diff options
Diffstat (limited to 'block/bio.c')
| -rw-r--r-- | block/bio.c | 218 |
1 files changed, 148 insertions, 70 deletions
diff --git a/block/bio.c b/block/bio.c index 0093bed81c0e..bbfeb4ee2892 100644 --- a/block/bio.c +++ b/block/bio.c @@ -609,7 +609,9 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; - bio_clone_blkcg_association(bio, bio_src); + bio_clone_blkg_association(bio, bio_src); + + blkcg_bio_issue_init(bio); } EXPORT_SYMBOL(__bio_clone_fast); @@ -729,7 +731,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page } /* If we may be able to merge these biovecs, force a recount */ - if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec))) + if (bio->bi_vcnt > 1 && biovec_phys_mergeable(q, bvec - 1, bvec)) bio_clear_flag(bio, BIO_SEG_VALID); done: @@ -827,6 +829,8 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); +#define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) + /** * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to @@ -839,38 +843,35 @@ EXPORT_SYMBOL(bio_add_page); */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { - unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx; + unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; + unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; + ssize_t size, left; + unsigned len, i; size_t offset; - ssize_t size; + + /* + * Move page array up in the allocated memory for the bio vecs as far as + * possible so that we can start filling biovecs from the beginning + * without overwriting the temporary page array. + */ + BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); + pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; - idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; - /* - * Deep magic below: We need to walk the pinned pages backwards - * because we are abusing the space allocated for the bio_vecs - * for the page array. Because the bio_vecs are larger than the - * page pointers by definition this will always work. But it also - * means we can't use bio_add_page, so any changes to it's semantics - * need to be reflected here as well. - */ - bio->bi_iter.bi_size += size; - bio->bi_vcnt += nr_pages; + for (left = size, i = 0; left > 0; left -= len, i++) { + struct page *page = pages[i]; - while (idx--) { - bv[idx].bv_page = pages[idx]; - bv[idx].bv_len = PAGE_SIZE; - bv[idx].bv_offset = 0; + len = min_t(size_t, PAGE_SIZE - offset, left); + if (WARN_ON_ONCE(bio_add_page(bio, page, len, offset) != len)) + return -EINVAL; + offset = 0; } - bv[0].bv_offset += offset; - bv[0].bv_len -= offset; - bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size; - iov_iter_advance(iter, size); return 0; } @@ -1807,7 +1808,6 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); - bio->bi_iter.bi_done = 0; if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); @@ -1956,69 +1956,151 @@ EXPORT_SYMBOL(bioset_init_from_src); #ifdef CONFIG_BLK_CGROUP +/** + * bio_associate_blkg - associate a bio with the a blkg + * @bio: target bio + * @blkg: the blkg to associate + * + * This tries to associate @bio with the specified blkg. Association failure + * is handled by walking up the blkg tree. Therefore, the blkg associated can + * be anything between @blkg and the root_blkg. This situation only happens + * when a cgroup is dying and then the remaining bios will spill to the closest + * alive blkg. + * + * A reference will be taken on the @blkg and will be released when @bio is + * freed. + */ +int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) +{ + if (unlikely(bio->bi_blkg)) + return -EBUSY; + bio->bi_blkg = blkg_tryget_closest(blkg); + return 0; +} + +/** + * __bio_associate_blkg_from_css - internal blkg association function + * + * This in the core association function that all association paths rely on. + * A blkg reference is taken which is released upon freeing of the bio. + */ +static int __bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ + struct request_queue *q = bio->bi_disk->queue; + struct blkcg_gq *blkg; + int ret; + + rcu_read_lock(); + + if (!css || !css->parent) + blkg = q->root_blkg; + else + blkg = blkg_lookup_create(css_to_blkcg(css), q); + + ret = bio_associate_blkg(bio, blkg); + + rcu_read_unlock(); + return ret; +} + +/** + * bio_associate_blkg_from_css - associate a bio with a specified css + * @bio: target bio + * @css: target css + * + * Associate @bio with the blkg found by combining the css's blkg and the + * request_queue of the @bio. This falls back to the queue's root_blkg if + * the association fails with the css. + */ +int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ + if (unlikely(bio->bi_blkg)) + return -EBUSY; + return __bio_associate_blkg_from_css(bio, css); +} +EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); + #ifdef CONFIG_MEMCG /** - * bio_associate_blkcg_from_page - associate a bio with the page's blkcg + * bio_associate_blkg_from_page - associate a bio with the page's blkg * @bio: target bio * @page: the page to lookup the blkcg from * - * Associate @bio with the blkcg from @page's owning memcg. This works like - * every other associate function wrt references. + * Associate @bio with the blkg from @page's owning memcg and the respective + * request_queue. If cgroup_e_css returns NULL, fall back to the queue's + * root_blkg. + * + * Note: this must be called after bio has an associated device. */ -int bio_associate_blkcg_from_page(struct bio *bio, struct page *page) +int bio_associate_blkg_from_page(struct bio *bio, struct page *page) { - struct cgroup_subsys_state *blkcg_css; + struct cgroup_subsys_state *css; + int ret; - if (unlikely(bio->bi_css)) + if (unlikely(bio->bi_blkg)) return -EBUSY; if (!page->mem_cgroup) return 0; - blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup, - &io_cgrp_subsys); - bio->bi_css = blkcg_css; - return 0; + + rcu_read_lock(); + + css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); + + ret = __bio_associate_blkg_from_css(bio, css); + + rcu_read_unlock(); + return ret; } #endif /* CONFIG_MEMCG */ /** - * bio_associate_blkcg - associate a bio with the specified blkcg + * bio_associate_create_blkg - associate a bio with a blkg from q + * @q: request_queue where bio is going * @bio: target bio - * @blkcg_css: css of the blkcg to associate - * - * Associate @bio with the blkcg specified by @blkcg_css. Block layer will - * treat @bio as if it were issued by a task which belongs to the blkcg. * - * This function takes an extra reference of @blkcg_css which will be put - * when @bio is released. The caller must own @bio and is responsible for - * synchronizing calls to this function. + * Associate @bio with the blkg found from the bio's css and the request_queue. + * If one is not found, bio_lookup_blkg creates the blkg. This falls back to + * the queue's root_blkg if association fails. */ -int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) +int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { - if (unlikely(bio->bi_css)) - return -EBUSY; - css_get(blkcg_css); - bio->bi_css = blkcg_css; - return 0; + struct cgroup_subsys_state *css; + int ret = 0; + + /* someone has already associated this bio with a blkg */ + if (bio->bi_blkg) + return ret; + + rcu_read_lock(); + + css = blkcg_css(); + + ret = __bio_associate_blkg_from_css(bio, css); + + rcu_read_unlock(); + return ret; } -EXPORT_SYMBOL_GPL(bio_associate_blkcg); /** - * bio_associate_blkg - associate a bio with the specified blkg + * bio_reassociate_blkg - reassociate a bio with a blkg from q + * @q: request_queue where bio is going * @bio: target bio - * @blkg: the blkg to associate * - * Associate @bio with the blkg specified by @blkg. This is the queue specific - * blkcg information associated with the @bio, a reference will be taken on the - * @blkg and will be freed when the bio is freed. + * When submitting a bio, multiple recursive calls to make_request() may occur. + * This causes the initial associate done in blkcg_bio_issue_check() to be + * incorrect and reference the prior request_queue. This performs reassociation + * when this situation happens. */ -int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) +int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) { - if (unlikely(bio->bi_blkg)) - return -EBUSY; - if (!blkg_try_get(blkg)) - return -ENODEV; - bio->bi_blkg = blkg; - return 0; + if (bio->bi_blkg) { + blkg_put(bio->bi_blkg); + bio->bi_blkg = NULL; + } + + return bio_associate_create_blkg(q, bio); } /** @@ -2031,10 +2113,6 @@ void bio_disassociate_task(struct bio *bio) put_io_context(bio->bi_ioc); bio->bi_ioc = NULL; } - if (bio->bi_css) { - css_put(bio->bi_css); - bio->bi_css = NULL; - } if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; @@ -2042,16 +2120,16 @@ void bio_disassociate_task(struct bio *bio) } /** - * bio_clone_blkcg_association - clone blkcg association from src to dst bio + * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ -void bio_clone_blkcg_association(struct bio *dst, struct bio *src) +void bio_clone_blkg_association(struct bio *dst, struct bio *src) { - if (src->bi_css) - WARN_ON(bio_associate_blkcg(dst, src->bi_css)); + if (src->bi_blkg) + bio_associate_blkg(dst, src->bi_blkg); } -EXPORT_SYMBOL_GPL(bio_clone_blkcg_association); +EXPORT_SYMBOL_GPL(bio_clone_blkg_association); #endif /* CONFIG_BLK_CGROUP */ static void __init biovec_init_slabs(void) |