diff options
Diffstat (limited to 'block/bio.c')
-rw-r--r-- | block/bio.c | 2324 |
1 files changed, 960 insertions, 1364 deletions
diff --git a/block/bio.c b/block/bio.c index 67bba12d273b..b9642a41f286 100644 --- a/block/bio.c +++ b/block/bio.c @@ -15,28 +15,54 @@ #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/cgroup.h> -#include <linux/blk-cgroup.h> +#include <linux/highmem.h> +#include <linux/sched/sysctl.h> +#include <linux/blk-crypto.h> +#include <linux/xarray.h> #include <trace/events/block.h> #include "blk.h" #include "blk-rq-qos.h" +#include "blk-cgroup.h" -/* - * Test patch to inline a certain number of bi_io_vec's inside the bio - * itself, to shrink a bio data allocation from two mempool calls to one - */ -#define BIO_INLINE_VECS 4 +#define ALLOC_CACHE_THRESHOLD 16 +#define ALLOC_CACHE_MAX 256 -/* - * if you change this list, also change bvec_alloc or things will - * break badly! cannot be bigger than what you can fit into an - * unsigned short - */ -#define BV(x, n) { .nr_vecs = x, .name = "biovec-"#n } -static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = { - BV(1, 1), BV(4, 4), BV(16, 16), BV(64, 64), BV(128, 128), BV(BIO_MAX_PAGES, max), +struct bio_alloc_cache { + struct bio *free_list; + struct bio *free_list_irq; + unsigned int nr; + unsigned int nr_irq; +}; + +static struct biovec_slab { + int nr_vecs; + char *name; + struct kmem_cache *slab; +} bvec_slabs[] __read_mostly = { + { .nr_vecs = 16, .name = "biovec-16" }, + { .nr_vecs = 64, .name = "biovec-64" }, + { .nr_vecs = 128, .name = "biovec-128" }, + { .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" }, }; -#undef BV + +static struct biovec_slab *biovec_slab(unsigned short nr_vecs) +{ + switch (nr_vecs) { + /* smaller bios use inline vecs */ + case 5 ... 16: + return &bvec_slabs[0]; + case 17 ... 64: + return &bvec_slabs[1]; + case 65 ... 128: + return &bvec_slabs[2]; + case 129 ... BIO_MAX_VECS: + return &bvec_slabs[3]; + default: + BUG(); + return NULL; + } +} /* * fs_bio_set is the bio_set containing bio and iovec memory pools used by @@ -55,207 +81,161 @@ struct bio_slab { char name[8]; }; static DEFINE_MUTEX(bio_slab_lock); -static struct bio_slab *bio_slabs; -static unsigned int bio_slab_nr, bio_slab_max; +static DEFINE_XARRAY(bio_slabs); -static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) +static struct bio_slab *create_bio_slab(unsigned int size) { - unsigned int sz = sizeof(struct bio) + extra_size; - struct kmem_cache *slab = NULL; - struct bio_slab *bslab, *new_bio_slabs; - unsigned int new_bio_slab_max; - unsigned int i, entry = -1; + struct bio_slab *bslab = kzalloc(sizeof(*bslab), GFP_KERNEL); - mutex_lock(&bio_slab_lock); + if (!bslab) + return NULL; - i = 0; - while (i < bio_slab_nr) { - bslab = &bio_slabs[i]; + snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size); + bslab->slab = kmem_cache_create(bslab->name, size, + ARCH_KMALLOC_MINALIGN, + SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL); + if (!bslab->slab) + goto fail_alloc_slab; - if (!bslab->slab && entry == -1) - entry = i; - else if (bslab->slab_size == sz) { - slab = bslab->slab; - bslab->slab_ref++; - break; - } - i++; - } + bslab->slab_ref = 1; + bslab->slab_size = size; - if (slab) - goto out_unlock; - - if (bio_slab_nr == bio_slab_max && entry == -1) { - new_bio_slab_max = bio_slab_max << 1; - new_bio_slabs = krealloc(bio_slabs, - new_bio_slab_max * sizeof(struct bio_slab), - GFP_KERNEL); - if (!new_bio_slabs) - goto out_unlock; - bio_slab_max = new_bio_slab_max; - bio_slabs = new_bio_slabs; - } - if (entry == -1) - entry = bio_slab_nr++; + if (!xa_err(xa_store(&bio_slabs, size, bslab, GFP_KERNEL))) + return bslab; - bslab = &bio_slabs[entry]; + kmem_cache_destroy(bslab->slab); - snprintf(bslab->name, sizeof(bslab->name), "bio-%d", entry); - slab = kmem_cache_create(bslab->name, sz, ARCH_KMALLOC_MINALIGN, - SLAB_HWCACHE_ALIGN, NULL); - if (!slab) - goto out_unlock; +fail_alloc_slab: + kfree(bslab); + return NULL; +} - bslab->slab = slab; - bslab->slab_ref = 1; - bslab->slab_size = sz; -out_unlock: +static inline unsigned int bs_bio_slab_size(struct bio_set *bs) +{ + return bs->front_pad + sizeof(struct bio) + bs->back_pad; +} + +static struct kmem_cache *bio_find_or_create_slab(struct bio_set *bs) +{ + unsigned int size = bs_bio_slab_size(bs); + struct bio_slab *bslab; + + mutex_lock(&bio_slab_lock); + bslab = xa_load(&bio_slabs, size); + if (bslab) + bslab->slab_ref++; + else + bslab = create_bio_slab(size); mutex_unlock(&bio_slab_lock); - return slab; + + if (bslab) + return bslab->slab; + return NULL; } static void bio_put_slab(struct bio_set *bs) { struct bio_slab *bslab = NULL; - unsigned int i; + unsigned int slab_size = bs_bio_slab_size(bs); mutex_lock(&bio_slab_lock); - for (i = 0; i < bio_slab_nr; i++) { - if (bs->bio_slab == bio_slabs[i].slab) { - bslab = &bio_slabs[i]; - break; - } - } - + bslab = xa_load(&bio_slabs, slab_size); if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n")) goto out; + WARN_ON_ONCE(bslab->slab != bs->bio_slab); + WARN_ON(!bslab->slab_ref); if (--bslab->slab_ref) goto out; + xa_erase(&bio_slabs, slab_size); + kmem_cache_destroy(bslab->slab); - bslab->slab = NULL; + kfree(bslab); out: mutex_unlock(&bio_slab_lock); } -unsigned int bvec_nr_vecs(unsigned short idx) -{ - return bvec_slabs[--idx].nr_vecs; -} - -void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx) +void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs) { - if (!idx) - return; - idx--; + BUG_ON(nr_vecs > BIO_MAX_VECS); - BIO_BUG_ON(idx >= BVEC_POOL_NR); - - if (idx == BVEC_POOL_MAX) { + if (nr_vecs == BIO_MAX_VECS) mempool_free(bv, pool); - } else { - struct biovec_slab *bvs = bvec_slabs + idx; + else if (nr_vecs > BIO_INLINE_VECS) + kmem_cache_free(biovec_slab(nr_vecs)->slab, bv); +} - kmem_cache_free(bvs->slab, bv); - } +/* + * Make the first allocation restricted and don't dump info on allocation + * failures, since we'll fall back to the mempool in case of failure. + */ +static inline gfp_t bvec_alloc_gfp(gfp_t gfp) +{ + return (gfp & ~(__GFP_DIRECT_RECLAIM | __GFP_IO)) | + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; } -struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx, - mempool_t *pool) +struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs, + gfp_t gfp_mask) { - struct bio_vec *bvl; + struct biovec_slab *bvs = biovec_slab(*nr_vecs); - /* - * see comment near bvec_array define! - */ - switch (nr) { - case 1: - *idx = 0; - break; - case 2 ... 4: - *idx = 1; - break; - case 5 ... 16: - *idx = 2; - break; - case 17 ... 64: - *idx = 3; - break; - case 65 ... 128: - *idx = 4; - break; - case 129 ... BIO_MAX_PAGES: - *idx = 5; - break; - default: + if (WARN_ON_ONCE(!bvs)) return NULL; - } /* - * idx now points to the pool we want to allocate from. only the - * 1-vec entry pool is mempool backed. + * Upgrade the nr_vecs request to take full advantage of the allocation. + * We also rely on this in the bvec_free path. */ - if (*idx == BVEC_POOL_MAX) { -fallback: - bvl = mempool_alloc(pool, gfp_mask); - } else { - struct biovec_slab *bvs = bvec_slabs + *idx; - gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO); + *nr_vecs = bvs->nr_vecs; - /* - * Make this allocation restricted and don't dump info on - * allocation failures, since we'll fallback to the mempool - * in case of failure. - */ - __gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; + /* + * Try a slab allocation first for all smaller allocations. If that + * fails and __GFP_DIRECT_RECLAIM is set retry with the mempool. + * The mempool is sized to handle up to BIO_MAX_VECS entries. + */ + if (*nr_vecs < BIO_MAX_VECS) { + struct bio_vec *bvl; - /* - * Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM - * is set, retry with the 1-entry mempool - */ - bvl = kmem_cache_alloc(bvs->slab, __gfp_mask); - if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) { - *idx = BVEC_POOL_MAX; - goto fallback; - } + bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask)); + if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM)) + return bvl; + *nr_vecs = BIO_MAX_VECS; } - (*idx)++; - return bvl; + return mempool_alloc(pool, gfp_mask); } void bio_uninit(struct bio *bio) { - bio_disassociate_blkg(bio); +#ifdef CONFIG_BLK_CGROUP + if (bio->bi_blkg) { + blkg_put(bio->bi_blkg); + bio->bi_blkg = NULL; + } +#endif + if (bio_integrity(bio)) + bio_integrity_free(bio); + + bio_crypt_free_ctx(bio); } EXPORT_SYMBOL(bio_uninit); static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; - void *p; - - bio_uninit(bio); - - if (bs) { - bvec_free(&bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio)); + void *p = bio; - /* - * If we have front padding, adjust the bio pointer before freeing - */ - p = bio; - p -= bs->front_pad; + WARN_ON_ONCE(!bs); - mempool_free(p, &bs->bio_pool); - } else { - /* Bio was allocated by bio_kmalloc() */ - kfree(bio); - } + bio_uninit(bio); + bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs); + mempool_free(p - bs->front_pad, &bs->bio_pool); } /* @@ -263,21 +243,53 @@ static void bio_free(struct bio *bio) * they must remember to pair any call to bio_init() with bio_uninit() * when IO has completed, or when the bio is released. */ -void bio_init(struct bio *bio, struct bio_vec *table, - unsigned short max_vecs) -{ - memset(bio, 0, sizeof(*bio)); +void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, + unsigned short max_vecs, blk_opf_t opf) +{ + bio->bi_next = NULL; + bio->bi_bdev = bdev; + bio->bi_opf = opf; + bio->bi_flags = 0; + bio->bi_ioprio = 0; + bio->bi_status = 0; + bio->bi_iter.bi_sector = 0; + bio->bi_iter.bi_size = 0; + bio->bi_iter.bi_idx = 