[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/include/asm-x86_64/dma-mapping.h b/include/asm-x86_64/dma-mapping.h
index 36d16df..49a81a6 100644
--- a/include/asm-x86_64/dma-mapping.h
+++ b/include/asm-x86_64/dma-mapping.h
@@ -12,155 +12,176 @@
#include <asm/io.h>
#include <asm/swiotlb.h>
+struct dma_mapping_ops {
+ int (*mapping_error)(dma_addr_t dma_addr);
+ void* (*alloc_coherent)(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp);
+ void (*free_coherent)(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle);
+ dma_addr_t (*map_single)(struct device *hwdev, void *ptr,
+ size_t size, int direction);
+ /* like map_single, but doesn't check the device mask */
+ dma_addr_t (*map_simple)(struct device *hwdev, char *ptr,
+ size_t size, int direction);
+ void (*unmap_single)(struct device *dev, dma_addr_t addr,
+ size_t size, int direction);
+ void (*sync_single_for_cpu)(struct device *hwdev,
+ dma_addr_t dma_handle, size_t size,
+ int direction);
+ void (*sync_single_for_device)(struct device *hwdev,
+ dma_addr_t dma_handle, size_t size,
+ int direction);
+ void (*sync_single_range_for_cpu)(struct device *hwdev,
+ dma_addr_t dma_handle, unsigned long offset,
+ size_t size, int direction);
+ void (*sync_single_range_for_device)(struct device *hwdev,
+ dma_addr_t dma_handle, unsigned long offset,
+ size_t size, int direction);
+ void (*sync_sg_for_cpu)(struct device *hwdev,
+ struct scatterlist *sg, int nelems,
+ int direction);
+ void (*sync_sg_for_device)(struct device *hwdev,
+ struct scatterlist *sg, int nelems,
+ int direction);
+ int (*map_sg)(struct device *hwdev, struct scatterlist *sg,
+ int nents, int direction);
+ void (*unmap_sg)(struct device *hwdev,
+ struct scatterlist *sg, int nents,
+ int direction);
+ int (*dma_supported)(struct device *hwdev, u64 mask);
+ int is_phys;
+};
+
extern dma_addr_t bad_dma_address;
-#define dma_mapping_error(x) \
- (swiotlb ? swiotlb_dma_mapping_error(x) : ((x) == bad_dma_address))
+extern struct dma_mapping_ops* dma_ops;
+extern int iommu_merge;
-void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp);
-void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle);
-
-#ifdef CONFIG_GART_IOMMU
-
-extern dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size,
- int direction);
-extern void dma_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
- int direction);
-
-#else
-
-/* No IOMMU */
-
-static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr,
- size_t size, int direction)
+static inline int dma_mapping_error(dma_addr_t dma_addr)
{
- dma_addr_t addr;
+ if (dma_ops->mapping_error)
+ return dma_ops->mapping_error(dma_addr);
- if (direction == DMA_NONE)
- out_of_line_bug();
- addr = virt_to_bus(ptr);
-
- if ((addr+size) & ~*hwdev->dma_mask)
- out_of_line_bug();
- return addr;
+ return (dma_addr == bad_dma_address);
}
-static inline void dma_unmap_single(struct device *hwdev, dma_addr_t dma_addr,
- size_t size, int direction)
+extern void *dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp);
+extern void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle);
+
+static inline dma_addr_t
+dma_map_single(struct device *hwdev, void *ptr, size_t size,
+ int direction)
{
- if (direction == DMA_NONE)
- out_of_line_bug();
- /* Nothing to do */
+ return dma_ops->map_single(hwdev, ptr, size, direction);
}
-#endif
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
+ int direction)
+{
+ dma_ops->unmap_single(dev, addr, size, direction);
+}
#define dma_map_page(dev,page,offset,size,dir) \
dma_map_single((dev), page_address(page)+(offset), (size), (dir))
-static inline void dma_sync_single_for_cpu(struct device *hwdev,
- dma_addr_t dma_handle,
