ARM: integrate CMA with DMA-mapping subsystem

This patch adds support for CMA to dma-mapping subsystem for ARM
architecture. By default a global CMA area is used, but specific devices
are allowed to have their private memory areas if required (they can be
created with dma_declare_contiguous() function during board
initialisation).

Contiguous memory areas reserved for DMA are remapped with 2-level page
tables on boot. Once a buffer is requested, a low memory kernel mapping
is updated to to match requested memory access type.

GFP_ATOMIC allocations are performed from special pool which is created
early during boot. This way remapping page attributes is not needed on
allocation time.

CMA has been enabled unconditionally for ARMv6+ systems.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
CC: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Rob Clark <rob.clark@linaro.org>
Tested-by: Ohad Ben-Cohen <ohad@wizery.com>
Tested-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Tested-by: Robert Nelson <robertcnelson@gmail.com>
Tested-by: Barry Song <Baohua.Song@csr.com>

Documentation/kernel-parameters.txt

@@ -520,6 +520,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			a hypervisor.
 			Default: yes
 
+	coherent_pool=nn[KMG]	[ARM,KNL]
+			Sets the size of memory pool for coherent, atomic dma
+			allocations if Contiguous Memory Allocator (CMA) is used.
+
 	code_bytes	[X86] How many bytes of object code to print
 			in an oops report.
 			Range: 0 - 8192

arch/arm/Kconfig

@@ -4,6 +4,8 @@ config ARM
 	select HAVE_AOUT
 	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE if PCI || ISA || PCMCIA
+	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
+	select CMA if (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION

arch/arm/include/asm/dma-contiguous.h

+#ifndef ASMARM_DMA_CONTIGUOUS_H
+#define ASMARM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_CMA
+
+#include <linux/types.h>
+#include <asm-generic/dma-contiguous.h>
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
+
+#endif
+#endif
+
+#endif

arch/arm/include/asm/mach/map.h

@@ -30,6 +30,7 @@ struct map_desc {
 #define MT_MEMORY_DTCM		12
 #define MT_MEMORY_ITCM		13
 #define MT_MEMORY_SO		14
+#define MT_MEMORY_DMA_READY	15
 
 #ifdef CONFIG_MMU
 extern void iotable_init(struct map_desc *, int);

arch/arm/kernel/setup.c

@@ -81,6 +81,7 @@ __setup("fpe=", fpe_setup);
 extern void paging_init(struct machine_desc *desc);
 extern void sanity_check_meminfo(void);
 extern void reboot_setup(char *str);
+extern void setup_dma_zone(struct machine_desc *desc);
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
@@ -939,12 +940,8 @@ void __init setup_arch(char **cmdline_p)
 	machine_desc = mdesc;
 	machine_name = mdesc->name;
 
-#ifdef CONFIG_ZONE_DMA
-	if (mdesc->dma_zone_size) {
-		extern unsigned long arm_dma_zone_size;
-		arm_dma_zone_size = mdesc->dma_zone_size;
-	}
-#endif
+	setup_dma_zone(mdesc);
+
 	if (mdesc->restart_mode)
 		reboot_setup(&mdesc->restart_mode);
 

arch/arm/mm/init.c

@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/mach-types.h>
 #include <asm/memblock.h>
@@ -226,6 +227,17 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
 }
 #endif
 
+void __init setup_dma_zone(struct machine_desc *mdesc)
+{
+#ifdef CONFIG_ZONE_DMA
+	if (mdesc->dma_zone_size) {
+		arm_dma_zone_size = mdesc->dma_zone_size;
+		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
+	} else
+		arm_dma_limit = 0xffffffff;
+#endif
+}
+
 static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
 	unsigned long max_high)
 {
@@ -273,12 +285,9 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
 	 * Adjust the sizes according to any special requirements for
 	 * this machine type.
 	 */
-	if (arm_dma_zone_size) {
+	if (arm_dma_zone_size)
 		arm_adjust_dma_zone(zone_size, zhole_size,
 			arm_dma_zone_size >> PAGE_SHIFT);
-		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
-	} else
-		arm_dma_limit = 0xffffffff;
 #endif
 
 	free_area_init_node(0, zone_size, min, zhole_size);
@@ -364,6 +373,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 	if (mdesc->reserve)
 		mdesc->reserve();
 
