Merge branch 'lsk-3.10-armlt-atomic-dma-alloc' into integration-lsk-3.10-juno-android

7 files changed, 292 insertions, 67 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 096179c4e0c..19cab5318d0 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -265,37 +265,19 @@ static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
 	const void *caller)
 {
-	struct vm_struct *area;
-	unsigned long addr;
-
 	/*
 	 * DMA allocation can be mapped to user space, so lets
 	 * set VM_USERMAP flags too.
 	 */
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-	addr = (unsigned long)area->addr;
-	area->phys_addr = __pfn_to_phys(page_to_pfn(page));
-
-	if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
-		vunmap((void *)addr);
-		return NULL;
-	}
-	return (void *)addr;
+	return dma_common_contiguous_remap(page, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+			prot, caller);
 }
 
 static void __dma_free_remap(void *cpu_addr, size_t size)
 {
-	unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
-	struct vm_struct *area = find_vm_area(cpu_addr);
-	if (!area || (area->flags & flags) != flags) {
-		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
-		return;
-	}
-	unmap_kernel_range((unsigned long)cpu_addr, size);
-	vunmap(cpu_addr);
+	dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 }
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
@@ -1167,29 +1149,8 @@ static void *
 __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
 		    const void *caller)
 {
-	unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct vm_struct *area;
-	unsigned long p;
-
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-
-	area->pages = pages;
-	area->nr_pages = nr_pages;
-	p = (unsigned long)area->addr;
-
-	for (i = 0; i < nr_pages; i++) {
-		phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
-		if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
-			goto err;
-		p += PAGE_SIZE;
-	}
-	return area->addr;
-err:
-	unmap_kernel_range((unsigned long)area->addr, size);
-	vunmap(area->addr);
+	return dma_common_pages_remap(pages, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
 	return NULL;
 }
 
@@ -1386,8 +1347,8 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
-		unmap_kernel_range((unsigned long)cpu_addr, size);
-		vunmap(cpu_addr);
+		dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 	}
 
 	__iommu_remove_mapping(dev, handle, size);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4ff74ee25d6..2cbd679b0a5 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -18,6 +18,7 @@ config ARM64
 	select COMMON_CLK
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
+	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_CPU_AUTOPROBE
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index f39a55d5891..eeb1cf3ff29 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/genalloc.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/of.h>
@@ -43,6 +44,54 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 	return prot;
 }
 
+static struct gen_pool *atomic_pool;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+	atomic_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
+{
+	unsigned long val;
+	void *ptr = NULL;
+
+	if (!atomic_pool) {
+		WARN(1, "coherent pool not initialised!\n");
+		return NULL;
+	}
+
+	val = gen_pool_alloc(atomic_pool, size);
+	if (val) {
+		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+		*ret_page = phys_to_page(phys);
+		ptr = (void *)val;
+	}
+
+	return ptr;
+}
+
+static bool __in_atomic_pool(void *start, size_t size)
+{
+	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+static int __free_from_pool(void *start, size_t size)
+{
+	if (!__in_atomic_pool(start, size))
+		return 0;
+
+	gen_pool_free(atomic_pool, (unsigned long)start, size);
+
+	return 1;
+}
+
 static void *__dma_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  struct dma_attrs *attrs)
@@ -50,7 +99,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA;
-	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
 		struct page *page;
 
 		size = PAGE_ALIGN(size);
@@ -70,50 +119,54 @@ static void __dma_free_coherent(struct device *dev, size_t size,
 				void *vaddr, dma_addr_t dma_handle,
 				struct dma_attrs *attrs)
 {
+	bool freed;
+	phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
 		return;
 	}
 
-	if (IS_ENABLED(CONFIG_DMA_CMA)) {
-		phys_addr_t paddr = dma_to_phys(dev, dma_handle);
-
-		dma_release_from_contiguous(dev,
+	freed = dma_release_from_contiguous(dev,
 					phys_to_page(paddr),
 					size >> PAGE_SHIFT);
-	} else {
+	if (!freed)
 		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-	}
 }
 
 static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
 				     dma_addr_t *dma_handle, gfp_t flags,
 				     struct dma_attrs *attrs)
 {
-	struct page *page, **map;
+	struct page *page;
 	void *ptr, *coherent_ptr;
-	int order, i;
 
 	size = PAGE_ALIGN(size);
-	order = get_order(size);
+
+	if (!(flags & __GFP_WAIT)) {
+		struct page *page = NULL;
+		void *addr = __alloc_from_pool(size, &page);
+
+		if (addr)
+			*dma_handle = phys_to_dma(dev, page_to_phys(page));
+
+		return addr;
+
+	}
 
 	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
 	if (!ptr)
 		goto no_mem;
-	map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
-	if (!map)
-		goto no_map;
 
 	/* remove any dirty cache lines on the kernel alias */
 	__dma_flush_range(ptr, ptr + size);
 
 	/* create a coherent mapping */
 	page = virt_to_page(ptr);
-	for (i = 0; i < (size >> PAGE_SHIFT); i++)
-		map[i] = page + i;
-	coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
-			    __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false));
-	kfree(map);
+	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+				__get_dma_pgprot(attrs,
+					__pgprot(PROT_NORMAL_NC), false),
+					NULL);
 	if (!coherent_ptr)
 		goto no_map;
 
@@ -132,6 +185,8 @@ static void __dma_free_noncoherent(struct device *dev, size_t size,
 {
 	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
 
+	if (__free_from_pool(vaddr, size))
+		return;
 	vunmap(vaddr);
 	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
 }
@@ -329,6 +384,67 @@ static struct notifier_block amba_bus_nb = {
 
 extern int swiotlb_late_init_with_default_size(size_t default_size);
 
