Merge branch 'sglist-arch' into for-linus

71 files changed, 509 insertions, 276 deletions

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 68699b3..bbaa545 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;
 	}
 }
@@ -4950,16 +4952,18 @@ static void __atapi_pio_bytes(struct ata_queued_cmd *qc, unsigned int bytes)
 {
 	int do_write = (qc->tf.flags & ATA_TFLAG_WRITE);
 	struct scatterlist *sg = qc->__sg;
+	struct scatterlist *lsg = sg_last(qc->__sg, qc->n_elem);
 	struct ata_port *ap = qc->ap;
 	struct page *page;
 	unsigned char *buf;
 	unsigned int offset, count;
+	int no_more_sg = 0;
 
 	if (qc->curbytes + bytes >= qc->nbytes)
 		ap->hsm_task_state = HSM_ST_LAST;
 
 next_sg:
-	if (unlikely(qc->cursg >= qc->n_elem)) {
+	if (unlikely(no_more_sg)) {
 		/*
 		 * The end of qc->sg is reached and the device expects
 		 * more data to transfer. In order not to overrun qc->sg
@@ -4982,7 +4986,7 @@ next_sg:
 		return;
 	}
 
-	sg = &qc->__sg[qc->cursg];
+	sg = qc->cursg;
 
 	page = sg->page;
 	offset = sg->offset + qc->cursg_ofs;
@@ -5021,7 +5025,10 @@ next_sg:
 	qc->cursg_ofs += count;
 
 	if (qc->cursg_ofs == sg->length) {
-		qc->cursg++;
+		if (qc->cursg == lsg)
+			no_more_sg = 1;
+
+		qc->cursg = sg_next(qc->cursg);
 		qc->cursg_ofs = 0;
 	}
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index d63c81e..ba62d53 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -801,8 +801,6 @@ int ata_scsi_slave_config(struct scsi_device *sdev)
 
 	ata_scsi_sdev_config(sdev);
 
-	blk_queue_max_phys_segments(sdev->request_queue, LIBATA_MAX_PRD);
-
 	sdev->manage_start_stop = 1;
 
 	if (dev)
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index a895228..3fb7e8b 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -2569,6 +2569,7 @@ static void do_cciss_request(struct request_queue *q)
 	       (int)creq->nr_sectors);
 #endif				/* CCISS_DEBUG */
 
+	memset(tmp_sg, 0, sizeof(tmp_sg));
 	seg = blk_rq_map_sg(q, creq, tmp_sg);
 
 	/* get the DMA records for the setup */
diff --git a/drivers/ide/cris/ide-cris.c b/drivers/ide/cris/ide-cris.c
index 2b4d2a0..c306c9f 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 b453211..a4cbbba 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 f36ff59..04273d3 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 d101171..34b1fb6 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 aa06daf..2a3c8d4 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -45,6 +45,7 @@
 #include <linux/hdreg.h>
 #include <linux/ide.h>
 #include <linux/bitops.h>
+#include <linux/scatterlist.h>
 
 #include <asm/byteorder.h>
 #include <asm/irq.h>
@@ -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 aebde49..892d08f 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 85ffaaa..c74fef6 100644
--- a/drivers/ide/pci/sgiioc4.c
+++ b/drivers/ide/pci/sgiioc4.c
@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/ioport.h>
 #include <linux/blkdev.h>
+#include <linux/scatterlist.h>
 #include <linux/ioc4.h>
 #include <asm/io.h>
 
@@ -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 7d88738..9e86406 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/drivers/infiniband/hw/ipath/ipath_dma.c b/drivers/infiniband/hw/ipath/ipath_dma.c
index f87f003..22709a4 100644
--- a/drivers/infiniband/hw/ipath/ipath_dma.c
+++ b/drivers/infiniband/hw/ipath/ipath_dma.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/scatterlist.h>
 #include <rdma/ib_verbs.h>
 
 #include "ipath_verbs.h"
@@ -96,17 +97,18 @@ static void ipath_dma_unmap_page(struct ib_device *dev,
 	BUG_ON(!valid_dma_direction(direction));
 }
 
-static int ipath_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents,
-			enum dma_data_direction direction)
+static int ipath_map_sg(struct ib_device *dev, struct scatterlist *sgl,
+			int nents, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	u64 addr;
 	int i;
 	int ret = nents;
 
 	BUG_ON(!valid_dma_direction(direction));
 
-	for (i = 0; i < nents; i++) {
-		addr = (u64) page_address(sg[i].page);
+	for_each_sg(sgl, sg, nents, i) {
+		addr = (u64) page_address(sg->page);
 		/* TODO: handle highmem pages */
 		if (!addr) {
 			ret = 0;
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index e05690e..f3529b6 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -124,17 +124,19 @@ static int iser_start_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask,
 
 	if (cmd_dir == ISER_DIR_OUT) {
 		/* copy the unaligned sg the buffer which is used for RDMA */
-		struct scatterlist *sg = (struct scatterlist *)data->buf;
+		struct scatterlist *sgl = (struct scatterlist *)data->buf;
+		struct scatterlist *sg;
 		int i;
 		char *p, *from;
 
-		for (p = mem, i = 0; i < data->size; i++) {
-			from = kmap_atomic(sg[i].page, KM_USER0);
+		p = mem;
+		for_each_sg(sgl, sg, data->size, i) {
+			from = kmap_atomic(sg->page, KM_USER0);
 			memcpy(p,
-			       from + sg[i].offset,
-			       sg[i].length);
+			       from + sg->offset,
+			       sg->length);
 			kunmap_atomic(from, KM_USER0);
-			p += sg[i].length;
+			p += sg->length;
 		}
 	}
 
@@ -176,7 +178,7 @@ void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask,
 
 	if (cmd_dir == ISER_DIR_IN) {
 		char *mem;
-		struct scatterlist *sg;
+		struct scatterlist *sgl, *sg;
 		unsigned char *p, *to;
 		unsigned int sg_size;
 		int i;
@@ -184,16 +186,17 @@ void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask,
 		/* copy back read RDMA to unaligned sg */
 		mem	= mem_copy->copy_buf;
 
-		sg	= (struct scatterlist *)iser_ctask->data[ISER_DIR_IN].buf;
+		sgl	= (struct scatterlist *)iser_ctask->data[ISER_DIR_IN].buf;
 		sg_size = iser_ctask->data[ISER_DIR_IN].size;
 
-		for (p = mem, i = 0; i < sg_size; i++){
-			to = kmap_atomic(sg[i].page, KM_SOFTIRQ0);
-			memcpy(to + sg[i].offset,
+		p = mem;
+		for_each_sg(sgl, sg, sg_size, i) {
+			to = kmap_atomic(sg->page, KM_SOFTIRQ0);
+			memcpy(to + sg->offset,
 			       p,
-			       sg[i].length);
+			       sg->length);
 			kunmap_atomic(to, KM_SOFTIRQ0);
-			p += sg[i].length;
+			p += sg->length;
 		}
 	}
 
@@ -224,7 +227,8 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data,
 			       struct iser_page_vec *page_vec,
 			       struct ib_device *ibdev)
 {
-	struct scatterlist *sg = (struct scatterlist *)data->buf;
+	struct scatterlist *sgl = (struct scatterlist *)data->buf;
+	struct scatterlist *sg;
 	u64 first_addr, last_addr, page;
 	int end_aligned;
 	unsigned int cur_page = 0;
@@ -232,24 +236,25 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data,
 	int i;
 
 	/* compute the offset of first element */
-	page_vec->offset = (u64) sg[0].offset & ~MASK_4K;
+	page_vec->offset = (u64) sgl[0].offset & ~MASK_4K;
 
-	for (i = 0; i < data->dma_nents; i++) {
-		unsigned int dma_len = ib_sg_dma_len(ibdev, &sg[i]);
+	for_each_sg(sgl, sg, data->dma_nents, i) {
+		unsigned int dma_len = ib_sg_dma_len(ibdev, sg);
 
 		total_sz += dma_len;
 
-		first_addr = ib_sg_dma_address(ibdev, &sg[i]);
+		first_addr = ib_sg_dma_address(ibdev, sg);
 		last_addr  = first_addr + dma_len;
 
 		end_aligned   = !(last_addr  & ~MASK_4K);
 
