aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/ia64/include/asm/dma-mapping.h19
-rw-r--r--arch/powerpc/include/asm/dma-mapping.h23
-rw-r--r--arch/powerpc/kernel/dma-swiotlb.c48
-rw-r--r--arch/sparc/Kconfig2
-rw-r--r--arch/sparc/include/asm/dma-mapping.h145
-rw-r--r--arch/sparc/include/asm/pci.h3
-rw-r--r--arch/sparc/include/asm/pci_32.h105
-rw-r--r--arch/sparc/include/asm/pci_64.h88
-rw-r--r--arch/sparc/kernel/Makefile2
-rw-r--r--arch/sparc/kernel/dma.c175
-rw-r--r--arch/sparc/kernel/dma.h14
-rw-r--r--arch/sparc/kernel/iommu.c20
-rw-r--r--arch/sparc/kernel/ioport.c190
-rw-r--r--arch/sparc/kernel/pci.c2
-rw-r--r--arch/sparc/kernel/pci_sun4v.c30
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/include/asm/amd_iommu.h1
-rw-r--r--arch/x86/include/asm/amd_iommu_types.h50
-rw-r--r--arch/x86/include/asm/dma-mapping.h18
-rw-r--r--arch/x86/kernel/amd_iommu.c489
-rw-r--r--arch/x86/kernel/amd_iommu_init.c42
-rw-r--r--arch/x86/kernel/pci-dma.c11
-rw-r--r--arch/x86/kernel/pci-gart_64.c5
-rw-r--r--arch/x86/kernel/pci-nommu.c29
-rw-r--r--arch/x86/kernel/pci-swiotlb.c25
-rw-r--r--include/asm-generic/dma-mapping-common.h6
-rw-r--r--include/linux/dma-mapping.h5
-rw-r--r--include/linux/swiotlb.h11
-rw-r--r--lib/swiotlb.c124
29 files changed, 720 insertions, 963 deletions
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 5a61b5c2e18..8d3c79cd81e 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -44,7 +44,6 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
#define get_dma_ops(dev) platform_dma_get_ops(dev)
-#define flush_write_buffers()
#include <asm-generic/dma-mapping-common.h>
@@ -69,6 +68,24 @@ dma_set_mask (struct device *dev, u64 mask)
return 0;
}
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+ if (!dev->dma_mask)
+ return 0;
+
+ return addr + size <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ return paddr;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+ return daddr;
+}
+
extern int dma_get_cache_alignment(void);
static inline void
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index b44aaabdd1a..0c34371ec49 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -424,6 +424,29 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
#endif
}
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+ struct dma_mapping_ops *ops = get_dma_ops(dev);
+
+ if (ops->addr_needs_map && ops->addr_needs_map(dev, addr, size))
+ return 0;
+
+ if (!dev->dma_mask)
+ return 0;
+
+ return addr + size <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ return paddr + get_dma_direct_offset(dev);
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+ return daddr - get_dma_direct_offset(dev);
+}
+
#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
#ifdef CONFIG_NOT_COHERENT_CACHE
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 68ccf11e4f1..e8a57de85bc 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -24,50 +24,12 @@
int swiotlb __read_mostly;
unsigned int ppc_swiotlb_enable;
-void *swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t addr)
-{
- unsigned long pfn = PFN_DOWN(swiotlb_bus_to_phys(hwdev, addr));
- void *pageaddr = page_address(pfn_to_page(pfn));
-
- if (pageaddr != NULL)
- return pageaddr + (addr % PAGE_SIZE);
- return NULL;
-}
-
-dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
- return paddr + get_dma_direct_offset(hwdev);
-}
-
-phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-
-{
- return baddr - get_dma_direct_offset(hwdev);
-}
-
-/*
- * Determine if an address needs bounce buffering via swiotlb.
- * Going forward I expect the swiotlb code to generalize on using
- * a dma_ops->addr_needs_map, and this function will move from here to the
- * generic swiotlb code.
- */
-int
-swiotlb_arch_address_needs_mapping(struct device *hwdev, dma_addr_t addr,
- size_t size)
-{
- struct dma_mapping_ops *dma_ops = get_dma_ops(hwdev);
-
- BUG_ON(!dma_ops);
- return dma_ops->addr_needs_map(hwdev, addr, size);
-}
-
/*
* Determine if an address is reachable by a pci device, or if we must bounce.
*/
static int
swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
{
- u64 mask = dma_get_mask(hwdev);
dma_addr_t max;
struct pci_controller *hose;
struct pci_dev *pdev = to_pci_dev(hwdev);
@@ -79,16 +41,9 @@ swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
if ((addr + size > max) | (addr < hose->dma_window_base_cur))
return 1;
- return !is_buffer_dma_capable(mask, addr, size);
-}
-
-static int
-swiotlb_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
-{
- return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+ return 0;
}
-
/*
* At the moment, all platforms that use this code only require
* swiotlb to be used if we're operating on HIGHMEM. Since
@@ -104,7 +59,6 @@ struct dma_mapping_ops swiotlb_dma_ops = {
.dma_supported = swiotlb_dma_supported,
.map_page = swiotlb_map_page,
.unmap_page = swiotlb_unmap_page,
- .addr_needs_map = swiotlb_addr_needs_map,
.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 3f8b6a92eab..233cff53a62 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -25,6 +25,8 @@ config SPARC
select ARCH_WANT_OPTIONAL_GPIOLIB
select RTC_CLASS
select RTC_DRV_M48T59
+ select HAVE_DMA_ATTRS
+ select HAVE_DMA_API_DEBUG
config SPARC32
def_bool !64BIT
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 204e4bf6443..5a8c308e2b5 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -3,6 +3,7 @@
#include <linux/scatterlist.h>
#include <linux/mm.h>
+#include <linux/dma-debug.h>
#define DMA_ERROR_CODE (~(dma_addr_t)0x0)
@@ -13,142 +14,40 @@ extern int dma_set_mask(struct device *dev, u64 dma_mask);
#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
#define dma_is_consistent(d, h) (1)
-struct dma_ops {
- void *(*alloc_coherent)(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag);
- void (*free_coherent)(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t dma_handle);
- dma_addr_t (*map_page)(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction);
- void (*unmap_page)(struct device *dev, dma_addr_t dma_addr,
- size_t size,
- enum dma_data_direction direction);
- int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction direction);
- void (*unmap_sg)(struct device *dev, struct scatterlist *sg,
- int nhwentries,
- enum dma_data_direction direction);
- void (*sync_single_for_cpu)(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction);
- void (*sync_single_for_device)(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction);
- void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
- int nelems,
- enum dma_data_direction direction);
- void (*sync_sg_for_device)(struct device *dev,
- struct scatterlist *sg, int nents,
- enum dma_data_direction dir);
-};
-extern const struct dma_ops *dma_ops;
+extern struct dma_map_ops *dma_ops, pci32_dma_ops;
+extern struct bus_type pci_bus_type;
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
-{
- return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t dma_handle)
-{
- dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
-}
-
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
- size_t size,
- enum dma_data_direction direction)
-{
- return dma_ops->map_page(dev, virt_to_page(cpu_addr),
- (unsigned long)cpu_addr & ~PAGE_MASK, size,
- direction);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
- size_t size,
- enum dma_data_direction direction)
-{
- dma_ops->unmap_page(dev, dma_addr, size, direction);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction)
-{
- return dma_ops->map_page(dev, page, offset, size, direction);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
- size_t size,
- enum dma_data_direction direction)
-{
- dma_ops->unmap_page(dev, dma_address, size, direction);
-}
-
-static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction)
-{
- return dma_ops->map_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
{
- dma_ops->unmap_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
- dma_ops->sync_single_for_cpu(dev, dma_handle, size, direction);
+#if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
+ if (dev->bus == &pci_bus_type)
+ return &pci32_dma_ops;
+#endif
+ return dma_ops;
}
-static inline void dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle,
- size_t size,
- enum dma_data_direction direction)
-{
- if (dma_ops->sync_single_for_device)
- dma_ops->sync_single_for_device(dev, dma_handle, size,
- direction);
-}
+#include <asm-generic/dma-mapping-common.h>
-static inline void dma_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sg, int nelems,
- enum dma_data_direction direction)
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag)
{
- dma_ops->sync_sg_for_cpu(dev, sg, nelems, direction);
-}
+ struct dma_map_ops *ops = get_dma_ops(dev);
+ void *cpu_addr;
-static inline void dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sg, int nelems,
- enum dma_data_direction direction)
-{
- if (dma_ops->sync_sg_for_device)
- dma_ops->sync_sg_for_device(dev, sg, nelems, direction);
+ cpu_addr = ops->alloc_coherent(dev, size, dma_handle, flag);
+ debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+ return cpu_addr;
}
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
- dma_addr_t dma_handle,
- unsigned long offset,
- size_t size,
- enum dma_data_direction dir)
+static inline void dma_free_coherent(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t dma_handle)
{
- dma_sync_single_for_cpu(dev, dma_handle+offset, size, dir);
-}
+ struct dma_map_ops *ops = get_dma_ops(dev);
-static inline void dma_sync_single_range_for_device(struct device *dev,
- dma_addr_t dma_handle,
- unsigned long offset,
- size_t size,
- enum dma_data_direction dir)
-{
- dma_sync_single_for_device(dev, dma_handle+offset, size, dir);
+ debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+ ops->free_coherent(dev, size, cpu_addr, dma_handle);
}
-
static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return (dma_addr == DMA_ERROR_CODE);
diff --git a/arch/sparc/include/asm/pci.h b/arch/sparc/include/asm/pci.h
index 6e14fd17933..d9c031f9910 100644
--- a/arch/sparc/include/asm/pci.h
+++ b/arch/sparc/include/asm/pci.h
@@ -5,4 +5,7 @@
#else
#include <asm/pci_32.h>
#endif
+
+#include <asm-generic/pci-dma-compat.h>
+
#endif
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index b41c4c19815..ac0e8369fd9 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -31,42 +31,8 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
*/
#define PCI_DMA_BUS_IS_PHYS (0)
-#include <asm/scatterlist.h>
-
struct pci_dev;
-/* Allocate and map kernel buffer using consistent mode DMA for a device.
- * hwdev should be valid struct pci_dev pointer for PCI devices.
- */
-extern void *pci_alloc_consistent(struct pci_dev *hwdev, size_t size, dma_addr_t *dma_handle);
-
-/* Free and unmap a consistent DMA buffer.
- * cpu_addr is what was returned from pci_alloc_consistent,
- * size must be the same as what as passed into pci_alloc_consistent,
- * and likewise dma_addr must be the same as what *dma_addrp was set to.
