From 61fd21670d048017c81e62f60894ef1b04b481db Mon Sep 17 00:00:00 2001 From: Andre Noll Date: Thu, 25 Jun 2009 13:03:04 +0200 Subject: Trivial typo fixes in Documentation/block/data-integrity.txt. Signed-off-by: Andre Noll Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- Documentation/block/data-integrity.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt index e8ca040ba2c..2d735b0ae38 100644 --- a/Documentation/block/data-integrity.txt +++ b/Documentation/block/data-integrity.txt @@ -50,7 +50,7 @@ encouraged them to allow separation of the data and integrity metadata scatter-gather lists. The controller will interleave the buffers on write and split them on -read. This means that the Linux can DMA the data buffers to and from +read. This means that Linux can DMA the data buffers to and from host memory without changes to the page cache. Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs @@ -66,7 +66,7 @@ software RAID5). The IP checksum is weaker than the CRC in terms of detecting bit errors. However, the strength is really in the separation of the data -buffers and the integrity metadata. These two distinct buffers much +buffers and the integrity metadata. These two distinct buffers must match up for an I/O to complete. The separation of the data and integrity metadata buffers as well as -- cgit v1.2.3-70-g09d2 From d5036d770f871bd34c9cfd955e6dee692e1e8e81 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Jun 2009 10:44:34 +0200 Subject: cfq-iosched: move cfqq initialization out of cfq_find_alloc_queue() We're going to be needing that init code outside of that function to get rid of the __GFP_NOFAIL in cfqq allocation. Reviewed-by: Jeff Moyer Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 833ec18eaa6..c760ae7019d 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1641,6 +1641,26 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc) ioc->ioprio_changed = 0; } +static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, + pid_t pid, int is_sync) +{ + RB_CLEAR_NODE(&cfqq->rb_node); + RB_CLEAR_NODE(&cfqq->p_node); + INIT_LIST_HEAD(&cfqq->fifo); + + atomic_set(&cfqq->ref, 0); + cfqq->cfqd = cfqd; + + cfq_mark_cfqq_prio_changed(cfqq); + + if (is_sync) { + if (!cfq_class_idle(cfqq)) + cfq_mark_cfqq_idle_window(cfqq); + cfq_mark_cfqq_sync(cfqq); + } + cfqq->pid = pid; +} + static struct cfq_queue * cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, gfp_t gfp_mask) @@ -1678,23 +1698,8 @@ retry: goto out; } - RB_CLEAR_NODE(&cfqq->rb_node); - RB_CLEAR_NODE(&cfqq->p_node); - INIT_LIST_HEAD(&cfqq->fifo); - - atomic_set(&cfqq->ref, 0); - cfqq->cfqd = cfqd; - - cfq_mark_cfqq_prio_changed(cfqq); - + cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); cfq_init_prio_data(cfqq, ioc); - - if (is_sync) { - if (!cfq_class_idle(cfqq)) - cfq_mark_cfqq_idle_window(cfqq); - cfq_mark_cfqq_sync(cfqq); - } - cfqq->pid = current->pid; cfq_log_cfqq(cfqd, cfqq, "alloced"); } -- cgit v1.2.3-70-g09d2 From 6118b70b3a0b4c583439bb77600194c82f220ce3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 30 Jun 2009 09:34:12 +0200 Subject: cfq-iosched: get rid of the need for __GFP_NOFAIL in cfq_find_alloc_queue() Setup an emergency fallback cfqq that we allocate at IO scheduler init time. If the slab allocation fails in cfq_find_alloc_queue(), we'll just punt IO to that cfqq instead. This ensures that cfq_find_alloc_queue() never fails without having to ensure free memory. On cfqq lookup, always try to allocate a new cfqq if the given cfq io context has the oom_cfqq assigned. This ensures that we only temporarily punt to this shared queue. Reviewed-by: Jeff Moyer Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 137 ++++++++++++++++++++++++++++------------------------ 1 file changed, 73 insertions(+), 64 deletions(-) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index c760ae7019d..1d9160ffa26 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -70,6 +70,51 @@ struct cfq_rb_root { }; #define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, } +/* + * Per process-grouping structure + */ +struct cfq_queue { + /* reference count */ + atomic_t ref; + /* various state flags, see below */ + unsigned int flags; + /* parent cfq_data */ + struct cfq_data *cfqd; + /* service_tree member */ + struct rb_node rb_node; + /* service_tree key */ + unsigned long rb_key; + /* prio tree member */ + struct rb_node p_node; + /* prio tree root we belong to, if any */ + struct rb_root *p_root; + /* sorted list of pending requests */ + struct rb_root sort_list; + /* if