summaryrefslogtreecommitdiffstats
path: root/include/asm-x86_64/pci.h
diff options
context:
space:
mode:
authorMuli Ben-Yehuda <mulix@mulix.org>2006-01-11 22:44:42 +0100
committerLinus Torvalds <torvalds@g5.osdl.org>2006-01-11 19:04:55 -0800
commit17a941d854a3f7b0bb916fdeee4c9ffdcc19d8d3 (patch)
treeb6b3b55318336adf769bf57141a01a9defbbb202 /include/asm-x86_64/pci.h
parent8a6fdd3e912e0ce6f723431d66baf704bf8a1d26 (diff)
downloadop-kernel-dev-17a941d854a3f7b0bb916fdeee4c9ffdcc19d8d3.zip
op-kernel-dev-17a941d854a3f7b0bb916fdeee4c9ffdcc19d8d3.tar.gz
[PATCH] x86_64: Use function pointers to call DMA mapping functions
AK: I hacked Muli's original patch a lot and there were a lot of changes - all bugs are probably to blame on me now. There were also some changes in the fall back behaviour for swiotlb - in particular it doesn't try to use GFP_DMA now anymore. Also all DMA mapping operations use the same core dma_alloc_coherent code with proper fallbacks now. And various other changes and cleanups. Known problems: iommu=force swiotlb=force together breaks needs more testing. This patch cleans up x86_64's DMA mapping dispatching code. Right now we have three possible IOMMU types: AGP GART, swiotlb and nommu, and in the future we will also have Xen's x86_64 swiotlb and other HW IOMMUs for x86_64. In order to support all of them cleanly, this patch: - introduces a struct dma_mapping_ops with function pointers for each of the DMA mapping operations of gart (AMD HW IOMMU), swiotlb (software IOMMU) and nommu (no IOMMU). - gets rid of: if (swiotlb) return swiotlb_xxx(); - PCI_DMA_BUS_IS_PHYS is now checked against the dma_ops being set This makes swiotlb faster by avoiding double copying in some cases. Signed-Off-By: Muli Ben-Yehuda <mulix@mulix.org> Signed-Off-By: Jon D. Mason <jdmason@us.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'include/asm-x86_64/pci.h')
-rw-r--r--include/asm-x86_64/pci.h11
1 files changed, 6 insertions, 5 deletions
diff --git a/include/asm-x86_64/pci.h b/include/asm-x86_64/pci.h
index eeb3088..fd03e15 100644
--- a/include/asm-x86_64/pci.h
+++ b/include/asm-x86_64/pci.h
@@ -42,18 +42,20 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
#include <asm/scatterlist.h>
#include <linux/string.h>
#include <asm/page.h>
+#include <linux/dma-mapping.h> /* for have_iommu */
extern int iommu_setup(char *opt);
-#ifdef CONFIG_GART_IOMMU
/* The PCI address space does equal the physical memory
* address space. The networking and block device layers use
* this boolean for bounce buffer decisions
*
- * On AMD64 it mostly equals, but we set it to zero to tell some subsystems
- * that an IOMMU is available.
+ * On AMD64 it mostly equals, but we set it to zero if a hardware
+ * IOMMU (gart) of sotware IOMMU (swiotlb) is available.
*/
-#define PCI_DMA_BUS_IS_PHYS (no_iommu ? 1 : 0)
+#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
+
+#ifdef CONFIG_GART_IOMMU
/*
* x86-64 always supports DAC, but sometimes it is useful to force
@@ -79,7 +81,6 @@ extern int iommu_sac_force;
#else
/* No IOMMU */
-#define PCI_DMA_BUS_IS_PHYS 1
#define pci_dac_dma_supported(pci_dev, mask) 1
#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
OpenPOWER on IntegriCloud