[PATCH 19/21] ARM: dma-mapping: use generic form of arch_sync_dma_* helpers

[Arnd Bergmann <arnd@xxxxxxxxxx>]

From: Arnd Bergmann <arnd@xxxxxxxx>

As the final step of the conversion to generic arch_sync_dma_*
helpers, change the Arm implementation to look the same as the
new generic version, by calling the dmac_{clean,inv,flush}_area
low-level functions instead of the abstracted dmac_{map,unmap}_area
version.

On ARMv6/v7, this invalidates the caches after a DMA transfer from
a device because of speculative prefetching, while on earlier versions
it only needs to do this before the transfer.

This should not change any of the current behavior.

FIXME: address CONFIG_DMA_CACHE_RWFO properly.

Signed-off-by: Arnd Bergmann <arnd@xxxxxxxx>
---
 arch/arm/mm/dma-mapping-nommu.c | 11 +++----
 arch/arm/mm/dma-mapping.c       | 53 +++++++++++++++++++++++----------
 2 files changed, 43 insertions(+), 21 deletions(-)

diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index cfd9c933d2f0..12b5c6ae93fc 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -16,12 +16,13 @@
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
-	dmac_map_area(__va(paddr), size, dir);
-
-	if (dir == DMA_FROM_DEVICE)
+	if (dir == DMA_FROM_DEVICE) {
+		dmac_inv_range(__va(paddr), __va(paddr + size));
 		outer_inv_range(paddr, paddr + size);
-	else
+	} else {
+		dmac_clean_range(__va(paddr), __va(paddr + size));
 		outer_clean_range(paddr, paddr + size);
+	}
 }
 
 void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
@@ -29,7 +30,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 {
 	if (dir != DMA_TO_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
-		dmac_unmap_area(__va(paddr), size, dir);
+		dmac_inv_range(__va(paddr), __va(paddr));
 	}
 }
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ce4b74f34a58..cc702cb27ae7 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -623,8 +623,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 }
 
 static void dma_cache_maint(phys_addr_t paddr,
-	size_t size, enum dma_data_direction dir,
-	void (*op)(const void *, size_t, int))
+	size_t size, void (*op)(const void *, const void *))
 {
 	unsigned long pfn = PFN_DOWN(paddr);
 	unsigned long offset = paddr % PAGE_SIZE;
@@ -647,18 +646,18 @@ static void dma_cache_maint(phys_addr_t paddr,
 
 			if (cache_is_vipt_nonaliasing()) {
 				vaddr = kmap_atomic(page);
-				op(vaddr + offset, len, dir);
+				op(vaddr + offset, vaddr + offset + len);
 				kunmap_atomic(vaddr);
 			} else {
 				vaddr = kmap_high_get(page);
 				if (vaddr) {
-					op(vaddr + offset, len, dir);
+					op(vaddr + offset, vaddr + offset + len);
 					kunmap_high(page);
 				}
 			}
 		} else {
 			vaddr = page_address(page) + offset;
-			op(vaddr, len, dir);
+			op(vaddr, vaddr + len);
 		}
 		offset = 0;
 		pfn++;
@@ -666,6 +665,18 @@ static void dma_cache_maint(phys_addr_t paddr,
 	} while (left);
 }
 
+static bool arch_sync_dma_cpu_needs_post_dma_flush(void)
+{
+	if (IS_ENABLED(CONFIG_CPU_V6) ||
+	    IS_ENABLED(CONFIG_CPU_V6K) ||
+	    IS_ENABLED(CONFIG_CPU_V7) ||
+	    IS_ENABLED(CONFIG_CPU_V7M))
+		return true;
+
+	/* FIXME: runtime detection */
+	return false;
+}
+
 /*
  * Make an area consistent for devices.
  * Note: Drivers should NOT use this function directly.
@@ -674,25 +685,35 @@ static void dma_cache_maint(phys_addr_t paddr,
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
-	dma_cache_maint(paddr, size, dir, dmac_map_area);
-
-	if (dir == DMA_FROM_DEVICE) {
-		outer_inv_range(paddr, paddr + size);
-	} else {
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_maint(paddr, size, dmac_clean_range);
 		outer_clean_range(paddr, paddr + size);
+		break;
+	case DMA_FROM_DEVICE:
+		dma_cache_maint(paddr, size, dmac_inv_range);
+		outer_inv_range(paddr, paddr + size);
+		break;
+	case DMA_BIDIRECTIONAL:
+		if (arch_sync_dma_cpu_needs_post_dma_flush()) {
+			dma_cache_maint(paddr, size, dmac_clean_range);
+			outer_clean_range(paddr, paddr + size);
+		} else {
+			dma_cache_maint(paddr, size, dmac_flush_range);
+			outer_flush_range(paddr, paddr + size);
+		}
+		break;
+	default:
+		break;
 	}
-	/* FIXME: non-speculating: flush on bidirectional mappings? */
 }
 
 void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
-	/* FIXME: non-speculating: not required */
-	/* in any case, don't bother invalidating if DMA to device */
-	if (dir != DMA_TO_DEVICE) {
+	if (dir != DMA_TO_DEVICE && arch_sync_dma_cpu_needs_post_dma_flush()) {
 		outer_inv_range(paddr, paddr + size);
-
-		dma_cache_maint(paddr, size, dir, dmac_unmap_area);
+		dma_cache_maint(paddr, size, dmac_inv_range);
 	}
 
 	/*
-- 
2.39.2