From 96b418c960af0d5c7185ff5c4af9376eb37ac9d3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 May 2007 09:02:57 +0200 Subject: Add sg helpers for iterating over a scatterlist table First step to being able to change the scatterlist setup without having to modify drivers (a lot :-) Signed-off-by: Jens Axboe --- include/linux/scatterlist.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 4efbd9c445f5..bed5ab4d756a 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -20,4 +20,13 @@ static inline void sg_init_one(struct scatterlist *sg, const void *buf, sg_set_buf(sg, buf, buflen); } +#define sg_next(sg) ((sg) + 1) +#define sg_last(sg, nents) (&(sg[(nents) - 1])) + +/* + * Loop over each sg element, following the pointer to a new list if necessary + */ +#define for_each_sg(sglist, sg, nr, __i) \ + for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg)) + #endif /* _LINUX_SCATTERLIST_H */ -- cgit v1.2.3 From c6132da1704be252ee6c923f47501083d835c238 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2007 11:08:49 +0200 Subject: scsi: convert to using sg helpers This converts the SCSI mid layer to using the sg helpers for looking up sg elements, instead of doing it manually. Signed-off-by: Jens Axboe --- drivers/scsi/scsi_lib.c | 22 +++++++++++++--------- include/scsi/scsi_cmnd.h | 3 ++- 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 207f1aa08869..960f949b8f8f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -289,14 +290,16 @@ static int scsi_req_map_sg(struct request *rq, struct scatterlist *sgl, struct request_queue *q = rq->q; int nr_pages = (bufflen + sgl[0].offset + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned int data_len = bufflen, len, bytes, off; + struct scatterlist *sg; struct page *page; struct bio *bio = NULL; int i, err, nr_vecs = 0; - for (i = 0; i < nsegs; i++) { - page = sgl[i].page; - off = sgl[i].offset; - len = sgl[i].length; + for_each_sg(sgl, sg, nsegs, i) { + page = sg->page; + off = sg->offset; + len = sg->length; + data_len += len; while (len > 0 && data_len > 0) { /* @@ -2193,18 +2196,19 @@ EXPORT_SYMBOL_GPL(scsi_target_unblock); * * Returns virtual address of the start of the mapped page */ -void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, +void *scsi_kmap_atomic_sg(struct scatterlist *sgl, int sg_count, size_t *offset, size_t *len) { int i; size_t sg_len = 0, len_complete = 0; + struct scatterlist *sg; struct page *page; WARN_ON(!irqs_disabled()); - for (i = 0; i < sg_count; i++) { + for_each_sg(sgl, sg, sg_count, i) { len_complete = sg_len; /* Complete sg-entries */ - sg_len += sg[i].length; + sg_len += sg->length; if (sg_len > *offset) break; } @@ -2218,10 +2222,10 @@ void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, } /* Offset starting from the beginning of first page in this sg-entry */ - *offset = *offset - len_complete + sg[i].offset; + *offset = *offset - len_complete + sg->offset; /* Assumption: contiguous pages can be accessed as "page + i" */ - page = nth_page(sg[i].page, (*offset >> PAGE_SHIFT)); + page = nth_page(sg->page, (*offset >> PAGE_SHIFT)); *offset &= ~PAGE_MASK; /* Bytes in this sg-entry from *offset to the end of the page */ diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 65ab5145a09b..3b0bb6680e62 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -5,6 +5,7 @@ #include #include #include +#include struct request; struct scatterlist; @@ -148,6 +149,6 @@ static inline int scsi_get_resid(struct scsi_cmnd *cmd) } #define scsi_for_each_sg(cmd, sg, nseg, __i) \ - for (__i = 0, sg = scsi_sglist(cmd); __i < (nseg); __i++, (sg)++) + for_each_sg(scsi_sglist(cmd), sg, nseg, __i) #endif /* _SCSI_SCSI_CMND_H */ -- cgit v1.2.3 From 70eb8040dc81212c884a464b75e37dca8014f3ad Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 16 Jul 2007 21:17:16 +0200 Subject: Add chained sg support to linux/scatterlist.h The core of the patch - allow the last sg element in a scatterlist table to point to the start of a new table. We overload the LSB of the page pointer to indicate whether this is a valid sg entry, or merely a link to the next list. Includes a fix from Bartlomiej Zolnierkiewicz correcting the ifdef ARCH_HAS_SG_CHAIN guarding sg_last(). Signed-off-by: Jens Axboe --- include/linux/scatterlist.h | 79 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 77 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index bed5ab4d756a..2dc7464cce52 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -20,8 +20,36 @@ static inline void sg_init_one(struct scatterlist *sg, const void *buf, sg_set_buf(sg, buf, buflen); } -#define sg_next(sg) ((sg) + 1) -#define sg_last(sg, nents) (&(sg[(nents) - 1])) +/* + * We overload the LSB of the page pointer to indicate whether it's + * a valid sg entry, or whether it points to the start of a new scatterlist. + * Those low bits are there for everyone! (thanks mason :-) + */ +#define sg_is_chain(sg) ((unsigned long) (sg)->page & 0x01) +#define sg_chain_ptr(sg) \ + ((struct scatterlist *) ((unsigned long) (sg)->page & ~0x01)) + +/** + * sg_next - return the next scatterlist entry in a list + * @sg: The current sg entry + * + * Usually the next entry will be @sg@ + 1, but if this sg element is part + * of a chained scatterlist, it could jump to the start of a new + * scatterlist array. + * + * Note that the caller must ensure that there are further entries after + * the current entry, this function will NOT return NULL for an end-of-list. + * + */ +static inline struct scatterlist *sg_next(struct scatterlist *sg) +{ + sg++; + + if (unlikely(sg_is_chain(sg))) + sg = sg_chain_ptr(sg); + + return sg; +} /* * Loop over each sg element, following the pointer to a new list if necessary @@ -29,4 +57,51 @@ static inline void sg_init_one(struct scatterlist *sg, const void *buf, #define for_each_sg(sglist, sg, nr, __i) \ for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg)) +/** + * sg_last - return the last scatterlist entry in a list + * @sgl: First entry in the scatterlist + * @nents: Number of entries in the scatterlist + * + * Should only be used casually, it (currently) scan the entire list + * to get the last entry. + * + * Note that the @sgl@ pointer passed in need not be the first one, + * the important bit is that @nents@ denotes the number of entries that + * exist from @sgl@. + * + */ +static inline struct scatterlist *sg_last(struct scatterlist *sgl, + unsigned int nents) +{ +#ifndef ARCH_HAS_SG_CHAIN + struct scatterlist *ret = &sgl[nents - 1]; +#else + struct scatterlist *sg, *ret = NULL; + int i; + + for_each_sg(sgl, sg, nents, i) + ret = sg; + +#endif + return ret; +} + +/** + * sg_chain - Chain two sglists together + * @prv: First scatterlist + * @prv_nents: Number of entries in prv + * @sgl: Second scatterlist + * + * Links @prv@ and @sgl@ together, to form a longer scatterlist. + * + */ +static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, + struct scatterlist *sgl) +{ +#ifndef ARCH_HAS_SG_CHAIN + BUG(); +#endif + prv[prv_nents - 1].page = (struct page *) ((unsigned long) sgl | 0x01); +} + #endif /* _LINUX_SCATTERLIST_H */ -- cgit v1.2.3 From 0cde8d9510e242c73b2d68f9949cd3c456c863b4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2007 11:12:37 +0200 Subject: scsi: simplify scsi_free_sgtable() Just pass in the command, no point in passing in the scatterlist and scatterlist pool index seperately. Signed-off-by: Jens Axboe --- drivers/scsi/scsi_lib.c | 9 +++++---- drivers/scsi/scsi_tgt_lib.c | 4 ++-- include/scsi/scsi_cmnd.h | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 960f949b8f8f..7e1dcc57f115 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -741,13 +741,14 @@ struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask) EXPORT_SYMBOL(scsi_alloc_sgtable); -void scsi_free_sgtable(struct scatterlist *sgl, int index) +void scsi_free_sgtable(struct scsi_cmnd *cmd) { + struct scatterlist *sgl = cmd->request_buffer; struct scsi_host_sg_pool *sgp; - BUG_ON(index >= SG_MEMPOOL_NR); + BUG_ON(cmd->sglist_len >= SG_MEMPOOL_NR); - sgp = scsi_sg_pools + index; + sgp = scsi_sg_pools + cmd->sglist_len; mempool_free(sgl, sgp->pool); } @@ -773,7 +774,7 @@ EXPORT_SYMBOL(scsi_free_sgtable); static void scsi_release_buffers(struct scsi_cmnd *cmd) { if (cmd->use_sg) - scsi_free_sgtable(cmd->request_buffer, cmd->sglist_len); + scsi_free_sgtable(cmd); /* * Zero these out. They now point to freed memory, and it is diff --git a/drivers/scsi/scsi_tgt_lib.c b/drivers/scsi/scsi_tgt_lib.c index 66c692ffa305..a91761c3645f 100644 --- a/drivers/scsi/scsi_tgt_lib.c +++ b/drivers/scsi/scsi_tgt_lib.c @@ -332,7 +332,7 @@ static void scsi_tgt_cmd_done(struct scsi_cmnd *cmd) scsi_tgt_uspace_send_status(cmd, tcmd->itn_id, tcmd->tag); if (cmd->request_buffer) - scsi_free_sgtable(cmd->request_buffer, cmd->sglist_len); + scsi_free_sgtable(cmd); queue_work(scsi_tgtd, &tcmd->work); } @@ -373,7 +373,7 @@ static int scsi_tgt_init_cmd(struct scsi_cmnd *cmd, gfp_t gfp_mask) } eprintk("cmd %p cnt %d\n", cmd, cmd->use_sg); - scsi_free_sgtable(cmd->request_buffer, cmd->sglist_len); + scsi_free_sgtable(cmd); return -EINVAL; } diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 3b0bb6680e62..a5439a4b8f97 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -129,7 +129,7 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, extern void scsi_kunmap_atomic_sg(void *virt); extern struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *, gfp_t); -extern void scsi_free_sgtable(struct scatterlist *, int); +extern void scsi_free_sgtable(struct scsi_cmnd *); extern int scsi_dma_map(struct scsi_cmnd *cmd); extern void scsi_dma_unmap(struct scsi_cmnd *cmd); -- cgit v1.2.3 From a8474ce23a73185dd2bae4c884b1716474032d31 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 7 Aug 2007 09:02:51 +0200 Subject: SCSI: support for allocating large scatterlists This is what enables large commands. If we need to allocate an sgtable that doesn't fit in a single page, allocate several SCSI_MAX_SG_SEGMENTS sized tables and chain them together. SCSI defaults to large chained sg tables, if the arch supports it. Signed-off-by: Jens Axboe --- drivers/scsi/scsi_lib.c | 209 ++++++++++++++++++++++++++++++++++++----------- include/scsi/scsi.h | 7 -- include/scsi/scsi_cmnd.h | 1 + 3 files changed, 163 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 7e1dcc57f115..c75cb6ad6d94 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -36,33 +36,19 @@ struct scsi_host_sg_pool { size_t size; - char *name; + char *name; struct kmem_cache *slab; mempool_t *pool; }; -#if (SCSI_MAX_PHYS_SEGMENTS < 32) -#error SCSI_MAX_PHYS_SEGMENTS is too small -#endif - -#define SP(x) { x, "sgpool-" #x } +#define SP(x) { x, "sgpool-" #x } static struct scsi_host_sg_pool scsi_sg_pools[] = { SP(8), SP(16), SP(32), -#if (SCSI_MAX_PHYS_SEGMENTS > 32) SP(64), -#if (SCSI_MAX_PHYS_SEGMENTS > 64) SP(128), -#if (SCSI_MAX_PHYS_SEGMENTS > 128) - SP(256), -#if (SCSI_MAX_PHYS_SEGMENTS > 256) -#error SCSI_MAX_PHYS_SEGMENTS is too large -#endif -#endif -#endif -#endif -}; +}; #undef SP static void scsi_run_queue(struct request_queue *q); @@ -698,45 +684,126 @@ static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int uptodate, return NULL; } -struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask) -{ - struct scsi_host_sg_pool *sgp; - struct scatterlist *sgl; +/* + * The maximum number of SG segments that we will put inside a scatterlist + * (unless chaining is used). Should ideally fit inside a single page, to + * avoid a higher order allocation. + */ +#define SCSI_MAX_SG_SEGMENTS 128 - BUG_ON(!cmd->use_sg); +/* + * Like SCSI_MAX_SG_SEGMENTS, but for archs that have sg chaining. This limit + * is totally arbitrary, a setting of 2048 will get you at least 8mb ios. + */ +#define SCSI_MAX_SG_CHAIN_SEGMENTS 2048 - switch (cmd->use_sg) { +static inline unsigned int scsi_sgtable_index(unsigned short nents) +{ + unsigned int index; + + switch (nents) { case 1 ... 8: - cmd->sglist_len = 0; + index = 0; break; case 9 ... 16: - cmd->sglist_len = 1; + index = 1; break; case 17 ... 32: - cmd->sglist_len = 2; + index = 2; break; -#if (SCSI_MAX_PHYS_SEGMENTS > 32) case 33 ... 64: - cmd->sglist_len = 3; + index = 3; break; -#if (SCSI_MAX_PHYS_SEGMENTS > 64) - case 65 ... 128: - cmd->sglist_len = 4; + case 65 ... SCSI_MAX_SG_SEGMENTS: + index = 4; break; -#if (SCSI_MAX_PHYS_SEGMENTS > 128) - case 129 ... 256: - cmd->sglist_len = 5; - break; -#endif -#endif -#endif default: - return NULL; + printk(KERN_ERR "scsi: bad segment count=%d\n", nents); + BUG(); } - sgp = scsi_sg_pools + cmd->sglist_len; - sgl = mempool_alloc(sgp->pool, gfp_mask); - return sgl; + return index; +} + +struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask) +{ + struct scsi_host_sg_pool *sgp; + struct scatterlist *sgl, *prev, *ret; + unsigned int index; + int this, left; + + BUG_ON(!cmd->use_sg); + + left = cmd->use_sg; + ret = prev = NULL; + do { + this = left; + if (this > SCSI_MAX_SG_SEGMENTS) { + this = SCSI_MAX_SG_SEGMENTS - 1; + index = SG_MEMPOOL_NR - 1; + } else + index = scsi_sgtable_index(this); + + left -= this; + + sgp = scsi_sg_pools + index; + + sgl = mempool_alloc(sgp->pool, gfp_mask); + if (unlikely(!sgl)) + goto enomem; + + memset(sgl, 0, sizeof(*sgl) * sgp->size); + + /* + * first loop through, set initial index and return value + */ + if (!ret) { + cmd->sglist_len = index; + ret = sgl; + } + + /* + * chain previous sglist, if any. we know the previous + * sglist must be the biggest one, or we would not have + * ended up doing another loop. + */ + if (prev) + sg_chain(prev, SCSI_MAX_SG_SEGMENTS, sgl); + + /* + * don't allow subsequent mempool allocs to sleep, it would + * violate the mempool principle. + */ + gfp_mask &= ~__GFP_WAIT; + gfp_mask |= __GFP_HIGH; + prev = sgl; + } while (left); + + /* + * ->use_sg may get modified after dma mapping has potentially + * shrunk the number of segments, so keep a copy of it for free. + */ + cmd->__use_sg = cmd->use_sg; + return ret; +enomem: + if (ret) { + /* + * Free entries chained off ret. Since we were trying to + * allocate another sglist, we know that all entries are of + * the max size. + */ + sgp = scsi_sg_pools + SG_MEMPOOL_NR - 1; + prev = ret; + ret = &ret[SCSI_MAX_SG_SEGMENTS - 1]; + + while ((sgl = sg_chain_ptr(ret)) != NULL) { + ret = &sgl[SCSI_MAX_SG_SEGMENTS - 1]; + mempool_free(sgl, sgp->pool); + } + + mempool_free(prev, sgp->pool); + } + return NULL; } EXPORT_SYMBOL(scsi_alloc_sgtable); @@ -748,6 +815,42 @@ void scsi_free_sgtable(struct scsi_cmnd *cmd) BUG_ON(cmd->sglist_len >= SG_MEMPOOL_NR); + /* + * if this is the biggest size sglist, check if we have + * chained parts we need to free + */ + if (cmd->__use_sg > SCSI_MAX_SG_SEGMENTS) { + unsigned short this, left; + struct scatterlist *next; + unsigned int index; + + left = cmd->__use_sg - (SCSI_MAX_SG_SEGMENTS - 1); + next = sg_chain_ptr(&sgl[SCSI_MAX_SG_SEGMENTS - 1]); + while (left && next) { + sgl = next; + this = left; + if (this > SCSI_MAX_SG_SEGMENTS) { + this = SCSI_MAX_SG_SEGMENTS - 1; + index = SG_MEMPOOL_NR - 1; + } else + index = scsi_sgtable_index(this); + + left -= this; + + sgp = scsi_sg_pools + index; + + if (left) + next = sg_chain_ptr(&sgl[sgp->size - 1]); + + mempool_free(sgl, sgp->pool); + } + + /* + * Restore original, will be freed below + */ + sgl = cmd->request_buffer; + } + sgp = scsi_sg_pools + cmd->sglist_len; mempool_free(sgl, sgp->pool); } @@ -988,7 +1091,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) static int scsi_init_io(struct scsi_cmnd *cmd) { struct request *req = cmd->request; - struct scatterlist *sgpnt; int count; /* @@ -1001,14 +1103,13 @@ static int scsi_init_io(struct scsi_cmnd *cmd) /* * If sg table allocation fails, requeue request later. */ - sgpnt = scsi_alloc_sgtable(cmd, GFP_ATOMIC); - if (unlikely(!sgpnt)) { + cmd->request_buffer = scsi_alloc_sgtable(cmd, GFP_ATOMIC); + if (unlikely(!cmd->request_buffer)) { scsi_unprep_request(req); return BLKPREP_DEFER; } req->buffer = NULL; - cmd->request_buffer = (char *) sgpnt; if (blk_pc_request(req)) cmd->request_bufflen = req->data_len; else @@ -1533,8 +1634,22 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, if (!q) return NULL; + /* + * this limit is imposed by hardware restrictions + */ blk_queue_max_hw_segments(q, shost->sg_tablesize); - blk_queue_max_phys_segments(q, SCSI_MAX_PHYS_SEGMENTS); + + /* + * In the future, sg chaining support will be mandatory and this + * ifdef can then go away. Right now we don't have all archs + * converted, so better keep it safe. + */ +#ifdef ARCH_HAS_SG_CHAIN + blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS); +#else + blk_queue_max_phys_segments(q, SCSI_MAX_SG_SEGMENTS); +#endif + blk_queue_max_sectors(q, shost->max_sectors); blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost)); blk_queue_segment_boundary(q, shost->dma_boundary); diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 9f8f80ab0c8b..702fcfeb37f1 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -10,13 +10,6 @@ #include -/* - * The maximum sg list length SCSI can cope with - * (currently must be a power of 2 between 32 and 256) - */ -#define SCSI_MAX_PHYS_SEGMENTS MAX_PHYS_SEGMENTS - - /* * SCSI command lengths */ diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index a5439a4b8f97..4a5fa2d1c44c 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -70,6 +70,7 @@ struct scsi_cmnd { /* These elements define the operation we ultimately want to perform */ unsigned short use_sg; /* Number of pieces of scatter-gather */ unsigned short sglist_len; /* size of malloc'd scatter-gather list */ + unsigned short __use_sg; unsigned underflow; /* Return error if less than this amount is transferred */ -- cgit v1.2.3 From 8726021626780a73e795c9b939e1ee49ac8c9136 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2007 11:14:12 +0200 Subject: libata: convert to using sg helpers This converts libata to using the sg helpers for looking up sg elements, instead of doing it manually. Signed-off-by: Jens Axboe --- drivers/ata/libata-core.c | 30 ++++++++++++++++-------------- include/linux/libata.h | 16 ++++++++++------ 2 files changed, 26 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 68699b3e7998..e52c33180e42 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1410,7 +1410,7 @@ static void ata_qc_complete_internal(struct ata_queued_cmd *qc) */ unsigned ata_exec_internal_sg(struct ata_device *dev, struct ata_taskfile *tf, const u8 *cdb, - int dma_dir, struct scatterlist *sg, + int dma_dir, struct scatterlist *sgl, unsigned int n_elem, unsigned long timeout) { struct ata_link *link = dev->link; @@ -1472,11 +1472,12 @@ unsigned ata_exec_internal_sg(struct ata_device *dev, qc->dma_dir = dma_dir; if (dma_dir != DMA_NONE) { unsigned int i, buflen = 0; + struct scatterlist *sg; - for (i = 0; i < n_elem; i++) - buflen += sg[i].length; + for_each_sg(sgl, sg, n_elem, i) + buflen += sg->length; - ata_sg_init(qc, sg, n_elem); + ata_sg_init(qc, sgl, n_elem); qc->nbytes = buflen; } @@ -4292,7 +4293,7 @@ void ata_sg_clean(struct ata_queued_cmd *qc) if (qc->n_elem) dma_unmap_sg(ap->dev, sg, qc->n_elem, dir); /* restore last sg */ - sg[qc->orig_n_elem - 1].length += qc->pad_len; + sg_last(sg, qc->orig_n_elem)->length += qc->pad_len; if (pad_buf) { struct scatterlist *psg = &qc->pad_sgent; void *addr = kmap_atomic(psg->page, KM_IRQ0); @@ -4547,6 +4548,7 @@ void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, unsigned int buflen) qc->orig_n_elem = 1; qc->buf_virt = buf; qc->nbytes = buflen; + qc->cursg = qc->__sg; sg_init_one(&qc->sgent, buf, buflen); } @@ -4572,6 +4574,7 @@ void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, qc->__sg = sg; qc->n_elem = n_elem; qc->orig_n_elem = n_elem; + qc->cursg = qc->__sg; } /** @@ -4661,7 +4664,7 @@ static int ata_sg_setup(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct scatterlist *sg = qc->__sg; - struct scatterlist *lsg = &sg[qc->n_elem - 1]; + struct scatterlist *lsg = sg_last(qc->__sg, qc->n_elem); int n_elem, pre_n_elem, dir, trim_sg = 0; VPRINTK("ENTER, ata%u\n", ap->print_id); @@ -4825,7 +4828,6 @@ void ata_data_xfer_noirq(struct ata_device *adev, unsigned char *buf, static void ata_pio_sector(struct ata_queued_cmd *qc) { int do_write = (qc->tf.flags & ATA_TFLAG_WRITE); - struct scatterlist *sg = qc->__sg; struct ata_port *ap = qc->ap; struct page *page; unsigned int offset; @@ -4834,8 +4836,8 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) if (qc->curbytes == qc->nbytes - qc->sect_size) ap->hsm_task_state = HSM_ST_LAST; - page = sg[qc->cursg].page; - offset = sg[qc->cursg].offset + qc->cursg_ofs; + page = qc->cursg->page; + offset = qc->cursg->offset + qc->cursg_ofs; /* get the current page and offset */ page = nth_page(page, (offset >> PAGE_SHIFT)); @@ -4863,8 +4865,8 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) qc->curbytes += qc->sect_size; qc->cursg_ofs += qc->sect_size; - if (qc->cursg_ofs == (&sg[qc->cursg])->length) { - qc->cursg++; + if (qc->cursg_ofs == qc->cursg->length) { + qc->cursg = sg_next(qc->cursg); qc->cursg_ofs = 0; } } @@ -4959,7 +4961,7 @@ static void __atapi_pio_bytes(struct ata_queued_cmd *qc, unsigned int bytes) ap->hsm_task_state = HSM_ST_LAST; next_sg: - if (unlikely(qc->cursg >= qc->n_elem)) { + if (unlikely(qc->cursg == sg_last(qc->__sg, qc->n_elem))) { /* * The end of qc->sg is reached and the device expects * more data to transfer. In order not to overrun qc->sg @@ -4982,7 +4984,7 @@ next_sg: return; } - sg = &qc->__sg[qc->cursg]; + sg = qc->cursg; page = sg->page; offset = sg->offset + qc->cursg_ofs; @@ -5021,7 +5023,7 @@ next_sg: qc->cursg_ofs += count; if (qc->cursg_ofs == sg->length) { - qc->cursg++; + qc->cursg = sg_next(qc->cursg); qc->cursg_ofs = 0; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 229a9ff9f924..377e6d4d9be3 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -29,7 +29,7 @@ #include #include #include -#include +#include #include #include #include @@ -416,6 +416,7 @@ struct ata_queued_cmd { unsigned long flags; /* ATA_QCFLAG_xxx */ unsigned int tag; unsigned int n_elem; + unsigned int n_iter; unsigned int orig_n_elem; int dma_dir; @@ -426,7 +427,7 @@ struct ata_queued_cmd { unsigned int nbytes; unsigned int curbytes; - unsigned int cursg; + struct scatterlist *cursg; unsigned int cursg_ofs; struct scatterlist sgent; @@ -1043,7 +1044,7 @@ ata_sg_is_last(struct scatterlist *sg, struct ata_queued_cmd *qc) return 1; if (qc->pad_len) return 0; - if (((sg - qc->__sg) + 1) == qc->n_elem) + if (qc->n_iter == qc->n_elem) return 1; return 0; } @@ -1051,6 +1052,7 @@ ata_sg_is_last(struct scatterlist *sg, struct ata_queued_cmd *qc) static inline struct scatterlist * ata_qc_first_sg(struct ata_queued_cmd *qc) { + qc->n_iter = 0; if (qc->n_elem) return qc->__sg; if (qc->pad_len) @@ -1063,8 +1065,8 @@ ata_qc_next_sg(struct scatterlist *sg, struct ata_queued_cmd *qc) { if (sg == &qc->pad_sgent) return NULL; - if (++sg - qc->__sg < qc->n_elem) - return sg; + if (++qc->n_iter < qc->n_elem) + return sg_next(sg); if (qc->pad_len) return &qc->pad_sgent; return NULL; @@ -1309,9 +1311,11 @@ static inline void ata_qc_reinit(struct ata_queued_cmd *qc) qc->dma_dir = DMA_NONE; qc->__sg = NULL; qc->flags = 0; - qc->cursg = qc->cursg_ofs = 0; + qc->cursg = NULL; + qc->cursg_ofs = 0; qc->nbytes = qc->curbytes = 0; qc->n_elem = 0; + qc->n_iter = 0; qc->err_mask = 0; qc->pad_len = 0; qc->sect_size = ATA_SECT_SIZE; -- cgit v1.2.3 From ba2da2f8d61a9d2e24754c6311a4ab6a5e70060a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 24 Jul 2007 14:42:11 +0200 Subject: i2o: sg chaining support Acked-by: Alan Cox Signed-off-by: Jens Axboe --- include/linux/i2o.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 9752307d16ba..7da5b98d90e6 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -32,6 +32,7 @@ #include /* work_struct */ #include #include +#include #include #include /* Needed for MUTEX init macros */ @@ -837,7 +838,7 @@ static inline int i2o_dma_map_sg(struct i2o_controller *c, if ((sizeof(dma_addr_t) > 4) && c->pae_support) *mptr++ = cpu_to_le32(i2o_dma_high(sg_dma_address(sg))); #endif - sg++; + sg = sg_next(sg); } *sg_ptr = mptr; -- cgit v1.2.3 From 55c16a70041ba55e235c5944dccb9c1de0dd3ca6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 25 Jul 2007 08:13:56 +0200 Subject: IDE: sg chaining support Acked-by: Bartlomiej Zolnierkiewicz Signed-off-by: Jens Axboe --- drivers/ide/cris/ide-cris.c | 3 ++- drivers/ide/ide-dma.c | 2 +- drivers/ide/ide-io.c | 3 ++- drivers/ide/ide-probe.c | 2 +- drivers/ide/ide-taskfile.c | 18 ++++++++++++++---- drivers/ide/mips/au1xxx-ide.c | 2 +- drivers/ide/pci/sgiioc4.c | 3 ++- drivers/ide/ppc/pmac.c | 2 +- include/linux/ide.h | 2 +- 9 files changed, 25 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/ide/cris/ide-cris.c b/drivers/ide/cris/ide-cris.c index 2b4d2a0ae5c2..c306c9f534ab 100644 --- a/drivers/ide/cris/ide-cris.c +++ b/drivers/ide/cris/ide-cris.c @@ -939,7 +939,8 @@ static int cris_ide_build_dmatable (ide_drive_t *drive) /* group sequential buffers into one large buffer */ addr = page_to_phys(sg->page) + sg->offset; size = sg_dma_len(sg); - while (sg++, --i) { + while (--i) { + sg = sg_next(sg); if ((addr + size) != page_to_phys(sg->page) + sg->offset) break; size += sg_dma_len(sg); diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c index b453211ee0fc..a4cbbbaccde9 100644 --- a/drivers/ide/ide-dma.c +++ b/drivers/ide/ide-dma.c @@ -280,7 +280,7 @@ int ide_build_dmatable (ide_drive_t *drive, struct request *rq) } } - sg++; + sg = sg_next(sg); i--; } diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index f36ff5962af6..04273d3c147c 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -846,7 +846,8 @@ void ide_init_sg_cmd(ide_drive_t *drive, struct request *rq) ide_hwif_t *hwif = drive->hwif; hwif->nsect = hwif->nleft = rq->nr_sectors; - hwif->cursg = hwif->cursg_ofs = 0; + hwif->cursg_ofs = 0; + hwif->cursg = NULL; } EXPORT_SYMBOL_GPL(ide_init_sg_cmd); diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index d1011712601c..34b1fb65bc79 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1349,7 +1349,7 @@ static int hwif_init(ide_hwif_t *hwif) if (!hwif->sg_max_nents) hwif->sg_max_nents = PRD_ENTRIES; - hwif->sg_table = kmalloc(sizeof(struct scatterlist)*hwif->sg_max_nents, + hwif->sg_table = kzalloc(sizeof(struct scatterlist)*hwif->sg_max_nents, GFP_KERNEL); if (!hwif->sg_table) { printk(KERN_ERR "%s: unable to allocate SG table.\n", hwif->name); diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c index aa06dafb74ac..2a3c8d498343 100644 --- a/drivers/ide/ide-taskfile.c +++ b/drivers/ide/ide-taskfile.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -263,6 +264,7 @@ static void ide_pio_sector(ide_drive_t *drive, unsigned int write) { ide_hwif_t *hwif = drive->hwif; struct scatterlist *sg = hwif->sg_table; + struct scatterlist *cursg = hwif->cursg; struct page *page; #ifdef CONFIG_HIGHMEM unsigned long flags; @@ -270,8 +272,14 @@ static void ide_pio_sector(ide_drive_t *drive, unsigned int write) unsigned int offset; u8 *buf; - page = sg[hwif->cursg].page; - offset = sg[hwif->cursg].offset + hwif->cursg_ofs * SECTOR_SIZE; + cursg = hwif->cursg; + if (!cursg) { + cursg = sg; + hwif->cursg = sg; + } + + page = cursg->page; + offset = cursg->offset + hwif->cursg_ofs * SECTOR_SIZE; /* get the current page and offset */ page = nth_page(page, (offset >> PAGE_SHIFT)); @@ -285,8 +293,8 @@ static void ide_pio_sector(ide_drive_t *drive, unsigned int write) hwif->nleft--; hwif->cursg_ofs++; - if ((hwif->cursg_ofs * SECTOR_SIZE) == sg[hwif->cursg].length) { - hwif->cursg++; + if ((hwif->cursg_ofs * SECTOR_SIZE) == cursg->length) { + hwif->cursg = sg_next(hwif->cursg); hwif->cursg_ofs = 0; } @@ -367,6 +375,8 @@ static ide_startstop_t task_error(ide_drive_t *drive, struct request *rq, static void task_end_request(ide_drive_t *drive, struct request *rq, u8 stat) { + HWIF(drive)->cursg = NULL; + if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE) { ide_task_t *task = rq->special; diff --git a/drivers/ide/mips/au1xxx-ide.c b/drivers/ide/mips/au1xxx-ide.c index aebde49365d1..892d08f61dc0 100644 --- a/drivers/ide/mips/au1xxx-ide.c +++ b/drivers/ide/mips/au1xxx-ide.c @@ -296,7 +296,7 @@ static int auide_build_dmatable(ide_drive_t *drive) cur_addr += tc; cur_len -= tc; } - sg++; + sg = sg_next(sg); i--; } diff --git a/drivers/ide/pci/sgiioc4.c b/drivers/ide/pci/sgiioc4.c index 85ffaaa39b1b..c74fef6bbc91 100644 --- a/drivers/ide/pci/sgiioc4.c +++ b/drivers/ide/pci/sgiioc4.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -537,7 +538,7 @@ sgiioc4_build_dma_table(ide_drive_t * drive, struct request *rq, int ddir) } } - sg++; + sg = sg_next(sg); i--; } diff --git a/drivers/ide/ppc/pmac.c b/drivers/ide/ppc/pmac.c index 7d8873839e21..9e86406bf44b 100644 --- a/drivers/ide/ppc/pmac.c +++ b/drivers/ide/ppc/pmac.c @@ -1539,7 +1539,7 @@ pmac_ide_build_dmatable(ide_drive_t *drive, struct request *rq) cur_len -= tc; ++table; } - sg++; + sg = sg_next(sg); i--; } diff --git a/include/linux/ide.h b/include/linux/ide.h index 234fa3df24f6..30a1931466a6 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -772,7 +772,7 @@ typedef struct hwif_s { unsigned int nsect; unsigned int nleft; - unsigned int cursg; + struct scatterlist *cursg; unsigned int cursg_ofs; int rqsize; /* max sectors per request */ -- cgit v1.2.3 From 9cb83c7529d929c00f37d821daed1942a1b20602 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 16 Oct 2007 11:24:32 +0200 Subject: [SCSI] add use_sg_chaining option to scsi_host_template This option is true if a low-level driver can support sg chaining. This will be removed eventually when all the drivers are converted to support sg chaining. q->max_phys_segments is set to SCSI_MAX_SG_SEGMENTS if false. Signed-off-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- arch/ia64/hp/sim/simscsi.c | 1 + drivers/scsi/3w-9xxx.c | 1 + drivers/scsi/3w-xxxx.c | 1 + drivers/scsi/BusLogic.c | 1 + drivers/scsi/NCR53c406a.c | 3 ++- drivers/scsi/a100u2w.c | 1 + drivers/scsi/aacraid/linit.c | 1 + drivers/scsi/aha1740.c | 1 + drivers/scsi/aic7xxx/aic79xx_osm.c | 1 + drivers/scsi/aic7xxx/aic7xxx_osm.c | 1 + drivers/scsi/aic7xxx_old.c | 1 + drivers/scsi/arcmsr/arcmsr_hba.c | 1 + drivers/scsi/dc395x.c | 1 + drivers/scsi/dpt_i2o.c | 1 + drivers/scsi/eata.c | 3 ++- drivers/scsi/hosts.c | 1 + drivers/scsi/hptiop.c | 1 + drivers/scsi/ibmmca.c | 1 + drivers/scsi/ibmvscsi/ibmvscsi.c | 1 + drivers/scsi/initio.c | 1 + drivers/scsi/lpfc/lpfc_scsi.c | 2 ++ drivers/scsi/mac53c94.c | 1 + drivers/scsi/megaraid.c | 1 + drivers/scsi/megaraid/megaraid_mbox.c | 1 + drivers/scsi/megaraid/megaraid_sas.c | 1 + drivers/scsi/mesh.c | 1 + drivers/scsi/nsp32.c | 1 + drivers/scsi/pcmcia/sym53c500_cs.c | 1 + drivers/scsi/qla2xxx/qla_os.c | 2 ++ drivers/scsi/qla4xxx/ql4_os.c | 1 + drivers/scsi/qlogicfas.c | 1 + drivers/scsi/scsi_lib.c | 5 ++++- drivers/scsi/stex.c | 1 + drivers/scsi/sym53c416.c | 1 + drivers/scsi/sym53c8xx_2/sym_glue.c | 1 + drivers/scsi/u14-34f.c | 1 + drivers/scsi/ultrastor.c | 1 + drivers/scsi/wd7000.c | 1 + include/scsi/scsi_host.h | 13 +++++++++++++ 39 files changed, 58 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c index d62fa76e5a7d..a3a558a06757 100644 --- a/arch/ia64/hp/sim/simscsi.c +++ b/arch/ia64/hp/sim/simscsi.c @@ -360,6 +360,7 @@ static struct scsi_host_template driver_template = { .max_sectors = 1024, .cmd_per_lun = SIMSCSI_REQ_QUEUE_LEN, .use_clustering = DISABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static int __init diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index efd9d8d3a890..fb14014ee16e 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -1990,6 +1990,7 @@ static struct scsi_host_template driver_template = { .max_sectors = TW_MAX_SECTORS, .cmd_per_lun = TW_MAX_CMDS_PER_LUN, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = twa_host_attrs, .emulated = 1 }; diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index c7995fc216e8..a64153b96034 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -2261,6 +2261,7 @@ static struct scsi_host_template driver_template = { .max_sectors = TW_MAX_SECTORS, .cmd_per_lun = TW_MAX_CMDS_PER_LUN, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = tw_host_attrs, .emulated = 1 }; diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c index 9b206176f717..49e1ffa4b2ff 100644 --- a/drivers/scsi/BusLogic.c +++ b/drivers/scsi/BusLogic.c @@ -3575,6 +3575,7 @@ static struct scsi_host_template Bus_Logic_template = { .unchecked_isa_dma = 1, .max_sectors = 128, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; /* diff --git a/drivers/scsi/NCR53c406a.c b/drivers/scsi/NCR53c406a.c index eda8c48f6be7..3168a1794849 100644 --- a/drivers/scsi/NCR53c406a.c +++ b/drivers/scsi/NCR53c406a.c @@ -1066,7 +1066,8 @@ static struct scsi_host_template driver_template = .sg_tablesize = 32 /*SG_ALL*/ /*SG_NONE*/, .cmd_per_lun = 1 /* commands per lun */, .unchecked_isa_dma = 1 /* unchecked_isa_dma */, - .use_clustering = ENABLE_CLUSTERING + .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/a100u2w.c b/drivers/scsi/a100u2w.c index f608d4a1d6da..d3a6d15fb77a 100644 --- a/drivers/scsi/a100u2w.c +++ b/drivers/scsi/a100u2w.c @@ -1071,6 +1071,7 @@ static struct scsi_host_template inia100_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static int __devinit inia100_probe_one(struct pci_dev *pdev, diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index a7f42a17b5c7..038980be763d 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -944,6 +944,7 @@ static struct scsi_host_template aac_driver_template = { .cmd_per_lun = AAC_NUM_IO_FIB, #endif .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .emulated = 1, }; diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c index e4a4f3a965d9..f6722fd46008 100644 --- a/drivers/scsi/aha1740.c +++ b/drivers/scsi/aha1740.c @@ -563,6 +563,7 @@ static struct scsi_host_template aha1740_template = { .sg_tablesize = AHA1740_SCATTER, .cmd_per_lun = AHA1740_CMDLUN, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .eh_abort_handler = aha1740_eh_abort_handler, }; diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c index a055a96e3ad3..42c0f14a262c 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.c +++ b/drivers/scsi/aic7xxx/aic79xx_osm.c @@ -766,6 +766,7 @@ struct scsi_host_template aic79xx_driver_template = { .max_sectors = 8192, .cmd_per_lun = 2, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .slave_alloc = ahd_linux_slave_alloc, .slave_configure = ahd_linux_slave_configure, .target_alloc = ahd_linux_target_alloc, diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index 2e9c38f2e8a6..7770befbf50c 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -747,6 +747,7 @@ struct scsi_host_template aic7xxx_driver_template = { .max_sectors = 8192, .cmd_per_lun = 2, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .slave_alloc = ahc_linux_slave_alloc, .slave_configure = ahc_linux_slave_configure, .target_alloc = ahc_linux_target_alloc, diff --git a/drivers/scsi/aic7xxx_old.c b/drivers/scsi/aic7xxx_old.c index 1a71b0236c97..4025608d6964 100644 --- a/drivers/scsi/aic7xxx_old.c +++ b/drivers/scsi/aic7xxx_old.c @@ -11142,6 +11142,7 @@ static struct scsi_host_template driver_template = { .max_sectors = 2048, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index cfcf40159eab..f81777586b8f 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -122,6 +122,7 @@ static struct scsi_host_template arcmsr_scsi_host_template = { .max_sectors = ARCMSR_MAX_XFER_SECTORS, .cmd_per_lun = ARCMSR_MAX_CMD_PERLUN, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = arcmsr_host_attrs, }; #ifdef CONFIG_SCSI_ARCMSR_AER diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c index 1591824cf4b3..fd42d4789202 100644 --- a/drivers/scsi/dc395x.c +++ b/drivers/scsi/dc395x.c @@ -4765,6 +4765,7 @@ static struct scsi_host_template dc395x_driver_template = { .eh_bus_reset_handler = dc395x_eh_bus_reset, .unchecked_isa_dma = 0, .use_clustering = DISABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c index bea9d659af15..8258506ba7d7 100644 --- a/drivers/scsi/dpt_i2o.c +++ b/drivers/scsi/dpt_i2o.c @@ -3295,6 +3295,7 @@ static struct scsi_host_template adpt_template = { .this_id = 7, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static s32 adpt_scsi_register(adpt_hba* pHba) diff --git a/drivers/scsi/eata.c b/drivers/scsi/eata.c index ec2233114bc9..7ead5210de96 100644 --- a/drivers/scsi/eata.c +++ b/drivers/scsi/eata.c @@ -523,7 +523,8 @@ static struct scsi_host_template driver_template = { .slave_configure = eata2x_slave_configure, .this_id = 7, .unchecked_isa_dma = 1, - .use_clustering = ENABLE_CLUSTERING + .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; #if !defined(__BIG_ENDIAN_BITFIELD) && !defined(__LITTLE_ENDIAN_BITFIELD) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index adc9559cb6f4..112ab6abe62b 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -343,6 +343,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost->use_clustering = sht->use_clustering; shost->ordered_tag = sht->ordered_tag; shost->active_mode = sht->supported_mode; + shost->use_sg_chaining = sht->use_sg_chaining; if (sht->max_host_blocked) shost->max_host_blocked = sht->max_host_blocked; diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c index 8b384fa7f048..8515054cdf70 100644 --- a/drivers/scsi/hptiop.c +++ b/drivers/scsi/hptiop.c @@ -655,6 +655,7 @@ static struct scsi_host_template driver_template = { .unchecked_isa_dma = 0, .emulated = 0, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .proc_name = driver_name, .shost_attrs = hptiop_attrs, .this_id = -1, diff --git a/drivers/scsi/ibmmca.c b/drivers/scsi/ibmmca.c index 1a924e9b0271..714e6273a70d 100644 --- a/drivers/scsi/ibmmca.c +++ b/drivers/scsi/ibmmca.c @@ -1501,6 +1501,7 @@ static struct scsi_host_template ibmmca_driver_template = { .sg_tablesize = 16, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static int ibmmca_probe(struct device *dev) diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index cda0cc3d182f..22d91ee173c5 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -1548,6 +1548,7 @@ static struct scsi_host_template driver_template = { .this_id = -1, .sg_tablesize = SG_ALL, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = ibmvscsi_attrs, }; diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c index d9dfb69ae031..22d40fd5845b 100644 --- a/drivers/scsi/initio.c +++ b/drivers/scsi/initio.c @@ -2831,6 +2831,7 @@ static struct scsi_host_template initio_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static int initio_probe_one(struct pci_dev *pdev, diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index cd674938ccd5..c0755565fae9 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1438,6 +1438,7 @@ struct scsi_host_template lpfc_template = { .scan_finished = lpfc_scan_finished, .this_id = -1, .sg_tablesize = LPFC_SG_SEG_CNT, + .use_sg_chaining = ENABLE_SG_CHAINING, .cmd_per_lun = LPFC_CMD_PER_LUN, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = lpfc_hba_attrs, @@ -1460,6 +1461,7 @@ struct scsi_host_template lpfc_vport_template = { .sg_tablesize = LPFC_SG_SEG_CNT, .cmd_per_lun = LPFC_CMD_PER_LUN, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = lpfc_vport_attrs, .max_sectors = 0xFFFF, }; diff --git a/drivers/scsi/mac53c94.c b/drivers/scsi/mac53c94.c index b12ad7c7c673..a035001f4438 100644 --- a/drivers/scsi/mac53c94.c +++ b/drivers/scsi/mac53c94.c @@ -402,6 +402,7 @@ static struct scsi_host_template mac53c94_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = DISABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static int mac53c94_probe(struct macio_dev *mdev, const struct of_device_id *match) diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index e7e11f282c8f..10d1aff9938a 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -4492,6 +4492,7 @@ static struct scsi_host_template megaraid_template = { .sg_tablesize = MAX_SGLIST, .cmd_per_lun = DEF_CMD_PER_LUN, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .eh_abort_handler = megaraid_abort, .eh_device_reset_handler = megaraid_reset, .eh_bus_reset_handler = megaraid_reset, diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c index c6a53dccc16a..e4e4c6a39ed6 100644 --- a/drivers/scsi/megaraid/megaraid_mbox.c +++ b/drivers/scsi/megaraid/megaraid_mbox.c @@ -361,6 +361,7 @@ static struct scsi_host_template megaraid_template_g = { .eh_host_reset_handler = megaraid_reset_handler, .change_queue_depth = megaraid_change_queue_depth, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .sdev_attrs = megaraid_sdev_attrs, .shost_attrs = megaraid_shost_attrs, }; diff --git a/drivers/scsi/megaraid/megaraid_sas.c b/drivers/scsi/megaraid/megaraid_sas.c index ebb948c016bb..e3c5c5282203 100644 --- a/drivers/scsi/megaraid/megaraid_sas.c +++ b/drivers/scsi/megaraid/megaraid_sas.c @@ -1110,6 +1110,7 @@ static struct scsi_host_template megasas_template = { .eh_timed_out = megasas_reset_timer, .bios_param = megasas_bios_param, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; /** diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c index 651d09b08f2a..7470ff39ab22 100644 --- a/drivers/scsi/mesh.c +++ b/drivers/scsi/mesh.c @@ -1843,6 +1843,7 @@ static struct scsi_host_template mesh_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 2, .use_clustering = DISABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static int mesh_probe(struct macio_dev *mdev, const struct of_device_id *match) diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c index 7fed35372150..28161dc95e0d 100644 --- a/drivers/scsi/nsp32.c +++ b/drivers/scsi/nsp32.c @@ -281,6 +281,7 @@ static struct scsi_host_template nsp32_template = { .cmd_per_lun = 1, .this_id = NSP32_HOST_SCSIID, .use_clustering = DISABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .eh_abort_handler = nsp32_eh_abort, .eh_bus_reset_handler = nsp32_eh_bus_reset, .eh_host_reset_handler = nsp32_eh_host_reset, diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index 961839ecfe86..190e2a7d7067 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -694,6 +694,7 @@ static struct scsi_host_template sym53c500_driver_template = { .sg_tablesize = 32, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = SYM53C500_shost_attrs }; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index a6bb8d0ecf13..0351d380c2d7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -132,6 +132,7 @@ struct scsi_host_template qla2x00_driver_template = { .this_id = -1, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .sg_tablesize = SG_ALL, /* @@ -163,6 +164,7 @@ struct scsi_host_template qla24xx_driver_template = { .this_id = -1, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .sg_tablesize = SG_ALL, .max_sectors = 0xFFFF, diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index b1d565c12c5b..03b68d4f3bd0 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -94,6 +94,7 @@ static struct scsi_host_template qla4xxx_driver_template = { .this_id = -1, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .sg_tablesize = SG_ALL, .max_sectors = 0xFFFF, diff --git a/drivers/scsi/qlogicfas.c b/drivers/scsi/qlogicfas.c index 1e874f1fb5c6..1769f965eedf 100644 --- a/drivers/scsi/qlogicfas.c +++ b/drivers/scsi/qlogicfas.c @@ -197,6 +197,7 @@ static struct scsi_host_template qlogicfas_driver_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = DISABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static __init int qlogicfas_init(void) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index c75cb6ad6d94..b6e6d801768b 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1645,7 +1645,10 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, * converted, so better keep it safe. */ #ifdef ARCH_HAS_SG_CHAIN - blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS); + if (shost->use_sg_chaining) + blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS); + else + blk_queue_max_phys_segments(q, SCSI_MAX_SG_SEGMENTS); #else blk_queue_max_phys_segments(q, SCSI_MAX_SG_SEGMENTS); #endif diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c index 72f6d8015358..e3fab3a6aed7 100644 --- a/drivers/scsi/stex.c +++ b/drivers/scsi/stex.c @@ -1123,6 +1123,7 @@ static struct scsi_host_template driver_template = { .this_id = -1, .sg_tablesize = ST_MAX_SG, .cmd_per_lun = ST_CMD_PER_LUN, + .use_sg_chaining = ENABLE_SG_CHAINING, }; static int stex_set_dma_mask(struct pci_dev * pdev) diff --git a/drivers/scsi/sym53c416.c b/drivers/scsi/sym53c416.c index 92bfaeafe30d..8befab7e9839 100644 --- a/drivers/scsi/sym53c416.c +++ b/drivers/scsi/sym53c416.c @@ -854,5 +854,6 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = 1, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c index 3db22325ea2c..db03c4c8ec1e 100644 --- a/drivers/scsi/sym53c8xx_2/sym_glue.c +++ b/drivers/scsi/sym53c8xx_2/sym_glue.c @@ -1808,6 +1808,7 @@ static struct scsi_host_template sym2_template = { .eh_host_reset_handler = sym53c8xx_eh_host_reset_handler, .this_id = 7, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .max_sectors = 0xFFFF, #ifdef SYM_LINUX_PROC_INFO_SUPPORT .proc_info = sym53c8xx_proc_info, diff --git a/drivers/scsi/u14-34f.c b/drivers/scsi/u14-34f.c index fc9f51818e8f..d6cb549a60ca 100644 --- a/drivers/scsi/u14-34f.c +++ b/drivers/scsi/u14-34f.c @@ -451,6 +451,7 @@ static struct scsi_host_template driver_template = { .this_id = 7, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING + .use_sg_chaining = ENABLE_SG_CHAINING, }; #if !defined(__BIG_ENDIAN_BITFIELD) && !defined(__LITTLE_ENDIAN_BITFIELD) diff --git a/drivers/scsi/ultrastor.c b/drivers/scsi/ultrastor.c index c08235d5afc9..ea72bbeb8f9d 100644 --- a/drivers/scsi/ultrastor.c +++ b/drivers/scsi/ultrastor.c @@ -1197,5 +1197,6 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = ULTRASTOR_MAX_CMDS_PER_LUN, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/wd7000.c b/drivers/scsi/wd7000.c index d6fd4259c56b..255c611e78b8 100644 --- a/drivers/scsi/wd7000.c +++ b/drivers/scsi/wd7000.c @@ -1671,6 +1671,7 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = 1, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 7d210cd6c38d..0fd4746ee39d 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -39,6 +39,9 @@ struct blk_queue_tags; #define DISABLE_CLUSTERING 0 #define ENABLE_CLUSTERING 1 +#define DISABLE_SG_CHAINING 0 +#define ENABLE_SG_CHAINING 1 + enum scsi_eh_timer_return { EH_NOT_HANDLED, EH_HANDLED, @@ -442,6 +445,15 @@ struct scsi_host_template { */ unsigned ordered_tag:1; + /* + * true if the low-level driver can support sg chaining. this + * will be removed eventually when all the drivers are + * converted to support sg chaining. + * + * Status: OBSOLETE + */ + unsigned use_sg_chaining:1; + /* * Countdown for host blocking with no commands outstanding */ @@ -586,6 +598,7 @@ struct Scsi_Host { unsigned unchecked_isa_dma:1; unsigned use_clustering:1; unsigned use_blk_tcq:1; + unsigned use_sg_chaining:1; /* * Host has requested that no further requests come through for the -- cgit v1.2.3 From 2a7c59e79ce060c746358b08521de0acbca6a4f1 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 18 Sep 2007 12:17:28 +0200 Subject: remove sglist_len Signed-off-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- drivers/scsi/scsi_lib.c | 11 ++++------- include/scsi/scsi_cmnd.h | 1 - 2 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 1a7e8d811a08..aac8a02cbe80 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -769,10 +769,8 @@ struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask) /* * first loop through, set initial index and return value */ - if (!ret) { - cmd->sglist_len = index; + if (!ret) ret = sgl; - } /* * chain previous sglist, if any. we know the previous @@ -825,8 +823,6 @@ void scsi_free_sgtable(struct scsi_cmnd *cmd) struct scatterlist *sgl = cmd->request_buffer; struct scsi_host_sg_pool *sgp; - BUG_ON(cmd->sglist_len >= SG_MEMPOOL_NR); - /* * if this is the biggest size sglist, check if we have * chained parts we need to free @@ -861,9 +857,10 @@ void scsi_free_sgtable(struct scsi_cmnd *cmd) * Restore original, will be freed below */ sgl = cmd->request_buffer; - } + sgp = scsi_sg_pools + SG_MEMPOOL_NR - 1; + } else + sgp = scsi_sg_pools + scsi_sgtable_index(cmd->__use_sg); - sgp = scsi_sg_pools + cmd->sglist_len; mempool_free(sgl, sgp->pool); } diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 4a5fa2d1c44c..3f47e522a1ec 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -69,7 +69,6 @@ struct scsi_cmnd { /* These elements define the operation we ultimately want to perform */ unsigned short use_sg; /* Number of pieces of scatter-gather */ - unsigned short sglist_len; /* size of malloc'd scatter-gather list */ unsigned short __use_sg; unsigned underflow; /* Return error if less than -- cgit v1.2.3 From a17b4904206eda7d1120a099a9717e73113b275d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 May 2007 09:15:27 +0200 Subject: i386 dma_map_sg: convert to using sg helpers The dma mapping helpers need to be converted to using sg helpers as well, so they will work with a chained sglist setup. Signed-off-by: Jens Axboe --- include/asm-x86/dma-mapping_32.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/asm-x86/dma-mapping_32.h b/include/asm-x86/dma-mapping_32.h index f1d72d177f68..6a2d26cb5da6 100644 --- a/include/asm-x86/dma-mapping_32.h +++ b/include/asm-x86/dma-mapping_32.h @@ -2,10 +2,10 @@ #define _ASM_I386_DMA_MAPPING_H #include +#include #include #include -#include #include #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) @@ -35,18 +35,19 @@ dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, } static inline int -dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; BUG_ON(!valid_dma_direction(direction)); - WARN_ON(nents == 0 || sg[0].length == 0); + WARN_ON(nents == 0 || sglist[0].length == 0); - for (i = 0; i < nents; i++ ) { - BUG_ON(!sg[i].page); + for_each_sg(sglist, sg, nents, i) { + BUG_ON(!sg->page); - sg[i].dma_address = page_to_phys(sg[i].page) + sg[i].offset; + sg->dma_address = page_to_phys(sg->page) + sg->offset; } flush_write_buffers(); -- cgit v1.2.3 From 38d375561f0f89e76f28ed9e69706bb2c980200f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 11 May 2007 12:57:30 +0200 Subject: i386: enable sg chaining We don't need to do more on x86, there's no iommu to be worried about. Signed-off-by: Jens Axboe --- include/asm-x86/scatterlist_32.