 		/* continue to collect page fragments till aligned or SG ends */
 		while (!end_aligned && (i + 1 < data->dma_nents)) {
+			sg = sg_next(sg);
 			i++;
-			dma_len = ib_sg_dma_len(ibdev, &sg[i]);
+			dma_len = ib_sg_dma_len(ibdev, sg);
 			total_sz += dma_len;
-			last_addr = ib_sg_dma_address(ibdev, &sg[i]) + dma_len;
+			last_addr = ib_sg_dma_address(ibdev, sg) + dma_len;
 			end_aligned = !(last_addr  & ~MASK_4K);
 		}
 
@@ -284,25 +289,26 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data,
 static unsigned int iser_data_buf_aligned_len(struct iser_data_buf *data,
 					      struct ib_device *ibdev)
 {
-	struct scatterlist *sg;
+	struct scatterlist *sgl, *sg;
 	u64 end_addr, next_addr;
 	int i, cnt;
 	unsigned int ret_len = 0;
 
-	sg = (struct scatterlist *)data->buf;
+	sgl = (struct scatterlist *)data->buf;
 
-	for (cnt = 0, i = 0; i < data->dma_nents; i++, cnt++) {
+	cnt = 0;
+	for_each_sg(sgl, sg, data->dma_nents, i) {
 		/* iser_dbg("Checking sg iobuf [%d]: phys=0x%08lX "
 		   "offset: %ld sz: %ld\n", i,
-		   (unsigned long)page_to_phys(sg[i].page),
-		   (unsigned long)sg[i].offset,
-		   (unsigned long)sg[i].length); */
-		end_addr = ib_sg_dma_address(ibdev, &sg[i]) +
-			   ib_sg_dma_len(ibdev, &sg[i]);
+		   (unsigned long)page_to_phys(sg->page),
+		   (unsigned long)sg->offset,
+		   (unsigned long)sg->length); */
+		end_addr = ib_sg_dma_address(ibdev, sg) +
+			   ib_sg_dma_len(ibdev, sg);
 		/* iser_dbg("Checking sg iobuf end address "
 		       "0x%08lX\n", end_addr); */
 		if (i + 1 < data->dma_nents) {
-			next_addr = ib_sg_dma_address(ibdev, &sg[i+1]);
+			next_addr = ib_sg_dma_address(ibdev, sg_next(sg));
 			/* are i, i+1 fragments of the same page? */
 			if (end_addr == next_addr)
 				continue;
@@ -322,15 +328,16 @@ static unsigned int iser_data_buf_aligned_len(struct iser_data_buf *data,
 static void iser_data_buf_dump(struct iser_data_buf *data,
 			       struct ib_device *ibdev)
 {
-	struct scatterlist *sg = (struct scatterlist *)data->buf;
+	struct scatterlist *sgl = (struct scatterlist *)data->buf;
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < data->dma_nents; i++)
+	for_each_sg(sgl, sg, data->dma_nents, i)
 		iser_err("sg[%d] dma_addr:0x%lX page:0x%p "
 			 "off:0x%x sz:0x%x dma_len:0x%x\n",
-			 i, (unsigned long)ib_sg_dma_address(ibdev, &sg[i]),
-			 sg[i].page, sg[i].offset,
-			 sg[i].length, ib_sg_dma_len(ibdev, &sg[i]));
+			 i, (unsigned long)ib_sg_dma_address(ibdev, sg),
+			 sg->page, sg->offset,
+			 sg->length, ib_sg_dma_len(ibdev, sg));
 }
 
 static void iser_dump_page_vec(struct iser_page_vec *page_vec)
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index bdff950..3918ebf 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -293,7 +293,7 @@ nextSGEset:
 	for (ii=0; ii < (numSgeThisFrame-1); ii++) {
 		thisxfer = sg_dma_len(sg);
 		if (thisxfer == 0) {
-			sg ++; /* Get next SG element from the OS */
+			sg = sg_next(sg); /* Get next SG element from the OS */
 			sg_done++;
 			continue;
 		}
@@ -301,7 +301,7 @@ nextSGEset:
 		v2 = sg_dma_address(sg);
 		mptscsih_add_sge(psge, sgflags | thisxfer, v2);
 
-		sg++;		/* Get next SG element from the OS */
+		sg = sg_next(sg);	/* Get next SG element from the OS */
 		psge += (sizeof(u32) + sizeof(dma_addr_t));
 		sgeOffset += (sizeof(u32) + sizeof(dma_addr_t));
 		sg_done++;
@@ -322,7 +322,7 @@ nextSGEset:
 		v2 = sg_dma_address(sg);
 		mptscsih_add_sge(psge, sgflags | thisxfer, v2);
 		/*
-		sg++;
+		sg = sg_next(sg);
 		psge += (sizeof(u32) + sizeof(dma_addr_t));
 		*/
 		sgeOffset += (sizeof(u32) + sizeof(dma_addr_t));
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index b0abc7d..a5d0354 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -153,14 +153,14 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock
 			blk_queue_max_hw_segments(mq->queue, bouncesz / 512);
 			blk_queue_max_segment_size(mq->queue, bouncesz);
 
-			mq->sg = kmalloc(sizeof(struct scatterlist),
+			mq->sg = kzalloc(sizeof(struct scatterlist),
 				GFP_KERNEL);
 			if (!mq->sg) {
 				ret = -ENOMEM;
 				goto cleanup_queue;
 			}
 
-			mq->bounce_sg = kmalloc(sizeof(struct scatterlist) *
+			mq->bounce_sg = kzalloc(sizeof(struct scatterlist) *
 				bouncesz / 512, GFP_KERNEL);
 			if (!mq->bounce_sg) {
 				ret = -ENOMEM;
@@ -177,7 +177,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock
 		blk_queue_max_hw_segments(mq->queue, host->max_hw_segs);
 		blk_queue_max_segment_size(mq->queue, host->max_seg_size);
 
-		mq->sg = kmalloc(sizeof(struct scatterlist) *
+		mq->sg = kzalloc(sizeof(struct scatterlist) *
 			host->max_phys_segs, GFP_KERNEL);
 		if (!mq->sg) {
 			ret = -ENOMEM;
diff --git a/drivers/s390/scsi/zfcp_def.h b/drivers/s390/scsi/zfcp_def.h
index 16e5563..57cac70 100644
--- a/drivers/s390/scsi/zfcp_def.h
+++ b/drivers/s390/scsi/zfcp_def.h
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/mempool.h>
 #include <linux/syscalls.h>
+#include <linux/scatterlist.h>
 #include <linux/ioctl.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c
index 3f105fd..51d92b1 100644
--- a/drivers/s390/scsi/zfcp_qdio.c
+++ b/drivers/s390/scsi/zfcp_qdio.c
@@ -590,7 +590,7 @@ zfcp_qdio_sbals_from_segment(struct zfcp_fsf_req *fsf_req, unsigned long sbtype,
  */
 int
 zfcp_qdio_sbals_from_sg(struct zfcp_fsf_req *fsf_req, unsigned long sbtype,
-                        struct scatterlist *sg,	int sg_count, int max_sbals)
+                        struct scatterlist *sgl, int sg_count, int max_sbals)
 {
 	int sg_index;
 	struct scatterlist *sg_segment;
@@ -606,9 +606,7 @@ zfcp_qdio_sbals_from_sg(struct zfcp_fsf_req *fsf_req, unsigned long sbtype,
 	sbale->flags |= sbtype;
 
 	/* process all segements of scatter-gather list */
-	for (sg_index = 0, sg_segment = sg, bytes = 0;
-	     sg_index < sg_count;
-	     sg_index++, sg_segment++) {
+	for_each_sg(sgl, sg_segment, sg_count, sg_index) {
 		retval = zfcp_qdio_sbals_from_segment(
 				fsf_req,
 				sbtype,
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index efd9d8d..fb14014 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 c7995fc..a64153b 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 9b20617..49e1ffa 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 eda8c48..3168a17 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 f608d4a..d3a6d15 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 a7f42a1..038980b 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/aha1542.c b/drivers/scsi/aha1542.c
index cbbfbc9..961a188 100644
--- a/drivers/scsi/aha1542.c
+++ b/drivers/scsi/aha1542.c
@@ -61,15 +61,15 @@ static void BAD_DMA(void *address, unsigned int length)
 }
 
 static void BAD_SG_DMA(Scsi_Cmnd * SCpnt,
-		       struct scatterlist *sgpnt,
+		       struct scatterlist *sgp,
 		       int nseg,
 		       int badseg)
 {
 	printk(KERN_CRIT "sgpnt[%d:%d] page %p/0x%llx length %u\n",
 	       badseg, nseg,
-	       page_address(sgpnt[badseg].page) + sgpnt[badseg].offset,
-	       (unsigned long long)SCSI_SG_PA(&sgpnt[badseg]),
-	       sgpnt[badseg].length);
+	       page_address(sgp->page) + sgp->offset,
+	       (unsigned long long)SCSI_SG_PA(sgp),
+	       sgp->length);
 