fifo isn't expired, next request to serve */ + struct request *next_rq; + /* requests queued in sort_list */ + int queued[2]; + /* currently allocated requests */ + int allocated[2]; + /* fifo list of requests in sort_list */ + struct list_head fifo; + + unsigned long slice_end; + long slice_resid; + unsigned int slice_dispatch; + + /* pending metadata requests */ + int meta_pending; + /* number of requests that are on the dispatch list or inside driver */ + int dispatched; + + /* io prio of this group */ + unsigned short ioprio, org_ioprio; + unsigned short ioprio_class, org_ioprio_class; + + pid_t pid; +}; + /* * Per block device queue structure */ @@ -135,51 +180,11 @@ struct cfq_data { unsigned int cfq_slice_idle; struct list_head cic_list; -}; -/* - * Per process-grouping structure - */ -struct cfq_queue { - /* reference count */ - atomic_t ref; - /* various state flags, see below */ - unsigned int flags; - /* parent cfq_data */ - struct cfq_data *cfqd; - /* service_tree member */ - struct rb_node rb_node; - /* service_tree key */ - unsigned long rb_key; - /* prio tree member */ - struct rb_node p_node; - /* prio tree root we belong to, if any */ - struct rb_root *p_root; - /* sorted list of pending requests */ - struct rb_root sort_list; - /* if fifo isn't expired, next request to serve */ - struct request *next_rq; - /* requests queued in sort_list */ - int queued[2]; - /* currently allocated requests */ - int allocated[2]; - /* fifo list of requests in sort_list */ - struct list_head fifo; - - unsigned long slice_end; - long slice_resid; - unsigned int slice_dispatch; - - /* pending metadata requests */ - int meta_pending; - /* number of requests that are on the dispatch list or inside driver */ - int dispatched; - - /* io prio of this group */ - unsigned short ioprio, org_ioprio; - unsigned short ioprio_class, org_ioprio_class; - - pid_t pid; + /* + * Fallback dummy cfqq for extreme OOM conditions + */ + struct cfq_queue oom_cfqq; }; enum cfqq_state_flags { @@ -1673,41 +1678,40 @@ retry: /* cic always exists here */ cfqq = cic_to_cfqq(cic, is_sync); - if (!cfqq) { + /* + * Always try a new alloc if we fell back to the OOM cfqq + * originally, since it should just be a temporary situation. + */ + if (!cfqq || cfqq == &cfqd->oom_cfqq) { + cfqq = NULL; if (new_cfqq) { cfqq = new_cfqq; new_cfqq = NULL; } else if (gfp_mask & __GFP_WAIT) { - /* - * Inform the allocator of the fact that we will - * just repeat this allocation if it fails, to allow - * the allocator to do whatever it needs to attempt to - * free memory. - */ spin_unlock_irq(cfqd->queue->queue_lock); new_cfqq = kmem_cache_alloc_node(cfq_pool, - gfp_mask | __GFP_NOFAIL | __GFP_ZERO, + gfp_mask | __GFP_ZERO, cfqd->queue->node); spin_lock_irq(cfqd->queue->queue_lock); - goto retry; + if (new_cfqq) + goto retry; } else { cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask | __GFP_ZERO, cfqd->queue->node); - if (!cfqq) - goto out; } - cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); - cfq_init_prio_data(cfqq, ioc); - cfq_log_cfqq(cfqd, cfqq, "alloced"); + if (cfqq) { + cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); + cfq_init_prio_data(cfqq, ioc); + cfq_log_cfqq(cfqd, cfqq, "alloced"); + } else + cfqq = &cfqd->oom_cfqq; } if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); -out: - WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq); return cfqq; } @@ -1740,11 +1744,8 @@ cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, cfqq = *async_cfqq; } - if (!cfqq) { + if (!cfqq) cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask); - if (!cfqq) - return NULL; - } /* * pin the queue now that it's allocated, scheduler exit will prune it @@ -2470,6 +2471,14 @@ static void *cfq_init_queue(struct request_queue *q) for (i = 0; i < CFQ_PRIO_LISTS; i++) cfqd->prio_trees[i] = RB_ROOT; + /* + * Our fallback cfqq if cfq_find_alloc_queue() runs into OOM issues. + * Grab a permanent reference to it, so that the normal code flow + * will not attempt to free it. + */ + cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0); + atomic_inc(&cfqd->oom_cfqq.ref); + INIT_LIST_HEAD(&cfqd->cic_list); cfqd->queue = q; -- cgit v1.2.3-70-g09d2 From 7878cba9f0037f5599004b03a1260b32d9050360 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Jun 2009 15:37:49 +0200 Subject: block: Create bip slabs with embedded integrity vectors This patch restores stacking ability to the block layer integrity infrastructure by creating a set of dedicated bip slabs. Each bip slab has an embedded bio_vec array at the end. This cuts down on memory allocations and also simplifies the code compared to the original bvec version. Only the largest bip slab is backed by a mempool. The pool is contained in the bio_set so stacking drivers can ensure forward progress. