Merge branch 'for-linus' of git://git.kernel.dk/data/git/linux-2.6-block

* 'for-linus' of git://git.kernel.dk/data/git/linux-2.6-block: (63 commits)
  Fix memory leak in dm-crypt
  SPARC64: sg chaining support
  SPARC: sg chaining support
  PPC: sg chaining support
  PS3: sg chaining support
  IA64: sg chaining support
  x86-64: enable sg chaining
  x86-64: update pci-gart iommu to sg helpers
  x86-64: update nommu to sg helpers
  x86-64: update calgary iommu to sg helpers
  swiotlb: sg chaining support
  i386: enable sg chaining
  i386 dma_map_sg: convert to using sg helpers
  mmc: need to zero sglist on init
  Panic in blk_rq_map_sg() from CCISS driver
  remove sglist_len
  remove blk_queue_max_phys_segments in libata
  revert sg segment size ifdefs
  Fixup u14-34f ENABLE_SG_CHAINING
  qla1280: enable use_sg_chaining option
  ...

16 files changed, 167 insertions, 127 deletions

diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index e980e7a..4338f41 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -396,7 +396,7 @@ sba_dump_sg( struct ioc *ioc, struct scatterlist *startsg, int nents)
 		printk(KERN_DEBUG " %d : DMA %08lx/%05x CPU %p\n", nents,
 		       startsg->dma_address, startsg->dma_length,
 		       sba_sg_address(startsg));
-		startsg++;
+		startsg = sg_next(startsg);
 	}
 }
 
@@ -409,7 +409,7 @@ sba_check_sg( struct ioc *ioc, struct scatterlist *startsg, int nents)
 	while (the_nents-- > 0) {
 		if (sba_sg_address(the_sg) == 0x0UL)
 			sba_dump_sg(NULL, startsg, nents);
-		the_sg++;
+		the_sg = sg_next(the_sg);
 	}
 }
 
@@ -1201,7 +1201,7 @@ sba_fill_pdir(
 			u32 pide = startsg->dma_address & ~PIDE_FLAG;
 			dma_offset = (unsigned long) pide & ~iovp_mask;
 			startsg->dma_address = 0;
-			dma_sg++;
+			dma_sg = sg_next(dma_sg);
 			dma_sg->dma_address = pide | ioc->ibase;
 			pdirp = &(ioc->pdir_base[pide >> iovp_shift]);
 			n_mappings++;
@@ -1228,7 +1228,7 @@ sba_fill_pdir(
 				pdirp++;
 			} while (cnt > 0);
 		}
-		startsg++;
+		startsg = sg_next(startsg);
 	}
 	/* force pdir update */
 	wmb();
@@ -1297,7 +1297,7 @@ sba_coalesce_chunks( struct ioc *ioc,
 		while (--nents > 0) {
 			unsigned long vaddr;	/* tmp */
 
-			startsg++;
+			startsg = sg_next(startsg);
 
 			/* PARANOID */
 			startsg->dma_address = startsg->dma_length = 0;
@@ -1407,7 +1407,7 @@ int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, int di
 #ifdef ALLOW_IOV_BYPASS_SG
 	ASSERT(to_pci_dev(dev)->dma_mask);
 	if (likely((ioc->dma_mask & ~to_pci_dev(dev)->dma_mask) == 0)) {
-		for (sg = sglist ; filled < nents ; filled++, sg++){
+		for_each_sg(sglist, sg, nents, filled) {
 			sg->dma_length = sg->length;
 			sg->dma_address = virt_to_phys(sba_sg_address(sg));
 		}
@@ -1501,7 +1501,7 @@ void sba_unmap_sg (struct device *dev, struct scatterlist *sglist, int nents, in
 	while (nents && sglist->dma_length) {
 
 		sba_unmap_single(dev, sglist->dma_address, sglist->dma_length, dir);
-		sglist++;
+		sglist = sg_next(sglist);
 		nents--;
 	}
 
diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c
index d62fa76..a3a558a 100644
--- a/arch/ia64/hp/sim/simscsi.c
+++ b/arch/ia64/hp/sim/simscsi.c
@@ -360,6 +360,7 @@ static struct scsi_host_template driver_template = {
 	.max_sectors		= 1024,
 	.cmd_per_lun		= SIMSCSI_REQ_QUEUE_LEN,
 	.use_clustering		= DISABLE_CLUSTERING,
+	.use_sg_chaining	= ENABLE_SG_CHAINING,
 };
 
 static int __init
diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index d79ddac..ecd8a52 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -218,16 +218,17 @@ EXPORT_SYMBOL(sn_dma_unmap_single);
  *
  * Unmap a set of streaming mode DMA translations.
  */
-void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		     int nhwentries, int direction)
 {
 	int i;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
+	struct scatterlist *sg;
 
