aboutsummaryrefslogtreecommitdiff
path: root/block/io.c
diff options
context:
space:
mode:
authorVladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>2020-09-24 22:39:59 +0300
committerStefan Hajnoczi <stefanha@redhat.com>2020-10-23 13:42:16 +0100
commit67c095c8b8097748edf6c4521d8eb6cfc4d2a0ef (patch)
treeb9a2410d1edd19c8cc46d0f051997da707e1e583 /block/io.c
parentd9b495f9c6a943c9bbd50f7469efb645c23009c3 (diff)
downloadqemu-67c095c8b8097748edf6c4521d8eb6cfc4d2a0ef.zip
qemu-67c095c8b8097748edf6c4521d8eb6cfc4d2a0ef.tar.gz
qemu-67c095c8b8097748edf6c4521d8eb6cfc4d2a0ef.tar.bz2
block/io: fix bdrv_co_block_status_above
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>
Diffstat (limited to 'block/io.c')
-rw-r--r--block/io.c68
1 files changed, 54 insertions, 14 deletions
diff --git a/block/io.c b/block/io.c
index 54f0968..a718d50 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2350,34 +2350,74 @@ 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;
}