- size_t size, int direction)
-{
- if (direction == DMA_NONE)
- out_of_line_bug();
-
- if (swiotlb)
- return swiotlb_sync_single_for_cpu(hwdev,dma_handle,size,direction);
-
- flush_write_buffers();
-}
-
-static inline void dma_sync_single_for_device(struct device *hwdev,
- dma_addr_t dma_handle,
- size_t size, int direction)
-{
- if (direction == DMA_NONE)
- out_of_line_bug();
-
- if (swiotlb)
- return swiotlb_sync_single_for_device(hwdev,dma_handle,size,direction);
-
- flush_write_buffers();
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *hwdev,
- dma_addr_t dma_handle,
- unsigned long offset,
- size_t size, int direction)
-{
- if (direction == DMA_NONE)
- out_of_line_bug();
-
- if (swiotlb)
- return swiotlb_sync_single_range_for_cpu(hwdev,dma_handle,offset,size,direction);
-
- flush_write_buffers();
-}
-
-static inline void dma_sync_single_range_for_device(struct device *hwdev,
- dma_addr_t dma_handle,
- unsigned long offset,
- size_t size, int direction)
-{
- if (direction == DMA_NONE)
- out_of_line_bug();
-
- if (swiotlb)
- return swiotlb_sync_single_range_for_device(hwdev,dma_handle,offset,size,direction);
-
- flush_write_buffers();
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *hwdev,
- struct scatterlist *sg,
- int nelems, int direction)
-{
- if (direction == DMA_NONE)
- out_of_line_bug();
-
- if (swiotlb)
- return swiotlb_sync_sg_for_cpu(hwdev,sg,nelems,direction);
-
- flush_write_buffers();
-}
-
-static inline void dma_sync_sg_for_device(struct device *hwdev,
- struct scatterlist *sg,
- int nelems, int direction)
-{
- if (direction == DMA_NONE)
- out_of_line_bug();
-
- if (swiotlb)
- return swiotlb_sync_sg_for_device(hwdev,sg,nelems,direction);
-
- flush_write_buffers();
-}
-
-extern int dma_map_sg(struct device *hwdev, struct scatterlist *sg,
- int nents, int direction);
-extern void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg,
- int nents, int direction);
-
#define dma_unmap_page dma_unmap_single
-extern int dma_supported(struct device *hwdev, u64 mask);
-extern int dma_get_cache_alignment(void);
-#define dma_is_consistent(h) 1
-
-static inline int dma_set_mask(struct device *dev, u64 mask)
+static inline void
+dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+ size_t size, int direction)
{
- if (!dev->dma_mask || !dma_supported(dev, mask))
- return -EIO;
- *dev->dma_mask = mask;
- return 0;
+ if (dma_ops->sync_single_for_cpu)
+ dma_ops->sync_single_for_cpu(hwdev, dma_handle, size,
+ direction);
+ flush_write_buffers();
}
-static inline void dma_cache_sync(void *vaddr, size_t size, enum dma_data_direction dir)
+static inline void
+dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
+ size_t size, int direction)
+{
+ if (dma_ops->sync_single_for_device)
+ dma_ops->sync_single_for_device(hwdev, dma_handle, size,
+ direction);
+ flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+ unsigned long offset, size_t size, int direction)
+{
+ if (dma_ops->sync_single_range_for_cpu) {
+ dma_ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, size, direction);
+ }
+
+ flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
+ unsigned long offset, size_t size, int direction)
+{
+ if (dma_ops->sync_single_range_for_device)
+ dma_ops->sync_single_range_for_device(hwdev, dma_handle,
+ offset, size, direction);
+
+ flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+ int nelems, int direction)
+{
+ if (dma_ops->sync_sg_for_cpu)
+ dma_ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
+ flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+ int nelems, int direction)
+{
+ if (dma_ops->sync_sg_for_device) {
+ dma_ops->sync_sg_for_device(hwdev, sg, nelems, direction);
+ }
