1 | The following changes since commit 64175afc695c0672876fbbfc31b299c86d562cb4: | 1 | The following changes since commit 36f87b4513373b3cd79c87c9197d17face95d4ac: |
---|---|---|---|
2 | 2 | ||
3 | arm_gicv3: Fix ICC_BPR1 reset value when EL3 not implemented (2017-06-07 17:21:44 +0100) | 3 | Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.10-20170630' into staging (2017-06-30 11:58:49 +0100) |
4 | 4 | ||
5 | are available in the git repository at: | 5 | are available in the git repository at: |
6 | 6 | ||
7 | git://github.com/codyprime/qemu-kvm-jtc.git tags/block-pull-request | 7 | git://github.com/famz/qemu.git tags/block-pull-request |
8 | 8 | ||
9 | for you to fetch changes up to 56faeb9bb6872b3f926b3b3e0452a70beea10af2: | 9 | for you to fetch changes up to c61e684e44272f2acb2bef34cf2aa234582a73a9: |
10 | 10 | ||
11 | block/gluster.c: Handle qdict_array_entries() failure (2017-06-09 08:41:29 -0400) | 11 | block: Exploit BDRV_BLOCK_EOF for larger zero blocks (2017-06-30 21:48:06 +0800) |
12 | 12 | ||
13 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
14 | Gluster patch | 14 | |
15 | Hi Peter, | ||
16 | |||
17 | Here are Eric Blake's enhancement to block layer API. Thanks! | ||
18 | |||
15 | ---------------------------------------------------------------- | 19 | ---------------------------------------------------------------- |
16 | 20 | ||
17 | Peter Maydell (1): | 21 | Eric Blake (2): |
18 | block/gluster.c: Handle qdict_array_entries() failure | 22 | block: Add BDRV_BLOCK_EOF to bdrv_get_block_status() |
23 | block: Exploit BDRV_BLOCK_EOF for larger zero blocks | ||
19 | 24 | ||
20 | block/gluster.c | 3 +-- | 25 | block/io.c | 42 +++++++++++++++++++++++++++++++++--------- |
21 | 1 file changed, 1 insertion(+), 2 deletions(-) | 26 | include/block/block.h | 2 ++ |
27 | tests/qemu-iotests/154 | 4 ---- | ||
28 | tests/qemu-iotests/154.out | 12 ++++++------ | ||
29 | 4 files changed, 41 insertions(+), 19 deletions(-) | ||
22 | 30 | ||
23 | -- | 31 | -- |
24 | 2.9.3 | 32 | 2.9.4 |
25 | 33 | ||
26 | 34 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Eric Blake <eblake@redhat.com> | ||
1 | 2 | ||
3 | Just as the block layer already sets BDRV_BLOCK_ALLOCATED as a | ||
4 | shortcut for subsequent operations, there are also some optimizations | ||
5 | that are made easier if we can quickly tell that *pnum will advance | ||
6 | us to the end of a file, via a new BDRV_BLOCK_EOF which gets set | ||
7 | by the block layer. | ||
8 | |||
9 | This just plumbs up the new bit; subsequent patches will make use | ||
10 | of it. | ||
11 | |||
12 | Signed-off-by: Eric Blake <eblake@redhat.com> | ||
13 | Message-Id: <20170505021500.19315-2-eblake@redhat.com> | ||
14 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
15 | Signed-off-by: Fam Zheng <famz@redhat.com> | ||
16 | --- | ||
17 | block/io.c | 15 +++++++++++---- | ||
18 | include/block/block.h | 2 ++ | ||
19 | 2 files changed, 13 insertions(+), 4 deletions(-) | ||
20 | |||
21 | diff --git a/block/io.c b/block/io.c | ||
22 | index XXXXXXX..XXXXXXX 100644 | ||
23 | --- a/block/io.c | ||
24 | +++ b/block/io.c | ||
25 | @@ -XXX,XX +XXX,XX @@ typedef struct BdrvCoGetBlockStatusData { | ||
26 | * Drivers not implementing the functionality are assumed to not support | ||
27 | * backing files, hence all their sectors are reported as allocated. | ||
28 | * | ||
29 | - * If 'sector_num' is beyond the end of the disk image the return value is 0 | ||