 	BUG_ON(dev->bus != &pci_bus_type);
 
-	for (i = 0; i < nhwentries; i++, sg++) {
+	for_each_sg(sgl, sg, nhwentries, i) {
 		provider->dma_unmap(pdev, sg->dma_address, direction);
 		sg->dma_address = (dma_addr_t) NULL;
 		sg->dma_length = 0;
@@ -244,11 +245,11 @@ EXPORT_SYMBOL(sn_dma_unmap_sg);
  *
  * Maps each entry of @sg for DMA.
  */
-int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
+int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries,
 		  int direction)
 {
 	unsigned long phys_addr;
-	struct scatterlist *saved_sg = sg;
+	struct scatterlist *saved_sg = sgl, *sg;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 	int i;
@@ -258,7 +259,7 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
 	/*
 	 * Setup a DMA address for each entry in the scatterlist.
 	 */
-	for (i = 0; i < nhwentries; i++, sg++) {
+	for_each_sg(sgl, sg, nhwentries, i) {
 		phys_addr = SG_ENT_PHYS_ADDRESS(sg);
 		sg->dma_address = provider->dma_map(pdev,
 						    phys_addr, sg->length,
diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c
index 7b0e754..9001104 100644
--- a/arch/powerpc/kernel/dma_64.c
+++ b/arch/powerpc/kernel/dma_64.c
@@ -154,12 +154,13 @@ static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr,
 {
 }
 
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sg,
+static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 			     int nents, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < nents; i++, sg++) {
+	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = (page_to_phys(sg->page) + sg->offset) |
 			dma_direct_offset;
 		sg->dma_length = sg->length;
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 53bf646..2e16ca5 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -87,15 +87,16 @@ static void ibmebus_unmap_single(struct device *dev,
 }
 
 static int ibmebus_map_sg(struct device *dev,
-			  struct scatterlist *sg,
+			  struct scatterlist *sgl,
 			  int nents, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < nents; i++) {
-		sg[i].dma_address = (dma_addr_t)page_address(sg[i].page)
-			+ sg[i].offset;
-		sg[i].dma_length = sg[i].length;
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = (dma_addr_t)page_address(sg->page)
+			+ sg->offset;
+		sg->dma_length = sg->length;
 	}
 
 	return nents;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index e4ec6ee..306a6f7 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -277,7 +277,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned long flags;
 	struct scatterlist *s, *outs, *segstart;
-	int outcount, incount;
+	int outcount, incount, i;
 	unsigned long handle;
 
 	BUG_ON(direction == DMA_NONE);
@@ -297,7 +297,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
 	spin_lock_irqsave(&(tbl->it_lock), flags);
 
-	for (s = outs; nelems; nelems--, s++) {
+	for_each_sg(sglist, s, nelems, i) {
 		unsigned long vaddr, npages, entry, slen;
 
 		slen = s->length;
@@ -341,7 +341,8 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 			if (novmerge || (dma_addr != dma_next)) {
 				/* Can't merge: create a new segment */
 				segstart = s;
-				outcount++; outs++;
+				outcount++;
+				outs = sg_next(outs);
 				DBG("    can't merge, new segment.\n");
 			} else {
 				outs->dma_length += s->length;
@@ -374,7 +375,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	 * next entry of the sglist if we didn't fill the list completely
 	 */
 	if (outcount < incount) {
-		outs++;
+		outs = sg_next(outs);
 		outs->dma_address = DMA_ERROR_CODE;
 		outs->dma_length = 0;
 	}
@@ -385,7 +386,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	return outcount;
 
  failure:
-	for (s = &sglist[0]; s <= outs; s++) {
+	for_each_sg(sglist, s, nelems, i) {
 		if (s->dma_length != 0) {
 			unsigned long vaddr, npages;
 
@@ -395,6 +396,8 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
 		}
+		if (s == outs)
+			break;
 	}
 	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 	return 0;
@@ -404,6 +407,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	unsigned long flags;
 
 	BUG_ON(direction == DMA_NONE);
@@ -413,15 +417,16 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
 	spin_lock_irqsave(&(tbl->it_lock), flags);
 
+	sg = sglist;
 	while (nelems--) {
 		unsigned int npages;
-		dma_addr_t dma_handle = sglist->dma_address;
+		dma_addr_t dma_handle = sg->dma_address;
 