0; + bio->bi_iter.bi_bvec_done = 0; + bio->bi_end_io = NULL; + bio->bi_private = NULL; +#ifdef CONFIG_BLK_CGROUP + bio->bi_blkg = NULL; + bio->bi_issue.value = 0; + if (bdev) + bio_associate_blkg(bio); +#ifdef CONFIG_BLK_CGROUP_IOCOST + bio->bi_iocost_cost = 0; +#endif +#endif +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + bio->bi_crypt_context = NULL; +#endif +#ifdef CONFIG_BLK_DEV_INTEGRITY + bio->bi_integrity = NULL; +#endif + bio->bi_vcnt = 0; + atomic_set(&bio->__bi_remaining, 1); atomic_set(&bio->__bi_cnt, 1); + bio->bi_cookie = BLK_QC_T_NONE; - bio->bi_io_vec = table; bio->bi_max_vecs = max_vecs; + bio->bi_io_vec = table; + bio->bi_pool = NULL; } EXPORT_SYMBOL(bio_init); /** * bio_reset - reinitialize a bio * @bio: bio to reset + * @bdev: block device to use the bio for + * @opf: operation and flags for bio * * Description: * After calling bio_reset(), @bio will be in the same state as a freshly @@ -285,15 +297,15 @@ EXPORT_SYMBOL(bio_init); * preserved are the ones that are initialized by bio_alloc_bioset(). See * comment in struct bio. */ -void bio_reset(struct bio *bio) +void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf) { - unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS); - bio_uninit(bio); - memset(bio, 0, BIO_RESET_BYTES); - bio->bi_flags = flags; atomic_set(&bio->__bi_remaining, 1); + bio->bi_bdev = bdev; + if (bio->bi_bdev) + bio_associate_blkg(bio); + bio->bi_opf = opf; } EXPORT_SYMBOL(bio_reset); @@ -301,7 +313,7 @@ static struct bio *__bio_chain_endio(struct bio *bio) { struct bio *parent = bio->bi_private; - if (!parent->bi_status) + if (bio->bi_status && !parent->bi_status) parent->bi_status = bio->bi_status; bio_put(bio); return parent; @@ -315,7 +327,7 @@ static void bio_chain_endio(struct bio *bio) /** * bio_chain - chain bio completions * @bio: the target bio - * @parent: the @bio's parent bio + * @parent: the parent bio of @bio * * The caller won't have a bi_end_io called when @bio completes - instead, * @parent's bi_end_io won't be called until both @parent and @bio have @@ -333,6 +345,20 @@ void bio_chain(struct bio *bio, struct bio *parent) } EXPORT_SYMBOL(bio_chain); +struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, + unsigned int nr_pages, blk_opf_t opf, gfp_t gfp) +{ + struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp); + + if (bio) { + bio_chain(bio, new); + submit_bio(bio); + } + + return new; +} +EXPORT_SYMBOL_GPL(blk_next_bio); + static void bio_alloc_rescue(struct work_struct *work) { struct bio_set *bs = container_of(work, struct bio_set, rescue_work); @@ -346,7 +372,7 @@ static void bio_alloc_rescue(struct work_struct *work) if (!bio) break; - generic_make_request(bio); + submit_bio_noacct(bio); } } @@ -387,130 +413,165 @@ static void punt_bios_to_rescuer(struct bio_set *bs) queue_work(bs->rescue_workqueue, &bs->rescue_work); } +static void bio_alloc_irq_cache_splice(struct bio_alloc_cache *cache) +{ + unsigned long flags; + + /* cache->free_list must be empty */ + if (WARN_ON_ONCE(cache->free_list)) + return; + + local_irq_save(flags); + cache->free_list = cache->free_list_irq; + cache->free_list_irq = NULL; + cache->nr += cache->nr_irq; + cache->nr_irq = 0; + local_irq_restore(flags); +} + +static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, + unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp, + struct bio_set *bs) +{ + struct bio_alloc_cache *cache; + struct bio *bio; + + cache = per_cpu_ptr(bs->cache, get_cpu()); + if (!cache->free_list) { + if (READ_ONCE(cache->nr_irq) >= ALLOC_CACHE_THRESHOLD) + bio_alloc_irq_cache_splice(cache); + if (!cache->free_list) { + put_cpu(); + return NULL; + } + } + bio = cache->free_list; + cache->free_list = bio->bi_next; + cache->nr--; + put_cpu(); + + bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs, opf); + bio->bi_pool = bs; + return bio; +} + /** * bio_alloc_bioset - allocate a bio for I/O + * @bdev: block device to allocate the bio for (can be %NULL) + * @nr_vecs: number of bvecs to pre-allocate + * @opf: operation and flags for bio * @gfp_mask: the GFP_* mask given to the slab allocator - * @nr_iovecs: number of iovecs to pre-allocate * @bs: the bio_set to allocate from. * - * Description: - * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is - * backed by the @bs's mempool. + * Allocate a bio from the mempools in @bs. * - * When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will - * always be able to allocate a bio. This is due to the mempool guarantees. - * To make this work, callers must never allocate more than 1 bio at a time - * from this pool. Callers that need to allocate more than 1 bio must always - * submit the previously allocated bio for IO before attempting to allocate - * a new one. Failure to do so can cause deadlocks under memory pressure. + * If %__GFP_DIRECT_RECLAIM is set then bio_alloc will always be able to + * allocate a bio. This is due to the mempool guarantees. To make this work, + * callers must never allocate more than 1 bio at a time from the general pool. + * Callers that need to allocate more than 1 bio must always submit the + * previously allocated bio for IO before attempting to allocate a new one. + * Failure to do so can cause deadlocks under memory pressure. * - * Note that when running under generic_make_request() (i.e. any block - * driver), bios are not submitted until after you return - see the code in - * generic_make_request() that converts recursion into iteration, to prevent - * stack overflows. + * Note that when running under submit_bio_noacct() (i.e. any block driver), + * bios are not submitted until after you return - see the code in + * submit_bio_noacct() that converts recursion into iteration, to prevent + * stack overflows. * - * This would normally mean allocating multiple bios under - * generic_make_request() would be susceptible to deadlocks, but we have - * deadlock avoidance code that resubmits any blocked bios from a rescuer - * thread. + * This would normally mean allocating multiple bios under submit_bio_noacct() + * would be susceptible to deadlocks, but we have + * deadlock avoidance code that resubmits any blocked bios from a rescuer + * thread. * - * However, we do not guarantee forward progress for allocations from other - * mempools. Doing multiple allocations from the same mempool under - * generic_make_request() should be avoided - instead, use bio_set's front_pad - * for per bio allocations. + * However, we do not guarantee forward progress for allocations from other + * mempools. Doing multiple allocations from the same mempool under + * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad + * for per bio allocations. * - * RETURNS: - * Pointer to new bio on success, NULL on failure. + * Returns: Pointer to new bio on success, NULL on failure. */ -struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, +struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, + blk_opf_t opf, gfp_t gfp_mask, struct bio_set *bs) { gfp_t saved_gfp = gfp_mask; - unsigned front_pad; - unsigned inline_vecs; - struct bio_vec *bvl = NULL; struct bio *bio; void *p; - if (!bs) { - if (nr_iovecs > UIO_MAXIOV) - return NULL; - - p = kmalloc(sizeof(struct bio) + - nr_iovecs * sizeof(struct bio_vec), - gfp_mask); - front_pad = 0; - inline_vecs = nr_iovecs; - } else { - /* should not use nobvec bioset for nr_iovecs > 0 */ - if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && - nr_iovecs > 0)) - return NULL; - /* - * generic_make_request() converts recursion to iteration; this - * means if we're running beneath it, any bios we allocate and - * submit will not be submitted (and thus freed) until after we - * return. - * - * This exposes us to a potential deadlock if we allocate - * multiple bios from the same bio_set() while running - * underneath generic_make_request(). If we were to allocate - * multiple bios (say a stacking block driver that was splitting - * bios), we would deadlock if we exhausted the mempool's - * reserve. - * - * We solve this, and guarantee forward progress, with a rescuer - * workqueue per bio_set. If we go to allocate and there are - * bios on current->bio_list, we first try the allocation - * without __GFP_DIRECT_RECLAIM; if that fails, we punt those - * bios we would be blocking to the rescuer workqueue before - * we retry with the original gfp_flags. - */ - - if (current->bio_list && - (!bio_list_empty(¤t->bio_list[0]) || - !bio_list_empty(¤t->bio_list[1])) && - bs->rescue_workqueue) - gfp_mask &= ~__GFP_DIRECT_RECLAIM; + /* should not use nobvec bioset for nr_vecs > 0 */ + if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0)) + return NULL; - p = mempool_alloc(&bs->bio_pool, gfp_mask); - if (!p && gfp_mask != saved_gfp) { - punt_bios_to_rescuer(bs); - gfp_mask = saved_gfp; - p = mempool_alloc(&bs->bio_pool, gfp_mask); + if (opf & REQ_ALLOC_CACHE) { + if (bs->cache && nr_vecs <= BIO_INLINE_VECS) { + bio = bio_alloc_percpu_cache(bdev, nr_vecs, opf, + gfp_mask, bs); + if (bio) + return bio; + /* + * No cached bio available, bio returned below marked with + * REQ_ALLOC_CACHE to particpate in per-cpu alloc cache. + */ + } else { + opf &= ~REQ_ALLOC_CACHE; } - - front_pad = bs->front_pad; - inline_vecs = BIO_INLINE_VECS; } + /* + * submit_bio_noacct() converts recursion to iteration; this means if + * we're running beneath it, any bios we allocate and submit will not be + * submitted (and thus freed) until after we return. + * + * This exposes us to a potential deadlock if we allocate multiple bios + * from the same bio_set() while running underneath submit_bio_noacct(). + * If we were to allocate multiple bios (say a stacking block driver + * that was splitting bios), we