30 | - * and 'pnum' is set to 0. | ||
31 | + * If 'sector_num' is beyond the end of the disk image the return value is | ||
32 | + * BDRV_BLOCK_EOF and 'pnum' is set to 0. | ||
33 | * | ||
34 | * 'pnum' is set to the number of sectors (including and immediately following | ||
35 | * the specified sector) that are known to be in the same | ||
36 | * allocated/unallocated state. | ||
37 | * | ||
38 | * 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes | ||
39 | - * beyond the end of the disk image it will be clamped. | ||
40 | + * beyond the end of the disk image it will be clamped; if 'pnum' is set to | ||
41 | + * the end of the image, then the returned value will include BDRV_BLOCK_EOF. | ||
42 | * | ||
43 | * If returned value is positive and BDRV_BLOCK_OFFSET_VALID bit is set, 'file' | ||
44 | * points to the BDS which the sector range is allocated in. | ||
45 | @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, | ||
46 | |||
47 | if (sector_num >= total_sectors) { | ||
48 | *pnum = 0; | ||
49 | - return 0; | ||
50 | + return BDRV_BLOCK_EOF; | ||
51 | } | ||
52 | |||
53 | n = total_sectors - sector_num; | ||
54 | @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, | ||
55 | if (!bs->drv->bdrv_co_get_block_status) { | ||
56 | *pnum = nb_sectors; | ||
57 | ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED; | ||
58 | + if (sector_num + nb_sectors == total_sectors) { | ||
59 | + ret |= BDRV_BLOCK_EOF; | ||
60 | + } | ||
61 | if (bs->drv->protocol_name) { | ||
62 | ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE); | ||
63 | } | ||
64 | @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, | ||
65 | |||
66 | out: | ||
67 | bdrv_dec_in_flight(bs); | ||
68 | + if (ret >= 0 && sector_num + *pnum == total_sectors) { | ||
69 | + ret |= BDRV_BLOCK_EOF; | ||
70 | + } | ||
71 | return ret; | ||
72 | } | ||
73 | |||
74 | diff --git a/include/block/block.h b/include/block/block.h | ||
75 | index XXXXXXX..XXXXXXX 100644 | ||
76 | --- a/include/block/block.h | ||
77 | +++ b/include/block/block.h | ||
78 | @@ -XXX,XX +XXX,XX @@ typedef struct HDGeometry { | ||
79 | * BDRV_BLOCK_OFFSET_VALID: an associated offset exists for accessing raw data | ||
80 | * BDRV_BLOCK_ALLOCATED: the content of the block is determined by this | ||
81 | * layer (short for DATA || ZERO), set by block layer | ||
82 | + * BDRV_BLOCK_EOF: the returned pnum covers through end of file for this layer | ||
83 | * | ||
84 | * Internal flag: | ||
85 | * BDRV_BLOCK_RAW: used internally to indicate that the request was | ||
86 | @@ -XXX,XX +XXX,XX @@ typedef struct HDGeometry { | ||
87 | #define BDRV_BLOCK_OFFSET_VALID 0x04 | ||
88 | #define BDRV_BLOCK_RAW 0x08 | ||
89 | #define BDRV_BLOCK_ALLOCATED 0x10 | ||
90 | +#define BDRV_BLOCK_EOF 0x20 | ||
91 | #define BDRV_BLOCK_OFFSET_MASK BDRV_SECTOR_MASK | ||
92 | |||
93 | typedef QSIMPLEQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue; | ||
94 | -- | ||
95 | 2.9.4 | ||
96 | |||
97 | diff view generated by jsdifflib |
1 | From: Peter Maydell <peter.maydell@linaro.org> | 1 | From: Eric Blake <eblake@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | In qemu_gluster_parse_json(), the call to qdict_array_entries() | 3 | When we have a BDS with unallocated clusters, but asking the status |
4 | could return a negative error code, which we were ignoring | 4 | of its underlying bs->file or backing layer encounters an end-of-file |
