dma-mapping: add the device argument to dma_mapping_error()

Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER
architecture does:

This enables us to cleanly fix the Calgary IOMMU issue that some devices
are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423).

I think that per-device dma_mapping_ops support would be also helpful for
KVM people to support PCI passthrough but Andi thinks that this makes it
difficult to support the PCI passthrough (see the above thread).  So I
CC'ed this to KVM camp.  Comments are appreciated.

A pointer to dma_mapping_ops to struct dev_archdata is added.  If the
pointer is non NULL, DMA operations in asm/dma-mapping.h use it.  If it's
NULL, the system-wide dma_ops pointer is used as before.

If it's useful for KVM people, I plan to implement a mechanism to register
a hook called when a new pci (or dma capable) device is created (it works
with hot plugging).  It enables IOMMUs to set up an appropriate
dma_mapping_ops per device.

The major obstacle is that dma_mapping_error doesn't take a pointer to the
device unlike other DMA operations.  So x86 can't have dma_mapping_ops per
device.  Note all the POWER IOMMUs use the same dma_mapping_error function
so this is not a problem for POWER but x86 IOMMUs use different
dma_mapping_error functions.

The first patch adds the device argument to dma_mapping_error.  The patch
is trivial but large since it touches lots of drivers and dma-mapping.h in
all the architecture.

This patch:

dma_mapping_error() doesn't take a pointer to the device unlike other DMA
operations.  So we can't have dma_mapping_ops per device.

Note that POWER already has dma_mapping_ops per device but all the POWER
IOMMUs use the same dma_mapping_error function.  x86 IOMMUs use device
argument.

[akpm@linux-foundation.org: fix sge]
[akpm@linux-foundation.org: fix svc_rdma]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix bnx2x]
[akpm@linux-foundation.org: fix s2io]
[akpm@linux-foundation.org: fix pasemi_mac]
[akpm@linux-foundation.org: fix sdhci]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix sparc]
[akpm@linux-foundation.org: fix ibmvscsi]
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Avi Kivity <avi@qumranet.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 68 insertions, 31 deletions

diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
index c2ddd3d1b883..0eaa9bf6011f 100644
--- a/include/asm-x86/dma-mapping.h
+++ b/include/asm-x86/dma-mapping.h
@@ -17,7 +17,8 @@ extern int panic_on_overflow;
 extern int force_iommu;
 
 struct dma_mapping_ops {
-        int             (*mapping_error)(dma_addr_t dma_addr);
+        int             (*mapping_error)(struct device *dev,
+                                         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,
@@ -56,14 +57,32 @@ struct dma_mapping_ops {
         int             is_phys;
 };
 
-extern const struct dma_mapping_ops *dma_ops;
+extern struct dma_mapping_ops *dma_ops;
 
-static inline int dma_mapping_error(dma_addr_t dma_addr)
+static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 {
-        if (dma_ops->mapping_error)
-                return dma_ops->mapping_error(dma_addr);
+#ifdef CONFIG_X86_32
+        return dma_ops;
+#else
+        if (unlikely(!dev) || !dev->archdata.dma_ops)
+                return dma_ops;
+        else
+                return dev->archdata.dma_ops;
+#endif
+}
+
+/* Make sure we keep the same behaviour */
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+#ifdef CONFIG_X86_32
+        return 0;
+#else
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+        if (ops->mapping_error)
+                return ops->mapping_error(dev, dma_addr);
 
         return (dma_addr == bad_dma_address);
+#endif
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
@@ -83,44 +102,53 @@ static inline dma_addr_t
 dma_map_single(struct device *hwdev, void *ptr, size_t size,
                int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        return dma_ops->map_single(hwdev, virt_to_phys(ptr), size, direction);
+        return ops->map_single(hwdev, virt_to_phys(ptr), size, direction);
 }
 
 static inline void
 dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
                  int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->unmap_single)
-                dma_ops->unmap_single(dev, addr, size, direction);
+        if (ops->unmap_single)
+                ops->unmap_single(dev, addr, size, direction);
 }
 
 static inline int
 dma_map_sg(struct device *hwdev, struct scatterlist *sg,
            int nents, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        return dma_ops->map_sg(hwdev, sg, nents, direction);
+        return ops->map_sg(hwdev, sg, nents, direction);
 }
 
 static inline void
 dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
              int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->unmap_sg)
-                dma_ops->unmap_sg(hwdev, sg, nents, direction);
+        if (ops->unmap_sg)
+                ops->unmap_sg(hwdev, sg, nents, direction);
 }
 
 static inline void
 dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
                         size_t size, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_for_cpu)
-                dma_ops->sync_single_for_cpu(hwdev, dma_handle, size,
-                                             direction);
+        if (ops->sync_single_for_cpu)
+                ops->sync_single_for_cpu(hwdev, dma_handle, size, direction);
         flush_write_buffers();
 }
 
@@ -128,10 +156,11 @@ static inline void
 dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
                            size_t size, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_for_device)
-                dma_ops->sync_single_for_device(hwdev, dma_handle, size,
-                                                direction);
+        if (ops->sync_single_for_device)
+                ops->sync_single_for_device(hwdev, dma_handle, size, direction);
         flush_write_buffers();
 }
 
@@ -139,11 +168,12 @@ 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)
 {
-        BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_range_for_cpu)
-                dma_ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
-                                                   size, direction);
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
 
+        BUG_ON(!valid_dma_direction(direction));
+        if (ops->sync_single_range_for_cpu)
+                ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
+                                               size, direction);
         flush_write_buffers();
 }
 
@@ -152,11 +182,12 @@ dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
                                  unsigned long offset, size_t size,
                                  int direction)
 {
-        BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_single_range_for_device)
-                dma_ops->sync_single_range_for_device(hwdev, dma_handle,
-                                                      offset, size, direction);
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
 
+        BUG_ON(!valid_dma_direction(direction));
+        if (ops->sync_single_range_for_device)
+                ops->sync_single_range_for_device(hwdev, dma_handle,
+                                                  offset, size, direction);
         flush_write_buffers();
 }
 
@@ -164,9 +195,11 @@ static inline void
 dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
                     int nelems, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_sg_for_cpu)
-                dma_ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
+        if (ops->sync_sg_for_cpu)
+                ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
         flush_write_buffers();
 }
 
@@ -174,9 +207,11 @@ static inline void
 dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
                        int nelems, int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
         BUG_ON(!valid_dma_direction(direction));
-        if (dma_ops->sync_sg_for_device)
-                dma_ops->sync_sg_for_device(hwdev, sg, nelems, direction);
+        if (ops->sync_sg_for_device)
+                ops->sync_sg_for_device(hwdev, sg, nelems, direction);
 
         flush_write_buffers();
 }
@@ -185,9 +220,11 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
                                       size_t offset, size_t size,
                                       int direction)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+
         BUG_ON(!valid_dma_direction(direction));
-        return dma_ops->map_single(dev, page_to_phys(page)+offset,
-                                   size, direction);
+        return ops->map_single(dev, page_to_phys(page) + offset,
+                               size, direction);
 }
 
 static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,