at offset 10240 === Testing monolithicFlat with internally generated JSON file name === Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 -qemu-io: can't open: Cannot use relative extent paths with VMDK descriptor file 'json:{"image": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, "driver": "blkdebug", "inject-error.0.event": "read_aio"}' +format name: IMGFMT +cluster size: 0 bytes +vm state offset: 0 bytes === Testing version 3 === image: TEST_DIR/iotest-version3.IMGFMT -- 2.21.0 We had a test for a case where relative extent paths did not work, but unfortunately we just fixed the underlying problem, so it works now. This patch adds a new test case that still fails. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Message-id: 20190815153638.4600-4-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/059 | 27 +++++++++++++++++++++++++++ tests/qemu-iotests/059.out | 4 ++++ 2 files changed, 31 insertions(+) diff --git a/tests/qemu-iotests/059 b/tests/qemu-iotests/059 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/059 +++ b/tests/qemu-iotests/059 @@ -XXX,XX +XXX,XX @@ $QEMU_IMG convert -f qcow2 -O vmdk -o subformat=streamOptimized "$TEST_IMG.qcow2 echo echo "=== Testing monolithicFlat with internally generated JSON file name ===" + +echo '--- blkdebug ---' # Should work, because bdrv_dirname() works fine with blkdebug IMGOPTS="subformat=monolithicFlat" _make_test_img 64M $QEMU_IO -c "open -o driver=$IMGFMT,file.driver=blkdebug,file.image.filename=$TEST_IMG,file.inject-error.0.event=read_aio" \ @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "open -o driver=$IMGFMT,file.driver=blkdebug,file.image.filename=$TE | _filter_testdir | _filter_imgfmt | _filter_img_info _cleanup_test_img +echo '--- quorum ---' +# Should not work, because bdrv_dirname() does not work with quorum +IMGOPTS="subformat=monolithicFlat" _make_test_img 64M +cp "$TEST_IMG" "$TEST_IMG.orig" + +filename="json:{ + \"driver\": \"$IMGFMT\", + \"file\": { + \"driver\": \"quorum\", + \"children\": [ { + \"driver\": \"file\", + \"filename\": \"$TEST_IMG\" + }, { + \"driver\": \"file\", + \"filename\": \"$TEST_IMG.orig\" + } ], + \"vote-threshold\": 1 + } }" + +filename=$(echo "$filename" | tr '\n' ' ' | sed -e 's/\s\+/ /g') +$QEMU_IMG info "$filename" 2>&1 \ + | sed -e "s/'json:[^']*'/\$QUORUM_FILE/g" \ + | _filter_testdir | _filter_imgfmt | _filter_img_info + + echo echo "=== Testing version 3 ===" _use_sample_img iotest-version3.vmdk.bz2 diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/059.out +++ b/tests/qemu-iotests/059.out @@ -XXX,XX +XXX,XX @@ wrote 512/512 bytes at offset 10240 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Testing monolithicFlat with internally generated JSON file name === +--- blkdebug --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 format name: IMGFMT cluster size: 0 bytes vm state offset: 0 bytes +--- quorum --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +qemu-img: Could not open $QUORUM_FILE: Cannot use relative paths with VMDK descriptor file $QUORUM_FILE: Cannot generate a base directory for quorum nodes === Testing version 3 === image: TEST_DIR/iotest-version3.IMGFMT -- 2.21.0 Compressed writes generally have to write full clusters, not just in theory but also in practice when it comes to vmdk's streamOptimized subformat. It currently is just silently broken for writes with non-zero in-cluster offsets: $ qemu-img create -f vmdk -o subformat=streamOptimized foo.vmdk 1M $ qemu-io -c 'write 4k 4k' -c 'read 4k 4k' foo.vmdk wrote 4096/4096 bytes at offset 4096 4 KiB, 1 ops; 00.01 sec (443.724 KiB/sec and 110.9309 ops/sec) read failed: Invalid argument (The technical reason is that vmdk_write_extent() just writes the incomplete compressed data actually to offset 4k. When reading the data, vmdk_read_extent() looks at offset 0 and finds the compressed data size to be 0, because that is what it reads from there. This yields an error.) For incomplete writes with zero in-cluster offsets, the error path when reading the rest of the cluster is a bit different, but the result is the same: $ qemu-img create -f vmdk -o subformat=streamOptimized foo.vmdk 1M $ qemu-io -c 'write 0k 4k' -c 'read 4k 4k' foo.vmdk wrote 4096/4096 bytes at offset 0 4 KiB, 1 ops; 00.01 sec (362.641 KiB/sec and 90.6603 ops/sec) read failed: Invalid argument (Here, vmdk_read_extent() finds the data and then sees that the uncompressed data is short.) It is better to reject invalid writes than to make the user believe they might have succeeded and then fail when trying to read it back. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Message-id: 20190815153638.4600-5-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/vmdk.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, if (extent->compressed) { void *compressed_data; + /* Only whole clusters */ + if (offset_in_cluster || + n_bytes > (extent->cluster_sectors * SECTOR_SIZE) || + (n_bytes < (extent->cluster_sectors * SECTOR_SIZE) && + offset + n_bytes != extent->end_sector * SECTOR_SIZE)) + { + ret = -EINVAL; + goto out; + } + if (!extent->has_marker) { ret = -EINVAL; goto out; -- 2.21.0 streamOptimized does not support writes that do not span exactly one cluster. Furthermore, it cannot rewrite already allocated clusters. As such, many iotests do not work with it. Disable them. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20190815153638.4600-6-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/002 | 1 + tests/qemu-iotests/003 | 1 + tests/qemu-iotests/005 | 3 ++- tests/qemu-iotests/009 | 1 + tests/qemu-iotests/010 | 1 + tests/qemu-iotests/011 | 1 + tests/qemu-iotests/017 | 3 ++- tests/qemu-iotests/018 | 3 ++- tests/qemu-iotests/019 | 3 ++- tests/qemu-iotests/020 | 3 ++- tests/qemu-iotests/027 | 1 + tests/qemu-iotests/032 | 1 + tests/qemu-iotests/033 | 1 + tests/qemu-iotests/034 | 3 ++- tests/qemu-iotests/037 | 3 ++- tests/qemu-iotests/063 | 3 ++- tests/qemu-iotests/072 | 1 + tests/qemu-iotests/105 | 3 ++- tests/qemu-iotests/197 | 1 + tests/qemu-iotests/215 | 1 + tests/qemu-iotests/251 | 1 + 21 files changed, 30 insertions(+), 9 deletions(-) diff --git a/tests/qemu-iotests/002 b/tests/qemu-iotests/002 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/002 +++ b/tests/qemu-iotests/002 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" size=128M diff --git a/tests/qemu-iotests/003 b/tests/qemu-iotests/003 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/003 +++ b/tests/qemu-iotests/003 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" size=128M offset=67M diff --git a/tests/qemu-iotests/005 b/tests/qemu-iotests/005 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/005 +++ b/tests/qemu-iotests/005 @@ -XXX,XX +XXX,XX @@ _supported_fmt generic _supported_proto generic _supported_os Linux _unsupported_imgopts "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" \ + "subformat=streamOptimized" # vpc is limited to 127GB, so we can't test it here if [ "$IMGFMT" = "vpc" ]; then diff --git a/tests/qemu-iotests/009 b/tests/qemu-iotests/009 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/009 +++ b/tests/qemu-iotests/009 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" size=6G diff --git a/tests/qemu-iotests/010 b/tests/qemu-iotests/010 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/010 +++ b/tests/qemu-iotests/010 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" size=6G diff --git a/tests/qemu-iotests/011 b/tests/qemu-iotests/011 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/011 +++ b/tests/qemu-iotests/011 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" size=6G diff --git a/tests/qemu-iotests/017 b/tests/qemu-iotests/017 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/017 +++ b/tests/qemu-iotests/017 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow qcow2 vmdk qed _supported_proto generic _unsupported_proto vxhs -_unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" +_unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" \ + "subformat=streamOptimized" TEST_OFFSETS="0 4294967296" diff --git a/tests/qemu-iotests/018 b/tests/qemu-iotests/018 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/018 +++ b/tests/qemu-iotests/018 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow qcow2 vmdk qed _supported_proto file _supported_os Linux -_unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" +_unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" \ + "streamOptimized" TEST_OFFSETS="0 4294967296" diff --git a/tests/qemu-iotests/019 b/tests/qemu-iotests/019 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/019 +++ b/tests/qemu-iotests/019 @@ -XXX,XX +XXX,XX @@ _supported_proto file _supported_os Linux _unsupported_imgopts "subformat=monolithicFlat" \ "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" \ + "subformat=streamOptimized" TEST_OFFSETS="0 4294967296" CLUSTER_SIZE=65536 diff --git a/tests/qemu-iotests/020 b/tests/qemu-iotests/020 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/020 +++ b/tests/qemu-iotests/020 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow qcow2 vmdk qed _supported_proto file _unsupported_imgopts "subformat=monolithicFlat" \ "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" \ + "subformat=streamOptimized" TEST_OFFSETS="0 4294967296" diff --git a/tests/qemu-iotests/027 b/tests/qemu-iotests/027 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/027 +++ b/tests/qemu-iotests/027 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt vmdk qcow qcow2 qed _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" size=128M diff --git a/tests/qemu-iotests/032 b/tests/qemu-iotests/032 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/032 +++ b/tests/qemu-iotests/032 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # This works for any image format (though unlikely to segfault for raw) _supported_fmt generic _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" echo echo === Prepare image === diff --git a/tests/qemu-iotests/033 b/tests/qemu-iotests/033 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/033 +++ b/tests/qemu-iotests/033 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto generic +_unsupported_imgopts "subformat=streamOptimized" size=128M diff --git a/tests/qemu-iotests/034 b/tests/qemu-iotests/034 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/034 +++ b/tests/qemu-iotests/034 @@ -XXX,XX +XXX,XX @@ _supported_proto file _supported_os Linux _unsupported_imgopts "subformat=monolithicFlat" \ "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" \ + "subformat=streamOptimized" CLUSTER_SIZE=4k size=128M diff --git a/tests/qemu-iotests/037 b/tests/qemu-iotests/037 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/037 +++ b/tests/qemu-iotests/037 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow qcow2 vmdk qed _supported_proto file _unsupported_imgopts "subformat=monolithicFlat" \ "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" \ + "subformat=streamOptimized" CLUSTER_SIZE=4k size=128M diff --git a/tests/qemu-iotests/063 b/tests/qemu-iotests/063 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/063 +++ b/tests/qemu-iotests/063 @@ -XXX,XX +XXX,XX @@ _supported_fmt qcow qcow2 vmdk qed raw _supported_proto file _unsupported_imgopts "subformat=monolithicFlat" \ "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" \ + "subformat=streamOptimized" _make_test_img 4M diff --git a/tests/qemu-iotests/072 b/tests/qemu-iotests/072 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/072 +++ b/tests/qemu-iotests/072 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt vpc vmdk vhdx vdi qed qcow2 qcow _supported_proto file +_unsupported_imgopts "subformat=streamOptimized" IMG_SIZE=64M diff --git a/tests/qemu-iotests/105 b/tests/qemu-iotests/105 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/105 +++ b/tests/qemu-iotests/105 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 vmdk vhdx qed _supported_proto generic _unsupported_imgopts "subformat=twoGbMaxExtentFlat" \ - "subformat=twoGbMaxExtentSparse" + "subformat=twoGbMaxExtentSparse" \ + "subformat=streamOptimized" echo echo "creating large image" diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/197 +++ b/tests/qemu-iotests/197 @@ -XXX,XX +XXX,XX @@ _supported_fmt generic _supported_proto generic # LUKS support may be possible, but it complicates things. _unsupported_fmt luks +_unsupported_imgopts "subformat=streamOptimized" echo echo '=== Copy-on-read ===' diff --git a/tests/qemu-iotests/215 b/tests/qemu-iotests/215 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/215 +++ b/tests/qemu-iotests/215 @@ -XXX,XX +XXX,XX @@ _supported_fmt generic _supported_proto generic # LUKS support may be possible, but it complicates things. _unsupported_fmt luks +_unsupported_imgopts "subformat=streamOptimized" echo echo '=== Copy-on-read ===' diff --git a/tests/qemu-iotests/251 b/tests/qemu-iotests/251 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/251 +++ b/tests/qemu-iotests/251 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto file _supported_os Linux +_unsupported_imgopts "subformat=streamOptimized" if [ "$IMGOPTSSYNTAX" = "true" ]; then # We use json:{} filenames here, so we cannot work with additional options. -- 2.21.0 The error message for the test case where we have a quorum node for which no directory name can be generated is different: For twoGbMaxExtentSparse, it complains that it cannot open the extent file. For other (sub)formats, it just notes that it cannot determine the backing file path. Both are fine, but just disable twoGbMaxExtentSparse for simplicity's sake. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Message-id: 20190815153638.4600-7-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/110 | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/110 b/tests/qemu-iotests/110 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/110 +++ b/tests/qemu-iotests/110 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # Any format supporting backing files _supported_fmt qed qcow qcow2 vmdk _supported_proto file -_unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" +_unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" \ + "subformat=twoGbMaxExtentSparse" TEST_IMG_REL=$(basename "$TEST_IMG") -- 2.21.0 iotest 126 requires backing file support, which flat vmdks cannot offer. Skip this test for such subformats. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20190815153638.4600-8-mreitz@redhat.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/126 | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tests/qemu-iotests/126 b/tests/qemu-iotests/126 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/126 +++ b/tests/qemu-iotests/126 @@ -XXX,XX +XXX,XX @@ status=1 # failure is the default! # Needs backing file support _supported_fmt qcow qcow2 qed vmdk +_unsupported_imgopts "subformat=monolithicFlat" \ + "subformat=twoGbMaxExtentFlat" # This is the default protocol (and we want to test the difference between # colons which separate a protocol prefix from the rest and colons which are # just part of the filename, so we cannot test protocols which require a prefix) -- 2.21.0 From: Stefan Hajnoczi <stefanha@redhat.com> Fixes: a6b257a08e3d72219f03e461a52152672fec0612 ("file-posix: Handle undetectable alignment") Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190827101328.4062-1-stefanha@redhat.com Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/file-posix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp) for (i = 0; i < ARRAY_SIZE(alignments); i++) { align = alignments[i]; if (raw_is_io_aligned(fd, buf + align, max_align)) { - /* Fallback to request_aligment. */ + /* Fallback to request_alignment. */ s->buf_align = (align != 1) ? align : bs->bl.request_alignment; break; } -- 2.21.0 From: Thomas Huth <thuth@redhat.com> It is possible to enable only a subset of the block drivers with the "--block-drv-rw-whitelist" option of the "configure" script. All other drivers are marked as unusable (or only included as read-only with the "--block-drv-ro-whitelist" option). If an iotest is now using such a disabled block driver, it is failing - which is bad, since at least the tests in the "auto" group should be able to deal with this situation. Thus let's introduce a "_require_drivers" function that can be used by the shell tests to check for the availability of certain drivers first, and marks the test as "not run" if one of the drivers is missing. This patch mainly targets the test in the "auto" group which should never fail in such a case, but also improves some of the other tests along the way. Note that we also assume that the "qcow2" and "file" drivers are always available - otherwise it does not make sense to run "make check-block" at all (which only tests with qcow2 by default). Signed-off-by: Thomas Huth <thuth@redhat.com> Message-id: 20190823133552.11680-1-thuth@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/071 | 1 + tests/qemu-iotests/081 | 4 +--- tests/qemu-iotests/099 | 1 + tests/qemu-iotests/120 | 1 + tests/qemu-iotests/162 | 4 +--- tests/qemu-iotests/184 | 1 + tests/qemu-iotests/186 | 1 + tests/qemu-iotests/common.rc | 14 ++++++++++++++ 8 files changed, 21 insertions(+), 6 deletions(-) diff --git a/tests/qemu-iotests/071 b/tests/qemu-iotests/071 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/071 +++ b/tests/qemu-iotests/071 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file +_require_drivers blkdebug blkverify do_run_qemu() { diff --git a/tests/qemu-iotests/081 b/tests/qemu-iotests/081 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/081 +++ b/tests/qemu-iotests/081 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt raw _supported_proto file _supported_os Linux +_require_drivers quorum do_run_qemu() { @@ -XXX,XX +XXX,XX @@ run_qemu() | _filter_qemu_io | _filter_generated_node_ids } -test_quorum=$($QEMU_IMG --help|grep quorum) -[ "$test_quorum" = "" ] && _supported_fmt quorum - quorum="driver=raw,file.driver=quorum,file.vote-threshold=2" quorum="$quorum,file.children.0.file.filename=$TEST_DIR/1.raw" quorum="$quorum,file.children.1.file.filename=$TEST_DIR/2.raw" diff --git a/tests/qemu-iotests/099 b/tests/qemu-iotests/099 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/099 +++ b/tests/qemu-iotests/099 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow qcow2 qed vdi vhdx vmdk vpc _supported_proto file _supported_os Linux +_require_drivers blkdebug blkverify _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat" \ "subformat=twoGbMaxExtentSparse" diff --git a/tests/qemu-iotests/120 b/tests/qemu-iotests/120 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/120 +++ b/tests/qemu-iotests/120 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic _supported_proto file _unsupported_fmt luks +_require_drivers raw _make_test_img 64M diff --git a/tests/qemu-iotests/162 b/tests/qemu-iotests/162 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/162 +++ b/tests/qemu-iotests/162 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 . ./common.filter _supported_fmt generic - -test_ssh=$($QEMU_IMG --help | grep '^Supported formats:.* ssh\( \|$\)') -[ "$test_ssh" = "" ] && _notrun "ssh support required" +_require_drivers ssh echo echo '=== NBD ===' diff --git a/tests/qemu-iotests/184 b/tests/qemu-iotests/184 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/184 +++ b/tests/qemu-iotests/184 @@ -XXX,XX +XXX,XX @@ trap "exit \$status" 0 1 2 3 15 . ./common.filter _supported_os Linux +_require_drivers throttle do_run_qemu() { diff --git a/tests/qemu-iotests/186 b/tests/qemu-iotests/186 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/186 +++ b/tests/qemu-iotests/186 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file +_require_drivers null-co if [ "$QEMU_DEFAULT_MACHINE" != "pc" ]; then _notrun "Requires a PC machine" diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _require_command() [ -x "$c" ] || _notrun "$1 utility required, skipped this test" } +# Check that a set of drivers has been whitelisted in the QEMU binary +# +_require_drivers() +{ + available=$($QEMU -drive format=help | \ + sed -e '/Supported formats:/!d' -e 's/Supported formats://') + for driver + do + if ! echo "$available" | grep -q " $driver\( \|$\)"; then + _notrun "$driver not available" + fi + done +} + # make sure this script returns success true -- 2.21.0 From: Thomas Huth <thuth@redhat.com> The sanitizers (especially the address sanitizer from Clang) are sometimes printing out warnings or false positives - this spoils the output of the iotests, causing some of the tests to fail. Thus let's skip the automatic iotests during "make check" when the user configured QEMU with --enable-sanitizers. Signed-off-by: Thomas Huth <thuth@redhat.com> Message-id: 20190823084203.29734-1-thuth@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/check-block.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tests/check-block.sh b/tests/check-block.sh index XXXXXXX..XXXXXXX 100755 --- a/tests/check-block.sh +++ b/tests/check-block.sh @@ -XXX,XX +XXX,XX @@ if grep -q "TARGET_GPROF=y" *-softmmu/config-target.mak 2>/dev/null ; then exit 0 fi +if grep -q "CFLAGS.*-fsanitize" config-host.mak 2>/dev/null ; then + echo "Sanitizers are enabled ==> Not running the qemu-iotests." + exit 0 +fi + if [ -z "$(find . -name 'qemu-system-*' -print)" ]; then echo "No qemu-system binary available ==> Not running the qemu-iotests." exit 0 -- 2.21.0 From: Nir Soffer <nirsof@gmail.com> Quoting cache mode is not needed, and most tests use unquoted values. Unify all test to use the same style. Message-id: 20190827173432.7656-1-nsoffer@redhat.com Signed-off-by: Nir Soffer <nsoffer@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/026 | 4 ++-- tests/qemu-iotests/039 | 4 ++-- tests/qemu-iotests/052 | 2 +- tests/qemu-iotests/091 | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/tests/qemu-iotests/026 b/tests/qemu-iotests/026 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/026 +++ b/tests/qemu-iotests/026 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 # Currently only qcow2 supports rebasing _supported_fmt qcow2 _supported_proto file -_default_cache_mode "writethrough" -_supported_cache_modes "writethrough" "none" +_default_cache_mode writethrough +_supported_cache_modes writethrough none # The refcount table tests expect a certain minimum width for refcount entries # (so that the refcount table actually needs to grow); that minimum is 16 bits, # being the default refcount entry width. diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/039 +++ b/tests/qemu-iotests/039 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -_default_cache_mode "writethrough" -_supported_cache_modes "writethrough" +_default_cache_mode writethrough +_supported_cache_modes writethrough size=128M diff --git a/tests/qemu-iotests/052 b/tests/qemu-iotests/052 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/052 +++ b/tests/qemu-iotests/052 @@ -XXX,XX +XXX,XX @@ _supported_fmt generic _supported_proto file # Don't do O_DIRECT on tmpfs -_supported_cache_modes "writeback" "writethrough" "unsafe" +_supported_cache_modes writeback writethrough unsafe size=128M _make_test_img $size diff --git a/tests/qemu-iotests/091 b/tests/qemu-iotests/091 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/091 +++ b/tests/qemu-iotests/091 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow2 _supported_proto file _supported_os Linux -_default_cache_mode "none" -_supported_cache_modes "writethrough" "none" "writeback" +_default_cache_mode none +_supported_cache_modes writethrough none writeback size=1G -- 2.21.0 The following changes since commit 2387df497b4b4bcf754eb7398edca82889e2ef54: Merge remote-tracking branch 'remotes/armbru/tags/pull-qapi-2020-10-10' into staging (2020-10-12 11:29:42 +0100) are available in the Git repository at: https://gitlab.