X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fbio.h;h=2aa283ab062b215ddb37975d8e55193ecd502c5f;hb=b1792e367053968f2ddb48bc911d314143ce6242;hp=9e93c9299479054aa0273ff65b144c6f161b4719;hpb=7a67f63b3233ff28e753854fe27891c44f8588ae;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/linux/bio.h b/include/linux/bio.h index 9e93c92..2aa283a 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -26,21 +26,8 @@ #ifdef CONFIG_BLOCK -/* Platforms may set this to teach the BIO layer about IOMMU hardware. */ #include -#if defined(BIO_VMERGE_MAX_SIZE) && defined(BIO_VMERGE_BOUNDARY) -#define BIOVEC_VIRT_START_SIZE(x) (bvec_to_phys(x) & (BIO_VMERGE_BOUNDARY - 1)) -#define BIOVEC_VIRT_OVERSIZE(x) ((x) > BIO_VMERGE_MAX_SIZE) -#else -#define BIOVEC_VIRT_START_SIZE(x) 0 -#define BIOVEC_VIRT_OVERSIZE(x) 0 -#endif - -#ifndef BIO_VMERGE_BOUNDARY -#define BIO_VMERGE_BOUNDARY 0 -#endif - #define BIO_DEBUG #ifdef BIO_DEBUG @@ -88,29 +75,26 @@ struct bio { /* Number of segments in this BIO after * physical address coalescing is performed. */ - unsigned short bi_phys_segments; - - /* Number of segments after physical and DMA remapping - * hardware coalescing is performed. - */ - unsigned short bi_hw_segments; + unsigned int bi_phys_segments; unsigned int bi_size; /* residual I/O count */ /* - * To keep track of the max hw size, we account for the - * sizes of the first and last virtually mergeable segments - * in this bio + * To keep track of the max segment size, we account for the + * sizes of the first and last mergeable segments in this bio. */ - unsigned int bi_hw_front_size; - unsigned int bi_hw_back_size; + unsigned int bi_seg_front_size; + unsigned int bi_seg_back_size; unsigned int bi_max_vecs; /* max bvl_vecs we can hold */ + unsigned int bi_comp_cpu; /* completion CPU */ + + atomic_t bi_cnt; /* pin count */ + struct bio_vec *bi_io_vec; /* the actual vec list */ bio_end_io_t *bi_end_io; - atomic_t bi_cnt; /* pin count */ void *bi_private; #if defined(CONFIG_BLK_DEV_INTEGRITY) @@ -118,6 +102,13 @@ struct bio { #endif bio_destructor_t *bi_destructor; /* destructor */ + + /* + * We can inline a number of vecs at the end of the bio, to avoid + * double allocations for a small number of bio_vecs. This member + * MUST obviously be kept at the very end of the bio. + */ + struct bio_vec bi_inline_vecs[0]; }; /* @@ -126,11 +117,15 @@ struct bio { #define BIO_UPTODATE 0 /* ok after I/O completion */ #define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */ #define BIO_EOF 2 /* out-out-bounds error */ -#define BIO_SEG_VALID 3 /* nr_hw_seg valid */ +#define BIO_SEG_VALID 3 /* bi_phys_segments valid */ #define BIO_CLONED 4 /* doesn't own data */ #define BIO_BOUNCED 5 /* bio is a bounce bio */ #define BIO_USER_MAPPED 6 /* contains user pages */ #define BIO_EOPNOTSUPP 7 /* not supported */ +#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */ +#define BIO_NULL_MAPPED 9 /* contains invalid user pages */ +#define BIO_FS_INTEGRITY 10 /* fs owns integrity data, not block layer */ +#define BIO_QUIET 11 /* Make BIO Quiet */ #define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) /* @@ -144,18 +139,57 @@ struct bio { /* * bio bi_rw flags * - * bit 0 -- read (not set) or write (set) + * bit 0 -- data direction + * If not set, bio is a read from device. If set, it's a write to device. * bit 1 -- rw-ahead when set * bit 2 -- barrier - * bit 3 -- fail fast, don't want low level driver retries - * bit 4 -- synchronous I/O hint: the block layer will unplug immediately + * Insert a serialization point in the IO queue, forcing previously + * submitted IO to be completed before this one is issued. + * bit 3 -- synchronous I/O hint: the block layer will unplug immediately + * Note that this does NOT indicate that the IO itself is sync, just + * that the block layer will not postpone issue of this IO by plugging. + * bit 4 -- metadata request + * Used for tracing to differentiate metadata and data IO. May also + * get some preferential treatment in the IO scheduler + * bit 5 -- discard sectors + * Informs the lower level device that this range of sectors is no longer + * used by the file system and may thus be freed by the device. Used + * for flash based storage. + * bit 