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- drivers/md/dm.c | 4 +- fs/bio-integrity.c | 170 ++++++++++++++++++++++++++++++++++++++-------------- fs/bio.c | 11 +++- include/linux/bio.h | 22 +++++-- 5 files changed, 152 insertions(+), 57 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index b06cf5c2a82..345d99da8d4 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2365,7 +2365,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, __bio_clone(bio, bio_src); if (bio_integrity(bio_src) && - bio_integrity_clone(bio, bio_src, gfp_mask)) + bio_integrity_clone(bio, bio_src, gfp_mask, bs)) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3c6d4ee8921..9acd54a5cff 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1017,7 +1017,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector, clone->bi_flags |= 1 << BIO_CLONED; if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO); + bio_integrity_clone(clone, bio, GFP_NOIO, bs); bio_integrity_trim(clone, bio_sector_offset(bio, idx, offset), len); } @@ -1045,7 +1045,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector, clone->bi_flags &= ~(1 << BIO_SEG_VALID); if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO); + bio_integrity_clone(clone, bio, GFP_NOIO, bs); if (idx != bio->bi_idx || clone->bi_size < bio->bi_size) bio_integrity_trim(clone, diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 31c46a241ba..49a34e7f730 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -1,7 +1,7 @@ /* * bio-integrity.c - bio data integrity extensions * - * Copyright (C) 2007, 2008 Oracle Corporation + * Copyright (C) 2007, 2008, 2009 Oracle Corporation * Written by: Martin K. Petersen * * This program is free software; you can redistribute it and/or @@ -25,63 +25,121 @@ #include #include -static struct kmem_cache *bio_integrity_slab __read_mostly; -static mempool_t *bio_integrity_pool; -static struct bio_set *integrity_bio_set; +struct integrity_slab { + struct kmem_cache *slab; + unsigned short nr_vecs; + char name[8]; +}; + +#define IS(x) { .nr_vecs = x, .name = "bip-"__stringify(x) } +struct integrity_slab bip_slab[BIOVEC_NR_POOLS] __read_mostly = { + IS(1), IS(4), IS(16), IS(64), IS(128), IS(BIO_MAX_PAGES), +}; +#undef IS + static struct workqueue_struct *kintegrityd_wq; +static inline unsigned int vecs_to_idx(unsigned int nr) +{ + switch (nr) { + case 1: + return 0; + case 2 ... 4: + return 1; + case 5 ... 16: + return 2; + case 17 ... 64: + return 3; + case 65 ... 128: + return 4; + case 129 ... BIO_MAX_PAGES: + return 5; + default: + BUG(); + } +} + +static inline int use_bip_pool(unsigned int idx) +{ + if (idx == BIOVEC_NR_POOLS) + return 1; + + return 0; +} + /** - * bio_integrity_alloc - Allocate integrity payload and attach it to bio + * bio_integrity_alloc_bioset - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to * @gfp_mask: Memory allocation mask * @nr_vecs: Number of integrity metadata scatter-gather elements + * @bs: bio_set to allocate from * * Description: This function prepares a bio for attaching integrity * metadata. nr_vecs specifies the maximum number of pages containing * integrity metadata that can be attached. */ -struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, - gfp_t gfp_mask, - unsigned int nr_vecs) +struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio, + gfp_t gfp_mask, + unsigned int nr_vecs, + struct bio_set *bs) { struct bio_integrity_payload *bip; - struct bio_vec *iv; - unsigned long idx; + unsigned int idx = vecs_to_idx(nr_vecs); BUG_ON(bio == NULL); + bip = NULL; - bip = mempool_alloc(bio_integrity_pool, gfp_mask); - if (unlikely(bip == NULL)) { - printk(KERN_ERR "%s: could not alloc bip\n", __func__); - return NULL; - } + /* Lower order allocations come straight from slab */ + if (!use_bip_pool(idx)) + bip = kmem_cache_alloc(bip_slab[idx].slab, gfp_mask); - memset(bip, 0, sizeof(*bip)); + /* Use mempool if lower order alloc failed or max vecs were requested */ + if (bip == NULL) { + bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask); - iv = bvec_alloc_bs(gfp_mask, nr_vecs, &idx, integrity_bio_set); - if (unlikely(iv == NULL)) { - printk(KERN_ERR "%s: could not alloc bip_vec\n", __func__); - mempool_free(bip, bio_integrity_pool); - return NULL; + if (unlikely(bip == NULL)) { + printk(KERN_ERR "%s: could not alloc bip\n", __func__); + return NULL; + } } - bip->bip_pool = idx; - bip->bip_vec = iv; + memset(bip, 0, sizeof(*bip)); + + bip->bip_slab = idx; bip->bip_bio = bio; bio->bi_integrity = bip; return bip; } +EXPORT_SYMBOL(bio_integrity_alloc_bioset); + +/** + * bio_integrity_alloc - Allocate integrity payload and attach it to bio + * @bio: bio to attach integrity metadata to + * @gfp_mask: Memory allocation mask + * @nr_vecs: Number of integrity metadata scatter-gather elements + * + * Description: This function prepares a bio for attaching integrity + * metadata. nr_vecs specifies the maximum number of pages containing + * integrity metadata that can be attached. + */ +struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, + gfp_t gfp_mask, + unsigned int nr_vecs) +{ + return bio_integrity_alloc_bioset(bio, gfp_mask, nr_vecs, fs_bio_set); +} EXPORT_SYMBOL(bio_integrity_alloc); /** * bio_integrity_free - Free bio integrity payload * @bio: bio containing bip to be freed + * @bs: bio_set this bio was allocated from * * Description: Used to free the integrity portion of a bio. Usually * called from bio_free(). */ -void bio_integrity_free(struct bio *bio) +void bio_integrity_free(struct bio *bio, struct bio_set *bs) { struct bio_integrity_payload *bip = bio->bi_integrity; @@ -92,8 +150,10 @@ void bio_integrity_free(struct bio *bio) && bip->bip_buf != NULL) kfree(bip->bip_buf); - bvec_free_bs(integrity_bio_set, bip->bip_vec, bip->bip_pool); - mempool_free(bip, bio_integrity_pool); + if (use_bip_pool(bip->bip_slab)) + mempool_free(bip, bs->bio_integrity_pool); + else + kmem_cache_free(bip_slab[bip->bip_slab].slab, bip); bio->bi_integrity = NULL; } @@ -114,7 +174,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, struct bio_integrity_payload *bip = bio->bi_integrity; struct bio_vec *iv; - if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_pool)) { + if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) { printk(KERN_ERR "%s: bip_vec full\n", __func__); return 0; } @@ -647,8 +707,8 @@ void bio_integrity_split(struct bio *bio, struct bio_pair *bp, int sectors) bp->iv1 = bip->bip_vec[0]; bp->iv2 = bip->bip_vec[0]; - bp->bip1.bip_vec = &bp->iv1; - bp->bip2.bip_vec = &bp->iv2; + bp->bip1.bip_vec[0] = bp->iv1; + bp->bip2.bip_vec[0] = bp->iv2; bp->iv1.bv_len = sectors * bi->tuple_size; bp->iv2.bv_offset += sectors * bi->tuple_size; @@ -667,17 +727,19 @@ EXPORT_SYMBOL(bio_integrity_split); * @bio: New bio * @bio_src: Original bio * @gfp_mask: Memory allocation mask + * @bs: bio_set to allocate bip from * * Description: Called to allocate a bip when cloning a bio */ -int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) +int bio_integrity_clone(struct bio *bio, struct bio *bio_src, + gfp_t gfp_mask, struct bio_set *bs) { struct bio_integrity_payload *bip_src = bio_src->bi_integrity; struct bio_integrity_payload *bip; BUG_ON(bip_src == NULL); - bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt); + bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs); if (bip == NULL) return -EIO; @@ -693,25 +755,43 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) } EXPORT_SYMBOL(bio_integrity_clone); -static int __init bio_integrity_init(void) +int bioset_integrity_create(struct bio_set *bs, int pool_size) { - kintegrityd_wq = create_workqueue("kintegrityd"); + unsigned int max_slab = vecs_to_idx(BIO_MAX_PAGES); + + bs->bio_integrity_pool = + mempool_create_slab_pool(pool_size, bip_slab[max_slab].slab); + if (!bs->bio_integrity_pool) + return -1; + + return 0; +} +EXPORT_SYMBOL(bioset_integrity_create); + +void bioset_integrity_free(struct bio_set *bs) +{ + if (bs->bio_integrity_pool) + mempool_destroy(bs->bio_integrity_pool); +} +EXPORT_SYMBOL(bioset_integrity_free); + +void __init bio_integrity_init(void) +{ + unsigned int i; + + kintegrityd_wq = create_workqueue("kintegrityd"); if (!kintegrityd_wq) panic("Failed to create kintegrityd\n"); - bio_integrity_slab = KMEM_CACHE(bio_integrity_payload, - SLAB_HWCACHE_ALIGN|SLAB_PANIC); + for (i = 0 ; i < BIOVEC_NR_POOLS ; i++) { + unsigned int size; - bio_integrity_pool = mempool_create_slab_pool(BIO_POOL_SIZE, - bio_integrity_slab); - if (!bio_integrity_pool) - panic("bio_integrity: can't allocate bip pool\n"); + size = sizeof(struct bio_integrity_payload) + + bip_slab[i].nr_vecs * sizeof(struct bio_vec); - integrity_bio_set = bioset_create(BIO_POOL_SIZE, 0); - if (!integrity_bio_set) - panic("bio_integrity: can't allocate bio_set\n"); - - return 