-		if (sglist->dma_length == 0)
+		if (sg->dma_length == 0)
 			break;
-		npages = iommu_num_pages(dma_handle,sglist->dma_length);
+		npages = iommu_num_pages(dma_handle, sg->dma_length);
 		__iommu_free(tbl, dma_handle, npages);
-		sglist++;
+		sg = sg_next(sg);
 	}
 
 	/* Flush/invalidate TLBs if necessary. As for iommu_free(), we
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 190ff4b..07e64b4 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -616,17 +616,18 @@ static void ps3_unmap_single(struct device *_dev, dma_addr_t dma_addr,
 	}
 }
 
-static int ps3_sb_map_sg(struct device *_dev, struct scatterlist *sg, int nents,
-	enum dma_data_direction direction)
+static int ps3_sb_map_sg(struct device *_dev, struct scatterlist *sgl,
+	int nents, enum dma_data_direction direction)
 {
 #if defined(CONFIG_PS3_DYNAMIC_DMA)
 	BUG_ON("do");
 	return -EPERM;
 #else
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < nents; i++, sg++) {
+	for_each_sg(sgl, sg, nents, i) {
 		int result = ps3_dma_map(dev->d_region,
 			page_to_phys(sg->page) + sg->offset, sg->length,
 					 &sg->dma_address, 0);
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 62182d2..9c3ed88 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/pci.h>		/* struct pci_dev */
 #include <linux/proc_fs.h>
+#include <linux/scatterlist.h>
 
 #include <asm/io.h>
 #include <asm/vaddrs.h>
@@ -717,19 +718,19 @@ void pci_unmap_page(struct pci_dev *hwdev,
  * Device ownership issues as mentioned above for pci_map_single are
  * the same here.
  */
-int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents,
+int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
     int direction)
 {
+	struct scatterlist *sg;
 	int n;
 
 	BUG_ON(direction == PCI_DMA_NONE);
 	/* IIep is write-through, not flushing. */
-	for (n = 0; n < nents; n++) {
+	for_each_sg(sgl, sg, nents, n) {
 		BUG_ON(page_address(sg->page) == NULL);
 		sg->dvma_address =
 			virt_to_phys(page_address(sg->page)) + sg->offset;
 		sg->dvma_length = sg->length;
-		sg++;
 	}
 	return nents;
 }
@@ -738,19 +739,19 @@ int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents,
  * Again, cpu read rules concerning calls here are the same as for
  * pci_unmap_single() above.
  */
-void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents,
+void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
     int direction)
 {
+	struct scatterlist *sg;
 	int n;
 
 	BUG_ON(direction == PCI_DMA_NONE);
 	if (direction != PCI_DMA_TODEVICE) {
-		for (n = 0; n < nents; n++) {
+		for_each_sg(sgl, sg, nents, n) {
 			BUG_ON(page_address(sg->page) == NULL);
 			mmu_inval_dma_area(
 			    (unsigned long) page_address(sg->page),
 			    (sg->length + PAGE_SIZE-1) & PAGE_MASK);
-			sg++;
 		}
 	}
 }
@@ -789,34 +790,34 @@ void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t ba, size_t
  * The same as pci_dma_sync_single_* but for a scatter-gather list,
  * same rules and usage.
  */
-void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction)
+void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
 {
+	struct scatterlist *sg;
 	int n;
 
 	BUG_ON(direction == PCI_DMA_NONE);
 	if (direction != PCI_DMA_TODEVICE) {
-		for (n = 0; n < nents; n++) {
+		for_each_sg(sgl, sg, nents, n) {
 			BUG_ON(page_address(sg->page) == NULL);
 			mmu_inval_dma_area(
 			    (unsigned long) page_address(sg->page),
 			    (sg->length + PAGE_SIZE-1) & PAGE_MASK);
-			sg++;
 		}
 	}
 }
 
-void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction)
+void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
 {
+	struct scatterlist *sg;
 	int n;
 
 	BUG_ON(direction == PCI_DMA_NONE);
 	if (direction != PCI_DMA_TODEVICE) {
-		for (n = 0; n < nents; n++) {
+		for_each_sg(sgl, sg, nents, n) {
 			BUG_ON(page_address(sg->page) == NULL);
 			mmu_inval_dma_area(
 			    (unsigned long) page_address(sg->page),
 			    (sg->length + PAGE_SIZE-1) & PAGE_MASK);
-			sg++;
 		}
 	}
 }
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index 7c89893..375b4db 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -11,8 +11,8 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>	/* pte_offset_map => kmap_atomic */
 #include <linux/bitops.h>
+#include <linux/scatterlist.h>
 