6 -- fail fast device errors + * bit 7 -- fail fast transport errors + * bit 8 -- fail fast driver errors + * Don't want driver retries for any fast fail whatever the reason. */ -#define BIO_RW 0 -#define BIO_RW_AHEAD 1 +#define BIO_RW 0 /* Must match RW in req flags (blkdev.h) */ +#define BIO_RW_AHEAD 1 /* Must match FAILFAST in req flags */ #define BIO_RW_BARRIER 2 -#define BIO_RW_FAILFAST 3 -#define BIO_RW_SYNC 4 +#define BIO_RW_SYNCIO 3 +#define BIO_RW_UNPLUG 4 #define BIO_RW_META 5 +#define BIO_RW_DISCARD 6 +#define BIO_RW_FAILFAST_DEV 7 +#define BIO_RW_FAILFAST_TRANSPORT 8 +#define BIO_RW_FAILFAST_DRIVER 9 + +#define BIO_RW_SYNC (BIO_RW_SYNCIO | BIO_RW_UNPLUG) + +#define bio_rw_flagged(bio, flag) ((bio)->bi_rw & (1 << (flag))) + +/* + * Old defines, these should eventually be replaced by direct usage of + * bio_rw_flagged() + */ +#define bio_barrier(bio) bio_rw_flagged(bio, BIO_RW_BARRIER) +#define bio_sync(bio) bio_rw_flagged(bio, BIO_RW_SYNCIO) +#define bio_unplug(bio) bio_rw_flagged(bio, BIO_RW_UNPLUG) +#define bio_failfast_dev(bio) bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV) +#define bio_failfast_transport(bio) \ + bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT) +#define bio_failfast_driver(bio) \ + bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER) +#define bio_rw_ahead(bio) bio_rw_flagged(bio, BIO_RW_AHEAD) +#define bio_rw_meta(bio) bio_rw_flagged(bio, BIO_RW_META) +#define bio_discard(bio) bio_rw_flagged(bio, BIO_RW_DISCARD) /* * upper 16 bits of bi_rw define the io priority of this bio @@ -180,19 +214,14 @@ struct bio { #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_barrier(bio) ((bio)->bi_rw & (1 << BIO_RW_BARRIER)) -#define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNC)) -#define bio_failfast(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST)) -#define bio_rw_ahead(bio) ((bio)->bi_rw & (1 << BIO_RW_AHEAD)) -#define bio_rw_meta(bio) ((bio)->bi_rw & (1 << BIO_RW_META)) -#define bio_empty_barrier(bio) (bio_barrier(bio) && !(bio)->bi_size) +#define bio_empty_barrier(bio) (bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio)) static inline unsigned int bio_cur_sectors(struct bio *bio) { if (bio->bi_vcnt) return bio_iovec(bio)->bv_len >> 9; - - return 0; + else /* dataless requests such as discard */ + return bio->bi_size >> 9; } static inline void *bio_data(struct bio *bio) @@ -203,6 +232,11 @@ static inline void *bio_data(struct bio *bio) return NULL; } +static inline int bio_has_allocated_vec(struct bio *bio) +{ + return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs; +} + /* * will die */ @@ -228,16 +262,18 @@ static inline void *bio_data(struct bio *bio) #define __BVEC_END(bio) bio_iovec_idx((bio), (bio)->bi_vcnt - 1) #define __BVEC_START(bio) bio_iovec_idx((bio), (bio)->bi_idx) +/* Default implementation of BIOVEC_PHYS_MERGEABLE */ +#define __BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) + /* * allow arch override, for eg virtualized architectures (put in asm/io.h) */ #ifndef BIOVEC_PHYS_MERGEABLE #define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) + __BIOVEC_PHYS_MERGEABLE(vec1, vec2) #endif -#define BIOVEC_VIRT_MERGEABLE(vec1, vec2) \ - ((((bvec_to_phys((vec1)) + (vec1)->bv_len) | bvec_to_phys((vec2))) & (BIO_VMERGE_BOUNDARY - 1)) == 0) #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \ (((addr1) | (mask)) == (((addr2) - 1) | (mask))) #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ @@ -288,7 +324,6 @@ struct bio_integrity_payload { void *bip_buf; /* generated integrity data */ bio_end_io_t *bip_end_io; /* saved I/O completion fn */ - int bip_error; /* saved I/O error */ unsigned int bip_size; unsigned short bip_pool; /* pool the ivec came from */ @@ -319,15 +354,14 @@ struct bio_pair { atomic_t cnt; int error; }; -extern struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, - int first_sectors); -extern mempool_t *bio_split_pool; +extern struct bio_pair *bio_split(struct bio *bi, int first_sectors); extern void bio_pair_release(struct bio_pair *dbio); -extern struct bio_set *bioset_create(int, int); +extern struct bio_set *bioset_create(unsigned int, unsigned int); extern void bioset_free(struct bio_set *); extern struct