0; + bip_slab[i].slab = + kmem_cache_create(bip_slab[i].name, size, 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + } } -subsys_initcall(bio_integrity_init); diff --git a/fs/bio.c b/fs/bio.c index 24c91404353..1486b19fc43 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -238,7 +238,7 @@ void bio_free(struct bio *bio, struct bio_set *bs) bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio)); if (bio_integrity(bio)) - bio_integrity_free(bio); + bio_integrity_free(bio, bs); /* * If we have front padding, adjust the bio pointer before freeing @@ -341,7 +341,7 @@ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs) static void bio_kmalloc_destructor(struct bio *bio) { if (bio_integrity(bio)) - bio_integrity_free(bio); + bio_integrity_free(bio, fs_bio_set); kfree(bio); } @@ -472,7 +472,7 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask) if (bio_integrity(bio)) { int ret; - ret = bio_integrity_clone(b, bio, gfp_mask); + ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set); if (ret < 0) { bio_put(b); @@ -1539,6 +1539,7 @@ void bioset_free(struct bio_set *bs) if (bs->bio_pool) mempool_destroy(bs->bio_pool); + bioset_integrity_free(bs); biovec_free_pools(bs); bio_put_slab(bs); @@ -1579,6 +1580,9 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad) if (!bs->bio_pool) goto bad; + if (bioset_integrity_create(bs, pool_size)) + goto bad; + if (!biovec_create_pools(bs, pool_size)) return bs; @@ -1616,6 +1620,7 @@ static int __init init_bio(void) if (!bio_slabs) panic("bio: can't allocate bios\n"); + bio_integrity_init(); biovec_init_slabs(); fs_bio_set = bioset_create(BIO_POOL_SIZE, 0); diff --git a/include/linux/bio.h b/include/linux/bio.h index 2a04eb54c0d..2892b710771 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -319,7 +319,6 @@ static inline int bio_has_allocated_vec(struct bio *bio) */ struct bio_integrity_payload { struct bio *bip_bio; /* parent bio */ - struct bio_vec *bip_vec; /* integrity data vector */ sector_t bip_sector; /* virtual start sector */ @@ -328,11 +327,12 @@ struct bio_integrity_payload { unsigned int bip_size; - unsigned short bip_pool; /* pool the ivec came from */ + unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_idx; /* current bip_vec index */ struct work_struct bip_work; /* I/O completion */ + struct bio_vec bip_vec[0]; /* embedded bvec array */ }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -430,6 +430,9 @@ struct bio_set { unsigned int front_pad; mempool_t *bio_pool; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + mempool_t *bio_integrity_pool; +#endif mempool_t *bvec_pool; }; @@ -634,8 +637,9 @@ static inline struct bio *bio_list_get(struct bio_list *bl) #define bio_integrity(bio) (bio->bi_integrity != NULL) +extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *); extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern void bio_integrity_free(struct bio *); +extern void bio_integrity_free(struct bio *, struct bio_set *); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern int bio_integrity_enabled(struct bio *bio); extern int bio_integrity_set_tag(struct bio *, void *, unsigned int); @@ -645,21 +649,27 @@ extern void bio_integrity_endio(struct bio *, int); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); extern void bio_integrity_split(struct bio *, struct bio_pair *, int); -extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); +extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t, struct bio_set *); +extern int bioset_integrity_create(struct bio_set *, int); +extern void bioset_integrity_free(struct bio_set *); +extern void bio_integrity_init(void); #else /* CONFIG_BLK_DEV_INTEGRITY */ #define bio_integrity(a) (0) +#define bioset_integrity_create(a, b) (0) #define bio_integrity_prep(a) (0) #define bio_integrity_enabled(a) (0) -#define bio_integrity_clone(a, b, c) (0) -#define bio_integrity_free(a) do { } while (0) +#define bio_integrity_clone(a, b, c, d) (0) +#define bioset_integrity_free(a) do { } while (0) +#define bio_integrity_free(a, b) do { } while (0) #define bio_integrity_endio(a, b) do { } while (0) #define bio_integrity_advance(a, b) do { } while (0) #define bio_integrity_trim(a, b, c) do { } while (0) #define bio_integrity_split(a, b, c) do { } while (0) #define bio_integrity_set_tag(a, b, c) do { } while (0) #define bio_integrity_get_tag(a, b, c) do { } while (0) +#define bio_integrity_init(a) do { } while (0) #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3-70-g09d2 From 018e0446890661504783f92388ecce7138c1566d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Jun 