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-x86/scatterlist_32.h b/include/asm-x86/scatterlist_32.h index d7e45a8f1aae..bd5164aa8f63 100644 --- a/include/asm-x86/scatterlist_32.h +++ b/include/asm-x86/scatterlist_32.h @@ -10,6 +10,8 @@ struct scatterlist { unsigned int length; }; +#define ARCH_HAS_SG_CHAIN + /* These macros should be used after a pci_map_sg call has been done * to get bus addresses of each of the SG entries and their lengths. * You should only work with the number of sg entries pci_map_sg -- cgit v1.2.3 From 46856afa01769db3a5b16c3f57aa5bca45729edd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 May 2007 11:59:55 +0200 Subject: x86-64: enable sg chaining Signed-off-by: Jens Axboe --- include/asm-x86/dma-mapping_64.h | 3 +-- include/asm-x86/scatterlist_64.h | 2 ++ 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-x86/dma-mapping_64.h b/include/asm-x86/dma-mapping_64.h index 6897e2a436e5..ecd0f6125ba3 100644 --- a/include/asm-x86/dma-mapping_64.h +++ b/include/asm-x86/dma-mapping_64.h @@ -6,8 +6,7 @@ * documentation. */ - -#include +#include #include #include diff --git a/include/asm-x86/scatterlist_64.h b/include/asm-x86/scatterlist_64.h index eaf7ada27e14..ef3986ba4b79 100644 --- a/include/asm-x86/scatterlist_64.h +++ b/include/asm-x86/scatterlist_64.h @@ -11,6 +11,8 @@ struct scatterlist { unsigned int dma_length; }; +#define ARCH_HAS_SG_CHAIN + #define ISA_DMA_THRESHOLD (0x00ffffff) /* These macros should be used after a pci_map_sg call has been done -- cgit v1.2.3 From 9b6eccfccbfb2cde5405021beaad2ebb8081a2e9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2007 11:27:26 +0200 Subject: IA64: sg chaining support This updates the ia64 iommu/pci dma mappers to sg chaining. Signed-off-by: Jens Axboe --- arch/ia64/hp/common/sba_iommu.c | 14 +++++++------- arch/ia64/sn/pci/pci_dma.c | 11 ++++++----- include/asm-ia64/dma-mapping.h | 2 +- include/asm-ia64/scatterlist.h | 2 ++ 4 files changed, 16 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index e980e7aa2306..4338f4123f31 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -396,7 +396,7 @@ sba_dump_sg( struct ioc *ioc, struct scatterlist *startsg, int nents) printk(KERN_DEBUG " %d : DMA %08lx/%05x CPU %p\n", nents, startsg->dma_address, startsg->dma_length, sba_sg_address(startsg)); - startsg++; + startsg = sg_next(startsg); } } @@ -409,7 +409,7 @@ sba_check_sg( struct ioc *ioc, struct scatterlist *startsg, int nents) while (the_nents-- > 0) { if (sba_sg_address(the_sg) == 0x0UL) sba_dump_sg(NULL, startsg, nents); - the_sg++; + the_sg = sg_next(the_sg); } } @@ -1201,7 +1201,7 @@ sba_fill_pdir( u32 pide = startsg->dma_address & ~PIDE_FLAG; dma_offset = (unsigned long) pide & ~iovp_mask; startsg->dma_address = 0; - dma_sg++; + dma_sg = sg_next(dma_sg); dma_sg->dma_address = pide | ioc->ibase; pdirp = &(ioc->pdir_base[pide >> iovp_shift]); n_mappings++; @@ -1228,7 +1228,7 @@ sba_fill_pdir( pdirp++; } while (cnt > 0); } - startsg++; + startsg = sg_next(startsg); } /* force pdir update */ wmb(); @@ -1297,7 +1297,7 @@ sba_coalesce_chunks( struct ioc *ioc, while (--nents > 0) { unsigned long vaddr; /* tmp */ - startsg++; + startsg = sg_next(startsg); /* PARANOID */ startsg->dma_address = startsg->dma_length = 0; @@ -1407,7 +1407,7 @@ int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, int di #ifdef ALLOW_IOV_BYPASS_SG ASSERT(to_pci_dev(dev)->dma_mask); if (likely((ioc->dma_mask & ~to_pci_dev(dev)->dma_mask) == 0)) { - for (sg = sglist ; filled < nents ; filled++, sg++){ + for_each_sg(sglist, sg, nents, filled) { sg->dma_length = sg->length; sg->dma_address = virt_to_phys(sba_sg_address(sg)); } @@ -1501,7 +1501,7 @@ void sba_unmap_sg (struct device *dev, struct scatterlist *sglist, int nents, in while (nents && sglist->dma_length) { sba_unmap_single(dev, sglist->dma_address, sglist->dma_length, dir); - sglist++; + sglist = sg_next(sglist); nents--; } diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index d79ddacfba2d..ecd8a52b9b9e 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -218,16 +218,17 @@ EXPORT_SYMBOL(sn_dma_unmap_single); * * Unmap a set of streaming mode DMA translations. */ -void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sg, +void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl, int nhwentries, int direction) { int i; struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); + struct scatterlist *sg; BUG_ON(dev->bus != &pci_bus_type); - for (i = 0; i < nhwentries; i++, sg++) { + for_each_sg(sgl, sg, nhwentries, i) { provider->dma_unmap(pdev, sg->dma_address, direction); sg->dma_address = (dma_addr_t) NULL; sg->dma_length = 0; @@ -244,11 +245,11 @@ EXPORT_SYMBOL(sn_dma_unmap_sg); * * Maps each entry of @sg for DMA. */ -int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries, +int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries, int direction) { unsigned long phys_addr; - struct scatterlist *saved_sg = sg; + struct scatterlist *saved_sg = sgl, *sg; struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); int i; @@ -258,7 +259,7 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries, /* * Setup a DMA address for each entry in the scatterlist. */ - for (i = 0; i < nhwentries; i++, sg++) { + for_each_sg(sgl, sg, nhwentries, i) { phys_addr = SG_ENT_PHYS_ADDRESS(sg); sg->dma_address = provider->dma_map(pdev, phys_addr, sg->length, diff --git a/include/asm-ia64/dma-mapping.h b/include/asm-ia64/dma-mapping.h index 3ca6d5c14b2e..f1735a22d0ea 100644 --- a/include/asm-ia64/dma-mapping.h +++ b/include/asm-ia64/dma-mapping.h @@ -6,7 +6,7 @@ * David Mosberger-Tang */ #include -#include +#include #define dma_alloc_coherent platform_dma_alloc_coherent /* coherent mem. is cheap */ diff --git a/include/asm-ia64/scatterlist.h b/include/asm-ia64/scatterlist.h index a452ea24205a..7d5234d50312 100644 --- a/include/asm-ia64/scatterlist.h +++ b/include/asm-ia64/scatterlist.h @@ -30,4 +30,6 @@ struct scatterlist { #define sg_dma_len(sg) ((sg)->dma_length) #define sg_dma_address(sg) ((sg)->dma_address) +#define ARCH_HAS_SG_CHAIN + #endif /* _ASM_IA64_SCATTERLIST_H */ -- cgit v1.2.3 From d1ed455e30e439e0d1483c2e236d7e15e1010704 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 19 Jul 2007 08:22:17 +0200 Subject: PS3: sg chaining support Acked-by: Geoff Levand Signed-off-by: Jens Axboe --- arch/powerpc/platforms/ps3/system-bus.c | 7 ++++--- include/asm-powerpc/dma-mapping.h | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 190ff4b59a55..07e64b48e7fc 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -616,17 +616,18 @@ static void ps3_unmap_single(struct device *_dev, dma_addr_t dma_addr, } } -static int ps3_sb_map_sg(struct device *_dev, struct scatterlist *sg, int nents, - enum dma_data_direction direction) +static int ps3_sb_map_sg(struct device *_dev, struct scatterlist *sgl, + int nents, enum dma_data_direction direction) { #if defined(CONFIG_PS3_DYNAMIC_DMA) BUG_ON("do"); return -EPERM; #else struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); + struct scatterlist *sg; int i; - for (i = 0; i < nents; i++, sg++) { + for_each_sg(sgl, sg, nents, i) { int result = ps3_dma_map(dev->d_region, page_to_phys(sg->page) + sg->offset, sg->length, &sg->dma_address, 0); diff --git a/include/asm-powerpc/dma-mapping.h b/include/asm-powerpc/dma-mapping.h index d05891608f74..60eacde828c0 100644 --- a/include/asm-powerpc/dma-mapping.h +++ b/include/asm-powerpc/dma-mapping.h @@ -12,7 +12,7 @@ #include /* need struct page definitions */ #include -#include +#include #include #define DMA_ERROR_CODE (~(dma_addr_t)0x0) -- cgit v1.2.3 From 78bdc3106a877cfa50439fa66b52acbc4e7868df Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 12 Oct 2007 13:44:12 +0200 Subject: PPC: sg chaining support This updates the ppc iommu/pci dma mappers to sg chaining. Includes further fixes from FUJITA Tomonori . Signed-off-by: Jens Axboe --- arch/powerpc/kernel/dma_64.c | 5 +- arch/powerpc/kernel/ibmebus.c | 11 +-- arch/powerpc/kernel/iommu.c | 23 +++--- include/asm-powerpc/dma-mapping.h | 158 +++----------------------------------- include/asm-powerpc/scatterlist.h | 2 + 5 files changed, 34 insertions(+), 165 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c index 7b0e754383cf..9001104b56b0 100644 --- a/arch/powerpc/kernel/dma_64.c +++ b/arch/powerpc/kernel/dma_64.c @@ -154,12 +154,13 @@ static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr, { } -static int dma_direct_map_sg(struct device *dev, struct scatterlist *sg, +static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; - for (i = 0; i < nents; i++, sg++) { + for_each_sg(sgl, sg, nents, i) { sg->dma_address = (page_to_phys(sg->page) + sg->offset) | dma_direct_offset; sg->dma_length = sg->length; diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 53bf64623bd8..2e16ca5778a3 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -87,15 +87,16 @@ static void ibmebus_unmap_single(struct device *dev, } static int ibmebus_map_sg(struct device *dev, - struct scatterlist *sg, + struct scatterlist *sgl, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; - for (i = 0; i < nents; i++) { - sg[i].dma_address = (dma_addr_t)page_address(sg[i].page) - + sg[i].offset; - sg[i].dma_length = sg[i].length; + for_each_sg(sgl, sg, nents, i) { + sg->dma_address = (dma_addr_t)page_address(sg->page) + + sg->offset; + sg->dma_length = sg->length; } return nents; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index e4ec6eee81a8..306a6f75b6c5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -277,7 +277,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, dma_addr_t dma_next = 0, dma_addr; unsigned long flags; struct scatterlist *s, *outs, *segstart; - int outcount, incount; + int outcount, incount, i; unsigned long handle; BUG_ON(direction == DMA_NONE); @@ -297,7 +297,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, spin_lock_irqsave(&(tbl->it_lock), flags); - for (s = outs; nelems; nelems--, s++) { + for_each_sg(sglist, s, nelems, i) { unsigned long vaddr, npages, entry, slen; slen = s->length; @@ -341,7 +341,8 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (novmerge || (dma_addr != dma_next)) { /* Can't merge: create a new segment */ segstart = s; - outcount++; outs++; + outcount++; + outs = sg_next(outs); DBG(" can't merge, new segment.