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>

3 files changed, 5 insertions, 11 deletions

diff --git a/arch/sparc/kernel/iommu-common.c b/arch/sparc/kernel/iommu-common.c
index 59cb16691322..23ca75f09277 100644
--- a/arch/sparc/kernel/iommu-common.c
+++ b/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);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 4ae7388b1bff..c3e4e2df26a8 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/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,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, 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;
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 14b93c5564e3..6b92dd51c002 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/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,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 
 	mask = *dev->dma_mask;
 	if (!iommu_use_atu(iommu, mask))