diff options
Diffstat (limited to 'block/copy-on-read.c')
| -rw-r--r-- | block/copy-on-read.c | 184 |
1 files changed, 172 insertions, 12 deletions
diff --git a/block/copy-on-read.c b/block/copy-on-read.c index 2816e61afe..9cad9e1b8c 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -23,11 +23,26 @@ #include "qemu/osdep.h" #include "block/block_int.h" #include "qemu/module.h" +#include "qapi/error.h" +#include "qapi/qmp/qdict.h" +#include "block/copy-on-read.h" + + +typedef struct BDRVStateCOR { + bool active; + BlockDriverState *bottom_bs; + bool chain_frozen; +} BDRVStateCOR; static int cor_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { + BlockDriverState *bottom_bs = NULL; + BDRVStateCOR *state = bs->opaque; + /* Find a bottom node name, if any */ + const char *bottom_node = qdict_get_try_str(options, "bottom"); + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, false, errp); @@ -35,6 +50,8 @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } + bs->supported_read_flags = BDRV_REQ_PREFETCH; + bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED | (BDRV_REQ_FUA & bs->file->bs->supported_write_flags); @@ -42,6 +59,44 @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags, ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & bs->file->bs->supported_zero_flags); + if (bottom_node) { + bottom_bs = bdrv_find_node(bottom_node); + if (!bottom_bs) { + error_setg(errp, "Bottom node '%s' not found", bottom_node); + qdict_del(options, "bottom"); + return -EINVAL; + } + qdict_del(options, "bottom"); + + if (!bottom_bs->drv) { + error_setg(errp, "Bottom node '%s' not opened", bottom_node); + return -EINVAL; + } + + if (bottom_bs->drv->is_filter) { + error_setg(errp, "Bottom node '%s' is a filter", bottom_node); + return -EINVAL; + } + + if (bdrv_freeze_backing_chain(bs, bottom_bs, errp) < 0) { + return -EINVAL; + } + state->chain_frozen = true; + + /* + * We do freeze the chain, so it shouldn't be removed. Still, storing a + * pointer worth bdrv_ref(). + */ + bdrv_ref(bottom_bs); + } + state->active = true; + state->bottom_bs = bottom_bs; + + /* + * We don't need to call bdrv_child_refresh_perms() now as the permissions + * will be updated later when the filter node gets its parent. + */ + return 0; } @@ -57,6 +112,17 @@ static void cor_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { + BDRVStateCOR *s = bs->opaque; + + if (!s->active) { + /* + * While the filter is being removed + */ + *nperm = 0; + *nshared = BLK_PERM_ALL; + return; + } + *nperm = perm & PERM_PASSTHROUGH; *nshared = (shared & PERM_PASSTHROUGH) | PERM_UNCHANGED; @@ -74,21 +140,67 @@ static int64_t cor_getlength(BlockDriverState *bs) } -static int coroutine_fn cor_co_preadv(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) +static int coroutine_fn cor_co_preadv_part(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, + size_t qiov_offset, + int flags) { - return bdrv_co_preadv(bs->file, offset, bytes, qiov, - flags | BDRV_REQ_COPY_ON_READ); + int64_t n; + int local_flags; + int ret; + BDRVStateCOR *state = bs->opaque; + + if (!state->bottom_bs) { + return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset, + flags | BDRV_REQ_COPY_ON_READ); + } + + while (bytes) { + local_flags = flags; + + /* In case of failure, try to copy-on-read anyway */ + ret = bdrv_is_allocated(bs->file->bs, offset, bytes, &n); + if (ret <= 0) { + ret = bdrv_is_allocated_above(bdrv_backing_chain_next(bs->file->bs), + state->bottom_bs, true, offset, + n, &n); + if (ret > 0 || ret < 0) { + local_flags |= BDRV_REQ_COPY_ON_READ; + } + /* Finish earlier if the end of a backing file has been reached */ + if (n == 0) { + break; + } + } + + /* Skip if neither read nor write are needed */ + if ((local_flags & (BDRV_REQ_PREFETCH | BDRV_REQ_COPY_ON_READ)) != + BDRV_REQ_PREFETCH) { + ret = bdrv_co_preadv_part(bs->file, offset, n, qiov, qiov_offset, + local_flags); + if (ret < 0) { + return ret; + } + } + + offset += n; + qiov_offset += n; + bytes -= n; + } + + return 0; } -static int coroutine_fn cor_co_pwritev(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) +static int coroutine_fn cor_co_pwritev_part(BlockDriverState *bs, + uint64_t offset, + uint64_t bytes, + QEMUIOVector *qiov, + size_t qiov_offset, int flags) { - - return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags); + return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset, + flags); } @@ -129,16 +241,31 @@ static void cor_lock_medium(BlockDriverState *bs, bool locked) } +static void cor_close(BlockDriverState *bs) +{ + BDRVStateCOR *s = bs->opaque; + + if (s->chain_frozen) { + s->chain_frozen = false; + bdrv_unfreeze_backing_chain(bs, s->bottom_bs); + } + + bdrv_unref(s->bottom_bs); +} + + static BlockDriver bdrv_copy_on_read = { .format_name = "copy-on-read", + .instance_size = sizeof(BDRVStateCOR), .bdrv_open = cor_open, + .bdrv_close = cor_close, .bdrv_child_perm = cor_child_perm, .bdrv_getlength = cor_getlength, - .bdrv_co_preadv = cor_co_preadv, - .bdrv_co_pwritev = cor_co_pwritev, + .bdrv_co_preadv_part = cor_co_preadv_part, + .bdrv_co_pwritev_part = cor_co_pwritev_part, .bdrv_co_pwrite_zeroes = cor_co_pwrite_zeroes, .bdrv_co_pdiscard = cor_co_pdiscard, .bdrv_co_pwritev_compressed = cor_co_pwritev_compressed, @@ -150,6 +277,39 @@ static BlockDriver bdrv_copy_on_read = { .is_filter = true, }; + +void bdrv_cor_filter_drop(BlockDriverState *cor_filter_bs) +{ + BdrvChild *child; + BlockDriverState *bs; + BDRVStateCOR *s = cor_filter_bs->opaque; + + child = bdrv_filter_child(cor_filter_bs); + if (!child) { + return; + } + bs = child->bs; + + /* Retain the BDS until we complete the graph change. */ + bdrv_ref(bs); + /* Hold a guest back from writing while permissions are being reset. */ + bdrv_drained_begin(bs); + /* Drop permissions before the graph change. */ + s->active = false; + /* unfreeze, as otherwise bdrv_replace_node() will fail */ + if (s->chain_frozen) { + s->chain_frozen = false; + bdrv_unfreeze_backing_chain(cor_filter_bs, s->bottom_bs); + } + bdrv_child_refresh_perms(cor_filter_bs, child, &error_abort); + bdrv_replace_node(cor_filter_bs, bs, &error_abort); + + bdrv_drained_end(bs); + bdrv_unref(bs); + bdrv_unref(cor_filter_bs); +} + + static void bdrv_copy_on_read_init(void) { bdrv_register(&bdrv_copy_on_read); |