- *
- * References to the memory and mappings assosciated with cpu_addr/dma_addr
- * past this call are illegal.
- */
-extern void pci_free_consistent(struct pci_dev *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle);
-
-/* Map a single buffer of the indicated size for DMA in streaming mode.
- * The 32-bit bus address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory
- * until either pci_unmap_single or pci_dma_sync_single_for_cpu is performed.
- */
-extern dma_addr_t pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction);
-
-/* Unmap a single streaming mode DMA translation. The dma_addr and size
- * must match what was provided for in a previous pci_map_single call. All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-extern void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, size_t size, int direction);
-
/* pci_unmap_{single,page} is not a nop, thus... */
#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \
dma_addr_t ADDR_NAME;
@@ -81,69 +47,6 @@ extern void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, size_t
#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
(((PTR)->LEN_NAME) = (VAL))
-/*
- * Same as above, only with pages instead of mapped addresses.
- */
-extern dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page,
- unsigned long offset, size_t size, int direction);
-extern void pci_unmap_page(struct pci_dev *hwdev,
- dma_addr_t dma_address, size_t size, int direction);
-
-/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA. This is the scather-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.
- */
-extern int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction);
-
-/* Unmap a set of streaming mode DMA translations.
- * Again, cpu read rules concerning calls here are the same as for
- * pci_unmap_single() above.
- */
-extern void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nhwents, int direction);
-
-/* Make physical memory consistent for a single
- * streaming mode DMA translation after a transfer.
- *
- * If you perform a pci_map_single() but wish to interrogate the
- * buffer using the cpu, yet do not wish to teardown the PCI dma
- * mapping, you must call this function before doing so. At the
- * next point you give the PCI dma address back to the card, you
- * must first perform a pci_dma_sync_for_device, and then the device
- * again owns the buffer.
- */
-extern void pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction);
-extern void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction);
-
-/* Make physical memory consistent for a set of streaming
- * mode DMA translations after a transfer.
- *
- * The same as pci_dma_sync_single_* but for a scatter-gather list,
- * same rules and usage.
- */
-extern void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, int nelems, int direction);
-extern void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, int nelems, int direction);
-
-/* Return whether the given PCI device DMA address mask can
- * be supported properly. For example, if your device can
- * only drive the low 24-bits during PCI bus mastering, then
- * you would pass 0x00ffffff as the mask to this function.
- */
-static inline int pci_dma_supported(struct pci_dev *hwdev, u64 mask)
-{
- return 1;
-}
-
#ifdef CONFIG_PCI
static inline void pci_dma_burst_advice(struct pci_dev *pdev,
enum pci_dma_burst_strategy *strat,
@@ -154,14 +57,6 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
}
#endif
-#define PCI_DMA_ERROR_CODE (~(dma_addr_t)0x0)
-
-static inline int pci_dma_mapping_error(struct pci_dev *pdev,
- dma_addr_t dma_addr)
-{
- return (dma_addr == PCI_DMA_ERROR_CODE);
-}
-
struct device_node;
extern struct device_node *pci_device_to_OF_node(struct pci_dev *pdev);
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index 7a1e3566e59..5cc9f6aa549 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -35,37 +35,6 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
*/
#define PCI_DMA_BUS_IS_PHYS (0)
-static inline void *pci_alloc_consistent(struct pci_dev *pdev, size_t size,
- dma_addr_t *dma_handle)
-{
- return dma_alloc_coherent(&pdev->dev, size, dma_handle, GFP_ATOMIC);
-}
-
-static inline void pci_free_consistent(struct pci_dev *pdev, size_t size,
- void *vaddr, dma_addr_t dma_handle)
-{
- return dma_free_coherent(&pdev->dev, size, vaddr, dma_handle);
-}
-
-static inline dma_addr_t pci_map_single(struct pci_dev *pdev, void *ptr,
- size_t size, int direction)
-{
- return dma_map_single(&pdev->dev, ptr, size,
- (enum dma_data_direction) direction);
-}
-
-static inline void pci_unmap_single(struct pci_dev *pdev, dma_addr_t dma_addr,
- size_t size, int direction)
-{
- dma_unmap_single(&pdev->dev, dma_addr, size,
- (enum dma_data_direction) direction);
-}
-
-#define pci_map_page(dev, page, off, size, dir) \
- pci_map_single(dev, (page_address(page) + (off)), size, dir)
-#define pci_unmap_page(dev,addr,sz,dir) \
- pci_unmap_single(dev,addr,sz,dir)
-
/* pci_unmap_{single,page} is not a nop, thus... */
#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \
dma_addr_t ADDR_NAME;
@@ -80,57 +49,6 @@ static inline void pci_unmap_single(struct pci_dev *pdev, dma_addr_t dma_addr,
#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
(((PTR)->LEN_NAME) = (VAL))
-static inline int pci_map_sg(struct pci_dev *pdev, struct scatterlist *sg,
- int nents, int direction)
-{
- return dma_map_sg(&pdev->dev, sg, nents,
- (enum dma_data_direction) direction);
-}
-
-static inline void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sg,
- int nents, int direction)
-{
- dma_unmap_sg(&pdev->dev, sg, nents,
- (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_single_for_cpu(struct pci_dev *pdev,
- dma_addr_t dma_handle,
- size_t size, int direction)
-{
- dma_sync_single_for_cpu(&pdev->dev, dma_handle, size,
- (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_single_for_device(struct pci_dev *pdev,
- dma_addr_t dma_handle,
- size_t size, int direction)
-{
- /* No flushing needed to sync cpu writes to the device. */
-}
-
-static inline void pci_dma_sync_sg_for_cpu(struct pci_dev *pdev,
- struct scatterlist *sg,
- int nents, int direction)
-{
- dma_sync_sg_for_cpu(&pdev->dev, sg, nents,
- (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_sg_for_device(struct pci_dev *pdev,
- struct scatterlist *sg,
- int nelems, int direction)
-{
- /* No flushing needed to sync cpu writes to the device. */
-}
-
-/* Return whether the given PCI device DMA address mask can
- * be supported properly. For example, if your device can
- * only drive the low 24-bits during PCI bus mastering, then
- * you would pass 0x00ffffff as the mask to this function.
- */
-extern int pci_dma_supported(struct pci_dev *hwdev, u64 mask);
-
/* PCI IOMMU mapping bypass support. */
/* PCI 64-bit addressing works for all slots on all controller
@@ -140,12 +58,6 @@ extern int pci_dma_supported(struct pci_dev *hwdev, u64 mask);
#define PCI64_REQUIRED_MASK (~(dma64_addr_t)0)
#define PCI64_ADDR_BASE 0xfffc000000000000UL
-static inline int pci_dma_mapping_error(struct pci_dev *pdev,
- dma_addr_t dma_addr)
-{
- return dma_mapping_error(&pdev->dev, dma_addr);
-}
-
#ifdef CONFIG_PCI
static inline void pci_dma_burst_advice(struct pci_dev *pdev,
enum pci_dma_burst_strategy *strat,
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 475ce4696ac..29b88a58066 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -61,7 +61,7 @@ obj-$(CONFIG_SPARC64_SMP) += cpumap.o
obj-$(CONFIG_SPARC32) += devres.o
devres-y := ../../../kernel/irq/devres.o
-obj-$(CONFIG_SPARC32) += dma.o
+obj-y += dma.o
obj-$(CONFIG_SPARC32_PCI) += pcic.o
diff --git a/arch/sparc/kernel/dma.c b/arch/sparc/kernel/dma.c
index 524c32f97c5..e1ba8ee21b9 100644
--- a/arch/sparc/kernel/dma.c
+++ b/arch/sparc/kernel/dma.c
@@ -1,178 +1,13 @@
-/* dma.c: PCI and SBUS DMA accessors for 32-bit sparc.
