[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>
diff --git a/arch/x86_64/kernel/pci-nommu.c b/arch/x86_64/kernel/pci-nommu.c
index 5a981dc..3209ada 100644
--- a/arch/x86_64/kernel/pci-nommu.c
+++ b/arch/x86_64/kernel/pci-nommu.c
@@ -6,89 +6,93 @@
#include <linux/string.h>
#include <asm/proto.h>
#include <asm/processor.h>
+#include <asm/dma.h>
-int iommu_merge = 0;
-EXPORT_SYMBOL(iommu_merge);
-
-dma_addr_t bad_dma_address;
-EXPORT_SYMBOL(bad_dma_address);
-
-int iommu_bio_merge = 0;
-EXPORT_SYMBOL(iommu_bio_merge);
-
-int iommu_sac_force = 0;
-EXPORT_SYMBOL(iommu_sac_force);
-
-/*
- * Dummy IO MMU functions
- */
-
-void *dma_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp)
+static int
+check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
{
- void *ret;
- u64 mask;
- int order = get_order(size);
-
- if (hwdev)
- mask = hwdev->coherent_dma_mask & *hwdev->dma_mask;
- else
- mask = 0xffffffff;
- for (;;) {
- ret = (void *)__get_free_pages(gfp, order);
- if (ret == NULL)
- return NULL;
- *dma_handle = virt_to_bus(ret);
- if ((*dma_handle & ~mask) == 0)
- break;
- free_pages((unsigned long)ret, order);
- if (gfp & GFP_DMA)
- return NULL;
- gfp |= GFP_DMA;
+ if (hwdev && bus + size > *hwdev->dma_mask) {
+ printk(KERN_ERR
+ "nommu_%s: overflow %Lx+%lu of device mask %Lx\n",
+ name, (long long)bus, size, (long long)*hwdev->dma_mask);
+ return 0;
}
-
- memset(ret, 0, size);
- return ret;
-}
-EXPORT_SYMBOL(dma_alloc_coherent);
-
-void dma_free_coherent(struct device *hwdev, size_t size,
- void *vaddr, dma_addr_t dma_handle)
-{
- free_pages((unsigned long)vaddr, get_order(size));
-}
-EXPORT_SYMBOL(dma_free_coherent);
-
-int dma_supported(struct device *hwdev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- * RED-PEN this won't work for pci_map_single. Caller has to
- * use GFP_DMA in the first place.
- */
- if (mask < 0x00ffffff)
- return 0;
-
return 1;
-}
-EXPORT_SYMBOL(dma_supported);
-
-int dma_get_cache_alignment(void)
-{
- return boot_cpu_data.x86_clflush_size;
}
-EXPORT_SYMBOL(dma_get_cache_alignment);
-static int __init check_ram(void)
-{
- if (end_pfn >= 0xffffffff>>PAGE_SHIFT) {
- printk(
- KERN_ERR "WARNING more than 4GB of memory but IOMMU not compiled in.\n"
- KERN_ERR "WARNING 32bit PCI may malfunction.\n");
- }
- return 0;
-}
-__initcall(check_ram);
+static dma_addr_t
+nommu_map_single(struct device *hwdev, void *ptr, size_t size,
+ int direction)
+{
+ dma_addr_t bus = virt_to_bus(ptr);
+ if (!check_addr("map_single", hwdev, bus, size))
+ return bad_dma_address;
+ return bus;
+}
+void nommu_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
+ int direction)
+{
+}
+
+/* Map a set of buffers described by scatterlist in streaming
+ * mode for DMA. This is the scatter-gather version of the
+ * above pci_map_single interface. Here the scatter gather list
+ * elements are each tagged with the appropriate dma address
+ * and length. They are obtained via sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ * DMA address/length pairs than there are SG table elements.
+ * (for example via virtual mapping capabilities)
+ * The routine returns the number of addr/length pairs actually
+ * used, at most nents.
+ *
+ * Device ownership issues as mentioned above for pci_map_single are
+ * the same here.
+ */
+int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
+ int nents, int direction)
+{
+ int i;
+
+ BUG_ON(direction == DMA_NONE);
+ for (i = 0; i < nents; i++ ) {
+ struct scatterlist *s = &sg[i];
+ BUG_ON(!s->page);
+ s->dma_address = virt_to_bus(page_address(s->page) +s->offset);
+ if (!check_addr("map_sg", hwdev, s->dma_address, s->length))
+ return 0;
+ s->dma_length = s->length;
+ }
+ return nents;
+}
+
+/* Unmap a set of streaming mode DMA translations.
+ * Again, cpu read rules concerning calls here are the same as for
+ * pci_unmap_single() above.
+ */
+void nommu_unmap_sg(struct device *dev, struct scatterlist *sg,
+ int nents, int dir)
+{
+}
+
+struct dma_mapping_ops nommu_dma_ops = {
+ .map_single = nommu_map_single,
+ .unmap_single = nommu_unmap_single,
+ .map_sg = nommu_map_sg,
+ .unmap_sg = nommu_unmap_sg,
+ .is_phys = 1,
+};
+
+void __init no_iommu_init(void)
+{
+ if (dma_ops)
+ return;
+ printk(KERN_INFO "PCI-DMA: Disabling IOMMU.\n");
+ dma_ops = &nommu_dma_ops;
+ if (end_pfn > MAX_DMA32_PFN) {
+ printk(KERN_ERR
+ "WARNING more than 4GB of memory but IOMMU disabled.\n"
+ KERN_ERR "WARNING 32bit PCI may malfunction.\n");
+ }
+}