[Intel-gfx] [PATCH 15/16] dma-mapping: clear __GFP_COMP in dma_alloc_attrs

[Christoph Hellwig]

Lift the code to clear __GFP_COMP from arm into the common DMA
allocator path.  For one this fixes the various other patches that
call alloc_pages_exact or split_page in case a bogus driver passes
the argument, and it also prepares for doing exact allocation in
the generic dma-direct allocator.

Signed-off-by: Christoph Hellwig <hch at lst.de>
---
 arch/arm/mm/dma-mapping.c | 17 -----------------
 kernel/dma/mapping.c      |  9 +++++++++
 2 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 0a75058c11f3..86135feb2c05 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -759,14 +759,6 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	if (mask < 0xffffffffULL)
 		gfp |= GFP_DMA;
 
-	/*
-	 * Following is a work-around (a.k.a. hack) to prevent pages
-	 * with __GFP_COMP being passed to split_page() which cannot
-	 * handle them.  The real problem is that this flag probably
-	 * should be 0 on ARM as it is not supported on this
-	 * platform; see CONFIG_HUGETLBFS.
-	 */
-	gfp &= ~(__GFP_COMP);
 	args.gfp = gfp;
 
 	*handle = DMA_MAPPING_ERROR;
@@ -1527,15 +1519,6 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 		return __iommu_alloc_simple(dev, size, gfp, handle,
 					    coherent_flag, attrs);
 
-	/*
-	 * Following is a work-around (a.k.a. hack) to prevent pages
-	 * with __GFP_COMP being passed to split_page() which cannot
-	 * handle them.  The real problem is that this flag probably
-	 * should be 0 on ARM as it is not supported on this
-	 * platform; see CONFIG_HUGETLBFS.
-	 */
-	gfp &= ~(__GFP_COMP);
-
 	pages = __iommu_alloc_buffer(dev, size, gfp, attrs, coherent_flag);
 	if (!pages)
 		return NULL;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index f7afdadb6770..4b618e1abbc1 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -252,6 +252,15 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
+	/*
+	 * __GFP_COMP interacts badly with splitting up a larger order
+	 * allocation.  But as our allocations might not even come from the
+	 * page allocator, the callers can't rely on the fact that they
+	 * even get pages, never mind which kind.
+	 */
+	if (WARN_ON_ONCE(flag & __GFP_COMP))
+		flag &= ~__GFP_COMP;
+
 	if (dma_is_direct(ops))
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	else if (ops->alloc)
-- 
2.20.1