 	/*
 	 * Not safe to continue.
@@ -691,7 +691,7 @@ static int aha1542_queuecommand(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
 	memcpy(ccb[mbo].cdb, cmd, ccb[mbo].cdblen);
 
 	if (SCpnt->use_sg) {
-		struct scatterlist *sgpnt;
+		struct scatterlist *sg;
 		struct chain *cptr;
 #ifdef DEBUG
 		unsigned char *ptr;
@@ -699,23 +699,21 @@ static int aha1542_queuecommand(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
 		int i;
 		ccb[mbo].op = 2;	/* SCSI Initiator Command  w/scatter-gather */
 		SCpnt->host_scribble = kmalloc(512, GFP_KERNEL | GFP_DMA);
-		sgpnt = (struct scatterlist *) SCpnt->request_buffer;
 		cptr = (struct chain *) SCpnt->host_scribble;
 		if (cptr == NULL) {
 			/* free the claimed mailbox slot */
 			HOSTDATA(SCpnt->device->host)->SCint[mbo] = NULL;
 			return SCSI_MLQUEUE_HOST_BUSY;
 		}
-		for (i = 0; i < SCpnt->use_sg; i++) {
-			if (sgpnt[i].length == 0 || SCpnt->use_sg > 16 ||
-			    (((int) sgpnt[i].offset) & 1) || (sgpnt[i].length & 1)) {
+		scsi_for_each_sg(SCpnt, sg, SCpnt->use_sg, i) {
+			if (sg->length == 0 || SCpnt->use_sg > 16 ||
+			    (((int) sg->offset) & 1) || (sg->length & 1)) {
 				unsigned char *ptr;
 				printk(KERN_CRIT "Bad segment list supplied to aha1542.c (%d, %d)\n", SCpnt->use_sg, i);
-				for (i = 0; i < SCpnt->use_sg; i++) {
+				scsi_for_each_sg(SCpnt, sg, SCpnt->use_sg, i) {
 					printk(KERN_CRIT "%d: %p %d\n", i,
-					       (page_address(sgpnt[i].page) +
-						sgpnt[i].offset),
-					       sgpnt[i].length);
+					       (page_address(sg->page) +
+						sg->offset), sg->length);
 				};
 				printk(KERN_CRIT "cptr %x: ", (unsigned int) cptr);
 				ptr = (unsigned char *) &cptr[i];
@@ -723,10 +721,10 @@ static int aha1542_queuecommand(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
 					printk("%02x ", ptr[i]);
 				panic("Foooooooood fight!");
 			};
-			any2scsi(cptr[i].dataptr, SCSI_SG_PA(&sgpnt[i]));
-			if (SCSI_SG_PA(&sgpnt[i]) + sgpnt[i].length - 1 > ISA_DMA_THRESHOLD)
-				BAD_SG_DMA(SCpnt, sgpnt, SCpnt->use_sg, i);
-			any2scsi(cptr[i].datalen, sgpnt[i].length);
+			any2scsi(cptr[i].dataptr, SCSI_SG_PA(sg));
+			if (SCSI_SG_PA(sg) + sg->length - 1 > ISA_DMA_THRESHOLD)
+				BAD_SG_DMA(SCpnt, sg, SCpnt->use_sg, i);
+			any2scsi(cptr[i].datalen, sg->length);
 		};
 		any2scsi(ccb[mbo].datalen, SCpnt->use_sg * sizeof(struct chain));
 		any2scsi(ccb[mbo].dataptr, SCSI_BUF_PA(cptr));
diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
index e4a4f3a..f6722fd 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 a055a96..42c0f14 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 2e9c38f..7770bef 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 1a71b02..4025608 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/aic94xx/aic94xx_task.c b/drivers/scsi/aic94xx/aic94xx_task.c
index f2b23e0..ee0a98b 100644
--- a/drivers/scsi/aic94xx/aic94xx_task.c
+++ b/drivers/scsi/aic94xx/aic94xx_task.c
@@ -94,7 +94,7 @@ static inline int asd_map_scatterlist(struct sas_task *task,
 			res = -ENOMEM;
 			goto err_unmap;
 		}
-		for (sc = task->scatter, i = 0; i < num_sg; i++, sc++) {
+		for_each_sg(task->scatter, sc, num_sg, i) {
 			struct sg_el *sg =
 				&((struct sg_el *)ascb->sg_arr->vaddr)[i];
 			sg->bus_addr = cpu_to_le64((u64)sg_dma_address(sc));
@@ -103,7 +103,7 @@ static inline int asd_map_scatterlist(struct sas_task *task,
 				sg->flags |= ASD_SG_EL_LIST_EOL;
 		}
 
-		for (sc = task->scatter, i = 0; i < 2; i++, sc++) {
+		for_each_sg(task->scatter, sc, 2, i) {
 			sg_arr[i].bus_addr =
 				cpu_to_le64((u64)sg_dma_address(sc));
 			sg_arr[i].size = cpu_to_le32((u32)sg_dma_len(sc));
@@ -115,7 +115,7 @@ static inline int asd_map_scatterlist(struct sas_task *task,
 		sg_arr[2].bus_addr=cpu_to_le64((u64)ascb->sg_arr->dma_handle);
 	} else {
 		int i;
-		for (sc = task->scatter, i = 0; i < num_sg; i++, sc++) {
+		for_each_sg(task->scatter, sc, num_sg, i) {
 			sg_arr[i].bus_addr =
 				cpu_to_le64((u64)sg_dma_address(sc));
 			sg_arr[i].size = cpu_to_le32((u32)sg_dma_len(sc));
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index cfcf401..f817775 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 1591824..fd42d47 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 bea9d65..8258506 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 ec22331..7ead521 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 adc9559..112ab6a 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 8b384fa..8515054 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 1a924e9..714e627 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 cda0cc3..22d91ee 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/ide-scsi.c b/drivers/scsi/ide-scsi.c
index d81bb076..d297f64 100644
--- a/drivers/scsi/ide-scsi.c
+++ b/drivers/scsi/ide-scsi.c
@@ -70,6 +70,7 @@ typedef struct idescsi_pc_s {
 	u8 *buffer;				/* Data buffer */
 	u8 *current_position;			/* Pointer into the above buffer */
 	struct scatterlist *sg;			/* Scatter gather table */
+	struct scatterlist *last_sg;		/* Last sg element */
 	int b_count;				/* Bytes transferred from current entry */
 	struct scsi_cmnd *scsi_cmd;		/* SCSI command */
 	void (*done)(struct scsi_cmnd *);	/* Scsi completion routine */
@@ -173,12 +174,6 @@ static void idescsi_input_buffers (ide_drive_t *drive, idescsi_pc_t *pc, unsigne
 	char *buf;
 
 	while (bcount) {
-		if (pc->sg - scsi_sglist(pc->scsi_cmd) >
-		                                 scsi_sg_count(pc->scsi_cmd)) {
-			printk (KERN_ERR "ide-scsi: scatter gather table too small, discarding data\n");
-			idescsi_discard_data (drive, bcount);
-			return;
-		}
 		count = min(pc->sg->length - pc->b_count, bcount);
 		if (PageHighMem(pc->sg->page)) {
 			unsigned long flags;
@@ -197,10 +192,17 @@ static void idescsi_input_buffers (ide_drive_t *drive, idescsi_pc_t *pc, unsigne
 		}
 		bcount -= count; pc->b_count += count;
 		if (pc->b_count == pc->sg->length) {
-			pc->sg++;
+			if (pc->sg == pc->last_sg)
+				break;
+			pc->sg = sg_next(pc->sg);
 			pc->b_count = 0;
 		}
 	}
+
+	if (bcount) {
+		printk (KERN_ERR "ide-scsi: scatter gather table too small, discarding data\n");
+		idescsi_discard_data (drive, bcount);
+	}
 }
 
 static void idescsi_output_buffers (ide_drive_t *drive, idescsi_pc_t *pc, unsigned int bcount)
@@ -209,12 +211,6 @@ static void idescsi_output_buffers (ide_drive_t *drive, idescsi_pc_t *pc, unsign
 	char *buf;
 