\n"); } else { outs->dma_length += s->length; @@ -374,7 +375,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, * next entry of the sglist if we didn't fill the list completely */ if (outcount < incount) { - outs++; + outs = sg_next(outs); outs->dma_address = DMA_ERROR_CODE; outs->dma_length = 0; } @@ -385,7 +386,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, return outcount; failure: - for (s = &sglist[0]; s <= outs; s++) { + for_each_sg(sglist, s, nelems, i) { if (s->dma_length != 0) { unsigned long vaddr, npages; @@ -395,6 +396,8 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; } + if (s == outs) + break; } spin_unlock_irqrestore(&(tbl->it_lock), flags); return 0; @@ -404,6 +407,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, int nelems, enum dma_data_direction direction) { + struct scatterlist *sg; unsigned long flags; BUG_ON(direction == DMA_NONE); @@ -413,15 +417,16 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, spin_lock_irqsave(&(tbl->it_lock), flags); + sg = sglist; while (nelems--) { unsigned int npages; - dma_addr_t dma_handle = sglist->dma_address; + dma_addr_t dma_handle = sg->dma_address; - if (sglist->dma_length == 0) + if (sg->dma_length == 0) break; - npages = iommu_num_pages(dma_handle,sglist->dma_length); + npages = iommu_num_pages(dma_handle, sg->dma_length); __iommu_free(tbl, dma_handle, npages); - sglist++; + sg = sg_next(sg); } /* Flush/invalidate TLBs if necessary. As for iommu_free(), we diff --git a/include/asm-powerpc/dma-mapping.h b/include/asm-powerpc/dma-mapping.h index 60eacde828c0..2af321f36aba 100644 --- a/include/asm-powerpc/dma-mapping.h +++ b/include/asm-powerpc/dma-mapping.h @@ -6,149 +6,6 @@ */ #ifndef _ASM_DMA_MAPPING_H #define _ASM_DMA_MAPPING_H -#ifdef __KERNEL__ - -#include -#include -/* need struct page definitions */ -#include -#include -#include - -#define DMA_ERROR_CODE (~(dma_addr_t)0x0) - -#ifdef CONFIG_NOT_COHERENT_CACHE -/* - * DMA-consistent mapping functions for PowerPCs that don't support - * cache snooping. These allocate/free a region of uncached mapped - * memory space for use with DMA devices. Alternatively, you could - * allocate the space "normally" and use the cache management functions - * to ensure it is consistent. - */ -extern void *__dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp); -extern void __dma_free_coherent(size_t size, void *vaddr); -extern void __dma_sync(void *vaddr, size_t size, int direction); -extern void __dma_sync_page(struct page *page, unsigned long offset, - size_t size, int direction); - -#else /* ! CONFIG_NOT_COHERENT_CACHE */ -/* - * Cache coherent cores. - */ - -#define __dma_alloc_coherent(gfp, size, handle) NULL -#define __dma_free_coherent(size, addr) ((void)0) -#define __dma_sync(addr, size, rw) ((void)0) -#define __dma_sync_page(pg, off, sz, rw) ((void)0) - -#endif /* ! CONFIG_NOT_COHERENT_CACHE */ - -#ifdef CONFIG_PPC64 -/* - * DMA operations are abstracted for G5 vs. i/pSeries, PCI vs. VIO - */ -struct dma_mapping_ops { - void * (*alloc_coherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag); - void (*free_coherent)(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - dma_addr_t (*map_single)(struct device *dev, void *ptr, - size_t size, enum dma_data_direction direction); - void (*unmap_single)(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction); - int (*map_sg)(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction); - void (*unmap_sg)(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction); - int (*dma_supported)(struct device *dev, u64 mask); - int (*set_dma_mask)(struct device *dev, u64 dma_mask); -}; - -static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) -{ - /* We don't handle the NULL dev case for ISA for now. We could - * do it via an out of line call but it is not needed for now. The - * only ISA DMA device we support is the floppy and we have a hack - * in the floppy driver directly to get a device for us. - */ - if (unlikely(dev == NULL || dev->archdata.dma_ops == NULL)) - return NULL; - return dev->archdata.dma_ops; -} - -static inline int dma_supported(struct device *dev, u64 mask) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (unlikely(dma_ops == NULL)) - return 0; - if (dma_ops->dma_supported == NULL) - return 1; - return dma_ops->dma_supported(dev, mask); -} - -static inline int dma_set_mask(struct device *dev, u64 dma_mask) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - if (unlikely(dma_ops == NULL)) - return -EIO; - if (dma_ops->set_dma_mask != NULL) - return dma_ops->set_dma_mask(dev, dma_mask); - if (!dev->dma_mask || !dma_supported(dev, dma_mask)) - return -EIO; - *dev->dma_mask = dma_mask; - return 0; -} - -static inline void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - BUG_ON(!dma_ops); - return dma_ops->alloc_coherent(dev, size, dma_handle, flag); -} - -static inline void dma_free_coherent(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t dma_handle) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - BUG_ON(!dma_ops); - dma_ops->free_coherent(dev, size, cpu_addr, dma_handle); -} - -static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, - size_t size, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - BUG_ON(!dma_ops); - return dma_ops->map_single(dev, cpu_addr, size, direction); -} - -static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - BUG_ON(!dma_ops); - dma_ops->unmap_single(dev, dma_addr, size, direction); -} - -static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - - BUG_ON(!dma_ops); - return dma_ops->map_single(dev, page_address(page) + offset, size, - direction); -} static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, @@ -276,14 +133,15 @@ static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address, } static inline int -dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +dma_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; BUG_ON(direction == DMA_NONE); - for (i = 0; i < nents; i++, sg++) { + for_each_sg(sgl, sg, nents, i) { BUG_ON(!sg->page); __dma_sync_page(sg->page, sg->offset, sg->length, direction); sg->dma_address = page_to_bus(sg->page) + sg->offset; @@ -318,26 +176,28 @@ static inline void dma_sync_single_for_device(struct device *dev, } static inline void dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sg, int nents, + struct scatterlist *sgl, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; BUG_ON(direction == DMA_NONE); - for (i = 0; i < nents; i++, sg++) + for_each_sg(sgl, sg, nents, i) __dma_sync_page(sg->page, sg->offset, sg->length, direction); } static inline void dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nents, + struct scatterlist *sgl, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; BUG_ON(direction == DMA_NONE); - for (i = 0; i < nents; i++, sg++) + for_each_sg(sgl, sg, nents, i) __dma_sync_page(sg->page, sg->offset, sg->length, direction); } diff --git a/include/asm-powerpc/scatterlist.h b/include/asm-powerpc/scatterlist.h index 8c992d1491d4..b075f619c3b7 100644 --- a/include/asm-powerpc/scatterlist.h +++ b/include/asm-powerpc/scatterlist.h @@ -41,5 +41,7 @@ struct scatterlist { #define ISA_DMA_THRESHOLD (~0UL) #endif +#define ARCH_HAS_SG_CHAIN + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SCATTERLIST_H */ -- cgit v1.2.3 From 0912a5db0ea45d8aef3ee99a882e093285e32c3c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 14 May 2007 15:44:38 +0200 Subject: SPARC: sg chaining support This updates the sparc iommu/pci dma mappers to sg chaining. Acked-by: David S. Miller Signed-off-by: Jens Axboe --- arch/sparc/kernel/ioport.c | 25 +++++++++++++------------ arch/sparc/mm/io-unit.c | 12 +++++++----- arch/sparc/mm/iommu.c | 10 +++++----- arch/sparc/mm/sun4c.c | 10 ++++++---- include/asm-sparc/scatterlist.h | 2 ++ 5 files changed, 33 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 62182d2d7b0d..9c3ed88853f3 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -35,6 +35,7 @@ #include #include /* struct pci_dev */ #include +#include #include #include @@ -717,19 +718,19 @@ void pci_unmap_page(struct pci_dev *hwdev, * Device ownership issues as mentioned above for pci_map_single are * the same here. */ -int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents, +int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction) { + struct scatterlist *sg; int n; BUG_ON(direction == PCI_DMA_NONE); /* IIep is write-through, not flushing. */ - for (n = 0; n < nents; n++) { + for_each_sg(sgl, sg, nents, n) { BUG_ON(page_address(sg->page) == NULL); sg->dvma_address = virt_to_phys(page_address(sg->page)) + sg->offset; sg->dvma_length = sg->length; - sg++; } return nents; } @@ -738,19 +739,19 @@ int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents, * Again, cpu read rules concerning calls here are the same as for * pci_unmap_single() above. */ -void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents, +void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction) { + struct scatterlist *sg; int n; BUG_ON(direction == PCI_DMA_NONE); if (direction != PCI_DMA_TODEVICE) { - for (n = 0; n < nents; n++) { + for_each_sg(sgl, sg, nents, n) { BUG_ON(page_address(sg->page) == NULL); mmu_inval_dma_area( (unsigned long) page_address(sg->page), (sg->length + PAGE_SIZE-1) & PAGE_MASK); - sg++; } } } @@ -789,34 +790,34 @@ void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t ba, size_t * The same as pci_dma_sync_single_* but for a scatter-gather list, * same rules and usage. */ -void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction) +void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction) { + struct scatterlist *sg; int n; BUG_ON(direction == PCI_DMA_NONE); if (direction != PCI_DMA_TODEVICE) { - for (n = 0; n < nents; n++) { + for_each_sg(sgl, sg, nents, n) { BUG_ON(page_address(sg->page) == NULL); mmu_inval_dma_area( (unsigned long) page_address(sg->page), (sg->length + PAGE_SIZE-1) & PAGE_MASK); - sg++; } } } -void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction) +void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction) { + struct scatterlist *sg; int n; BUG_ON(direction == PCI_DMA_NONE); if (direction != PCI_DMA_TODEVICE) { - for (n = 0; n < nents; n++) { + for_each_sg(sgl, sg, nents, n) { BUG_ON(page_address(sg->page) == NULL); mmu_inval_dma_area( (unsigned long) page_address(sg->page), (sg->length + PAGE_SIZE-1) & PAGE_MASK); - sg++; } } } diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c index 7c89893b1fe8..375b4db63704 100644 --- a/arch/sparc/mm/io-unit.c +++ b/arch/sparc/mm/io-unit.c @@ -11,8 +11,8 @@ #include #include /* pte_offset_map => kmap_atomic */ #include +#include -#include #include #include #include @@ -144,8 +144,9 @@ static void iounit_get_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_bus spin_lock_irqsave(&iounit->lock, flags); while (sz != 0) { --sz; - sg[sz].dvma_address = iounit_get_area(iounit, (unsigned long)page_address(sg[sz].page) + sg[sz].offset, sg[sz].length); - sg[sz].dvma_length = sg[sz].length; + sg->dvma_address = iounit_get_area(iounit, (unsigned long)page_address(sg->page) + sg->offset, sg->length); + sg->dvma_length = sg->length; + sg = sg_next(sg); } spin_unlock_irqrestore(&iounit->lock, flags); } @@ -173,11 +174,12 @@ static void iounit_release_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_ spin_lock_irqsave(&iounit->lock, flags); while (sz != 0) { --sz; - len = ((sg[sz].dvma_address & ~PAGE_MASK) + sg[sz].length + (PAGE_SIZE-1)) >> PAGE_SHIFT; - vaddr = (sg[sz].dvma_address - IOUNIT_DMA_BASE) >> PAGE_SHIFT; + len = ((sg->dvma_address & ~PAGE_MASK) + sg->length + (PAGE_SIZE-1)) >> PAGE_SHIFT; + vaddr = (sg->dvma_address - IOUNIT_DMA_BASE) >> PAGE_SHIFT; IOD(("iounit_release %08lx-%08lx\n", (long)vaddr, (long)len+vaddr)); for (len += vaddr; vaddr < len; vaddr++) clear_bit(vaddr, iounit->bmap); + sg = sg_next(sg); } spin_unlock_irqrestore(&iounit->lock, flags); } diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 52e907af9d29..283656d9f6ea 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -12,8 +12,8 @@ #include #include #include /* pte_offset_map => kmap_atomic */ +#include -#include #include #include #include @@ -240,7 +240,7 @@ static void iommu_get_scsi_sgl_noflush(struct scatterlist *sg, int sz, struct sb n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT; sg->dvma_address = iommu_get_one(sg->page, n, sbus) + sg->offset; sg->dvma_length = (__u32) sg->length; - sg++; + sg = sg_next(sg); } } @@ -254,7 +254,7 @@ static void iommu_get_scsi_sgl_gflush(struct scatterlist *sg, int sz, struct sbu n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT; sg->dvma_address = iommu_get_one(sg->page, n, sbus) + sg->offset; sg->dvma_length = (__u32) sg->length; - sg++; + sg = sg_next(sg); } } @@ -285,7 +285,7 @@ static void iommu_get_scsi_sgl_pflush(struct scatterlist *sg, int sz, struct sbu sg->dvma_address = iommu_get_one(sg->page, n, sbus) + sg->offset; sg->dvma_length = (__u32) sg->length; - sg++; + sg = sg_next(sg); } } @@ -325,7 +325,7 @@ static void iommu_release_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_b n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT; iommu_release_one(sg->dvma_address & PAGE_MASK, n, sbus); sg->dvma_address = 0x21212121; - sg++; + sg = sg_next(sg); } } diff --git a/arch/sparc/mm/sun4c.c b/arch/sparc/mm/sun4c.c index 005a3e72d4f2..ee6708fc4492 100644 --- a/arch/sparc/mm/sun4c.c +++ b/arch/sparc/mm/sun4c.c @@ -17,8 +17,8 @@ #include #include #include +#include -#include #include #include #include @@ -1228,8 +1228,9 @@ static void sun4c_get_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_bus * { while (sz != 0) { --sz; - sg[sz].dvma_address = (__u32)sun4c_lockarea(page_address(sg[sz].page) + sg[sz].offset, sg[sz].length); - sg[sz].dvma_length = sg[sz].length; + sg->dvma_address = (__u32)sun4c_lockarea(page_address(sg->page) + sg->offset, sg->length); + sg->dvma_length = sg->length; + sg = sg_next(sg); } } @@ -1244,7 +1245,8 @@ static void sun4c_release_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_b { while (sz != 0) { --sz; - sun4c_unlockarea((char *)sg[sz].dvma_address, sg[sz].length); + sun4c_unlockarea((char *)sg->dvma_address, sg->length); + sg = sg_next(sg); } } diff --git a/include/asm-sparc/scatterlist.h b/include/asm-sparc/scatterlist.h index a4fcf9ac9649..4055af90ad7e 100644 --- a/include/asm-sparc/scatterlist.h +++ b/include/asm-sparc/scatterlist.h @@ -19,4 +19,6 @@ struct scatterlist { #define ISA_DMA_THRESHOLD (~0UL) +#define ARCH_HAS_SG_CHAIN + #endif /* !(_SPARC_SCATTERLIST_H) */ -- cgit v1.2.3 From 2c941a204070ab32d92d40318a3196a7fb994c00 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 7 Aug 2007 09:37:10 +0200 Subject: SPARC64: sg chaining support This updates the sparc64 iommu/pci dma mappers to sg chaining. Acked-by: David S. Miller Later updated to newer kernel with unified sparc64 iommu sg handling. Signed-off-by: Jens Axboe --- arch/sparc64/kernel/iommu.c | 39 ++++++++++++++++++++++++--------------- arch/sparc64/kernel/pci_sun4v.c | 32 +++++++++++++++++++------------- include/asm-sparc64/scatterlist.h | 2 ++ 3 files changed, 45 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/arch/sparc64/kernel/iommu.c b/arch/sparc64/kernel/iommu.c index b35a62167e9c..db3ffcf7a120 100644 --- a/arch/sparc64/kernel/iommu.c +++ b/arch/sparc64/kernel/iommu.c @@ -10,6 +10,7 @@ #include #include #include +#include #ifdef CONFIG_PCI #include @@ -480,7 +481,7 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg, unsigned long iopte_protection) { struct scatterlist *dma_sg = sg; - struct scatterlist *sg_end = sg + nelems; + struct scatterlist *sg_end = sg_last(sg, nelems); int i; for (i = 0; i < nused; i++) { @@ -515,7 +516,7 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg, len -= (IO_PAGE_SIZE - (tmp & (IO_PAGE_SIZE - 1UL))); break; } - sg++; + sg = sg_next(sg); } pteval = iopte_protection | (pteval & IOPTE_PAGE); @@ -528,24 +529,24 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg, } pteval = (pteval & IOPTE_PAGE) + len; - sg++; + sg = sg_next(sg); /* Skip over any tail mappings we've fully mapped, * adjusting pteval along the way. Stop when we * detect a page crossing event. */ - while (sg < sg_end && + while (sg != sg_end && (pteval << (64 - IO_PAGE_SHIFT)) != 0UL && (pteval == SG_ENT_PHYS_ADDRESS(sg)) && ((pteval ^ (SG_ENT_PHYS_ADDRESS(sg) + sg->length - 1UL)) >> IO_PAGE_SHIFT) == 0UL) { pteval += sg->length; - sg++; + sg = sg_next(sg); } if ((pteval << (64 - IO_PAGE_SHIFT)) == 0UL) pteval = ~0UL; } while (dma_npages != 0); - dma_sg++; + dma_sg = sg_next(dma_sg); } } @@ -606,7 +607,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist, sgtmp = sglist; while (used && sgtmp->dma_length) { sgtmp->dma_address += dma_base; - sgtmp++; + sgtmp = sg_next(sgtmp); used--; } used = nelems - used; @@ -642,6 +643,7 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist, struct strbuf *strbuf; iopte_t *base; unsigned long flags, ctx, i, npages; + struct scatterlist *sg, *sgprv; u32 bus_addr; if (unlikely(direction == DMA_NONE)) { @@ -654,11 +656,14 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist, bus_addr = sglist->dma_address & IO_PAGE_MASK; - for (i = 1; i < nelems; i++) - if (sglist[i].dma_length == 0) + sgprv = NULL; + for_each_sg(sglist, sg, nelems, i) { + if (sg->dma_length == 0) break; - i--; - npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) - + sgprv = sg; + } + + npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length) - bus_addr) >> IO_PAGE_SHIFT; base = iommu->page_table + @@ -730,6 +735,7 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev, struct iommu *iommu; struct strbuf *strbuf; unsigned long flags, ctx, npages, i; + struct scatterlist *sg, *sgprv; u32 bus_addr; iommu = dev->archdata.iommu; @@ -753,11 +759,14 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev, /* Step 2: Kick data out of streaming buffers. */ bus_addr = sglist[0].dma_address & IO_PAGE_MASK; - for(i = 1; i < nelems; i++) - if (!sglist[i].dma_length) + sgprv = NULL; + for_each_sg(sglist, sg, nelems, i) { + if (sg->dma_length == 0) break; - i--; - npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) + sgprv = sg; + } + + npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length) - bus_addr) >> IO_PAGE_SHIFT; strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction); diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc64/kernel/pci_sun4v.c index 95de1444ee67..cacacfae5451 100644 --- a/arch/sparc64/kernel/pci_sun4v.c +++ b/arch/sparc64/kernel/pci_sun4v.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -373,7 +374,7 @@ static inline long fill_sg(long entry, struct device *dev, int nused, int nelems, unsigned long prot) { struct scatterlist *dma_sg = sg; - struct scatterlist *sg_end = sg + nelems; + struct scatterlist *sg_end = sg_last(sg, nelems); unsigned long flags; int i; @@ -413,7 +414,7 @@ static inline long fill_sg(long entry, struct device *dev, len -= (IO_PAGE_SIZE - (tmp & (IO_PAGE_SIZE - 1UL))); break; } - sg++; + sg = sg_next(sg); } pteval = (pteval & IOPTE_PAGE); @@ -431,24 +432,25 @@ static inline long fill_sg(long entry, struct device *dev, } pteval = (pteval & IOPTE_PAGE) + len; - sg++; + sg = sg_next(sg); /* Skip over any tail mappings we've fully mapped, * adjusting pteval along the way. Stop when we * detect a page crossing event. */ - while (sg < sg_end && - (pteval << (64 - IO_PAGE_SHIFT)) != 0UL && + while ((pteval << (64 - IO_PAGE_SHIFT)) != 0UL && (pteval == SG_ENT_PHYS_ADDRESS(sg)) && ((pteval ^ (SG_ENT_PHYS_ADDRESS(sg) + sg->length - 1UL)) >> IO_PAGE_SHIFT) == 0UL) { pteval += sg->length; - sg++; + if (sg == sg_end) + break; + sg = sg_next(sg); } if ((pteval << (64 - IO_PAGE_SHIFT)) == 0UL) pteval = ~0UL; } while (dma_npages != 0); - dma_sg++; + dma_sg = sg_next(dma_sg); } if (unlikely(iommu_batch_end() < 0L)) @@ -510,7 +512,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, sgtmp = sglist; while (used && sgtmp->dma_length) { sgtmp->dma_address += dma_base; - sgtmp++; + sgtmp = sg_next(sgtmp); used--; } used = nelems - used; @@ -545,6 +547,7 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, struct pci_pbm_info *pbm; struct iommu *iommu; unsigned long flags, i, npages; + struct scatterlist *sg, *sgprv; long entry; u32 devhandle, bus_addr; @@ -558,12 +561,15 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, devhandle = pbm->devhandle; bus_addr = sglist->dma_address & IO_PAGE_MASK; - - for (i = 1; i < nelems; i++) - if (sglist[i].dma_length == 0) + sgprv = NULL; + for_each_sg(sglist, sg, nelems, i) { + if (sg->dma_length == 0) break; - i--; - npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) - + + sgprv = sg; + } + + npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length) - bus_addr) >> IO_PAGE_SHIFT; entry = ((bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT); diff --git a/include/asm-sparc64/scatterlist.h b/include/asm-sparc64/scatterlist.h index 048fdb40e81d..703c5bbe6c8c 100644 --- a/include/asm-sparc64/scatterlist.h +++ b/include/asm-sparc64/scatterlist.h @@ -20,4 +20,6 @@ struct scatterlist { #define ISA_DMA_THRESHOLD (~0UL) +#define ARCH_HAS_SG_CHAIN + #endif /* !(_SPARC64_SCATTERLIST_H) */ -- cgit v1.2.3