Merge tag 'dma-mapping-5.9-1' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping fixes from Christoph Hellwig:
 "Fix more fallout from the dma-pool changes (Nicolas Saenz Julienne,
  me)"

* tag 'dma-mapping-5.9-1' of git://git.infradead.org/users/hch/dma-mapping:
  dma-pool: Only allocate from CMA when in same memory zone
  dma-pool: fix coherent pool allocations for IOMMU mappings

5 files changed, 92 insertions, 78 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 4959f5df21bd..5141d49a046b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1035,8 +1035,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 
 	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    !gfpflags_allow_blocking(gfp) && !coherent)
-		cpu_addr = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page,
-					       gfp);
+		page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr,
+					       gfp, NULL);
 	else
 		cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs);
 	if (!cpu_addr)
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 5a3ce2a24794..6e87225600ae 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 }
 
 u64 dma_direct_get_required_mask(struct device *dev);
-gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
-				  u64 *phys_mask);
-bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 016b96b384bd..52635e91143b 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
 			pgprot_t prot, const void *caller);
 void dma_common_free_remap(void *cpu_addr, size_t size);
 
-void *dma_alloc_from_pool(struct device *dev, size_t size,
-			  struct page **ret_page, gfp_t flags);
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t flags,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
 bool dma_free_from_pool(struct device *dev, void *start, size_t size);
 
 int
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index bb0041e99659..db6ef07aec3b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -43,7 +43,7 @@ u64 dma_direct_get_required_mask(struct device *dev)
 	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
 }
 
-gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
+static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 				  u64 *phys_limit)
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
@@ -68,7 +68,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	return 0;
 }
 
-bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
@@ -161,8 +161,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	size = PAGE_ALIGN(size);
 
 	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
-		ret = dma_alloc_from_pool(dev, size, &page, gfp);
-		if (!ret)
+		u64 phys_mask;
+
+		gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+				&phys_mask);
+		page = dma_alloc_from_pool(dev, size, &ret, gfp,
+				dma_coherent_ok);
+		if (!page)
 			return NULL;
 		goto done;
 	}
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 6bc74a2d5127..06582b488e31 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -3,7 +3,9 @@
  * Copyright (C) 2012 ARM Ltd.
  * Copyright (C) 2020 Google LLC
  */
+#include <linux/cma.h>
 #include <linux/debugfs.h>
+#include <linux/dma-contiguous.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/init.h>
@@ -55,6 +57,29 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size)
 		pool_size_kernel += size;
 }
 
+static bool cma_in_zone(gfp_t gfp)
+{
+	unsigned long size;
+	phys_addr_t end;
+	struct cma *cma;
+
+	cma = dev_get_cma_area(NULL);
+	if (!cma)
+		return false;
+
+	size = cma_get_size(cma);
+	if (!size)
+		return false;
+
+	/* CMA can't cross zone boundaries, see cma_activate_area() */
+	end = cma_get_base(cma) + size - 1;
+	if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+		return end <= DMA_BIT_MASK(zone_dma_bits);
+	if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+		return end <= DMA_BIT_MASK(32);
+	return true;
+}
+
 static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 			      gfp_t gfp)
 {
@@ -68,7 +93,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 	do {
 		pool_size = 1 << (PAGE_SHIFT + order);
-		page = alloc_pages(gfp, order);
+		if (cma_in_zone(gfp))
+			page = dma_alloc_from_contiguous(NULL, 1 << order,
+							 order, false);
+		if (!page)
+			page = alloc_pages(gfp, order);
 	} while (!page && order-- > 0);
 	if (!page)
 		goto out;
@@ -196,93 +225,75 @@ static int __init dma_atomic_pool_init(void)
 }
 postcore_initcall(dma_atomic_pool_init);
 