- *
- * Copyright (C) 2008 David S. Miller <davem@davemloft.net>
- */
-
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-#include <linux/mm.h>
-
-#ifdef CONFIG_PCI
-#include <linux/pci.h>
-#endif
+#include <linux/dma-debug.h>
-#include "dma.h"
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 15)
-int dma_supported(struct device *dev, u64 mask)
+static int __init dma_init(void)
{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type)
- return pci_dma_supported(to_pci_dev(dev), mask);
-#endif
+ dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
return 0;
}
-EXPORT_SYMBOL(dma_supported);
-
-int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type)
- return pci_set_dma_mask(to_pci_dev(dev), dma_mask);
-#endif
- return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL(dma_set_mask);
-
-static void *dma32_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type)
- return pci_alloc_consistent(to_pci_dev(dev), size, dma_handle);
-#endif
- return sbus_alloc_consistent(dev, size, dma_handle);
-}
-
-static void dma32_free_coherent(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t dma_handle)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type) {
- pci_free_consistent(to_pci_dev(dev), size,
- cpu_addr, dma_handle);
- return;
- }
-#endif
- sbus_free_consistent(dev, size, cpu_addr, dma_handle);
-}
-
-static dma_addr_t dma32_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type)
- return pci_map_page(to_pci_dev(dev), page, offset,
- size, (int)direction);
-#endif
- return sbus_map_single(dev, page_address(page) + offset,
- size, (int)direction);
-}
-
-static void dma32_unmap_page(struct device *dev, dma_addr_t dma_address,
- size_t size, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type) {
- pci_unmap_page(to_pci_dev(dev), dma_address,
- size, (int)direction);
- return;
- }
-#endif
- sbus_unmap_single(dev, dma_address, size, (int)direction);
-}
-
-static int dma32_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type)
- return pci_map_sg(to_pci_dev(dev), sg, nents, (int)direction);
-#endif
- return sbus_map_sg(dev, sg, nents, direction);
-}
-
-void dma32_unmap_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type) {
- pci_unmap_sg(to_pci_dev(dev), sg, nents, (int)direction);
- return;
- }
-#endif
- sbus_unmap_sg(dev, sg, nents, (int)direction);
-}
-
-static void dma32_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
- size_t size,
- enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type) {
- pci_dma_sync_single_for_cpu(to_pci_dev(dev), dma_handle,
- size, (int)direction);
- return;
- }
-#endif
- sbus_dma_sync_single_for_cpu(dev, dma_handle, size, (int) direction);
-}
-
-static void dma32_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type) {
- pci_dma_sync_single_for_device(to_pci_dev(dev), dma_handle,
- size, (int)direction);
- return;
- }
-#endif
- sbus_dma_sync_single_for_device(dev, dma_handle, size, (int) direction);
-}
-
-static void dma32_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
- int nelems, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type) {
- pci_dma_sync_sg_for_cpu(to_pci_dev(dev), sg,
- nelems, (int)direction);
- return;
- }
-#endif
- BUG();
-}
-
-static void dma32_sync_sg_for_device(struct device *dev,
- struct scatterlist *sg, int nelems,
- enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type) {
- pci_dma_sync_sg_for_device(to_pci_dev(dev), sg,
- nelems, (int)direction);
- return;
- }
-#endif
- BUG();
-}
-
-static const struct dma_ops dma32_dma_ops = {
- .alloc_coherent = dma32_alloc_coherent,
- .free_coherent = dma32_free_coherent,
- .map_page = dma32_map_page,
- .unmap_page = dma32_unmap_page,
- .map_sg = dma32_map_sg,
- .unmap_sg = dma32_unmap_sg,
- .sync_single_for_cpu = dma32_sync_single_for_cpu,
- .sync_single_for_device = dma32_sync_single_for_device,
- .sync_sg_for_cpu = dma32_sync_sg_for_cpu,
- .sync_sg_for_device = dma32_sync_sg_for_device,
-};
-
-const struct dma_ops *dma_ops = &dma32_dma_ops;
-EXPORT_SYMBOL(dma_ops);
+fs_initcall(dma_init);
diff --git a/arch/sparc/kernel/dma.h b/arch/sparc/kernel/dma.h
deleted file mode 100644
index f8d8951adb5..00000000000
--- a/arch/sparc/kernel/dma.h
+++ /dev/null
@@ -1,14 +0,0 @@
-void *sbus_alloc_consistent(struct device *dev, long len, u32 *dma_addrp);
-void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba);
-dma_addr_t sbus_map_single(struct device *dev, void *va,
- size_t len, int direction);
-void sbus_unmap_single(struct device *dev, dma_addr_t ba,
- size_t n, int direction);
-int sbus_map_sg(struct device *dev, struct scatterlist *sg,
- int n, int direction);
-void sbus_unmap_sg(struct device *dev, struct scatterlist *sg,
- int n, int direction);
-void sbus_dma_sync_single_for_cpu(struct device *dev, dma_addr_t ba,
- size_t size, int direction);
-void sbus_dma_sync_single_for_device(struct device *dev, dma_addr_t ba,
- size_t size, int direction);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 0aeaefe696b..7690cc219ec 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -353,7 +353,8 @@ static void dma_4u_free_coherent(struct device *dev, size_t size,
static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t sz,
- enum dma_data_direction direction)
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
struct iommu *iommu;
struct strbuf *strbuf;
@@ -474,7 +475,8 @@ do_flush_sync:
}
static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
- size_t sz, enum dma_data_direction direction)
+ size_t sz, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
struct iommu *iommu;
struct strbuf *strbuf;
@@ -520,7 +522,8 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
}
static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
- int nelems, enum dma_data_direction direction)
+ int nelems, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
struct scatterlist *s, *outs, *segstart;
unsigned long flags, handle, prot, ctx;
@@ -691,7 +694,8 @@ static unsigned long fetch_sg_ctx(struct iommu *iommu, struct scatterlist *sg)
}
static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
- int nelems, enum dma_data_direction direction)
+ int nelems, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
unsigned long flags, ctx;
struct scatterlist *sg;
@@ -822,7 +826,7 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
spin_unlock_irqrestore(&iommu->lock, flags);
}
-static const struct dma_ops sun4u_dma_ops = {
+static struct dma_map_ops sun4u_dma_ops = {
.alloc_coherent = dma_4u_alloc_coherent,
.free_coherent = dma_4u_free_coherent,
.map_page = dma_4u_map_page,
@@ -833,9 +837,11 @@ static const struct dma_ops sun4u_dma_ops = {
.sync_sg_for_cpu = dma_4u_sync_sg_for_cpu,
};
-const struct dma_ops *dma_ops = &sun4u_dma_ops;
+struct dma_map_ops *dma_ops = &sun4u_dma_ops;
EXPORT_SYMBOL(dma_ops);
+extern int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask);
+
int dma_supported(struct device *dev, u64 device_mask)
{
struct iommu *iommu = dev->archdata.iommu;
@@ -849,7 +855,7 @@ int dma_supported(struct device *dev, u64 device_mask)
#ifdef CONFIG_PCI
if (dev->bus == &pci_bus_type)
- return pci_dma_supported(to_pci_dev(dev), device_mask);
+ return pci64_dma_supported(to_pci_dev(dev), device_mask);
#endif
return 0;
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 87ea0d03d97..edbea232c61 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -48,8 +48,6 @@
#include <asm/iommu.h>
#include <asm/io-unit.h>
-#include "dma.h"
-
#define mmu_inval_dma_area(p, l) /* Anton pulled it out for 2.4.0-xx */
static struct resource *_sparc_find_resource(struct resource *r,
@@ -246,7 +244,8 @@ EXPORT_SYMBOL(sbus_set_sbus64);
* Typically devices use them for control blocks.
* CPU may access them without any explicit flushing.
*/
-void *sbus_alloc_consistent(struct device *dev, long len, u32 *dma_addrp)
+static void *sbus_alloc_coherent(struct device *dev, size_t len,
+ dma_addr_t *dma_addrp, gfp_t gfp)
{
struct of_device *op = to_of_device(dev);
unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK;
@@ -299,7 +298,8 @@ err_nopages:
return NULL;
}
-void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
+static void sbus_free_coherent(struct device *dev, size_t n, void *p,
+ dma_addr_t ba)
{
struct resource *res;
struct page *pgv;
@@ -317,7 +317,7 @@ void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
n = (n + PAGE_SIZE-1) & PAGE_MASK;
if ((res->end-res->start)+1 != n) {
- printk("sbus_free_consistent: region 0x%lx asked 0x%lx\n",
+ printk("sbus_free_consistent: region 0x%lx asked 0x%zx\n",
(long)((res->end-res->start)+1), n);
return;
}
@@ -337,8 +337,13 @@ void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
* CPU view of this memory may be inconsistent with
* a device view and explicit flushing is necessary.
*/
-dma_addr_t sbus_map_single(struct device *dev, void *va, size_t len, int direction)
+static dma_addr_t sbus_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t len,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
+ void *va = page_address(page) + offset;
+
/* XXX why are some lengths signed, others unsigned? */
if (len <= 0) {
return 0;
@@ -350,12 +355,14 @@ dma_addr_t sbus_map_single(struct device *dev, void *va, size_t len, int directi
return mmu_get_scsi_one(dev, va, len);
}
-void sbus_unmap_single(struct device *dev, dma_addr_t ba, size_t n, int direction)
+static void sbus_unmap_page(struct device *dev, dma_addr_t ba, size_t n,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
mmu_release_scsi_one(dev, ba, n);
}
-int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n, int direction)
+static int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
mmu_get_scsi_sgl(dev, sg, n);
@@ -366,19 +373,38 @@ int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n, int direction
return n;
}
-void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n, int direction)
+static void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
mmu_release_scsi_sgl(dev, sg, n);
}
-void sbus_dma_sync_single_for_cpu(struct device *dev, dma_addr_t ba, size_t size, int direction)
+static void sbus_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+ int n, enum dma_data_direction dir)
{
+ BUG();
}
-void sbus_dma_sync_single_for_device(struct device *dev, dma_addr_t ba, size_t size, int direction)
+static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+ int n, enum dma_data_direction dir)
{
+ BUG();
}
+struct dma_map_ops sbus_dma_ops = {
+ .alloc_coherent = sbus_alloc_coherent,
+ .free_coherent = sbus_free_coherent,
+ .map_page = sbus_map_page,
+ .unmap_page = sbus_unmap_page,
+ .map_sg = sbus_map_sg,
+ .unmap_sg = sbus_unmap_sg,
+ .sync_sg_for_cpu = sbus_sync_sg_for_cpu,
+ .sync_sg_for_device = sbus_sync_sg_for_device,
+};
+
+struct dma_map_ops *dma_ops = &sbus_dma_ops;
+EXPORT_SYMBOL(dma_ops);
+
static int __init sparc_register_ioport(void)
{
register_proc_sparc_ioport();
@@ -395,7 +421,8 @@ arch_initcall(sparc_register_ioport);
/* Allocate and map kernel buffer using consistent mode DMA for a device.
* hwdev should be valid struct pci_dev pointer for PCI devices.
*/
-void *pci_alloc_consistent(struct pci_dev *pdev, size_t len, dma_addr_t *pba)
+static void *pci32_alloc_coherent(struct device *dev, size_t len,
+ dma_addr_t *pba, gfp_t gfp)
{
unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK;
unsigned long va;
@@ -439,7 +466,6 @@ void *pci_alloc_consistent(struct pci_dev *pdev, size_t len, dma_addr_t *pba)
*pba = virt_to_phys(va); /* equals virt_to_bus (R.I.P.) for us. */
return (void *) res->start;
}
-EXPORT_SYMBOL(pci_alloc_consistent);
/* Free and unmap a consistent DMA buffer.
* cpu_addr is what was returned from pci_alloc_consistent,
@@ -449,7 +475,8 @@ EXPORT_SYMBOL(pci_alloc_consistent);
* References to the memory and mappings associated with cpu_addr/dma_addr
* past this call are illegal.
*/
-void pci_free_consistent(struct pci_dev *pdev, size_t n, void *p, dma_addr_t ba)
+static void pci32_free_coherent(struct device *dev, size_t n, void *p,
+ dma_addr_t ba)
{
struct resource *res;
unsigned long pgp;
@@ -481,60 +508,18 @@ void pci_free_consistent(struct pci_dev *pdev, size_t n, void *p, dma_addr_t ba)
free_pages(pgp, get_order(n));
}
-EXPORT_SYMBOL(pci_free_consistent);
-
-/* Map a single buffer of the indicated size for DMA in streaming mode.
- * The 32-bit bus address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory
- * until either pci_unmap_single or pci_dma_sync_single_* is performed.
- */
-dma_addr_t pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size,
- int direction)
-{
- BUG_ON(direction == PCI_DMA_NONE);
- /* IIep is write-through, not flushing. */
- return virt_to_phys(ptr);
-}
-EXPORT_SYMBOL(pci_map_single);
-
-/* Unmap a single streaming mode DMA translation. The dma_addr and size
- * must match what was provided for in a previous pci_map_single call. All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t ba, size_t size,
- int direction)
-{
- BUG_ON(direction == PCI_DMA_NONE);
- if (direction != PCI_DMA_TODEVICE) {
- mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
- (size + PAGE_SIZE-1) & PAGE_MASK);
- }
-}
-EXPORT_SYMBOL(pci_unmap_single);
/*
* Same as pci_map_single, but with pages.