 	while (bcount) {
-		if (pc->sg - scsi_sglist(pc->scsi_cmd) >
-		                                 scsi_sg_count(pc->scsi_cmd)) {
-			printk (KERN_ERR "ide-scsi: scatter gather table too small, padding with zeros\n");
-			idescsi_output_zeros (drive, bcount);
-			return;
-		}
 		count = min(pc->sg->length - pc->b_count, bcount);
 		if (PageHighMem(pc->sg->page)) {
 			unsigned long flags;
@@ -233,10 +229,17 @@ static void idescsi_output_buffers (ide_drive_t *drive, idescsi_pc_t *pc, unsign
 		}
 		bcount -= count; pc->b_count += count;
 		if (pc->b_count == pc->sg->length) {
-			pc->sg++;
+			if (pc->sg == pc->last_sg)
+				break;
+			pc->sg = sg_next(pc->sg);
 			pc->b_count = 0;
 		}
 	}
+
+	if (bcount) {
+		printk (KERN_ERR "ide-scsi: scatter gather table too small, padding with zeros\n");
+		idescsi_output_zeros (drive, bcount);
+	}
 }
 
 static void hexdump(u8 *x, int len)
@@ -804,6 +807,7 @@ static int idescsi_queue (struct scsi_cmnd *cmd,
 	memcpy (pc->c, cmd->cmnd, cmd->cmd_len);
 	pc->buffer = NULL;
 	pc->sg = scsi_sglist(cmd);
+	pc->last_sg = sg_last(pc->sg, cmd->use_sg);
 	pc->b_count = 0;
 	pc->request_transfer = pc->buffer_size = scsi_bufflen(cmd);
 	pc->scsi_cmd = cmd;
diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c
index d9dfb69..22d40fd 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/ips.c b/drivers/scsi/ips.c
index 2ed099e..edaac27 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -3252,7 +3252,7 @@ ips_done(ips_ha_t * ha, ips_scb_t * scb)
 		 */
 		if ((scb->breakup) || (scb->sg_break)) {
                         struct scatterlist *sg;
-                        int sg_dma_index, ips_sg_index = 0;
+                        int i, sg_dma_index, ips_sg_index = 0;
 
 			/* we had a data breakup */
 			scb->data_len = 0;
@@ -3261,20 +3261,22 @@ ips_done(ips_ha_t * ha, ips_scb_t * scb)
 
                         /* Spin forward to last dma chunk */
                         sg_dma_index = scb->breakup;
+                        for (i = 0; i < scb->breakup; i++)
+                                sg = sg_next(sg);
 
 			/* Take care of possible partial on last chunk */
                         ips_fill_scb_sg_single(ha,
-                                               sg_dma_address(&sg[sg_dma_index]),
+                                               sg_dma_address(sg),
                                                scb, ips_sg_index++,
-                                               sg_dma_len(&sg[sg_dma_index]));
+                                               sg_dma_len(sg));
 
                         for (; sg_dma_index < scsi_sg_count(scb->scsi_cmd);
-                             sg_dma_index++) {
+                             sg_dma_index++, sg = sg_next(sg)) {
                                 if (ips_fill_scb_sg_single
                                     (ha,
-                                     sg_dma_address(&sg[sg_dma_index]),
+                                     sg_dma_address(sg),
                                      scb, ips_sg_index++,
-                                     sg_dma_len(&sg[sg_dma_index])) < 0)
+                                     sg_dma_len(sg)) < 0)
                                         break;
                         }
 
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index cd67493..c075556 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 b12ad7c7..a035001 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 e7e11f2..10d1aff 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 c6a53dc..e4e4c6a 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 ebb948c..e3c5c52 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 651d09b..7470ff3 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 7fed353..28161dc 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 961839e..190e2a7 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/qla1280.c b/drivers/scsi/qla1280.c
index fba8aa8..76089cf 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -2775,7 +2775,7 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	struct device_reg __iomem *reg = ha->iobase;
 	struct scsi_cmnd *cmd = sp->cmd;
 	cmd_a64_entry_t *pkt;
-	struct scatterlist *sg = NULL;
+	struct scatterlist *sg = NULL, *s;
 	__le32 *dword_ptr;
 	dma_addr_t dma_handle;
 	int status = 0;
@@ -2889,13 +2889,16 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	 * Load data segments.
 	 */
 	if (seg_cnt) {	/* If data transfer. */
+		int remseg = seg_cnt;
 		/* Setup packet address segment pointer. */
 		dword_ptr = (u32 *)&pkt->dseg_0_address;
 
 		if (cmd->use_sg) {	/* If scatter gather */
 			/* Load command entry data segments. */
-			for (cnt = 0; cnt < 2 && seg_cnt; cnt++, seg_cnt--) {
-				dma_handle = sg_dma_address(sg);
+			for_each_sg(sg, s, seg_cnt, cnt) {
+				if (cnt == 2)
+					break;
+				dma_handle = sg_dma_address(s);
 #if defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_SGI_SN2)
 				if (ha->flags.use_pci_vchannel)
 					sn_pci_set_vchan(ha->pdev,
@@ -2906,12 +2909,12 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 					cpu_to_le32(pci_dma_lo32(dma_handle));
 				*dword_ptr++ =
 					cpu_to_le32(pci_dma_hi32(dma_handle));
-				*dword_ptr++ = cpu_to_le32(sg_dma_len(sg));
-				sg++;
+				*dword_ptr++ = cpu_to_le32(sg_dma_len(s));
 				dprintk(3, "S/G Segment phys_addr=%x %x, len=0x%x\n",
 					cpu_to_le32(pci_dma_hi32(dma_handle)),
 					cpu_to_le32(pci_dma_lo32(dma_handle)),
-					cpu_to_le32(sg_dma_len(sg)));
+					cpu_to_le32(sg_dma_len(sg_next(s))));
+				remseg--;
 			}
 			dprintk(5, "qla1280_64bit_start_scsi: Scatter/gather "
 				"command packet data - b %i, t %i, l %i \n",
@@ -2926,7 +2929,9 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 			dprintk(3, "S/G Building Continuation...seg_cnt=0x%x "
 				"remains\n", seg_cnt);
 
-			while (seg_cnt > 0) {
+			while (remseg > 0) {
+				/* Update sg start */
+				sg = s;
 				/* Adjust ring index. */
 				ha->req_ring_index++;
 				if (ha->req_ring_index == REQUEST_ENTRY_CNT) {
@@ -2952,9 +2957,10 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 					(u32 *)&((struct cont_a64_entry *) pkt)->dseg_0_address;
 
 				/* Load continuation entry data segments. */
-				for (cnt = 0; cnt < 5 && seg_cnt;
-				     cnt++, seg_cnt--) {
-					dma_handle = sg_dma_address(sg);
+				for_each_sg(sg, s, remseg, cnt) {
+					if (cnt == 5)
+						break;
+					dma_handle = sg_dma_address(s);
 #if defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_SGI_SN2)
 				if (ha->flags.use_pci_vchannel)
 					sn_pci_set_vchan(ha->pdev, 
@@ -2966,13 +2972,13 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 					*dword_ptr++ =
 						cpu_to_le32(pci_dma_hi32(dma_handle));
 					*dword_ptr++ =
-						cpu_to_le32(sg_dma_len(sg));
+						cpu_to_le32(sg_dma_len(s));
 					dprintk(3, "S/G Segment Cont. phys_addr=%x %x, len=0x%x\n",
 						cpu_to_le32(pci_dma_hi32(dma_handle)),
 						cpu_to_le32(pci_dma_lo32(dma_handle)),
-						cpu_to_le32(sg_dma_len(sg)));
-					sg++;
+						cpu_to_le32(sg_dma_len(s)));
 				}
+				remseg -= cnt;
 				dprintk(5, "qla1280_64bit_start_scsi: "
 					"continuation packet data - b %i, t "
 					"%i, l %i \n", SCSI_BUS_32(cmd),
@@ -3062,7 +3068,7 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	struct device_reg __iomem *reg = ha->iobase;
 	struct scsi_cmnd *cmd = sp->cmd;
 	struct cmd_entry *pkt;
-	struct scatterlist *sg = NULL;
+	struct scatterlist *sg = NULL, *s;
 	__le32 *dword_ptr;
 	int status = 0;
 	int cnt;
@@ -3188,6 +3194,7 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	 * Load data segments.
 	 */
 	if (seg_cnt) {
+		int remseg = seg_cnt;
 		/* Setup packet address segment pointer. */
 		dword_ptr = &pkt->dseg_0_address;
 
@@ -3196,22 +3203,25 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 			qla1280_dump_buffer(1, (char *)sg, 4 * 16);
 