2009 16:27:10 +0200 Subject: block: get rid of queue-private command filter The initial patches to support this through sysfs export were broken and have been if 0'ed out in any release. So lets just kill the code and reclaim some space in struct request_queue, if anyone would later like to fixup the sysfs bits, the git history can easily restore the removed bits. Signed-off-by: Jens Axboe --- block/Makefile | 2 +- block/blk-core.c | 2 - block/bsg.c | 2 +- block/cmd-filter.c | 233 ------------------------------------------------- block/scsi_ioctl.c | 43 +++++++-- drivers/scsi/sg.c | 4 +- include/linux/blkdev.h | 15 +--- 7 files changed, 42 insertions(+), 259 deletions(-) delete mode 100644 block/cmd-filter.c diff --git a/block/Makefile b/block/Makefile index e9fa4dd690f..6c54ed0ff75 100644 --- a/block/Makefile +++ b/block/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \ blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \ - ioctl.o genhd.o scsi_ioctl.o cmd-filter.o + ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o diff --git a/block/blk-core.c b/block/blk-core.c index 345d99da8d4..02b87134a16 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -595,8 +595,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) q->sg_reserved_size = INT_MAX; - blk_set_cmd_filter_defaults(&q->cmd_filter); - /* * all done */ diff --git a/block/bsg.c b/block/bsg.c index e7d47525424..5f184bb3ff9 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -186,7 +186,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, return -EFAULT; if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) { - if (blk_verify_command(&q->cmd_filter, rq->cmd, has_write_perm)) + if (blk_verify_command(rq->cmd, has_write_perm)) return -EPERM; } else if (!capable(CAP_SYS_RAWIO)) return -EPERM; diff --git a/block/cmd-filter.c b/block/cmd-filter.c deleted file mode 100644 index 572bbc2f900..00000000000 --- a/block/cmd-filter.c +++ /dev/null @@ -1,233 +0,0 @@ -/* - * Copyright 2004 Peter M. Jones - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public Licens - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- - * - */ - -#include -#include -#include -#include -#include -#include - -#include -#include - -int blk_verify_command(struct blk_cmd_filter *filter, - unsigned char *cmd, fmode_t has_write_perm) -{ - /* root can do any command. */ - if (capable(CAP_SYS_RAWIO)) - return 0; - - /* if there's no filter set, assume we're filtering everything out */ - if (!filter) - return -EPERM; - - /* Anybody who can open the device can do a read-safe command */ - if (test_bit(cmd[0], filter->read_ok)) - return 0; - - /* Write-safe commands require a writable open */ - if (test_bit(cmd[0], filter->write_ok) && has_write_perm) - return 0; - - return -EPERM; -} -EXPORT_SYMBOL(blk_verify_command); - -#if 0 -/* and now, the sysfs stuff */ -static ssize_t rcf_cmds_show(struct blk_cmd_filter *filter, char *page, - int rw) -{ - char *npage = page; - unsigned long *okbits; - int i; - - if (rw == READ) - okbits = filter->read_ok; - else - okbits = filter->write_ok; - - for (i = 0; i < BLK_SCSI_MAX_CMDS; i++) { - if (test_bit(i, okbits)) { - npage += sprintf(npage, "0x%02x", i); - if (i < BLK_SCSI_MAX_CMDS - 1) - sprintf(npage++, " "); - } - } - - if (npage != page) - npage += sprintf(npage, "\n"); - - return npage - page; -} - -static ssize_t rcf_readcmds_show(struct blk_cmd_filter *filter, char *page) -{ - return rcf_cmds_show(filter, page, READ); -} - -static ssize_t rcf_writecmds_show(struct blk_cmd_filter *filter, - char *page) -{ - return rcf_cmds_show(filter, page, WRITE); -} - -static ssize_t rcf_cmds_store(struct blk_cmd_filter *filter, - const char *page, size_t count, int rw) -{ - unsigned long okbits[BLK_SCSI_CMD_PER_LONG], *target_okbits; - int cmd, set; - char *p, *status; - - if (rw == READ) { - memcpy(&okbits, filter->read_ok, sizeof(okbits)); - target_okbits = filter->read_ok; - } else { - memcpy(&okbits, filter->write_ok, sizeof(okbits)); - target_okbits = filter->write_ok; - } - - while ((p = strsep((char **)&page, " ")) != NULL) { - set = 1; - - if (p[0] == '+') { - p++; - } else if (p[0] == '-') { - set = 0; - p++; - } - - cmd = simple_strtol(p, &status, 16); - - /* either of these cases means invalid input, so do nothing. */ - if ((status == p) || cmd >= BLK_SCSI_MAX_CMDS) - return -EINVAL; - - if (set) - __set_bit(cmd, okbits); - else - __clear_bit(cmd, okbits); - } - - memcpy(target_okbits, okbits, sizeof(okbits)); - return count; -} - -static