*/
-dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page,
- unsigned long offset, size_t size, int direction)
+static dma_addr_t pci32_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
- BUG_ON(direction == PCI_DMA_NONE);
/* IIep is write-through, not flushing. */
return page_to_phys(page) + offset;
}
-EXPORT_SYMBOL(pci_map_page);
-
-void pci_unmap_page(struct pci_dev *hwdev,
- dma_addr_t dma_address, size_t size, int direction)
-{
- BUG_ON(direction == PCI_DMA_NONE);
- /* mmu_inval_dma_area XXX */
-}
-EXPORT_SYMBOL(pci_unmap_page);
/* Map a set of buffers described by scatterlist in streaming
* mode for DMA. This is the scather-gather version of the
@@ -551,13 +536,13 @@ EXPORT_SYMBOL(pci_unmap_page);
* Device ownership issues as mentioned above for pci_map_single are
* the same here.
*/
-int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
- int direction)
+static int pci32_map_sg(struct device *device, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
struct scatterlist *sg;
int n;
- BUG_ON(direction == PCI_DMA_NONE);
/* IIep is write-through, not flushing. */
for_each_sg(sgl, sg, nents, n) {
BUG_ON(page_address(sg_page(sg)) == NULL);
@@ -566,20 +551,19 @@ int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
}
return nents;
}
-EXPORT_SYMBOL(pci_map_sg);
/* 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 pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
- int direction)
+static void pci32_unmap_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
struct scatterlist *sg;
int n;
- BUG_ON(direction == PCI_DMA_NONE);
- if (direction != PCI_DMA_TODEVICE) {
+ if (dir != PCI_DMA_TODEVICE) {
for_each_sg(sgl, sg, nents, n) {
BUG_ON(page_address(sg_page(sg)) == NULL);
mmu_inval_dma_area(
@@ -588,7 +572,6 @@ void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
}
}
}
-EXPORT_SYMBOL(pci_unmap_sg);
/* Make physical memory consistent for a single
* streaming mode DMA translation before or after a transfer.
@@ -600,25 +583,23 @@ EXPORT_SYMBOL(pci_unmap_sg);
* must first perform a pci_dma_sync_for_device, and then the
* device again owns the buffer.
*/
-void pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t ba, size_t size, int direction)
+static void pci32_sync_single_for_cpu(struct device *dev, dma_addr_t ba,
+ size_t size, enum dma_data_direction dir)
{
- BUG_ON(direction == PCI_DMA_NONE);
- if (direction != PCI_DMA_TODEVICE) {
+ if (dir != PCI_DMA_TODEVICE) {
mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
(size + PAGE_SIZE-1) & PAGE_MASK);
}
}
-EXPORT_SYMBOL(pci_dma_sync_single_for_cpu);
-void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t ba, size_t size, int direction)
+static void pci32_sync_single_for_device(struct device *dev, dma_addr_t ba,
+ size_t size, enum dma_data_direction dir)
{
- BUG_ON(direction == PCI_DMA_NONE);
- if (direction != PCI_DMA_TODEVICE) {
+ if (dir != PCI_DMA_TODEVICE) {
mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
(size + PAGE_SIZE-1) & PAGE_MASK);
}
}
-EXPORT_SYMBOL(pci_dma_sync_single_for_device);
/* Make physical memory consistent for a set of streaming
* mode DMA translations after a transfer.
@@ -626,13 +607,13 @@ EXPORT_SYMBOL(pci_dma_sync_single_for_device);
* The same as pci_dma_sync_single_* but for a scatter-gather list,
* same rules and usage.
*/
-void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
+static void pci32_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir)
{
struct scatterlist *sg;
int n;
- BUG_ON(direction == PCI_DMA_NONE);
- if (direction != PCI_DMA_TODEVICE) {
+ if (dir != PCI_DMA_TODEVICE) {
for_each_sg(sgl, sg, nents, n) {
BUG_ON(page_address(sg_page(sg)) == NULL);
mmu_inval_dma_area(
@@ -641,15 +622,14 @@ void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int
}
}
}
-EXPORT_SYMBOL(pci_dma_sync_sg_for_cpu);
-void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
+static void pci32_sync_sg_for_device(struct device *device, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir)
{
struct scatterlist *sg;
int n;
- BUG_ON(direction == PCI_DMA_NONE);
- if (direction != PCI_DMA_TODEVICE) {
+ if (dir != PCI_DMA_TODEVICE) {
for_each_sg(sgl, sg, nents, n) {
BUG_ON(page_address(sg_page(sg)) == NULL);
mmu_inval_dma_area(
@@ -658,9 +638,49 @@ void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl,
}
}
}
-EXPORT_SYMBOL(pci_dma_sync_sg_for_device);
+
+struct dma_map_ops pci32_dma_ops = {
+ .alloc_coherent = pci32_alloc_coherent,
+ .free_coherent = pci32_free_coherent,
+ .map_page = pci32_map_page,
+ .map_sg = pci32_map_sg,
+ .unmap_sg = pci32_unmap_sg,
+ .sync_single_for_cpu = pci32_sync_single_for_cpu,
+ .sync_single_for_device = pci32_sync_single_for_device,
+ .sync_sg_for_cpu = pci32_sync_sg_for_cpu,
+ .sync_sg_for_device = pci32_sync_sg_for_device,
+};
+EXPORT_SYMBOL(pci32_dma_ops);
+
#endif /* CONFIG_PCI */
+/*
+ * Return whether the given PCI device DMA address mask can be
+ * supported properly. For example, if your device can only drive the
+ * low 24-bits during PCI bus mastering, then you would pass
+ * 0x00ffffff as the mask to this function.
+ */
+int dma_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_PCI
+ if (dev->bus == &pci_bus_type)
+ return 1;
+#endif
+ return 0;
+}
+EXPORT_SYMBOL(dma_supported);
+
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+#ifdef CONFIG_PCI
+ if (dev->bus == &pci_bus_type)
+ return pci_set_dma_mask(to_pci_dev(dev), dma_mask);
+#endif
+ return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
+
#ifdef CONFIG_PROC_FS
static int
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 57859ad2354..c6864866280 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1039,7 +1039,7 @@ static void ali_sound_dma_hack(struct pci_dev *pdev, int set_bit)
pci_dev_put(ali_isa_bridge);
}
-int pci_dma_supported(struct pci_dev *pdev, u64 device_mask)
+int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask)
{
u64 dma_addr_mask;
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 2485eaa2310..23c33ff9c31 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -232,7 +232,8 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t sz,
- enum dma_data_direction direction)
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
struct iommu *iommu;
unsigned long flags, npages, oaddr;
@@ -296,7 +297,8 @@ iommu_map_fail:
}
static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
- size_t sz, enum dma_data_direction direction)
+ size_t sz, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
struct pci_pbm_info *pbm;
struct iommu *iommu;
@@ -336,7 +338,8 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
}
static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
- int nelems, enum dma_data_direction direction)
+ int nelems, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
struct scatterlist *s, *outs, *segstart;
unsigned long flags, handle, prot;
@@ -478,7 +481,8 @@ iommu_map_failed:
}
static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
- int nelems, enum dma_data_direction direction)
+ int nelems, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
struct pci_pbm_info *pbm;
struct scatterlist *sg;
@@ -521,29 +525,13 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
spin_unlock_irqrestore(&iommu->lock, flags);
}
-static void dma_4v_sync_single_for_cpu(struct device *dev,
- dma_addr_t bus_addr, size_t sz,
- enum dma_data_direction direction)
-{
- /* Nothing to do... */
-}
-
-static void dma_4v_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sglist, int nelems,
- enum dma_data_direction direction)
-{
- /* Nothing to do... */
-}
-
-static const struct dma_ops sun4v_dma_ops = {
+static struct dma_map_ops sun4v_dma_ops = {
.alloc_coherent = dma_4v_alloc_coherent,
.free_coherent = dma_4v_free_coherent,
.map_page = dma_4v_map_page,
.unmap_page = dma_4v_unmap_page,
.map_sg = dma_4v_map_sg,
.unmap_sg = dma_4v_unmap_sg,
- .sync_single_for_cpu = dma_4v_sync_single_for_cpu,
- .sync_sg_for_cpu = dma_4v_sync_sg_for_cpu,
};
static void __devinit pci_sun4v_scan_bus(struct pci_pbm_info *pbm,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 13ffa5df37d..1d9c18aa17e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -586,7 +586,6 @@ config GART_IOMMU
bool "GART IOMMU support" if EMBEDDED
default y
select SWIOTLB
- select AGP
depends on X86_64 && PCI
---help---
Support for full DMA access of devices with 32bit memory access only
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index bdf96f119f0..ac95995b7ba 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -25,6 +25,7 @@
#ifdef CONFIG_AMD_IOMMU
extern int amd_iommu_init(void);
extern int amd_iommu_init_dma_ops(void);
+extern int amd_iommu_init_passthrough(void);
extern void amd_iommu_detect(void);
extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
extern void amd_iommu_flush_all_domains(void);
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 0c878caaa0a..2a2cc7a78a8 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -143,22 +143,29 @@
#define EVT_BUFFER_SIZE 8192 /* 512 entries */
#define EVT_LEN_MASK (0x9ULL << 56)
+#define PAGE_MODE_NONE 0x00
#define PAGE_MODE_1_LEVEL 0x01
#define PAGE_MODE_2_LEVEL 0x02
#define PAGE_MODE_3_LEVEL 0x03
-
-#define IOMMU_PDE_NL_0 0x000ULL
-#define IOMMU_PDE_NL_1 0x200ULL
-#define IOMMU_PDE_NL_2 0x400ULL
-#define IOMMU_PDE_NL_3 0x600ULL
-
-#define IOMMU_PTE_L2_INDEX(address) (((address) >> 30) & 0x1ffULL)
-#define IOMMU_PTE_L1_INDEX(address) (((address) >> 21) & 0x1ffULL)
-#define IOMMU_PTE_L0_INDEX(address) (((address) >> 12) & 0x1ffULL)
-
-#define IOMMU_MAP_SIZE_L1 (1ULL << 21)
-#define IOMMU_MAP_SIZE_L2 (1ULL << 30)
-#define IOMMU_MAP_SIZE_L3 (1ULL << 39)
+#define PAGE_MODE_4_LEVEL 0x04
+#define PAGE_MODE_5_LEVEL 0x05
+#define PAGE_MODE_6_LEVEL 0x06
+
+#define PM_LEVEL_SHIFT(x) (12 + ((x) * 9))
+#define PM_LEVEL_SIZE(x) (((x) < 6) ? \
+ ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \
+ (0xffffffffffffffffULL))
+#define PM_LEVEL_INDEX(x, a) (((a) >> PM_LEVEL_SHIFT((x))) & 0x1ffULL)
+#define PM_LEVEL_ENC(x) (((x) << 9) & 0xe00ULL)
+#define PM_LEVEL_PDE(x, a) ((a) | PM_LEVEL_ENC((x)) | \
+ IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
+#define PM_PTE_LEVEL(pte) (((pte) >> 9) & 0x7ULL)
+
+#define PM_MAP_4k 0
+#define PM_ADDR_MASK 0x000ffffffffff000ULL
+#define PM_MAP_MASK(lvl) (PM_ADDR_MASK & \
+ (~((1ULL << (12 + ((lvl) * 9))) - 1)))
+#define PM_ALIGNED(lvl, addr) ((PM_MAP_MASK(lvl) & (addr)) == (addr))
#define IOMMU_PTE_P (1ULL << 0)
#define IOMMU_PTE_TV (1ULL << 1)
@@ -167,11 +174,6 @@
#define IOMMU_PTE_IR (1ULL << 61)
#define IOMMU_PTE_IW (1ULL << 62)
-#define IOMMU_L1_PDE(address) \
- ((address) | IOMMU_PDE_NL_1 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
-#define IOMMU_L2_PDE(address) \
