dma-mapping: add (back) arch_dma_mark_clean for ia64

Add back a hook to optimize dcache flushing after reading executable
code using DMA.  This gets ia64 out of the business of pretending to
be dma incoherent just for this optimization.

Signed-off-by: Christoph Hellwig <hch@lst.de>

arch/ia64/Kconfig

@@ -8,6 +8,7 @@ menu "Processor type and features"
 
 config IA64
 	bool
+	select ARCH_HAS_DMA_MARK_CLEAN
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ACPI
@@ -32,8 +33,6 @@ config IA64
 	select TTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select DMA_NONCOHERENT_MMAP
-	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP

arch/ia64/kernel/dma-mapping.c

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-direct.h>
+#include <linux/dma-mapping.h>
 #include <linux/export.h>
 
 /* Set this to 1 if there is a HW IOMMU in the system */
@@ -7,15 +7,3 @@ int iommu_detected __read_mostly;
 
 const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
-
-void *arch_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs)
-{
-	dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
-}

arch/ia64/mm/init.c

@@ -73,8 +73,7 @@ __ia64_sync_icache_dcache (pte_t pte)
  * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
  * flush them when they get mapped into an executable vm-area.
  */
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
-		enum dma_data_direction dir)
 {
 	unsigned long pfn = PHYS_PFN(paddr);
 

include/linux/dma-direct.h

@@ -150,6 +150,9 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 
 	if (unlikely(is_swiotlb_buffer(paddr)))
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+	if (dir == DMA_FROM_DEVICE)
+		arch_dma_mark_clean(paddr, size);
 }
 
 static inline dma_addr_t dma_direct_map_page(struct device *dev,

include/linux/dma-noncoherent.h

@@ -108,6 +108,14 @@ static inline void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
 
+#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
+#else
+static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
+{
+}
+#endif /* ARCH_HAS_DMA_MARK_CLEAN */
+
 void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 

kernel/dma/Kconfig

@@ -44,6 +44,12 @@ config ARCH_HAS_DMA_SET_MASK
 config ARCH_HAS_DMA_WRITE_COMBINE
 	bool
 
+#
+# Select if the architectures provides the arch_dma_mark_clean hook
+#
+config ARCH_HAS_DMA_MARK_CLEAN
+	bool
+
 config DMA_DECLARE_COHERENT
 	bool
 

kernel/dma/direct.c

@@ -345,6 +345,9 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		if (unlikely(is_swiotlb_buffer(paddr)))
 			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
 					SYNC_FOR_CPU);
+
+		if (dir == DMA_FROM_DEVICE)
+			arch_dma_mark_clean(paddr, sg->length);
 	}
 
 	if (!dev_is_dma_coherent(dev))