19 files changed, 165 insertions, 187 deletions

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 <davidm@hpl.hp.com>
  */
 #include <asm/machvec.h>
-#include <asm/scatterlist.h>
+#include <linux/scatterlist.h>
 
 #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 */
diff --git a/include/asm-powerpc/dma-mapping.h b/include/asm-powerpc/dma-mapping.h
index d05891608f74..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 <linux/types.h>
-#include <linux/cache.h>
-/* need struct page definitions */
-#include <linux/mm.h>
-#include <asm/scatterlist.h>
-#include <asm/io.h>
-
-#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 */
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) */
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) */
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 <linux/mm.h>
+#include <linux/scatterlist.h>
 
 #include <asm/cache.h>
 #include <asm/io.h>
-#include <asm/scatterlist.h>
 #include <asm/bug.h>
 
 #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();
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 <asm/scatterlist.h>
+#include <linux/scatterlist.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 
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
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
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 089a8bc55dd4..4da441337d6e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -176,13 +176,28 @@ 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_cur_sectors(bio)	(bio_iovec(bio)->bv_len >> 9)
-#define bio_data(bio)		(page_address(bio_page((bio))) + bio_offset((bio)))
 #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)
+
+static inline unsigned int bio_cur_sectors(struct bio *bio)
+{
+	if (bio->bi_vcnt)
+		return bio_iovec(bio)->bv_len >> 9;
+
+	return 0;
+}
+
+static inline void *bio_data(struct bio *bio)
+{
+	if (bio->bi_vcnt)
+		return page_address(bio_page(bio)) + bio_offset(bio);
+
+	return NULL;
+}
 
 /*
  * will die
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5ed888b04b29..bbf906a0b419 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -330,7 +330,6 @@ typedef void (unplug_fn) (struct request_queue *);
 
 struct bio_vec;
 typedef int (merge_bvec_fn) (struct request_queue *, struct bio *, struct bio_vec *);
-typedef int (issue_flush_fn) (struct request_queue *, struct gendisk *, sector_t *);
 typedef void (prepare_flush_fn) (struct request_queue *, struct request *);
 typedef void (softirq_done_fn)(struct request *);
 
@@ -368,7 +367,6 @@ struct request_queue
 	prep_rq_fn		*prep_rq_fn;
 	unplug_fn		*unplug_fn;
 	merge_bvec_fn		*merge_bvec_fn;
-	issue_flush_fn		*issue_flush_fn;
 	prepare_flush_fn	*prepare_flush_fn;
 	softirq_done_fn		*softirq_done_fn;
 
@@ -540,6 +538,7 @@ enum {
 #define blk_barrier_rq(rq)	((rq)->cmd_flags & REQ_HARDBARRIER)
 #define blk_fua_rq(rq)		((rq)->cmd_flags & REQ_FUA)
 #define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
+#define blk_empty_barrier(rq)	(blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
@@ -729,7 +728,9 @@ static inline void blk_run_address_space(struct address_space *mapping)
 extern int end_that_request_first(struct request *, int, int);
 extern int end_that_request_chunk(struct request *, int, int);
 extern void end_that_request_last(struct request *, int);
-extern void end_request(struct request *req, int uptodate);
+extern void end_request(struct request *, int);
+extern void end_queued_request(struct request *, int);
+extern void end_dequeued_request(struct request *, int);
 extern void blk_complete_request(struct request *);
 
 /*
@@ -767,7 +768,6 @@ extern void blk_queue_dma_alignment(struct request_queue *, int);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *);
-extern void blk_queue_issue_flush_fn(struct request_queue *, issue_flush_fn *);
 extern int blk_do_ordered(struct request_queue *, struct request **);
 extern unsigned blk_ordered_cur_seq(struct request_queue *);
 extern unsigned blk_ordered_req_seq(struct request *);
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 <linux/workqueue.h>	/* work_struct */
 #include <linux/mempool.h>
 #include <linux/mutex.h>
+#include <linux/scatterlist.h>
 
 #include <asm/io.h>
 #include <asm/semaphore.h>	/* 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;
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 02a27e8cbad2..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 */
@@ -1093,11 +1093,6 @@ extern ide_startstop_t ide_do_reset (ide_drive_t *);
 extern void ide_init_drive_cmd (struct request *rq);
 
 /*
- * this function returns error location sector offset in case of a write error
- */
-extern u64 ide_get_error_location(ide_drive_t *, char *);
-
-/*
  * "action" parameter type for ide_do_drive_cmd() below.
  */
 typedef enum {
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 <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
-#include <asm/scatterlist.h>
+#include <linux/scatterlist.h>
 #include <linux/io.h>
 #include <linux/ata.h>
 #include <linux/workqueue.h>
@@ -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;
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 4efbd9c445f5..2dc7464cce52 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -20,4 +20,88 @@ static inline void sg_init_one(struct scatterlist *sg, const void *buf,
 	sg_set_buf(sg, buf, buflen);
 }
 
+/*
+ * 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
+ */
+#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 */
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
@@ -11,13 +11,6 @@
 #include <linux/types.h>
 
 /*
- *	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 65ab5145a09b..3f47e522a1ec 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/timer.h>
+#include <linux/scatterlist.h>
 
 struct request;
 struct scatterlist;
@@ -68,7 +69,7 @@ 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 */
@@ -128,7 +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);
@@ -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 */
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,
@@ -443,6 +446,15 @@ 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
 	 */
 	unsigned int max_host_blocked;
@@ -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