- ((address) | IOMMU_PDE_NL_2 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
-
#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
@@ -194,11 +196,14 @@
#define PD_DMA_OPS_MASK (1UL << 0) /* domain used for dma_ops */
#define PD_DEFAULT_MASK (1UL << 1) /* domain is a default dma_ops
domain for an IOMMU */
+#define PD_PASSTHROUGH_MASK (1UL << 2) /* domain has no page
+ translation */
+
extern bool amd_iommu_dump;
#define DUMP_printk(format, arg...) \
do { \
if (amd_iommu_dump) \
- printk(KERN_INFO "AMD IOMMU: " format, ## arg); \
+ printk(KERN_INFO "AMD-Vi: " format, ## arg); \
} while(0);
/*
@@ -226,6 +231,7 @@ struct protection_domain {
int mode; /* paging mode (0-6 levels) */
u64 *pt_root; /* page table root pointer */
unsigned long flags; /* flags to find out type of domain */
+ bool updated; /* complete domain flush required */
unsigned dev_cnt; /* devices assigned to this domain */
void *priv; /* private data */
};
@@ -337,6 +343,9 @@ struct amd_iommu {
/* if one, we need to send a completion wait command */
bool need_sync;
+ /* becomes true if a command buffer reset is running */
+ bool reset_in_progress;
+
/* default dma_ops domain for that IOMMU */
struct dma_ops_domain *default_dom;
};
@@ -457,4 +466,7 @@ static inline void amd_iommu_stats_init(void) { }
#endif /* CONFIG_AMD_IOMMU_STATS */
+/* some function prototypes */
+extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
+
#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 1c3f9435f1c..0ee770d23d0 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -55,6 +55,24 @@ extern int dma_set_mask(struct device *dev, u64 mask);
extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag);
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+ if (!dev->dma_mask)
+ return 0;
+
+ return addr + size <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ return paddr;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+ return daddr;
+}
+
static inline void
dma_cache_sync(struct device *dev, void *vaddr, size_t size,
enum dma_data_direction dir)
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 6c99f503780..98f230f6a28 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -41,9 +41,13 @@ static DEFINE_RWLOCK(amd_iommu_devtable_lock);
static LIST_HEAD(iommu_pd_list);
static DEFINE_SPINLOCK(iommu_pd_list_lock);
-#ifdef CONFIG_IOMMU_API
+/*
+ * Domain for untranslated devices - only allocated
+ * if iommu=pt passed on kernel cmd line.
+ */
+static struct protection_domain *pt_domain;
+
static struct iommu_ops amd_iommu_ops;
-#endif
/*
* general struct to manage commands send to an IOMMU
@@ -55,16 +59,16 @@ struct iommu_cmd {
static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
struct unity_map_entry *e);
static struct dma_ops_domain *find_protection_domain(u16 devid);
-static u64* alloc_pte(struct protection_domain *dom,
- unsigned long address, u64
- **pte_page, gfp_t gfp);
+static u64 *alloc_pte(struct protection_domain *domain,
+ unsigned long address, int end_lvl,
+ u64 **pte_page, gfp_t gfp);
static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
unsigned long start_page,
unsigned int pages);
-
-#ifndef BUS_NOTIFY_UNBOUND_DRIVER
-#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
-#endif
+static void reset_iommu_command_buffer(struct amd_iommu *iommu);
+static u64 *fetch_pte(struct protection_domain *domain,
+ unsigned long address, int map_size);
+static void update_domain(struct protection_domain *domain);
#ifdef CONFIG_AMD_IOMMU_STATS
@@ -138,7 +142,25 @@ static int iommu_has_npcache(struct amd_iommu *iommu)
*
****************************************************************************/
-static void iommu_print_event(void *__evt)
+static void dump_dte_entry(u16 devid)
+{
+ int i;
+
+ for (i = 0; i < 8; ++i)
+ pr_err("AMD-Vi: DTE[%d]: %08x\n", i,
+ amd_iommu_dev_table[devid].data[i]);
+}
+
+static void dump_command(unsigned long phys_addr)
+{
+ struct iommu_cmd *cmd = phys_to_virt(phys_addr);
+ int i;
+
+ for (i = 0; i < 4; ++i)
+ pr_err("AMD-Vi: CMD[%d]: %08x\n", i, cmd->data[i]);
+}
+
+static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
{
u32 *event = __evt;
int type = (event[1] >> EVENT_TYPE_SHIFT) & EVENT_TYPE_MASK;
@@ -147,7 +169,7 @@ static void iommu_print_event(void *__evt)
int flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
u64 address = (u64)(((u64)event[3]) << 32) | event[2];
- printk(KERN_ERR "AMD IOMMU: Event logged [");
+ printk(KERN_ERR "AMD-Vi: Event logged [");
switch (type) {
case EVENT_TYPE_ILL_DEV:
@@ -155,6 +177,7 @@ static void iommu_print_event(void *__evt)
"address=0x%016llx flags=0x%04x]\n",
PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid),
address, flags);
+ dump_dte_entry(devid);
break;
case EVENT_TYPE_IO_FAULT:
printk("IO_PAGE_FAULT device=%02x:%02x.%x "
@@ -176,6 +199,8 @@ static void iommu_print_event(void *__evt)
break;
case EVENT_TYPE_ILL_CMD:
printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
+ reset_iommu_command_buffer(iommu);
+ dump_command(address);
break;
case EVENT_TYPE_CMD_HARD_ERR:
printk("COMMAND_HARDWARE_ERROR address=0x%016llx "
@@ -209,7 +234,7 @@ static void iommu_poll_events(struct amd_iommu *iommu)
tail = readl(iommu->mmio_base + MMIO_EVT_TAIL_OFFSET);
while (head != tail) {
- iommu_print_event(iommu->evt_buf + head);
+ iommu_print_event(iommu, iommu->evt_buf + head);
head = (head + EVENT_ENTRY_SIZE) % iommu->evt_buf_size;
}
@@ -296,8 +321,11 @@ static void __iommu_wait_for_completion(struct amd_iommu *iommu)
status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
- if (unlikely(i == EXIT_LOOP_COUNT))
- panic("AMD IOMMU: Completion wait loop failed\n");
+ if (unlikely(i == EXIT_LOOP_COUNT)) {
+ spin_unlock(&iommu->lock);
+ reset_iommu_command_buffer(iommu);
+ spin_lock(&iommu->lock);
+ }
}
/*
@@ -445,47 +473,78 @@ static void iommu_flush_tlb_pde(struct amd_iommu *iommu, u16 domid)
}
/*
+ * This function flushes one domain on one IOMMU
+ */
+static void flush_domain_on_iommu(struct amd_iommu *iommu, u16 domid)
+{
+ struct iommu_cmd cmd;
+ unsigned long flags;
+
+ __iommu_build_inv_iommu_pages(&cmd, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+ domid, 1, 1);
+
+ spin_lock_irqsave(&iommu->lock, flags);
+ __iommu_queue_command(iommu, &cmd);
+ __iommu_completion_wait(iommu);
+ __iommu_wait_for_completion(iommu);
+ spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static void flush_all_domains_on_iommu(struct amd_iommu *iommu)
+{
+ int i;
+
+ for (i = 1; i < MAX_DOMAIN_ID; ++i) {
+ if (!test_bit(i, amd_iommu_pd_alloc_bitmap))
+ continue;
+ flush_domain_on_iommu(iommu, i);
+ }
+
+}
+
+/*
* This function is used to flush the IO/TLB for a given protection domain
* on every IOMMU in the system
*/
static void iommu_flush_domain(u16 domid)
{
- unsigned long flags;
struct amd_iommu *iommu;
- struct iommu_cmd cmd;
INC_STATS_COUNTER(domain_flush_all);
- __iommu_build_inv_iommu_pages(&cmd, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
- domid, 1, 1);
-
- for_each_iommu(iommu) {
- spin_lock_irqsave(&iommu->lock, flags);
- __iommu_queue_command(iommu, &cmd);
- __iommu_completion_wait(iommu);
- __iommu_wait_for_completion(iommu);
- spin_unlock_irqrestore(&iommu->lock, flags);
- }
+ for_each_iommu(iommu)
+ flush_domain_on_iommu(iommu, domid);
}
void amd_iommu_flush_all_domains(void)
{
+ struct amd_iommu *iommu;
+
+ for_each_iommu(iommu)
+ flush_all_domains_on_iommu(iommu);
+}
+
+static void flush_all_devices_for_iommu(struct amd_iommu *iommu)
+{
int i;
- for (i = 1; i < MAX_DOMAIN_ID; ++i) {
- if (!test_bit(i, amd_iommu_pd_alloc_bitmap))
+ for (i = 0; i <= amd_iommu_last_bdf; ++i) {
+ if (iommu != amd_iommu_rlookup_table[i])
continue;
- iommu_flush_domain(i);
+
+ iommu_queue_inv_dev_entry(iommu, i);
+ iommu_completion_wait(iommu);
}
}
-void amd_iommu_flush_all_devices(void)
+static void flush_devices_by_domain(struct protection_domain *domain)
{
struct amd_iommu *iommu;
int i;
for (i = 0; i <= amd_iommu_last_bdf; ++i) {
- if (amd_iommu_pd_table[i] == NULL)
+ if ((domain == NULL && amd_iommu_pd_table[i] == NULL) ||
+ (amd_iommu_pd_table[i] != domain))
continue;
iommu = amd_iommu_rlookup_table[i];
@@ -497,6 +556,27 @@ void amd_iommu_flush_all_devices(void)
}
}
+static void reset_iommu_command_buffer(struct amd_iommu *iommu)
+{
+ pr_err("AMD-Vi: Resetting IOMMU command buffer\n");
+
+ if (iommu->reset_in_progress)
+ panic("AMD-Vi: ILLEGAL_COMMAND_ERROR while resetting command buffer\n");
+
+ iommu->reset_in_progress = true;
+
+ amd_iommu_reset_cmd_buffer(iommu);
+ flush_all_devices_for_iommu(iommu);
+ flush_all_domains_on_iommu(iommu);
+
+ iommu->reset_in_progress = false;
+}
+
+void amd_iommu_flush_all_devices(void)
+{
+ flush_devices_by_domain(NULL);
+}
+
/****************************************************************************
*
* The functions below are used the create the page table mappings for
@@ -514,18 +594,21 @@ void amd_iommu_flush_all_devices(void)
static int iommu_map_page(struct protection_domain *dom,
unsigned long bus_addr,
unsigned long phys_addr,
- int prot)
+ int prot,
+ int map_size)
{
u64 __pte, *pte;
bus_addr = PAGE_ALIGN(bus_addr);
phys_addr = PAGE_ALIGN(phys_addr);
- /* only support 512GB address spaces for now */
- if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
+ BUG_ON(!PM_ALIGNED(map_size, bus_addr));
+ BUG_ON(!PM_ALIGNED(map_size, phys_addr));
+
+ if (!(prot & IOMMU_PROT_MASK))
return -EINVAL;
- pte = alloc_pte(dom, bus_addr, NULL, GFP_KERNEL);
+ pte = alloc_pte(dom, bus_addr, map_size, NULL, GFP_KERNEL);
if (IOMMU_PTE_PRESENT(*pte))
return -EBUSY;
@@ -538,29 +621,18 @@ static int iommu_map_page(struct protection_domain *dom,
*pte = __pte;
+ update_domain(dom);
+
return 0;
}
static void iommu_unmap_page(struct protection_domain *dom,
- unsigned long bus_addr)
+ unsigned long bus_addr, int map_size)
{
- u64 *pte;
-
- pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(bus_addr)];
-
- if (!IOMMU_PTE_PRESENT(*pte))
- return;
-
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)];
+ u64 *pte = fetch_pte(dom, bus_addr, map_size);
- if (!IOMMU_PTE_PRESENT(*pte))
- return;
-
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)];
-
- *pte = 0;
+ if (pte)
+ *pte = 0;
}
/*
@@ -615,7 +687,8 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
for (addr = e->address_start; addr < e->address_end;
addr += PAGE_SIZE) {
- ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot);
+ ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot,
+ PM_MAP_4k);
if (ret)
return ret;
/*
@@ -670,24 +743,29 @@ static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
* This function checks if there is a PTE for a given dma address. If
* there is one, it returns the pointer to it.
