The boundary_size 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: 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 So fixing a potential overflow with the safer shortcut. Signed-off-by: Nicolin Chen <nicoleotsuka@xxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> --- arch/sparc/kernel/iommu-common.c | 9 +++------ arch/sparc/kernel/iommu.c | 4 ++-- arch/sparc/kernel/pci_sun4v.c | 4 ++-- 3 files changed, 7 insertions(+), 10 deletions(-) diff --git a/arch/sparc/kernel/iommu-common.c b/arch/sparc/kernel/iommu-common.c index 59cb16691322..843e71894d04 100644 --- a/arch/sparc/kernel/iommu-common.c +++ b/arch/sparc/kernel/iommu-common.c @@ -166,13 +166,10 @@ 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 = dev ? dma_get_seg_boundary(dev) : U32_MAX; - boundary_size = boundary_size >> iommu->table_shift; + /* Overflow-free shortcut for: ALIGN(b + 1, 1 << s) >> s */ + boundary_size = (boundary_size >> iommu->table_shift) + 1; /* * 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 diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 4ae7388b1bff..d981c37305ae 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -472,8 +472,8 @@ 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; + /* Overflow-free shortcut for: ALIGN(b + 1, 1 << s) >> s */ + seg_boundary_size = (dma_get_seg_boundary(dev) >> IO_PAGE_SHIFT) + 1; 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..233fe8a20cec 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -508,8 +508,8 @@ 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; + /* Overflow-free shortcut for: ALIGN(b + 1, 1 << s) >> s */ + seg_boundary_size = (dma_get_seg_boundary(dev) >> IO_PAGE_SHIFT) + 1; mask = *dev->dma_mask; if (!iommu_use_atu(iommu, mask)) -- 2.17.1