-#include <asm/scatterlist.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/sbus.h>
@@ -144,8 +144,9 @@ static void iounit_get_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_bus
 	spin_lock_irqsave(&iounit->lock, flags);
 	while (sz != 0) {
 		--sz;
-		sg[sz].dvma_address = iounit_get_area(iounit, (unsigned long)page_address(sg[sz].page) + sg[sz].offset, sg[sz].length);
-		sg[sz].dvma_length = sg[sz].length;
+		sg->dvma_address = iounit_get_area(iounit, (unsigned long)page_address(sg->page) + sg->offset, sg->length);
+		sg->dvma_length = sg->length;
+		sg = sg_next(sg);
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
 }
@@ -173,11 +174,12 @@ static void iounit_release_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_
 	spin_lock_irqsave(&iounit->lock, flags);
 	while (sz != 0) {
 		--sz;
-		len = ((sg[sz].dvma_address & ~PAGE_MASK) + sg[sz].length + (PAGE_SIZE-1)) >> PAGE_SHIFT;
-		vaddr = (sg[sz].dvma_address - IOUNIT_DMA_BASE) >> PAGE_SHIFT;
+		len = ((sg->dvma_address & ~PAGE_MASK) + sg->length + (PAGE_SIZE-1)) >> PAGE_SHIFT;
+		vaddr = (sg->dvma_address - IOUNIT_DMA_BASE) >> PAGE_SHIFT;
 		IOD(("iounit_release %08lx-%08lx\n", (long)vaddr, (long)len+vaddr));
 		for (len += vaddr; vaddr < len; vaddr++)
 			clear_bit(vaddr, iounit->bmap);
+		sg = sg_next(sg);
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
 }
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 52e907a..283656d 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -12,8 +12,8 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/highmem.h>	/* pte_offset_map => kmap_atomic */
+#include <linux/scatterlist.h>
 
-#include <asm/scatterlist.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/sbus.h>
@@ -240,7 +240,7 @@ static void iommu_get_scsi_sgl_noflush(struct scatterlist *sg, int sz, struct sb
 		n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT;
 		sg->dvma_address = iommu_get_one(sg->page, n, sbus) + sg->offset;
 		sg->dvma_length = (__u32) sg->length;
-		sg++;
+		sg = sg_next(sg);
 	}
 }
 
@@ -254,7 +254,7 @@ static void iommu_get_scsi_sgl_gflush(struct scatterlist *sg, int sz, struct sbu
 		n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT;
 		sg->dvma_address = iommu_get_one(sg->page, n, sbus) + sg->offset;
 		sg->dvma_length = (__u32) sg->length;
-		sg++;
+		sg = sg_next(sg);
 	}
 }
 
@@ -285,7 +285,7 @@ static void iommu_get_scsi_sgl_pflush(struct scatterlist *sg, int sz, struct sbu
 
 		sg->dvma_address = iommu_get_one(sg->page, n, sbus) + sg->offset;
 		sg->dvma_length = (__u32) sg->length;
-		sg++;
+		sg = sg_next(sg);
 	}
 }
 
@@ -325,7 +325,7 @@ static void iommu_release_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_b
 		n = (sg->length + sg->offset + PAGE_SIZE-1) >> PAGE_SHIFT;
 		iommu_release_one(sg->dvma_address & PAGE_MASK, n, sbus);
 		sg->dvma_address = 0x21212121;
-		sg++;
+		sg = sg_next(sg);
 	}
 }
 
diff --git a/arch/sparc/mm/sun4c.c b/arch/sparc/mm/sun4c.c
index 005a3e7..ee6708f 100644
--- a/arch/sparc/mm/sun4c.c
+++ b/arch/sparc/mm/sun4c.c
@@ -17,8 +17,8 @@
 #include <linux/highmem.h>
 #include <linux/fs.h>
 #include <linux/seq_file.h>
+#include <linux/scatterlist.h>
 
-#include <asm/scatterlist.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
@@ -1228,8 +1228,9 @@ static void sun4c_get_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_bus *
 {
 	while (sz != 0) {
 		--sz;
-		sg[sz].dvma_address = (__u32)sun4c_lockarea(page_address(sg[sz].page) + sg[sz].offset, sg[sz].length);
-		sg[sz].dvma_length = sg[sz].length;
+		sg->dvma_address = (__u32)sun4c_lockarea(page_address(sg->page) + sg->offset, sg->length);
+		sg->dvma_length = sg->length;
+		sg = sg_next(sg);
 	}
 }
 
