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>

5 files changed, 20 insertions, 28 deletions

diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 19e7fc7c2c4f..1eb86be93d7a 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -544,7 +544,7 @@ error:
         return ret;
 }
 
-static const struct dma_mapping_ops calgary_dma_ops = {
+static struct dma_mapping_ops calgary_dma_ops = {
         .alloc_coherent = calgary_alloc_coherent,
         .map_single = calgary_map_single,
         .unmap_single = calgary_unmap_single,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index cbecb05551bb..37544123896d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -11,7 +11,7 @@
 
 static int forbid_dac __read_mostly;
 
-const struct dma_mapping_ops *dma_ops;
+struct dma_mapping_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static int iommu_sac_force __read_mostly;
@@ -312,6 +312,8 @@ static int dma_release_coherent(struct device *dev, int order, void *vaddr)
 
 int dma_supported(struct device *dev, u64 mask)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+
 #ifdef CONFIG_PCI
         if (mask > 0xffffffff && forbid_dac > 0) {
                 dev_info(dev, "PCI: Disallowing DAC for device\n");
@@ -319,8 +321,8 @@ int dma_supported(struct device *dev, u64 mask)
         }
 #endif
 
-        if (dma_ops->dma_supported)
-                return dma_ops->dma_supported(dev, mask);
+        if (ops->dma_supported)
+                return ops->dma_supported(dev, mask);
 
         /* Copied from i386. Doesn't make much sense, because it will
            only work for pci_alloc_coherent.
@@ -367,6 +369,7 @@ void *
 dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
                    gfp_t gfp)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
         void *memory = NULL;
         struct page *page;
         unsigned long dma_mask = 0;
@@ -435,8 +438,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
                         /* Let low level make its own zone decisions */
                         gfp &= ~(GFP_DMA32|GFP_DMA);
 
-                        if (dma_ops->alloc_coherent)
-                                return dma_ops->alloc_coherent(dev, size,
+                        if (ops->alloc_coherent)
+                                return ops->alloc_coherent(dev, size,
                                                            dma_handle, gfp);
                         return NULL;
                 }
@@ -448,14 +451,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
                 }
         }
 
-        if (dma_ops->alloc_coherent) {
+        if (ops->alloc_coherent) {
                 free_pages((unsigned long)memory, get_order(size));
                 gfp &= ~(GFP_DMA|GFP_DMA32);
-                return dma_ops->alloc_coherent(dev, size, dma_handle, gfp);
+                return ops->alloc_coherent(dev, size, dma_handle, gfp);
         }
 
-        if (dma_ops->map_simple) {
-                *dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory),
+        if (ops->map_simple) {
+                *dma_handle = ops->map_simple(dev, virt_to_phys(memory),
                                               size,
                                               PCI_DMA_BIDIRECTIONAL);
                 if (*dma_handle != bad_dma_address)
@@ -477,12 +480,14 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_coherent(struct device *dev, size_t size,
                          void *vaddr, dma_addr_t bus)
 {
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+
         int order = get_order(size);
         WARN_ON(irqs_disabled());       /* for portability */
         if (dma_release_coherent(dev, order, vaddr))
                 return;
-        if (dma_ops->unmap_single)
-                dma_ops->unmap_single(dev, bus, size, 0);
+        if (ops->unmap_single)
+                ops->unmap_single(dev, bus, size, 0);
         free_pages((unsigned long)vaddr, order);
 }
 EXPORT_SYMBOL(dma_free_coherent);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index df5f142657d2..744126e64950 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -692,8 +692,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 extern int agp_amd64_init(void);
 
-static const struct dma_mapping_ops gart_dma_ops = {
-        .mapping_error                  = NULL,
+static struct dma_mapping_ops gart_dma_ops = {
         .map_single                     = gart_map_single,
         .map_simple                     = gart_map_simple,
         .unmap_single                   = gart_unmap_single,
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 792b9179eff3..3f91f71cdc3e 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -72,21 +72,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
         return nents;
 }
 
-/* Make sure we keep the same behaviour */
-static int nommu_mapping_error(dma_addr_t dma_addr)
-{
-#ifdef CONFIG_X86_32
-        return 0;
-#else
-        return (dma_addr == bad_dma_address);
-#endif
-}
-
-
-const struct dma_mapping_ops nommu_dma_ops = {
+struct dma_mapping_ops nommu_dma_ops = {
         .map_single = nommu_map_single,
         .map_sg = nommu_map_sg,
-        .mapping_error = nommu_mapping_error,
         .is_phys = 1,
 };
 
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index 20df839b9c20..c4ce0332759e 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -18,7 +18,7 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
         return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction);
 }
 
-const struct dma_mapping_ops swiotlb_dma_ops = {
+struct dma_mapping_ops swiotlb_dma_ops = {
         .mapping_error = swiotlb_dma_mapping_error,
         .alloc_coherent = swiotlb_alloc_coherent,
         .free_coherent = swiotlb_free_coherent,