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to 3664ec6bbe236126b79d251d4037889e7181ab55: iotests: add commit top->base cases to 274 (2020-10-12 16:47:58 +0100) ---------------------------------------------------------------- Pull request v2: * Rebase and resolve conflict with commit 029a88c9a7e3 ("qemu-nbd: Honor SIGINT and SIGHUP") [Peter] ---------------------------------------------------------------- Coiby Xu (7): libvhost-user: Allow vu_message_read to be replaced libvhost-user: remove watch for kick_fd when de-initialize vu-dev util/vhost-user-server: generic vhost user server block: move logical block size check function to a common utility function block/export: vhost-user block device backend server test: new qTest case to test the vhost-user-blk-server MAINTAINERS: Add vhost-user block device backend server maintainer Philippe Mathieu-Daudé (1): block/nvme: Add driver statistics for access alignment and hw errors Stefan Hajnoczi (17): util/vhost-user-server: s/fileds/fields/ typo fix util/vhost-user-server: drop unnecessary QOM cast util/vhost-user-server: drop unnecessary watch deletion block/export: consolidate request structs into VuBlockReq util/vhost-user-server: drop unused DevicePanicNotifier util/vhost-user-server: fix memory leak in vu_message_read() util/vhost-user-server: check EOF when reading payload util/vhost-user-server: rework vu_client_trip() coroutine lifecycle block/export: report flush errors block/export: convert vhost-user-blk server to block export API util/vhost-user-server: move header to include/ util/vhost-user-server: use static library in meson.build qemu-storage-daemon: avoid compiling blockdev_ss twice block: move block exports to libblockdev block/export: add iothread and fixed-iothread options block/export: add vhost-user-blk multi-queue support tests/qtest: add multi-queue test case to vhost-user-blk-test Vladimir Sementsov-Ogievskiy (5): block/io: fix bdrv_co_block_status_above block/io: bdrv_common_block_status_above: support include_base block/io: bdrv_common_block_status_above: support bs == base block/io: fix bdrv_is_allocated_above iotests: add commit top->base cases to 274 MAINTAINERS | 10 + qapi/block-core.json | 24 +- qapi/block-export.json | 36 +- block/coroutines.h | 2 + block/export/vhost-user-blk-server.h | 19 + contrib/libvhost-user/libvhost-user.h | 21 + include/qemu/vhost-user-server.h | 65 ++ tests/qtest/libqos/libqtest.h | 17 + tests/qtest/libqos/vhost-user-blk.h | 48 ++ util/block-helpers.h | 19 + block/export/export.c | 37 +- block/export/vhost-user-blk-server.c | 431 +++++++++++ block/io.c | 132 ++-- block/nvme.c | 27 + block/qcow2.c | 16 +- contrib/libvhost-user/libvhost-user-glib.c | 2 +- contrib/libvhost-user/libvhost-user.c | 15 +- hw/core/qdev-properties-system.c | 31 +- nbd/server.c | 2 - qemu-nbd.c | 25 +- softmmu/vl.c | 4 + stubs/blk-exp-close-all.c | 7 + tests/qtest/libqos/vhost-user-blk.c | 129 ++++ tests/qtest/libqtest.c | 36 +- tests/qtest/vhost-user-blk-test.c | 822 +++++++++++++++++++++ tests/vhost-user-bridge.c | 2 + tools/virtiofsd/fuse_virtio.c | 4 +- util/block-helpers.c | 46 ++ util/vhost-user-server.c | 446 +++++++++++ block/export/meson.build | 3 +- contrib/libvhost-user/meson.build | 1 + meson.build | 22 +- nbd/meson.build | 2 + storage-daemon/meson.build | 3 +- stubs/meson.build | 1 + tests/qemu-iotests/274 | 20 + tests/qemu-iotests/274.out | 68 ++ tests/qtest/libqos/meson.build | 1 + tests/qtest/meson.build | 4 +- util/meson.build | 4 + 40 files changed, 2476 insertions(+), 128 deletions(-) create mode 100644 block/export/vhost-user-blk-server.h create mode 100644 include/qemu/vhost-user-server.h create mode 100644 tests/qtest/libqos/vhost-user-blk.h create mode 100644 util/block-helpers.h create mode 100644 block/export/vhost-user-blk-server.c create mode 100644 stubs/blk-exp-close-all.c create mode 100644 tests/qtest/libqos/vhost-user-blk.c create mode 100644 tests/qtest/vhost-user-blk-test.c create mode 100644 util/block-helpers.c create mode 100644 util/vhost-user-server.c -- 2.26.2 From: Philippe Mathieu-Daudé <philmd@redhat.com> Keep statistics of some hardware errors, and number of aligned/unaligned I/O accesses. QMP example booting a full RHEL 8.3 aarch64 guest: { "execute": "query-blockstats" } { "return": [ { "device": "", "node-name": "drive0", "stats": { "flush_total_time_ns": 6026948, "wr_highest_offset": 3383991230464, "wr_total_time_ns": 807450995, "failed_wr_operations": 0, "failed_rd_operations": 0, "wr_merged": 3, "wr_bytes": 50133504, "failed_unmap_operations": 0, "failed_flush_operations": 0, "account_invalid": false, "rd_total_time_ns": 1846979900, "flush_operations": 130, "wr_operations": 659, "rd_merged": 1192, "rd_bytes": 218244096, "account_failed": false, "idle_time_ns": 2678641497, "rd_operations": 7406, }, "driver-specific": { "driver": "nvme", "completion-errors": 0, "unaligned-accesses": 2959, "aligned-accesses": 4477 }, "qdev": "/machine/peripheral-anon/device[0]/virtio-backend" } ] } Suggested-by: Stefan Hajnoczi <stefanha@gmail.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20201001162939.1567915-1-philmd@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-core.json | 24 +++++++++++++++++++++++- block/nvme.c | 27 +++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 1 deletion(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ 'discard-nb-failed': 'uint64', 'discard-bytes-ok': 'uint64' } } +## +# @BlockStatsSpecificNvme: +# +# NVMe driver statistics +# +# @completion-errors: The number of completion errors. +# +# @aligned-accesses: The number of aligned accesses performed by +# the driver. +# +# @unaligned-accesses: The number of unaligned accesses performed by +# the driver. +# +# Since: 5.2 +## +{ 'struct': 'BlockStatsSpecificNvme', + 'data': { + 'completion-errors': 'uint64', + 'aligned-accesses': 'uint64', + 'unaligned-accesses': 'uint64' } } + ## # @BlockStatsSpecific: # @@ -XXX,XX +XXX,XX @@ 'discriminator': 'driver', 'data': { 'file': 'BlockStatsSpecificFile', - 'host_device': 'BlockStatsSpecificFile' } } + 'host_device': 'BlockStatsSpecificFile', + 'nvme': 'BlockStatsSpecificNvme' } } ## # @BlockStats: diff --git a/block/nvme.c b/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -XXX,XX +XXX,XX @@ struct BDRVNVMeState { /* PCI address (required for nvme_refresh_filename()) */ char *device; + + struct { + uint64_t completion_errors; + uint64_t aligned_accesses; + uint64_t unaligned_accesses; + } stats; }; #define NVME_BLOCK_OPT_DEVICE "device" @@ -XXX,XX +XXX,XX @@ static bool nvme_process_completion(NVMeQueuePair *q) break; } ret = nvme_translate_error(c); + if (ret) { + s->stats.completion_errors++; + } q->cq.head = (q->cq.head + 1) % NVME_QUEUE_SIZE; if (!q->cq.head) { q->cq_phase = !q->cq_phase; @@ -XXX,XX +XXX,XX @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes, assert(QEMU_IS_ALIGNED(bytes, s->page_size)); assert(bytes <= s->max_transfer); if (nvme_qiov_aligned(bs, qiov)) { + s->stats.aligned_accesses++; return nvme_co_prw_aligned(bs, offset, bytes, qiov, is_write, flags); } + s->stats.unaligned_accesses++; trace_nvme_prw_buffered(s, offset, bytes, qiov->niov, is_write); buf = qemu_try_memalign(s->page_size, bytes); @@ -XXX,XX +XXX,XX @@ static void nvme_unregister_buf(BlockDriverState *bs, void *host) qemu_vfio_dma_unmap(s->vfio, host); } +static BlockStatsSpecific *nvme_get_specific_stats(BlockDriverState *bs) +{ + BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1); + BDRVNVMeState *s = bs->opaque; + + stats->driver = BLOCKDEV_DRIVER_NVME; + stats->u.nvme = (BlockStatsSpecificNvme) { + .completion_errors = s->stats.completion_errors, + .aligned_accesses = s->stats.aligned_accesses, + .unaligned_accesses = s->stats.unaligned_accesses, + }; + + return stats; +} + static const char *const nvme_strong_runtime_opts[] = { NVME_BLOCK_OPT_DEVICE, NVME_BLOCK_OPT_NAMESPACE, @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = { .bdrv_refresh_filename = nvme_refresh_filename, .bdrv_refresh_limits = nvme_refresh_limits, .strong_runtime_opts = nvme_strong_runtime_opts, + .bdrv_get_specific_stats = nvme_get_specific_stats, .bdrv_detach_aio_context = nvme_detach_aio_context, .bdrv_attach_aio_context = nvme_attach_aio_context, -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Allow vu_message_read to be replaced by one which will make use of the QIOChannel functions. Thus reading vhost-user message won't stall the guest. For slave channel, we still use the default vu_message_read. Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200918080912.321299-2-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- contrib/libvhost-user/libvhost-user.h | 21 +++++++++++++++++++++ contrib/libvhost-user/libvhost-user-glib.c | 2 +- contrib/libvhost-user/libvhost-user.c | 14 +++++++------- tests/vhost-user-bridge.c | 2 ++ tools/virtiofsd/fuse_virtio.c | 4 ++-- 5 files changed, 33 insertions(+), 10 deletions(-) diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.h +++ b/contrib/libvhost-user/libvhost-user.h @@ -XXX,XX +XXX,XX @@ */ #define VHOST_USER_MAX_RAM_SLOTS 32 +#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) + typedef enum VhostSetConfigType { VHOST_SET_CONFIG_TYPE_MASTER = 0, VHOST_SET_CONFIG_TYPE_MIGRATION = 1, @@ -XXX,XX +XXX,XX @@ typedef uint64_t (*vu_get_features_cb) (VuDev *dev); typedef void (*vu_set_features_cb) (VuDev *dev, uint64_t features); typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg, int *do_reply); +typedef bool (*vu_read_msg_cb) (VuDev *dev, int sock, VhostUserMsg *vmsg); typedef void (*vu_queue_set_started_cb) (VuDev *dev, int qidx, bool started); typedef bool (*vu_queue_is_processed_in_order_cb) (VuDev *dev, int qidx); typedef int (*vu_get_config_cb) (VuDev *dev, uint8_t *config, uint32_t len); @@ -XXX,XX +XXX,XX @@ struct VuDev { bool broken; uint16_t max_queues; + /* @read_msg: custom method to read vhost-user message + * + * Read data from vhost_user socket fd and fill up + * the passed VhostUserMsg *vmsg struct. + * + * If reading fails, it should close the received set of file + * descriptors as socket message's auxiliary data. + * + * For the details, please refer to vu_message_read in libvhost-user.c + * which will be used by default if not custom method is provided when + * calling vu_init + * + * Returns: true if vhost-user message successfully received, + * otherwise return false. + * + */ + vu_read_msg_cb read_msg; /* @set_watch: add or update the given fd to the watch set, * call cb when condition is met */ vu_set_watch_cb set_watch; @@ -XXX,XX +XXX,XX @@ bool vu_init(VuDev *dev, uint16_t max_queues, int socket, vu_panic_cb panic, + vu_read_msg_cb read_msg, vu_set_watch_cb set_watch, vu_remove_watch_cb remove_watch, const VuDevIface *iface); diff --git a/contrib/libvhost-user/libvhost-user-glib.c b/contrib/libvhost-user/libvhost-user-glib.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user-glib.c +++ b/contrib/libvhost-user/libvhost-user-glib.c @@ -XXX,XX +XXX,XX @@ vug_init(VugDev *dev, uint16_t max_queues, int socket, g_assert(dev); g_assert(iface); - if (!vu_init(&dev->parent, max_queues, socket, panic, set_watch, + if (!vu_init(&dev->parent, max_queues, socket, panic, NULL, set_watch, remove_watch, iface)) { return false; } diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -XXX,XX +XXX,XX @@ /* The version of inflight buffer */ #define INFLIGHT_VERSION 1 -#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64) - /* The version of the protocol we support */ #define VHOST_USER_VERSION 1 #define LIBVHOST_USER_DEBUG 0 @@ -XXX,XX +XXX,XX @@ have_userfault(void) } static bool -vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) +vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg) { char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {}; struct iovec iov = { @@ -XXX,XX +XXX,XX @@ vu_process_message_reply(VuDev *dev, const VhostUserMsg *vmsg) goto out; } - if (!vu_message_read(dev, dev->slave_fd, &msg_reply)) { + if (!vu_message_read_default(dev, dev->slave_fd, &msg_reply)) { goto out; } @@ -XXX,XX +XXX,XX @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) /* Wait for QEMU to confirm that it's registered the handler for the * faults. */ - if (!vu_message_read(dev, dev->sock, vmsg) || + if (!dev->read_msg(dev, dev->sock, vmsg) || vmsg->size != sizeof(vmsg->payload.u64) || vmsg->payload.u64 != 0) { vu_panic(dev, "failed to receive valid ack for postcopy set-mem-table"); @@ -XXX,XX +XXX,XX @@ vu_dispatch(VuDev *dev) int reply_requested; bool need_reply, success = false; - if (!vu_message_read(dev, dev->sock, &vmsg)) { + if (!dev->read_msg(dev, dev->sock, &vmsg)) { goto end; } @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, uint16_t max_queues, int socket, vu_panic_cb panic, + vu_read_msg_cb read_msg, vu_set_watch_cb set_watch, vu_remove_watch_cb remove_watch, const VuDevIface *iface) @@ -XXX,XX +XXX,XX @@ vu_init(VuDev *dev, dev->sock = socket; dev->panic = panic; + dev->read_msg = read_msg ? read_msg : vu_message_read_default; dev->set_watch = set_watch; dev->remove_watch = remove_watch; dev->iface = iface; @@ -XXX,XX +XXX,XX @@ static void _vu_queue_notify(VuDev *dev, VuVirtq *vq, bool sync) vu_message_write(dev, dev->slave_fd, &vmsg); if (ack) { - vu_message_read(dev, dev->slave_fd, &vmsg); + vu_message_read_default(dev, dev->slave_fd, &vmsg); } return; } diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c index XXXXXXX..XXXXXXX 100644 --- a/tests/vhost-user-bridge.c +++ b/tests/vhost-user-bridge.c @@ -XXX,XX +XXX,XX @@ vubr_accept_cb(int sock, void *ctx) VHOST_USER_BRIDGE_MAX_QUEUES, conn_fd, vubr_panic, + NULL, vubr_set_watch, vubr_remove_watch, &vuiface)) { @@ -XXX,XX +XXX,XX @@ vubr_new(const char *path, bool client) VHOST_USER_BRIDGE_MAX_QUEUES, dev->sock, vubr_panic, + NULL, vubr_set_watch, vubr_remove_watch, &vuiface)) { diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c index XXXXXXX..XXXXXXX 100644 --- a/tools/virtiofsd/fuse_virtio.c +++ b/tools/virtiofsd/fuse_virtio.c @@ -XXX,XX +XXX,XX @@ int virtio_session_mount(struct fuse_session *se) se->vu_socketfd = data_sock; se->virtio_dev->se = se; pthread_rwlock_init(&se->virtio_dev->vu_dispatch_rwlock, NULL); - vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, fv_set_watch, - fv_remove_watch, &fv_iface); + vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, NULL, + fv_set_watch, fv_remove_watch, &fv_iface); return 0; } -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> When the client is running in gdb and quit command is run in gdb, QEMU will still dispatch the event which will cause segment fault in the callback function. Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-3-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- contrib/libvhost-user/libvhost-user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -XXX,XX +XXX,XX @@ vu_deinit(VuDev *dev) } if (vq->kick_fd != -1) { + dev->remove_watch(dev, vq->kick_fd); close(vq->kick_fd); vq->kick_fd = -1; } -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Sharing QEMU devices via vhost-user protocol. Only one vhost-user client can connect to the server one time. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-4-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 65 ++++++ util/vhost-user-server.c | 428 +++++++++++++++++++++++++++++++++++++++ util/meson.build | 1 + 3 files changed, 494 insertions(+) create mode 100644 util/vhost-user-server.h create mode 100644 util/vhost-user-server.c diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU devices via vhost-user protocol + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ + +#ifndef VHOST_USER_SERVER_H +#define VHOST_USER_SERVER_H + +#include "contrib/libvhost-user/libvhost-user.h" +#include "io/channel-socket.h" +#include "io/channel-file.h" +#include "io/net-listener.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "standard-headers/linux/virtio_blk.h" + +typedef struct VuFdWatch { + VuDev *vu_dev; + int fd; /*kick fd*/ + void *pvt; + vu_watch_cb cb; + bool processing; + QTAILQ_ENTRY(VuFdWatch) next; +} VuFdWatch; + +typedef struct VuServer VuServer; +typedef void DevicePanicNotifierFn(VuServer *server); + +struct VuServer { + QIONetListener *listener; + AioContext *ctx; + DevicePanicNotifierFn *device_panic_notifier; + int max_queues; + const VuDevIface *vu_iface; + VuDev vu_dev; + QIOChannel *ioc; /* The I/O channel with the client */ + QIOChannelSocket *sioc; /* The underlying data channel with the client */ + /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ + QIOChannel *ioc_slave; + QIOChannelSocket *sioc_slave; + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ + QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; + /* restart coroutine co_trip if AIOContext is changed */ + bool aio_context_changed; + bool processing_msg; +}; + +bool vhost_user_server_start(VuServer *server, + SocketAddress *unix_socket, + AioContext *ctx, + uint16_t max_queues, + DevicePanicNotifierFn *device_panic_notifier, + const VuDevIface *vu_iface, + Error **errp); + +void vhost_user_server_stop(VuServer *server); + +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); + +#endif /* VHOST_USER_SERVER_H */ diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU devices via vhost-user protocol + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "qemu/main-loop.h" +#include "vhost-user-server.h" + +static void vmsg_close_fds(VhostUserMsg *vmsg) +{ + int i; + for (i = 0; i < vmsg->fd_num; i++) { + close(vmsg->fds[i]); + } +} + +static void vmsg_unblock_fds(VhostUserMsg *vmsg) +{ + int i; + for (i = 0; i < vmsg->fd_num; i++) { + qemu_set_nonblock(vmsg->fds[i]); + } +} + +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, + gpointer opaque); + +static void close_client(VuServer *server) +{ + /* + * Before closing the client + * + * 1. Let vu_client_trip stop processing new vhost-user msg + * + * 2. remove kick_handler + * + * 3. wait for the kick handler to be finished + * + * 4. wait for the current vhost-user msg to be finished processing + */ + + QIOChannelSocket *sioc = server->sioc; + /* When this is set vu_client_trip will stop new processing vhost-user message */ + server->sioc = NULL; + + VuFdWatch *vu_fd_watch, *next; + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, + NULL, NULL, NULL); + } + + while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (!vu_fd_watch->processing) { + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); + g_free(vu_fd_watch); + } + } + } + + while (server->processing_msg) { + if (server->ioc->read_coroutine) { + server->ioc->read_coroutine = NULL; + qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, + NULL, server->ioc); + server->processing_msg = false; + } + } + + vu_deinit(&server->vu_dev); + object_unref(OBJECT(sioc)); + object_unref(OBJECT(server->ioc)); +} + +static void panic_cb(VuDev *vu_dev, const char *buf) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + + /* avoid while loop in close_client */ + server->processing_msg = false; + + if (buf) { + error_report("vu_panic: %s", buf); + } + + if (server->sioc) { + close_client(server); + } + + if (server->device_panic_notifier) { + server->device_panic_notifier(server); + } + + /* + * Set the callback function for network listener so another + * vhost-user client can connect to this server + */ + qio_net_listener_set_client_func(server->listener, + vu_accept, + server, + NULL); +} + +static bool coroutine_fn +vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) +{ + struct iovec iov = { + .iov_base = (char *)vmsg, + .iov_len = VHOST_USER_HDR_SIZE, + }; + int rc, read_bytes = 0; + Error *local_err = NULL; + /* + * Store fds/nfds returned from qio_channel_readv_full into + * temporary variables. + * + * VhostUserMsg is a packed structure, gcc will complain about passing + * pointer to a packed structure member if we pass &VhostUserMsg.fd_num + * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, + * thus two temporary variables nfds and fds are used here. + */ + size_t nfds = 0, nfds_t = 0; + const size_t max_fds = G_N_ELEMENTS(vmsg->fds); + int *fds_t = NULL; + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + QIOChannel *ioc = server->ioc; + + if (!ioc) { + error_report_err(local_err); + goto fail; + } + + assert(qemu_in_coroutine()); + do { + /* + * qio_channel_readv_full may have short reads, keeping calling it + * until getting VHOST_USER_HDR_SIZE or 0 bytes in total + */ + rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); + if (rc < 0) { + if (rc == QIO_CHANNEL_ERR_BLOCK) { + qio_channel_yield(ioc, G_IO_IN); + continue; + } else { + error_report_err(local_err); + return false; + } + } + read_bytes += rc; + if (nfds_t > 0) { + if (nfds + nfds_t > max_fds) { + error_report("A maximum of %zu fds are allowed, " + "however got %lu fds now", + max_fds, nfds + nfds_t); + goto fail; + } + memcpy(vmsg->fds + nfds, fds_t, + nfds_t *sizeof(vmsg->fds[0])); + nfds += nfds_t; + g_free(fds_t); + } + if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { + break; + } + iov.iov_base = (char *)vmsg + read_bytes; + iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; + } while (true); + + vmsg->fd_num = nfds; + /* qio_channel_readv_full will make socket fds blocking, unblock them */ + vmsg_unblock_fds(vmsg); + if (vmsg->size > sizeof(vmsg->payload)) { + error_report("Error: too big message request: %d, " + "size: vmsg->size: %u, " + "while sizeof(vmsg->payload) = %zu", + vmsg->request, vmsg->size, sizeof(vmsg->payload)); + goto fail; + } + + struct iovec iov_payload = { + .iov_base = (char *)&vmsg->payload, + .iov_len = vmsg->size, + }; + if (vmsg->size) { + rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); + if (rc == -1) { + error_report_err(local_err); + goto fail; + } + } + + return true; + +fail: + vmsg_close_fds(vmsg); + + return false; +} + + +static void vu_client_start(VuServer *server); +static coroutine_fn void vu_client_trip(void *opaque) +{ + VuServer *server = opaque; + + while (!server->aio_context_changed && server->sioc) { + server->processing_msg = true; + vu_dispatch(&server->vu_dev); + server->processing_msg = false; + } + + if (server->aio_context_changed && server->sioc) { + server->aio_context_changed = false; + vu_client_start(server); + } +} + +static void vu_client_start(VuServer *server) +{ + server->co_trip = qemu_coroutine_create(vu_client_trip, server); + aio_co_enter(server->ctx, server->co_trip); +} + +/* + * a wrapper for vu_kick_cb + * + * since aio_dispatch can only pass one user data pointer to the + * callback function, pack VuDev and pvt into a struct. Then unpack it + * and pass them to vu_kick_cb + */ +static void kick_handler(void *opaque) +{ + VuFdWatch *vu_fd_watch = opaque; + vu_fd_watch->processing = true; + vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); + vu_fd_watch->processing = false; +} + + +static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) +{ + + VuFdWatch *vu_fd_watch, *next; + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (vu_fd_watch->fd == fd) { + return vu_fd_watch; + } + } + return NULL; +} + +static void +set_watch(VuDev *vu_dev, int fd, int vu_evt, + vu_watch_cb cb, void *pvt) +{ + + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + g_assert(vu_dev); + g_assert(fd >= 0); + g_assert(cb); + + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); + + if (!vu_fd_watch) { + VuFdWatch *vu_fd_watch = g_new0(VuFdWatch, 1); + + QTAILQ_INSERT_TAIL(&server->vu_fd_watches, vu_fd_watch, next); + + vu_fd_watch->fd = fd; + vu_fd_watch->cb = cb; + qemu_set_nonblock(fd); + aio_set_fd_handler(server->ioc->ctx, fd, true, kick_handler, + NULL, NULL, vu_fd_watch); + vu_fd_watch->vu_dev = vu_dev; + vu_fd_watch->pvt = pvt; + } +} + + +static void remove_watch(VuDev *vu_dev, int fd) +{ + VuServer *server; + g_assert(vu_dev); + g_assert(fd >= 0); + + server = container_of(vu_dev, VuServer, vu_dev); + + VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd); + + if (!vu_fd_watch) { + return; + } + aio_set_fd_handler(server->ioc->ctx, fd, true, NULL, NULL, NULL, NULL); + + QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); + g_free(vu_fd_watch); +} + + +static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, + gpointer opaque) +{ + VuServer *server = opaque; + + if (server->sioc) { + warn_report("Only one vhost-user client is allowed to " + "connect the server one time"); + return; + } + + if (!vu_init(&server->vu_dev, server->max_queues, sioc->fd, panic_cb, + vu_message_read, set_watch, remove_watch, server->vu_iface)) { + error_report("Failed to initialize libvhost-user"); + return; + } + + /* + * Unset the callback function for network listener to make another + * vhost-user client keeping waiting until this client disconnects + */ + qio_net_listener_set_client_func(server->listener, + NULL, + NULL, + NULL); + server->sioc = sioc; + /* + * Increase the object reference, so sioc will not freed by + * qio_net_listener_channel_func which will call object_unref(OBJECT(sioc)) + */ + object_ref(OBJECT(server->sioc)); + qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); + server->ioc = QIO_CHANNEL(sioc); + object_ref(OBJECT(server->ioc)); + qio_channel_attach_aio_context(server->ioc, server->ctx); + qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); + vu_client_start(server); +} + + +void vhost_user_server_stop(VuServer *server) +{ + if (server->sioc) { + close_client(server); + } + + if (server->listener) { + qio_net_listener_disconnect(server->listener); + object_unref(OBJECT(server->listener)); + } + +} + +void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) +{ + VuFdWatch *vu_fd_watch, *next; + void *opaque = NULL; + IOHandler *io_read = NULL; + bool attach; + + server->ctx = ctx ? ctx : qemu_get_aio_context(); + + if (!server->sioc) { + /* not yet serving any client*/ + return; + } + + if (ctx) { + qio_channel_attach_aio_context(server->ioc, ctx); + server->aio_context_changed = true; + io_read = kick_handler; + attach = true; + } else { + qio_channel_detach_aio_context(server->ioc); + /* server->ioc->ctx keeps the old AioConext */ + ctx = server->ioc->ctx; + attach = false; + } + + QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { + if (vu_fd_watch->cb) { + opaque = attach ? vu_fd_watch : NULL; + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, + io_read, NULL, NULL, + opaque); + } + } +} + + +bool vhost_user_server_start(VuServer *server, + SocketAddress *socket_addr, + AioContext *ctx, + uint16_t max_queues, + DevicePanicNotifierFn *device_panic_notifier, + const VuDevIface *vu_iface, + Error **errp) +{ + QIONetListener *listener = qio_net_listener_new(); + if (qio_net_listener_open_sync(listener, socket_addr, 1, + errp) < 0) { + object_unref(OBJECT(listener)); + return false; + } + + /* zero out unspecified fileds */ + *server = (VuServer) { + .listener = listener, + .vu_iface = vu_iface, + .max_queues = max_queues, + .ctx = ctx, + .device_panic_notifier = device_panic_notifier, + }; + + qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); + + qio_net_listener_set_client_func(server->listener, + vu_accept, + server, + NULL); + + QTAILQ_INIT(&server->vu_fd_watches); + return true; +} diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('main-loop.c')) util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) + util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) util_ss.add(files('thread-pool.c', 'qemu-timer.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Move the constants from hw/core/qdev-properties.c to util/block-helpers.h so that knowledge of the min/max values is Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Acked-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20200918080912.321299-5-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/block-helpers.h | 19 +++++++++++++ hw/core/qdev-properties-system.c | 31 ++++----------------- util/block-helpers.c | 46 ++++++++++++++++++++++++++++++++ util/meson.build | 1 + 4 files changed, 71 insertions(+), 26 deletions(-) create mode 100644 util/block-helpers.h create mode 100644 util/block-helpers.c diff --git a/util/block-helpers.h b/util/block-helpers.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/block-helpers.h @@ -XXX,XX +XXX,XX @@ +#ifndef BLOCK_HELPERS_H +#define BLOCK_HELPERS_H + +#include "qemu/units.h" + +/* lower limit is sector size */ +#define MIN_BLOCK_SIZE INT64_C(512) +#define MIN_BLOCK_SIZE_STR "512 B" +/* + * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and + * matches qcow2 cluster size limit + */ +#define MAX_BLOCK_SIZE (2 * MiB) +#define MAX_BLOCK_SIZE_STR "2 MiB" + +void check_block_size(const char *id, const char *name, int64_t value, + Error **errp); + +#endif /* BLOCK_HELPERS_H */ diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev-properties-system.c +++ b/hw/core/qdev-properties-system.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/blockdev.h" #include "net/net.h" #include "hw/pci/pci.h" +#include "util/block-helpers.h" static bool check_prop_still_unset(DeviceState *dev, const char *name, const void *old_val, const char *new_val, @@ -XXX,XX +XXX,XX @@ const PropertyInfo qdev_prop_losttickpolicy = { /* --- blocksize --- */ -/* lower limit is sector size */ -#define MIN_BLOCK_SIZE 512 -#define MIN_BLOCK_SIZE_STR "512 B" -/* - * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and - * matches qcow2 cluster size limit - */ -#define MAX_BLOCK_SIZE (2 * MiB) -#define MAX_BLOCK_SIZE_STR "2 MiB" - static void set_blocksize(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, Property *prop = opaque; uint32_t *ptr = qdev_get_prop_ptr(dev, prop); uint64_t value; + Error *local_err = NULL; if (dev->realized) { qdev_prop_set_after_realize(dev, name, errp); @@ -XXX,XX +XXX,XX @@ static void set_blocksize(Object *obj, Visitor *v, const char *name, if (!visit_type_size(v, name, &value, errp)) { return; } - /* value of 0 means "unset" */ - if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { - error_setg(errp, - "Property %s.%s doesn't take value %" PRIu64 - " (minimum: " MIN_BLOCK_SIZE_STR - ", maximum: " MAX_BLOCK_SIZE_STR ")", - dev->id ? : "", name, value); + check_block_size(dev->id ? : "", name, value, &local_err); + if (local_err) { + error_propagate(errp, local_err); return; } - - /* We rely on power-of-2 blocksizes for bitmasks */ - if ((value & (value - 1)) != 0) { - error_setg(errp, - "Property %s.%s doesn't take value '%" PRId64 "', " - "it's not a power of 2", dev->id ?: "", name, (int64_t)value); - return; - } - *ptr = value; } diff --git a/util/block-helpers.c b/util/block-helpers.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/block-helpers.c @@ -XXX,XX +XXX,XX @@ +/* + * Block utility functions + * + * Copyright IBM, Corp. 2011 + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qapi/qmp/qerror.h" +#include "block-helpers.h" + +/** + * check_block_size: + * @id: The unique ID of the object + * @name: The name of the property being validated + * @value: The block size in bytes + * @errp: A pointer to an area to store an error + * + * This function checks that the block size meets the following conditions: + * 1. At least MIN_BLOCK_SIZE + * 2. No larger than MAX_BLOCK_SIZE + * 3. A power of 2 + */ +void check_block_size(const char *id, const char *name, int64_t value, + Error **errp) +{ + /* value of 0 means "unset" */ + if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) { + error_setg(errp, QERR_PROPERTY_VALUE_OUT_OF_RANGE, + id, name, value, MIN_BLOCK_SIZE, MAX_BLOCK_SIZE); + return; + } + + /* We rely on power-of-2 blocksizes for bitmasks */ + if ((value & (value - 1)) != 0) { + error_setg(errp, + "Property %s.%s doesn't take value '%" PRId64 + "', it's not a power of 2", + id, name, value); + return; + } +} diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) + util_ss.add(files('block-helpers.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) util_ss.add(files('thread-pool.c', 'qemu-timer.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> By making use of libvhost-user, block device drive can be shared to the connected vhost-user client. Only one client can connect to the server one time. Since vhost-user-server needs a block drive to be created first, delay the creation of this object. Suggested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-6-coiby.xu@gmail.com [Shorten "vhost_user_blk_server" string to "vhost_user_blk" to avoid the following compiler warning: ../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=] --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.h | 36 ++ block/export/vhost-user-blk-server.c | 661 +++++++++++++++++++++++++++ softmmu/vl.c | 4 + block/meson.build | 1 + 4 files changed, 702 insertions(+) create mode 100644 block/export/vhost-user-blk-server.h create mode 100644 block/export/vhost-user-blk-server.c diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vhost-user-blk-server.h @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU block devices via vhost-user protocal + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ + +#ifndef VHOST_USER_BLK_SERVER_H +#define VHOST_USER_BLK_SERVER_H +#include "util/vhost-user-server.h" + +typedef struct VuBlockDev VuBlockDev; +#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" +#define VHOST_USER_BLK_SERVER(obj) \ + OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) + +/* vhost user block device */ +struct VuBlockDev { + Object parent_obj; + char *node_name; + SocketAddress *addr; + AioContext *ctx; + VuServer vu_server; + bool running; + uint32_t blk_size; + BlockBackend *backend; + QIOChannelSocket *sioc; + QTAILQ_ENTRY(VuBlockDev) next; + struct virtio_blk_config blkcfg; + bool writable; +}; + +#endif /* VHOST_USER_BLK_SERVER_H */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ +/* + * Sharing QEMU block devices via vhost-user protocal + * + * Parts of the code based on nbd/server.c. + * + * Copyright (c) Coiby Xu <coiby.xu@gmail.com>. + * Copyright (c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "block/block.h" +#include "vhost-user-blk-server.h" +#include "qapi/error.h" +#include "qom/object_interfaces.h" +#include "sysemu/block-backend.h" +#include "util/block-helpers.h" + +enum { + VHOST_USER_BLK_MAX_QUEUES = 1, +}; +struct virtio_blk_inhdr { + unsigned char status; +}; + +typedef struct VuBlockReq { + VuVirtqElement *elem; + int64_t sector_num; + size_t size; + struct virtio_blk_inhdr *in; + struct virtio_blk_outhdr out; + VuServer *server; + struct VuVirtq *vq; +} VuBlockReq; + +static void vu_block_req_complete(VuBlockReq *req) +{ + VuDev *vu_dev = &req->server->vu_dev; + + /* IO size with 1 extra status byte */ + vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); + vu_queue_notify(vu_dev, req->vq); + + if (req->elem) { + free(req->elem); + } + + g_free(req); +} + +static VuBlockDev *get_vu_block_device_by_server(VuServer *server) +{ + return container_of(server, VuBlockDev, vu_server); +} + +static int coroutine_fn +vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, + uint32_t iovcnt, uint32_t type) +{ + struct virtio_blk_discard_write_zeroes desc; + ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); + if (unlikely(size != sizeof(desc))) { + error_report("Invalid size %ld, expect %ld", size, sizeof(desc)); + return -EINVAL; + } + + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); + uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, + le32_to_cpu(desc.num_sectors) << 9 }; + if (type == VIRTIO_BLK_T_DISCARD) { + if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { + return 0; + } + } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { + if (blk_co_pwrite_zeroes(vdev_blk->backend, + range[0], range[1], 0) == 0) { + return 0; + } + } + + return -EINVAL; +} + +static void coroutine_fn vu_block_flush(VuBlockReq *req) +{ + VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); + BlockBackend *backend = vdev_blk->backend; + blk_co_flush(backend); +} + +struct req_data { + VuServer *server; + VuVirtq *vq; + VuVirtqElement *elem; +}; + +static void coroutine_fn vu_block_virtio_process_req(void *opaque) +{ + struct req_data *data = opaque; + VuServer *server = data->server; + VuVirtq *vq = data->vq; + VuVirtqElement *elem = data->elem; + uint32_t type; + VuBlockReq *req; + + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + BlockBackend *backend = vdev_blk->backend; + + struct iovec *in_iov = elem->in_sg; + struct iovec *out_iov = elem->out_sg; + unsigned in_num = elem->in_num; + unsigned out_num = elem->out_num; + /* refer to hw/block/virtio_blk.c */ + if (elem->out_num < 1 || elem->in_num < 1) { + error_report("virtio-blk request missing headers"); + free(elem); + return; + } + + req = g_new0(VuBlockReq, 1); + req->server = server; + req->vq = vq; + req->elem = elem; + + if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, + sizeof(req->out)) != sizeof(req->out))) { + error_report("virtio-blk request outhdr too short"); + goto err; + } + + iov_discard_front(&out_iov, &out_num, sizeof(req->out)); + + if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) { + error_report("virtio-blk request inhdr too short"); + goto err; + } + + /* We always touch the last byte, so just see how big in_iov is. */ + req->in = (void *)in_iov[in_num - 1].iov_base + + in_iov[in_num - 1].iov_len + - sizeof(struct virtio_blk_inhdr); + iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr)); + + type = le32_to_cpu(req->out.type); + switch (type & ~VIRTIO_BLK_T_BARRIER) { + case VIRTIO_BLK_T_IN: + case VIRTIO_BLK_T_OUT: { + ssize_t ret = 0; + bool is_write = type & VIRTIO_BLK_T_OUT; + req->sector_num = le64_to_cpu(req->out.sector); + + int64_t offset = req->sector_num * vdev_blk->blk_size; + QEMUIOVector qiov; + if (is_write) { + qemu_iovec_init_external(&qiov, out_iov, out_num); + ret = blk_co_pwritev(backend, offset, qiov.size, + &qiov, 0); + } else { + qemu_iovec_init_external(&qiov, in_iov, in_num); + ret = blk_co_preadv(backend, offset, qiov.size, + &qiov, 0); + } + if (ret >= 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } + break; + } + case VIRTIO_BLK_T_FLUSH: + vu_block_flush(req); + req->in->status = VIRTIO_BLK_S_OK; + break; + case VIRTIO_BLK_T_GET_ID: { + size_t size = MIN(iov_size(&elem->in_sg[0], in_num), + VIRTIO_BLK_ID_BYTES); + snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk"); + req->in->status = VIRTIO_BLK_S_OK; + req->size = elem->in_sg[0].iov_len; + break; + } + case VIRTIO_BLK_T_DISCARD: + case VIRTIO_BLK_T_WRITE_ZEROES: { + int rc; + rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], + out_num, type); + if (rc == 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } + break; + } + default: + req->in->status = VIRTIO_BLK_S_UNSUPP; + break; + } + + vu_block_req_complete(req); + return; + +err: + free(elem); + g_free(req); + return; +} + +static void vu_block_process_vq(VuDev *vu_dev, int idx) +{ + VuServer *server; + VuVirtq *vq; + struct req_data *req_data; + + server = container_of(vu_dev, VuServer, vu_dev); + assert(server); + + vq = vu_get_queue(vu_dev, idx); + assert(vq); + VuVirtqElement *elem; + while (1) { + elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + + sizeof(VuBlockReq)); + if (elem) { + req_data = g_new0(struct req_data, 1); + req_data->server = server; + req_data->vq = vq; + req_data->elem = elem; + Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, + req_data); + aio_co_enter(server->ioc->ctx, co); + } else { + break; + } + } +} + +static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) +{ + VuVirtq *vq; + + assert(vu_dev); + + vq = vu_get_queue(vu_dev, idx); + vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); +} + +static uint64_t vu_block_get_features(VuDev *dev) +{ + uint64_t features; + VuServer *server = container_of(dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + features = 1ull << VIRTIO_BLK_F_SIZE_MAX | + 1ull << VIRTIO_BLK_F_SEG_MAX | + 1ull << VIRTIO_BLK_F_TOPOLOGY | + 1ull << VIRTIO_BLK_F_BLK_SIZE | + 1ull << VIRTIO_BLK_F_FLUSH | + 1ull << VIRTIO_BLK_F_DISCARD | + 1ull << VIRTIO_BLK_F_WRITE_ZEROES | + 1ull << VIRTIO_BLK_F_CONFIG_WCE | + 1ull << VIRTIO_F_VERSION_1 | + 1ull << VIRTIO_RING_F_INDIRECT_DESC | + 1ull << VIRTIO_RING_F_EVENT_IDX | + 1ull << VHOST_USER_F_PROTOCOL_FEATURES; + + if (!vdev_blk->writable) { + features |= 1ull << VIRTIO_BLK_F_RO; + } + + return features; +} + +static uint64_t vu_block_get_protocol_features(VuDev *dev) +{ + return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | + 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; +} + +static int +vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + memcpy(config, &vdev_blk->blkcfg, len); + + return 0; +} + +static int +vu_block_set_config(VuDev *vu_dev, const uint8_t *data, + uint32_t offset, uint32_t size, uint32_t flags) +{ + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + uint8_t wce; + + /* don't support live migration */ + if (flags != VHOST_SET_CONFIG_TYPE_MASTER) { + return -EINVAL; + } + + if (offset != offsetof(struct virtio_blk_config, wce) || + size != 1) { + return -EINVAL; + } + + wce = *data; + vdev_blk->blkcfg.wce = wce; + blk_set_enable_write_cache(vdev_blk->backend, wce); + return 0; +} + +/* + * When the client disconnects, it sends a VHOST_USER_NONE request + * and vu_process_message will simple call exit which cause the VM + * to exit abruptly. + * To avoid this issue, process VHOST_USER_NONE request ahead + * of vu_process_message. + * + */ +static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) +{ + if (vmsg->request == VHOST_USER_NONE) { + dev->panic(dev, "disconnect"); + return true; + } + return false; +} + +static const VuDevIface vu_block_iface = { + .get_features = vu_block_get_features, + .queue_set_started = vu_block_queue_set_started, + .get_protocol_features = vu_block_get_protocol_features, + .get_config = vu_block_get_config, + .set_config = vu_block_set_config, + .process_msg = vu_block_process_msg, +}; + +static void blk_aio_attached(AioContext *ctx, void *opaque) +{ + VuBlockDev *vub_dev = opaque; + aio_context_acquire(ctx); + vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); + aio_context_release(ctx); +} + +static void blk_aio_detach(void *opaque) +{ + VuBlockDev *vub_dev = opaque; + AioContext *ctx = vub_dev->vu_server.ctx; + aio_context_acquire(ctx); + vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); + aio_context_release(ctx); +} + +static void +vu_block_initialize_config(BlockDriverState *bs, + struct virtio_blk_config *config, uint32_t blk_size) +{ + config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; + config->blk_size = blk_size; + config->size_max = 0; + config->seg_max = 128 - 2; + config->min_io_size = 1; + config->opt_io_size = 1; + config->num_queues = VHOST_USER_BLK_MAX_QUEUES; + config->max_discard_sectors = 32768; + config->max_discard_seg = 1; + config->discard_sector_alignment = config->blk_size >> 9; + config->max_write_zeroes_sectors = 32768; + config->max_write_zeroes_seg = 1; +} + +static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) +{ + + BlockBackend *blk; + Error *local_error = NULL; + const char *node_name = vu_block_device->node_name; + bool writable = vu_block_device->writable; + uint64_t perm = BLK_PERM_CONSISTENT_READ; + int ret; + + AioContext *ctx; + + BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); + + if (!bs) { + error_propagate(errp, local_error); + return NULL; + } + + if (bdrv_is_read_only(bs)) { + writable = false; + } + + if (writable) { + perm |= BLK_PERM_WRITE; + } + + ctx = bdrv_get_aio_context(bs); + aio_context_acquire(ctx); + bdrv_invalidate_cache(bs, NULL); + aio_context_release(ctx); + + /* + * Don't allow resize while the vhost user server is running, + * otherwise we don't care what happens with the node. + */ + blk = blk_new(bdrv_get_aio_context(bs), perm, + BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | + BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); + ret = blk_insert_bs(blk, bs, errp); + + if (ret < 0) { + goto fail; + } + + blk_set_enable_write_cache(blk, false); + + blk_set_allow_aio_context_change(blk, true); + + vu_block_device->blkcfg.wce = 0; + vu_block_device->backend = blk; + if (!vu_block_device->blk_size) { + vu_block_device->blk_size = BDRV_SECTOR_SIZE; + } + vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; + blk_set_guest_block_size(blk, vu_block_device->blk_size); + vu_block_initialize_config(bs, &vu_block_device->blkcfg, + vu_block_device->blk_size); + return vu_block_device; + +fail: + blk_unref(blk); + return NULL; +} + +static void vu_block_deinit(VuBlockDev *vu_block_device) +{ + if (vu_block_device->backend) { + blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, + blk_aio_detach, vu_block_device); + } + + blk_unref(vu_block_device->backend); +} + +static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) +{ + vhost_user_server_stop(&vu_block_device->vu_server); + vu_block_deinit(vu_block_device); +} + +static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, + Error **errp) +{ + AioContext *ctx; + SocketAddress *addr = vu_block_device->addr; + + if (!vu_block_init(vu_block_device, errp)) { + return; + } + + ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); + + if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, + VHOST_USER_BLK_MAX_QUEUES, + NULL, &vu_block_iface, + errp)) { + goto error; + } + + blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, + blk_aio_detach, vu_block_device); + vu_block_device->running = true; + return; + + error: + vu_block_deinit(vu_block_device); +} + +static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) +{ + if (vus->running) { + error_setg(errp, "The property can't be modified " + "while the server is running"); + return false; + } + return true; +} + +static void vu_set_node_name(Object *obj, const char *value, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + if (vus->node_name) { + g_free(vus->node_name); + } + + vus->node_name = g_strdup(value); +} + +static char *vu_get_node_name(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return g_strdup(vus->node_name); +} + +static void free_socket_addr(SocketAddress *addr) +{ + g_free(addr->u.q_unix.path); + g_free(addr); +} + +static void vu_set_unix_socket(Object *obj, const char *value, + Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + if (vus->addr) { + free_socket_addr(vus->addr); + } + + SocketAddress *addr = g_new0(SocketAddress, 1); + addr->type = SOCKET_ADDRESS_TYPE_UNIX; + addr->u.q_unix.path = g_strdup(value); + vus->addr = addr; +} + +static char *vu_get_unix_socket(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return g_strdup(vus->addr->u.q_unix.path); +} + +static bool vu_get_block_writable(Object *obj, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + return vus->writable; +} + +static void vu_set_block_writable(Object *obj, bool value, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + vus->writable = value; +} + +static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + uint32_t value = vus->blk_size; + + visit_type_uint32(v, name, &value, errp); +} + +static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); + + Error *local_err = NULL; + uint32_t value; + + if (!vu_prop_modifiable(vus, errp)) { + return; + } + + visit_type_uint32(v, name, &value, &local_err); + if (local_err) { + goto out; + } + + check_block_size(object_get_typename(obj), name, value, &local_err); + if (local_err) { + goto out; + } + + vus->blk_size = value; + +out: + error_propagate(errp, local_err); +} + +static void vhost_user_blk_server_instance_finalize(Object *obj) +{ + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); + + vhost_user_blk_server_stop(vub); + + /* + * Unlike object_property_add_str, object_class_property_add_str + * doesn't have a release method. Thus manual memory freeing is + * needed. + */ + free_socket_addr(vub->addr); + g_free(vub->node_name); +} + +static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) +{ + VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); + + vhost_user_blk_server_start(vub, errp); +} + +static void vhost_user_blk_server_class_init(ObjectClass *klass, + void *class_data) +{ + UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); + ucc->complete = vhost_user_blk_server_complete; + + object_class_property_add_bool(klass, "writable", + vu_get_block_writable, + vu_set_block_writable); + + object_class_property_add_str(klass, "node-name", + vu_get_node_name, + vu_set_node_name); + + object_class_property_add_str(klass, "unix-socket", + vu_get_unix_socket, + vu_set_unix_socket); + + object_class_property_add(klass, "logical-block-size", "uint32", + vu_get_blk_size, vu_set_blk_size, + NULL, NULL); +} + +static const TypeInfo vhost_user_blk_server_info = { + .name = TYPE_VHOST_USER_BLK_SERVER, + .parent = TYPE_OBJECT, + .instance_size = sizeof(VuBlockDev), + .instance_finalize = vhost_user_blk_server_instance_finalize, + .class_init = vhost_user_blk_server_class_init, + .interfaces = (InterfaceInfo[]) { + {TYPE_USER_CREATABLE}, + {} + }, +}; + +static void vhost_user_blk_server_register_types(void) +{ + type_register_static(&vhost_user_blk_server_info); +} + +type_init(vhost_user_blk_server_register_types) diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ static bool object_create_initial(const char *type, QemuOpts *opts) } #endif + /* Reason: vhost-user-blk-server property "node-name" */ + if (g_str_equal(type, "vhost-user-blk-server")) { + return false; + } /* * Reason: filter-* property "netdev" etc. */ diff --git a/block/meson.build b/block/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/meson.build +++ b/block/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) +block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> This test case has the same tests as tests/virtio-blk-test.c except for tests have block_resize. Since vhost-user server can only server one client one time, two instances of vhost-user-blk-server are started by qemu-storage-daemon for the hotplug test. In order to not block scripts/tap-driver.pl, vhost-user-blk-server will send "quit" command to qemu-storage-daemon's QMP monitor. So a function is added to libqtest.c to establish socket connection with socket server. Suggested-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-7-coiby.xu@gmail.com [Update meson.build to only test when CONFIG_TOOLS has built qemu-storage-daemon. This prevents CI failures with --disable-tools. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/libqos/libqtest.h | 17 + tests/qtest/libqos/vhost-user-blk.h | 48 ++ tests/qtest/libqos/vhost-user-blk.c | 129 +++++ tests/qtest/libqtest.c | 36 +- tests/qtest/vhost-user-blk-test.c | 751 ++++++++++++++++++++++++++++ tests/qtest/libqos/meson.build | 1 + tests/qtest/meson.build | 4 +- 7 files changed, 983 insertions(+), 3 deletions(-) create mode 100644 tests/qtest/libqos/vhost-user-blk.h create mode 100644 tests/qtest/libqos/vhost-user-blk.c create mode 100644 tests/qtest/vhost-user-blk-test.c diff --git a/tests/qtest/libqos/libqtest.h b/tests/qtest/libqos/libqtest.h index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/libqtest.h +++ b/tests/qtest/libqos/libqtest.h @@ -XXX,XX +XXX,XX @@ void qtest_qmp_send(QTestState *s, const char *fmt, ...) void qtest_qmp_send_raw(QTestState *s, const char *fmt, ...) GCC_FMT_ATTR(2, 3); +/** + * qtest_socket_client: + * @server_socket_path: the socket server's path + * + * Connect to a socket server. + */ +int qtest_socket_client(char *server_socket_path); + +/** + * qtest_create_state_with_qmp_fd: + * @fd: socket fd + * + * Wrap socket fd in QTestState to make use of qtest_qmp* + * functions + */ +QTestState *qtest_create_state_with_qmp_fd(int fd); + /** * qtest_vqmp_fds: * @s: #QTestState instance to operate on. diff --git a/tests/qtest/libqos/vhost-user-blk.h b/tests/qtest/libqos/vhost-user-blk.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/libqos/vhost-user-blk.h @@ -XXX,XX +XXX,XX @@ +/* + * libqos driver framework + * + * Based on tests/qtest/libqos/virtio-blk.c + * + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#ifndef TESTS_LIBQOS_VHOST_USER_BLK_H +#define TESTS_LIBQOS_VHOST_USER_BLK_H + +#include "qgraph.h" +#include "virtio.h" +#include "virtio-pci.h" + +typedef struct QVhostUserBlk QVhostUserBlk; +typedef struct QVhostUserBlkPCI QVhostUserBlkPCI; +typedef struct QVhostUserBlkDevice QVhostUserBlkDevice; + +struct QVhostUserBlk { + QVirtioDevice *vdev; +}; + +struct QVhostUserBlkPCI { + QVirtioPCIDevice pci_vdev; + QVhostUserBlk blk; +}; + +struct QVhostUserBlkDevice { + QOSGraphObject obj; + QVhostUserBlk blk; +}; + +#endif diff --git a/tests/qtest/libqos/vhost-user-blk.c b/tests/qtest/libqos/vhost-user-blk.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/libqos/vhost-user-blk.c @@ -XXX,XX +XXX,XX @@ +/* + * libqos driver framework + * + * Based on tests/qtest/libqos/virtio-blk.c + * + * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com> + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2.1 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#include "qemu/osdep.h" +#include "libqtest.h" +#include "qemu/module.h" +#include "standard-headers/linux/virtio_blk.h" +#include "vhost-user-blk.h" + +#define PCI_SLOT 0x04 +#define PCI_FN 0x00 + +/* virtio-blk-device */ +static void *qvhost_user_blk_get_driver(QVhostUserBlk *v_blk, + const char *interface) +{ + if (!g_strcmp0(interface, "vhost-user-blk")) { + return v_blk; + } + if (!g_strcmp0(interface, "virtio")) { + return v_blk->vdev; + } + + fprintf(stderr, "%s not present in vhost-user-blk-device\n", interface); + g_assert_not_reached(); +} + +static void *qvhost_user_blk_device_get_driver(void *object, + const char *interface) +{ + QVhostUserBlkDevice *v_blk = object; + return qvhost_user_blk_get_driver(&v_blk->blk, interface); +} + +static void *vhost_user_blk_device_create(void *virtio_dev, + QGuestAllocator *t_alloc, + void *addr) +{ + QVhostUserBlkDevice *vhost_user_blk = g_new0(QVhostUserBlkDevice, 1); + QVhostUserBlk *interface = &vhost_user_blk->blk; + + interface->vdev = virtio_dev; + + vhost_user_blk->obj.get_driver = qvhost_user_blk_device_get_driver; + + return &vhost_user_blk->obj; +} + +/* virtio-blk-pci */ +static void *qvhost_user_blk_pci_get_driver(void *object, const char *interface) +{ + QVhostUserBlkPCI *v_blk = object; + if (!g_strcmp0(interface, "pci-device")) { + return v_blk->pci_vdev.pdev; + } + return qvhost_user_blk_get_driver(&v_blk->blk, interface); +} + +static void *vhost_user_blk_pci_create(void *pci_bus, QGuestAllocator *t_alloc, + void *addr) +{ + QVhostUserBlkPCI *vhost_user_blk = g_new0(QVhostUserBlkPCI, 1); + QVhostUserBlk *interface = &vhost_user_blk->blk; + QOSGraphObject *obj = &vhost_user_blk->pci_vdev.obj; + + virtio_pci_init(&vhost_user_blk->pci_vdev, pci_bus, addr); + interface->vdev = &vhost_user_blk->pci_vdev.vdev; + + g_assert_cmphex(interface->vdev->device_type, ==, VIRTIO_ID_BLOCK); + + obj->get_driver = qvhost_user_blk_pci_get_driver; + + return obj; +} + +static void vhost_user_blk_register_nodes(void) +{ + /* + * FIXME: every test using these two nodes needs to setup a + * -drive,id=drive0 otherwise QEMU is not going to start. + * Therefore, we do not include "produces" edge for virtio + * and pci-device yet. + */ + + char *arg = g_strdup_printf("id=drv0,chardev=char1,addr=%x.%x", + PCI_SLOT, PCI_FN); + + QPCIAddress addr = { + .devfn = QPCI_DEVFN(PCI_SLOT, PCI_FN), + }; + + QOSGraphEdgeOptions opts = { }; + + /* virtio-blk-device */ + /** opts.extra_device_opts = "drive=drive0"; */ + qos_node_create_driver("vhost-user-blk-device", vhost_user_blk_device_create); + qos_node_consumes("vhost-user-blk-device", "virtio-bus", &opts); + qos_node_produces("vhost-user-blk-device", "vhost-user-blk"); + + /* virtio-blk-pci */ + opts.extra_device_opts = arg; + add_qpci_address(&opts, &addr); + qos_node_create_driver("vhost-user-blk-pci", vhost_user_blk_pci_create); + qos_node_consumes("vhost-user-blk-pci", "pci-bus", &opts); + qos_node_produces("vhost-user-blk-pci", "vhost-user-blk"); + + g_free(arg); +} + +libqos_init(vhost_user_blk_register_nodes); diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqtest.c +++ b/tests/qtest/libqtest.c @@ -XXX,XX +XXX,XX @@ * Copyright IBM, Corp. 2012 * Copyright Red Hat, Inc. 2012 * Copyright SUSE LINUX Products GmbH 2013 + * Copyright Copyright (c) Coiby Xu * * Authors: * Anthony Liguori <aliguori@us.ibm.com> * Paolo Bonzini <pbonzini@redhat.com> * Andreas Färber <afaerber@suse.de> + * Coiby Xu <coiby.xu@gmail.com> * * This work is licensed under the terms of the GNU GPL, version 2 or later. * See the COPYING file in the top-level directory. @@ -XXX,XX +XXX,XX @@ typedef struct QTestClientTransportOps { QTestRecvFn recv_line; /* for receiving qtest command responses */ } QTestTransportOps; -struct QTestState -{ +struct QTestState { int fd; int qmp_fd; pid_t qemu_pid; /* our child QEMU process */ @@ -XXX,XX +XXX,XX @@ QDict *qtest_qmp_receive(QTestState *s) return qmp_fd_receive(s->qmp_fd); } +QTestState *qtest_create_state_with_qmp_fd(int fd) +{ + QTestState *qmp_test_state = g_new0(QTestState, 1); + qmp_test_state->qmp_fd = fd; + return qmp_test_state; +} + +int qtest_socket_client(char *server_socket_path) +{ + struct sockaddr_un serv_addr; + int sock; + int ret; + int retries = 0; + sock = socket(PF_UNIX, SOCK_STREAM, 0); + g_assert_cmpint(sock, !=, -1); + serv_addr.sun_family = AF_UNIX; + snprintf(serv_addr.sun_path, sizeof(serv_addr.sun_path), "%s", + server_socket_path); + + for (retries = 0; retries < 3; retries++) { + ret = connect(sock, (struct sockaddr *)&serv_addr, sizeof(serv_addr)); + if (ret == 0) { + break; + } + g_usleep(G_USEC_PER_SEC); + } + + g_assert_cmpint(ret, ==, 0); + return sock; +} + /** * Allow users to send a message without waiting for the reply, * in the case that they choose to discard all replies up until diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/vhost-user-blk-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTest testcase for Vhost-user Block Device + * + * Based on tests/qtest//virtio-blk-test.c + + * Copyright (c) 2014 SUSE LINUX Products GmbH + * Copyright (c) 2014 Marc Marí + * Copyright (c) 2020 Coiby Xu + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "libqtest-single.h" +#include "qemu/bswap.h" +#include "qemu/module.h" +#include "standard-headers/linux/virtio_blk.h" +#include "standard-headers/linux/virtio_pci.h" +#include "libqos/qgraph.h" +#include "libqos/vhost-user-blk.h" +#include "libqos/libqos-pc.h" + +#define TEST_IMAGE_SIZE (64 * 1024 * 1024) +#define QVIRTIO_BLK_TIMEOUT_US (30 * 1000 * 1000) +#define PCI_SLOT_HP 0x06 + +typedef struct QVirtioBlkReq { + uint32_t type; + uint32_t ioprio; + uint64_t sector; + char *data; + uint8_t status; +} QVirtioBlkReq; + +#ifdef HOST_WORDS_BIGENDIAN +static const bool host_is_big_endian = true; +#else +static const bool host_is_big_endian; /* false */ +#endif + +static inline void virtio_blk_fix_request(QVirtioDevice *d, QVirtioBlkReq *req) +{ + if (qvirtio_is_big_endian(d) != host_is_big_endian) { + req->type = bswap32(req->type); + req->ioprio = bswap32(req->ioprio); + req->sector = bswap64(req->sector); + } +} + +static inline void virtio_blk_fix_dwz_hdr(QVirtioDevice *d, + struct virtio_blk_discard_write_zeroes *dwz_hdr) +{ + if (qvirtio_is_big_endian(d) != host_is_big_endian) { + dwz_hdr->sector = bswap64(dwz_hdr->sector); + dwz_hdr->num_sectors = bswap32(dwz_hdr->num_sectors); + dwz_hdr->flags = bswap32(dwz_hdr->flags); + } +} + +static uint64_t virtio_blk_request(QGuestAllocator *alloc, QVirtioDevice *d, + QVirtioBlkReq *req, uint64_t data_size) +{ + uint64_t addr; + uint8_t status = 0xFF; + QTestState *qts = global_qtest; + + switch (req->type) { + case VIRTIO_BLK_T_IN: + case VIRTIO_BLK_T_OUT: + g_assert_cmpuint(data_size % 512, ==, 0); + break; + case VIRTIO_BLK_T_DISCARD: + case VIRTIO_BLK_T_WRITE_ZEROES: + g_assert_cmpuint(data_size % + sizeof(struct virtio_blk_discard_write_zeroes), ==, 0); + break; + default: + g_assert_cmpuint(data_size, ==, 0); + } + + addr = guest_alloc(alloc, sizeof(*req) + data_size); + + virtio_blk_fix_request(d, req); + + qtest_memwrite(qts, addr, req, 16); + qtest_memwrite(qts, addr + 16, req->data, data_size); + qtest_memwrite(qts, addr + 16 + data_size, &status, sizeof(status)); + + return addr; +} + +/* Returns the request virtqueue so the caller can perform further tests */ +static QVirtQueue *test_basic(QVirtioDevice *dev, QGuestAllocator *alloc) +{ + QVirtioBlkReq req; + uint64_t req_addr; + uint64_t capacity; + uint64_t features; + uint32_t free_head; + uint8_t status; + char *data; + QTestState *qts = global_qtest; + QVirtQueue *vq; + + features = qvirtio_get_features(dev); + features = features & ~(QVIRTIO_F_BAD_FEATURE | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | + (1u << VIRTIO_RING_F_EVENT_IDX) | + (1u << VIRTIO_BLK_F_SCSI)); + qvirtio_set_features(dev, features); + + capacity = qvirtio_config_readq(dev, 0); + g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512); + + vq = qvirtqueue_setup(dev, alloc, 0); + + qvirtio_set_driver_ok(dev); + + /* Write and read with 3 descriptor layout */ + /* Write request */ + req.type = VIRTIO_BLK_T_OUT; + req.ioprio = 1; + req.sector = 0; + req.data = g_malloc0(512); + strcpy(req.data, "TEST"); + + req_addr = virtio_blk_request(alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true); + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); + + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + guest_free(alloc, req_addr); + + /* Read request */ + req.type = VIRTIO_BLK_T_IN; + req.ioprio = 1; + req.sector = 0; + req.data = g_malloc0(512); + + req_addr = virtio_blk_request(alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true); + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); + + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + data = g_malloc0(512); + qtest_memread(qts, req_addr + 16, data, 512); + g_assert_cmpstr(data, ==, "TEST"); + g_free(data); + + guest_free(alloc, req_addr); + + if (features & (1u << VIRTIO_BLK_F_WRITE_ZEROES)) { + struct virtio_blk_discard_write_zeroes dwz_hdr; + void *expected; + + /* + * WRITE_ZEROES request on the same sector of previous test where + * we wrote "TEST". + */ + req.type = VIRTIO_BLK_T_WRITE_ZEROES; + req.data = (char *) &dwz_hdr; + dwz_hdr.sector = 0; + dwz_hdr.num_sectors = 1; + dwz_hdr.flags = 0; + + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); + + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true); + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), 1, true, + false); + + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 16 + sizeof(dwz_hdr)); + g_assert_cmpint(status, ==, 0); + + guest_free(alloc, req_addr); + + /* Read request to check if the sector contains all zeroes */ + req.type = VIRTIO_BLK_T_IN; + req.ioprio = 1; + req.sector = 0; + req.data = g_malloc0(512); + + req_addr = virtio_blk_request(alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true); + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); + + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + data = g_malloc(512); + expected = g_malloc0(512); + qtest_memread(qts, req_addr + 16, data, 512); + g_assert_cmpmem(data, 512, expected, 512); + g_free(expected); + g_free(data); + + guest_free(alloc, req_addr); + } + + if (features & (1u << VIRTIO_BLK_F_DISCARD)) { + struct virtio_blk_discard_write_zeroes dwz_hdr; + + req.type = VIRTIO_BLK_T_DISCARD; + req.data = (char *) &dwz_hdr; + dwz_hdr.sector = 0; + dwz_hdr.num_sectors = 1; + dwz_hdr.flags = 0; + + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); + + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true); + qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), + 1, true, false); + + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 16 + sizeof(dwz_hdr)); + g_assert_cmpint(status, ==, 0); + + guest_free(alloc, req_addr); + } + + if (features & (1u << VIRTIO_F_ANY_LAYOUT)) { + /* Write and read with 2 descriptor layout */ + /* Write request */ + req.type = VIRTIO_BLK_T_OUT; + req.ioprio = 1; + req.sector = 1; + req.data = g_malloc0(512); + strcpy(req.data, "TEST"); + + req_addr = virtio_blk_request(alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(qts, vq, req_addr, 528, false, true); + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + guest_free(alloc, req_addr); + + /* Read request */ + req.type = VIRTIO_BLK_T_IN; + req.ioprio = 1; + req.sector = 1; + req.data = g_malloc0(512); + + req_addr = virtio_blk_request(alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, 513, true, false); + + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + data = g_malloc0(512); + qtest_memread(qts, req_addr + 16, data, 512); + g_assert_cmpstr(data, ==, "TEST"); + g_free(data); + + guest_free(alloc, req_addr); + } + + return vq; +} + +static void basic(void *obj, void *data, QGuestAllocator *t_alloc) +{ + QVhostUserBlk *blk_if = obj; + QVirtQueue *vq; + + vq = test_basic(blk_if->vdev, t_alloc); + qvirtqueue_cleanup(blk_if->vdev->bus, vq, t_alloc); + +} + +static void indirect(void *obj, void *u_data, QGuestAllocator *t_alloc) +{ + QVirtQueue *vq; + QVhostUserBlk *blk_if = obj; + QVirtioDevice *dev = blk_if->vdev; + QVirtioBlkReq req; + QVRingIndirectDesc *indirect; + uint64_t req_addr; + uint64_t capacity; + uint64_t features; + uint32_t free_head; + uint8_t status; + char *data; + QTestState *qts = global_qtest; + + features = qvirtio_get_features(dev); + g_assert_cmphex(features & (1u << VIRTIO_RING_F_INDIRECT_DESC), !