diff options
Diffstat (limited to 'arch/arm/mm')
32 files changed, 1308 insertions, 777 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 7c8a7d8467bf..101b9681c08c 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -4,23 +4,6 @@ comment "Processor Type" # which CPUs we support in the kernel image, and the compiler instruction # optimiser behaviour. -# ARM610 -config CPU_ARM610 - bool "Support ARM610 processor" if ARCH_RPC - select CPU_32v3 - select CPU_CACHE_V3 - select CPU_CACHE_VIVT - select CPU_CP15_MMU - select CPU_COPY_V3 if MMU - select CPU_TLB_V3 if MMU - select CPU_PABRT_LEGACY - help - The ARM610 is the successor to the ARM3 processor - and was produced by VLSI Technology Inc. - - Say Y if you want support for the ARM610 processor. - Otherwise, say N. - # ARM7TDMI config CPU_ARM7TDMI bool "Support ARM7TDMI processor" @@ -36,25 +19,6 @@ config CPU_ARM7TDMI Say Y if you want support for the ARM7TDMI processor. Otherwise, say N. -# ARM710 -config CPU_ARM710 - bool "Support ARM710 processor" if ARCH_RPC - select CPU_32v3 - select CPU_CACHE_V3 - select CPU_CACHE_VIVT - select CPU_CP15_MMU - select CPU_COPY_V3 if MMU - select CPU_TLB_V3 if MMU - select CPU_PABRT_LEGACY - help - A 32-bit RISC microprocessor based on the ARM7 processor core - designed by Advanced RISC Machines Ltd. The ARM710 is the - successor to the ARM610 processor. It was released in - July 1994 by VLSI Technology Inc. - - Say Y if you want support for the ARM710 processor. - Otherwise, say N. - # ARM720T config CPU_ARM720T bool "Support ARM720T processor" if ARCH_INTEGRATOR @@ -530,9 +494,6 @@ config CPU_CACHE_FA if MMU # The copy-page model -config CPU_COPY_V3 - bool - config CPU_COPY_V4WT bool @@ -549,11 +510,6 @@ config CPU_COPY_V6 bool # This selects the TLB model -config CPU_TLB_V3 - bool - help - ARM Architecture Version 3 TLB. - config CPU_TLB_V4WT bool help @@ -731,7 +687,7 @@ config CPU_HIGH_VECTOR config CPU_ICACHE_DISABLE bool "Disable I-Cache (I-bit)" - depends on CPU_CP15 && !(CPU_ARM610 || CPU_ARM710 || CPU_ARM720T || CPU_ARM740T || CPU_XSCALE || CPU_XSC3) + depends on CPU_CP15 && !(CPU_ARM720T || CPU_ARM740T || CPU_XSCALE || CPU_XSC3) help Say Y here to disable the processor instruction cache. Unless you have a reason not to or are unsure, say N. diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index bca7e61928c7..8a9c4cb50a93 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -44,7 +44,6 @@ obj-$(CONFIG_CPU_CACHE_FA) += cache-fa.o AFLAGS_cache-v6.o :=-Wa,-march=armv6 AFLAGS_cache-v7.o :=-Wa,-march=armv7-a -obj-$(CONFIG_CPU_COPY_V3) += copypage-v3.o obj-$(CONFIG_CPU_COPY_V4WT) += copypage-v4wt.o obj-$(CONFIG_CPU_COPY_V4WB) += copypage-v4wb.o obj-$(CONFIG_CPU_COPY_FEROCEON) += copypage-feroceon.o @@ -54,7 +53,6 @@ obj-$(CONFIG_CPU_XSCALE) += copypage-xscale.o obj-$(CONFIG_CPU_XSC3) += copypage-xsc3.o obj-$(CONFIG_CPU_COPY_FA) += copypage-fa.o -obj-$(CONFIG_CPU_TLB_V3) += tlb-v3.o obj-$(CONFIG_CPU_TLB_V4WT) += tlb-v4.o obj-$(CONFIG_CPU_TLB_V4WB) += tlb-v4wb.o obj-$(CONFIG_CPU_TLB_V4WBI) += tlb-v4wbi.o @@ -66,8 +64,6 @@ obj-$(CONFIG_CPU_TLB_FA) += tlb-fa.o AFLAGS_tlb-v6.o :=-Wa,-march=armv6 AFLAGS_tlb-v7.o :=-Wa,-march=armv7-a -obj-$(CONFIG_CPU_ARM610) += proc-arm6_7.o -obj-$(CONFIG_CPU_ARM710) += proc-arm6_7.o obj-$(CONFIG_CPU_ARM7TDMI) += proc-arm7tdmi.o obj-$(CONFIG_CPU_ARM720T) += proc-arm720.o obj-$(CONFIG_CPU_ARM740T) += proc-arm740.o diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c index 1fbca05fe906..23a7643e9a87 100644 --- a/arch/arm/mm/cache-tauros2.c +++ b/arch/arm/mm/cache-tauros2.c @@ -108,6 +108,26 @@ static void tauros2_flush_range(unsigned long start, unsigned long end) dsb(); } + +static void tauros2_disable(void) +{ + __asm__ __volatile__ ( + "mcr p15, 1, %0, c7, c11, 0 @L2 Cache Clean All\n\t" + "mrc p15, 0, %0, c1, c0, 0\n\t" + "bic %0, %0, #(1 << 26)\n\t" + "mcr p15, 0, %0, c1, c0, 0 @Disable L2 Cache\n\t" + : : "r" (0x0)); +} + +static void tauros2_resume(void) +{ + __asm__ __volatile__ ( + "mcr p15, 1, %0, c7, c7, 0 @L2 Cache Invalidate All\n\t" + "mrc p15, 0, %0, c1, c0, 0\n\t" + "orr %0, %0, #(1 << 26)\n\t" + "mcr p15, 0, %0, c1, c0, 0 @Enable L2 Cache\n\t" + : : "r" (0x0)); +} #endif static inline u32 __init read_extra_features(void) @@ -194,6 +214,8 @@ void __init tauros2_init(void) outer_cache.inv_range = tauros2_inv_range; outer_cache.clean_range = tauros2_clean_range; outer_cache.flush_range = tauros2_flush_range; + outer_cache.disable = tauros2_disable; + outer_cache.resume = tauros2_resume; } #endif @@ -219,6 +241,8 @@ void __init tauros2_init(void) outer_cache.inv_range = tauros2_inv_range; outer_cache.clean_range = tauros2_clean_range; outer_cache.flush_range = tauros2_flush_range; + outer_cache.disable = tauros2_disable; + outer_cache.resume = tauros2_resume; } #endif diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S index c2301f226100..52e35f32eefb 100644 --- a/arch/arm/mm/cache-v3.S +++ b/arch/arm/mm/cache-v3.S @@ -78,6 +78,7 @@ ENTRY(v3_coherent_kern_range) * - end - virtual end address */ ENTRY(v3_coherent_user_range) + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index fd9bb7addc8d..022135d2b7e4 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -88,6 +88,7 @@ ENTRY(v4_coherent_kern_range) * - end - virtual end address */ ENTRY(v4_coherent_user_range) + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S index 4f2c14151ccb..8f1eeae340c8 100644 --- a/arch/arm/mm/cache-v4wb.S +++ b/arch/arm/mm/cache-v4wb.S @@ -167,9 +167,9 @@ ENTRY(v4wb_coherent_user_range) add r0, r0, #CACHE_DLINESIZE cmp r0, r1 blo 1b - mov ip, #0 - mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache - mcr p15, 0, ip, c7, c10, 4 @ drain WB + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mcr p15, 0, r0, c7, c10, 4 @ drain WB mov pc, lr diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S index 4d7b467631ce..b34a5f908a82 100644 --- a/arch/arm/mm/cache-v4wt.S +++ b/arch/arm/mm/cache-v4wt.S @@ -125,6 +125,7 @@ ENTRY(v4wt_coherent_user_range) add r0, r0, #CACHE_DLINESIZE cmp r0, r1 blo 1b + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index 74c2e5a33a4d..4b10760c56d6 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -12,6 +12,7 @@ #include <linux/linkage.h> #include <linux/init.h> #include <asm/assembler.h> +#include <asm/errno.h> #include <asm/unwind.h> #include "proc-macros.S" @@ -135,7 +136,6 @@ ENTRY(v6_coherent_user_range) 1: USER( mcr p15, 0, r0, c7, c10, 1 ) @ clean D line add r0, r0, #CACHE_LINE_SIZE -2: cmp r0, r1 blo 1b #endif @@ -154,13 +154,11 @@ ENTRY(v6_coherent_user_range) /* * Fault handling for the cache operation above. If the virtual address in r0 - * isn't mapped, just try the next page. + * isn't mapped, fail with -EFAULT. */ 9001: - mov r0, r0, lsr #12 - mov r0, r0, lsl #12 - add r0, r0, #4096 - b 2b + mov r0, #-EFAULT + mov pc, lr UNWIND(.fnend ) ENDPROC(v6_coherent_user_range) ENDPROC(v6_coherent_kern_range) diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index a655d3da386d..39e3fb3db801 