 			/* Load command entry data segments. */
-			for (cnt = 0; cnt < 4 && seg_cnt; cnt++, seg_cnt--) {
+			for_each_sg(sg, s, seg_cnt, cnt) {
+				if (cnt == 4)
+					break;
 				*dword_ptr++ =
-					cpu_to_le32(pci_dma_lo32(sg_dma_address(sg)));
-				*dword_ptr++ =
-					cpu_to_le32(sg_dma_len(sg));
+					cpu_to_le32(pci_dma_lo32(sg_dma_address(s)));
+				*dword_ptr++ = cpu_to_le32(sg_dma_len(s));
 				dprintk(3, "S/G Segment phys_addr=0x%lx, len=0x%x\n",
-					(pci_dma_lo32(sg_dma_address(sg))),
-					(sg_dma_len(sg)));
-				sg++;
+					(pci_dma_lo32(sg_dma_address(s))),
+					(sg_dma_len(s)));
+				remseg--;
 			}
 			/*
 			 * Build continuation packets.
 			 */
 			dprintk(3, "S/G Building Continuation"
 				"...seg_cnt=0x%x remains\n", seg_cnt);
-			while (seg_cnt > 0) {
+			while (remseg > 0) {
+				/* Continue from end point */
+				sg = s;
 				/* Adjust ring index. */
 				ha->req_ring_index++;
 				if (ha->req_ring_index == REQUEST_ENTRY_CNT) {
@@ -3239,19 +3249,20 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 					&((struct cont_entry *) pkt)->dseg_0_address;
 
 				/* Load continuation entry data segments. */
-				for (cnt = 0; cnt < 7 && seg_cnt;
-				     cnt++, seg_cnt--) {
+				for_each_sg(sg, s, remseg, cnt) {
+					if (cnt == 7)
+						break;
 					*dword_ptr++ =
-						cpu_to_le32(pci_dma_lo32(sg_dma_address(sg)));
+						cpu_to_le32(pci_dma_lo32(sg_dma_address(s)));
 					*dword_ptr++ =
-						cpu_to_le32(sg_dma_len(sg));
+						cpu_to_le32(sg_dma_len(s));
 					dprintk(1,
 						"S/G Segment Cont. phys_addr=0x%x, "
 						"len=0x%x\n",
-						cpu_to_le32(pci_dma_lo32(sg_dma_address(sg))),
-						cpu_to_le32(sg_dma_len(sg)));
-					sg++;
+						cpu_to_le32(pci_dma_lo32(sg_dma_address(s))),
+						cpu_to_le32(sg_dma_len(s)));
 				}
+				remseg -= cnt;
 				dprintk(5, "qla1280_32bit_start_scsi: "
 					"continuation packet data - "
 					"scsi(%i:%i:%i)\n", SCSI_BUS_32(cmd),
@@ -4248,6 +4259,7 @@ static struct scsi_host_template qla1280_driver_template = {
 	.sg_tablesize		= SG_ALL,
 	.cmd_per_lun		= 1,
 	.use_clustering		= ENABLE_CLUSTERING,
+	.use_sg_chaining	= ENABLE_SG_CHAINING,
 };
 
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index a6bb8d0..0351d38 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 b1d565c..03b68d4 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 1e874f1..1769f96 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/qlogicpti.c b/drivers/scsi/qlogicpti.c
index e93f803..7a2e798 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -868,7 +868,7 @@ static inline int load_cmd(struct scsi_cmnd *Cmnd, struct Command_Entry *cmd,
 			   struct qlogicpti *qpti, u_int in_ptr, u_int out_ptr)
 {
 	struct dataseg *ds;
-	struct scatterlist *sg;
+	struct scatterlist *sg, *s;
 	int i, n;
 
 	if (Cmnd->use_sg) {
@@ -884,11 +884,12 @@ static inline int load_cmd(struct scsi_cmnd *Cmnd, struct Command_Entry *cmd,
 		n = sg_count;
 		if (n > 4)
 			n = 4;
-		for (i = 0; i < n; i++, sg++) {
-			ds[i].d_base = sg_dma_address(sg);
-			ds[i].d_count = sg_dma_len(sg);
+		for_each_sg(sg, s, n, i) {
+			ds[i].d_base = sg_dma_address(s);
+			ds[i].d_count = sg_dma_len(s);
 		}
 		sg_count -= 4;
+		sg = s;
 		while (sg_count > 0) {
 			struct Continuation_Entry *cont;
 
@@ -907,9 +908,9 @@ static inline int load_cmd(struct scsi_cmnd *Cmnd, struct Command_Entry *cmd,
 			n = sg_count;
 			if (n > 7)
 				n = 7;
-			for (i = 0; i < n; i++, sg++) {
-				ds[i].d_base = sg_dma_address(sg);
-				ds[i].d_count = sg_dma_len(sg);
+			for_each_sg(sg, s, n, i) {
+				ds[i].d_base = sg_dma_address(s);
+				ds[i].d_count = sg_dma_len(s);
 			}
 			sg_count -= n;
 		}
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 4947dfe..72ee4c9 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -38,6 +38,7 @@
 #include <linux/proc_fs.h>
 #include <linux/vmalloc.h>
 #include <linux/moduleparam.h>
+#include <linux/scatterlist.h>
 
 #include <linux/blkdev.h>
 #include "scsi.h"
@@ -600,7 +601,7 @@ static int fill_from_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr,
 	int k, req_len, act_len, len, active;
 	void * kaddr;
 	void * kaddr_off;
-	struct scatterlist * sgpnt;
+	struct scatterlist * sg;
 
 	if (0 == scp->request_bufflen)
 		return 0;
@@ -619,16 +620,16 @@ static int fill_from_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr,
 			scp->resid = req_len - act_len;
 		return 0;
 	}
-	sgpnt = (struct scatterlist *)scp->request_buffer;
 	active = 1;
-	for (k = 0, req_len = 0, act_len = 0; k < scp->use_sg; ++k, ++sgpnt) {
+	req_len = act_len = 0;
+	scsi_for_each_sg(scp, sg, scp->use_sg, k) {
 		if (active) {
 			kaddr = (unsigned char *)
-				kmap_atomic(sgpnt->page, KM_USER0);
+				kmap_atomic(sg->page, KM_USER0);
 			if (NULL == kaddr)
 				return (DID_ERROR << 16);
-			kaddr_off = (unsigned char *)kaddr + sgpnt->offset;
-			len = sgpnt->length;
+			kaddr_off = (unsigned char *)kaddr + sg->offset;
+			len = sg->length;
 			if ((req_len + len) > arr_len) {
 				active = 0;
 				len = arr_len - req_len;
@@ -637,7 +638,7 @@ static int fill_from_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr,
 			kunmap_atomic(kaddr, KM_USER0);
 			act_len += len;
 		}
-		req_len += sgpnt->length;
+		req_len += sg->length;
 	}
 	if (scp->resid)
 		scp->resid -= act_len;
@@ -653,7 +654,7 @@ static int fetch_to_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr,
 	int k, req_len, len, fin;
 	void * kaddr;
 	void * kaddr_off;
-	struct scatterlist * sgpnt;
+	struct scatterlist * sg;
 
 	if (0 == scp->request_bufflen)
 		return 0;
@@ -668,13 +669,14 @@ static int fetch_to_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr,
 		memcpy(arr, scp->request_buffer, len);
 		return len;
 	}
-	sgpnt = (struct scatterlist *)scp->request_buffer;
-	for (k = 0, req_len = 0, fin = 0; k < scp->use_sg; ++k, ++sgpnt) {
-		kaddr = (unsigned char *)kmap_atomic(sgpnt->page, KM_USER0);
+	sg = scsi_sglist(scp);
+	req_len = fin = 0;
+	for (k = 0; k < scp->use_sg; ++k, sg = sg_next(sg)) {
+		kaddr = (unsigned char *)kmap_atomic(sg->page, KM_USER0);
 		if (NULL == kaddr)
 			return -1;
-		kaddr_off = (unsigned char *)kaddr + sgpnt->offset;
-		len = sgpnt->length;
+		kaddr_off = (unsigned char *)kaddr + sg->offset;
+		len = sg->length;
 		if ((req_len + len) > max_arr_len) {
 			len = max_arr_len - req_len;
 			fin = 1;
@@ -683,7 +685,7 @@ static int fetch_to_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr,
 		kunmap_atomic(kaddr, KM_USER0);
 		if (fin)
 			return req_len + len;
-		req_len += sgpnt->length;
+		req_len += sg->length;
 	}
 	return req_len;
 }
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 207f1aa..aac8a02 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -17,6 +17,7 @@
 #include <linux/pci.h>
 #include <linux/delay.h>
 #include <linux/hardirq.h>
+#include <linux/scatterlist.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -33,35 +34,34 @@
 #define SG_MEMPOOL_NR		ARRAY_SIZE(scsi_sg_pools)
 #define SG_MEMPOOL_SIZE		2
 