*/
-static u64* fetch_pte(struct protection_domain *domain,
- unsigned long address)
+static u64 *fetch_pte(struct protection_domain *domain,
+ unsigned long address, int map_size)
{
+ int level;
u64 *pte;
- pte = &domain->pt_root[IOMMU_PTE_L2_INDEX(address)];
+ level = domain->mode - 1;
+ pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
- if (!IOMMU_PTE_PRESENT(*pte))
- return NULL;
+ while (level > map_size) {
+ if (!IOMMU_PTE_PRESENT(*pte))
+ return NULL;
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+ level -= 1;
- if (!IOMMU_PTE_PRESENT(*pte))
- return NULL;
+ pte = IOMMU_PTE_PAGE(*pte);
+ pte = &pte[PM_LEVEL_INDEX(level, address)];
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+ if ((PM_PTE_LEVEL(*pte) == 0) && level != map_size) {
+ pte = NULL;
+ break;
+ }
+ }
return pte;
}
@@ -727,7 +805,7 @@ static int alloc_new_range(struct amd_iommu *iommu,
u64 *pte, *pte_page;
for (i = 0; i < num_ptes; ++i) {
- pte = alloc_pte(&dma_dom->domain, address,
+ pte = alloc_pte(&dma_dom->domain, address, PM_MAP_4k,
&pte_page, gfp);
if (!pte)
goto out_free;
@@ -760,16 +838,20 @@ static int alloc_new_range(struct amd_iommu *iommu,
for (i = dma_dom->aperture[index]->offset;
i < dma_dom->aperture_size;
i += PAGE_SIZE) {
- u64 *pte = fetch_pte(&dma_dom->domain, i);
+ u64 *pte = fetch_pte(&dma_dom->domain, i, PM_MAP_4k);
if (!pte || !IOMMU_PTE_PRESENT(*pte))
continue;
dma_ops_reserve_addresses(dma_dom, i << PAGE_SHIFT, 1);
}
+ update_domain(&dma_dom->domain);
+
return 0;
out_free:
+ update_domain(&dma_dom->domain);
+
free_page((unsigned long)dma_dom->aperture[index]->bitmap);
kfree(dma_dom->aperture[index]);
@@ -1009,7 +1091,7 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu)
dma_dom->domain.id = domain_id_alloc();
if (dma_dom->domain.id == 0)
goto free_dma_dom;
- dma_dom->domain.mode = PAGE_MODE_3_LEVEL;
+ dma_dom->domain.mode = PAGE_MODE_2_LEVEL;
dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
dma_dom->domain.flags = PD_DMA_OPS_MASK;
dma_dom->domain.priv = dma_dom;
@@ -1063,6 +1145,41 @@ static struct protection_domain *domain_for_device(u16 devid)
return dom;
}
+static void set_dte_entry(u16 devid, struct protection_domain *domain)
+{
+ u64 pte_root = virt_to_phys(domain->pt_root);
+
+ pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
+ << DEV_ENTRY_MODE_SHIFT;
+ pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
+
+ amd_iommu_dev_table[devid].data[2] = domain->id;
+ amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
+ amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
+
+ amd_iommu_pd_table[devid] = domain;
+}
+
+/*
+ * If a device is not yet associated with a domain, this function does
+ * assigns it visible for the hardware
+ */
+static void __attach_device(struct amd_iommu *iommu,
+ struct protection_domain *domain,
+ u16 devid)
+{
+ /* lock domain */
+ spin_lock(&domain->lock);
+
+ /* update DTE entry */
+ set_dte_entry(devid, domain);
+
+ domain->dev_cnt += 1;
+
+ /* ready */
+ spin_unlock(&domain->lock);
+}
+
/*
* If a device is not yet associated with a domain, this function does
* assigns it visible for the hardware
@@ -1072,27 +1189,16 @@ static void attach_device(struct amd_iommu *iommu,
u16 devid)
{
unsigned long flags;
- u64 pte_root = virt_to_phys(domain->pt_root);
-
- domain->dev_cnt += 1;
-
- pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
- << DEV_ENTRY_MODE_SHIFT;
- pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
write_lock_irqsave(&amd_iommu_devtable_lock, flags);
- amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
- amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
- amd_iommu_dev_table[devid].data[2] = domain->id;
-
- amd_iommu_pd_table[devid] = domain;
+ __attach_device(iommu, domain, devid);
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
- /*
- * We might boot into a crash-kernel here. The crashed kernel
- * left the caches in the IOMMU dirty. So we have to flush
- * here to evict all dirty stuff.
- */
+ /*
+ * We might boot into a crash-kernel here. The crashed kernel
+ * left the caches in the IOMMU dirty. So we have to flush
+ * here to evict all dirty stuff.
+ */
iommu_queue_inv_dev_entry(iommu, devid);
iommu_flush_tlb_pde(iommu, domain->id);
}
@@ -1119,6 +1225,15 @@ static void __detach_device(struct protection_domain *domain, u16 devid)
/* ready */
spin_unlock(&domain->lock);
+
+ /*
+ * If we run in passthrough mode the device must be assigned to the
+ * passthrough domain if it is detached from any other domain
+ */
+ if (iommu_pass_through) {
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+ __attach_device(iommu, pt_domain, devid);
+ }
}
/*
@@ -1164,6 +1279,8 @@ static int device_change_notifier(struct notifier_block *nb,
case BUS_NOTIFY_UNBOUND_DRIVER:
if (!domain)
goto out;
+ if (iommu_pass_through)
+ break;
detach_device(domain, devid);
break;
case BUS_NOTIFY_ADD_DEVICE:
@@ -1292,39 +1409,91 @@ static int get_device_resources(struct device *dev,
return 1;
}
+static void update_device_table(struct protection_domain *domain)
+{
+ unsigned long flags;
+ int i;
+
+ for (i = 0; i <= amd_iommu_last_bdf; ++i) {
+ if (amd_iommu_pd_table[i] != domain)
+ continue;
+ write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ set_dte_entry(i, domain);
+ write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ }
+}
+
+static void update_domain(struct protection_domain *domain)
+{
+ if (!domain->updated)
+ return;
+
+ update_device_table(domain);
+ flush_devices_by_domain(domain);
+ iommu_flush_domain(domain->id);
+
+ domain->updated = false;
+}
+
/*
- * If the pte_page is not yet allocated this function is called
+ * This function is used to add another level to an IO page table. Adding
+ * another level increases the size of the address space by 9 bits to a size up
+ * to 64 bits.