@@ -1244,7 +1245,8 @@ static void sun4c_release_scsi_sgl(struct scatterlist *sg, int sz, struct sbus_b
 {
 	while (sz != 0) {
 		--sz;
-		sun4c_unlockarea((char *)sg[sz].dvma_address, sg[sz].length);
+		sun4c_unlockarea((char *)sg->dvma_address, sg->length);
+		sg = sg_next(sg);
 	}
 }
 
diff --git a/arch/sparc64/kernel/iommu.c b/arch/sparc64/kernel/iommu.c
index b35a621..db3ffcf 100644
--- a/arch/sparc64/kernel/iommu.c
+++ b/arch/sparc64/kernel/iommu.c
@@ -10,6 +10,7 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/errno.h>
+#include <linux/scatterlist.h>
 
 #ifdef CONFIG_PCI
 #include <linux/pci.h>
@@ -480,7 +481,7 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg,
 			   unsigned long iopte_protection)
 {
 	struct scatterlist *dma_sg = sg;
-	struct scatterlist *sg_end = sg + nelems;
+	struct scatterlist *sg_end = sg_last(sg, nelems);
 	int i;
 
 	for (i = 0; i < nused; i++) {
@@ -515,7 +516,7 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg,
 					len -= (IO_PAGE_SIZE - (tmp & (IO_PAGE_SIZE - 1UL)));
 					break;
 				}
-				sg++;
+				sg = sg_next(sg);
 			}
 
 			pteval = iopte_protection | (pteval & IOPTE_PAGE);
@@ -528,24 +529,24 @@ static inline void fill_sg(iopte_t *iopte, struct scatterlist *sg,
 			}
 
 			pteval = (pteval & IOPTE_PAGE) + len;
-			sg++;
+			sg = sg_next(sg);
 
 			/* Skip over any tail mappings we've fully mapped,
 			 * adjusting pteval along the way.  Stop when we
 			 * detect a page crossing event.
 			 */
-			while (sg < sg_end &&
+			while (sg != sg_end &&
 			       (pteval << (64 - IO_PAGE_SHIFT)) != 0UL &&
 			       (pteval == SG_ENT_PHYS_ADDRESS(sg)) &&
 			       ((pteval ^
 				 (SG_ENT_PHYS_ADDRESS(sg) + sg->length - 1UL)) >> IO_PAGE_SHIFT) == 0UL) {
 				pteval += sg->length;
-				sg++;
+				sg = sg_next(sg);
 			}
 			if ((pteval << (64 - IO_PAGE_SHIFT)) == 0UL)
 				pteval = ~0UL;
 		} while (dma_npages != 0);
-		dma_sg++;
+		dma_sg = sg_next(dma_sg);
 	}
 }
 
@@ -606,7 +607,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	sgtmp = sglist;
 	while (used && sgtmp->dma_length) {
 		sgtmp->dma_address += dma_base;
-		sgtmp++;
+		sgtmp = sg_next(sgtmp);
 		used--;
 	}
 	used = nelems - used;
@@ -642,6 +643,7 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct strbuf *strbuf;
 	iopte_t *base;
 	unsigned long flags, ctx, i, npages;
+	struct scatterlist *sg, *sgprv;
 	u32 bus_addr;
 
 	if (unlikely(direction == DMA_NONE)) {
@@ -654,11 +656,14 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	bus_addr = sglist->dma_address & IO_PAGE_MASK;
 
-	for (i = 1; i < nelems; i++)
-		if (sglist[i].dma_length == 0)
+	sgprv = NULL;
+	for_each_sg(sglist, sg, nelems, i) {
+		if (sg->dma_length == 0)
 			break;
-	i--;
-	npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) -
+		sgprv = sg;
+	}
+
+	npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length) -
 		  bus_addr) >> IO_PAGE_SHIFT;
 
 	base = iommu->page_table +
@@ -730,6 +735,7 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 	struct iommu *iommu;
 	struct strbuf *strbuf;
 	unsigned long flags, ctx, npages, i;
+	struct scatterlist *sg, *sgprv;
 	u32 bus_addr;
 