+	/*
+	 * reserve memory for DMA contigouos allocations,
+	 * must come from DMA area inside low memory
+	 */
+	dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit));
+
 	arm_memblock_steal_permitted = false;
 	memblock_allow_resize();
 	memblock_dump_all();

arch/arm/mm/mm.h

@@ -67,5 +67,8 @@ extern u32 arm_dma_limit;
 #define arm_dma_limit ((u32)~0)
 #endif
 
+extern phys_addr_t arm_lowmem_limit;
+
 void __init bootmem_init(void);
 void arm_mm_memblock_reserve(void);
+void dma_contiguous_remap(void);

arch/arm/mm/mmu.c

@@ -288,6 +288,11 @@ static struct mem_type mem_types[] = {
 				PMD_SECT_UNCACHED | PMD_SECT_XN,
 		.domain    = DOMAIN_KERNEL,
 	},
+	[MT_MEMORY_DMA_READY] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.domain    = DOMAIN_KERNEL,
+	},
 };
 
 const struct mem_type *get_mem_type(unsigned int type)
@@ -429,6 +434,7 @@ static void __init build_mem_type_table(void)
 	if (arch_is_coherent() && cpu_is_xsc3()) {
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+		mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
 		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 	}
@@ -460,6 +466,7 @@ static void __init build_mem_type_table(void)
 			mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
 			mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 		}
@@ -512,6 +519,7 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
 	mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot;
 	mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
 
@@ -596,7 +604,7 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr,
 	 * L1 entries, whereas PGDs refer to a group of L1 entries making
 	 * up one logical pointer to an L2 table.
 	 */
-	if (((addr | end | phys) & ~SECTION_MASK) == 0) {
+	if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) {
 		pmd_t *p = pmd;
 
 #ifndef CONFIG_ARM_LPAE
@@ -814,7 +822,7 @@ static int __init early_vmalloc(char *arg)
 }
 early_param("vmalloc", early_vmalloc);
 
-static phys_addr_t lowmem_limit __initdata = 0;
+phys_addr_t arm_lowmem_limit __initdata = 0;
 
 void __init sanity_check_meminfo(void)
 {
@@ -897,8 +905,8 @@ void __init sanity_check_meminfo(void)
 			bank->size = newsize;
 		}
 #endif
-		if (!bank->highmem && bank->start + bank->size > lowmem_limit)
-			lowmem_limit = bank->start + bank->size;
+		if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit)
+			arm_lowmem_limit = bank->start + bank->size;
 
 		j++;
 	}
@@ -923,8 +931,8 @@ void __init sanity_check_meminfo(void)
 	}
 #endif
 	meminfo.nr_banks = j;
-	high_memory = __va(lowmem_limit - 1) + 1;
-	memblock_set_current_limit(lowmem_limit);
+	high_memory = __va(arm_lowmem_limit - 1) + 1;
+	memblock_set_current_limit(arm_lowmem_limit);
 }
 
 static inline void prepare_page_table(void)
@@ -949,8 +957,8 @@ static inline void prepare_page_table(void)
 	 * Find the end of the first block of lowmem.
 	 */
 	end = memblock.memory.regions[0].base + memblock.memory.regions[0].size;
-	if (end >= lowmem_limit)
-		end = lowmem_limit;
+	if (end >= arm_lowmem_limit)
+		end = arm_lowmem_limit;
 
 	/*
 	 * Clear out all the kernel space mappings, except for the first
@@ -1093,8 +1101,8 @@ static void __init map_lowmem(void)
 		phys_addr_t end = start + reg->size;
 		struct map_desc map;
 
-		if (end > lowmem_limit)
-			end = lowmem_limit;
+		if (end > arm_lowmem_limit)
+			end = arm_lowmem_limit;
 		if (start >= end)
 			break;
 
@@ -1115,11 +1123,12 @@ void __init paging_init(struct machine_desc *mdesc)
 {
 	void *zero_page;
 
-	memblock_set_current_limit(lowmem_limit);
+	memblock_set_current_limit(arm_lowmem_limit);
 
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
+	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();