5 | because we assigned the result to an unsigned variable. | 5 | condition, we know that the rest of the unallocated area will read as |
6 | Fix this by using the 'int' type instead, which matches the | 6 | zeroes. However, pre-patch, this required two separate calls to |
7 | return type of qdict_array_entries() and also the type | 7 | bdrv_get_block_status(), as the first call stops at the point where |
8 | we use for the loop enumeration variable 'i'. | 8 | the underlying file ends. Thanks to BDRV_BLOCK_EOF, we can now widen |
9 | the results of the primary status if the secondary status already | ||
10 | includes BDRV_BLOCK_ZERO. | ||
9 | 11 | ||
10 | (Spotted by Coverity, CID 1360960.) | 12 | In turn, this fixes a TODO mentioned in iotest 154, where we can now |
13 | see that all sectors in a partial cluster at the end of a file read | ||
14 | as zero when coupling the shorter backing file's status along with our | ||
15 | knowledge that the remaining sectors came from an unallocated cluster. | ||
11 | 16 | ||
12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 17 | Also, note that the loop in bdrv_co_get_block_status_above() had an |
13 | Reviewed-by: Eric Blake <eblake@redhat.com> | 18 | inefficent exit: in cases where the active layer sets BDRV_BLOCK_ZERO |
14 | Reviewed-by: Jeff Cody <jcody@redhat.com> | 19 | but does NOT set BDRV_BLOCK_ALLOCATED (namely, where we know we read |
15 | Message-id: 1496682098-1540-1-git-send-email-peter.maydell@linaro.org | 20 | zeroes merely because our unallocated clusters lie beyond the backing |
16 | Signed-off-by: Jeff Cody <jcody@redhat.com> | 21 | file's shorter length), we still ended up probing the backing layer |
22 | even though we already had a good answer. | ||
23 | |||
24 | Signed-off-by: Eric Blake <eblake@redhat.com> | ||
25 | Message-Id: <20170505021500.19315-3-eblake@redhat.com> | ||
26 | Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> | ||
27 | Signed-off-by: Fam Zheng <famz@redhat.com> | ||
17 | --- | 28 | --- |
18 | block/gluster.c | 3 +-- | 29 | block/io.c | 27 ++++++++++++++++++++++----- |
19 | 1 file changed, 1 insertion(+), 2 deletions(-) | 30 | tests/qemu-iotests/154 | 4 ---- |
31 | tests/qemu-iotests/154.out | 12 ++++++------ | ||
32 | 3 files changed, 28 insertions(+), 15 deletions(-) | ||
20 | 33 | ||
21 | diff --git a/block/gluster.c b/block/gluster.c | 34 | diff --git a/block/io.c b/block/io.c |
22 | index XXXXXXX..XXXXXXX 100644 | 35 | index XXXXXXX..XXXXXXX 100644 |
23 | --- a/block/gluster.c | 36 | --- a/block/io.c |
24 | +++ b/block/gluster.c | 37 | +++ b/block/io.c |
25 | @@ -XXX,XX +XXX,XX @@ static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf, | 38 | @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, |
26 | Error *local_err = NULL; | 39 | /* Ignore errors. This is just providing extra information, it |
27 | char *str = NULL; | 40 | * is useful but not necessary. |
28 | const char *ptr; | 41 | */ |
29 | - size_t num_servers; | 42 | - if (!file_pnum) { |
30 | - int i, type; | 43 | - /* !file_pnum indicates an offset at or beyond the EOF; it is |
31 | + int i, type, num_servers; | 44 | - * perfectly valid for the format block driver to point to such |
32 | 45 | - * offsets, so catch it and mark everything as zero */ | |
33 | /* create opts info from runtime_json_opts list */ | 46 | + if (ret2 & BDRV_BLOCK_EOF && |
34 | opts = qemu_opts_create(&runtime_json_opts, NULL, 0, &error_abort); | 47 | + (!file_pnum || ret2 & BDRV_BLOCK_ZERO)) { |