-static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev)
+static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp)
 {
-	u64 phys_mask;
-	gfp_t gfp;
-
-	gfp = dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-					  &phys_mask);
-	if (IS_ENABLED(CONFIG_ZONE_DMA) && gfp == GFP_DMA)
+	if (prev == NULL) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+			return atomic_pool_dma32;
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+			return atomic_pool_dma;
+		return atomic_pool_kernel;
+	}
+	if (prev == atomic_pool_kernel)
+		return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma;
+	if (prev == atomic_pool_dma32)
 		return atomic_pool_dma;
-	if (IS_ENABLED(CONFIG_ZONE_DMA32) && gfp == GFP_DMA32)
-		return atomic_pool_dma32;
-	return atomic_pool_kernel;
+	return NULL;
 }
 
-static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool)
+static struct page *__dma_alloc_from_pool(struct device *dev, size_t size,
+		struct gen_pool *pool, void **cpu_addr,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
 {
-	if (bad_pool == atomic_pool_kernel)
-		return atomic_pool_dma32 ? : atomic_pool_dma;
+	unsigned long addr;
+	phys_addr_t phys;
 
-	if (bad_pool == atomic_pool_dma32)
-		return atomic_pool_dma;
+	addr = gen_pool_alloc(pool, size);
+	if (!addr)
+		return NULL;
 
-	return NULL;
-}
+	phys = gen_pool_virt_to_phys(pool, addr);
+	if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) {
+		gen_pool_free(pool, addr, size);
+		return NULL;
+	}
 
-static inline struct gen_pool *dma_guess_pool(struct device *dev,
-					      struct gen_pool *bad_pool)
-{
-	if (bad_pool)
-		return dma_get_safer_pool(bad_pool);
+	if (gen_pool_avail(pool) < atomic_pool_size)
+		schedule_work(&atomic_pool_work);
 
-	return dma_guess_pool_from_device(dev);
+	*cpu_addr = (void *)addr;
+	memset(*cpu_addr, 0, size);
+	return pfn_to_page(__phys_to_pfn(phys));
 }
 
-void *dma_alloc_from_pool(struct device *dev, size_t size,
-			  struct page **ret_page, gfp_t flags)
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t gfp,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
 {
 	struct gen_pool *pool = NULL;
-	unsigned long val = 0;
-	void *ptr = NULL;
-	phys_addr_t phys;
-
-	while (1) {
-		pool = dma_guess_pool(dev, pool);
-		if (!pool) {
-			WARN(1, "Failed to get suitable pool for %s\n",
-			     dev_name(dev));
-			break;
-		}
-
-		val = gen_pool_alloc(pool, size);
-		if (!val)
-			continue;
-
-		phys = gen_pool_virt_to_phys(pool, val);
-		if (dma_coherent_ok(dev, phys, size))
-			break;
-
-		gen_pool_free(pool, val, size);
-		val = 0;
-	}
-
-
-	if (val) {
-		*ret_page = pfn_to_page(__phys_to_pfn(phys));
-		ptr = (void *)val;
-		memset(ptr, 0, size);
+	struct page *page;
 
-		if (gen_pool_avail(pool) < atomic_pool_size)
-			schedule_work(&atomic_pool_work);
+	while ((pool = dma_guess_pool(pool, gfp))) {
+		page = __dma_alloc_from_pool(dev, size, pool, cpu_addr,
+					     phys_addr_ok);
+		if (page)
+			return page;
 	}
 
-	return ptr;
+	WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev));
+	return NULL;
 }
 
 bool dma_free_from_pool(struct device *dev, void *start, size_t size)
 {
 	struct gen_pool *pool = NULL;
 
-	while (1) {
-		pool = dma_guess_pool(dev, pool);
-		if (!pool)
-			return false;
-
-		if (gen_pool_has_addr(pool, (unsigned long)start, size)) {
-			gen_pool_free(pool, (unsigned long)start, size);
-			return true;
-		}
+	while ((pool = dma_guess_pool(pool, 0))) {
+		if (!gen_pool_has_addr(pool, (unsigned long)start, size))
+			continue;
+		gen_pool_free(pool, (unsigned long)start, size);
+		return true;
 	}
+
+	return false;
 }