#include "blk.h"
#include "blk-rq-qos.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
-
-/*
- * 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),
+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_PAGES, .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_PAGES:
+ return &bvec_slabs[3];
+ default:
+ BUG();
+ return NULL;
+ }
+}
/*
* fs_bio_set is the bio_set containing bio and iovec memory pools used by
mutex_unlock(&bio_slab_lock);
}
-unsigned int bvec_nr_vecs(unsigned short idx)
+void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs)
{
- return bvec_slabs[--idx].nr_vecs;
-}
+ BIO_BUG_ON(nr_vecs > BIO_MAX_PAGES);
-void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
-{
- if (!idx)
- return;
- idx--;
-
- BIO_BUG_ON(idx >= BVEC_POOL_NR);
-
- if (idx == BVEC_POOL_MAX) {
+ if (nr_vecs == BIO_MAX_PAGES)
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_PAGES entries.
+ */
+ if (*nr_vecs < BIO_MAX_PAGES) {
+ 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_PAGES;
}
- (*idx)++;
- return bvl;
+ return mempool_alloc(pool, gfp_mask);
}
void bio_uninit(struct bio *bio)
bio_uninit(bio);
if (bs) {
- bvec_free(&bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
+ bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs);
/*
* If we have front padding, adjust the bio pointer before freeing
*/
void bio_reset(struct bio *bio)
{
- 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);
}
EXPORT_SYMBOL(bio_reset);
* @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 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.
+ * 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
- * submit_bio_noacct() 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
- * submit_bio_noacct() 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(gfp_t gfp_mask, unsigned short nr_iovecs,
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(struct_size(bio, bi_inline_vecs, nr_iovecs), 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;
- /*
- * 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;
+ /* should not use nobvec bioset for nr_iovecs > 0 */
+ if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_iovecs > 0))
+ return NULL;
+ /*
+ * 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 (!p && gfp_mask != saved_gfp) {
- punt_bios_to_rescuer(bs);
- gfp_mask = saved_gfp;
- p = mempool_alloc(&bs->bio_pool, gfp_mask);
- }
-
- front_pad = bs->front_pad;
- inline_vecs = BIO_INLINE_VECS;
}
-
if (unlikely(!p))
return NULL;
- bio = p + front_pad;
- bio_init(bio, NULL, 0);
+ bio = p + bs->front_pad;
+ if (nr_iovecs > BIO_INLINE_VECS) {
+ struct bio_vec *bvl = NULL;
- if (nr_iovecs > inline_vecs) {
- unsigned long idx = 0;
-
- bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool);
+ bvl = bvec_alloc(&bs->bvec_pool, &nr_iovecs, 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_iovecs, gfp_mask);
}
-
if (unlikely(!bvl))
goto err_free;
- bio->bi_flags |= idx << BVEC_POOL_OFFSET;
- bio->bi_max_vecs = bvec_nr_vecs(idx);
+ bio_init(bio, bvl, nr_iovecs);
} else if (nr_iovecs) {
- bvl = bio->bi_inline_vecs;
- bio->bi_max_vecs = inline_vecs;
+ bio_init(bio, bio->bi_inline_vecs, BIO_INLINE_VECS);
+ } else {
+ bio_init(bio, NULL, 0);
}
bio->bi_pool = bs;
- bio->bi_io_vec = bvl;
return bio;
err_free:
}
EXPORT_SYMBOL(bio_alloc_bioset);
+/**
+ * bio_kmalloc - kmalloc a bio for I/O
+ * @gfp_mask: the GFP_* mask given to the slab allocator
+ * @nr_iovecs: number of iovecs to pre-allocate
+ *
+ * Use kmalloc to allocate and initialize a bio.
+ *
+ * Returns: Pointer to new bio on success, NULL on failure.
+ */
+struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs)
+{
+ struct bio *bio;
+
+ if (nr_iovecs > UIO_MAXIOV)
+ return NULL;
+
+ bio = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask);
+ if (unlikely(!bio))
+ return NULL;
+ bio_init(bio, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs);
+ bio->bi_pool = NULL;
+ return bio;
+}
+EXPORT_SYMBOL(bio_kmalloc);
+
void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
{
unsigned long flags;
*/
void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
{
- BUG_ON(bio->bi_pool && BVEC_POOL_IDX(bio));
+ WARN_ON_ONCE(bio->bi_pool && bio->bi_max_vecs);
/*
* most users will be overriding ->bi_bdev with a new target,
}
EXPORT_SYMBOL(bio_add_pc_page);
+/**
+ * bio_add_zone_append_page - attempt to add page to zone-append bio
+ * @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 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.
+ *
+ * Returns: number of bytes added to the bio, or 0 in case of a failure.
+ */
+int bio_add_zone_append_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int offset)
+{
+ struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ bool same_page = false;
+
+ if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND))
+ return 0;
+
+ if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
+ return 0;
+
+ return bio_add_hw_page(q, bio, page, len, offset,
+ queue_max_zone_append_sectors(q), &same_page);
+}
+EXPORT_SYMBOL_GPL(bio_add_zone_append_page);
+
/**
* __bio_try_merge_page - try appending data to an existing bvec.
* @bio: destination bio
static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
{
- WARN_ON_ONCE(BVEC_POOL_IDX(bio) != 0);
+ WARN_ON_ONCE(bio->bi_max_vecs);
bio->bi_vcnt = iter->nr_segs;
- bio->bi_max_vecs = 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 = iter->count;
+ bio_set_flag(bio, BIO_NO_PAGE_REF);
+ bio_set_flag(bio, BIO_CLONED);
iov_iter_advance(iter, iter->count);
return 0;
if (iov_iter_is_bvec(iter)) {
if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
return -EINVAL;
- bio_iov_bvec_set(bio, iter);
- bio_set_flag(bio, BIO_NO_PAGE_REF);
- return 0;
- } else {
- do {
- if (bio_op(bio) == REQ_OP_ZONE_APPEND)
- ret = __bio_iov_append_get_pages(bio, iter);
- else
- ret = __bio_iov_iter_get_pages(bio, iter);
- } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
+ return bio_iov_bvec_set(bio, iter);
}
+ do {
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+ ret = __bio_iov_append_get_pages(bio, iter);
+ else
+ ret = __bio_iov_iter_get_pages(bio, iter);
+ } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
+
/* don't account direct I/O as memory stall */
bio_clear_flag(bio, BIO_WORKINGSET);
return bio->bi_vcnt ? 0 : ret;
*/
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);
}
}
EXPORT_SYMBOL(bioset_init_from_src);
-static void __init biovec_init_slabs(void)
+static int __init init_bio(void)
{
int i;
- for (i = 0; i < BVEC_POOL_NR; i++) {
- int size;
- struct biovec_slab *bvs = bvec_slabs + i;
+ bio_integrity_init();
- if (bvs->nr_vecs <= BIO_INLINE_VECS) {
- bvs->slab = NULL;
- continue;
- }
+ for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) {
+ struct biovec_slab *bvs = bvec_slabs + i;
- 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)
-{
- BUILD_BUG_ON(BIO_FLAG_LAST > BVEC_POOL_OFFSET);
-
- bio_integrity_init();
- biovec_init_slabs();
if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS))
panic("bio: can't allocate bios\n");
projects / linux-2.6-microblaze.git / blobdiff