 	iommu = dev->archdata.iommu;
@@ -753,11 +759,14 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 
 	/* Step 2: Kick data out of streaming buffers. */
 	bus_addr = sglist[0].dma_address & IO_PAGE_MASK;
-	for(i = 1; i < nelems; i++)
-		if (!sglist[i].dma_length)
+	sgprv = NULL;
+	for_each_sg(sglist, sg, nelems, i) {
+		if (sg->dma_length == 0)
 			break;
-	i--;
-	npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length)
+		sgprv = sg;
+	}
+
+	npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length)
 		  - bus_addr) >> IO_PAGE_SHIFT;
 	strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction);
 
diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc64/kernel/pci_sun4v.c
index 95de144..cacacfa 100644
--- a/arch/sparc64/kernel/pci_sun4v.c
+++ b/arch/sparc64/kernel/pci_sun4v.c
@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/log2.h>
+#include <linux/scatterlist.h>
 
 #include <asm/iommu.h>
 #include <asm/irq.h>
@@ -373,7 +374,7 @@ static inline long fill_sg(long entry, struct device *dev,
 			   int nused, int nelems, unsigned long prot)
 {
 	struct scatterlist *dma_sg = sg;
-	struct scatterlist *sg_end = sg + nelems;
+	struct scatterlist *sg_end = sg_last(sg, nelems);
 	unsigned long flags;
 	int i;
 
@@ -413,7 +414,7 @@ static inline long fill_sg(long entry, struct device *dev,
 					len -= (IO_PAGE_SIZE - (tmp & (IO_PAGE_SIZE - 1UL)));
 					break;
 				}
-				sg++;
+				sg = sg_next(sg);
 			}
 
 			pteval = (pteval & IOPTE_PAGE);
@@ -431,24 +432,25 @@ static inline long fill_sg(long entry, struct device *dev,
 			}
 
 			pteval = (pteval & IOPTE_PAGE) + len;
-			sg++;
+			sg = sg_next(sg);
 
 			/* Skip over any tail mappings we've fully mapped,
 			 * adjusting pteval along the way.  Stop when we
 			 * detect a page crossing event.
 			 */
-			while (sg < sg_end &&
-			       (pteval << (64 - IO_PAGE_SHIFT)) != 0UL &&
+			while ((pteval << (64 - IO_PAGE_SHIFT)) != 0UL &&
 			       (pteval == SG_ENT_PHYS_ADDRESS(sg)) &&
 			       ((pteval ^
 				 (SG_ENT_PHYS_ADDRESS(sg) + sg->length - 1UL)) >> IO_PAGE_SHIFT) == 0UL) {
 				pteval += sg->length;
-				sg++;
+				if (sg == sg_end)
+					break;
+				sg = sg_next(sg);
 			}
 			if ((pteval << (64 - IO_PAGE_SHIFT)) == 0UL)
 				pteval = ~0UL;
 		} while (dma_npages != 0);
-		dma_sg++;
+		dma_sg = sg_next(dma_sg);
 	}
 
 	if (unlikely(iommu_batch_end() < 0L))
@@ -510,7 +512,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	sgtmp = sglist;
 	while (used && sgtmp->dma_length) {
 		sgtmp->dma_address += dma_base;
-		sgtmp++;
+		sgtmp = sg_next(sgtmp);
 		used--;
 	}
 	used = nelems - used;
@@ -545,6 +547,7 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
 	unsigned long flags, i, npages;
+	struct scatterlist *sg, *sgprv;
 	long entry;
 	u32 devhandle, bus_addr;
 
@@ -558,12 +561,15 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	devhandle = pbm->devhandle;
 	
 	bus_addr = sglist->dma_address & IO_PAGE_MASK;
-
-	for (i = 1; i < nelems; i++)
-		if (sglist[i].dma_length == 0)
+	sgprv = NULL;
+	for_each_sg(sglist, sg, nelems, i) {
+		if (sg->dma_length == 0)
 			break;
-	i--;
-	npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) -
+
+		sgprv = sg;
+	}
+
+	npages = (IO_PAGE_ALIGN(sgprv->dma_address + sgprv->dma_length) -
 		  bus_addr) >> IO_PAGE_SHIFT;
 
 	entry = ((bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 71da01e..a50b787 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -35,6 +35,7 @@
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
 #include <linux/delay.h>
+#include <linux/scatterlist.h>
 #include <asm/iommu.h>
 #include <asm/calgary.h>
 #include <asm/tce.h>
@@ -384,31 +385,32 @@ static void calgary_unmap_sg(struct device *dev,
 	struct scatterlist *sglist, int nelems, int direction)
 {
 	struct iommu_table *tbl = find_iommu_table(dev);
+	struct scatterlist *s;
+	int i;
 
 	if (!translate_phb(to_pci_dev(dev)))
 		return;
 