bio *bio_alloc(gfp_t, int); +extern struct bio *bio_kmalloc(gfp_t, int); extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *); extern void bio_put(struct bio *); extern void bio_free(struct bio *, struct bio_set *); @@ -335,7 +369,6 @@ extern void bio_free(struct bio *, struct bio_set *); extern void bio_endio(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); -extern int bio_hw_segments(struct request_queue *, struct bio *); extern void __bio_clone(struct bio *, struct bio *); extern struct bio *bio_clone(struct bio *, gfp_t); @@ -346,12 +379,14 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); extern int bio_get_nr_vecs(struct block_device *); +extern sector_t bio_sector_offset(struct bio *, unsigned short, unsigned int); extern struct bio *bio_map_user(struct request_queue *, struct block_device *, - unsigned long, unsigned int, int); + unsigned long, unsigned int, int, gfp_t); struct sg_iovec; +struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, struct block_device *, - struct sg_iovec *, int, int); + struct sg_iovec *, int, int, gfp_t); extern void bio_unmap_user(struct bio *); extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int, gfp_t); @@ -359,15 +394,26 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, gfp_t, int); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -extern struct bio *bio_copy_user(struct request_queue *, unsigned long, unsigned int, int); -extern struct bio *bio_copy_user_iov(struct request_queue *, struct sg_iovec *, - int, int); +extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, + unsigned long, unsigned int, int, gfp_t); +extern struct bio *bio_copy_user_iov(struct request_queue *, + struct rq_map_data *, struct sg_iovec *, + int, int, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio(struct bio *bio); extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *); +extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); /* + * Allow queuer to specify a completion CPU for this bio + */ +static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu) +{ + bio->bi_comp_cpu = cpu; +} + +/* * bio_set is used to allow other portions of the IO system to * allocate their own private memory pools for bio and iovec structures. * These memory pools in turn all allocate from the bio_slab @@ -375,13 +421,17 @@ extern unsigned int bvec_nr_vecs(unsigned short idx); */ #define BIO_POOL_SIZE 2 #define BIOVEC_NR_POOLS 6 +#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) struct bio_set { + struct kmem_cache *bio_slab; + unsigned int front_pad; + mempool_t *bio_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) mempool_t *bio_integrity_pool; #endif - mempool_t *bvec_pools[BIOVEC_NR_POOLS]; + mempool_t *bvec_pool; }; struct biovec_slab { @@ -391,6 +441,7 @@ struct biovec_slab { }; extern struct bio_set *fs_bio_set; +extern struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly; /* * a small number of entries is fine, not going to be performance critical. @@ -400,12 +451,13 @@ extern struct bio_set *fs_bio_set; #ifdef CONFIG_HIGHMEM /* - * remember to add offset! and never ever reenable interrupts between a - * bvec_kmap_irq and bvec_kunmap_irq!! + * remember never ever reenable interrupts between a bvec_kmap_irq and + * bvec_kunmap_irq! * * This function MUST be inlined - it plays with the CPU interrupt flags. */ -static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) +static __always_inline char *bvec_kmap_irq(struct bio_vec *bvec, + unsigned long *flags) { unsigned long addr; @@ -421,7 +473,8 @@ static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) return (char *) addr + bvec->bv_offset; } -static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) +static __always_inline void bvec_kunmap_irq(char *buffer, + unsigned long *flags) { unsigned long ptr = (unsigned long) buffer & PAGE_MASK; @@ -466,14 +519,7 @@ static inline int bio_has_data(struct bio *bio) #define bip_for_each_vec(bvl, bip, i) \ __bip_for_each_vec(bvl, bip, i, (bip)->bip_idx) -static inline int bio_integrity(struct bio *bio) -{ -#if defined(CONFIG_BLK_DEV_INTEGRITY) - return bio->bi_integrity != NULL; -#else - return 0; -#endif -} +#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);