+/*
+ * 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
+
 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),
+#if (SCSI_MAX_SG_SEGMENTS > 16)
 	SP(32),
-#if (SCSI_MAX_PHYS_SEGMENTS > 32)
+#if (SCSI_MAX_SG_SEGMENTS > 32)
 	SP(64),
-#if (SCSI_MAX_PHYS_SEGMENTS > 64)
+#if (SCSI_MAX_SG_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);
@@ -289,14 +289,16 @@ 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) {
 			/*
@@ -695,56 +697,170 @@ 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;
+/*
+ * 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
 
-	BUG_ON(!cmd->use_sg);
+static inline unsigned int scsi_sgtable_index(unsigned short nents)
+{
+	unsigned int index;
 
-	switch (cmd->use_sg) {
+	switch (nents) {
 	case 1 ... 8:
-		cmd->sglist_len = 0;
+		index = 0;
 		break;
 	case 9 ... 16:
-		cmd->sglist_len = 1;
+		index = 1;
 		break;
+#if (SCSI_MAX_SG_SEGMENTS > 16)
 	case 17 ... 32:
-		cmd->sglist_len = 2;
+		index = 2;
 		break;
-#if (SCSI_MAX_PHYS_SEGMENTS > 32)
+#if (SCSI_MAX_SG_SEGMENTS > 32)
 	case 33 ... 64:
-		cmd->sglist_len = 3;
+		index = 3;
 		break;
-#if (SCSI_MAX_PHYS_SEGMENTS > 64)
+#if (SCSI_MAX_SG_SEGMENTS > 64)
 	case 65 ... 128:
-		cmd->sglist_len = 4;
-		break;
-#if (SCSI_MAX_PHYS_SEGMENTS  > 128)
-	case 129 ... 256:
-		cmd->sglist_len = 5;
+		index = 4;
 		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)
+			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);
 
-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);
+	/*
+	 * 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 + SG_MEMPOOL_NR - 1;
+	} else
+		sgp = scsi_sg_pools + scsi_sgtable_index(cmd->__use_sg);
 
-	sgp = scsi_sg_pools + index;
 	mempool_free(sgl, sgp->pool);
 }
 
@@ -770,7 +886,7 @@ 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
@@ -984,7 +1100,6 @@ 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;
 
 	/*
@@ -997,14 +1112,13 @@ 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
@@ -1529,8 +1643,25 @@ 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
+	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
+
 	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);
@@ -2193,18 +2324,19 @@ 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 +2350,10 @@ 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/drivers/scsi/scsi_tgt_lib.c b/drivers/scsi/scsi_tgt_lib.c
index 66c692f..a91761c 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/drivers/scsi/sg.c b/drivers/scsi/sg.c
index f6f5fc7..7238b2d 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1165,7 +1165,7 @@ sg_vma_nopage(struct vm_area_struct *vma, unsigned long addr, int *type)
 	sg = rsv_schp->buffer;
 	sa = vma->vm_start;
 	for (k = 0; (k < rsv_schp->k_use_sg) && (sa < vma->vm_end);
-	     ++k, ++sg) {
+	     ++k, sg = sg_next(sg)) {
 		len = vma->vm_end - sa;
 		len = (len < sg->length) ? len : sg->length;
 		if (offset < len) {
@@ -1209,7 +1209,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	sa = vma->vm_start;
 	sg = rsv_schp->buffer;
 	for (k = 0; (k < rsv_schp->k_use_sg) && (sa < vma->vm_end);
-	     ++k, ++sg) {
+	     ++k, sg = sg_next(sg)) {
 		len = vma->vm_end - sa;
 		len = (len < sg->length) ? len : sg->length;
 		sa += len;
@@ -1840,7 +1840,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
 	}
 	for (k = 0, sg = schp->buffer, rem_sz = blk_size;
 	     (rem_sz > 0) && (k < mx_sc_elems);
-	     ++k, rem_sz -= ret_sz, ++sg) {
+	     ++k, rem_sz -= ret_sz, sg = sg_next(sg)) {
 		
 		num = (rem_sz > scatter_elem_sz_prev) ?
 		      scatter_elem_sz_prev : rem_sz;
@@ -1913,7 +1913,7 @@ sg_write_xfer(Sg_request * srp)
 		if (res)
 			return res;
 
-		for (; p; ++sg, ksglen = sg->length,
+		for (; p; sg = sg_next(sg), ksglen = sg->length,
 		     p = page_address(sg->page)) {
 			if (usglen <= 0)
 				break;
@@ -1992,7 +1992,7 @@ sg_remove_scat(Sg_scatter_hold * schp)
 			int k;
 
 			for (k = 0; (k < schp->k_use_sg) && sg->page;
-			     ++k, ++sg) {
+			     ++k, sg = sg_next(sg)) {
 				SCSI_LOG_TIMEOUT(5, printk(
 				    "sg_remove_scat: k=%d, pg=0x%p, len=%d\n",
 				    k, sg->page, sg->length));
@@ -2045,7 +2045,7 @@ sg_read_xfer(Sg_request * srp)
 		if (res)
 			return res;
 
-		for (; p; ++sg, ksglen = sg->length,
+		for (; p; sg = sg_next(sg), ksglen = sg->length,
 		     p = page_address(sg->page)) {
 			if (usglen <= 0)
 				break;
@@ -2092,7 +2092,7 @@ sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer)
 	if ((!outp) || (num_read_xfer <= 0))
 		return 0;
 
-	for (k = 0; (k < schp->k_use_sg) && sg->page; ++k, ++sg) {
+	for (k = 0; (k < schp->k_use_sg) && sg->page; ++k, sg = sg_next(sg)) {
 		num = sg->length;
 		if (num > num_read_xfer) {
 			if (__copy_to_user(outp, page_address(sg->page),
@@ -2142,7 +2142,7 @@ sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size)
 	SCSI_LOG_TIMEOUT(4, printk("sg_link_reserve: size=%d\n", size));
 	rem = size;
 
-	for (k = 0; k < rsv_schp->k_use_sg; ++k, ++sg) {
+	for (k = 0; k < rsv_schp->k_use_sg; ++k, sg = sg_next(sg)) {
 		num = sg->length;
 		if (rem <= num) {
 			sfp->save_scat_len = num;
diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c
index 72f6d80..e3fab3a 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 92bfaea..8befab7 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 3db2232..db03c4c8 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 fc9f518..7edd6ce 100644
--- a/drivers/scsi/u14-34f.c
+++ b/drivers/scsi/u14-34f.c
@@ -450,7 +450,8 @@ static struct scsi_host_template driver_template = {
                 .slave_configure         = u14_34f_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/ultrastor.c b/drivers/scsi/ultrastor.c
index c08235d..ea72bbe 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 d6fd425..255c611 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/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c
index 4d3cbb1..8d3711a 100644
--- a/drivers/usb/storage/alauda.c
+++ b/drivers/usb/storage/alauda.c
@@ -798,12 +798,13 @@ static int alauda_read_data(struct us_data *us, unsigned long address,
 {
 	unsigned char *buffer;
 	u16 lba, max_lba;
-	unsigned int page, len, index, offset;
+	unsigned int page, len, offset;
 	unsigned int blockshift = MEDIA_INFO(us).blockshift;
 	unsigned int pageshift = MEDIA_INFO(us).pageshift;
 	unsigned int blocksize = MEDIA_INFO(us).blocksize;
 	unsigned int pagesize = MEDIA_INFO(us).pagesize;
 	unsigned int uzonesize = MEDIA_INFO(us).uzonesize;
+	struct scatterlist *sg;
 	int result;
 
 	/*
@@ -827,7 +828,8 @@ static int alauda_read_data(struct us_data *us, unsigned long address,
 	max_lba = MEDIA_INFO(us).capacity >> (blockshift + pageshift);
 
 	result = USB_STOR_TRANSPORT_GOOD;
-	index = offset = 0;
+	offset = 0;
+	sg = NULL;
 
 	while (sectors > 0) {
 		unsigned int zone = lba / uzonesize; /* integer division */
@@ -873,7 +875,7 @@ static int alauda_read_data(struct us_data *us, unsigned long address,
 