=, 0); + features = features & ~(QVIRTIO_F_BAD_FEATURE | + (1u << VIRTIO_RING_F_EVENT_IDX) | + (1u << VIRTIO_BLK_F_SCSI)); + qvirtio_set_features(dev, features); + + capacity = qvirtio_config_readq(dev, 0); + g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512); + + vq = qvirtqueue_setup(dev, t_alloc, 0); + qvirtio_set_driver_ok(dev); + + /* Write request */ + req.type = VIRTIO_BLK_T_OUT; + req.ioprio = 1; + req.sector = 0; + req.data = g_malloc0(512); + strcpy(req.data, "TEST"); + + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); + + g_free(req.data); + + indirect = qvring_indirect_desc_setup(qts, dev, t_alloc, 2); + qvring_indirect_desc_add(dev, qts, indirect, req_addr, 528, false); + qvring_indirect_desc_add(dev, qts, indirect, req_addr + 528, 1, true); + free_head = qvirtqueue_add_indirect(qts, vq, indirect); + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + g_free(indirect); + guest_free(t_alloc, req_addr); + + /* Read request */ + req.type = VIRTIO_BLK_T_IN; + req.ioprio = 1; + req.sector = 0; + req.data = g_malloc0(512); + strcpy(req.data, "TEST"); + + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); + + g_free(req.data); + + indirect = qvring_indirect_desc_setup(qts, dev, t_alloc, 2); + qvring_indirect_desc_add(dev, qts, indirect, req_addr, 16, false); + qvring_indirect_desc_add(dev, qts, indirect, req_addr + 16, 513, true); + free_head = qvirtqueue_add_indirect(qts, vq, indirect); + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + data = g_malloc0(512); + qtest_memread(qts, req_addr + 16, data, 512); + g_assert_cmpstr(data, ==, "TEST"); + g_free(data); + + g_free(indirect); + guest_free(t_alloc, req_addr); + qvirtqueue_cleanup(dev->bus, vq, t_alloc); +} + +static void idx(void *obj, void *u_data, QGuestAllocator *t_alloc) +{ + QVirtQueue *vq; + QVhostUserBlkPCI *blk = obj; + QVirtioPCIDevice *pdev = &blk->pci_vdev; + QVirtioDevice *dev = &pdev->vdev; + QVirtioBlkReq req; + uint64_t req_addr; + uint64_t capacity; + uint64_t features; + uint32_t free_head; + uint32_t write_head; + uint32_t desc_idx; + uint8_t status; + char *data; + QOSGraphObject *blk_object = obj; + QPCIDevice *pci_dev = blk_object->get_driver(blk_object, "pci-device"); + QTestState *qts = global_qtest; + + if (qpci_check_buggy_msi(pci_dev)) { + return; + } + + qpci_msix_enable(pdev->pdev); + qvirtio_pci_set_msix_configuration_vector(pdev, t_alloc, 0); + + features = qvirtio_get_features(dev); + features = features & ~(QVIRTIO_F_BAD_FEATURE | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | + (1u << VIRTIO_F_NOTIFY_ON_EMPTY) | + (1u << VIRTIO_BLK_F_SCSI)); + qvirtio_set_features(dev, features); + + capacity = qvirtio_config_readq(dev, 0); + g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512); + + vq = qvirtqueue_setup(dev, t_alloc, 0); + qvirtqueue_pci_msix_setup(pdev, (QVirtQueuePCI *)vq, t_alloc, 1); + + qvirtio_set_driver_ok(dev); + + /* Write request */ + req.type = VIRTIO_BLK_T_OUT; + req.ioprio = 1; + req.sector = 0; + req.data = g_malloc0(512); + strcpy(req.data, "TEST"); + + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true); + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); + qvirtqueue_kick(qts, dev, vq, free_head); + + qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + + /* Write request */ + req.type = VIRTIO_BLK_T_OUT; + req.ioprio = 1; + req.sector = 1; + req.data = g_malloc0(512); + strcpy(req.data, "TEST"); + + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); + + g_free(req.data); + + /* Notify after processing the third request */ + qvirtqueue_set_used_event(qts, vq, 2); + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true); + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); + qvirtqueue_kick(qts, dev, vq, free_head); + write_head = free_head; + + /* No notification expected */ + status = qvirtio_wait_status_byte_no_isr(qts, dev, + vq, req_addr + 528, + QVIRTIO_BLK_TIMEOUT_US); + g_assert_cmpint(status, ==, 0); + + guest_free(t_alloc, req_addr); + + /* Read request */ + req.type = VIRTIO_BLK_T_IN; + req.ioprio = 1; + req.sector = 1; + req.data = g_malloc0(512); + + req_addr = virtio_blk_request(t_alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true); + qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true); + qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false); + + qvirtqueue_kick(qts, dev, vq, free_head); + + /* We get just one notification for both requests */ + qvirtio_wait_used_elem(qts, dev, vq, write_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + g_assert(qvirtqueue_get_buf(qts, vq, &desc_idx, NULL)); + g_assert_cmpint(desc_idx, ==, free_head); + + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + data = g_malloc0(512); + qtest_memread(qts, req_addr + 16, data, 512); + g_assert_cmpstr(data, ==, "TEST"); + g_free(data); + + guest_free(t_alloc, req_addr); + + /* End test */ + qpci_msix_disable(pdev->pdev); + + qvirtqueue_cleanup(dev->bus, vq, t_alloc); +} + +static void pci_hotplug(void *obj, void *data, QGuestAllocator *t_alloc) +{ + QVirtioPCIDevice *dev1 = obj; + QVirtioPCIDevice *dev; + QTestState *qts = dev1->pdev->bus->qts; + + /* plug secondary disk */ + qtest_qmp_device_add(qts, "vhost-user-blk-pci", "drv1", + "{'addr': %s, 'chardev': 'char2'}", + stringify(PCI_SLOT_HP) ".0"); + + dev = virtio_pci_new(dev1->pdev->bus, + &(QPCIAddress) { .devfn = QPCI_DEVFN(PCI_SLOT_HP, 0) + }); + g_assert_nonnull(dev); + g_assert_cmpint(dev->vdev.device_type, ==, VIRTIO_ID_BLOCK); + qvirtio_pci_device_disable(dev); + qos_object_destroy((QOSGraphObject *)dev); + + /* unplug secondary disk */ + qpci_unplug_acpi_device_test(qts, "drv1", PCI_SLOT_HP); +} + +/* + * Check that setting the vring addr on a non-existent virtqueue does + * not crash. + */ +static void test_nonexistent_virtqueue(void *obj, void *data, + QGuestAllocator *t_alloc) +{ + QVhostUserBlkPCI *blk = obj; + QVirtioPCIDevice *pdev = &blk->pci_vdev; + QPCIBar bar0; + QPCIDevice *dev; + + dev = qpci_device_find(pdev->pdev->bus, QPCI_DEVFN(4, 0)); + g_assert(dev != NULL); + qpci_device_enable(dev); + + bar0 = qpci_iomap(dev, 0, NULL); + + qpci_io_writeb(dev, bar0, VIRTIO_PCI_QUEUE_SEL, 2); + qpci_io_writel(dev, bar0, VIRTIO_PCI_QUEUE_PFN, 1); + + g_free(dev); +} + +static const char *qtest_qemu_storage_daemon_binary(void) +{ + const char *qemu_storage_daemon_bin; + + qemu_storage_daemon_bin = getenv("QTEST_QEMU_STORAGE_DAEMON_BINARY"); + if (!qemu_storage_daemon_bin) { + fprintf(stderr, "Environment variable " + "QTEST_QEMU_STORAGE_DAEMON_BINARY required\n"); + exit(0); + } + + return qemu_storage_daemon_bin; +} + +static void drive_destroy(void *path) +{ + unlink(path); + g_free(path); + qos_invalidate_command_line(); +} + +static char *drive_create(void) +{ + int fd, ret; + /** vhost-user-blk won't recognize drive located in /tmp */ + char *t_path = g_strdup("qtest.XXXXXX"); + + /** Create a temporary raw image */ + fd = mkstemp(t_path); + g_assert_cmpint(fd, >=, 0); + ret = ftruncate(fd, TEST_IMAGE_SIZE); + g_assert_cmpint(ret, ==, 0); + close(fd); + + g_test_queue_destroy(drive_destroy, t_path); + return t_path; +} + +static char sock_path_tempate[] = "/tmp/qtest.vhost_user_blk.XXXXXX"; +static char qmp_sock_path_tempate[] = "/tmp/qtest.vhost_user_blk.qmp.XXXXXX"; + +static void quit_storage_daemon(void *qmp_test_state) +{ + const char quit_str[] = "{ 'execute': 'quit' }"; + + /* Before quiting storate-daemon, quit qemu to avoid dubious messages */ + qobject_unref(qtest_qmp(global_qtest, quit_str)); + + /* + * Give storage-daemon enough time to wake up&terminate + * vu_client_trip coroutine so the Coroutine object could + * be cleaned up. Otherwise LeakSanitizer would complain + * about memory leaks. + */ + g_usleep(1000); + + qobject_unref(qtest_qmp((QTestState *)qmp_test_state, quit_str)); + g_free(qmp_test_state); +} + +static char *start_vhost_user_blk(GString *cmd_line, int vus_instances) +{ + const char *vhost_user_blk_bin = qtest_qemu_storage_daemon_binary(); + int fd, qmp_fd, i; + QTestState *qmp_test_state; + gchar *img_path; + char *sock_path = NULL; + char *qmp_sock_path = g_strdup(qmp_sock_path_tempate); + GString *storage_daemon_command = g_string_new(NULL); + + qmp_fd = mkstemp(qmp_sock_path); + g_assert_cmpint(qmp_fd, >=, 0); + g_test_queue_destroy(drive_destroy, qmp_sock_path); + + g_string_append_printf(storage_daemon_command, + "exec %s " + "--chardev socket,id=qmp,path=%s,server,nowait --monitor chardev=qmp ", + vhost_user_blk_bin, qmp_sock_path); + + g_string_append_printf(cmd_line, + " -object memory-backend-memfd,id=mem,size=128M,share=on -numa node,memdev=mem "); + + for (i = 0; i < vus_instances; i++) { + sock_path = g_strdup(sock_path_tempate); + fd = mkstemp(sock_path); + g_assert_cmpint(fd, >=, 0); + g_test_queue_destroy(drive_destroy, sock_path); + /* create image file */ + img_path = drive_create(); + g_string_append_printf(storage_daemon_command, + "--blockdev driver=file,node-name=disk%d,filename=%s " + "--object vhost-user-blk-server,id=disk%d,unix-socket=%s," + "node-name=disk%i,writable=on ", + i, img_path, i, sock_path, i); + + g_string_append_printf(cmd_line, "-chardev socket,id=char%d,path=%s ", + i + 1, sock_path); + } + + g_test_message("starting vhost-user backend: %s", + storage_daemon_command->str); + pid_t pid = fork(); + if (pid == 0) { + execlp("/bin/sh", "sh", "-c", storage_daemon_command->str, NULL); + exit(1); + } + g_string_free(storage_daemon_command, true); + + qmp_test_state = qtest_create_state_with_qmp_fd( + qtest_socket_client(qmp_sock_path)); + /* + * Ask qemu-storage-daemon to quit so it + * will not block scripts/tap-driver.pl. + */ + g_test_queue_destroy(quit_storage_daemon, qmp_test_state); + + qobject_unref(qtest_qmp(qmp_test_state, "{'execute': 'qmp_capabilities'}")); + return sock_path; +} + +static void *vhost_user_blk_test_setup(GString *cmd_line, void *arg) +{ + start_vhost_user_blk(cmd_line, 1); + return arg; +} + +/* + * Setup for hotplug. + * + * Since vhost-user server only serves one vhost-user client one time, + * another exprot + * + */ +static void *vhost_user_blk_hotplug_test_setup(GString *cmd_line, void *arg) +{ + /* "-chardev socket,id=char2" is used for pci_hotplug*/ + start_vhost_user_blk(cmd_line, 2); + return arg; +} + +static void register_vhost_user_blk_test(void) +{ + QOSGraphTestOptions opts = { + .before = vhost_user_blk_test_setup, + }; + + /* + * tests for vhost-user-blk and vhost-user-blk-pci + * The tests are borrowed from tests/virtio-blk-test.c. But some tests + * regarding block_resize don't work for vhost-user-blk. + * vhost-user-blk device doesn't have -drive, so tests containing + * block_resize are also abandoned, + * - config + * - resize + */ + qos_add_test("basic", "vhost-user-blk", basic, &opts); + qos_add_test("indirect", "vhost-user-blk", indirect, &opts); + qos_add_test("idx", "vhost-user-blk-pci", idx, &opts); + qos_add_test("nxvirtq", "vhost-user-blk-pci", + test_nonexistent_virtqueue, &opts); + + opts.before = vhost_user_blk_hotplug_test_setup; + qos_add_test("hotplug", "vhost-user-blk-pci", pci_hotplug, &opts); +} + +libqos_init(register_vhost_user_blk_test); diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/meson.build +++ b/tests/qtest/libqos/meson.build @@ -XXX,XX +XXX,XX @@ libqos_srcs = files('../libqtest.c', 'virtio-9p.c', 'virtio-balloon.c', 'virtio-blk.c', + 'vhost-user-blk.c', 'virtio-mmio.c', 'virtio-net.c', 'virtio-pci.c', diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qos_test_ss.add( ) qos_test_ss.add(when: 'CONFIG_VIRTFS', if_true: files('virtio-9p-test.c')) qos_test_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-test.c')) +qos_test_ss.add(when: ['CONFIG_LINUX', 'CONFIG_TOOLS'], if_true: files('vhost-user-blk-test.c')) extra_qtest_deps = { 'bios-tables-test': [io], @@ -XXX,XX +XXX,XX @@ foreach dir : target_dirs endif qtest_env.set('G_TEST_DBUS_DAEMON', meson.source_root() / 'tests/dbus-vmstate-daemon.sh') qtest_env.set('QTEST_QEMU_BINARY', './qemu-system-' + target_base) - + qtest_env.set('QTEST_QEMU_STORAGE_DAEMON_BINARY', './storage-daemon/qemu-storage-daemon') + foreach test : qtests # Executables are shared across targets, declare them only the first time we # encounter them -- 2.26.2 From: Coiby Xu <coiby.xu@gmail.com> Suggested-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-id: 20200918080912.321299-8-coiby.xu@gmail.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-block@nongnu.org S: Supported F: tests/image-fuzzer/ +Vhost-user block device backend server +M: Coiby Xu <Coiby.Xu@gmail.com> +S: Maintained +F: block/export/vhost-user-blk-server.c +F: util/vhost-user-server.c +F: tests/qtest/vhost-user-blk-test.c +F: tests/qtest/libqos/vhost-user-blk.c + Replication M: Wen Congyang <wencongyang2@huawei.com> M: Xie Changlong <xiechanglong.d@gmail.com> -- 2.26.2 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, return false; } - /* zero out unspecified fileds */ + /* zero out unspecified fields */ *server = (VuServer) { .listener = listener, .vu_iface = vu_iface, -- 2.26.2 We already have access to the value with the correct type (ioc and sioc are the same QIOChannel). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-4-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, server->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(server->ioc)); qio_channel_attach_aio_context(server->ioc, server->ctx); - qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL); + qio_channel_set_blocking(server->ioc, false, NULL); vu_client_start(server); } -- 2.26.2 Explicitly deleting watches is not necessary since libvhost-user calls remove_watch() during vu_deinit(). Add an assertion to check this though. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-5-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) /* When this is set vu_client_trip will stop new processing vhost-user message */ server->sioc = NULL; - VuFdWatch *vu_fd_watch, *next; - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL, - NULL, NULL, NULL); - } - - while (!QTAILQ_EMPTY(&server->vu_fd_watches)) { - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - if (!vu_fd_watch->processing) { - QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next); - g_free(vu_fd_watch); - } - } - } - while (server->processing_msg) { if (server->ioc->read_coroutine) { server->ioc->read_coroutine = NULL; @@ -XXX,XX +XXX,XX @@ static void close_client(VuServer *server) } vu_deinit(&server->vu_dev); + + /* vu_deinit() should have called remove_watch() */ + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); + object_unref(OBJECT(sioc)); object_unref(OBJECT(server->ioc)); } -- 2.26.2 Only one struct is needed per request. Drop req_data and the separate VuBlockReq instance. Instead let vu_queue_pop() allocate everything at once. This fixes the req_data memory leak in vu_block_virtio_process_req(). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-6-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.c | 68 +++++++++------------------- 1 file changed, 21 insertions(+), 47 deletions(-) diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { }; typedef struct VuBlockReq { - VuVirtqElement *elem; + VuVirtqElement elem; int64_t sector_num; size_t size; struct virtio_blk_inhdr *in; @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) VuDev *vu_dev = &req->server->vu_dev; /* IO size with 1 extra status byte */ - vu_queue_push(vu_dev, req->vq, req->elem, req->size + 1); + vu_queue_push(vu_dev, req->vq, &req->elem, req->size + 1); vu_queue_notify(vu_dev, req->vq); - if (req->elem) { - free(req->elem); - } - - g_free(req); + free(req); } static VuBlockDev *get_vu_block_device_by_server(VuServer *server) @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_flush(VuBlockReq *req) blk_co_flush(backend); } -struct req_data { - VuServer *server; - VuVirtq *vq; - VuVirtqElement *elem; -}; - static void coroutine_fn vu_block_virtio_process_req(void *opaque) { - struct req_data *data = opaque; - VuServer *server = data->server; - VuVirtq *vq = data->vq; - VuVirtqElement *elem = data->elem; + VuBlockReq *req = opaque; + VuServer *server = req->server; + VuVirtqElement *elem = &req->elem; uint32_t type; - VuBlockReq *req; VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); BlockBackend *backend = vdev_blk->backend; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) struct iovec *out_iov = elem->out_sg; unsigned in_num = elem->in_num; unsigned out_num = elem->out_num; + /* refer to hw/block/virtio_blk.c */ if (elem->out_num < 1 || elem->in_num < 1) { error_report("virtio-blk request missing headers"); - free(elem); - return; + goto err; } - req = g_new0(VuBlockReq, 1); - req->server = server; - req->vq = vq; - req->elem = elem; - if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out, sizeof(req->out)) != sizeof(req->out))) { error_report("virtio-blk request outhdr too short"); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) err: free(elem); - g_free(req); - return; } static void vu_block_process_vq(VuDev *vu_dev, int idx) { - VuServer *server; - VuVirtq *vq; - struct req_data *req_data; + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + VuVirtq *vq = vu_get_queue(vu_dev, idx); - server = container_of(vu_dev, VuServer, vu_dev); - assert(server); - - vq = vu_get_queue(vu_dev, idx); - assert(vq); - VuVirtqElement *elem; while (1) { - elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + - sizeof(VuBlockReq)); - if (elem) { - req_data = g_new0(struct req_data, 1); - req_data->server = server; - req_data->vq = vq; - req_data->elem = elem; - Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req, - req_data); - aio_co_enter(server->ioc->ctx, co); - } else { + VuBlockReq *req; + + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); + if (!req) { break; } + + req->server = server; + req->vq = vq; + + Coroutine *co = + qemu_coroutine_create(vu_block_virtio_process_req, req); + qemu_coroutine_enter(co); } } -- 2.26.2 The device panic notifier callback is not used. Drop it. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-7-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 3 --- block/export/vhost-user-blk-server.c | 3 +-- util/vhost-user-server.c | 6 ------ 3 files changed, 1 insertion(+), 11 deletions(-) diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.h +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ typedef struct VuFdWatch { } VuFdWatch; typedef struct VuServer VuServer; -typedef void DevicePanicNotifierFn(VuServer *server); struct VuServer { QIONetListener *listener; AioContext *ctx; - DevicePanicNotifierFn *device_panic_notifier; int max_queues; const VuDevIface *vu_iface; VuDev vu_dev; @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, SocketAddress *unix_socket, AioContext *ctx, uint16_t max_queues, - DevicePanicNotifierFn *device_panic_notifier, const VuDevIface *vu_iface, Error **errp); diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, - VHOST_USER_BLK_MAX_QUEUES, - NULL, &vu_block_iface, + VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, errp)) { goto error; } diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ static void panic_cb(VuDev *vu_dev, const char *buf) close_client(server); } - if (server->device_panic_notifier) { - server->device_panic_notifier(server); - } - /* * Set the callback function for network listener so another * vhost-user client can connect to this server @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, SocketAddress *socket_addr, AioContext *ctx, uint16_t max_queues, - DevicePanicNotifierFn *device_panic_notifier, const VuDevIface *vu_iface, Error **errp) { @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, .vu_iface = vu_iface, .max_queues = max_queues, .ctx = ctx, - .device_panic_notifier = device_panic_notifier, }; qio_net_listener_set_name(server->listener, "vhost-user-backend-listener"); -- 2.26.2 fds[] is leaked when qio_channel_readv_full() fails. Use vmsg->fds[] instead of keeping a local fds[] array. Then we can reuse goto fail to clean up fds. vmsg->fd_num must be zeroed before the loop to make this safe. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-8-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 50 ++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 27 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) }; int rc, read_bytes = 0; Error *local_err = NULL; - /* - * Store fds/nfds returned from qio_channel_readv_full into - * temporary variables. - * - * VhostUserMsg is a packed structure, gcc will complain about passing - * pointer to a packed structure member if we pass &VhostUserMsg.fd_num - * and &VhostUserMsg.fds directly when calling qio_channel_readv_full, - * thus two temporary variables nfds and fds are used here. - */ - size_t nfds = 0, nfds_t = 0; const size_t max_fds = G_N_ELEMENTS(vmsg->fds); - int *fds_t = NULL; VuServer *server = container_of(vu_dev, VuServer, vu_dev); QIOChannel *ioc = server->ioc; + vmsg->fd_num = 0; if (!ioc) { error_report_err(local_err); goto fail; @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) assert(qemu_in_coroutine()); do { + size_t nfds = 0; + int *fds = NULL; + /* * qio_channel_readv_full may have short reads, keeping calling it * until getting VHOST_USER_HDR_SIZE or 0 bytes in total */ - rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err); + rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err); if (rc < 0) { if (rc == QIO_CHANNEL_ERR_BLOCK) { + assert(local_err == NULL); qio_channel_yield(ioc, G_IO_IN); continue; } else { error_report_err(local_err); - return false; + goto fail; } } - read_bytes += rc; - if (nfds_t > 0) { - if (nfds + nfds_t > max_fds) { + + if (nfds > 0) { + if (vmsg->fd_num + nfds > max_fds) { error_report("A maximum of %zu fds are allowed, " "however got %lu fds now", - max_fds, nfds + nfds_t); + max_fds, vmsg->fd_num + nfds); + g_free(fds); goto fail; } - memcpy(vmsg->fds + nfds, fds_t, - nfds_t *sizeof(vmsg->fds[0])); - nfds += nfds_t; - g_free(fds_t); + memcpy(vmsg->fds + vmsg->fd_num, fds, nfds * sizeof(vmsg->fds[0])); + vmsg->fd_num += nfds; + g_free(fds); } - if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) { - break; + + if (rc == 0) { /* socket closed */ + goto fail; } - iov.iov_base = (char *)vmsg + read_bytes; - iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes; - } while (true); - vmsg->fd_num = nfds; + iov.iov_base += rc; + iov.iov_len -= rc; + read_bytes += rc; + } while (read_bytes != VHOST_USER_HDR_SIZE); + /* qio_channel_readv_full will make socket fds blocking, unblock them */ vmsg_unblock_fds(vmsg); if (vmsg->size > sizeof(vmsg->payload)) { -- 2.26.2 Unexpected EOF is an error that must be reported. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-9-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg) }; if (vmsg->size) { rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err); - if (rc == -1) { - error_report_err(local_err); + if (rc != 1) { + if (local_err) { + error_report_err(local_err); + } goto fail; } } -- 2.26.2 The vu_client_trip() coroutine is leaked during AioContext switching. It is also unsafe to destroy the vu_dev in panic_cb() since its callers still access it in some cases. Rework the lifecycle to solve these safety issues. