dma-mapping: introduce dma_get_seg_boundary_nr_pages()

We found that callers of dma_get_seg_boundary mostly do an ALIGN
with page mask and then do a page shift to get number of pages:
    ALIGN(boundary + 1, 1 << shift) >> shift

However, the boundary might be as large as ULONG_MAX, which means
that a device has no specific boundary limit. So either "+ 1" or
passing it to ALIGN() would potentially overflow.

According to kernel defines:
    #define ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
    #define ALIGN(x, a)	ALIGN_MASK(x, (typeof(x))(a) - 1)

We can simplify the logic here into a helper function doing:
  ALIGN(boundary + 1, 1 << shift) >> shift
= ALIGN_MASK(b + 1, (1 << s) - 1) >> s
= {[b + 1 + (1 << s) - 1] & ~[(1 << s) - 1]} >> s
= [b + 1 + (1 << s) - 1] >> s
= [b + (1 << s)] >> s
= (b >> s) + 1

This patch introduces and applies dma_get_seg_boundary_nr_pages()
as an overflow-free helper for the dma_get_seg_boundary() callers
to get numbers of pages. It also takes care of the NULL dev case
for non-DMA API callers.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Acked-by: Niklas Schnelle <schnelle@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Signed-off-by: Christoph Hellwig <hch@lst.de>

arch/alpha/kernel/pci_iommu.c

@@ -141,12 +141,7 @@ iommu_arena_find_pages(struct device *dev, struct pci_iommu_arena *arena,
 	unsigned long boundary_size;
 
 	base = arena->dma_base >> PAGE_SHIFT;
-	if (dev) {
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
-		boundary_size = dma_get_seg_boundary(dev) + 1;
-		boundary_size >>= PAGE_SHIFT;
-	} else {
-		boundary_size = 1UL << (32 - PAGE_SHIFT);
-	}
 
 	/* Search forward for the first mask-aligned sequence of N free ptes */
 	ptes = arena->ptes;

arch/ia64/hp/common/sba_iommu.c

@@ -485,8 +485,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	ASSERT(((unsigned long) ioc->res_hint & (sizeof(unsigned long) - 1UL)) == 0);
 	ASSERT(res_ptr < res_end);
 
-	boundary_size = (unsigned long long)dma_get_seg_boundary(dev) + 1;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, iovp_shift);
-	boundary_size = ALIGN(boundary_size, 1ULL << iovp_shift) >> iovp_shift;
 
 	BUG_ON(ioc->ibase & ~iovp_mask);
 	shift = ioc->ibase >> iovp_shift;

arch/powerpc/kernel/iommu.c

@@ -172,7 +172,6 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	int largealloc = npages > 15;
 	int pass = 0;
 	unsigned long align_mask;
-	unsigned long boundary_size;
 	unsigned long flags;
 	unsigned int pool_nr;
 	struct iommu_pool *pool;
@@ -236,15 +235,9 @@ again:
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << tbl->it_page_shift);
-	else
-		boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
-	/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
-
 	n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
-			     boundary_size >> tbl->it_page_shift, align_mask);
+			dma_get_seg_boundary_nr_pages(dev, tbl->it_page_shift),
+			align_mask);
 	if (n == -1) {
 		if (likely(pass == 0)) {
 			/* First try the pool from the start */

arch/s390/pci/pci_dma.c

@@ -261,13 +261,11 @@ static unsigned long __dma_alloc_iommu(struct device *dev,
 				       unsigned long start, int size)
 {
 	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
-	unsigned long boundary_size;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, zdev->start_dma >> PAGE_SHIFT,
-				boundary_size, 0);
+				dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT),
+				0);
 }
 
 static dma_addr_t dma_alloc_address(struct device *dev, int size)

arch/sparc/kernel/iommu-common.c

@@ -166,13 +166,6 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << iommu->table_shift);
-	else
-		boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift);
-
-	boundary_size = boundary_size >> iommu->table_shift;
 	/*
 	 * if the skip_span_boundary_check had been set during init, we set
 	 * things up so that iommu_is_span_boundary() merely checks if the
@@ -181,6 +174,9 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 	if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) {
 		shift = 0;
 		boundary_size = iommu->poolsize * iommu->nr_pools;
+	} else {
+		boundary_size = dma_get_seg_boundary_nr_pages(dev,
+					iommu->table_shift);
 	}
 	n = iommu_area_alloc(iommu->map, limit, start, npages, shift,
 			     boundary_size, align_mask);

arch/sparc/kernel/iommu.c

@@ -472,8 +472,7 @@ 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,
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
 	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;

arch/sparc/kernel/pci_sun4v.c

@@ -508,8 +508,7 @@ 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,
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
 
 	mask = *dev->dma_mask;
 	if (!iommu_use_atu(iommu, mask))

arch/x86/kernel/amd_gart_64.c

@@ -96,8 +96,7 @@ static unsigned long alloc_iommu(struct device *dev, int size,
 
 	base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
 			   PAGE_SIZE) >> PAGE_SHIFT;
-	boundary_size = ALIGN((u64)dma_get_seg_boundary(dev) + 1,
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
-			      PAGE_SIZE) >> PAGE_SHIFT;
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,

drivers/parisc/ccio-dma.c

@@ -356,8 +356,7 @@ ccio_alloc_range(struct ioc *ioc, struct device *dev, size_t size)
 	** ggg sacrifices another 710 to the computer gods.
 	*/
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
 
 	if (pages_needed <= 8) {
 		/*

drivers/parisc/sba_iommu.c

@@ -342,8 +342,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	unsigned long shift;
 	int ret;
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
 
 #if defined(ZX1_SUPPORT)
 	BUG_ON(ioc->ibase & ~IOVP_MASK);

include/linux/dma-mapping.h

@@ -632,6 +632,25 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev)
 	return DMA_BIT_MASK(32);
 }
 
+/**
+ * dma_get_seg_boundary_nr_pages - return the segment boundary in "page" units
+ * @dev: device to guery the boundary for
+ * @page_shift: ilog() of the IOMMU page size
+ *
+ * Return the segment boundary in IOMMU page units (which may be different from
+ * the CPU page size) for the passed in device.
+ *
+ * If @dev is NULL a boundary of U32_MAX is assumed, this case is just for
+ * non-DMA API callers.
+ */
+static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev,
+		unsigned int page_shift)
+{
+	if (!dev)
+		return (U32_MAX >> page_shift) + 1;
+	return (dma_get_seg_boundary(dev) >> page_shift) + 1;
+}
+
 static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
 {
 	if (dev->dma_parms) {