 		/* Store the data in the transfer buffer */
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&index, &offset, TO_XFER_BUF);
+				&sg, &offset, TO_XFER_BUF);
 
 		page = 0;
 		lba++;
@@ -891,11 +893,12 @@ static int alauda_write_data(struct us_data *us, unsigned long address,
 		unsigned int sectors)
 {
 	unsigned char *buffer, *blockbuffer;
-	unsigned int page, len, index, offset;
+	unsigned int page, len, offset;
 	unsigned int blockshift = MEDIA_INFO(us).blockshift;
 	unsigned int pageshift = MEDIA_INFO(us).pageshift;
 	unsigned int blocksize = MEDIA_INFO(us).blocksize;
 	unsigned int pagesize = MEDIA_INFO(us).pagesize;
+	struct scatterlist *sg;
 	u16 lba, max_lba;
 	int result;
 
@@ -929,7 +932,8 @@ static int alauda_write_data(struct us_data *us, unsigned long address,
 	max_lba = MEDIA_INFO(us).capacity >> (pageshift + blockshift);
 
 	result = USB_STOR_TRANSPORT_GOOD;
-	index = offset = 0;
+	offset = 0;
+	sg = NULL;
 
 	while (sectors > 0) {
 		/* Write as many sectors as possible in this block */
@@ -946,7 +950,7 @@ static int alauda_write_data(struct us_data *us, unsigned long address,
 
 		/* Get the data from the transfer buffer */
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&index, &offset, FROM_XFER_BUF);
+				&sg, &offset, FROM_XFER_BUF);
 
 		result = alauda_write_lba(us, lba, page, pages, buffer,
 			blockbuffer);
diff --git a/drivers/usb/storage/datafab.c b/drivers/usb/storage/datafab.c
index c87ad1b..579e9f5 100644
--- a/drivers/usb/storage/datafab.c
+++ b/drivers/usb/storage/datafab.c
@@ -98,7 +98,8 @@ static int datafab_read_data(struct us_data *us,
 	unsigned char  thistime;
 	unsigned int totallen, alloclen;
 	int len, result;
-	unsigned int sg_idx = 0, sg_offset = 0;
+	unsigned int sg_offset = 0;
+	struct scatterlist *sg = NULL;
 
 	// we're working in LBA mode.  according to the ATA spec, 
 	// we can support up to 28-bit addressing.  I don't know if Datafab
@@ -155,7 +156,7 @@ static int datafab_read_data(struct us_data *us,
 
 		// Store the data in the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				 &sg_idx, &sg_offset, TO_XFER_BUF);
+				 &sg, &sg_offset, TO_XFER_BUF);
 
 		sector += thistime;
 		totallen -= len;
@@ -181,7 +182,8 @@ static int datafab_write_data(struct us_data *us,
 	unsigned char thistime;
 	unsigned int totallen, alloclen;
 	int len, result;
-	unsigned int sg_idx = 0, sg_offset = 0;
+	unsigned int sg_offset = 0;
+	struct scatterlist *sg = NULL;
 
 	// we're working in LBA mode.  according to the ATA spec, 
 	// we can support up to 28-bit addressing.  I don't know if Datafab
@@ -217,7 +219,7 @@ static int datafab_write_data(struct us_data *us,
 
 		// Get the data from the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&sg_idx, &sg_offset, FROM_XFER_BUF);
+				&sg, &sg_offset, FROM_XFER_BUF);
 
 		command[0] = 0;
 		command[1] = thistime;
diff --git a/drivers/usb/storage/jumpshot.c b/drivers/usb/storage/jumpshot.c
index 003fcf5..61097cb 100644
--- a/drivers/usb/storage/jumpshot.c
+++ b/drivers/usb/storage/jumpshot.c
@@ -119,7 +119,8 @@ static int jumpshot_read_data(struct us_data *us,
 	unsigned char  thistime;
 	unsigned int totallen, alloclen;
 	int len, result;
-	unsigned int sg_idx = 0, sg_offset = 0;
+	unsigned int sg_offset = 0;
+	struct scatterlist *sg = NULL;
 
 	// we're working in LBA mode.  according to the ATA spec, 
 	// we can support up to 28-bit addressing.  I don't know if Jumpshot
@@ -170,7 +171,7 @@ static int jumpshot_read_data(struct us_data *us,
 
 		// Store the data in the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				 &sg_idx, &sg_offset, TO_XFER_BUF);
+				 &sg, &sg_offset, TO_XFER_BUF);
 
 		sector += thistime;
 		totallen -= len;
@@ -195,7 +196,8 @@ static int jumpshot_write_data(struct us_data *us,
 	unsigned char  thistime;
 	unsigned int totallen, alloclen;
 	int len, result, waitcount;
-	unsigned int sg_idx = 0, sg_offset = 0;
+	unsigned int sg_offset = 0;
+	struct scatterlist *sg = NULL;
 
 	// we're working in LBA mode.  according to the ATA spec, 
 	// we can support up to 28-bit addressing.  I don't know if Jumpshot
@@ -225,7 +227,7 @@ static int jumpshot_write_data(struct us_data *us,
 
 		// Get the data from the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&sg_idx, &sg_offset, FROM_XFER_BUF);
+				&sg, &sg_offset, FROM_XFER_BUF);
 
 		command[0] = 0;
 		command[1] = thistime;
diff --git a/drivers/usb/storage/protocol.c b/drivers/usb/storage/protocol.c
index 9ad3042..cc8f7c5 100644
--- a/drivers/usb/storage/protocol.c
+++ b/drivers/usb/storage/protocol.c
@@ -157,7 +157,7 @@ void usb_stor_transparent_scsi_command(struct scsi_cmnd *srb,
  * pick up from where this one left off. */
 
 unsigned int usb_stor_access_xfer_buf(unsigned char *buffer,
-	unsigned int buflen, struct scsi_cmnd *srb, unsigned int *index,
+	unsigned int buflen, struct scsi_cmnd *srb, struct scatterlist **sgptr,
 	unsigned int *offset, enum xfer_buf_dir dir)
 {
 	unsigned int cnt;
@@ -184,16 +184,17 @@ unsigned int usb_stor_access_xfer_buf(unsigned char *buffer,
 	 * located in high memory -- then kmap() will map it to a temporary
 	 * position in the kernel's virtual address space. */
 	} else {
-		struct scatterlist *sg =
-				(struct scatterlist *) srb->request_buffer
-				+ *index;
+		struct scatterlist *sg = *sgptr;
+
+		if (!sg)
+			sg = (struct scatterlist *) srb->request_buffer;
 
 		/* This loop handles a single s-g list entry, which may
 		 * include multiple pages.  Find the initial page structure
 		 * and the starting offset within the page, and update
 		 * the *offset and *index values for the next loop. */
 		cnt = 0;
-		while (cnt < buflen && *index < srb->use_sg) {
+		while (cnt < buflen) {
 			struct page *page = sg->page +
 					((sg->offset + *offset) >> PAGE_SHIFT);
 			unsigned int poff =
@@ -209,8 +210,7 @@ unsigned int usb_stor_access_xfer_buf(unsigned char *buffer,
 
 				/* Transfer continues to next s-g entry */
 				*offset = 0;
-				++*index;
-				++sg;
+				sg = sg_next(sg);
 			}
 
 			/* Transfer the data for all the pages in this
@@ -234,6 +234,7 @@ unsigned int usb_stor_access_xfer_buf(unsigned char *buffer,
 				sglen -= plen;
 			}
 		}
+		*sgptr = sg;
 	}
 
 	/* Return the amount actually transferred */
@@ -245,9 +246,10 @@ unsigned int usb_stor_access_xfer_buf(unsigned char *buffer,
 void usb_stor_set_xfer_buf(unsigned char *buffer,
 	unsigned int buflen, struct scsi_cmnd *srb)
 {
-	unsigned int index = 0, offset = 0;
+	unsigned int offset = 0;
+	struct scatterlist *sg = NULL;
 