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-10-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/vhost-user-server.h | 29 ++-- block/export/vhost-user-blk-server.c | 9 +- util/vhost-user-server.c | 245 +++++++++++++++------------ 3 files changed, 155 insertions(+), 128 deletions(-) diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.h +++ b/util/vhost-user-server.h @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "standard-headers/linux/virtio_blk.h" +/* A kick fd that we monitor on behalf of libvhost-user */ typedef struct VuFdWatch { VuDev *vu_dev; int fd; /*kick fd*/ void *pvt; vu_watch_cb cb; - bool processing; QTAILQ_ENTRY(VuFdWatch) next; } VuFdWatch; -typedef struct VuServer VuServer; - -struct VuServer { +/** + * VuServer: + * A vhost-user server instance with user-defined VuDevIface callbacks. + * Vhost-user device backends can be implemented using VuServer. VuDevIface + * callbacks and virtqueue kicks run in the given AioContext. + */ +typedef struct { QIONetListener *listener; + QEMUBH *restart_listener_bh; AioContext *ctx; int max_queues; const VuDevIface *vu_iface; + + /* Protected by ctx lock */ VuDev vu_dev; QIOChannel *ioc; /* The I/O channel with the client */ QIOChannelSocket *sioc; /* The underlying data channel with the client */ - /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */ - QIOChannel *ioc_slave; - QIOChannelSocket *sioc_slave; - Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ QTAILQ_HEAD(, VuFdWatch) vu_fd_watches; - /* restart coroutine co_trip if AIOContext is changed */ - bool aio_context_changed; - bool processing_msg; -}; + + Coroutine *co_trip; /* coroutine for processing VhostUserMsg */ +} VuServer; bool vhost_user_server_start(VuServer *server, SocketAddress *unix_socket, @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, void vhost_user_server_stop(VuServer *server); -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx); +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx); +void vhost_user_server_detach_aio_context(VuServer *server); #endif /* VHOST_USER_SERVER_H */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_block_iface = { static void blk_aio_attached(AioContext *ctx, void *opaque) { VuBlockDev *vub_dev = opaque; - aio_context_acquire(ctx); - vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx); - aio_context_release(ctx); + vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); } static void blk_aio_detach(void *opaque) { VuBlockDev *vub_dev = opaque; - AioContext *ctx = vub_dev->vu_server.ctx; - aio_context_acquire(ctx); - vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL); - aio_context_release(ctx); + vhost_user_server_detach_aio_context(&vub_dev->vu_server); } static void diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "qemu/main-loop.h" +#include "block/aio-wait.h" #include "vhost-user-server.h" +/* + * Theory of operation: + * + * VuServer is started and stopped by vhost_user_server_start() and + * vhost_user_server_stop() from the main loop thread. Starting the server + * opens a vhost-user UNIX domain socket and listens for incoming connections. + * Only one connection is allowed at a time. + * + * The connection is handled by the vu_client_trip() coroutine in the + * VuServer->ctx AioContext. The coroutine consists of a vu_dispatch() loop + * where libvhost-user calls vu_message_read() to receive the next vhost-user + * protocol messages over the UNIX domain socket. + * + * When virtqueues are set up libvhost-user calls set_watch() to monitor kick + * fds. These fds are also handled in the VuServer->ctx AioContext. + * + * Both vu_client_trip() and kick fd monitoring can be stopped by shutting down + * the socket connection. Shutting down the socket connection causes + * vu_message_read() to fail since no more data can be received from the socket. + * After vu_dispatch() fails, vu_client_trip() calls vu_deinit() to stop + * libvhost-user before terminating the coroutine. vu_deinit() calls + * remove_watch() to stop monitoring kick fds and this stops virtqueue + * processing. + * + * When vu_client_trip() has finished cleaning up it schedules a BH in the main + * loop thread to accept the next client connection. + * + * When libvhost-user detects an error it calls panic_cb() and sets the + * dev->broken flag. Both vu_client_trip() and kick fd processing stop when + * the dev->broken flag is set. + * + * It is possible to switch AioContexts using + * vhost_user_server_detach_aio_context() and + * vhost_user_server_attach_aio_context(). They stop monitoring fds in the old + * AioContext and resume monitoring in the new AioContext. The vu_client_trip() + * coroutine remains in a yielded state during the switch. This is made + * possible by QIOChannel's support for spurious coroutine re-entry in + * qio_channel_yield(). The coroutine will restart I/O when re-entered from the + * new AioContext. + */ + static void vmsg_close_fds(VhostUserMsg *vmsg) { int i; @@ -XXX,XX +XXX,XX @@ static void vmsg_unblock_fds(VhostUserMsg *vmsg) } } -static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, - gpointer opaque); - -static void close_client(VuServer *server) -{ - /* - * Before closing the client - * - * 1. Let vu_client_trip stop processing new vhost-user msg - * - * 2. remove kick_handler - * - * 3. wait for the kick handler to be finished - * - * 4. wait for the current vhost-user msg to be finished processing - */ - - QIOChannelSocket *sioc = server->sioc; - /* When this is set vu_client_trip will stop new processing vhost-user message */ - server->sioc = NULL; - - while (server->processing_msg) { - if (server->ioc->read_coroutine) { - server->ioc->read_coroutine = NULL; - qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL, - NULL, server->ioc); - server->processing_msg = false; - } - } - - vu_deinit(&server->vu_dev); - - /* vu_deinit() should have called remove_watch() */ - assert(QTAILQ_EMPTY(&server->vu_fd_watches)); - - object_unref(OBJECT(sioc)); - object_unref(OBJECT(server->ioc)); -} - static void panic_cb(VuDev *vu_dev, const char *buf) { - VuServer *server = container_of(vu_dev, VuServer, vu_dev); - - /* avoid while loop in close_client */ - server->processing_msg = false; - - if (buf) { - error_report("vu_panic: %s", buf); - } - - if (server->sioc) { - close_client(server); - } - - /* - * Set the callback function for network listener so another - * vhost-user client can connect to this server - */ - qio_net_listener_set_client_func(server->listener, - vu_accept, - server, - NULL); + error_report("vu_panic: %s", buf); } static bool coroutine_fn @@ -XXX,XX +XXX,XX @@ fail: return false; } - -static void vu_client_start(VuServer *server); static coroutine_fn void vu_client_trip(void *opaque) { VuServer *server = opaque; + VuDev *vu_dev = &server->vu_dev; - while (!server->aio_context_changed && server->sioc) { - server->processing_msg = true; - vu_dispatch(&server->vu_dev); - server->processing_msg = false; + while (!vu_dev->broken && vu_dispatch(vu_dev)) { + /* Keep running */ } - if (server->aio_context_changed && server->sioc) { - server->aio_context_changed = false; - vu_client_start(server); - } -} + vu_deinit(vu_dev); + + /* vu_deinit() should have called remove_watch() */ + assert(QTAILQ_EMPTY(&server->vu_fd_watches)); + + object_unref(OBJECT(server->sioc)); + server->sioc = NULL; -static void vu_client_start(VuServer *server) -{ - server->co_trip = qemu_coroutine_create(vu_client_trip, server); - aio_co_enter(server->ctx, server->co_trip); + object_unref(OBJECT(server->ioc)); + server->ioc = NULL; + + server->co_trip = NULL; + if (server->restart_listener_bh) { + qemu_bh_schedule(server->restart_listener_bh); + } + aio_wait_kick(); } /* @@ -XXX,XX +XXX,XX @@ static void vu_client_start(VuServer *server) static void kick_handler(void *opaque) { VuFdWatch *vu_fd_watch = opaque; - vu_fd_watch->processing = true; - vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt); - vu_fd_watch->processing = false; + VuDev *vu_dev = vu_fd_watch->vu_dev; + + vu_fd_watch->cb(vu_dev, 0, vu_fd_watch->pvt); + + /* Stop vu_client_trip() if an error occurred in vu_fd_watch->cb() */ + if (vu_dev->broken) { + VuServer *server = container_of(vu_dev, VuServer, vu_dev); + + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + } } - static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd) { @@ -XXX,XX +XXX,XX @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc, qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client"); server->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(server->ioc)); - qio_channel_attach_aio_context(server->ioc, server->ctx); + + /* TODO vu_message_write() spins if non-blocking! */ qio_channel_set_blocking(server->ioc, false, NULL); - vu_client_start(server); + + server->co_trip = qemu_coroutine_create(vu_client_trip, server); + + aio_context_acquire(server->ctx); + vhost_user_server_attach_aio_context(server, server->ctx); + aio_context_release(server->ctx); } - void vhost_user_server_stop(VuServer *server) { + aio_context_acquire(server->ctx); + + qemu_bh_delete(server->restart_listener_bh); + server->restart_listener_bh = NULL; + if (server->sioc) { - close_client(server); + VuFdWatch *vu_fd_watch; + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, + NULL, NULL, NULL, vu_fd_watch); + } + + qio_channel_shutdown(server->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + + AIO_WAIT_WHILE(server->ctx, server->co_trip); } + aio_context_release(server->ctx); + if (server->listener) { qio_net_listener_disconnect(server->listener); object_unref(OBJECT(server->listener)); } +} + +/* + * Allow the next client to connect to the server. Called from a BH in the main + * loop. + */ +static void restart_listener_bh(void *opaque) +{ + VuServer *server = opaque; + qio_net_listener_set_client_func(server->listener, vu_accept, server, + NULL); } -void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx) +/* Called with ctx acquired */ +void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx) { - VuFdWatch *vu_fd_watch, *next; - void *opaque = NULL; - IOHandler *io_read = NULL; - bool attach; + VuFdWatch *vu_fd_watch; - server->ctx = ctx ? ctx : qemu_get_aio_context(); + server->ctx = ctx; if (!server->sioc) { - /* not yet serving any client*/ return; } - if (ctx) { - qio_channel_attach_aio_context(server->ioc, ctx); - server->aio_context_changed = true; - io_read = kick_handler; - attach = true; - } else { + qio_channel_attach_aio_context(server->ioc, ctx); + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(ctx, vu_fd_watch->fd, true, kick_handler, NULL, + NULL, vu_fd_watch); + } + + aio_co_schedule(ctx, server->co_trip); +} + +/* Called with server->ctx acquired */ +void vhost_user_server_detach_aio_context(VuServer *server) +{ + if (server->sioc) { + VuFdWatch *vu_fd_watch; + + QTAILQ_FOREACH(vu_fd_watch, &server->vu_fd_watches, next) { + aio_set_fd_handler(server->ctx, vu_fd_watch->fd, true, + NULL, NULL, NULL, vu_fd_watch); + } + qio_channel_detach_aio_context(server->ioc); - /* server->ioc->ctx keeps the old AioConext */ - ctx = server->ioc->ctx; - attach = false; } - QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) { - if (vu_fd_watch->cb) { - opaque = attach ? vu_fd_watch : NULL; - aio_set_fd_handler(ctx, vu_fd_watch->fd, true, - io_read, NULL, NULL, - opaque); - } - } + server->ctx = NULL; } - bool vhost_user_server_start(VuServer *server, SocketAddress *socket_addr, AioContext *ctx, @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, const VuDevIface *vu_iface, Error **errp) { + QEMUBH *bh; QIONetListener *listener = qio_net_listener_new(); if (qio_net_listener_open_sync(listener, socket_addr, 1, errp) < 0) { @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, return false; } + bh = qemu_bh_new(restart_listener_bh, server); + /* zero out unspecified fields */ *server = (VuServer) { .listener = listener, + .restart_listener_bh = bh, .vu_iface = vu_iface, .max_queues = max_queues, .ctx = ctx, -- 2.26.2 Propagate the flush return value since errors are possible. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-11-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/vhost-user-blk-server.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } -static void coroutine_fn vu_block_flush(VuBlockReq *req) +static int coroutine_fn vu_block_flush(VuBlockReq *req) { VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); BlockBackend *backend = vdev_blk->backend; - blk_co_flush(backend); + return blk_co_flush(backend); } static void coroutine_fn vu_block_virtio_process_req(void *opaque) @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } case VIRTIO_BLK_T_FLUSH: - vu_block_flush(req); - req->in->status = VIRTIO_BLK_S_OK; + if (vu_block_flush(req) == 0) { + req->in->status = VIRTIO_BLK_S_OK; + } else { + req->in->status = VIRTIO_BLK_S_IOERR; + } break; case VIRTIO_BLK_T_GET_ID: { size_t size = MIN(iov_size(&elem->in_sg[0], in_num), -- 2.26.2 Use the new QAPI block exports API instead of defining our own QOM objects. This is a large change because the lifecycle of VuBlockDev needs to follow BlockExportDriver. QOM properties are replaced by QAPI options objects. VuBlockDev is renamed VuBlkExport and contains a BlockExport field. Several fields can be dropped since BlockExport already has equivalents. The file names and meson build integration will be adjusted in a future patch. libvhost-user should probably be built as a static library that is linked into QEMU instead of as a .c file that results in duplicate compilation. The new command-line syntax is: $ qemu-storage-daemon \ --blockdev file,node-name=drive0,filename=test.img \ --export vhost-user-blk,node-name=drive0,id=export0,unix-socket=/tmp/vhost-user-blk.sock Note that unix-socket is optional because we may wish to accept chardevs too in the future. Markus noted that supported address families are not explicit in the QAPI schema. It is unlikely that support for more address families will be added since file descriptor passing is required and few address families support it. If a new address family needs to be added, then the QAPI 'features' syntax can be used to advertize them. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20200924151549.913737-12-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 21 +- block/export/vhost-user-blk-server.h | 23 +- block/export/export.c | 6 + block/export/vhost-user-blk-server.c | 452 +++++++-------------------- tests/qtest/vhost-user-blk-test.c | 2 +- util/vhost-user-server.c | 10 +- block/export/meson.build | 1 + block/meson.build | 1 - 8 files changed, 157 insertions(+), 359 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ 'data': { '*name': 'str', '*description': 'str', '*bitmap': 'str' } } +## +# @BlockExportOptionsVhostUserBlk: +# +# A vhost-user-blk block export. +# +# @addr: The vhost-user socket on which to listen. Both 'unix' and 'fd' +# SocketAddress types are supported. Passed fds must be UNIX domain +# sockets. +# @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. +# +# Since: 5.2 +## +{ 'struct': 'BlockExportOptionsVhostUserBlk', + 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } + ## # @NbdServerAddOptions: # @@ -XXX,XX +XXX,XX @@ # An enumeration of block export types # # @nbd: NBD export +# @vhost-user-blk: vhost-user-blk export (since 5.2) # # Since: 4.2 ## { 'enum': 'BlockExportType', - 'data': [ 'nbd' ] } + 'data': [ 'nbd', 'vhost-user-blk' ] } ## # @BlockExportOptions: @@ -XXX,XX +XXX,XX @@ '*writethrough': 'bool' }, 'discriminator': 'type', 'data': { - 'nbd': 'BlockExportOptionsNbd' + 'nbd': 'BlockExportOptionsNbd', + 'vhost-user-blk': 'BlockExportOptionsVhostUserBlk' } } ## diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.h +++ b/block/export/vhost-user-blk-server.h @@ -XXX,XX +XXX,XX @@ #ifndef VHOST_USER_BLK_SERVER_H #define VHOST_USER_BLK_SERVER_H -#include "util/vhost-user-server.h" -typedef struct VuBlockDev VuBlockDev; -#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" -#define VHOST_USER_BLK_SERVER(obj) \ - OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) +#include "block/export.h" -/* vhost user block device */ -struct VuBlockDev { - Object parent_obj; - char *node_name; - SocketAddress *addr; - AioContext *ctx; - VuServer vu_server; - bool running; - uint32_t blk_size; - BlockBackend *backend; - QIOChannelSocket *sioc; - QTAILQ_ENTRY(VuBlockDev) next; - struct virtio_blk_config blkcfg; - bool writable; -}; +/* For block/export/export.c */ +extern const BlockExportDriver blk_exp_vhost_user_blk; #endif /* VHOST_USER_BLK_SERVER_H */ diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/block-backend.h" #include "block/export.h" #include "block/nbd.h" +#if CONFIG_LINUX +#include "block/export/vhost-user-blk-server.h" +#endif #include "qapi/error.h" #include "qapi/qapi-commands-block-export.h" #include "qapi/qapi-events-block-export.h" @@ -XXX,XX +XXX,XX @@ static const BlockExportDriver *blk_exp_drivers[] = { &blk_exp_nbd, +#if CONFIG_LINUX + &blk_exp_vhost_user_blk, +#endif }; /* Only accessed from the main thread */ diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "block/block.h" +#include "contrib/libvhost-user/libvhost-user.h" +#include "standard-headers/linux/virtio_blk.h" +#include "util/vhost-user-server.h" #include "vhost-user-blk-server.h" #include "qapi/error.h" #include "qom/object_interfaces.h" @@ -XXX,XX +XXX,XX @@ struct virtio_blk_inhdr { unsigned char status; }; -typedef struct VuBlockReq { +typedef struct VuBlkReq { VuVirtqElement elem; int64_t sector_num; size_t size; @@ -XXX,XX +XXX,XX @@ typedef struct VuBlockReq { struct virtio_blk_outhdr out; VuServer *server; struct VuVirtq *vq; -} VuBlockReq; +} VuBlkReq; -static void vu_block_req_complete(VuBlockReq *req) +/* vhost user block device */ +typedef struct { + BlockExport export; + VuServer vu_server; + uint32_t blk_size; + QIOChannelSocket *sioc; + struct virtio_blk_config blkcfg; + bool writable; +} VuBlkExport; + +static void vu_blk_req_complete(VuBlkReq *req) { VuDev *vu_dev = &req->server->vu_dev; @@ -XXX,XX +XXX,XX @@ static void vu_block_req_complete(VuBlockReq *req) free(req); } -static VuBlockDev *get_vu_block_device_by_server(VuServer *server) -{ - return container_of(server, VuBlockDev, vu_server); -} - static int coroutine_fn -vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, - uint32_t iovcnt, uint32_t type) +vu_blk_discard_write_zeroes(BlockBackend *blk, struct iovec *iov, + uint32_t iovcnt, uint32_t type) { struct virtio_blk_discard_write_zeroes desc; ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, le32_to_cpu(desc.num_sectors) << 9 }; if (type == VIRTIO_BLK_T_DISCARD) { - if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { + if (blk_co_pdiscard(blk, range[0], range[1]) == 0) { return 0; } } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { - if (blk_co_pwrite_zeroes(vdev_blk->backend, - range[0], range[1], 0) == 0) { + if (blk_co_pwrite_zeroes(blk, range[0], range[1], 0) == 0) { return 0; } } @@ -XXX,XX +XXX,XX @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } -static int coroutine_fn vu_block_flush(VuBlockReq *req) +static void coroutine_fn vu_blk_virtio_process_req(void *opaque) { - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); - BlockBackend *backend = vdev_blk->backend; - return blk_co_flush(backend); -} - -static void coroutine_fn vu_block_virtio_process_req(void *opaque) -{ - VuBlockReq *req = opaque; + VuBlkReq *req = opaque; VuServer *server = req->server; VuVirtqElement *elem = &req->elem; uint32_t type; - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - BlockBackend *backend = vdev_blk->backend; + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + BlockBackend *blk = vexp->export.blk; struct iovec *in_iov = elem->in_sg; struct iovec *out_iov = elem->out_sg; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) bool is_write = type & VIRTIO_BLK_T_OUT; req->sector_num = le64_to_cpu(req->out.sector); - int64_t offset = req->sector_num * vdev_blk->blk_size; + if (is_write && !vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + int64_t offset = req->sector_num * vexp->blk_size; QEMUIOVector qiov; if (is_write) { qemu_iovec_init_external(&qiov, out_iov, out_num); - ret = blk_co_pwritev(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0); } else { qemu_iovec_init_external(&qiov, in_iov, in_num); - ret = blk_co_preadv(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0); } if (ret >= 0) { req->in->status = VIRTIO_BLK_S_OK; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } case VIRTIO_BLK_T_FLUSH: - if (vu_block_flush(req) == 0) { + if (blk_co_flush(blk) == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { req->in->status = VIRTIO_BLK_S_IOERR; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) case VIRTIO_BLK_T_DISCARD: case VIRTIO_BLK_T_WRITE_ZEROES: { int rc; - rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], - out_num, type); + + if (!vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type); if (rc == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { @@ -XXX,XX +XXX,XX @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } - vu_block_req_complete(req); + vu_blk_req_complete(req); return; err: - free(elem); + free(req); } -static void vu_block_process_vq(VuDev *vu_dev, int idx) +static void vu_blk_process_vq(VuDev *vu_dev, int idx) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); VuVirtq *vq = vu_get_queue(vu_dev, idx); while (1) { - VuBlockReq *req; + VuBlkReq *req; - req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlkReq)); if (!req) { break; } @@ -XXX,XX +XXX,XX @@ static void vu_block_process_vq(VuDev *vu_dev, int idx) req->vq = vq; Coroutine *co = - qemu_coroutine_create(vu_block_virtio_process_req, req); + qemu_coroutine_create(vu_blk_virtio_process_req, req); qemu_coroutine_enter(co); } } -static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) +static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started) { VuVirtq *vq; assert(vu_dev); vq = vu_get_queue(vu_dev, idx); - vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); + vu_set_queue_handler(vu_dev, vq, started ? vu_blk_process_vq : NULL); } -static uint64_t vu_block_get_features(VuDev *dev) +static uint64_t vu_blk_get_features(VuDev *dev) { uint64_t features; VuServer *server = container_of(dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); features = 1ull << VIRTIO_BLK_F_SIZE_MAX | 1ull << VIRTIO_BLK_F_SEG_MAX | 1ull << VIRTIO_BLK_F_TOPOLOGY | @@ -XXX,XX +XXX,XX @@ static uint64_t vu_block_get_features(VuDev *dev) 1ull << VIRTIO_RING_F_EVENT_IDX | 1ull << VHOST_USER_F_PROTOCOL_FEATURES; - if (!vdev_blk->writable) { + if (!vexp->writable) { features |= 1ull << VIRTIO_BLK_F_RO; } return features; } -static uint64_t vu_block_get_protocol_features(VuDev *dev) +static uint64_t vu_blk_get_protocol_features(VuDev *dev) { return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; } static int -vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) +vu_blk_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) { + /* TODO blkcfg must be little-endian for VIRTIO 1.0 */ VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - memcpy(config, &vdev_blk->blkcfg, len); - + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + memcpy(config, &vexp->blkcfg, len); return 0; } static int -vu_block_set_config(VuDev *vu_dev, const uint8_t *data, +vu_blk_set_config(VuDev *vu_dev, const uint8_t *data, uint32_t offset, uint32_t size, uint32_t flags) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); uint8_t wce; /* don't support live migration */ @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, } wce = *data; - vdev_blk->blkcfg.wce = wce; - blk_set_enable_write_cache(vdev_blk->backend, wce); + vexp->blkcfg.wce = wce; + blk_set_enable_write_cache(vexp->export.blk, wce); return 0; } @@ -XXX,XX +XXX,XX @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, * of vu_process_message. * */ -static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) +static int vu_blk_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) { if (vmsg->request == VHOST_USER_NONE) { dev->panic(dev, "disconnect"); @@ -XXX,XX +XXX,XX @@ static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) return false; } -static const VuDevIface vu_block_iface = { - .get_features = vu_block_get_features, - .queue_set_started = vu_block_queue_set_started, - .get_protocol_features = vu_block_get_protocol_features, - .get_config = vu_block_get_config, - .set_config = vu_block_set_config, - .process_msg = vu_block_process_msg, +static const VuDevIface vu_blk_iface = { + .get_features = vu_blk_get_features, + .queue_set_started = vu_blk_queue_set_started, + .get_protocol_features = vu_blk_get_protocol_features, + .get_config = vu_blk_get_config, + .set_config = vu_blk_set_config, + .process_msg = vu_blk_process_msg, }; static void blk_aio_attached(AioContext *ctx, void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); + VuBlkExport *vexp = opaque; + vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); } static void blk_aio_detach(void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_detach_aio_context(&vub_dev->vu_server); + VuBlkExport *vexp = opaque; + vhost_user_server_detach_aio_context(&vexp->vu_server); } static void -vu_block_initialize_config(BlockDriverState *bs, +vu_blk_initialize_config(BlockDriverState *bs, struct virtio_blk_config *config, uint32_t