ssize_t rcf_readcmds_store(struct blk_cmd_filter *filter, - const char *page, size_t count) -{ - return rcf_cmds_store(filter, page, count, READ); -} - -static ssize_t rcf_writecmds_store(struct blk_cmd_filter *filter, - const char *page, size_t count) -{ - return rcf_cmds_store(filter, page, count, WRITE); -} - -struct rcf_sysfs_entry { - struct attribute attr; - ssize_t (*show)(struct blk_cmd_filter *, char *); - ssize_t (*store)(struct blk_cmd_filter *, const char *, size_t); -}; - -static struct rcf_sysfs_entry rcf_readcmds_entry = { - .attr = { .name = "read_table", .mode = S_IRUGO | S_IWUSR }, - .show = rcf_readcmds_show, - .store = rcf_readcmds_store, -}; - -static struct rcf_sysfs_entry rcf_writecmds_entry = { - .attr = {.name = "write_table", .mode = S_IRUGO | S_IWUSR }, - .show = rcf_writecmds_show, - .store = rcf_writecmds_store, -}; - -static struct attribute *default_attrs[] = { - &rcf_readcmds_entry.attr, - &rcf_writecmds_entry.attr, - NULL, -}; - -#define to_rcf(atr) container_of((atr), struct rcf_sysfs_entry, attr) - -static ssize_t -rcf_attr_show(struct kobject *kobj, struct attribute *attr, char *page) -{ - struct rcf_sysfs_entry *entry = to_rcf(attr); - struct blk_cmd_filter *filter; - - filter = container_of(kobj, struct blk_cmd_filter, kobj); - if (entry->show) - return entry->show(filter, page); - - return 0; -} - -static ssize_t -rcf_attr_store(struct kobject *kobj, struct attribute *attr, - const char *page, size_t length) -{ - struct rcf_sysfs_entry *entry = to_rcf(attr); - struct blk_cmd_filter *filter; - - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - - if (!entry->store) - return -EINVAL; - - filter = container_of(kobj, struct blk_cmd_filter, kobj); - return entry->store(filter, page, length); -} - -static struct sysfs_ops rcf_sysfs_ops = { - .show = rcf_attr_show, - .store = rcf_attr_store, -}; - -static struct kobj_type rcf_ktype = { - .sysfs_ops = &rcf_sysfs_ops, - .default_attrs = default_attrs, -}; - -int blk_register_filter(struct gendisk *disk) -{ - int ret; - struct blk_cmd_filter *filter = &disk->queue->cmd_filter; - - ret = kobject_init_and_add(&filter->kobj, &rcf_ktype, - &disk_to_dev(disk)->kobj, - "%s", "cmd_filter"); - if (ret < 0) - return ret; - - return 0; -} -EXPORT_SYMBOL(blk_register_filter); - -void blk_unregister_filter(struct gendisk *disk) -{ - struct blk_cmd_filter *filter = &disk->queue->cmd_filter; - - kobject_put(&filter->kobj); -} -EXPORT_SYMBOL(blk_unregister_filter); -#endif diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 5f8e798ede4..f0e0ce0a607 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -32,6 +32,11 @@ #include #include +struct blk_cmd_filter { + unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; + unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; +} blk_default_cmd_filter; + /* Command group 3 is reserved and should never be used. */ const unsigned char scsi_command_size_tbl[8] = { @@ -105,7 +110,7 @@ static int sg_emulated_host(struct request_queue *q, int __user *p) return put_user(1, p); } -void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) +static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) { /* Basic read-only commands */ __set_bit(TEST_UNIT_READY, filter->read_ok); @@ -187,14 +192,37 @@ void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) __set_bit(GPCMD_SET_STREAMING, filter->write_ok); __set_bit(GPCMD_SET_READ_AHEAD, filter->write_ok); } -EXPORT_SYMBOL_GPL(blk_set_cmd_filter_defaults); + +int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm) +{ + struct blk_cmd_filter *filter = &blk_default_cmd_filter; + + /* root can do any command. */ + if (capable(CAP_SYS_RAWIO)) + return 0; + + /* if there's no filter set, assume we're filtering everything out */ + if (!filter) + return -EPERM; + + /* Anybody who can open the device can do a read-safe command */ + if (test_bit(cmd[0], filter->read_ok)) + return 0; + + /* Write-safe commands require a writable open */ + if (test_bit(cmd[0], filter->write_ok) && has_write_perm) + return 0; + + return -EPERM; +} +EXPORT_SYMBOL(blk_verify_command); static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, struct sg_io_hdr *hdr, fmode_t mode) { if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len)) return -EFAULT; - if (blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE)) + if (blk_verify_command(rq->cmd, mode & FMODE_WRITE)) return -EPERM; /* @@ -427,7 +455,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len)) goto error; - err = blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE); + err = blk_verify_command(rq->cmd, mode & FMODE_WRITE); if (err) goto error; @@ -645,5 +673,10 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod blk_put_queue(q); return err; } - EXPORT_SYMBOL(scsi_cmd_ioctl); + +int __init blk_scsi_ioctl_init(void) +{ + blk_set_cmd_filter_defaults(&blk_default_cmd_filter); + return 0; +} diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 8201387b4da..ef142fd47a8 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -210,13 +210,11 @@ static void sg_put_dev(Sg_device *sdp); static int sg_allow_access(struct file *filp, unsigned char *cmd) { struct sg_fd *sfp = (struct sg_fd *)filp->private_data; - struct request_queue *q = sfp->parentdp->device->request_queue; if (sfp->parentdp->device->type == TYPE_SCANNER) return 0; - return blk_verify_command(&q->cmd_filter, - cmd, filp->f_mode & FMODE_WRITE); + return blk_verify_command(cmd, filp->f_mode & FMODE_WRITE); } static int diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8963d9149b5..49ae07951d5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -301,12 +301,6 @@ struct blk_queue_tag { #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) -struct blk_cmd_filter { - unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; - unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; - struct kobject kobj; -}; - struct queue_limits { unsigned long bounce_pfn; unsigned long seg_boundary_mask; @@ -445,7 +439,6 @@ struct request_queue #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif - struct blk_cmd_filter cmd_filter; }; #define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ @@ -998,13 +991,7 @@ static inline int sb_issue_discard(struct super_block *sb, return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL); } -/* -* command filter functions -*/ -extern int blk_verify_command(struct blk_cmd_filter *filter, - unsigned char *cmd, fmode_t has_write_perm); -extern void blk_unregister_filter(struct gendisk *disk); -extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); +extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); #define MAX_PHYS_SEGMENTS 128 #define MAX_HW_SEGMENTS 128 -- cgit v1.2.3-70-g09d2 From db64f680ba4b5c56c4be59f0698000df89ff0281 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 30 Jun 2009 09:35:44 +0200 Subject: blocK: Restore barrier support for md and probably other virtual devices. The next_ordered flag is only meaningful for devices that use __make_request. So move the test against next_ordered out of generic code and in to __make_request Since this test was added, barriers have not worked on md or any devices that don't use __make_request and so don't bother to set next_ordered. (dm explicitly sets something other than QUEUE_ORDERED_NONE since commit 99360b4c18f7675b50d283301d46d755affe75fd but notes in the comments that it is otherwise meaningless). Cc: Ken Milmore Cc: stable@kernel.org Signed-off-by: NeilBrown Signed-off-by: Jens Axboe --- block/blk-core.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 02b87134a16..4b45435c6ea 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1170,6 +1170,11 @@ static int __make_request(struct request_queue *q, struct bio *bio) const int unplug = bio_unplug(bio); int rw_flags; + if (bio_barrier(bio) && bio_has_data(bio) && + (q->next_ordered == QUEUE_ORDERED_NONE)) { + bio_endio(bio, -EOPNOTSUPP); + return 0; + } /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even @@ -1470,11 +1475,6 @@ static inline void __generic_make_request(struct bio *bio) err = -EOPNOTSUPP; goto end_io; } - if (bio_barrier(bio) && bio_has_data(bio) && - (q->next_ordered == QUEUE_ORDERED_NONE)) { - err = -EOPNOTSUPP; - goto end_io; - } ret = q->make_request_fn(q, bio); } while (ret); -- cgit v1.2.3-70-g09d2 From b706f64281b24d8b1fdc8ae883700131d365c412 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Wed, 1 Jul 2009 12:41:14 +0200 Subject: cfq-iosched: remove redundant check for NULL cfqq in cfq_set_request() With the changes for falling back to an oom_cfqq, we never fail to find/allocate a queue in cfq_get_queue(). So remove the check. Signed-off-by: Shan Wei Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 1d9160ffa26..87276eb83f7 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -2313,10 +2313,6 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) cfqq = cic_to_cfqq(cic, is_sync); if (!cfqq) { cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask); - - if (!cfqq) - goto queue_fail; - cic_set_cfqq(cic, cfqq, is_sync); } -- cgit v1.2.3-70-g09d2