diff options
Diffstat (limited to 'block/stream.c')
| -rw-r--r-- | block/stream.c | 185 |
1 files changed, 111 insertions, 74 deletions
diff --git a/block/stream.c b/block/stream.c index 236384f2f7..1fa742b0db 100644 --- a/block/stream.c +++ b/block/stream.c @@ -17,8 +17,10 @@ #include "block/blockjob_int.h" #include "qapi/error.h" #include "qapi/qmp/qerror.h" +#include "qapi/qmp/qdict.h" #include "qemu/ratelimit.h" #include "sysemu/block-backend.h" +#include "block/copy-on-read.h" enum { /* @@ -33,10 +35,11 @@ typedef struct StreamBlockJob { BlockJob common; BlockDriverState *base_overlay; /* COW overlay (stream from this) */ BlockDriverState *above_base; /* Node directly above the base */ + BlockDriverState *cor_filter_bs; + BlockDriverState *target_bs; BlockdevOnError on_error; char *backing_file_str; bool bs_read_only; - bool chain_frozen; } StreamBlockJob; static int coroutine_fn stream_populate(BlockBackend *blk, @@ -44,39 +47,28 @@ static int coroutine_fn stream_populate(BlockBackend *blk, { assert(bytes < SIZE_MAX); - return blk_co_preadv(blk, offset, bytes, NULL, - BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH); -} - -static void stream_abort(Job *job) -{ - StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); - - if (s->chain_frozen) { - BlockJob *bjob = &s->common; - bdrv_unfreeze_backing_chain(blk_bs(bjob->blk), s->above_base); - } + return blk_co_preadv(blk, offset, bytes, NULL, BDRV_REQ_PREFETCH); } static int stream_prepare(Job *job) { StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); - BlockJob *bjob = &s->common; - BlockDriverState *bs = blk_bs(bjob->blk); - BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs); + BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs); BlockDriverState *base = bdrv_filter_or_cow_bs(s->above_base); + BlockDriverState *unfiltered_base = bdrv_skip_filters(base); Error *local_err = NULL; int ret = 0; - bdrv_unfreeze_backing_chain(bs, s->above_base); - s->chain_frozen = false; + /* We should drop filter at this point, as filter hold the backing chain */ + bdrv_cor_filter_drop(s->cor_filter_bs); + s->cor_filter_bs = NULL; if (bdrv_cow_child(unfiltered_bs)) { const char *base_id = NULL, *base_fmt = NULL; - if (base) { - base_id = s->backing_file_str; - if (base->drv) { - base_fmt = base->drv->format_name; + if (unfiltered_base) { + base_id = s->backing_file_str ?: unfiltered_base->filename; + if (unfiltered_base->drv) { + base_fmt = unfiltered_base->drv->format_name; } } bdrv_set_backing_hd(unfiltered_bs, base, &local_err); @@ -94,13 +86,17 @@ static void stream_clean(Job *job) { StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); BlockJob *bjob = &s->common; - BlockDriverState *bs = blk_bs(bjob->blk); + + if (s->cor_filter_bs) { + bdrv_cor_filter_drop(s->cor_filter_bs); + s->cor_filter_bs = NULL; + } /* Reopen the image back in read-only mode if necessary */ if (s->bs_read_only) { /* Give up write permissions before making it read-only */ blk_set_perm(bjob->blk, 0, BLK_PERM_ALL, &error_abort); - bdrv_reopen_set_read_only(bs, true, NULL); + bdrv_reopen_set_read_only(s->target_bs, true, NULL); } g_free(s->backing_file_str); @@ -110,9 +106,7 @@ static int coroutine_fn stream_run(Job *job, Error **errp) { StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); BlockBackend *blk = s->common.blk; - BlockDriverState *bs = blk_bs(blk); - BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs); - bool enable_cor = !bdrv_cow_child(s->base_overlay); + BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs); int64_t len; int64_t offset = 0; uint64_t delay_ns = 0; @@ -124,21 +118,12 @@ static int coroutine_fn stream_run(Job *job, Error **errp) return 0; } - len = bdrv_getlength(bs); + len = bdrv_getlength(s->target_bs); if (len < 0) { return len; } job_progress_set_remaining(&s->common.job, len); - /* Turn on copy-on-read for the whole block device so that guest read - * requests help us make progress. Only do this when copying the entire - * backing chain since the copy-on-read operation does not take base into - * account. - */ - if (enable_cor) { - bdrv_enable_copy_on_read(bs); - } - for ( ; offset < len; offset += n) { bool copy; int ret; @@ -197,10 +182,6 @@ static int coroutine_fn stream_run(Job *job, Error **errp) } } - if (enable_cor) { - bdrv_disable_copy_on_read(bs); - } - /* Do not remove the backing file if an error was there but ignored. */ return error; } @@ -212,7 +193,6 @@ static const BlockJobDriver stream_job_driver = { .free = block_job_free, .run = stream_run, .prepare = stream_prepare, - .abort = stream_abort, .clean = stream_clean, .user_resume = block_job_user_resume, }, @@ -220,59 +200,113 @@ static const BlockJobDriver stream_job_driver = { void stream_start(const char *job_id, BlockDriverState *bs, BlockDriverState *base, const char *backing_file_str, + BlockDriverState *bottom, int creation_flags, int64_t speed, - BlockdevOnError on_error, Error **errp) + BlockdevOnError on_error, + const char *filter_node_name, + Error **errp) { StreamBlockJob *s; BlockDriverState *iter; bool bs_read_only; int basic_flags = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED; - BlockDriverState *base_overlay = bdrv_find_overlay(bs, base); + BlockDriverState *base_overlay; + BlockDriverState *cor_filter_bs = NULL; BlockDriverState *above_base; - - if (!base_overlay) { - error_setg(errp, "'%s' is not in the backing chain of '%s'", - base->node_name, bs->node_name); - return; - } - - /* - * Find the node directly above @base. @base_overlay is a COW overlay, so - * it must have a bdrv_cow_child(), but it is the immediate overlay of - * @base, so between the two there can only be filters. - */ - above_base = base_overlay; - if (bdrv_cow_bs(above_base) != base) { - above_base = bdrv_cow_bs(above_base); - while (bdrv_filter_bs(above_base) != base) { - above_base = bdrv_filter_bs(above_base); + QDict *opts; + + assert(!(base && bottom)); + assert(!(backing_file_str && bottom)); + + if (bottom) { + /* + * New simple interface. The code is written in terms of old interface + * with @base parameter (still, it doesn't freeze link to base, so in + * this mean old code is correct for new interface). So, for now, just + * emulate base_overlay and above_base. Still, when old interface + * finally removed, we should refactor code to use only "bottom", but + * not "*base*" things. + */ + assert(!bottom->drv->is_filter); + base_overlay = above_base = bottom; + } else { + base_overlay = bdrv_find_overlay(bs, base); + if (!base_overlay) { + error_setg(errp, "'%s' is not in the backing chain of '%s'", + base->node_name, bs->node_name); + return; } - } - if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) { - return; + /* + * Find the node directly above @base. @base_overlay is a COW overlay, + * so it must have a bdrv_cow_child(), but it is the immediate overlay + * of @base, so between the two there can only be filters. + */ + above_base = base_overlay; + if (bdrv_cow_bs(above_base) != base) { + above_base = bdrv_cow_bs(above_base); + while (bdrv_filter_bs(above_base) != base) { + above_base = bdrv_filter_bs(above_base); + } + } } /* Make sure that the image is opened in read-write mode */ bs_read_only = bdrv_is_read_only(bs); if (bs_read_only) { - if (bdrv_reopen_set_read_only(bs, false, errp) != 0) { - bs_read_only = false; - goto fail; + int ret; + /* Hold the chain during reopen */ + if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) { + return; + } + + ret = bdrv_reopen_set_read_only(bs, false, errp); + + /* failure, or cor-filter will hold the chain */ + bdrv_unfreeze_backing_chain(bs, above_base); + + if (ret < 0) { + return; } } - /* Prevent concurrent jobs trying to modify the graph structure here, we - * already have our own plans. Also don't allow resize as the image size is - * queried only at the job start and then cached. */ - s = block_job_create(job_id, &stream_job_driver, NULL, bs, - basic_flags | BLK_PERM_GRAPH_MOD, + opts = qdict_new(); + + qdict_put_str(opts, "driver", "copy-on-read"); + qdict_put_str(opts, "file", bdrv_get_node_name(bs)); + /* Pass the base_overlay node name as 'bottom' to COR driver */ + qdict_put_str(opts, "bottom", base_overlay->node_name); + if (filter_node_name) { + qdict_put_str(opts, "node-name", filter_node_name); + } + + cor_filter_bs = bdrv_insert_node(bs, opts, BDRV_O_RDWR, errp); + if (!cor_filter_bs) { + goto fail; + } + + if (!filter_node_name) { + cor_filter_bs->implicit = true; + } + + s = block_job_create(job_id, &stream_job_driver, NULL, cor_filter_bs, + BLK_PERM_CONSISTENT_READ, basic_flags | BLK_PERM_WRITE, speed, creation_flags, NULL, NULL, errp); if (!s) { goto fail; } + /* + * Prevent concurrent jobs trying to modify the graph structure here, we + * already have our own plans. Also don't allow resize as the image size is + * queried only at the job start and then cached. + */ + if (block_job_add_bdrv(&s->common, "active node", bs, 0, + basic_flags | BLK_PERM_WRITE, &error_abort)) { + goto fail; + } + /* Block all intermediate nodes between bs and base, because they will * disappear from the chain after this operation. The streaming job reads * every block only once, assuming that it doesn't change, so forbid writes @@ -293,8 +327,9 @@ void stream_start(const char *job_id, BlockDriverState *bs, s->base_overlay = base_overlay; s->above_base = above_base; s->backing_file_str = g_strdup(backing_file_str); + s->cor_filter_bs = cor_filter_bs; + s->target_bs = bs; s->bs_read_only = bs_read_only; - s->chain_frozen = true; s->on_error = on_error; trace_stream_start(bs, base, s); @@ -302,8 +337,10 @@ void stream_start(const char *job_id, BlockDriverState *bs, return; fail: + if (cor_filter_bs) { + bdrv_cor_filter_drop(cor_filter_bs); + } if (bs_read_only) { bdrv_reopen_set_read_only(bs, true, NULL); } - bdrv_unfreeze_backing_chain(bs, above_base); } |