blk_size) { config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; @@ -XXX,XX +XXX,XX @@ vu_block_initialize_config(BlockDriverState *bs, config->max_write_zeroes_seg = 1; } -static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) +static void vu_blk_exp_request_shutdown(BlockExport *exp) { + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - BlockBackend *blk; - Error *local_error = NULL; - const char *node_name = vu_block_device->node_name; - bool writable = vu_block_device->writable; - uint64_t perm = BLK_PERM_CONSISTENT_READ; - int ret; - - AioContext *ctx; - - BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); - - if (!bs) { - error_propagate(errp, local_error); - return NULL; - } - - if (bdrv_is_read_only(bs)) { - writable = false; - } - - if (writable) { - perm |= BLK_PERM_WRITE; - } - - ctx = bdrv_get_aio_context(bs); - aio_context_acquire(ctx); - bdrv_invalidate_cache(bs, NULL); - aio_context_release(ctx); - - /* - * Don't allow resize while the vhost user server is running, - * otherwise we don't care what happens with the node. - */ - blk = blk_new(bdrv_get_aio_context(bs), perm, - BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | - BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); - ret = blk_insert_bs(blk, bs, errp); - - if (ret < 0) { - goto fail; - } - - blk_set_enable_write_cache(blk, false); - - blk_set_allow_aio_context_change(blk, true); - - vu_block_device->blkcfg.wce = 0; - vu_block_device->backend = blk; - if (!vu_block_device->blk_size) { - vu_block_device->blk_size = BDRV_SECTOR_SIZE; - } - vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; - blk_set_guest_block_size(blk, vu_block_device->blk_size); - vu_block_initialize_config(bs, &vu_block_device->blkcfg, - vu_block_device->blk_size); - return vu_block_device; - -fail: - blk_unref(blk); - return NULL; -} - -static void vu_block_deinit(VuBlockDev *vu_block_device) -{ - if (vu_block_device->backend) { - blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - } - - blk_unref(vu_block_device->backend); -} - -static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) -{ - vhost_user_server_stop(&vu_block_device->vu_server); - vu_block_deinit(vu_block_device); -} - -static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, - Error **errp) -{ - AioContext *ctx; - SocketAddress *addr = vu_block_device->addr; - - if (!vu_block_init(vu_block_device, errp)) { - return; - } - - ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); - - if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, - VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, - errp)) { - goto error; - } - - blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - vu_block_device->running = true; - return; - - error: - vu_block_deinit(vu_block_device); -} - -static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) -{ - if (vus->running) { - error_setg(errp, "The property can't be modified " - "while the server is running"); - return false; - } - return true; -} - -static void vu_set_node_name(Object *obj, const char *value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->node_name) { - g_free(vus->node_name); - } - - vus->node_name = g_strdup(value); -} - -static char *vu_get_node_name(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->node_name); -} - -static void free_socket_addr(SocketAddress *addr) -{ - g_free(addr->u.q_unix.path); - g_free(addr); -} - -static void vu_set_unix_socket(Object *obj, const char *value, - Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->addr) { - free_socket_addr(vus->addr); - } - - SocketAddress *addr = g_new0(SocketAddress, 1); - addr->type = SOCKET_ADDRESS_TYPE_UNIX; - addr->u.q_unix.path = g_strdup(value); - vus->addr = addr; + vhost_user_server_stop(&vexp->vu_server); } -static char *vu_get_unix_socket(Object *obj, Error **errp) +static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, + Error **errp) { - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->addr->u.q_unix.path); -} - -static bool vu_get_block_writable(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return vus->writable; -} - -static void vu_set_block_writable(Object *obj, bool value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - vus->writable = value; -} - -static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - uint32_t value = vus->blk_size; - - visit_type_uint32(v, name, &value, errp); -} - -static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); + BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; Error *local_err = NULL; - uint32_t value; + uint64_t logical_block_size; - if (!vu_prop_modifiable(vus, errp)) { - return; - } + vexp->writable = opts->writable; + vexp->blkcfg.wce = 0; - visit_type_uint32(v, name, &value, &local_err); - if (local_err) { - goto out; + if (vu_opts->has_logical_block_size) { + logical_block_size = vu_opts->logical_block_size; + } else { + logical_block_size = BDRV_SECTOR_SIZE; } - - check_block_size(object_get_typename(obj), name, value, &local_err); + check_block_size(exp->id, "logical-block-size", logical_block_size, + &local_err); if (local_err) { - goto out; + error_propagate(errp, local_err); + return -EINVAL; + } + vexp->blk_size = logical_block_size; + blk_set_guest_block_size(exp->blk, logical_block_size); + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, + logical_block_size); + + blk_set_allow_aio_context_change(exp->blk, true); + blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); + + if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, + VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, + errp)) { + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, + blk_aio_detach, vexp); + return -EADDRNOTAVAIL; } - vus->blk_size = value; - -out: - error_propagate(errp, local_err); -} - -static void vhost_user_blk_server_instance_finalize(Object *obj) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_stop(vub); - - /* - * Unlike object_property_add_str, object_class_property_add_str - * doesn't have a release method. Thus manual memory freeing is - * needed. - */ - free_socket_addr(vub->addr); - g_free(vub->node_name); -} - -static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_start(vub, errp); + return 0; } -static void vhost_user_blk_server_class_init(ObjectClass *klass, - void *class_data) +static void vu_blk_exp_delete(BlockExport *exp) { - UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); - ucc->complete = vhost_user_blk_server_complete; - - object_class_property_add_bool(klass, "writable", - vu_get_block_writable, - vu_set_block_writable); - - object_class_property_add_str(klass, "node-name", - vu_get_node_name, - vu_set_node_name); - - object_class_property_add_str(klass, "unix-socket", - vu_get_unix_socket, - vu_set_unix_socket); + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - object_class_property_add(klass, "logical-block-size", "uint32", - vu_get_blk_size, vu_set_blk_size, - NULL, NULL); + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); } -static const TypeInfo vhost_user_blk_server_info = { - .name = TYPE_VHOST_USER_BLK_SERVER, - .parent = TYPE_OBJECT, - .instance_size = sizeof(VuBlockDev), - .instance_finalize = vhost_user_blk_server_instance_finalize, - .class_init = vhost_user_blk_server_class_init, - .interfaces = (InterfaceInfo[]) { - {TYPE_USER_CREATABLE}, - {} - }, +const BlockExportDriver blk_exp_vhost_user_blk = { + .type = BLOCK_EXPORT_TYPE_VHOST_USER_BLK, + .instance_size = sizeof(VuBlkExport), + .create = vu_blk_exp_create, + .delete = vu_blk_exp_delete, + .request_shutdown = vu_blk_exp_request_shutdown, }; - -static void vhost_user_blk_server_register_types(void) -{ - type_register_static(&vhost_user_blk_server_info); -} - -type_init(vhost_user_blk_server_register_types) diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/vhost-user-blk-test.c +++ b/tests/qtest/vhost-user-blk-test.c @@ -XXX,XX +XXX,XX @@ static char *start_vhost_user_blk(GString *cmd_line, int vus_instances) img_path = drive_create(); g_string_append_printf(storage_daemon_command, "--blockdev driver=file,node-name=disk%d,filename=%s " - "--object vhost-user-blk-server,id=disk%d,unix-socket=%s," + "--export type=vhost-user-blk,id=disk%d,addr.type=unix,addr.path=%s," "node-name=disk%i,writable=on ", i, img_path, i, sock_path, i); diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ bool vhost_user_server_start(VuServer *server, Error **errp) { QEMUBH *bh; - QIONetListener *listener = qio_net_listener_new(); + QIONetListener *listener; + + if (socket_addr->type != SOCKET_ADDRESS_TYPE_UNIX && + socket_addr->type != SOCKET_ADDRESS_TYPE_FD) { + error_setg(errp, "Only socket address types 'unix' and 'fd' are supported"); + return false; + } + + listener = qio_net_listener_new(); if (qio_net_listener_open_sync(listener, socket_addr, 1, errp) < 0) { object_unref(OBJECT(listener)); diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -1 +1,2 @@ block_ss.add(files('export.c')) +block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) diff --git a/block/meson.build b/block/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/meson.build +++ b/block/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) -block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) -- 2.26.2 Headers used by other subsystems are located in include/. Also add the vhost-user-server and vhost-user-blk-server headers to MAINTAINERS. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-13-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 4 +++- {util => include/qemu}/vhost-user-server.h | 0 block/export/vhost-user-blk-server.c | 2 +- util/vhost-user-server.c | 2 +- 4 files changed, 5 insertions(+), 3 deletions(-) rename {util => include/qemu}/vhost-user-server.h (100%) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ Vhost-user block device backend server M: Coiby Xu <Coiby.Xu@gmail.com> S: Maintained F: block/export/vhost-user-blk-server.c -F: util/vhost-user-server.c +F: block/export/vhost-user-blk-server.h +F: include/qemu/vhost-user-server.h F: tests/qtest/vhost-user-blk-test.c F: tests/qtest/libqos/vhost-user-blk.c +F: util/vhost-user-server.c Replication M: Wen Congyang <wencongyang2@huawei.com> diff --git a/util/vhost-user-server.h b/include/qemu/vhost-user-server.h similarity index 100% rename from util/vhost-user-server.h rename to include/qemu/vhost-user-server.h diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "contrib/libvhost-user/libvhost-user.h" #include "standard-headers/linux/virtio_blk.h" -#include "util/vhost-user-server.h" +#include "qemu/vhost-user-server.h" #include "vhost-user-blk-server.h" #include "qapi/error.h" #include "qom/object_interfaces.h" diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c index XXXXXXX..XXXXXXX 100644 --- a/util/vhost-user-server.c +++ b/util/vhost-user-server.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" #include "qemu/main-loop.h" +#include "qemu/vhost-user-server.h" #include "block/aio-wait.h" -#include "vhost-user-server.h" /* * Theory of operation: -- 2.26.2 Don't compile contrib/libvhost-user/libvhost-user.c again. Instead build the static library once and then reuse it throughout QEMU. Also switch from CONFIG_LINUX to CONFIG_VHOST_USER, which is what the vhost-user tools (vhost-user-gpu, etc) do. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200924151549.913737-14-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/export/export.c | 8 ++++---- block/export/meson.build | 2 +- contrib/libvhost-user/meson.build | 1 + meson.build | 6 +++++- tests/qtest/meson.build | 2 +- util/meson.build | 4 +++- 6 files changed, 15 insertions(+), 8 deletions(-) diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/block-backend.h" #include "block/export.h" #include "block/nbd.h" -#if CONFIG_LINUX -#include "block/export/vhost-user-blk-server.h" -#endif #include "qapi/error.h" #include "qapi/qapi-commands-block-export.h" #include "qapi/qapi-events-block-export.h" #include "qemu/id.h" +#ifdef CONFIG_VHOST_USER +#include "vhost-user-blk-server.h" +#endif static const BlockExportDriver *blk_exp_drivers[] = { &blk_exp_nbd, -#if CONFIG_LINUX +#ifdef CONFIG_VHOST_USER &blk_exp_vhost_user_blk, #endif }; diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(files('export.c')) -block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) +block_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-blk-server.c')) diff --git a/contrib/libvhost-user/meson.build b/contrib/libvhost-user/meson.build index XXXXXXX..XXXXXXX 100644 --- a/contrib/libvhost-user/meson.build +++ b/contrib/libvhost-user/meson.build @@ -XXX,XX +XXX,XX @@ libvhost_user = static_library('vhost-user', files('libvhost-user.c', 'libvhost-user-glib.c'), build_by_default: false) +vhost_user = declare_dependency(link_with: libvhost_user) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ trace_events_subdirs += [ 'util', ] +vhost_user = not_found +if 'CONFIG_VHOST_USER' in config_host + subdir('contrib/libvhost-user') +endif + subdir('qapi') subdir('qobject') subdir('stubs') @@ -XXX,XX +XXX,XX @@ if have_tools install: true) if 'CONFIG_VHOST_USER' in config_host - subdir('contrib/libvhost-user') subdir('contrib/vhost-user-blk') subdir('contrib/vhost-user-gpu') subdir('contrib/vhost-user-input') diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qos_test_ss.add( ) qos_test_ss.add(when: 'CONFIG_VIRTFS', if_true: files('virtio-9p-test.c')) qos_test_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-test.c')) -qos_test_ss.add(when: ['CONFIG_LINUX', 'CONFIG_TOOLS'], if_true: files('vhost-user-blk-test.c')) +qos_test_ss.add(when: ['CONFIG_VHOST_USER', 'CONFIG_TOOLS'], if_true: files('vhost-user-blk-test.c')) extra_qtest_deps = { 'bios-tables-test': [io], diff --git a/util/meson.build b/util/meson.build index XXXXXXX..XXXXXXX 100644 --- a/util/meson.build +++ b/util/meson.build @@ -XXX,XX +XXX,XX @@ if have_block util_ss.add(files('main-loop.c')) util_ss.add(files('nvdimm-utils.c')) util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c')) - util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c')) + util_ss.add(when: 'CONFIG_VHOST_USER', if_true: [ + files('vhost-user-server.c'), vhost_user + ]) util_ss.add(files('block-helpers.c')) util_ss.add(files('qemu-coroutine-sleep.c')) util_ss.add(files('qemu-co-shared-resource.c')) -- 2.26.2 Introduce libblkdev.fa to avoid recompiling blockdev_ss twice. Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200929125516.186715-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- meson.build | 12 ++++++++++-- storage-daemon/meson.build | 3 +-- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ blockdev_ss.add(files( blockdev_ss.add(when: 'CONFIG_POSIX', if_true: files('os-posix.c')) softmmu_ss.add(when: 'CONFIG_WIN32', if_true: [files('os-win32.c')]) -softmmu_ss.add_all(blockdev_ss) softmmu_ss.add(files( 'bootdevice.c', 'dma-helpers.c', @@ -XXX,XX +XXX,XX @@ block = declare_dependency(link_whole: [libblock], link_args: '@block.syms', dependencies: [crypto, io]) +blockdev_ss = blockdev_ss.apply(config_host, strict: false) +libblockdev = static_library('blockdev', blockdev_ss.sources() + genh, + dependencies: blockdev_ss.dependencies(), + name_suffix: 'fa', + build_by_default: false) + +blockdev = declare_dependency(link_whole: [libblockdev], + dependencies: [block]) + qmp_ss = qmp_ss.apply(config_host, strict: false) libqmp = static_library('qmp', qmp_ss.sources() + genh, dependencies: qmp_ss.dependencies(), @@ -XXX,XX +XXX,XX @@ foreach m : block_mods + softmmu_mods install_dir: config_host['qemu_moddir']) endforeach -softmmu_ss.add(authz, block, chardev, crypto, io, qmp) +softmmu_ss.add(authz, blockdev, chardev, crypto, io, qmp) common_ss.add(qom, qemuutil) common_ss.add_all(when: 'CONFIG_SOFTMMU', if_true: [softmmu_ss]) diff --git a/storage-daemon/meson.build b/storage-daemon/meson.build index XXXXXXX..XXXXXXX 100644 --- a/storage-daemon/meson.build +++ b/storage-daemon/meson.build @@ -XXX,XX +XXX,XX @@ qsd_ss = ss.source_set() qsd_ss.add(files('qemu-storage-daemon.c')) -qsd_ss.add(block, chardev, qmp, qom, qemuutil) -qsd_ss.add_all(blockdev_ss) +qsd_ss.add(blockdev, chardev, qmp, qom, qemuutil) subdir('qapi') -- 2.26.2 Block exports are used by softmmu, qemu-storage-daemon, and qemu-nbd. They are not used by other programs and are not otherwise needed in libblock. Undo the recent move of blockdev-nbd.c from blockdev_ss into block_ss. Since bdrv_close_all() (libblock) calls blk_exp_close_all() (libblockdev) a stub function is required.. Make qemu-nbd.c use signal handling utility functions instead of duplicating the code. This helps because os-posix.c is in libblockdev and it depends on a qemu_system_killed() symbol that qemu-nbd.c lacks. Once we use the signal handling utility functions we also end up providing the necessary symbol. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200929125516.186715-4-stefanha@redhat.com [Fixed s/ndb/nbd/ typo in commit description as suggested by Eric Blake --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qemu-nbd.c | 25 +++++++++---------------- stubs/blk-exp-close-all.c | 7 +++++++ block/export/meson.build | 4 ++-- meson.build | 4 ++-- nbd/meson.build | 2 ++ stubs/meson.build | 1 + 6 files changed, 23 insertions(+), 20 deletions(-) create mode 100644 stubs/blk-exp-close-all.c diff --git a/qemu-nbd.c b/qemu-nbd.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-nbd.c +++ b/qemu-nbd.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qemu/cutils.h" #include "sysemu/block-backend.h" +#include "sysemu/runstate.h" /* for qemu_system_killed() prototype */ #include "block/block_int.h" #include "block/nbd.h" #include "qemu/main-loop.h" @@ -XXX,XX +XXX,XX @@ QEMU_COPYRIGHT "\n" , name); } -#ifdef CONFIG_POSIX -static void termsig_handler(int signum) +#if CONFIG_POSIX +/* + * The client thread uses SIGTERM to interrupt the server. A signal + * handler ensures that "qemu-nbd -v -c" exits with a nice status code. + */ +void qemu_system_killed(int signum, pid_t pid) { qatomic_cmpxchg(&state, RUNNING, TERMINATE); qemu_notify_event(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) const char *pid_file_name = NULL; BlockExportOptions *export_opts; -#ifdef CONFIG_POSIX - /* - * Exit gracefully on various signals, which includes SIGTERM used - * by 'qemu-nbd -v -c'. - */ - struct sigaction sa_sigterm; - memset(&sa_sigterm, 0, sizeof(sa_sigterm)); - sa_sigterm.sa_handler = termsig_handler; - sigaction(SIGTERM, &sa_sigterm, NULL); - sigaction(SIGINT, &sa_sigterm, NULL); - sigaction(SIGHUP, &sa_sigterm, NULL); - - signal(SIGPIPE, SIG_IGN); -#endif + os_setup_early_signal_handling(); + os_setup_signal_handling(); socket_init(); error_init(argv[0]); diff --git a/stubs/blk-exp-close-all.c b/stubs/blk-exp-close-all.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/stubs/blk-exp-close-all.c @@ -XXX,XX +XXX,XX @@ +#include "qemu/osdep.h" +#include "block/export.h" + +/* Only used in programs that support block exports (libblockdev.fa) */ +void blk_exp_close_all(void) +{ +} diff --git a/block/export/meson.build b/block/export/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -XXX,XX +XXX,XX @@ -block_ss.add(files('export.c')) -block_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-blk-server.c')) +blockdev_ss.add(files('export.c')) +blockdev_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-blk-server.c')) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ subdir('dump') block_ss.add(files( 'block.c', - 'blockdev-nbd.c', 'blockjob.c', 'job.c', 'qemu-io-cmds.c', @@ -XXX,XX +XXX,XX @@ subdir('block') blockdev_ss.add(files( 'blockdev.c', + 'blockdev-nbd.c', 'iothread.c', 'job-qmp.c', )) @@ -XXX,XX +XXX,XX @@ if have_tools qemu_io = executable('qemu-io', files('qemu-io.c'), dependencies: [block, qemuutil], install: true) qemu_nbd = executable('qemu-nbd', files('qemu-nbd.c'), - dependencies: [block, qemuutil], install: true) + dependencies: [blockdev, qemuutil], install: true) subdir('storage-daemon') subdir('contrib/rdmacm-mux') diff --git a/nbd/meson.build b/nbd/meson.build index XXXXXXX..XXXXXXX 100644 --- a/nbd/meson.build +++ b/nbd/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(files( 'client.c', 'common.c', +)) +blockdev_ss.add(files( 'server.c', )) diff --git a/stubs/meson.build b/stubs/meson.build index XXXXXXX..XXXXXXX 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -XXX,XX +XXX,XX @@ stub_ss.add(files('arch_type.c')) stub_ss.add(files('bdrv-next-monitor-owned.c')) stub_ss.add(files('blk-commit-all.c')) +stub_ss.add(files('blk-exp-close-all.c')) stub_ss.add(files('blockdev-close-all-bdrv-states.c')) stub_ss.add(files('change-state-handler.c')) stub_ss.add(files('cmos.c')) -- 2.26.2 Make it possible to specify the iothread where the export will run. By default the block node can be moved to other AioContexts later and the export will follow. The fixed-iothread option forces strict behavior that prevents changing AioContext while the export is active. See the QAPI docs for details. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200929125516.186715-5-stefanha@redhat.com [Fix stray '#' character in block-export.json and add missing "(since: 5.2)" as suggested by Eric Blake. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 11 ++++++++++ block/export/export.c | 31 +++++++++++++++++++++++++++- block/export/vhost-user-blk-server.c | 5 ++++- nbd/server.c | 2 -- 4 files changed, 45 insertions(+), 4 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ # export before completion is signalled. (since: 5.2; # default: false) # +# @iothread: The name of the iothread object where the export will run. The +# default is to use the thread currently associated with the +# block node. (since: 5.2) +# +# @fixed-iothread: True prevents the block node from being moved to another +# thread while the export is active. If true and @iothread is +# given, export creation fails if the block node cannot be +# moved to the iothread. The default is false. (since: 5.2) +# # Since: 4.2 ## { 'union': 'BlockExportOptions', 'base': { 'type': 'BlockExportType', 'id': 'str', + '*fixed-iothread': 'bool', + '*iothread': 'str', 'node-name': 'str', '*writable': 'bool', '*writethrough': 'bool' }, diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "sysemu/block-backend.h" +#include "sysemu/iothread.h" #include "block/export.h" #include "block/nbd.h" #include "qapi/error.h" @@ -XXX,XX +XXX,XX @@ static const BlockExportDriver *blk_exp_find_driver(BlockExportType type) BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) { + bool fixed_iothread = export->has_fixed_iothread && export->fixed_iothread; const BlockExportDriver *drv; BlockExport *exp = NULL; BlockDriverState *bs; - BlockBackend *blk; + BlockBackend *blk = NULL; AioContext *ctx; uint64_t perm; int ret; @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) ctx = bdrv_get_aio_context(bs); aio_context_acquire(ctx); + if (export->has_iothread) { + IOThread *iothread; + AioContext *new_ctx; + + iothread = iothread_by_id(export->iothread); + if (!iothread) { + error_setg(errp, "iothread \"%s\" not found", export->iothread); + goto fail; + } + + new_ctx = iothread_get_aio_context(iothread); + + ret = bdrv_try_set_aio_context(bs, new_ctx, errp); + if (ret == 0) { + aio_context_release(ctx); + aio_context_acquire(new_ctx); + ctx = new_ctx; + } else if (fixed_iothread) { + goto fail; + } + } + /* * Block exports are used for non-shared storage migration. Make sure * that BDRV_O_INACTIVE is cleared and the image is ready for write @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) } blk = blk_new(ctx, perm, BLK_PERM_ALL); + + if (!fixed_iothread) { + blk_set_allow_aio_context_change(blk, true); + } + ret = blk_insert_bs(blk, bs, errp); if (ret < 0) { goto fail; diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ static const VuDevIface vu_blk_iface = { static void blk_aio_attached(AioContext *ctx, void *opaque) { VuBlkExport *vexp = opaque; + + vexp->export.ctx = ctx; vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); } static void blk_aio_detach(void *opaque) { VuBlkExport *vexp = opaque; + vhost_user_server_detach_aio_context(&vexp->vu_server); + vexp->export.ctx = NULL; } static void @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, logical_block_size); - blk_set_allow_aio_context_change(exp->blk, true); blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); diff --git a/nbd/server.c b/nbd/server.