-	while (nelems--) {
+	for_each_sg(sglist, s, nelems, i) {
 		unsigned int npages;
-		dma_addr_t dma = sglist->dma_address;
-		unsigned int dmalen = sglist->dma_length;
+		dma_addr_t dma = s->dma_address;
+		unsigned int dmalen = s->dma_length;
 
 		if (dmalen == 0)
 			break;
 
 		npages = num_dma_pages(dma, dmalen);
 		iommu_free(tbl, dma, npages);
-		sglist++;
 	}
 }
 
 static int calgary_nontranslate_map_sg(struct device* dev,
 	struct scatterlist *sg, int nelems, int direction)
 {
+	struct scatterlist *s;
 	int i;
 
-	for (i = 0; i < nelems; i++ ) {
-		struct scatterlist *s = &sg[i];
+	for_each_sg(sg, s, nelems, i) {
 		BUG_ON(!s->page);
 		s->dma_address = virt_to_bus(page_address(s->page) +s->offset);
 		s->dma_length = s->length;
@@ -420,6 +422,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	int nelems, int direction)
 {
 	struct iommu_table *tbl = find_iommu_table(dev);
+	struct scatterlist *s;
 	unsigned long vaddr;
 	unsigned int npages;
 	unsigned long entry;
@@ -428,8 +431,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	if (!translate_phb(to_pci_dev(dev)))
 		return calgary_nontranslate_map_sg(dev, sg, nelems, direction);
 
-	for (i = 0; i < nelems; i++ ) {
-		struct scatterlist *s = &sg[i];
+	for_each_sg(sg, s, nelems, i) {
 		BUG_ON(!s->page);
 
 		vaddr = (unsigned long)page_address(s->page) + s->offset;
@@ -454,9 +456,9 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	return nelems;
 error:
 	calgary_unmap_sg(dev, sg, nelems, direction);
-	for (i = 0; i < nelems; i++) {
-		sg[i].dma_address = bad_dma_address;
-		sg[i].dma_length = 0;
+	for_each_sg(sg, s, nelems, i) {
+		sg->dma_address = bad_dma_address;
+		sg->dma_length = 0;
 	}
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 4918c57..cfcc84e 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/bitops.h>
 #include <linux/kdebug.h>
+#include <linux/scatterlist.h>
 #include <asm/atomic.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
@@ -278,10 +279,10 @@ static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
  */
 static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 {
+	struct scatterlist *s;
 	int i;
 
-	for (i = 0; i < nents; i++) {
-		struct scatterlist *s = &sg[i];
+	for_each_sg(sg, s, nents, i) {
 		if (!s->dma_length || !s->length)
 			break;
 		gart_unmap_single(dev, s->dma_address, s->dma_length, dir);
@@ -292,14 +293,14 @@ static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
 			       int nents, int dir)
 {
+	struct scatterlist *s;
 	int i;
 
 #ifdef CONFIG_IOMMU_DEBUG
 	printk(KERN_DEBUG "dma_map_sg overflow\n");
 #endif
 
- 	for (i = 0; i < nents; i++ ) {
-		struct scatterlist *s = &sg[i];
+	for_each_sg(sg, s, nents, i) {
 		unsigned long addr = page_to_phys(s->page) + s->offset; 
 		if (nonforced_iommu(dev, addr, s->length)) { 
 			addr = dma_map_area(dev, addr, s->length, dir);
@@ -319,23 +320,23 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
 }
 
 /* Map multiple scatterlist entries continuous into the first. */
-static int __dma_map_cont(struct scatterlist *sg, int start, int stopat,
+static int __dma_map_cont(struct scatterlist *start, int nelems,
 		      struct scatterlist *sout, unsigned long pages)
 {
 	unsigned long iommu_start = alloc_iommu(pages);
 	unsigned long iommu_page = iommu_start; 
+	struct scatterlist *s;
 	int i;
 
 	if (iommu_start == -1)
 		return -1;
-	
-	for (i = start; i < stopat; i++) {
-		struct scatterlist *s = &sg[i];
+
+	for_each_sg(start, s, nelems, i) {
 		unsigned long pages, addr;
 		unsigned long phys_addr = s->dma_address;
 		
