ARM: add coherent dma ops

arch_is_coherent is problematic as it is a global symbol. This
doesn't work for multi-platform kernels or platforms which can support
per device coherent DMA.

This adds arm_coherent_dma_ops to be used for devices which connected
coherently (i.e. to the ACP port on Cortex-A9 or A15). The arm_dma_ops
are modified at boot when arch_is_coherent is true.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>

1 files changed, 59 insertions, 12 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 13f555d6249..7d772c0a93f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -73,11 +73,18 @@ static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page,
              unsigned long offset, size_t size, enum dma_data_direction dir,
              struct dma_attrs *attrs)
 {
-        if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+        if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
                 __dma_page_cpu_to_dev(page, offset, size, dir);
         return pfn_to_dma(dev, page_to_pfn(page)) + offset;
 }
 
+static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page,
+             unsigned long offset, size_t size, enum dma_data_direction dir,
+             struct dma_attrs *attrs)
+{
+        return pfn_to_dma(dev, page_to_pfn(page)) + offset;
+}
+
 /**
  * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
@@ -96,7 +103,7 @@ static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle,
                 size_t size, enum dma_data_direction dir,
                 struct dma_attrs *attrs)
 {
-        if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+        if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
                 __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
                                       handle & ~PAGE_MASK, size, dir);
 }
@@ -106,8 +113,7 @@ static void arm_dma_sync_single_for_cpu(struct device *dev,
 {
         unsigned int offset = handle & (PAGE_SIZE - 1);
         struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
-        if (!arch_is_coherent())
-                __dma_page_dev_to_cpu(page, offset, size, dir);
+        __dma_page_dev_to_cpu(page, offset, size, dir);
 }
 
 static void arm_dma_sync_single_for_device(struct device *dev,
@@ -115,8 +121,7 @@ static void arm_dma_sync_single_for_device(struct device *dev,
 {
         unsigned int offset = handle & (PAGE_SIZE - 1);
         struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
-        if (!arch_is_coherent())
-                __dma_page_cpu_to_dev(page, offset, size, dir);
+        __dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
 static int arm_dma_set_mask(struct device *dev, u64 dma_mask);
@@ -138,6 +143,22 @@ struct dma_map_ops arm_dma_ops = {
 };
 EXPORT_SYMBOL(arm_dma_ops);
 
+static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
+        dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs);
+static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,
+                                  dma_addr_t handle, struct dma_attrs *attrs);
+
+struct dma_map_ops arm_coherent_dma_ops = {
+        .alloc                  = arm_coherent_dma_alloc,
+        .free                   = arm_coherent_dma_free,
+        .mmap                   = arm_dma_mmap,
+        .get_sgtable            = arm_dma_get_sgtable,
+        .map_page               = arm_coherent_dma_map_page,
+        .map_sg                 = arm_dma_map_sg,
+        .set_dma_mask           = arm_dma_set_mask,
+};
+EXPORT_SYMBOL(arm_coherent_dma_ops);
+
 static u64 get_coherent_dma_mask(struct device *dev)
 {
         u64 mask = (u64)arm_dma_limit;
@@ -586,7 +607,7 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
 
 
 static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-                         gfp_t gfp, pgprot_t prot, const void *caller)
+                         gfp_t gfp, pgprot_t prot, bool is_coherent, const void *caller)
 {
         u64 mask = get_coherent_dma_mask(dev);
         struct page *page;
@@ -619,7 +640,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
         *handle = DMA_ERROR_CODE;
         size = PAGE_ALIGN(size);
 
-        if (arch_is_coherent() || nommu())
+        if (is_coherent || nommu())
                 addr = __alloc_simple_buffer(dev, size, gfp, &page);
         else if (gfp & GFP_ATOMIC)
                 addr = __alloc_from_pool(size, &page);
@@ -647,7 +668,20 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
         if (dma_alloc_from_coherent(dev, size, handle, &memory))
                 return memory;
 
-        return __dma_alloc(dev, size, handle, gfp, prot,
+        return __dma_alloc(dev, size, handle, gfp, prot, false,
+                           __builtin_return_address(0));
+}
+
+static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
+        dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+        pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+        void *memory;
+
+        if (dma_alloc_from_coherent(dev, size, handle, &memory))
+                return memory;
+
+        return __dma_alloc(dev, size, handle, gfp, prot, true,
                            __builtin_return_address(0));
 }
 
@@ -684,8 +718,9 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 /*
  * Free a buffer as defined by the above mapping.
  */
-void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
-                  dma_addr_t handle, struct dma_attrs *attrs)
+static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
+                           dma_addr_t handle, struct dma_attrs *attrs,
+                           bool is_coherent)
 {
         struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
 
@@ -694,7 +729,7 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 
         size = PAGE_ALIGN(size);
 
-        if (arch_is_coherent() || nommu()) {
+        if (is_coherent || nommu()) {
                 __dma_free_buffer(page, size);
         } else if (__free_from_pool(cpu_addr, size)) {
                 return;
@@ -710,6 +745,18 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
         }
 }
 
+void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
+                  dma_addr_t handle, struct dma_attrs *attrs)
+{
+        __arm_dma_free(dev, size, cpu_addr, handle, attrs, false);
+}
+
+static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,
+                                  dma_addr_t handle, struct dma_attrs *attrs)
+{
+        __arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
+}
+
 int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
                  void *cpu_addr, dma_addr_t handle, size_t size,
                  struct dma_attrs *attrs)