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -XXX,XX +XXX,XX @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, return ret; } - blk_set_allow_aio_context_change(blk, true); - QTAILQ_INIT(&exp->clients); exp->name = g_strdup(arg->name); exp->description = g_strdup(arg->description); -- 2.26.2 Allow the number of queues to be configured using --export vhost-user-blk,num-queues=N. This setting should match the QEMU --device vhost-user-blk-pci,num-queues=N setting but QEMU vhost-user-blk.c lowers its own value if the vhost-user-blk backend offers fewer queues than QEMU. The vhost-user-blk-server.c code is already capable of multi-queue. All virtqueue processing runs in the same AioContext. No new locking is needed. Add the num-queues=N option and set the VIRTIO_BLK_F_MQ feature bit. Note that the feature bit only announces the presence of the num_queues configuration space field. It does not promise that there is more than 1 virtqueue, so we can set it unconditionally. I tested multi-queue by running a random read fio test with numjobs=4 on an -smp 4 guest. After the benchmark finished the guest /proc/interrupts file showed activity on all 4 virtio-blk MSI-X. The /sys/block/vda/mq/ directory shows that Linux blk-mq has 4 queues configured. An automated test is included in the next commit. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Markus Armbruster <armbru@redhat.com> Message-id: 20201001144604.559733-2-stefanha@redhat.com [Fixed accidental tab characters as suggested by Markus Armbruster --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-export.json | 10 +++++++--- block/export/vhost-user-blk-server.c | 24 ++++++++++++++++++------ 2 files changed, 25 insertions(+), 9 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -XXX,XX +XXX,XX @@ # SocketAddress types are supported. Passed fds must be UNIX domain # sockets. # @logical-block-size: Logical block size in bytes. Defaults to 512 bytes. +# @num-queues: Number of request virtqueues. Must be greater than 0. Defaults +# to 1. # # Since: 5.2 ## { 'struct': 'BlockExportOptionsVhostUserBlk', - 'data': { 'addr': 'SocketAddress', '*logical-block-size': 'size' } } + 'data': { 'addr': 'SocketAddress', + '*logical-block-size': 'size', + '*num-queues': 'uint16'} } ## # @NbdServerAddOptions: @@ -XXX,XX +XXX,XX @@ { 'union': 'BlockExportOptions', 'base': { 'type': 'BlockExportType', 'id': 'str', - '*fixed-iothread': 'bool', - '*iothread': 'str', + '*fixed-iothread': 'bool', + '*iothread': 'str', 'node-name': 'str', '*writable': 'bool', '*writethrough': 'bool' }, diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -XXX,XX +XXX,XX @@ #include "util/block-helpers.h" enum { - VHOST_USER_BLK_MAX_QUEUES = 1, + VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1, }; struct virtio_blk_inhdr { unsigned char status; @@ -XXX,XX +XXX,XX @@ static uint64_t vu_blk_get_features(VuDev *dev) 1ull << VIRTIO_BLK_F_DISCARD | 1ull << VIRTIO_BLK_F_WRITE_ZEROES | 1ull << VIRTIO_BLK_F_CONFIG_WCE | + 1ull << VIRTIO_BLK_F_MQ | 1ull << VIRTIO_F_VERSION_1 | 1ull << VIRTIO_RING_F_INDIRECT_DESC | 1ull << VIRTIO_RING_F_EVENT_IDX | @@ -XXX,XX +XXX,XX @@ static void blk_aio_detach(void *opaque) static void vu_blk_initialize_config(BlockDriverState *bs, - struct virtio_blk_config *config, uint32_t blk_size) + struct virtio_blk_config *config, + uint32_t blk_size, + uint16_t num_queues) { config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; config->blk_size = blk_size; @@ -XXX,XX +XXX,XX @@ vu_blk_initialize_config(BlockDriverState *bs, config->seg_max = 128 - 2; config->min_io_size = 1; config->opt_io_size = 1; - config->num_queues = VHOST_USER_BLK_MAX_QUEUES; + config->num_queues = num_queues; config->max_discard_sectors = 32768; config->max_discard_seg = 1; config->discard_sector_alignment = config->blk_size >> 9; @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; Error *local_err = NULL; uint64_t logical_block_size; + uint16_t num_queues = VHOST_USER_BLK_NUM_QUEUES_DEFAULT; vexp->writable = opts->writable; vexp->blkcfg.wce = 0; @@ -XXX,XX +XXX,XX @@ static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, } vexp->blk_size = logical_block_size; blk_set_guest_block_size(exp->blk, logical_block_size); + + if (vu_opts->has_num_queues) { + num_queues = vu_opts->num_queues; + } + if (num_queues == 0) { + error_setg(errp, "num-queues must be greater than 0"); + return -EINVAL; + } + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, - logical_block_size); + logical_block_size, num_queues); blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx, - VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, - errp)) { + num_queues, &vu_blk_iface, errp)) { blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, vexp); return -EADDRNOTAVAIL; -- 2.26.2 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20201001144604.559733-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/vhost-user-blk-test.c | 81 +++++++++++++++++++++++++++++-- 1 file changed, 76 insertions(+), 5 deletions(-) diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/vhost-user-blk-test.c +++ b/tests/qtest/vhost-user-blk-test.c @@ -XXX,XX +XXX,XX @@ static void pci_hotplug(void *obj, void *data, QGuestAllocator *t_alloc) qpci_unplug_acpi_device_test(qts, "drv1", PCI_SLOT_HP); } +static void multiqueue(void *obj, void *data, QGuestAllocator *t_alloc) +{ + QVirtioPCIDevice *pdev1 = obj; + QVirtioDevice *dev1 = &pdev1->vdev; + QVirtioPCIDevice *pdev8; + QVirtioDevice *dev8; + QTestState *qts = pdev1->pdev->bus->qts; + uint64_t features; + uint16_t num_queues; + + /* + * The primary device has 1 queue and VIRTIO_BLK_F_MQ is not enabled. The + * VIRTIO specification allows VIRTIO_BLK_F_MQ to be enabled when there is + * only 1 virtqueue, but --device vhost-user-blk-pci doesn't do this (which + * is also spec-compliant). + */ + features = qvirtio_get_features(dev1); + g_assert_cmpint(features & (1u << VIRTIO_BLK_F_MQ), ==, 0); + features = features & ~(QVIRTIO_F_BAD_FEATURE | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | + (1u << VIRTIO_F_NOTIFY_ON_EMPTY) | + (1u << VIRTIO_BLK_F_SCSI)); + qvirtio_set_features(dev1, features); + + /* Hotplug a secondary device with 8 queues */ + qtest_qmp_device_add(qts, "vhost-user-blk-pci", "drv1", + "{'addr': %s, 'chardev': 'char2', 'num-queues': 8}", + stringify(PCI_SLOT_HP) ".0"); + + pdev8 = virtio_pci_new(pdev1->pdev->bus, + &(QPCIAddress) { + .devfn = QPCI_DEVFN(PCI_SLOT_HP, 0) + }); + g_assert_nonnull(pdev8); + g_assert_cmpint(pdev8->vdev.device_type, ==, VIRTIO_ID_BLOCK); + + qos_object_start_hw(&pdev8->obj); + + dev8 = &pdev8->vdev; + features = qvirtio_get_features(dev8); + g_assert_cmpint(features & (1u << VIRTIO_BLK_F_MQ), + ==, + (1u << VIRTIO_BLK_F_MQ)); + features = features & ~(QVIRTIO_F_BAD_FEATURE | + (1u << VIRTIO_RING_F_INDIRECT_DESC) | + (1u << VIRTIO_F_NOTIFY_ON_EMPTY) | + (1u << VIRTIO_BLK_F_SCSI) | + (1u << VIRTIO_BLK_F_MQ)); + qvirtio_set_features(dev8, features); + + num_queues = qvirtio_config_readw(dev8, + offsetof(struct virtio_blk_config, num_queues)); + g_assert_cmpint(num_queues, ==, 8); + + qvirtio_pci_device_disable(pdev8); + qos_object_destroy(&pdev8->obj); + + /* unplug secondary disk */ + qpci_unplug_acpi_device_test(qts, "drv1", PCI_SLOT_HP); +} + /* * Check that setting the vring addr on a non-existent virtqueue does * not crash. @@ -XXX,XX +XXX,XX @@ static void quit_storage_daemon(void *qmp_test_state) g_free(qmp_test_state); } -static char *start_vhost_user_blk(GString *cmd_line, int vus_instances) +static char *start_vhost_user_blk(GString *cmd_line, int vus_instances, + int num_queues) { const char *vhost_user_blk_bin = qtest_qemu_storage_daemon_binary(); int fd, qmp_fd, i; @@ -XXX,XX +XXX,XX @@ static char *start_vhost_user_blk(GString *cmd_line, int vus_instances) g_string_append_printf(storage_daemon_command, "--blockdev driver=file,node-name=disk%d,filename=%s " "--export type=vhost-user-blk,id=disk%d,addr.type=unix,addr.path=%s," - "node-name=disk%i,writable=on ", - i, img_path, i, sock_path, i); + "node-name=disk%i,writable=on,num-queues=%d ", + i, img_path, i, sock_path, i, num_queues); g_string_append_printf(cmd_line, "-chardev socket,id=char%d,path=%s ", i + 1, sock_path); @@ -XXX,XX +XXX,XX @@ static char *start_vhost_user_blk(GString *cmd_line, int vus_instances) static void *vhost_user_blk_test_setup(GString *cmd_line, void *arg) { - start_vhost_user_blk(cmd_line, 1); + start_vhost_user_blk(cmd_line, 1, 1); return arg; } @@ -XXX,XX +XXX,XX @@ static void *vhost_user_blk_test_setup(GString *cmd_line, void *arg) static void *vhost_user_blk_hotplug_test_setup(GString *cmd_line, void *arg) { /* "-chardev socket,id=char2" is used for pci_hotplug*/ - start_vhost_user_blk(cmd_line, 2); + start_vhost_user_blk(cmd_line, 2, 1); + return arg; +} + +static void *vhost_user_blk_multiqueue_test_setup(GString *cmd_line, void *arg) +{ + start_vhost_user_blk(cmd_line, 2, 8); return arg; } @@ -XXX,XX +XXX,XX @@ static void register_vhost_user_blk_test(void) opts.before = vhost_user_blk_hotplug_test_setup; qos_add_test("hotplug", "vhost-user-blk-pci", pci_hotplug, &opts); + + opts.before = vhost_user_blk_multiqueue_test_setup; + qos_add_test("multiqueue", "vhost-user-blk-pci", multiqueue, &opts); } libqos_init(register_vhost_user_blk_test); -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> bdrv_co_block_status_above has several design problems with handling short backing files: 1. With want_zeros=true, it may return ret with BDRV_BLOCK_ZERO but without BDRV_BLOCK_ALLOCATED flag, when actually short backing file which produces these after-EOF zeros is inside requested backing sequence. 2. With want_zero=false, it may return pnum=0 prior to actual EOF, because of EOF of short backing file. Fix these things, making logic about short backing files clearer. With fixed bdrv_block_status_above we also have to improve is_zero in qcow2 code, otherwise iotest 154 will fail, because with this patch we stop to merge zeros of different types (produced by fully unallocated in the whole backing chain regions vs produced by short backing files). Note also, that this patch leaves for another day the general problem around block-status: misuse of BDRV_BLOCK_ALLOCATED as is-fs-allocated vs go-to-backing. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200924194003.22080-2-vsementsov@virtuozzo.com [Fix s/comes/come/ as suggested by Eric Blake --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 68 ++++++++++++++++++++++++++++++++++++++++----------- block/qcow2.c | 16 ++++++++++-- 2 files changed, 68 insertions(+), 16 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, int64_t *map, BlockDriverState **file) { + int ret; BlockDriverState *p; - int ret = 0; - bool first = true; + int64_t eof = 0; assert(bs != base); - for (p = bs; p != base; p = bdrv_filter_or_cow_bs(p)) { + + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { + return ret; + } + + if (ret & BDRV_BLOCK_EOF) { + eof = offset + *pnum; + } + + assert(*pnum <= bytes); + bytes = *pnum; + + for (p = bdrv_filter_or_cow_bs(bs); p != base; + p = bdrv_filter_or_cow_bs(p)) + { ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, file); if (ret < 0) { - break; + return ret; } - if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { + if (*pnum == 0) { /* - * Reading beyond the end of the file continues to read - * zeroes, but we can only widen the result to the - * unallocated length we learned from an earlier - * iteration. + * The top layer deferred to this layer, and because this layer is + * short, any zeroes that we synthesize beyond EOF behave as if they + * were allocated at this layer. + * + * We don't include BDRV_BLOCK_EOF into ret, as upper layer may be + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see + * below. */ + assert(ret & BDRV_BLOCK_EOF); *pnum = bytes; + if (file) { + *file = p; + } + ret = BDRV_BLOCK_ZERO | BDRV_BLOCK_ALLOCATED; + break; } - if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { + if (ret & BDRV_BLOCK_ALLOCATED) { + /* + * We've found the node and the status, we must break. + * + * Drop BDRV_BLOCK_EOF, as it's not for upper layer, which may be + * larger. We'll add BDRV_BLOCK_EOF if needed at function end, see + * below. + */ + ret &= ~BDRV_BLOCK_EOF; break; } - /* [offset, pnum] unallocated on this layer, which could be only - * the first part of [offset, bytes]. */ - bytes = MIN(bytes, *pnum); - first = false; + + /* + * OK, [offset, offset + *pnum) region is unallocated on this layer, + * let's continue the diving. + */ + assert(*pnum <= bytes); + bytes = *pnum; + } + + if (offset + *pnum == eof) { + ret |= BDRV_BLOCK_EOF; } + return ret; } diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) if (!bytes) { return true; } - res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); - return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; + + /* + * bdrv_block_status_above doesn't merge different types of zeros, for + * example, zeros which come from the region which is unallocated in + * the whole backing chain, and zeros which come because of a short + * backing file. So, we need a loop. + */ + do { + res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); + offset += nr; + bytes -= nr; + } while (res >= 0 && (res & BDRV_BLOCK_ZERO) && nr && bytes); + + return res >= 0 && (res & BDRV_BLOCK_ZERO) && bytes == 0; } static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> In order to reuse bdrv_common_block_status_above in bdrv_is_allocated_above, let's support include_base parameter. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20200924194003.22080-3-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/coroutines.h | 2 ++ block/io.c | 21 ++++++++++++++------- 2 files changed, 16 insertions(+), 7 deletions(-) diff --git a/block/coroutines.h b/block/coroutines.h index XXXXXXX..XXXXXXX 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -XXX,XX +XXX,XX @@ bdrv_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, int coroutine_fn bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, int generated_co_wrapper bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ early_out: int coroutine_fn bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, bool want_zero, int64_t offset, int64_t bytes, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t eof = 0; - assert(bs != base); + assert(include_base || bs != base); + assert(!include_base || base); /* Can't include NULL base */ ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); - if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED) { + if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { return ret; } @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, assert(*pnum <= bytes); bytes = *pnum; - for (p = bdrv_filter_or_cow_bs(bs); p != base; + for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base; p = bdrv_filter_or_cow_bs(p)) { ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, break; } + if (p == base) { + assert(include_base); + break; + } + /* * OK, [offset, offset + *pnum) region is unallocated on this layer, * let's continue the diving. @@ -XXX,XX +XXX,XX @@ int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file) { - return bdrv_common_block_status_above(bs, base, true, offset, bytes, + return bdrv_common_block_status_above(bs, base, false, true, offset, bytes, pnum, map, file); } @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int ret; int64_t dummy; - ret = bdrv_common_block_status_above(bs, bdrv_filter_or_cow_bs(bs), false, - offset, bytes, pnum ? pnum : &dummy, - NULL, NULL); + ret = bdrv_common_block_status_above(bs, bs, true, false, offset, + bytes, pnum ? pnum : &dummy, NULL, + NULL); if (ret < 0) { return ret; } -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to reuse bdrv_common_block_status_above in bdrv_is_allocated_above. bdrv_is_allocated_above may be called with include_base == false and still bs == base (for ex. from img_rebase()). So, support this corner case. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-4-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ bdrv_co_common_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t eof = 0; - assert(include_base || bs != base); assert(!include_base || base); /* Can't include NULL base */ + if (!include_base && bs == base) { + *pnum = bytes; + return 0; + } + ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { return ret; -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> bdrv_is_allocated_above wrongly handles short backing files: it reports after-EOF space as UNALLOCATED which is wrong, as on read the data is generated on the level of short backing file (if all overlays have unallocated areas at that place). Reusing bdrv_common_block_status_above fixes the issue and unifies code path. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-5-vsementsov@virtuozzo.com [Fix s/has/have/ as suggested by Eric Blake. Fix s/area/areas/. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 43 +++++-------------------------------------- 1 file changed, 5 insertions(+), 38 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, * at 'offset + *pnum' may return the same allocation status (in other * words, the result is not necessarily the maximum possible range); * but 'pnum' will only be 0 when end of file is reached. - * */ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, bool include_base, int64_t offset, int64_t bytes, int64_t *pnum) { - BlockDriverState *intermediate; - int ret; - int64_t n = bytes; - - assert(base || !include_base); - - intermediate = top; - while (include_base || intermediate != base) { - int64_t pnum_inter; - int64_t size_inter; - - assert(intermediate); - ret = bdrv_is_allocated(intermediate, offset, bytes, &pnum_inter); - if (ret < 0) { - return ret; - } - if (ret) { - *pnum = pnum_inter; - return 1; - } - - size_inter = bdrv_getlength(intermediate); - if (size_inter < 0) { - return size_inter; - } - if (n > pnum_inter && - (intermediate == top || offset + pnum_inter < size_inter)) { - n = pnum_inter; - } - - if (intermediate == base) { - break; - } - - intermediate = bdrv_filter_or_cow_bs(intermediate); + int ret = bdrv_common_block_status_above(top, base, include_base, false, + offset, bytes, pnum, NULL, NULL); + if (ret < 0) { + return ret; } - *pnum = n; - return 0; + return !!(ret & BDRV_BLOCK_ALLOCATED); } int coroutine_fn -- 2.26.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> These cases are fixed by previous patches around block_status and is_allocated. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-id: 20200924194003.22080-6-vsementsov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qemu-iotests/274 | 20 +++++++++++ tests/qemu-iotests/274.out | 68 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+) diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/274 +++ b/tests/qemu-iotests/274 @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('base') as base, \ iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + iotests.log('=== Testing qemu-img commit (top -> base) ===') + + create_chain() + iotests.qemu_img_log('commit', '-b', base, top) + iotests.img_info_log(base) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) + + iotests.log('=== Testing QMP active commit (top -> base) ===') + + create_chain() + with create_vm() as vm: + vm.launch() + vm.qmp_log('block-commit', device='top', base_node='base', + job_id='job0', auto_dismiss=False) + vm.run_job('job0', wait=5) + + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, base) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), base) iotests.log('== Resize tests ==') diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/274.out +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 0 read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +=== Testing qemu-img commit (top -> base) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 + +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 + +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 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image committed. + +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +Format specific information: + compat: 1.1 + compression type: zlib + lazy refcounts: false + refcount bits: 16 + corrupt: false + extended l2: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing QMP active commit (top -> base) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=2097152 lazy_refcounts=off refcount_bits=16 + +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 + +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 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +{"execute": "block-commit", "arguments": {"auto-dismiss": false, "base-node": "base", "device": "top", "job-id": "job0"}} +{"return": {}} +{"execute": "job-complete", "arguments": {"id": "job0"}} +{"return": {}} +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"data": {"device": "job0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"execute": "job-dismiss", "arguments": {"id": "job0"}} +{"return": {}} +image: TEST_IMG +file format: IMGFMT +virtual size: 1 MiB (1048576 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +backing file format: IMGFMT +Format specific information: + compat: 1.1 + compression type: zlib + lazy refcounts: false + refcount bits: 16 + corrupt: false + extended l2: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + == Resize tests == === preallocation=off === Formatting 'TEST_DIR/PID-base', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=6442450944 lazy_refcounts=off refcount_bits=16 -- 2.26.2