Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753341AbYGWLT4 (ORCPT ); Wed, 23 Jul 2008 07:19:56 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751402AbYGWLTs (ORCPT ); Wed, 23 Jul 2008 07:19:48 -0400 Received: from mx1.redhat.com ([66.187.233.31]:38094 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751394AbYGWLTr (ORCPT ); Wed, 23 Jul 2008 07:19:47 -0400 Date: Wed, 23 Jul 2008 07:19:43 -0400 From: Prarit Bhargava To: linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, jbarnes@virtuousgeek.org, fujita.tomonori@lab.ntt.co.jp Cc: Prarit Bhargava Message-Id: <20080723111928.15828.42561.sendpatchset@prarit.bos.redhat.com> Subject: [PATCH]: PCI: GART iommu alignment fixes [v2] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5275 Lines: 134 pci_alloc_consistent/dma_alloc_coherent does not return size aligned addresses. >From Documentation/DMA-mapping.txt: "pci_alloc_consistent returns two values: the virtual address which you can use to access it from the CPU and dma_handle which you pass to the card. 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." 1. Modify alloc_iommu to allow for an alignment mask 2. Modify pci_gart_simple to return size-aligned values. 3. Fixup the alignment calculation in the iommu-helper code. 4. Fix possible overflow in alloc_iommu's boundary_size calculation. (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.) End result: When allocating from IOMMU, pci_alloc_consistent/dma_alloc_coherent will now return a size aligned value. Signed-off-by: Prarit Bhargava diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index faf3229..717ae64 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -83,7 +83,8 @@ 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 mask) { unsigned long offset, flags; unsigned long boundary_size; @@ -91,16 +92,17 @@ 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); offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit, - size, base_index, boundary_size, 0); + size, base_index, boundary_size, 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, + mask); } if (offset != -1) { set_bit_string(iommu_gart_bitmap, offset, size); @@ -240,10 +242,11 @@ 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, u64 align_mask) { unsigned long npages = to_pages(phys_mem, size); - unsigned long iommu_page = alloc_iommu(dev, npages); + unsigned long palign_mask = align_mask >> PAGE_SHIFT; + unsigned long iommu_page = alloc_iommu(dev, npages, palign_mask); int i; if (iommu_page == -1) { @@ -266,7 +269,8 @@ 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, char *buf, size_t size, int dir) { - dma_addr_t map = dma_map_area(dev, virt_to_bus(buf), size, dir); + dma_addr_t map = dma_map_area(dev, virt_to_bus(buf), size, dir, + size - 1); flush_gart(); @@ -286,7 +290,8 @@ gart_map_single(struct device *dev, void *addr, size_t size, int dir) if (!need_iommu(dev, phys_mem, size)) return phys_mem; - bus = gart_map_simple(dev, addr, size, dir); + dma_addr_t map = dma_map_area(dev, virt_to_bus(addr), size, dir, 0); + flush_gart(); return bus; } @@ -345,7 +350,7 @@ 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); @@ -367,7 +372,7 @@ 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; diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c index a3b8d4c..39940e7 100644 --- a/lib/iommu-helper.c +++ b/lib/iommu-helper.c @@ -16,7 +16,7 @@ again: index = find_next_zero_bit(map, size, start); /* Align allocation */ - index = (index + align_mask) & ~align_mask; + index = __ALIGN_MASK(index, align_mask); end = index + nr; if (end >= size) -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/