48 | + /* | ||
49 | + * It is valid for the format block driver to read | ||
50 | + * beyond the end of the underlying file's current | ||
51 | + * size; such areas read as zero. | ||
52 | + */ | ||
53 | ret |= BDRV_BLOCK_ZERO; | ||
54 | } else { | ||
55 | /* Limit request to the range reported by the protocol driver */ | ||
56 | @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, | ||
57 | { | ||
58 | BlockDriverState *p; | ||
59 | int64_t ret = 0; | ||
60 | + bool first = true; | ||
61 | |||
62 | assert(bs != base); | ||
63 | for (p = bs; p != base; p = backing_bs(p)) { | ||
64 | ret = bdrv_co_get_block_status(p, sector_num, nb_sectors, pnum, file); | ||
65 | - if (ret < 0 || ret & BDRV_BLOCK_ALLOCATED) { | ||
66 | + if (ret < 0) { | ||
67 | + break; | ||
68 | + } | ||
69 | + if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { | ||
70 | + /* | ||
71 | + * Reading beyond the end of the file continues to read | ||
72 | + * zeroes, but we can only widen the result to the | ||
73 | + * unallocated length we learned from an earlier | ||
74 | + * iteration. | ||
75 | + */ | ||
76 | + *pnum = nb_sectors; | ||
77 | + } | ||
78 | + if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { | ||
79 | break; | ||
80 | } | ||
81 | /* [sector_num, pnum] unallocated on this layer, which could be only | ||
82 | * the first part of [sector_num, nb_sectors]. */ | ||
83 | nb_sectors = MIN(nb_sectors, *pnum); | ||
84 | + first = false; | ||
85 | } | ||
86 | return ret; | ||
87 | } | ||
88 | diff --git a/tests/qemu-iotests/154 b/tests/qemu-iotests/154 | ||
89 | index XXXXXXX..XXXXXXX 100755 | ||
90 | --- a/tests/qemu-iotests/154 | ||
91 | +++ b/tests/qemu-iotests/154 | ||
92 | @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "alloc $size 2048" "$TEST_IMG" | _filter_qemu_io | ||
93 | $QEMU_IMG map --output=json "$TEST_IMG" | _filter_qemu_img_map | ||
94 | |||
95 | # Repeat with backing file holding unallocated cluster. | ||
96 | -# TODO: Note that this forces an allocation, because we aren't yet able to | ||
97 | -# quickly detect that reads beyond EOF of the backing file are always zero | ||
98 | CLUSTER_SIZE=2048 TEST_IMG="$TEST_IMG.base" _make_test_img $((size + 1024)) | ||
99 | |||
100 | # Write at the front: sector-wise, the request is: | ||
101 | @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "alloc $size 2048" "$TEST_IMG" | _filter_qemu_io | ||
102 | $QEMU_IMG map --output=json "$TEST_IMG" | _filter_qemu_img_map | ||
103 | |||
104 | # Repeat with backing file holding zero'd cluster | ||
105 | -# TODO: Note that this forces an allocation, because we aren't yet able to | ||
106 | -# quickly detect that reads beyond EOF of the backing file are always zero | ||
107 | $QEMU_IO -c "write -z $size 512" "$TEST_IMG.base" | _filter_qemu_io | ||
108 | |||
109 | # Write at the front: sector-wise, the request is: | ||
110 | diff --git a/tests/qemu-iotests/154.out b/tests/qemu-iotests/154.out | ||
111 | index XXXXXXX..XXXXXXX 100644 | ||
112 | --- a/tests/qemu-iotests/154.out | ||
113 | +++ b/tests/qemu-iotests/154.out | ||
114 | @@ -XXX,XX +XXX,XX @@ wrote 512/512 bytes at offset 134217728 | ||
115 | 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
116 | 2048/2048 bytes allocated at offset 128 MiB | ||
117 | [{ "start": 0, "length": 134217728, "depth": 1, "zero": true, "data": false}, | ||