-	usb_stor_access_xfer_buf(buffer, buflen, srb, &index, &offset,
+	usb_stor_access_xfer_buf(buffer, buflen, srb, &sg, &offset,
 			TO_XFER_BUF);
 	if (buflen < srb->request_bufflen)
 		srb->resid = srb->request_bufflen - buflen;
diff --git a/drivers/usb/storage/protocol.h b/drivers/usb/storage/protocol.h
index 845bed4..8737a36 100644
--- a/drivers/usb/storage/protocol.h
+++ b/drivers/usb/storage/protocol.h
@@ -52,7 +52,7 @@ extern void usb_stor_transparent_scsi_command(struct scsi_cmnd*,
 enum xfer_buf_dir	{TO_XFER_BUF, FROM_XFER_BUF};
 
 extern unsigned int usb_stor_access_xfer_buf(unsigned char *buffer,
-	unsigned int buflen, struct scsi_cmnd *srb, unsigned int *index,
+	unsigned int buflen, struct scsi_cmnd *srb, struct scatterlist **,
 	unsigned int *offset, enum xfer_buf_dir dir);
 
 extern void usb_stor_set_xfer_buf(unsigned char *buffer,
diff --git a/drivers/usb/storage/sddr09.c b/drivers/usb/storage/sddr09.c
index b2ed2a3..b12202c 100644
--- a/drivers/usb/storage/sddr09.c
+++ b/drivers/usb/storage/sddr09.c
@@ -705,7 +705,8 @@ sddr09_read_data(struct us_data *us,
 	unsigned char *buffer;
 	unsigned int lba, maxlba, pba;
 	unsigned int page, pages;
-	unsigned int len, index, offset;
+	unsigned int len, offset;
+	struct scatterlist *sg;
 	int result;
 
 	// Figure out the initial LBA and page
@@ -730,7 +731,8 @@ sddr09_read_data(struct us_data *us,
 	// contiguous LBA's. Another exercise left to the student.
 
 	result = 0;
-	index = offset = 0;
+	offset = 0;
+	sg = NULL;
 
 	while (sectors > 0) {
 
@@ -777,7 +779,7 @@ sddr09_read_data(struct us_data *us,
 
 		// Store the data in the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&index, &offset, TO_XFER_BUF);
+				&sg, &offset, TO_XFER_BUF);
 
 		page = 0;
 		lba++;
@@ -931,7 +933,8 @@ sddr09_write_data(struct us_data *us,
 	unsigned int pagelen, blocklen;
 	unsigned char *blockbuffer;
 	unsigned char *buffer;
-	unsigned int len, index, offset;
+	unsigned int len, offset;
+	struct scatterlist *sg;
 	int result;
 
 	// Figure out the initial LBA and page
@@ -968,7 +971,8 @@ sddr09_write_data(struct us_data *us,
 	}
 
 	result = 0;
-	index = offset = 0;
+	offset = 0;
+	sg = NULL;
 
 	while (sectors > 0) {
 
@@ -987,7 +991,7 @@ sddr09_write_data(struct us_data *us,
 
 		// Get the data from the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&index, &offset, FROM_XFER_BUF);
+				&sg, &offset, FROM_XFER_BUF);
 
 		result = sddr09_write_lba(us, lba, page, pages,
 				buffer, blockbuffer);
diff --git a/drivers/usb/storage/sddr55.c b/drivers/usb/storage/sddr55.c
index 0b1b5b5..d43a341 100644
--- a/drivers/usb/storage/sddr55.c
+++ b/drivers/usb/storage/sddr55.c
@@ -167,7 +167,8 @@ static int sddr55_read_data(struct us_data *us,
 	unsigned long address;
 
 	unsigned short pages;
-	unsigned int len, index, offset;
+	unsigned int len, offset;
+	struct scatterlist *sg;
 
 	// Since we only read in one block at a time, we have to create
 	// a bounce buffer and move the data a piece at a time between the
@@ -178,7 +179,8 @@ static int sddr55_read_data(struct us_data *us,
 	buffer = kmalloc(len, GFP_NOIO);
 	if (buffer == NULL)
 		return USB_STOR_TRANSPORT_ERROR; /* out of memory */
-	index = offset = 0;
+	offset = 0;
+	sg = NULL;
 
 	while (sectors>0) {
 
@@ -255,7 +257,7 @@ static int sddr55_read_data(struct us_data *us,
 
 		// Store the data in the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&index, &offset, TO_XFER_BUF);
+				&sg, &offset, TO_XFER_BUF);
 
 		page = 0;
 		lba++;
@@ -287,7 +289,8 @@ static int sddr55_write_data(struct us_data *us,
 
 	unsigned short pages;
 	int i;
-	unsigned int len, index, offset;
+	unsigned int len, offset;
+	struct scatterlist *sg;
 
 	/* check if we are allowed to write */
 	if (info->read_only || info->force_read_only) {
@@ -304,7 +307,8 @@ static int sddr55_write_data(struct us_data *us,
 	buffer = kmalloc(len, GFP_NOIO);
 	if (buffer == NULL)
 		return USB_STOR_TRANSPORT_ERROR;
-	index = offset = 0;
+	offset = 0;
+	sg = NULL;
 
 	while (sectors > 0) {
 
@@ -322,7 +326,7 @@ static int sddr55_write_data(struct us_data *us,
 
 		// Get the data from the transfer buffer
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-				&index, &offset, FROM_XFER_BUF);
+				&sg, &offset, FROM_XFER_BUF);
 
 		US_DEBUGP("Write %02X pages, to PBA %04X"
 			" (LBA %04X) page %02X\n",
diff --git a/drivers/usb/storage/shuttle_usbat.c b/drivers/usb/storage/shuttle_usbat.c
index 17ca4d7..cb22a9a 100644
--- a/drivers/usb/storage/shuttle_usbat.c
+++ b/drivers/usb/storage/shuttle_usbat.c
@@ -993,7 +993,8 @@ static int usbat_flash_read_data(struct us_data *us,
 	unsigned char  thistime;
 	unsigned int totallen, alloclen;
 	int len, result;
-	unsigned int sg_idx = 0, sg_offset = 0;
+	unsigned int sg_offset = 0;
+	struct scatterlist *sg = NULL;
 
 	result = usbat_flash_check_media(us, info);
 	if (result != USB_STOR_TRANSPORT_GOOD)
@@ -1047,7 +1048,7 @@ static int usbat_flash_read_data(struct us_data *us,
 	
 		/* Store the data in the transfer buffer */
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-					 &sg_idx, &sg_offset, TO_XFER_BUF);
+					 &sg, &sg_offset, TO_XFER_BUF);
 
 		sector += thistime;
 		totallen -= len;
@@ -1083,7 +1084,8 @@ static int usbat_flash_write_data(struct us_data *us,
 	unsigned char  thistime;
 	unsigned int totallen, alloclen;
 	int len, result;
-	unsigned int sg_idx = 0, sg_offset = 0;
+	unsigned int sg_offset = 0;
+	struct scatterlist *sg = NULL;
 
 	result = usbat_flash_check_media(us, info);
 	if (result != USB_STOR_TRANSPORT_GOOD)
@@ -1122,7 +1124,7 @@ static int usbat_flash_write_data(struct us_data *us,
 
 		/* Get the data from the transfer buffer */
 		usb_stor_access_xfer_buf(buffer, len, us->srb,
-					 &sg_idx, &sg_offset, FROM_XFER_BUF);
+					 &sg, &sg_offset, FROM_XFER_BUF);
 
 		/* ATA command 0x30 (WRITE SECTORS) */
 		usbat_pack_ata_sector_cmd(command, thistime, sector, 0x30);
@@ -1162,8 +1164,8 @@ static int usbat_hp8200e_handle_read10(struct us_data *us,
 	unsigned char *buffer;
 	unsigned int len;
 	unsigned int sector;
-	unsigned int sg_segment = 0;
 	unsigned int sg_offset = 0;
+	struct scatterlist *sg = NULL;
 
 	US_DEBUGP("handle_read10: transfersize %d\n",
 		srb->transfersize);
@@ -1220,9 +1222,6 @@ static int usbat_hp8200e_handle_read10(struct us_data *us,
 	sector |= short_pack(data[7+5], data[7+4]);
 	transferred = 0;
 
-	sg_segment = 0; /* for keeping track of where we are in */
-	sg_offset = 0;  /* the scatter/gather list */
-
 	while (transferred != srb->request_bufflen) {
 
 		if (len > srb->request_bufflen - transferred)
@@ -1255,7 +1254,7 @@ static int usbat_hp8200e_handle_read10(struct us_data *us,
 
 		/* Store the data in the transfer buffer */
 		usb_stor_access_xfer_buf(buffer, len, srb,
-				 &sg_segment, &sg_offset, TO_XFER_BUF);
+				 &sg, &sg_offset, TO_XFER_BUF);
 
 		/* Update the amount transferred and the sector number */