From 05d3ed0a1fe3ea05ab9f3b8d32576a0bc2e19660 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Mon, 21 Jul 2008 10:15:22 -0400 Subject: x86, pci: iommu fix potential overflow in alloc_iommu() It is possible that alloc_iommu()'s boundary_size overflows as dma_get_seg_boundary can return 0xffffffff. In that case, further usage of boundary_size triggers a BUG_ON() in the iommu code. Signed-off-by: Prarit Bhargava Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-gart_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/pci-gart_64.c') diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index df5f142657d..1062dc1e639 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -93,7 +93,7 @@ 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(dma_get_seg_boundary(dev) + 1, + boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1, PAGE_SIZE) >> PAGE_SHIFT; spin_lock_irqsave(&iommu_bitmap_lock, flags); -- cgit v1.2.3 From 7b22ff5344fda666e0938e5261ea7b9a3dfce497 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 18 Aug 2008 00:36:18 +0900 Subject: x86 gart: allocate size-aligned address for alloc_coherent, v2 This patch changes GART IOMMU to return a size aligned address wrt dma_alloc_coherent, as DMA-mapping.txt defines: The cpu return address and the DMA bus master address are both guaranteed to be aligned to the smallest PAGE_SIZE order which is greater than or equal to the requested size. This invariant exists (for example) to guarantee that if you allocate a chunk which is smaller than or equal to 64 kilobytes, the extent of the buffer you receive will not cross a 64K boundary. Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-gart_64.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel/pci-gart_64.c') diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index cdab6784907..4d8efb05428 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -82,7 +82,8 @@ AGPEXTERN __u32 *agp_gatt_table; static unsigned long next_bit; /* protected by iommu_bitmap_lock */ static int need_flush; /* global flush state. set for each gart wrap */ -static unsigned long alloc_iommu(struct device *dev, int size) +static unsigned long alloc_iommu(struct device *dev, int size, + unsigned long align_mask) { unsigned long offset, flags; unsigned long boundary_size; @@ -95,11 +96,12 @@ static unsigned long alloc_iommu(struct device *dev, int size) spin_lock_irqsave(&iommu_bitmap_lock, flags); offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit, - size, base_index, boundary_size, 0); + size, base_index, boundary_size, align_mask); if (offset == -1) { need_flush = 1; offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, 0, - size, base_index, boundary_size, 0); + size, base_index, boundary_size, + align_mask); } if (offset != -1) { next_bit = offset+size; @@ -236,10 +238,10 @@ nonforced_iommu(struct device *dev, unsigned long addr, size_t size) * Caller needs to check if the iommu is needed and flush. */ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, - size_t size, int dir) + size_t size, int dir, unsigned long align_mask) { unsigned long npages = iommu_num_pages(phys_mem, size); - unsigned long iommu_page = alloc_iommu(dev, npages); + unsigned long iommu_page = alloc_iommu(dev, npages, align_mask); int i; if (iommu_page == -1) { @@ -262,7 +264,11 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, static dma_addr_t gart_map_simple(struct device *dev, phys_addr_t paddr, size_t size, int dir) { - dma_addr_t map = dma_map_area(dev, paddr, size, dir); + dma_addr_t map; + unsigned long align_mask; + + align_mask = (1UL << get_order(size)) - 1; + map = dma_map_area(dev, paddr, size, dir, align_mask); flush_gart(); @@ -281,7 +287,8 @@ gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir) if (!need_iommu(dev, paddr, size)) return paddr; - bus = gart_map_simple(dev, paddr, size, dir); + bus = dma_map_area(dev, paddr, size, dir, 0); + flush_gart(); return bus; } @@ -340,7 +347,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, unsigned long addr = sg_phys(s); if (nonforced_iommu(dev, addr, s->length)) { - addr = dma_map_area(dev, addr, s->length, dir); + addr = dma_map_area(dev, addr, s->length, dir, 0); if (addr == bad_dma_address) { if (i > 0) gart_unmap_sg(dev, sg, i, dir); @@ -362,7 +369,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start, int nelems, struct scatterlist *sout, unsigned long pages) { - unsigned long iommu_start = alloc_iommu(dev, pages); + unsigned long iommu_start = alloc_iommu(dev, pages, 0); unsigned long iommu_page = iommu_start; struct scatterlist *s; int i; -- cgit v1.2.3 From d99e90164e6cf2eb85fa94d547d6336f8127a107 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 4 Oct 2008 15:55:12 -0700 Subject: x86: gart iommu have direct mapping when agp is present too move init_memory_mapping() out of init_k8_gatt. for: http://bugzilla.kernel.org/show_bug.cgi?id=11676 2.6.27-rc2 to rc8, apgart fails, iommu=soft works, regression This is needed because we need to map the GART aperture even if the GATT is not initialized. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-gart_64.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel/pci-gart_64.c') diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 49285f8fd4d..be33a5442d8 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -626,7 +626,6 @@ static __init int init_k8_gatt(struct agp_kern_info *info) struct pci_dev *dev; void *gatt; int i, error; - unsigned long start_pfn, end_pfn; printk(KERN_INFO "PCI-DMA: Disabling AGP.\n"); aper_size = aper_base = info->aper_size = 0; @@ -672,12 +671,6 @@ static __init int init_k8_gatt(struct agp_kern_info *info) printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n", aper_base, aper_size>>10); - /* need to map that range */ - end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT); - if (end_pfn > max_low_pfn_mapped) { - start_pfn = (aper_base>>PAGE_SHIFT); - init_memory_mapping(start_pfn<>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT); + if (end_pfn > max_low_pfn_mapped) { + start_pfn = (aper_base>>PAGE_SHIFT); + init_memory_mapping(start_pfn<> PAGE_SHIFT; -- cgit v1.2.3