would deadlock if we exhausted the + * mempool's reserve. + * + * We solve this, and guarantee forward progress, with a rescuer + * workqueue per bio_set. If we go to allocate and there are bios on + * current->bio_list, we first try the allocation without + * __GFP_DIRECT_RECLAIM; if that fails, we punt those bios we would be + * blocking to the rescuer workqueue before we retry with the original + * gfp_flags. + */ + if (current->bio_list && + (!bio_list_empty(¤t->bio_list[0]) || + !bio_list_empty(¤t->bio_list[1])) && + bs->rescue_workqueue) + gfp_mask &= ~__GFP_DIRECT_RECLAIM; + + p = mempool_alloc(&bs->bio_pool, gfp_mask); + if (!p && gfp_mask != saved_gfp) { + punt_bios_to_rescuer(bs); + gfp_mask = saved_gfp; + p = mempool_alloc(&bs->bio_pool, gfp_mask); + } if (unlikely(!p)) return NULL; + if (!mempool_is_saturated(&bs->bio_pool)) + opf &= ~REQ_ALLOC_CACHE; - bio = p + front_pad; - bio_init(bio, NULL, 0); - - if (nr_iovecs > inline_vecs) { - unsigned long idx = 0; + bio = p + bs->front_pad; + if (nr_vecs > BIO_INLINE_VECS) { + struct bio_vec *bvl = NULL; - bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool); + bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask); if (!bvl && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; - bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool); + bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask); } - if (unlikely(!bvl)) goto err_free; - bio->bi_flags |= idx << BVEC_POOL_OFFSET; - } else if (nr_iovecs) { - bvl = bio->bi_inline_vecs; + bio_init(bio, bdev, bvl, nr_vecs, opf); + } else if (nr_vecs) { + bio_init(bio, bdev, bio->bi_inline_vecs, BIO_INLINE_VECS, opf); + } else { + bio_init(bio, bdev, NULL, 0, opf); } bio->bi_pool = bs; - bio->bi_max_vecs = nr_iovecs; - bio->bi_io_vec = bvl; return bio; err_free: @@ -519,147 +580,363 @@ err_free: } EXPORT_SYMBOL(bio_alloc_bioset); +/** + * bio_kmalloc - kmalloc a bio + * @nr_vecs: number of bio_vecs to allocate + * @gfp_mask: the GFP_* mask given to the slab allocator + * + * Use kmalloc to allocate a bio (including bvecs). The bio must be initialized + * using bio_init() before use. To free a bio returned from this function use + * kfree() after calling bio_uninit(). A bio returned from this function can + * be reused by calling bio_uninit() before calling bio_init() again. + * + * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this + * function are not backed by a mempool can fail. Do not use this function + * for allocations in the file system I/O path. + * + * Returns: Pointer to new bio on success, NULL on failure. + */ +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) +{ + struct bio *bio; + + if (nr_vecs > UIO_MAXIOV) + return NULL; + return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); +} +EXPORT_SYMBOL(bio_kmalloc); + void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) { - unsigned long flags; struct bio_vec bv; struct bvec_iter iter; - __bio_for_each_segment(bv, bio, iter, start) { - char *data = bvec_kmap_irq(&bv, &flags); - memset(data, 0, bv.bv_len); - flush_dcache_page(bv.bv_page); - bvec_kunmap_irq(data, &flags); - } + __bio_for_each_segment(bv, bio, iter, start) + memzero_bvec(&bv); } EXPORT_SYMBOL(zero_fill_bio_iter); /** - * bio_put - release a reference to a bio - * @bio: bio to release reference to + * bio_truncate - truncate the bio to small size of @new_size + * @bio: the bio to be truncated + * @new_size: new size for truncating the bio * * Description: - * Put a reference to a &struct bio, either one you have gotten with - * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it. - **/ -void bio_put(struct bio *bio) + * Truncate the bio to new size of @new_size. If bio_op(bio) is + * REQ_OP_READ, zero the truncated part. This function should only + * be used for handling corner cases, such as bio eod. + */ +static void bio_truncate(struct bio *bio, unsigned new_size) { - if (!bio_flagged(bio, BIO_REFFED)) - bio_free(bio); - else { - BIO_BUG_ON(!atomic_read(&bio->__bi_cnt)); + struct bio_vec bv; + struct bvec_iter iter; + unsigned int done = 0; + bool truncated = false; - /* - * last put frees it - */ - if (atomic_dec_and_test(&bio->__bi_cnt)) - bio_free(bio); - } -} -EXPORT_SYMBOL(bio_put); + if (new_size >= bio->bi_iter.bi_size) + return; -int bio_phys_segments(struct request_queue *q, struct bio *bio) -{ - if (unlikely(!bio_flagged(bio, BIO_SEG_VALID))) - blk_recount_segments(q, bio); + if (bio_op(bio) != REQ_OP_READ) + goto exit; + + bio_for_each_segment(bv, bio, iter) { + if (done + bv.bv_len > new_size) { + unsigned offset; + + if (!truncated) + offset = new_size - done; + else + offset = 0; + zero_user(bv.bv_page, bv.bv_offset + offset, + bv.bv_len - offset); + truncated = true; + } + done += bv.bv_len; + } - return bio->bi_phys_segments; + exit: + /* + * Don't touch bvec table here and make it really immutable, since + * fs bio user has to retrieve all pages via bio_for_each_segment_all + * in its .end_bio() callback. + * + * It is enough to truncate bio by updating .bi_size since we can make + * correct bvec with the updated .bi_size for drivers. + */ + bio->bi_iter.bi_size = new_size; } /** - * __bio_clone_fast - clone a bio that shares the original bio's biovec - * @bio: destination bio - * @bio_src: bio to clone + * guard_bio_eod - truncate a BIO to fit the block device + * @bio: bio to truncate * - * Clone a &bio. Caller will own the returned bio, but not - * the actual data it points to. Reference count of returned - * bio will be one. + * This allows us to do IO even on the odd last sectors of a device, even if the + * block size is some multiple of the physical sector size. * - * Caller must ensure that @bio_src is not freed before @bio. + * We'll just truncate the bio to the size of the device, and clear the end of + * the buffer head manually. Truly out-of-range accesses will turn into actual + * I/O errors, this only handles the "we need to be able to do I/O at the final + * sector" case. */ -void __bio_clone_fast(struct bio *bio, struct bio *bio_src) +void guard_bio_eod(struct bio *bio) { - BUG_ON(bio->bi_pool && BVEC_POOL_IDX(bio)); + sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); + + if (!maxsector) + return; /* - * most users will be overriding ->bi_disk with a new target, - * so we don't set nor calculate new physical/hw segment counts here + * If the *whole* IO is past the end of the device, + * let it through, and the IO layer will turn it into + * an EIO. */ - bio->bi_disk = bio_src->bi_disk; - bio->bi_partno = bio_src->bi_partno; + if (unlikely(bio->bi_iter.bi_sector >= maxsector)) + return; + + maxsector -= bio->bi_iter.bi_sector; + if (likely((bio->bi_iter.bi_size >> 9) <= maxsector)) + return; + + bio_truncate(bio, maxsector << 9); +} + +static int __bio_alloc_cache_prune(struct bio_alloc_cache *cache, + unsigned int nr) +{ + unsigned int i = 0; + struct bio *bio; + + while ((bio = cache->free_list) != NULL) { + cache->free_list = bio->bi_next; + cache->nr--; + bio_free(bio); + if (++i == nr) + break; + } + return i; +} + +static void bio_alloc_cache_prune(struct bio_alloc_cache *cache, + unsigned int nr) +{ + nr -= __bio_alloc_cache_prune(cache, nr); + if (!READ_ONCE(cache->free_list)) { + bio_alloc_irq_cache_splice(cache); + __bio_alloc_cache_prune(cache, nr); + } +} + +static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node) +{ + struct bio_set *bs; + + bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead); + if (bs->cache) { + struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu); + + bio_alloc_cache_prune(cache, -1U); + } + return 0; +} + +static void bio_alloc_cache_destroy(struct bio_set *bs) +{ + int cpu; + + if (!bs->cache) + return; + + cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); + for_each_possible_cpu(cpu) { + struct bio_alloc_cache *cache; + + cache = per_cpu_ptr(bs->cache, cpu); + bio_alloc_cache_prune(cache, -1U); + } + free_percpu(bs->cache); + bs->cache = NULL; +} + +static inline void bio_put_percpu_cache(struct bio *bio) +{ + struct bio_alloc_cache *cache; + + cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu()); + if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) { + put_cpu(); + bio_free(bio); + return; + } + + bio_uninit(bio); + + if ((bio->bi_opf & REQ_POLLED) && !WARN_ON_ONCE(in_interrupt())) { + bio->bi_next = cache->free_list; + bio->bi_bdev = NULL; + cache->free_list = bio; + cache->nr++; + } else { + unsigned long flags; + + local_irq_save(flags); + bio->bi_next = cache->free_list_irq; + cache->free_list_irq = bio; + cache->nr_irq++; + local_irq_restore(flags); + } + put_cpu(); +} + +/** + * bio_put - release a reference to a bio + * @bio: bio to release reference to + * + * Description: + * Put a reference to a &struct bio, either one you have gotten with + * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it. + **/ +void bio_put(struct bio *bio) +{ + if (unlikely(bio_flagged(bio, BIO_REFFED))) { + BUG_ON(!atomic_read(&bio->__bi_cnt)); + if (!atomic_dec_and_test(&bio->__bi_cnt)) + return; + } + if (bio->bi_opf & REQ_ALLOC_CACHE) + bio_put_percpu_cache(bio); + else + bio_free(bio); +} +EXPORT_SYMBOL(bio_put); + +static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) +{ bio_set_flag(bio, BIO_CLONED); - if (bio_flagged(bio_src, BIO_THROTTLED)) - bio_set_flag(bio, BIO_THROTTLED); - bio->bi_opf = bio_src->bi_opf; bio->bi_ioprio = bio_src->bi_ioprio; - bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter = bio_src->bi_iter; - bio->bi_io_vec = bio_src->bi_io_vec; - bio_clone_blkg_association(bio, bio_src); - blkcg_bio_issue_init(bio); + if (bio->bi_bdev) { + if (bio->bi_bdev == bio_src->bi_bdev && + bio_flagged(bio_src, BIO_REMAPPED)) + bio_set_flag(bio, BIO_REMAPPED); + bio_clone_blkg_association(bio, bio_src); + } + + if (bio_crypt_clone(bio, bio_src, gfp) < 0) + return -ENOMEM; + if (bio_integrity(bio_src) && + bio_integrity_clone(bio, bio_src, gfp) < 0) + return -ENOMEM; + return 0; } -EXPORT_SYMBOL(__bio_clone_fast); /** - * bio_clone_fast - clone a bio that shares the original bio's biovec - * @bio: bio to clone - * @gfp_mask: allocation priority - * @bs: bio_set to allocate from + * bio_alloc_clone - clone a bio that shares the original bio's biovec + * @bdev: block_device to clone onto + * @bio_src: bio to clone from + * @gfp: allocation priority + * @bs: bio_set to allocate from + * + * Allocate a new bio that is a clone of @bio_src. The caller owns the returned + * bio, but not the actual data it points to. * - * Like __bio_clone_fast, only also allocates the returned bio + * The caller must ensure that the return bio is not freed before @bio_src. */ -struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs) +struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, + gfp_t gfp, struct bio_set *bs) { - struct bio *b; + struct bio *bio; - b = bio_alloc_bioset(gfp_mask, 0, bs); - if (!b) + bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs); + if (!bio) return NULL; - __bio_clone_fast(b, bio); + if (__bio_clone(bio, bio_src, gfp) < 0) { + bio_put(bio); + return NULL; + } + bio->bi_io_vec = bio_src->bi_io_vec; - if (bio_integrity(bio)) { - int ret; + return bio; +} +EXPORT_SYMBOL(bio_alloc_clone); - ret = bio_integrity_clone(b, bio, gfp_mask); +/** + * bio_init_clone - clone a bio that shares the original bio's biovec + * @bdev: block_device to clone onto + * @bio: bio to clone into + * @bio_src: bio to clone from + * @gfp: allocation priority + * + * Initialize a new bio in caller provided memory that is a clone of @bio_src. + * The caller owns the returned bio, but not the actual data it points to. + * + * The caller must ensure that @bio_src is not freed before @bio. + */ +int bio_init_clone(struct block_device *bdev, struct bio *bio, + struct bio *bio_src, gfp_t gfp) +{ + int ret; - if (ret < 0) { - bio_put(b); - return NULL; - } - } + bio_init(bio, bdev, bio_src->bi_io_vec, 0, bio_src->bi_opf); + ret = __bio_clone(bio, bio_src, gfp); + if (ret) + bio_uninit(bio); + return ret; +} +EXPORT_SYMBOL(bio_init_clone); - return b; +/** + * bio_full - check if the bio is full + * @bio: bio to check + * @len: length of one segment to be added + * + * Return true if @bio is full and one segment with @len bytes can't be + * added to the bio, otherwise return false + */ +static inline bool bio_full(struct bio *bio, unsigned len) +{ + if (bio->bi_vcnt >= bio->bi_max_vecs) + return true; + if (bio->bi_iter.bi_size > UINT_MAX - len) + return true; + return false; } -EXPORT_SYMBOL(bio_clone_fast); -static inline bool page_is_mergeable(const struct bio_vec *bv, - struct page *page, unsigned int len, unsigned int off, - bool *same_page) +static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, + unsigned int len, unsigned int off, bool *same_page) { - phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + - bv->bv_offset + bv->bv_len - 1; + size_t bv_end = bv->bv_offset + bv->bv_len; + phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1; phys_addr_t page_addr = page_to_phys(page); if (vec_end_addr + 1 != page_addr + off) return false; if (xen_domain() && !xen_biovec_phys_mergeable(bv, page)) return false; + if (!zone_device_pages_have_same_pgmap(bv->bv_page, page)) + return false; *same_page = ((vec_end_addr & PAGE_MASK) == page_addr); - if (!*same_page && pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page) - return false; + if (!*same_page) { + if (IS_ENABLED(CONFIG_KMSAN)) + return false; + if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE) + return false; + } + + bv->bv_len += len; return true; } /* - * Check if the @page can be added to the current segment(@bv), and make - * sure to call it only if page_is_mergeable(@bv, @page) is true + * Try to merge a page into a segment, while obeying the hardware segment + * size limit. This is not for normal read/write bios, but for passthrough + * or Zone Append operations that we can't split. */ -static bool can_add_page_to_seg(struct request_queue *q, - struct bio_vec *bv, struct page *page, unsigned len, - unsigned offset) +bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, + struct page *page, unsigned len, unsigned offset, + bool *same_page) { unsigned long mask = queue_segment_boundary(q); phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset; @@ -667,129 +944,120 @@ static bool can_add_page_to_seg(struct request_queue *q, if ((addr1 | mask) != (addr2 | mask)) return false; - - if (bv->bv_len + len > queue_max_segment_size(q)) + if (len > queue_max_segment_size(q) - bv->bv_len) return false; - - return true; + return bvec_try_merge_page(bv, page, len, offset, same_page); } /** - * __bio_add_pc_page - attempt to add page to passthrough bio - * @q: the target queue - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset - * @put_same_page: put the page if it is same with last added page - * - * Attempt to add a page to the bio_vec maplist. This can fail for a - * number of reasons, such as the bio being full or target block device - * limitations. The target block device must allow bio's up to PAGE_SIZE, - * so it is always possible to add a single page to an empty bio. + * bio_add_hw_page - attempt to add a page to a bio with hw constraints + * @q: the target queue + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * @max_sectors: maximum number of sectors that can be added + * @same_page: return if the segment has been merged inside the same page * - * This should only be used by passthrough bios. + * Add a page to a bio while respecting the hardware max_sectors, max_segment + * and gap limitations. */ -static int __bio_add_pc_page(struct request_queue *q, struct bio *bio, +int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, - bool put_same_page) + unsigned int max_sectors, bool *same_page) { - struct bio_vec *bvec; - bool same_page = false; + unsigned int max_size = max_sectors << SECTOR_SHIFT; - /* - * cloned bio must not modify vec list - */ - if (unlikely(bio_flagged(bio, BIO_CLONED))) + if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; - if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q)) + len = min3(len, max_size, queue_max_segment_size(q)); + if (len > max_size - bio->bi_iter.bi_size) return 0; if (bio->bi_vcnt > 0) { - bvec = &bio->bi_io_vec[bio->bi_vcnt - 1]; - - if (page == bvec->bv_page && - offset == bvec->bv_offset + bvec->bv_len) { - if (put_same_page) - put_page(page); - bvec->bv_len += len; - goto done; + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + + if (bvec_try_merge_hw_page(q, bv, page, len, offset, + same_page)) { + bio->bi_iter.bi_size += len; + return len; } + if (bio->bi_vcnt >= + min(bio->bi_max_vecs, queue_max_segments(q))) + return 0; + /* - * If the queue doesn't support SG gaps and adding this - * offset would create a gap, disallow it. + * If the queue doesn't support SG gaps and adding this segment + * would create a gap, disallow it. */ - if (bvec_gap_to_prev(q, bvec, offset)) + if (bvec_gap_to_prev(&q->limits, bv, offset)) return 0; - - if (page_is_mergeable(bvec, page, len, offset, &same_page) && - can_add_page_to_seg(q, bvec, page, len, offset)) { - bvec->bv_len += len; - goto done; - } } - if (bio_full(bio, len)) - return 0; - - if (bio->bi_phys_segments >= queue_max_segments(q)) - return 0; - - bvec = &bio->bi_io_vec[bio->bi_vcnt]; - bvec->bv_page = page; - bvec->bv_len = len; - bvec->bv_offset = offset; + bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, offset); bio->bi_vcnt++; - done: bio->bi_iter.bi_size += len; - bio->bi_phys_segments = bio->bi_vcnt; - bio_set_flag(bio, BIO_SEG_VALID); return len; } +/** + * bio_add_pc_page - attempt to add page to passthrough bio + * @q: the target queue + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * + * Attempt to add a page to the bio_vec maplist. This can fail for a + * number of reasons, such as the bio being full or target block device + * limitations. The target block device must allow bio's up to PAGE_SIZE, + * so it is always possible to add a single page to an empty bio. + * + * This should only be used by passthrough bios. + */ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { - return __bio_add_pc_page(q, bio, page, len, offset, false); + bool same_page = false; + return bio_add_hw_page(q, bio, page, len, offset, + queue_max_hw_sectors(q), &same_page); } EXPORT_SYMBOL(bio_add_pc_page); /** - * __bio_try_merge_page - try appending data to an existing bvec. + * bio_add_zone_append_page - attempt to add page to zone-append bio * @bio: destination bio - * @page: start page to add - * @len: length of the data to add - * @off: offset of the data relative to @page - * @same_page: return if the segment has been merged inside the same page - * - * Try to add the data at @page + @off to the last bvec of @bio. This is a - * a useful optimisation for file systems with a block size smaller than the - * page size. + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset * - * Warn if (@len, @off) crosses pages in case that @same_page is true. + * Attempt to add a page to the bio_vec maplist of a bio that will be submitted + * for a zone-append request. This can fail for a number of reasons, such as the + * bio being full or the target block device is not a zoned block device or + * other limitations of the target block device. The target block device must + * allow bio's up to PAGE_SIZE, so