+
+ flush_write_buffers();
+}
+
+static inline int
+dma_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction)
+{
+ return dma_ops->map_sg(hwdev, sg, nents, direction);
+}
+
+static inline void
+dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
+ int direction)
+{
+ dma_ops->unmap_sg(hwdev, sg, nents, direction);
+}
+
+extern int dma_supported(struct device *hwdev, u64 mask);
+
+/* same for gart, swiotlb, and nommu */
+static inline int dma_get_cache_alignment(void)
+{
+ return boot_cpu_data.x86_clflush_size;
+}
+
+#define dma_is_consistent(h) 1
+
+extern int dma_set_mask(struct device *dev, u64 mask);
+
+static inline void
+dma_cache_sync(void *vaddr, size_t size, enum dma_data_direction dir)
{
flush_write_buffers();
}
-#endif
+extern struct device fallback_dev;
+extern int panic_on_overflow;
+
+#endif /* _X8664_DMA_MAPPING_H */
diff --git a/include/asm-x86_64/gart-mapping.h b/include/asm-x86_64/gart-mapping.h
new file mode 100644
index 0000000..ada497b
--- /dev/null
+++ b/include/asm-x86_64/gart-mapping.h
@@ -0,0 +1,16 @@
+#ifndef _X8664_GART_MAPPING_H
+#define _X8664_GART_MAPPING_H 1
+
+#include <linux/types.h>
+#include <asm/types.h>
+
+struct device;
+
+extern void*
+gart_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp);
+
+extern int
+gart_dma_supported(struct device *hwdev, u64 mask);
+
+#endif /* _X8664_GART_MAPPING_H */
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 @@
#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 @@
#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)
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
index 3450108..113e8a2 100644
--- a/include/asm-x86_64/proto.h
+++ b/include/asm-x86_64/proto.h
@@ -92,7 +92,9 @@
extern int unhandled_signal(struct task_struct *tsk, int sig);
extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void swiotlb_init(void);
+
+extern void gart_parse_options(char *);
+extern void __init no_iommu_init(void);
extern unsigned long table_start, table_end;
@@ -106,12 +108,17 @@
extern int acpi_ht;
extern int acpi_disabled;
+#ifdef CONFIG_GART_IOMMU
extern int fallback_aper_order;
extern int fallback_aper_force;
extern int iommu_aperture;
-extern int iommu_aperture_disabled;
extern int iommu_aperture_allowed;
+extern int iommu_aperture_disabled;
extern int fix_aperture;
+#else
+#define iommu_aperture 0
+#define iommu_aperture_allowed 0
+#endif
extern int force_iommu;
extern int reboot_force;
diff --git a/include/asm-x86_64/swiotlb.h b/include/asm-x86_64/swiotlb.h
index dddf1b2..60757ef 100644
--- a/include/asm-x86_64/swiotlb.h
+++ b/include/asm-x86_64/swiotlb.h
@@ -3,10 +3,14 @@
#include <linux/config.h>
+#include <asm/dma-mapping.h>
+
/* SWIOTLB interface */
-extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr, size_t size,
- int dir);
+extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
+ size_t size, int dir);
+extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags);
extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, int dir);
extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
@@ -34,10 +38,10 @@
extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
int nents, int direction);
extern int swiotlb_dma_mapping_error(dma_addr_t dma_addr);
-extern void *swiotlb_alloc_coherent (struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags);
extern void swiotlb_free_coherent (struct device *hwdev, size_t size,
void *vaddr, dma_addr_t dma_handle);
+extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
+extern void swiotlb_init(void);
#ifdef CONFIG_SWIOTLB
extern int swiotlb;
@@ -45,4 +49,6 @@
#define swiotlb 0
#endif
-#endif
+extern void pci_swiotlb_init(void);
+
+#endif /* _ASM_SWTIOLB_H */