*/
-static u64* alloc_pte(struct protection_domain *dom,
- unsigned long address, u64 **pte_page, gfp_t gfp)
+static bool increase_address_space(struct protection_domain *domain,
+ gfp_t gfp)
+{
+ u64 *pte;
+
+ if (domain->mode == PAGE_MODE_6_LEVEL)
+ /* address space already 64 bit large */
+ return false;
+
+ pte = (void *)get_zeroed_page(gfp);
+ if (!pte)
+ return false;
+
+ *pte = PM_LEVEL_PDE(domain->mode,
+ virt_to_phys(domain->pt_root));
+ domain->pt_root = pte;
+ domain->mode += 1;
+ domain->updated = true;
+
+ return true;
+}
+
+static u64 *alloc_pte(struct protection_domain *domain,
+ unsigned long address,
+ int end_lvl,
+ u64 **pte_page,
+ gfp_t gfp)
{
u64 *pte, *page;
+ int level;
- pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(address)];
+ while (address > PM_LEVEL_SIZE(domain->mode))
+ increase_address_space(domain, gfp);
- if (!IOMMU_PTE_PRESENT(*pte)) {
- page = (u64 *)get_zeroed_page(gfp);
- if (!page)
- return NULL;
- *pte = IOMMU_L2_PDE(virt_to_phys(page));
- }
+ level = domain->mode - 1;
+ pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+ while (level > end_lvl) {
+ if (!IOMMU_PTE_PRESENT(*pte)) {
+ page = (u64 *)get_zeroed_page(gfp);
+ if (!page)
+ return NULL;
+ *pte = PM_LEVEL_PDE(level, virt_to_phys(page));
+ }
- if (!IOMMU_PTE_PRESENT(*pte)) {
- page = (u64 *)get_zeroed_page(gfp);
- if (!page)
- return NULL;
- *pte = IOMMU_L1_PDE(virt_to_phys(page));
- }
+ level -= 1;
- pte = IOMMU_PTE_PAGE(*pte);
+ pte = IOMMU_PTE_PAGE(*pte);
- if (pte_page)
- *pte_page = pte;
+ if (pte_page && level == end_lvl)
+ *pte_page = pte;
- pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+ pte = &pte[PM_LEVEL_INDEX(level, address)];
+ }
return pte;
}
@@ -1344,10 +1513,13 @@ static u64* dma_ops_get_pte(struct dma_ops_domain *dom,
pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
if (!pte) {
- pte = alloc_pte(&dom->domain, address, &pte_page, GFP_ATOMIC);
+ pte = alloc_pte(&dom->domain, address, PM_MAP_4k, &pte_page,
+ GFP_ATOMIC);
aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page;
} else
- pte += IOMMU_PTE_L0_INDEX(address);
+ pte += PM_LEVEL_INDEX(0, address);
+
+ update_domain(&dom->domain);
return pte;
}
@@ -1409,7 +1581,7 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
if (!pte)
return;
- pte += IOMMU_PTE_L0_INDEX(address);
+ pte += PM_LEVEL_INDEX(0, address);
WARN_ON(!*pte);
@@ -1988,19 +2160,47 @@ static void cleanup_domain(struct protection_domain *domain)
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
}
-static int amd_iommu_domain_init(struct iommu_domain *dom)
+static void protection_domain_free(struct protection_domain *domain)
+{
+ if (!domain)
+ return;
+
+ if (domain->id)
+ domain_id_free(domain->id);
+
+ kfree(domain);
+}
+
+static struct protection_domain *protection_domain_alloc(void)
{
struct protection_domain *domain;
domain = kzalloc(sizeof(*domain), GFP_KERNEL);
if (!domain)
- return -ENOMEM;
+ return NULL;
spin_lock_init(&domain->lock);
- domain->mode = PAGE_MODE_3_LEVEL;
domain->id = domain_id_alloc();
if (!domain->id)
+ goto out_err;
+
+ return domain;
+
+out_err:
+ kfree(domain);
+
+ return NULL;
+}
+
+static int amd_iommu_domain_init(struct iommu_domain *dom)
+{
+ struct protection_domain *domain;
+
+ domain = protection_domain_alloc();
+ if (!domain)
goto out_free;
+
+ domain->mode = PAGE_MODE_3_LEVEL;
domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
if (!domain->pt_root)
goto out_free;
@@ -2010,7 +2210,7 @@ static int amd_iommu_domain_init(struct iommu_domain *dom)
return 0;
out_free:
- kfree(domain);
+ protection_domain_free(domain);
return -ENOMEM;
}
@@ -2115,7 +2315,7 @@ static int amd_iommu_map_range(struct iommu_domain *dom,
paddr &= PAGE_MASK;
for (i = 0; i < npages; ++i) {
- ret = iommu_map_page(domain, iova, paddr, prot);
+ ret = iommu_map_page(domain, iova, paddr, prot, PM_MAP_4k);
if (ret)
return ret;
@@ -2136,7 +2336,7 @@ static void amd_iommu_unmap_range(struct iommu_domain *dom,
iova &= PAGE_MASK;
for (i = 0; i < npages; ++i) {
- iommu_unmap_page(domain, iova);
+ iommu_unmap_page(domain, iova, PM_MAP_4k);
iova += PAGE_SIZE;
}
@@ -2151,21 +2351,9 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
phys_addr_t paddr;
u64 *pte;
- pte = &domain->pt_root[IOMMU_PTE_L2_INDEX(iova)];
-
- if (!IOMMU_PTE_PRESENT(*pte))
- return 0;
-
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L1_INDEX(iova)];
-
- if (!IOMMU_PTE_PRESENT(*pte))
- return 0;
-
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L0_INDEX(iova)];
+ pte = fetch_pte(domain, iova, PM_MAP_4k);
- if (!IOMMU_PTE_PRESENT(*pte))
+ if (!pte || !IOMMU_PTE_PRESENT(*pte))
return 0;
paddr = *pte & IOMMU_PAGE_MASK;
@@ -2191,3 +2379,46 @@ static struct iommu_ops amd_iommu_ops = {
.domain_has_cap = amd_iommu_domain_has_cap,
};
+/*****************************************************************************
+ *
+ * The next functions do a basic initialization of IOMMU for pass through
+ * mode
+ *
+ * In passthrough mode the IOMMU is initialized and enabled but not used for
+ * DMA-API translation.
+ *
+ *****************************************************************************/
+
+int __init amd_iommu_init_passthrough(void)
+{
+ struct pci_dev *dev = NULL;
+ u16 devid, devid2;
+
+ /* allocate passthroug domain */
+ pt_domain = protection_domain_alloc();
+ if (!pt_domain)
+ return -ENOMEM;
+
+ pt_domain->mode |= PAGE_MODE_NONE;
+
+ while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+ struct amd_iommu *iommu;
+
+ devid = calc_devid(dev->bus->number, dev->devfn);
+ if (devid > amd_iommu_last_bdf)
+ continue;
+
+ devid2 = amd_iommu_alias_table[devid];
+
+ iommu = amd_iommu_rlookup_table[devid2];
+ if (!iommu)
+ continue;
+
+ __attach_device(iommu, pt_domain, devid);
+ __attach_device(iommu, pt_domain, devid2);
+ }
+
+ pr_info("AMD-Vi: Initialized for Passthrough Mode\n");
+
+ return 0;
+}
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index c1b17e97252..b4b61d462dc 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -252,7 +252,7 @@ static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
/* Function to enable the hardware */
static void iommu_enable(struct amd_iommu *iommu)
{
- printk(KERN_INFO "AMD IOMMU: Enabling IOMMU at %s cap 0x%hx\n",
+ printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx\n",
dev_name(&iommu->dev->dev), iommu->cap_ptr);
iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
@@ -435,6 +435,20 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
}
/*
+ * This function resets the command buffer if the IOMMU stopped fetching
+ * commands from it.
+ */
+void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu)
+{
+ iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
+
+ writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+ writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
+ iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
+}
+
+/*
* This function writes the command buffer address to the hardware and
* enables it.
*/
@@ -450,11 +464,7 @@ static void iommu_enable_command_buffer(struct amd_iommu *iommu)
memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
&entry, sizeof(entry));
- /* set head and tail to zero manually */
- writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
- writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
-
- iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
+ amd_iommu_reset_cmd_buffer(iommu);
}
static void __init free_command_buffer(struct amd_iommu *iommu)
@@ -858,7 +868,7 @@ static int __init init_iommu_all(struct acpi_table_header *table)
switch (*p) {
case ACPI_IVHD_TYPE:
- DUMP_printk("IOMMU: device: %02x:%02x.%01x cap: %04x "
+ DUMP_printk("device: %02x:%02x.%01x cap: %04x "
"seg: %d flags: %01x info %04x\n",
PCI_BUS(h->devid), PCI_SLOT(h->devid),
PCI_FUNC(h->devid), h->cap_ptr,
@@ -902,7 +912,7 @@ static int __init iommu_setup_msi(struct amd_iommu *iommu)
r = request_irq(iommu->dev->irq, amd_iommu_int_handler,
IRQF_SAMPLE_RANDOM,
- "AMD IOMMU",
+ "AMD-Vi",
NULL);
if (r) {
@@ -1150,7 +1160,7 @@ int __init amd_iommu_init(void)
if (no_iommu) {
- printk(KERN_INFO "AMD IOMMU disabled by kernel command line\n");
+ printk(KERN_INFO "AMD-Vi disabled by kernel command line\n");
return 0;
}
@@ -1242,22 +1252,28 @@ int __init amd_iommu_init(void)
if (ret)
goto free;
- ret = amd_iommu_init_dma_ops();
+ if (iommu_pass_through)
+ ret = amd_iommu_init_passthrough();
+ else
+ ret = amd_iommu_init_dma_ops();
if (ret)
goto free;
enable_iommus();
- printk(KERN_INFO "AMD IOMMU: device isolation ");
+ if (iommu_pass_through)
+ goto out;
+
+ printk(KERN_INFO "AMD-Vi: device isolation ");
if (amd_iommu_isolate)
printk("enabled\n");
else
printk("disabled\n");
if (amd_iommu_unmap_flush)
- printk(KERN_INFO "AMD IOMMU: IO/TLB flush on unmap enabled\n");
+ printk(KERN_INFO "AMD-Vi: IO/TLB flush on unmap enabled\n");
else
- printk(KERN_INFO "AMD IOMMU: Lazy IO/TLB flushing enabled\n");
+ printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n");
out:
return ret;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index fa80f60e960..d71c8655905 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -33,7 +33,14 @@ int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
-int iommu_pass_through;
+/*
+ * This variable becomes 1 if iommu=pt is passed on the kernel command line.
+ * If this variable is 1, IOMMU implementations do no DMA ranslation for
+ * devices and allow every device to access to whole physical memory. This is
+ * useful if a user want to use an IOMMU only for KVM device assignment to
+ * guests and not for driver dma translation.
+ */
+int iommu_pass_through __read_mostly;
dma_addr_t bad_dma_address __read_mostly = 0;
EXPORT_SYMBOL(bad_dma_address);
@@ -153,7 +160,7 @@ again:
return NULL;
addr = page_to_phys(page);
- if (!is_buffer_dma_capable(dma_mask, addr, size)) {
+ if (addr + size > dma_mask) {
__free_pages(page, get_order(size));
if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index d2e56b8f48e..98a827ee9ed 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -190,14 +190,13 @@ static void iommu_full(struct device *dev, size_t size, int dir)
static inline int
need_iommu(struct device *dev, unsigned long addr, size_t size)
{
- return force_iommu ||
- !is_buffer_dma_capable(*dev->dma_mask, addr, size);
+ return force_iommu || !dma_capable(dev, addr, size);
}
static inline int
nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
{
- return !is_buffer_dma_capable(*dev->dma_mask, addr, size);
+ return !dma_capable(dev, addr, size);
}
/* Map a single continuous physical area into the IOMMU.
