diff options
author | Pavel Begunkov <asml.silence@gmail.com> | 2022-11-02 18:18:22 +0300 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2022-11-16 19:44:26 +0300 |
commit | b99182c501c3dedeba4c9e6c92a60df1a2fee119 (patch) | |
tree | b2ef978e4ea4f3e7ea0ea551b5343afb95fc655d /block/bio.c | |
parent | f25cf75a452150c243f74ab1f1836822137d5d2c (diff) | |
download | linux-b99182c501c3dedeba4c9e6c92a60df1a2fee119.tar.xz |
bio: add pcpu caching for non-polling bio_put
This patch extends REQ_ALLOC_CACHE to IRQ completions, whenever
currently it's only limited to iopoll. Instead of guarding the list with
irq toggling on alloc, which is expensive, it keeps an additional
irq-safe list from which bios are spliced in batches to ammortise
overhead. On the put side it toggles irqs, but in many cases they're
already disabled and so cheap.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/c2306de96b900ab9264f4428ec37768ddcf0da36.1667384020.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/bio.c')
-rw-r--r-- | block/bio.c | 70 |
1 files changed, 54 insertions, 16 deletions
diff --git a/block/bio.c b/block/bio.c index 0d03b8d36447..14a7105231d2 100644 --- a/block/bio.c +++ b/block/bio.c @@ -25,9 +25,15 @@ #include "blk-rq-qos.h" #include "blk-cgroup.h" +#define ALLOC_CACHE_THRESHOLD 16 +#define ALLOC_CACHE_SLACK 64 +#define ALLOC_CACHE_MAX 512 + struct bio_alloc_cache { struct bio *free_list; + struct bio *free_list_irq; unsigned int nr; + unsigned int nr_irq; }; static struct biovec_slab { @@ -408,6 +414,22 @@ 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) @@ -417,8 +439,12 @@ static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, cache = per_cpu_ptr(bs->cache, get_cpu()); if (!cache->free_list) { - put_cpu(); - return NULL; + 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; @@ -462,9 +488,6 @@ static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * - * If REQ_ALLOC_CACHE is set, the final put of the bio MUST be done from process - * context, not hard/soft IRQ. - * * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, @@ -678,11 +701,8 @@ void guard_bio_eod(struct bio *bio) bio_truncate(bio, maxsector << 9); } -#define ALLOC_CACHE_MAX 512 -#define ALLOC_CACHE_SLACK 64 - -static void bio_alloc_cache_prune(struct bio_alloc_cache *cache, - unsigned int nr) +static int __bio_alloc_cache_prune(struct bio_alloc_cache *cache, + unsigned int nr) { unsigned int i = 0; struct bio *bio; @@ -694,6 +714,17 @@ static void bio_alloc_cache_prune(struct bio_alloc_cache *cache, 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) @@ -732,6 +763,12 @@ 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())) { @@ -739,13 +776,14 @@ static inline void bio_put_percpu_cache(struct bio *bio) cache->free_list = bio; cache->nr++; } else { - put_cpu(); - bio_free(bio); - return; - } + unsigned long flags; - if (cache->nr > ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK) - bio_alloc_cache_prune(cache, ALLOC_CACHE_SLACK); + 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(); } |