it is always possible to add a single page + * to an empty bio. * - * Return %true on success or %false on failure. + * Returns: number of bytes added to the bio, or 0 in case of a failure. */ -bool __bio_try_merge_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int off, bool *same_page) +int bio_add_zone_append_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) { - if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) - return false; + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + bool same_page = false; - if (bio->bi_vcnt > 0) { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND)) + return 0; - if (page_is_mergeable(bv, page, len, off, same_page)) { - bv->bv_len += len; - bio->bi_iter.bi_size += len; - return true; - } - } - return false; + if (WARN_ON_ONCE(!bdev_is_zoned(bio->bi_bdev))) + return 0; + + return bio_add_hw_page(q, bio, page, len, offset, + queue_max_zone_append_sectors(q), &same_page); } -EXPORT_SYMBOL_GPL(__bio_try_merge_page); +EXPORT_SYMBOL_GPL(bio_add_zone_append_page); /** * __bio_add_page - add page(s) to a bio in a new segment @@ -804,15 +1072,10 @@ EXPORT_SYMBOL_GPL(__bio_try_merge_page); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off) { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt]; - WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_full(bio, len)); - bv->bv_page = page; - bv->bv_offset = off; - bv->bv_len = len; - + bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off); bio->bi_iter.bi_size += len; bio->bi_vcnt++; } @@ -833,48 +1096,129 @@ int bio_add_page(struct bio *bio, struct page *page, { bool same_page = false; - if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) { - if (bio_full(bio, len)) - return 0; - __bio_add_page(bio, page, len, offset); + if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) + return 0; + if (bio->bi_iter.bi_size > UINT_MAX - len) + return 0; + + if (bio->bi_vcnt > 0 && + bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1], + page, len, offset, &same_page)) { + bio->bi_iter.bi_size += len; + return len; } + + if (bio->bi_vcnt >= bio->bi_max_vecs) + return 0; + __bio_add_page(bio, page, len, offset); return len; } EXPORT_SYMBOL(bio_add_page); -static void bio_get_pages(struct bio *bio) +void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, + size_t off) { - struct bvec_iter_all iter_all; - struct bio_vec *bvec; + WARN_ON_ONCE(len > UINT_MAX); + WARN_ON_ONCE(off > UINT_MAX); + __bio_add_page(bio, &folio->page, len, off); +} - bio_for_each_segment_all(bvec, bio, iter_all) - get_page(bvec->bv_page); +/** + * bio_add_folio - Attempt to add part of a folio to a bio. + * @bio: BIO to add to. + * @folio: Folio to add. + * @len: How many bytes from the folio to add. + * @off: First byte in this folio to add. + * + * Filesystems that use folios can call this function instead of calling + * bio_add_page() for each page in the folio. If @off is bigger than + * PAGE_SIZE, this function can create a bio_vec that starts in a page + * after the bv_page. BIOs do not support folios that are 4GiB or larger. + * + * Return: Whether the addition was successful. + */ +bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len, + size_t off) +{ + if (len > UINT_MAX || off > UINT_MAX) + return false; + return bio_add_page(bio, &folio->page, len, off) > 0; } +EXPORT_SYMBOL(bio_add_folio); -static void bio_release_pages(struct bio *bio) +void __bio_release_pages(struct bio *bio, bool mark_dirty) { - struct bvec_iter_all iter_all; - struct bio_vec *bvec; + struct folio_iter fi; - bio_for_each_segment_all(bvec, bio, iter_all) - put_page(bvec->bv_page); + bio_for_each_folio_all(fi, bio) { + struct page *page; + size_t done = 0; + + if (mark_dirty) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); + } + page = folio_page(fi.folio, fi.offset / PAGE_SIZE); + do { + bio_release_page(bio, page++); + done += PAGE_SIZE; + } while (done < fi.length); + } } +EXPORT_SYMBOL_GPL(__bio_release_pages); -static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) +void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) { - const struct bio_vec *bv = iter->bvec; - unsigned int len; - size_t size; + size_t size = iov_iter_count(iter); - if (WARN_ON_ONCE(iter->iov_offset > bv->bv_len)) - return -EINVAL; + WARN_ON_ONCE(bio->bi_max_vecs); + + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + size_t max_sectors = queue_max_zone_append_sectors(q); + + size = min(size, max_sectors << SECTOR_SHIFT); + } + + bio->bi_vcnt = iter->nr_segs; + bio->bi_io_vec = (struct bio_vec *)iter->bvec; + bio->bi_iter.bi_bvec_done = iter->iov_offset; + bio->bi_iter.bi_size = size; + bio_set_flag(bio, BIO_CLONED); +} + +static int bio_iov_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + bool same_page = false; + + if (WARN_ON_ONCE(bio->bi_iter.bi_size > UINT_MAX - len)) + return -EIO; + + if (bio->bi_vcnt > 0 && + bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1], + page, len, offset, &same_page)) { + bio->bi_iter.bi_size += len; + if (same_page) + bio_release_page(bio, page); + return 0; + } + __bio_add_page(bio, page, len, offset); + return 0; +} + +static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + bool same_page = false; - len = min_t(size_t, bv->bv_len - iter->iov_offset, iter->count); - size = bio_add_page(bio, bv->bv_page, len, - bv->bv_offset + iter->iov_offset); - if (unlikely(size != len)) + if (bio_add_hw_page(q, bio, page, len, offset, + queue_max_zone_append_sectors(q), &same_page) != len) return -EINVAL; - iov_iter_advance(iter, size); + if (same_page) + bio_release_page(bio, page); return 0; } @@ -885,52 +1229,81 @@ static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins pages from *iter and appends them to @bio's bvec array. The - * pages will have to be released using put_page() when done. - * For multi-segment *iter, this function only adds pages from the - * the next non-empty segment of the iov iterator. + * Extracts pages from *iter and appends them to @bio's bvec array. The pages + * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag. + * For a multi-segment *iter, this function only adds pages from the next + * non-empty segment of the iov iterator. */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { + iov_iter_extraction_t extraction_flags = 0; 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; - bool same_page = false; ssize_t size, left; - unsigned len, i; + unsigned len, i = 0; size_t offset; + int ret = 0; /* * 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 (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue)) + extraction_flags |= ITER_ALLOW_P2PDMA; + + /* + * Each segment in the iov is required to be a block size multiple. + * However, we may not be able to get the entire segment if it spans + * more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the + * result to ensure the bio's total size is correct. The remainder of + * the iov data will be picked up in the next bio iteration. + */ + size = iov_iter_extract_pages(iter, &pages, + UINT_MAX - bio->bi_iter.bi_size, + nr_pages, extraction_flags, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; + nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE); + + if (bio->bi_bdev) { + size_t trim = size & (bdev_logical_block_size(bio->bi_bdev) - 1); + iov_iter_revert(iter, trim); + size -= trim; + } + + if (unlikely(!size)) { + ret = -EFAULT; + goto out; + } + for (left = size, i = 0; left > 0; left -= len, i++) { struct page *page = pages[i]; len = min_t(size_t, PAGE_SIZE - offset, left); + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + ret = bio_iov_add_zone_append_page(bio, page, len, + offset); + if (ret) + break; + } else + bio_iov_add_page(bio, page, len, offset); - if (__bio_try_merge_page(bio, page, len, offset, &same_page)) { - if (same_page) - put_page(page); - } else { - if (WARN_ON_ONCE(bio_full(bio, len))) - return -EINVAL; - __bio_add_page(bio, page, len, offset); - } offset = 0; } - iov_iter_advance(iter, size); - return 0; + iov_iter_revert(iter, left); +out: + while (i < nr_pages) + bio_release_page(bio, pages[i++]); + + return ret; } /** @@ -941,40 +1314,40 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) * This takes either an iterator pointing to user memory, or one pointing to * kernel pages (BVEC iterator). If we're adding user pages, we pin them and * map them into the kernel. On IO completion, the caller should put those - * pages. If we're adding kernel pages, and the caller told us it's safe to - * do so, we just have to add the pages to the bio directly. We don't grab an - * extra reference to those pages (the user should already have that), and we - * don't put the page on IO completion. The caller needs to check if the bio is - * flagged BIO_NO_PAGE_REF on IO completion. If it isn't, then pages should be - * released. + * pages. For bvec based iterators bio_iov_iter_get_pages() uses the provided + * bvecs rather than copying them. Hence anyone issuing kiocb based IO needs + * to ensure the bvecs and pages stay referenced until the submitted I/O is + * completed by a call to ->ki_complete() or returns with an error other than + * -EIOCBQUEUED. The caller needs to check if the bio is flagged BIO_NO_PAGE_REF + * on IO completion. If it isn't, then pages should be released. * * The function tries, but does not guarantee, to pin as many pages as - * fit into the bio, or are requested in *iter, whatever is smaller. If + * fit into the bio, or are requested in @iter, whatever is smaller. If * MM encounters an error pinning the requested pages, it stops. Error * is returned only if 0 pages could be pinned. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { - const bool is_bvec = iov_iter_is_bvec(iter); - int ret; + int ret = 0; - if (WARN_ON_ONCE(bio->bi_vcnt)) - return -EINVAL; + if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) + return -EIO; + if (iov_iter_is_bvec(iter)) { + bio_iov_bvec_set(bio, iter); + iov_iter_advance(iter, bio->bi_iter.bi_size); + return 0; + } + + if (iov_iter_extract_will_pin(iter)) + bio_set_flag(bio, BIO_PAGE_PINNED); do { - if (is_bvec) - ret = __bio_iov_bvec_add_pages(bio, iter); - else - ret = __bio_iov_iter_get_pages(bio, iter); + ret = __bio_iov_iter_get_pages(bio, iter); } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); - if (iov_iter_bvec_no_ref(iter)) - bio_set_flag(bio, BIO_NO_PAGE_REF); - else if (is_bvec) - bio_get_pages(bio); - return bio->bi_vcnt ? 0 : ret; } +EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) { @@ -994,65 +1367,55 @@ static void submit_bio_wait_endio(struct bio *bio) */ int submit_bio_wait(struct bio *bio) { - DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_disk->lockdep_map); + DECLARE_COMPLETION_ONSTACK_MAP(done, + bio->bi_bdev->bd_disk->lockdep_map); + unsigned long hang_check; bio->bi_private = &done; bio->bi_end_io = submit_bio_wait_endio; bio->bi_opf |= REQ_SYNC; submit_bio(bio); - wait_for_completion_io(&done); + + /* Prevent hang_check timer from firing at us during very long I/O */ + hang_check = sysctl_hung_task_timeout_secs; + if (hang_check) + while (!wait_for_completion_io_timeout(&done, + hang_check * (HZ/2))) + ; + else + wait_for_completion_io(&done); return blk_status_to_errno(bio->bi_status); } EXPORT_SYMBOL(submit_bio_wait); -/** - * bio_advance - increment/complete a bio by some number of bytes - * @bio: bio to advance - * @bytes: number of bytes to complete - * - * This updates bi_sector, bi_size and bi_idx; if the number of bytes to - * complete doesn't align with a bvec boundary, then bv_len and bv_offset will - * be updated on the last bvec as well. - * - * @bio will then represent the remaining, uncompleted portion of the io. - */ -void bio_advance(struct bio *bio, unsigned bytes) +void __bio_advance(struct bio *bio, unsigned bytes) { if (bio_integrity(bio)) bio_integrity_advance(bio, bytes); + bio_crypt_advance(bio, bytes); bio_advance_iter(bio, &bio->bi_iter, bytes); } -EXPORT_SYMBOL(bio_advance); +EXPORT_SYMBOL(__bio_advance); void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter) { - struct bio_vec src_bv, dst_bv; - void *src_p, *dst_p; - unsigned bytes; - while (src_iter->bi_size && dst_iter->bi_size) { - src_bv = bio_iter_iovec(src, *src_iter); - dst_bv = bio_iter_iovec(dst, *dst_iter); - - bytes = min(src_bv.bv_len, dst_bv.bv_len); + struct bio_vec src_bv = bio_iter_iovec(src, *src_iter); + struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter); + unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len); + void *src_buf = bvec_kmap_local(&src_bv); + void *dst_buf = bvec_kmap_local(&dst_bv); - src_p = kmap_atomic(src_bv.bv_page); - dst_p = kmap_atomic(dst_bv.bv_page); + memcpy(dst_buf, src_buf, bytes); - memcpy(dst_p + dst_bv.bv_offset, - src_p + src_bv.bv_offset, - bytes); + kunmap_local(dst_buf); + kunmap_local(src_buf); - kunmap_atomic(dst_p); - kunmap_atomic(src_p); - - flush_dcache_page(dst_bv.bv_page); - - bio_advance_iter(src, src_iter, bytes); - bio_advance_iter(dst, dst_iter, bytes); + bio_advance_iter_single(src, src_iter, bytes); + bio_advance_iter_single(dst, dst_iter, bytes); } } EXPORT_SYMBOL(bio_copy_data_iter); @@ -1074,128 +1437,6 @@ void bio_copy_data(struct bio *dst, struct bio *src) } EXPORT_SYMBOL(bio_copy_data); -/** - * bio_list_copy_data - copy contents of data buffers from one chain of bios to - * another - * @src: source bio list - * @dst: destination bio list - * - * Stops when it reaches the end of either the @src list or @dst list - that is, - * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of - * bios). - */ -void bio_list_copy_data(struct bio *dst, struct bio *src) -{ - struct bvec_iter src_iter = src->bi_iter; - struct bvec_iter dst_iter = dst->bi_iter; - - while (1) { - if (!src_iter.bi_size) { - src = src->bi_next; - if (!src) - break; - - src_iter = src->bi_iter; - } - - if (!dst_iter.bi_size) { - dst = dst->bi_next; - if (!dst) - break; - - dst_iter = dst->bi_iter; - } - - bio_copy_data_iter(dst, &dst_iter, src, &src_iter); - } -} -EXPORT_SYMBOL(bio_list_copy_data); - -struct bio_map_data { - int is_our_pages; - struct iov_iter iter; - struct iovec iov[]; -}; - -static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data, - gfp_t gfp_mask) -{ - struct bio_map_data *bmd; - if (data->nr_segs > UIO_MAXIOV) - return NULL; - - bmd = kmalloc(sizeof(struct bio_map_data) + - sizeof(struct iovec) * data->nr_segs, gfp_mask); - if (!bmd) - return NULL; - memcpy(bmd->iov, data->iov, sizeof(struct iovec) * data->nr_segs); - bmd->iter = *data; - bmd->iter.iov = bmd->iov; - return bmd; -} - -/** - * bio_copy_from_iter - copy all pages from iov_iter to bio - * @bio: The &struct bio which describes the I/O as destination - * @iter: iov_iter as source - * - * Copy all pages from iov_iter to bio. - * Returns 0 on success, or error on failure. - */ -static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter) -{ - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, iter_all) { - ssize_t ret; - - ret = copy_page_from_iter(bvec->bv_page, - bvec->bv_offset, - bvec->bv_len, - iter); - - if (!iov_iter_count(iter)) - break; - - if (ret < bvec->bv_len) - return -EFAULT; - } - - return 0; -} - -/** - * bio_copy_to_iter - copy all pages from bio to iov_iter - * @bio: The &struct bio which describes the I/O as source - * @iter: iov_iter as destination - * - * Copy all pages from bio to iov_iter. - * Returns 0 on success, or error on failure. - */ -static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter) -{ - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, iter_all) { - ssize_t ret; - - ret = copy_page_to_iter(bvec->bv_page, - bvec->bv_offset, - bvec->bv_len, - &iter); - - if (!iov_iter_count(&iter)) - break; - - if (ret < bvec->bv_len) - return -EFAULT; - } - - return 0; -} - void bio_free_pages(struct bio *bio) { struct bio_vec *bvec; @@ -1206,439 +1447,16 @@ void bio_free_pages(struct bio *bio) } EXPORT_SYMBOL(bio_free_pages); -/** - * bio_uncopy_user - finish previously mapped bio - * @bio: bio being terminated - * - * Free pages allocated from bio_copy_user_iov() and write back data - * to user space in case of a read. - */ -int bio_uncopy_user(struct bio *bio) -{ - struct bio_map_data *bmd = bio->bi_private; - int ret = 0; - - if (!bio_flagged(bio, BIO_NULL_MAPPED)) { - /* - * if we're in a workqueue, the request is orphaned, so - * don't copy into a random user address space, just free - * and return -EINTR so user space doesn't expect any data. - */ - if (!current->mm) - ret = -EINTR; - else if (bio_data_dir(bio) == READ) - ret = bio_copy_to_iter(bio, bmd->iter); - if (bmd->is_our_pages) - bio_free_pages(bio); - } - kfree(bmd); - bio_put(bio); - return ret; -} - -/** - * bio_copy_user_iov - copy user data to bio - * @q: destination block queue - * @map_data: pointer to the rq_map_data holding pages (if necessary) - * @iter: iovec iterator - * @gfp_mask: memory allocation flags - * - * Prepares and returns a bio for indirect user io, bouncing data - * to/from kernel pages as necessary. Must be paired with - * call bio_uncopy_user() on io completion. - */ -struct bio *bio_copy_user_iov(struct request_queue *q, - struct rq_map_data *map_data, - struct iov_iter *iter, - gfp_t gfp_mask) -{ - struct bio_map_data *bmd; - struct page *page; - struct bio *bio; - int i = 0, ret; - int nr_pages; - unsigned int len = iter->count; - unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0; - - bmd = bio_alloc_map_data(iter, gfp_mask); - if (!bmd) - return ERR_PTR(-ENOMEM); - - /* - * We need to do a deep copy of the iov_iter including the iovecs. - * The caller provided iov might point to an on-stack or otherwise - * shortlived one. - */ - bmd->is_our_pages = map_data ? 0 : 1; - - nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE); - if (nr_pages > BIO_MAX_PAGES) - nr_pages = BIO_MAX_PAGES; - - ret = -ENOMEM; - bio = bio_kmalloc(gfp_mask, nr_pages); - if (!bio) - goto out_bmd; - - ret = 0; - - if (map_data) { - nr_pages = 1 << map_data->page_order; - i = map_data->offset / PAGE_SIZE; - } - while (len) { - unsigned int bytes = PAGE_SIZE; - - bytes -= offset; - - if (bytes > len) - bytes = len; - - if (map_data) { - if (i == map_data->nr_entries * nr_pages) { - ret = -ENOMEM; - break; - } - - page = map_data->pages[i / nr_pages]; - page += (i % nr_pages); - - i++; - } else { - page = alloc_page(q->bounce_gfp | gfp_mask); - if (!page) { - ret = -ENOMEM; - break; - } - } - - if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) { - if (!map_data) - __free_page(page); - break; - } - - len -= bytes; - offset = 0; - } - - if (ret) - goto cleanup; - - if (map_data) - map_data->offset += bio->bi_iter.bi_size; - - /* - * success - */ - if ((iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) || - (map_data && map_data->from_user)) { - ret = bio_copy_from_iter(bio, iter); - if (ret) - goto cleanup; - } else { - if (bmd->is_our_pages) - zero_fill_bio(bio); - iov_iter_advance(iter, bio->bi_iter.bi_size); - } - - bio->bi_private = bmd; - if (map_data && map_data->null_mapped) - bio_set_flag(bio, BIO_NULL_MAPPED); - return bio; -cleanup: - if (!map_data) - bio_free_pages(bio); - bio_put(bio); -out_bmd: - kfree(bmd); - return ERR_PTR(ret); -} - -/** - * bio_map_user_iov - map user iovec into bio - * @q: the struct request_queue for the bio - * @iter: iovec iterator - * @gfp_mask: memory allocation flags - * - * Map the user space address into a bio suitable for io to a block - * device. Returns an error pointer in case of error. - */ -struct bio *bio_map_user_iov(struct request_queue *q, - struct iov_iter *iter, - gfp_t gfp_mask) -{ - int j; - struct bio *bio; - int ret; - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - if (!iov_iter_count(iter)) - return ERR_PTR(-EINVAL); - - bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES)); - if (!bio) - return ERR_PTR(-ENOMEM); - - while (iov_iter_count(iter)) { - struct page **pages; - ssize_t bytes; - size_t offs, added = 0; - int npages; - - bytes = iov_iter_get_pages_alloc(iter, &pages, LONG_MAX, &offs); - if (unlikely(bytes <= 0)) { - ret = bytes ? bytes : -EFAULT; - goto out_unmap; - } - - npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE); - - if (unlikely(offs & queue_dma_alignment(q))) { - ret = -EINVAL; - j = 0; - } else { - for (j = 0; j < npages; j++) { - struct page *page = pages[j]; - unsigned int n = PAGE_SIZE - offs; - - if (n > bytes) - n = bytes; - - if (!