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 71d412a09f3..a3933d4330c 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -14,7 +14,7 @@
static int
check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
{
- if (hwdev && !is_buffer_dma_capable(*hwdev->dma_mask, bus, size)) {
+ if (hwdev && !dma_capable(hwdev, bus, size)) {
if (*hwdev->dma_mask >= DMA_BIT_MASK(32))
printk(KERN_ERR
"nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
@@ -79,12 +79,29 @@ static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
free_pages((unsigned long)vaddr, get_order(size));
}
+static void nommu_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size,
+ enum dma_data_direction dir)
+{
+ flush_write_buffers();
+}
+
+
+static void nommu_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sg, int nelems,
+ enum dma_data_direction dir)
+{
+ flush_write_buffers();
+}
+
struct dma_map_ops nommu_dma_ops = {
- .alloc_coherent = dma_generic_alloc_coherent,
- .free_coherent = nommu_free_coherent,
- .map_sg = nommu_map_sg,
- .map_page = nommu_map_page,
- .is_phys = 1,
+ .alloc_coherent = dma_generic_alloc_coherent,
+ .free_coherent = nommu_free_coherent,
+ .map_sg = nommu_map_sg,
+ .map_page = nommu_map_page,
+ .sync_single_for_device = nommu_sync_single_for_device,
+ .sync_sg_for_device = nommu_sync_sg_for_device,
+ .is_phys = 1,
};
void __init no_iommu_init(void)
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 6af96ee4420..e8a35016115 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -13,31 +13,6 @@
int swiotlb __read_mostly;
-void * __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
-{
- return alloc_bootmem_low_pages(size);
-}
-
-void *swiotlb_alloc(unsigned order, unsigned long nslabs)
-{
- return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
-}
-
-dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
- return paddr;
-}
-
-phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-{
- return baddr;
-}
-
-int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
-{
- return 0;
-}
-
static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags)
{
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index 5406a601185..e694263445f 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -103,7 +103,6 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
if (ops->sync_single_for_cpu)
ops->sync_single_for_cpu(dev, addr, size, dir);
debug_dma_sync_single_for_cpu(dev, addr, size, dir);
- flush_write_buffers();
}
static inline void dma_sync_single_for_device(struct device *dev,
@@ -116,7 +115,6 @@ static inline void dma_sync_single_for_device(struct device *dev,
if (ops->sync_single_for_device)
ops->sync_single_for_device(dev, addr, size, dir);
debug_dma_sync_single_for_device(dev, addr, size, dir);
- flush_write_buffers();
}
static inline void dma_sync_single_range_for_cpu(struct device *dev,
@@ -132,7 +130,6 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
ops->sync_single_range_for_cpu(dev, addr, offset, size, dir);
debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
- flush_write_buffers();
} else
dma_sync_single_for_cpu(dev, addr, size, dir);
}
@@ -150,7 +147,6 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
ops->sync_single_range_for_device(dev, addr, offset, size, dir);
debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
- flush_write_buffers();
} else
dma_sync_single_for_device(dev, addr, size, dir);
}
@@ -165,7 +161,6 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
if (ops->sync_sg_for_cpu)
ops->sync_sg_for_cpu(dev, sg, nelems, dir);
debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
- flush_write_buffers();
}
static inline void
@@ -179,7 +174,6 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
ops->sync_sg_for_device(dev, sg, nelems, dir);
debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
- flush_write_buffers();
}
#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 07dfd460d28..c0f6c3cd788 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -98,11 +98,6 @@ static inline int is_device_dma_capable(struct device *dev)
return dev->dma_mask != NULL && *dev->dma_mask != DMA_MASK_NONE;
}
-static inline int is_buffer_dma_capable(u64 mask, dma_addr_t addr, size_t size)
-{
- return addr + size <= mask;
-}
-
#ifdef CONFIG_HAS_DMA
#include <asm/dma-mapping.h>
#else
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index cb1a6631b8f..73b1f1cec42 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -14,7 +14,6 @@ struct scatterlist;
*/
#define IO_TLB_SEGSIZE 128
-
/*
* log of the size of each IO TLB slab. The number of slabs is command line
* controllable.
@@ -24,16 +23,6 @@ struct scatterlist;
extern void
swiotlb_init(void);
-extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs);
-extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
-
-extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev,
- phys_addr_t address);
-extern phys_addr_t swiotlb_bus_to_phys(struct device *hwdev,
- dma_addr_t address);
-
-extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size);
-
extern void
*swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index bffe6d7ef9d..ac25cd28e80 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -114,46 +114,11 @@ setup_io_tlb_npages(char *str)
__setup("swiotlb=", setup_io_tlb_npages);
/* make io_tlb_overflow tunable too? */
-void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
-{
- return alloc_bootmem_low_pages(size);
-}
-
-void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
-{
- return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
-}
-
-dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
- return paddr;
-}
-
-phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-{
- return baddr;
-}
-
+/* Note that this doesn't work with highmem page */
static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
volatile void *address)
{
- return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
-}
-
-void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
-{
- return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
-}
-
-int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
- dma_addr_t addr, size_t size)
-{
- return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
-}
-
-int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
-{
- return 0;
+ return phys_to_dma(hwdev, virt_to_phys(address));
}
static void swiotlb_print_info(unsigned long bytes)
@@ -189,7 +154,7 @@ swiotlb_init_with_default_size(size_t default_size)
/*
* Get IO TLB memory from the low pages
*/
- io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
+ io_tlb_start = alloc_bootmem_low_pages(bytes);
if (!io_tlb_start)
panic("Cannot allocate SWIOTLB buffer");
io_tlb_end = io_tlb_start + bytes;
@@ -245,7 +210,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
bytes = io_tlb_nslabs << IO_TLB_SHIFT;
while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
- io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs);
+ io_tlb_start = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+ order);
if (io_tlb_start)
break;
order--;
@@ -315,20 +281,10 @@ cleanup1:
return -ENOMEM;
}
-static inline int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
+static int is_swiotlb_buffer(phys_addr_t paddr)
{
- return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
-}
-
-static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
-{
- return swiotlb_force || swiotlb_arch_range_needs_mapping(paddr, size);
-}
-
-static int is_swiotlb_buffer(char *addr)
-{
- return addr >= io_tlb_start && addr < io_tlb_end;
+ return paddr >= virt_to_phys(io_tlb_start) &&
+ paddr < virt_to_phys(io_tlb_end);
}
/*
@@ -561,9 +517,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_mask = hwdev->coherent_dma_mask;
ret = (void *)__get_free_pages(flags, order);
- if (ret &&
- !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(hwdev, ret),
- size)) {
+ if (ret && swiotlb_virt_to_bus(hwdev, ret) + size > dma_mask) {
/*
* The allocated memory isn't reachable by the device.
*/
@@ -585,7 +539,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dev_addr = swiotlb_virt_to_bus(hwdev, ret);
/* Confirm address can be DMA'd by device */
- if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
+ if (dev_addr + size > dma_mask) {
printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
(unsigned long long)dma_mask,
(unsigned long long)dev_addr);
@@ -601,11 +555,13 @@ EXPORT_SYMBOL(swiotlb_alloc_coherent);
void
swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
- dma_addr_t dma_handle)
+ dma_addr_t dev_addr)
{
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
WARN_ON(irqs_disabled());
- if (!is_swiotlb_buffer(vaddr))
- free_pages((unsigned long) vaddr, get_order(size));
+ if (!is_swiotlb_buffer(paddr))
+ free_pages((unsigned long)vaddr, get_order(size));
else
/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
@@ -625,12 +581,15 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
"device %s\n", size, dev ? dev_name(dev) : "?");
- if (size > io_tlb_overflow && do_panic) {
- if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
- panic("DMA: Memory would be corrupted\n");
- if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
- panic("DMA: Random memory would be DMAed\n");
- }
+ if (size <= io_tlb_overflow || !do_panic)
+ return;
+
+ if (dir == DMA_BIDIRECTIONAL)
+ panic("DMA: Random memory could be DMA accessed\n");
+ if (dir == DMA_FROM_DEVICE)
+ panic("DMA: Random memory could be DMA written\n");
+ if (dir == DMA_TO_DEVICE)
+ panic("DMA: Random memory could be DMA read\n");
}
/*
@@ -646,7 +605,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
struct dma_attrs *attrs)
{
phys_addr_t phys = page_to_phys(page) + offset;
- dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
+ dma_addr_t dev_addr = phys_to_dma(dev, phys);
void *map;
BUG_ON(dir == DMA_NONE);
@@ -655,8 +614,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
- if (!address_needs_mapping(dev, dev_addr, size) &&
- !range_needs_mapping(phys, size))
+ if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
return dev_addr;
/*
@@ -673,7 +631,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
/*
* Ensure that the address returned is DMA'ble
*/
- if (address_needs_mapping(dev, dev_addr, size))
+ if (!dma_capable(dev, dev_addr, size))
panic("map_single: bounce buffer is not DMA'ble");
return dev_addr;
@@ -691,19 +649,25 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, int dir)
{
- char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(dma_addr)) {
- do_unmap_single(hwdev, dma_addr, size, dir);
+ if (is_swiotlb_buffer(paddr)) {
+ do_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
return;
}
if (dir != DMA_FROM_DEVICE)
return;
- dma_mark_clean(dma_addr, size);
+ /*
+ * phys_to_virt doesn't work with hihgmem page but we could
+ * call dma_mark_clean() with hihgmem page here. However, we
+ * are fine since dma_mark_clean() is null on POWERPC. We can
+ * make dma_mark_clean() take a physical address if necessary.
+ */
+ dma_mark_clean(phys_to_virt(paddr), size);
}
void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
@@ -728,19 +692,19 @@ static void
swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, int dir, int target)
{
- char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(dma_addr)) {
- sync_single(hwdev, dma_addr, size, dir, target);
+ if (is_swiotlb_buffer(paddr)) {
+ sync_single(hwdev, phys_to_virt(paddr), size, dir, target);
return;
}
if (dir != DMA_FROM_DEVICE)
return;
- dma_mark_clean(dma_addr, size);
+ dma_mark_clean(phys_to_virt(paddr), size);
}
void
@@ -817,10 +781,10 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
for_each_sg(sgl, sg, nelems, i) {
phys_addr_t paddr = sg_phys(sg);
- dma_addr_t dev_addr = swiotlb_phys_to_bus(hwdev, paddr);
+ dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
- if (range_needs_mapping(paddr, sg->length) ||
- address_needs_mapping(hwdev, dev_addr, sg->length)) {
+ if (swiotlb_force ||
+ !dma_capable(hwdev, dev_addr, sg->length)) {
void *map = map_single(hwdev, sg_phys(sg),
sg->length, dir);
if (!map) {