diff options
Diffstat (limited to 'block/io.c')
| -rw-r--r-- | block/io.c | 68 |
1 files changed, 65 insertions, 3 deletions
diff --git a/block/io.c b/block/io.c index a19942718b..99ee182ca4 100644 --- a/block/io.c +++ b/block/io.c @@ -1883,6 +1883,9 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, return -ENOTSUP; } + /* Invalidate the cached block-status data range if this write overlaps */ + bdrv_bsc_invalidate_range(bs, offset, bytes); + assert(alignment % bs->bl.request_alignment == 0); head = offset % alignment; tail = (offset + bytes) % alignment; @@ -2447,9 +2450,65 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset; if (bs->drv->bdrv_co_block_status) { - ret = bs->drv->bdrv_co_block_status(bs, want_zero, aligned_offset, - aligned_bytes, pnum, &local_map, - &local_file); + /* + * Use the block-status cache only for protocol nodes: Format + * drivers are generally quick to inquire the status, but protocol + * drivers often need to get information from outside of qemu, so + * we do not have control over the actual implementation. There + * have been cases where inquiring the status took an unreasonably + * long time, and we can do nothing in qemu to fix it. + * This is especially problematic for images with large data areas, + * because finding the few holes in them and giving them special + * treatment does not gain much performance. Therefore, we try to + * cache the last-identified data region. + * + * Second, limiting ourselves to protocol nodes allows us to assume + * the block status for data regions to be DATA | OFFSET_VALID, and + * that the host offset is the same as the guest offset. + * + * Note that it is possible that external writers zero parts of + * the cached regions without the cache being invalidated, and so + * we may report zeroes as data. This is not catastrophic, + * however, because reporting zeroes as data is fine. + */ + if (QLIST_EMPTY(&bs->children) && + bdrv_bsc_is_data(bs, aligned_offset, pnum)) + { + ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID; + local_file = bs; + local_map = aligned_offset; + } else { + ret = bs->drv->bdrv_co_block_status(bs, want_zero, aligned_offset, + aligned_bytes, pnum, &local_map, + &local_file); + + /* + * Note that checking QLIST_EMPTY(&bs->children) is also done when + * the cache is queried above. Technically, we do not need to check + * it here; the worst that can happen is that we fill the cache for + * non-protocol nodes, and then it is never used. However, filling + * the cache requires an RCU update, so double check here to avoid + * such an update if possible. + */ + if (ret == (BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID) && + QLIST_EMPTY(&bs->children)) + { + /* + * When a protocol driver reports BLOCK_OFFSET_VALID, the + * returned local_map value must be the same as the offset we + * have passed (aligned_offset), and local_bs must be the node + * itself. + * Assert this, because we follow this rule when reading from + * the cache (see the `local_file = bs` and + * `local_map = aligned_offset` assignments above), and the + * result the cache delivers must be the same as the driver + * would deliver. + */ + assert(local_file == bs); + assert(local_map == aligned_offset); + bdrv_bsc_fill(bs, aligned_offset, *pnum); + } + } } else { /* Default code for filters */ @@ -3002,6 +3061,9 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, return 0; } + /* Invalidate the cached block-status data range if this discard overlaps */ + bdrv_bsc_invalidate_range(bs, offset, bytes); + /* Discard is advisory, but some devices track and coalesce * unaligned requests, so we must pass everything down rather than * round here. Still, most devices will just silently ignore |