__bio_add_pc_page(q, bio, page, n, offs, - true)) - break; - - added += n; - bytes -= n; - offs = 0; - } - iov_iter_advance(iter, added); - } - /* - * release the pages we didn't map into the bio, if any - */ - while (j < npages) - put_page(pages[j++]); - kvfree(pages); - /* couldn't stuff something into bio? */ - if (bytes) - break; - } - - bio_set_flag(bio, BIO_USER_MAPPED); - - /* - * subtle -- if bio_map_user_iov() ended up bouncing a bio, - * it would normally disappear when its bi_end_io is run. - * however, we need it for the unmap, so grab an extra - * reference to it - */ - bio_get(bio); - return bio; - - out_unmap: - bio_for_each_segment_all(bvec, bio, iter_all) { - put_page(bvec->bv_page); - } - bio_put(bio); - return ERR_PTR(ret); -} - -static void __bio_unmap_user(struct bio *bio) -{ - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - /* - * make sure we dirty pages we wrote to - */ - bio_for_each_segment_all(bvec, bio, iter_all) { - if (bio_data_dir(bio) == READ) - set_page_dirty_lock(bvec->bv_page); - - put_page(bvec->bv_page); - } - - bio_put(bio); -} - -/** - * bio_unmap_user - unmap a bio - * @bio: the bio being unmapped - * - * Unmap a bio previously mapped by bio_map_user_iov(). Must be called from - * process context. - * - * bio_unmap_user() may sleep. - */ -void bio_unmap_user(struct bio *bio) -{ - __bio_unmap_user(bio); - bio_put(bio); -} - -static void bio_map_kern_endio(struct bio *bio) -{ - bio_put(bio); -} - -/** - * bio_map_kern - map kernel address into bio - * @q: the struct request_queue for the bio - * @data: pointer to buffer to map - * @len: length in bytes - * @gfp_mask: allocation flags for bio allocation - * - * Map the kernel address into a bio suitable for io to a block - * device. Returns an error pointer in case of error. - */ -struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len, - gfp_t gfp_mask) -{ - unsigned long kaddr = (unsigned long)data; - unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - unsigned long start = kaddr >> PAGE_SHIFT; - const int nr_pages = end - start; - int offset, i; - struct bio *bio; - - bio = bio_kmalloc(gfp_mask, nr_pages); - if (!bio) - return ERR_PTR(-ENOMEM); - - offset = offset_in_page(kaddr); - for (i = 0; i < nr_pages; i++) { - unsigned int bytes = PAGE_SIZE - offset; - - if (len <= 0) - break; - - if (bytes > len) - bytes = len; - - if (bio_add_pc_page(q, bio, virt_to_page(data), bytes, - offset) < bytes) { - /* we don't support partial mappings */ - bio_put(bio); - return ERR_PTR(-EINVAL); - } - - data += bytes; - len -= bytes; - offset = 0; - } - - bio->bi_end_io = bio_map_kern_endio; - return bio; -} -EXPORT_SYMBOL(bio_map_kern); - -static void bio_copy_kern_endio(struct bio *bio) -{ - bio_free_pages(bio); - bio_put(bio); -} - -static void bio_copy_kern_endio_read(struct bio *bio) -{ - char *p = bio->bi_private; - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, iter_all) { - memcpy(p, page_address(bvec->bv_page), bvec->bv_len); - p += bvec->bv_len; - } - - bio_copy_kern_endio(bio); -} - -/** - * bio_copy_kern - copy kernel address into bio - * @q: the struct request_queue for the bio - * @data: pointer to buffer to copy - * @len: length in bytes - * @gfp_mask: allocation flags for bio and page allocation - * @reading: data direction is READ - * - * copy the kernel address into a bio suitable for io to a block - * device. Returns an error pointer in case of error. - */ -struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len, - gfp_t gfp_mask, int reading) -{ - unsigned long kaddr = (unsigned long)data; - unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - unsigned long start = kaddr >> PAGE_SHIFT; - struct bio *bio; - void *p = data; - int nr_pages = 0; - - /* - * Overflow, abort - */ - if (end < start) - return ERR_PTR(-EINVAL); - - nr_pages = end - start; - bio = bio_kmalloc(gfp_mask, nr_pages); - if (!bio) - return ERR_PTR(-ENOMEM); - - while (len) { - struct page *page; - unsigned int bytes = PAGE_SIZE; - - if (bytes > len) - bytes = len; - - page = alloc_page(q->bounce_gfp | gfp_mask); - if (!page) - goto cleanup; - - if (!reading) - memcpy(page_address(page), p, bytes); - - if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) - break; - - len -= bytes; - p += bytes; - } - - if (reading) { - bio->bi_end_io = bio_copy_kern_endio_read; - bio->bi_private = data; - } else { - bio->bi_end_io = bio_copy_kern_endio; - } - - return bio; - -cleanup: - bio_free_pages(bio); - bio_put(bio); - return ERR_PTR(-ENOMEM); -} - /* * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions * for performing direct-IO in BIOs. * - * The problem is that we cannot run set_page_dirty() from interrupt context + * The problem is that we cannot run folio_mark_dirty() from interrupt context * because the required locks are not interrupt-safe. So what we can do is to * mark the pages dirty _before_ performing IO. And in interrupt context, * check that the pages are still dirty. If so, fine. If not, redirty them * in process context. * - * We special-case compound pages here: normally this means reads into hugetlb - * pages. The logic in here doesn't really work right for compound pages - * because the VM does not uniformly chase down the head page in all cases. - * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't - * handle them at all. So we skip compound pages here at an early stage. - * * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. @@ -1654,14 +1472,15 @@ cleanup: */ void bio_set_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct folio_iter fi; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); + bio_for_each_folio_all(fi, bio) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); } } +EXPORT_SYMBOL_GPL(bio_set_pages_dirty); /* * bio_check_pages_dirty() will check that all the BIO's pages are still dirty. @@ -1670,8 +1489,8 @@ void bio_set_pages_dirty(struct bio *bio) * the BIO and re-dirty the pages in process context. * * It is expected that bio_check_pages_dirty() will wholly own the BIO from - * here on. It will run one put_page() against each page and will run one - * bio_put() against the BIO. + * here on. It will unpin each page and will run one bio_put() against the + * BIO. */ static void bio_dirty_fn(struct work_struct *work); @@ -1695,26 +1514,22 @@ static void bio_dirty_fn(struct work_struct *work) while ((bio = next) != NULL) { next = bio->bi_private; - bio_set_pages_dirty(bio); - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) - bio_release_pages(bio); + bio_release_pages(bio, true); bio_put(bio); } } void bio_check_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; + struct folio_iter fi; unsigned long flags; - struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page)) + bio_for_each_folio_all(fi, bio) { + if (!folio_test_dirty(fi.folio)) goto defer; } - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) - bio_release_pages(bio); + bio_release_pages(bio, false); bio_put(bio); return; defer: @@ -1724,68 +1539,7 @@ defer: spin_unlock_irqrestore(&bio_dirty_lock, flags); schedule_work(&bio_dirty_work); } - -void update_io_ticks(struct hd_struct *part, unsigned long now) -{ - unsigned long stamp; -again: - stamp = READ_ONCE(part->stamp); - if (unlikely(stamp != now)) { - if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) { - __part_stat_add(part, io_ticks, 1); - } - } - if (part->partno) { - part = &part_to_disk(part)->part0; - goto again; - } -} - -void generic_start_io_acct(struct request_queue *q, int op, - unsigned long sectors, struct hd_struct *part) -{ - const int sgrp = op_stat_group(op); - - part_stat_lock(); - - update_io_ticks(part, jiffies); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, sectors[sgrp], sectors); - part_inc_in_flight(q, part, op_is_write(op)); - - part_stat_unlock(); -} -EXPORT_SYMBOL(generic_start_io_acct); - -void generic_end_io_acct(struct request_queue *q, int req_op, - struct hd_struct *part, unsigned long start_time) -{ - unsigned long now = jiffies; - unsigned long duration = now - start_time; - const int sgrp = op_stat_group(req_op); - - part_stat_lock(); - - update_io_ticks(part, now); - part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); - part_stat_add(part, time_in_queue, duration); - part_dec_in_flight(q, part, op_is_write(req_op)); - - part_stat_unlock(); -} -EXPORT_SYMBOL(generic_end_io_acct); - -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -void bio_flush_dcache_pages(struct bio *bi) -{ - struct bio_vec bvec; - struct bvec_iter iter; - - bio_for_each_segment(bvec, bi, iter) - flush_dcache_page(bvec.bv_page); -} -EXPORT_SYMBOL(bio_flush_dcache_pages); -#endif +EXPORT_SYMBOL_GPL(bio_check_pages_dirty); static inline bool bio_remaining_done(struct bio *bio) { @@ -1817,8 +1571,7 @@ static inline bool bio_remaining_done(struct bio *bio) * * bio_endio() can be called several times on a bio that has been chained * using bio_chain(). The ->bi_end_io() function will only be called the - * last time. At this point the BLK_TA_COMPLETE tracing event will be - * generated if BIO_TRACE_COMPLETION is set. + * last time. **/ void bio_endio(struct bio *bio) { @@ -1828,8 +1581,12 @@ again: if (!bio_integrity_endio(bio)) return; - if (bio->bi_disk) - rq_qos_done_bio(bio->bi_disk->queue, bio); + rq_qos_done_bio(bio); + + if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { + trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio); + bio_clear_flag(bio, BIO_TRACE_COMPLETION); + } /* * Need to have a real endio function for chained bios, otherwise @@ -1844,12 +1601,6 @@ again: goto again; } - if (bio->bi_disk && bio_flagged(bio, BIO_TRACE_COMPLETION)) { - trace_block_bio_complete(bio->bi_disk->queue, bio, - blk_status_to_errno(bio->bi_status)); - bio_clear_flag(bio, BIO_TRACE_COMPLETION); - } - blk_throtl_bio_endio(bio); /* release cgroup info */ bio_uninit(bio); @@ -1869,8 +1620,8 @@ EXPORT_SYMBOL(bio_endio); * @bio, and updates @bio to represent the remaining sectors. * * Unless this is a discard request the newly allocated bio will point - * to @bio's bi_io_vec; it is the caller's responsibility to ensure that - * @bio is not freed before the split. + * to @bio's bi_io_vec. It is the caller's responsibility to ensure that + * neither @bio nor @bs are freed before the split bio. */ struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) @@ -1880,7 +1631,11 @@ struct bio *bio_split(struct bio *bio, int sectors, BUG_ON(sectors <= 0); BUG_ON(sectors >= bio_sectors(bio)); - split = bio_clone_fast(bio, gfp, bs); + /* Zone append commands cannot be split */ + if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND)) + return NULL; + + split = bio_alloc_clone(bio->bi_bdev, bio, gfp, bs); if (!split) return NULL; @@ -1903,26 +1658,25 @@ EXPORT_SYMBOL(bio_split); * @bio: bio to trim * @offset: number of sectors to trim from the front of @bio * @size: size we want to trim @bio to, in sectors + * + * This function is typically used for bios that are cloned and submitted + * to the underlying device in parts. */ -void bio_trim(struct bio *bio, int offset, int size) +void bio_trim(struct bio *bio, sector_t offset, sector_t size) { - /* 'bio' is a cloned bio which we need to trim to match - * the given offset and size. - */ + if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || + offset + size > bio_sectors(bio))) + return; size <<= 9; if (offset == 0 && size == bio->bi_iter.bi_size) return; - bio_clear_flag(bio, BIO_SEG_VALID); - bio_advance(bio, offset << 9); - bio->bi_iter.bi_size = size; if (bio_integrity(bio)) bio_integrity_trim(bio); - } EXPORT_SYMBOL_GPL(bio_trim); @@ -1932,7 +1686,7 @@ EXPORT_SYMBOL_GPL(bio_trim); */ int biovec_init_pool(mempool_t *pool, int pool_entries) { - struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX; + struct biovec_slab *bp = bvec_slabs + ARRAY_SIZE(bvec_slabs) - 1; return mempool_init_slab_pool(pool, pool_entries, bp->slab); } @@ -1945,6 +1699,7 @@ int biovec_init_pool(mempool_t *pool, int pool_entries) */ void bioset_exit(struct bio_set *bs) { + bio_alloc_cache_destroy(bs); if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); bs->rescue_workqueue = NULL; @@ -1975,9 +1730,9 @@ EXPORT_SYMBOL(bioset_exit); * Note that the bio must be embedded at the END of that structure always, * or things will break badly. * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated - * for allocating iovecs. This pool is not needed e.g. for bio_clone_fast(). - * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to - * dispatch queued requests when the mempool runs out of space. + * for allocating iovecs. This pool is not needed e.g. for bio_init_clone(). + * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used + * to dispatch queued requests when the mempool runs out of space. * */ int bioset_init(struct bio_set *bs, @@ -1985,15 +1740,17 @@ int bioset_init(struct bio_set *bs, unsigned int front_pad, int flags) { - unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); - bs->front_pad = front_pad; + if (flags & BIOSET_NEED_BVECS) + bs->back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); + else + bs->back_pad = 0; spin_lock_init(&bs->rescue_lock); bio_list_init(&bs->rescue_list); INIT_WORK(&bs->rescue_work, bio_alloc_rescue); - bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad); + bs->bio_slab = bio_find_or_create_slab(bs); if (!bs->bio_slab) return -ENOMEM; @@ -2004,12 +1761,18 @@ int bioset_init(struct bio_set *bs, biovec_init_pool(&bs->bvec_pool, pool_size)) goto bad; - if (!(flags & BIOSET_NEED_RESCUER)) - return 0; - - bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0); - if (!bs->rescue_workqueue) - goto bad; + if (flags & BIOSET_NEED_RESCUER) { + bs->rescue_workqueue = alloc_workqueue("bioset", + WQ_MEM_RECLAIM, 0); + if (!bs->rescue_workqueue) + goto bad; + } + if (flags & BIOSET_PERCPU_CACHE) { + bs->cache = alloc_percpu(struct bio_alloc_cache); + if (!bs->cache) + goto bad; + cpuhp_state_add_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); + } return 0; bad: @@ -2018,194 +1781,27 @@ bad: } EXPORT_SYMBOL(bioset_init); -/* - * Initialize and setup a new bio_set, based on the settings from - * another bio_set. - */ -int bioset_init_from_src(struct bio_set *bs, struct bio_set *src) -{ - int flags; - - flags = 0; - if (src->bvec_pool.min_nr) - flags |= BIOSET_NEED_BVECS; - if (src->rescue_workqueue) - flags |= BIOSET_NEED_RESCUER; - - return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags); -} -EXPORT_SYMBOL(bioset_init_from_src); - -#ifdef CONFIG_BLK_CGROUP - -/** - * bio_disassociate_blkg - puts back the blkg reference if associated - * @bio: target bio - * - * Helper to disassociate the blkg from @bio if a blkg is associated. - */ -void bio_disassociate_blkg(struct bio *bio) -{ - if (bio->bi_blkg) { - blkg_put(bio->bi_blkg); - bio->bi_blkg = NULL; - } -} -EXPORT_SYMBOL_GPL(bio_disassociate_blkg); - -/** - * __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. - */ -static void __bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) -{ - bio_disassociate_blkg(bio); - - bio->bi_blkg = blkg_tryget_closest(blkg); -} - -/** - * 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. - */ -void 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; - - rcu_read_lock(); - - if (!css || !css->parent) - blkg = q->root_blkg; - else - blkg = blkg_lookup_create(css_to_blkcg(css), q); - - __bio_associate_blkg(bio, blkg); - - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); - -#ifdef CONFIG_MEMCG -/** - * 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 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. - */ -void bio_associate_blkg_from_page(struct bio *bio, struct page *page) -{ - struct cgroup_subsys_state *css; - - if (!page->mem_cgroup) - return; - - rcu_read_lock(); - - css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); - bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); -} -#endif /* CONFIG_MEMCG */ - -/** - * bio_associate_blkg - associate a bio with a blkg - * @bio: target bio - * - * Associate @bio with the blkg found from the bio's css and request_queue. - * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is - * already associated, the css is reused and association redone as the - * request_queue may have changed. - */ -void bio_associate_blkg(struct bio *bio) -{ - struct cgroup_subsys_state *css; - - rcu_read_lock(); - - if (bio->bi_blkg) - css = &bio_blkcg(bio)->css; - else - css = blkcg_css(); - - bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(bio_associate_blkg); - -/** - * bio_clone_blkg_association - clone blkg association from src to dst bio - * @dst: destination bio - * @src: source bio - */ -void bio_clone_blkg_association(struct bio *dst, struct bio *src) +static int __init init_bio(void) { - rcu_read_lock(); - - if (src->bi_blkg) - __bio_associate_blkg(dst, src->bi_blkg); + int i; - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(bio_clone_blkg_association); -#endif /* CONFIG_BLK_CGROUP */ + BUILD_BUG_ON(BIO_FLAG_LAST > 8 * sizeof_field(struct bio, bi_flags)); -static void __init biovec_init_slabs(void) -{ - int i; + bio_integrity_init(); - for (i = 0; i < BVEC_POOL_NR; i++) { - int size; + for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) { struct biovec_slab *bvs = bvec_slabs + i; - if (bvs->nr_vecs <= BIO_INLINE_VECS) { - bvs->slab = NULL; - continue; - } - - size = bvs->nr_vecs * sizeof(struct bio_vec); - bvs->slab = kmem_cache_create(bvs->name, size, 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + bvs->slab = kmem_cache_create(bvs->name, + bvs->nr_vecs * sizeof(struct bio_vec), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); } -} - -static int __init init_bio(void) -{ - bio_slab_max = 2; - bio_slab_nr = 0; - bio_slabs = kcalloc(bio_slab_max, sizeof(struct bio_slab), - GFP_KERNEL); - - BUILD_BUG_ON(BIO_FLAG_LAST > BVEC_POOL_OFFSET); - if (!bio_slabs) - panic("bio: can't allocate bios\n"); - - bio_integrity_init(); - biovec_init_slabs(); + cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL, + bio_cpu_dead); - if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS)) + if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, + BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE)) panic("bio: can't allocate bios\n"); if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE)) |