+static int __init atomic_pool_init(void)
+{
+	pgprot_t prot = __pgprot(PROT_NORMAL_NC);
+	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+	struct page *page;
+	void *addr;
+	unsigned int pool_size_order = get_order(atomic_pool_size);
+
+	if (dev_get_cma_area(NULL))
+		page = dma_alloc_from_contiguous(NULL, nr_pages,
+							pool_size_order);
+	else
+		page = alloc_pages(GFP_DMA, pool_size_order);
+
+	if (page) {
+		int ret;
+		void *page_addr = page_address(page);
+
+		memset(page_addr, 0, atomic_pool_size);
+		__dma_flush_range(page_addr, page_addr + atomic_pool_size);
+
+		atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+		if (!atomic_pool)
+			goto free_page;
+
+		addr = dma_common_contiguous_remap(page, atomic_pool_size,
+					VM_USERMAP, prot, atomic_pool_init);
+
+		if (!addr)
+			goto destroy_genpool;
+
+		ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+					page_to_phys(page),
+					atomic_pool_size, -1);
+		if (ret)
+			goto remove_mapping;
+
+		gen_pool_set_algo(atomic_pool,
+				  gen_pool_first_fit_order_align,
+				  (void *)PAGE_SHIFT);
+
+		pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+			atomic_pool_size / 1024);
+		return 0;
+	}
+	goto out;
+
+remove_mapping:
+	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+	gen_pool_destroy(atomic_pool);
+	atomic_pool = NULL;
+free_page:
+	if (!dma_release_from_contiguous(NULL, page, nr_pages))
+		__free_pages(page, pool_size_order);
+out:
+	pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+		atomic_pool_size / 1024);
+	return -ENOMEM;
+}
+
 static int __init swiotlb_late_init(void)
 {
 	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
@@ -343,7 +459,17 @@ static int __init swiotlb_late_init(void)
 
 	return swiotlb_late_init_with_default_size(swiotlb_size);
 }
-arch_initcall(swiotlb_late_init);
+
+static int __init arm64_dma_init(void)
+{
+	int ret = 0;
+
+	ret |= swiotlb_late_init();
+	ret |= atomic_pool_init();
+
+	return ret;
+}
+arch_initcall(arm64_dma_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 0ce39a33b3c..dd302ea3b59 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -10,6 +10,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm-generic/dma-coherent.h>
 
 /*
@@ -267,3 +269,73 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 EXPORT_SYMBOL(dma_common_mmap);
+
+#ifdef CONFIG_MMU
+/*
+ * remaps an array of PAGE_SIZE pages into another vm_area
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(size, vm_flags, caller);
+	if (!area)
+		return NULL;
+
+	area->pages = pages;
+
+	if (map_vm_area(area, prot, &pages)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+
+	return area->addr;
+}
+
+/*
+ * remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller)
+{
+	int i;
+	struct page **pages;
+	void *ptr;
+	unsigned long pfn;
+
+	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+
+	for (i = 0, pfn = page_to_pfn(page); i < (size >> PAGE_SHIFT); i++)
+		pages[i] = pfn_to_page(pfn + i);
+
+	ptr = dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+	kfree(pages);
+
+	return ptr;
+}
+
+/*
+ * unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || (area->flags & vm_flags) != vm_flags) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
+	}
+
+	unmap_kernel_range((unsigned long)cpu_addr, size);
+	vunmap(cpu_addr);
+}
+#endif
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index de8bf89940f..a9fd248f5d4 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -179,6 +179,15 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
 
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller);
+
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+
 /**
  * dma_mmap_attrs - map a coherent DMA allocation into user space
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index f8d41cb1cbe..9e8986ae700 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -106,6 +106,10 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo,
 extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
+extern unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start, unsigned int nr,
+		void *data);
+
 extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
@@ -113,6 +117,9 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev,
 		int min_alloc_order, int nid);
 extern struct gen_pool *dev_get_gen_pool(struct device *dev);
 
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size);
+
 #ifdef CONFIG_OF
 extern struct gen_pool *of_get_named_gen_pool(struct device_node *np,
 	const char *propname, int index);
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 2a39bf62d8c..9e9c46c267d 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -374,6 +374,35 @@ void gen_pool_for_each_chunk(struct gen_pool *pool,
 EXPORT_SYMBOL(gen_pool_for_each_chunk);
 
 /**
+ * addr_in_gen_pool - checks if an address falls within the range of a pool
+ * @pool:	the generic memory pool
+ * @start:	start address
+ * @size:	size of the region
+ *
+ * Check if the range of addresses falls within the specified pool. Returns
+ * true if the entire range is contained in the pool and false otherwise.
+ */
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size)
+{
+	bool found = false;
+	unsigned long end = start + size;
+	struct gen_pool_chunk *chunk;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk) {
+		if (start >= chunk->start_addr && start <= chunk->end_addr) {
+			if (end <= chunk->end_addr) {
+				found = true;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+	return found;
+}
+
+/**
  * gen_pool_avail - get available free space of the pool
  * @pool: pool to get available free space
  *
@@ -452,6 +481,26 @@ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 EXPORT_SYMBOL(gen_pool_first_fit);
 
 /**
+ * gen_pool_first_fit_order_align - find the first available region
+ * of memory matching the size requirement. The region will be aligned
+ * to the order of the size specified.
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @data: additional data - unused
+ */
+unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start,
+		unsigned int nr, void *data)
+{
+	unsigned long align_mask = roundup_pow_of_two(nr) - 1;
+
+	return bitmap_find_next_zero_area(map, size, start, nr, align_mask);
+}
+EXPORT_SYMBOL(gen_pool_first_fit_order_align);
+
+/**
  * gen_pool_best_fit - find the best fitting region of memory
  * macthing the size requirement (no alignment constraint)
  * @map: The address to base the search on