powerpc: Implement dma_mmap_coherent()

This is used by Alsa to mmap buffers allocated with dma_alloc_coherent()
into userspace. We need a special variant to handle machines with
non-coherent DMAs as those buffers have "special" virt addresses and
require non-cachable mappings

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

3 files changed, 44 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 6d2416a85709..dd70fac57ec8 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -42,6 +42,7 @@ extern void __dma_free_coherent(size_t size, void *vaddr);
 extern void __dma_sync(void *vaddr, size_t size, int direction);
 extern void __dma_sync_page(struct page *page, unsigned long offset,
 				 size_t size, int direction);
+extern unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr);
 
 #else /* ! CONFIG_NOT_COHERENT_CACHE */
 /*
@@ -198,6 +199,11 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 #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)
 
+extern int dma_mmap_coherent(struct device *, struct vm_area_struct *,
+			     void *, dma_addr_t, size_t);
+#define ARCH_HAS_DMA_MMAP_COHERENT
+
+
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction)
 {
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index cf02cad62d9a..d238c082c3c5 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -179,3 +179,21 @@ static int __init dma_init(void)
        return 0;
 }
 fs_initcall(dma_init);
+
+int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+		      void *cpu_addr, dma_addr_t handle, size_t size)
+{
+	unsigned long pfn;
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
+#else
+	pfn = page_to_pfn(virt_to_page(cpu_addr));
+#endif
+	return remap_pfn_range(vma, vma->vm_start,
+			       pfn + vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot);
+}
+EXPORT_SYMBOL_GPL(dma_mmap_coherent);
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 757c0bed9a91..b42f76c4948d 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -399,3 +399,23 @@ void __dma_sync_page(struct page *page, unsigned long offset,
 #endif
 }
 EXPORT_SYMBOL(__dma_sync_page);
+
+/*
+ * Return the PFN for a given cpu virtual address returned by
+ * __dma_alloc_coherent. This is used by dma_mmap_coherent()
+ */
+unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr)
+{
+	/* This should always be populated, so we don't test every
+	 * level. If that fails, we'll have a nice crash which
+	 * will be as good as a BUG_ON()
+	 */
+	pgd_t *pgd = pgd_offset_k(cpu_addr);
+	pud_t *pud = pud_offset(pgd, cpu_addr);
+	pmd_t *pmd = pmd_offset(pud, cpu_addr);
+	pte_t *ptep = pte_offset_kernel(pmd, cpu_addr);
+
+	if (pte_none(*ptep) || !pte_present(*ptep))
+		return 0;
+	return pte_pfn(*ptep);
+}