sparc64: add the segment boundary checking to IOMMUs while merging SG entries

Some IOMMUs allocate memory areas spanning LLD's segment boundary limit.  It
forces low level drivers to have a workaround to adjust scatter lists that the
IOMMU builds.  We are in the process of making all the IOMMUs respect the
segment boundary limits to remove such work around in LLDs.

SPARC64 IOMMUs were rewritten to use the IOMMU helper functions and the commit
89c94f2f made the IOMMUs not allocate memory
areas spanning the segment boundary limit.

However, SPARC64 IOMMUs allocate memory areas first then try to merge them
(while some IOMMUs walk through all the sg entries to see how they can be
merged first and allocate memory areas).  So SPARC64 IOMMUs also need the
boundary limit checking when they try to merge sg entries.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc64/kernel/iommu.c

@@ -516,9 +516,11 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	unsigned long flags, handle, prot, ctx;
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned int max_seg_size;
+	unsigned long seg_boundary_size;
 	int outcount, incount, i;
 	struct strbuf *strbuf;
 	struct iommu *iommu;
+	unsigned long base_shift;
 
 	BUG_ON(direction == DMA_NONE);
 
@@ -549,8 +551,11 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	outs->dma_length = 0;
 
 	max_seg_size = dma_get_max_seg_size(dev);
+	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	base_shift = iommu->page_table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
-		unsigned long paddr, npages, entry, slen;
+		unsigned long paddr, npages, entry, out_entry = 0, slen;
 		iopte_t *base;
 
 		slen = s->length;
@@ -593,7 +598,9 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 			 * - allocated dma_addr isn't contiguous to previous allocation
 			 */
 			if ((dma_addr != dma_next) ||
-			    (outs->dma_length + s->length > max_seg_size)) {
+			    (outs->dma_length + s->length > max_seg_size) ||
+			    (is_span_boundary(out_entry, base_shift,
+					      seg_boundary_size, outs, s))) {
 				/* Can't merge: create a new segment */
 				segstart = s;
 				outcount++;
@@ -607,6 +614,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 			/* This is a new segment, fill entries */
 			outs->dma_address = dma_addr;
 			outs->dma_length = slen;
+			out_entry = entry;
 		}
 
 		/* Calculate next page pointer for contiguous check */

arch/sparc64/kernel/iommu_common.h

@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 #include <linux/device.h>
+#include <linux/iommu-helper.h>
 
 #include <asm/iommu.h>
 #include <asm/scatterlist.h>
@@ -58,6 +59,18 @@ static inline unsigned long calc_npages(struct scatterlist *sglist, int nelems)
 	return npages;
 }
 
+static inline int is_span_boundary(unsigned long entry,
+				   unsigned long shift,
+				   unsigned long boundary_size,
+				   struct scatterlist *outs,
+				   struct scatterlist *sg)
+{
+	unsigned long paddr = SG_ENT_PHYS_ADDRESS(outs);
+	int nr = iommu_num_pages(paddr, outs->dma_length + sg->length);
+
+	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
+}
+
 extern unsigned long iommu_range_alloc(struct device *dev,
 				       struct iommu *iommu,
 				       unsigned long npages,

arch/sparc64/kernel/pci_sun4v.c

@@ -335,8 +335,10 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	unsigned long flags, handle, prot;
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned int max_seg_size;
+	unsigned long seg_boundary_size;
 	int outcount, incount, i;
 	struct iommu *iommu;
+	unsigned long base_shift;
 	long err;
 
 	BUG_ON(direction == DMA_NONE);
@@ -362,8 +364,11 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	iommu_batch_start(dev, prot, ~0UL);
 
 	max_seg_size = dma_get_max_seg_size(dev);
+	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	base_shift = iommu->page_table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
-		unsigned long paddr, npages, entry, slen;
+		unsigned long paddr, npages, entry, out_entry = 0, slen;
 
 		slen = s->length;
 		/* Sanity check */
@@ -406,7 +411,9 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 			 * - allocated dma_addr isn't contiguous to previous allocation
 			 */
 			if ((dma_addr != dma_next) ||
-			    (outs->dma_length + s->length > max_seg_size)) {
+			    (outs->dma_length + s->length > max_seg_size) ||
+			    (is_span_boundary(out_entry, base_shift,
+					      seg_boundary_size, outs, s))) {
 				/* Can't merge: create a new segment */
 				segstart = s;
 				outcount++;
@@ -420,6 +427,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 			/* This is a new segment, fill entries */
 			outs->dma_address = dma_addr;
 			outs->dma_length = slen;
+			out_entry = entry;
 		}
 
 		/* Calculate next page pointer for contiguous check */