-		BUG_ON(i > start && s->offset);
-		if (i == start) {
+		BUG_ON(s != start && s->offset);
+		if (s == start) {
 			*sout = *s; 
 			sout->dma_address = iommu_bus_base;
 			sout->dma_address += iommu_page*PAGE_SIZE + s->offset;
@@ -357,17 +358,17 @@ static int __dma_map_cont(struct scatterlist *sg, int start, int stopat,
 	return 0;
 }
 
-static inline int dma_map_cont(struct scatterlist *sg, int start, int stopat,
+static inline int dma_map_cont(struct scatterlist *start, int nelems,
 		      struct scatterlist *sout,
 		      unsigned long pages, int need)
 {
-	if (!need) { 
-		BUG_ON(stopat - start != 1);
-		*sout = sg[start]; 
-		sout->dma_length = sg[start].length; 
+	if (!need) {
+		BUG_ON(nelems != 1);
+		*sout = *start;
+		sout->dma_length = start->length;
 		return 0;
-	} 
-	return __dma_map_cont(sg, start, stopat, sout, pages);
+	}
+	return __dma_map_cont(start, nelems, sout, pages);
 }
 		
 /*
@@ -381,6 +382,7 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 	int start;
 	unsigned long pages = 0;
 	int need = 0, nextneed;
+	struct scatterlist *s, *ps, *start_sg, *sgmap;
 
 	if (nents == 0) 
 		return 0;
@@ -390,8 +392,9 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 
 	out = 0;
 	start = 0;
-	for (i = 0; i < nents; i++) {
-		struct scatterlist *s = &sg[i];
+	start_sg = sgmap = sg;
+	ps = NULL; /* shut up gcc */
+	for_each_sg(sg, s, nents, i) {
 		dma_addr_t addr = page_to_phys(s->page) + s->offset;
 		s->dma_address = addr;
 		BUG_ON(s->length == 0); 
@@ -400,29 +403,33 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 
 		/* Handle the previous not yet processed entries */
 		if (i > start) {
-			struct scatterlist *ps = &sg[i-1];
 			/* Can only merge when the last chunk ends on a page 
 			   boundary and the new one doesn't have an offset. */
 			if (!iommu_merge || !nextneed || !need || s->offset ||
-			    (ps->offset + ps->length) % PAGE_SIZE) { 
-				if (dma_map_cont(sg, start, i, sg+out, pages,
-						 need) < 0)
+			    (ps->offset + ps->length) % PAGE_SIZE) {
+				if (dma_map_cont(start_sg, i - start, sgmap,
+						  pages, need) < 0)
 					goto error;
 				out++;
+				sgmap = sg_next(sgmap);
 				pages = 0;
-				start = i;	
+				start = i;
+				start_sg = s;
 			}
 		}
 
 		need = nextneed;
 		pages += to_pages(s->offset, s->length);
+		ps = s;
 	}
-	if (dma_map_cont(sg, start, i, sg+out, pages, need) < 0)
+	if (dma_map_cont(start_sg, i - start, sgmap, pages, need) < 0)
 		goto error;
 	out++;
 	flush_gart();
-	if (out < nents) 
-		sg[out].dma_length = 0; 
+	if (out < nents) {
+		sgmap = sg_next(sgmap);
+		sgmap->dma_length = 0;
+	}
 	return out;
 
 error:
@@ -437,8 +444,8 @@ error:
 	if (panic_on_overflow)
 		panic("dma_map_sg: overflow on %lu pages\n", pages);
 	iommu_full(dev, pages << PAGE_SHIFT, dir);
-	for (i = 0; i < nents; i++)
-		sg[i].dma_address = bad_dma_address;
+	for_each_sg(sg, s, nents, i)
+		s->dma_address = bad_dma_address;
 	return 0;
 } 
 
diff --git a/arch/x86/kernel/pci-nommu_64.c b/arch/x86/kernel/pci-nommu_64.c
index 2a34c6c..e85d436 100644
--- a/arch/x86/kernel/pci-nommu_64.c
+++ b/arch/x86/kernel/pci-nommu_64.c
@@ -5,6 +5,7 @@
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
 
 #include <asm/iommu.h>
 #include <asm/processor.h>
@@ -57,10 +58,10 @@ static void nommu_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
 static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 	       int nents, int direction)
 {
+	struct scatterlist *s;
 	int i;
 
- 	for (i = 0; i < nents; i++ ) {
-		struct scatterlist *s = &sg[i];
+	for_each_sg(sg, s, nents, i) {
 		BUG_ON(!s->page);
 		s->dma_address = virt_to_bus(page_address(s->page) +s->offset);
 		if (!check_addr("map_sg", hwdev, s->dma_address, s->length))