118 | -{ "start": 134217728, "length": 2048, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] | ||
119 | +{ "start": 134217728, "length": 2048, "depth": 0, "zero": true, "data": false}] | ||
120 | Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134219776 backing_file=TEST_DIR/t.IMGFMT.base | ||
121 | wrote 512/512 bytes at offset 134219264 | ||
122 | 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
123 | 2048/2048 bytes allocated at offset 128 MiB | ||
124 | [{ "start": 0, "length": 134217728, "depth": 1, "zero": true, "data": false}, | ||
125 | -{ "start": 134217728, "length": 2048, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] | ||
126 | +{ "start": 134217728, "length": 2048, "depth": 0, "zero": true, "data": false}] | ||
127 | Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134219776 backing_file=TEST_DIR/t.IMGFMT.base | ||
128 | wrote 1024/1024 bytes at offset 134218240 | ||
129 | 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
130 | 2048/2048 bytes allocated at offset 128 MiB | ||
131 | [{ "start": 0, "length": 134217728, "depth": 1, "zero": true, "data": false}, | ||
132 | -{ "start": 134217728, "length": 2048, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] | ||
133 | +{ "start": 134217728, "length": 2048, "depth": 0, "zero": true, "data": false}] | ||
134 | Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134219776 backing_file=TEST_DIR/t.IMGFMT.base | ||
135 | wrote 2048/2048 bytes at offset 134217728 | ||
136 | 2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
137 | @@ -XXX,XX +XXX,XX @@ wrote 512/512 bytes at offset 134217728 | ||
138 | 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
139 | 2048/2048 bytes allocated at offset 128 MiB | ||
140 | [{ "start": 0, "length": 134217728, "depth": 1, "zero": true, "data": false}, | ||
141 | -{ "start": 134217728, "length": 2048, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] | ||
142 | +{ "start": 134217728, "length": 2048, "depth": 0, "zero": true, "data": false}] | ||
143 | Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134219776 backing_file=TEST_DIR/t.IMGFMT.base | ||
144 | wrote 512/512 bytes at offset 134219264 | ||
145 | 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
146 | 2048/2048 bytes allocated at offset 128 MiB | ||
147 | [{ "start": 0, "length": 134217728, "depth": 1, "zero": true, "data": false}, | ||
148 | -{ "start": 134217728, "length": 2048, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] | ||
149 | +{ "start": 134217728, "length": 2048, "depth": 0, "zero": true, "data": false}] | ||
150 | Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134219776 backing_file=TEST_DIR/t.IMGFMT.base | ||
151 | wrote 1024/1024 bytes at offset 134218240 | ||
152 | 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
153 | 2048/2048 bytes allocated at offset 128 MiB | ||
154 | [{ "start": 0, "length": 134217728, "depth": 1, "zero": true, "data": false}, | ||
155 | -{ "start": 134217728, "length": 2048, "depth": 0, "zero": false, "data": true, "offset": OFFSET}] | ||
156 | +{ "start": 134217728, "length": 2048, "depth": 0, "zero": true, "data": false}] | ||
157 | Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134219776 backing_file=TEST_DIR/t.IMGFMT.base | ||
158 | wrote 2048/2048 bytes at offset 134217728 | ||
159 | 2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) | ||
35 | -- | 160 | -- |
36 | 2.9.3 | 161 | 2.9.4 |
37 | 162 | ||
38 | 163 | diff view generated by jsdifflib |