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -13,6 +13,7 @@ #include <linux/linkage.h> #include <linux/init.h> #include <asm/assembler.h> +#include <asm/errno.h> #include <asm/unwind.h> #include "proc-macros.S" @@ -198,7 +199,6 @@ ENTRY(v7_coherent_user_range) add r12, r12, r2 cmp r12, r1 blo 2b -3: mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 6) @ invalidate BTB Inner Shareable ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB @@ -208,13 +208,11 @@ ENTRY(v7_coherent_user_range) /* * Fault handling for the cache operation above. If the virtual address in r0 - * isn't mapped, just try the next page. + * isn't mapped, fail with -EFAULT. */ 9001: - mov r12, r12, lsr #12 - mov r12, r12, lsl #12 - add r12, r12, #4096 - b 3b + mov r0, #-EFAULT + mov pc, lr UNWIND(.fnend ) ENDPROC(v7_coherent_kern_range) ENDPROC(v7_coherent_user_range) diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index ee9bb363d606..806cc4f63516 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -18,30 +18,39 @@ static DEFINE_RAW_SPINLOCK(cpu_asid_lock); unsigned int cpu_last_asid = ASID_FIRST_VERSION; -#ifdef CONFIG_SMP -DEFINE_PER_CPU(struct mm_struct *, current_mm); -#endif #ifdef CONFIG_ARM_LPAE -#define cpu_set_asid(asid) { \ - unsigned long ttbl, ttbh; \ - asm volatile( \ - " mrrc p15, 0, %0, %1, c2 @ read TTBR0\n" \ - " mov %1, %2, lsl #(48 - 32) @ set ASID\n" \ - " mcrr p15, 0, %0, %1, c2 @ set TTBR0\n" \ - : "=&r" (ttbl), "=&r" (ttbh) \ - : "r" (asid & ~ASID_MASK)); \ +void cpu_set_reserved_ttbr0(void) +{ + unsigned long ttbl = __pa(swapper_pg_dir); + unsigned long ttbh = 0; + + /* + * Set TTBR0 to swapper_pg_dir which contains only global entries. The + * ASID is set to 0. + */ + asm volatile( + " mcrr p15, 0, %0, %1, c2 @ set TTBR0\n" + : + : "r" (ttbl), "r" (ttbh)); + isb(); } #else -#define cpu_set_asid(asid) \ - asm(" mcr p15, 0, %0, c13, c0, 1\n" : : "r" (asid)) +void cpu_set_reserved_ttbr0(void) +{ + u32 ttb; + /* Copy TTBR1 into TTBR0 */ + asm volatile( + " mrc p15, 0, %0, c2, c0, 1 @ read TTBR1\n" + " mcr p15, 0, %0, c2, c0, 0 @ set TTBR0\n" + : "=r" (ttb)); + isb(); +} #endif /* * We fork()ed a process, and we need a new context for the child - * to run in. We reserve version 0 for initial tasks so we will - * always allocate an ASID. The ASID 0 is reserved for the TTBR - * register changing sequence. + * to run in. */ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) { @@ -51,9 +60,7 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) static void flush_context(void) { - /* set the reserved ASID before flushing the TLB */ - cpu_set_asid(0); - isb(); + cpu_set_reserved_ttbr0(); local_flush_tlb_all(); if (icache_is_vivt_asid_tagged()) { __flush_icache_all(); @@ -98,14 +105,7 @@ static void reset_context(void *info) { unsigned int asid; unsigned int cpu = smp_processor_id(); - struct mm_struct *mm = per_cpu(current_mm, cpu); - - /* - * Check if a current_mm was set on this CPU as it might still - * be in the early booting stages and using the reserved ASID. - */ - if (!mm) - return; + struct mm_struct *mm = current->active_mm; smp_rmb(); asid = cpu_last_asid + cpu + 1; @@ -114,8 +114,7 @@ static void reset_context(void *info) set_mm_context(mm, asid); /* set the new ASID */ - cpu_set_asid(mm->context.id); - isb(); + cpu_switch_mm(mm->pgd, mm); } #else diff --git a/arch/arm/mm/copypage-v3.c b/arch/arm/mm/copypage-v3.c deleted file mode 100644 index 3935bddd4769..000000000000 --- a/arch/arm/mm/copypage-v3.c +++ /dev/null @@ -1,81 +0,0 @@ -/* - * linux/arch/arm/mm/copypage-v3.c - * - * Copyright (C) 1995-1999 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/init.h> -#include <linux/highmem.h> - -/* - * ARMv3 optimised copy_user_highpage - * - * FIXME: do we need to handle cache stuff... - */ -static void __naked -v3_copy_user_page(void *kto, const void *kfrom) -{ - asm("\n\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia %0!, {r3, r4, ip, lr} @ 4+1\n\ -1: stmia %1!, {r3, r4, ip, lr} @ 4\n\ - ldmia %0!, {r3, r4, ip, lr} @ 4+1\n\ - stmia %1!, {r3, r4, ip, lr} @ 4\n\ - ldmia %0!, {r3, r4, ip, lr} @ 4+1\n\ - stmia %1!, {r3, r4, ip, lr} @ 4\n\ - ldmia %0!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia %1!, {r3, r4, ip, lr} @ 4\n\ - ldmneia %0!, {r3, r4, ip, lr} @ 4\n\ - bne 1b @ 1\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kfrom), "r" (kto), "I" (PAGE_SIZE / 64)); -} - -void v3_copy_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma) -{ - void *kto, *kfrom; - - kto = kmap_atomic(to); - kfrom = kmap_atomic(from); - v3_copy_user_page(kto, kfrom); - kunmap_atomic(kfrom); - kunmap_atomic(kto); -} - -/* - * ARMv3 optimised clear_user_page - * - * FIXME: do we need to handle cache stuff... - */ -void v3_clear_user_highpage(struct page *page, unsigned long vaddr) -{ - void *ptr, *kaddr = kmap_atomic(page); - asm volatile("\n\ - mov r1, %2 @ 1\n\ - mov r2, #0 @ 1\n\ - mov r3, #0 @ 1\n\ - mov ip, #0 @ 1\n\ - mov lr, #0 @ 1\n\ -1: stmia %0!, {r2, r3, ip, lr} @ 4\n\ - stmia %0!, {r2, r3, ip, lr} @ 4\n\ - stmia %0!, {r2, r3, ip, lr} @ 4\n\ - stmia %0!, {r2, r3, ip, lr} @ 4\n\ - subs r1, r1, #1 @ 1\n\ - bne 1b @ 1" - : "=r" (ptr) - : "0" (kaddr), "I" (PAGE_SIZE / 64) - : "r1", "r2", "r3", "ip", "lr"); - kunmap_atomic(kaddr); -} - -struct cpu_user_fns v3_user_fns __initdata = { - .cpu_clear_user_highpage = v3_clear_user_highpage, - .cpu_copy_user_highpage = v3_copy_user_highpage, -}; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index db23ae4aaaab..106c4c0ebccd 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -17,8 +17,12 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/dma-contiguous.h> #include <linux/highmem.h> +#include <linux/memblock.h> #include <linux/slab.h> +#include <linux/iommu.h> +#include <linux/vmalloc.h> #include <asm/memory.h> #include <asm/highmem.h> @@ -26,9 +30,112 @@ #include <asm/tlbflush.h> #include <asm/sizes.h> #include <asm/mach/arch.h> +#include <asm/dma-iommu.h> +#include <asm/mach/map.h> +#include <asm/system_info.h> +#include <asm/dma-contiguous.h> #include "mm.h" +/* + * The DMA API is built upon the notion of "buffer ownership". A buffer + * is either exclusively owned by the CPU (and therefore may be accessed + * by it) or exclusively owned by the DMA device. These helper functions + * represent the transitions between these two ownership states. + * + * Note, however, that on later ARMs, this notion does not work due to + * speculative prefetches. We model our approach on the assumption that + * the CPU does do speculative prefetches, which means we clean caches + * before transfers and delay cache invalidation until transfer completion. + * + */ +static void __dma_page_cpu_to_dev(struct page *, unsigned long, + size_t, enum dma_data_direction); +static void __dma_page_dev_to_cpu(struct page *, unsigned long, + size_t, enum dma_data_direction); + +/** + * arm_dma_map_page - map a portion of a page for streaming DMA + * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices + * @page: page that buffer resides in + * @offset: offset into page for start of buffer + * @size: size of buffer to map + * @dir: DMA transfer direction + * + * Ensure that any data held in the cache is appropriately discarded + * or written back. + * + * The device owns this memory once this call has completed. The CPU + * can regain ownership by calling dma_unmap_page(). + */ +static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(page, offset, size, dir); + return pfn_to_dma(dev, page_to_pfn(page)) + offset; +} + +/** + * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page() + * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices + * @handle: DMA address of buffer + * @size: size of buffer (same as passed to dma_map_page) + * @dir: DMA transfer direction (same as passed to dma_map_page) + * + * Unmap a page streaming mode DMA translation. The handle and size + * must match what was provided in the previous dma_map_page() call. + * All other usages are undefined. + * + * After this call, reads by the CPU to the buffer are guaranteed to see + * whatever the device wrote there. + */ +static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), + handle & ~PAGE_MASK, size, dir); +} + +static void arm_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + unsigned int offset = handle & (PAGE_SIZE - 1); + struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(page, offset, size, dir); +} + +static void arm_dma_sync_single_for_device(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + unsigned int offset = handle & (PAGE_SIZE - 1); + struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(page, offset, size, dir); +} + +static int arm_dma_set_mask(struct device *dev, u64 dma_mask); + +struct dma_map_ops arm_dma_ops = { + .alloc = arm_dma_alloc, + .free = arm_dma_free, + .mmap = arm_dma_mmap, + .map_page = arm_dma_map_page, + .unmap_page = arm_dma_unmap_page, + .map_sg = arm_dma_map_sg, + .unmap_sg = arm_dma_unmap_sg, + .sync_single_for_cpu = arm_dma_sync_single_for_cpu, + .sync_single_for_device = arm_dma_sync_single_for_device, + .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, + .sync_sg_for_device = arm_dma_sync_sg_for_device, + .set_dma_mask = arm_dma_set_mask, +}; +EXPORT_SYMBOL(arm_dma_ops); + static u64 get_coherent_dma_mask(struct device *dev) { u64 mask = (u64)arm_dma_limit; @@ -56,6 +163,21 @@ static u64 get_coherent_dma_mask(struct device *dev) return mask; } +static void __dma_clear_buffer(struct page *page, size_t size) +{ + void *ptr; + /* + * Ensure that the allocated pages are zeroed, and that any data + * lurking in the kernel direct-mapped region is invalidated. + */ + ptr = page_address(page); + if (ptr) { + memset(ptr, 0, size); + dmac_flush_range(ptr, ptr + size); + outer_flush_range(__pa(ptr), __pa(ptr) + size); + } +} + /* * Allocate a DMA buffer for 'dev' of size 'size' using the * specified gfp mask. Note that 'size' must be page aligned. @@ -64,23 +186,6 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf { unsigned long order = get_order(size); struct page *page, *p, *e; - void *ptr; - u64 mask = get_coherent_dma_mask(dev); - -#ifdef CONFIG_DMA_API_DEBUG - u64 limit = (mask + 1) & ~mask; - if (limit && size >= limit) { - dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n", - size, mask); - return NULL; - } -#endif - - if (!mask) - return NULL; - - if (mask < 0xffffffffULL) - gfp |= GFP_DMA; page = alloc_pages(gfp, order); if (!page) @@ -93,14 +198,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++) __free_page(p); - /* - * Ensure that the allocated pages are zeroed, and that any data - * lurking in the kernel direct-mapped region is invalidated. - */ - ptr = page_address(page); - memset(ptr, 0, size); - dmac_flush_range(ptr, ptr + size); - outer_flush_range(__pa(ptr), __pa(ptr) + size); + __dma_clear_buffer(page, size); return page; } @@ -170,6 +268,9 @@ static int __init consistent_init(void) unsigned long base = consistent_base; unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT; + if (IS_ENABLED(CONFIG_CMA) && !IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) + return 0; + consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL); if (!consistent_pte) { pr_err("%s: no memory\n", __func__); @@ -184,14 +285,14 @@ static int __init consistent_init(void) pud = pud_alloc(&init_mm, pgd, base); if (!pud) { - printk(KERN_ERR "%s: no pud tables\n", __func__); + pr_err("%s: no pud tables\n", __func__); ret = -ENOMEM; break; } pmd = pmd_alloc(&init_mm, pud, base); if (!pmd) { - printk(KERN_ERR "%s: no pmd tables\n", __func__); + pr_err("%s: no pmd tables\n", __func__); ret = -ENOMEM; break; } @@ -199,7 +300,7 @@ static int __init consistent_init(void) pte = pte_alloc_kernel(pmd, base); if (!pte) { - printk(KERN_ERR "%s: no pte tables\n", __func__); + pr_err("%s: no pte tables\n", __func__); ret = -ENOMEM; break; } @@ -210,9 +311,101 @@ static int __init consistent_init(void) return ret; } - core_initcall(consistent_init); +static void *__alloc_from_contiguous(struct device *dev, size_t size, + pgprot_t prot, struct page **ret_page); + +static struct arm_vmregion_head coherent_head = { + .vm_lock = __SPIN_LOCK_UNLOCKED(&coherent_head.vm_lock), + .vm_list = LIST_HEAD_INIT(coherent_head.vm_list), +}; + +size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8; + +static int __init early_coherent_pool(char *p) +{ + coherent_pool_size = memparse(p, &p); + return 0; +} +early_param("coherent_pool", early_coherent_pool); + +/* + * Initialise the coherent pool for atomic allocations. + */ +static int __init coherent_init(void) +{ + pgprot_t prot = pgprot_dmacoherent(pgprot_kernel); + size_t size = coherent_pool_size; + struct page *page; + void *ptr; + + if (!IS_ENABLED(CONFIG_CMA)) + return 0; + + ptr = __alloc_from_contiguous(NULL, size, prot, &page); + if (ptr) { + coherent_head.vm_start = (unsigned long) ptr; + coherent_head.vm_end = (unsigned long) ptr + size; + printk(KERN_INFO "DMA: preallocated %u KiB pool for atomic coherent allocations\n", + (unsigned)size / 1024); + return 0; + } + printk(KERN_ERR "DMA: failed to allocate %u KiB pool for atomic coherent allocation\n", + (unsigned)size / 1024); + return -ENOMEM; +} +/* + * CMA is activated by core_initcall, so we must be called after it. + */ +postcore_initcall(coherent_init); + +struct dma_contig_early_reserve { + phys_addr_t base; + unsigned long size; +}; + +static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata; + +static int dma_mmu_remap_num __initdata; + +void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) +{ + dma_mmu_remap[dma_mmu_remap_num].base = base; + dma_mmu_remap[dma_mmu_remap_num].size = size; + dma_mmu_remap_num++; +} + +void __init dma_contiguous_remap(void) +{ + int i; + for (i = 0; i < dma_mmu_remap_num; i++) { + phys_addr_t start = dma_mmu_remap[i].base; + phys_addr_t end = start + dma_mmu_remap[i].size; + struct map_desc map; + unsigned long addr; + + if (end > arm_lowmem_limit) + end = arm_lowmem_limit; + if (start >= end) + return; + + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = end - start; + map.type = MT_MEMORY_DMA_READY; + + /* + * Clear previous low-memory mapping + */ + for (addr = __phys_to_virt(start); addr < __phys_to_virt(end); + addr += PMD_SIZE) + pmd_clear(pmd_off_k(addr)); + + iotable_init(&map, 1); + } +} + static void * __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, const void *caller) @@ -222,7 +415,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, int bit; if (!consistent_pte) { - printk(KERN_ERR "%s: not initialised\n", __func__); + pr_err("%s: not initialised\n", __func__); dump_stack(); return NULL; } @@ -249,7 +442,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1); pte = consistent_pte[idx] + off; - c->vm_pages = page; + c->priv = page; do { BUG_ON(!pte_none(*pte)); @@ -281,14 +474,14 @@ static void __dma_free_remap(void *cpu_addr, size_t size) c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr); if (!c) { - printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n", + pr_err("%s: trying to free invalid coherent area: %p\n", __func__, cpu_addr); dump_stack(); return; } if ((c->vm_end - c->vm_start) != size) { - printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n", + pr_err("%s: freeing wrong coherent size (%ld != %d)\n", __func__, c->vm_end - c->vm_start, size); dump_stack(); size = c->vm_end - c->vm_start; @@ -310,8 +503,8 @@ static void __dma_free_remap(void *cpu_addr, size_t size) } if (pte_none(pte) || !pte_present(pte)) - printk(KERN_CRIT "%s: bad page in kernel page table\n", - __func__); + pr_crit("%s: bad page in kernel page table\n", + __func__); } while (size -= PAGE_SIZE); flush_tlb_kernel_range(c->vm_start, c->vm_end); @@ -319,20 +512,182 @@ static void __dma_free_remap(void *cpu_addr, size_t size) arm_vmregion_free(&consistent_head, c); } +static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr, + void *data) +{ + struct page *page = virt_to_page(addr); + pgprot_t prot = *(pgprot_t *)data; + + set_pte_ext(pte, mk_pte(page, prot), 0); + return 0; +} + +static void __dma_remap(struct page *page, size_t size, pgprot_t prot) +{ + unsigned long start = (unsigned long) page_address(page); + unsigned end = start + size; + + apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot); + dsb(); + flush_tlb_kernel_range(start, end); +} + +static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp, + pgprot_t prot, struct page **ret_page, + const void *caller) +{ + struct page *page; + void *ptr; + page = __dma_alloc_buffer(dev, size, gfp); + if (!page) + return NULL; + + ptr = __dma_alloc_remap(page, size, gfp, prot, caller); + if (!ptr) { + __dma_free_buffer(page, size); + return NULL; + } + + *ret_page = page; + return ptr; +} + +static void *__alloc_from_pool(struct device *dev, size_t size, + struct page **ret_page, const void *caller) +{ + struct arm_vmregion *c; + size_t align; + + if (!coherent_head.vm_start) { + printk(KERN_ERR "%s: coherent pool not initialised!\n", + __func__); + dump_stack(); + return NULL; + } + + /* + * Align the region allocation - allocations from pool are rather + * small, so align them to their order in pages, minimum is a page + * size. This helps reduce fragmentation of the DMA space. + */ + align = PAGE_SIZE << get_order(size); + c = arm_vmregion_alloc(&coherent_head, align, size, 0, caller); + if (c) { + void *ptr = (void *)c->vm_start; + struct page *page = virt_to_page(ptr); + *ret_page = page; + return ptr; + } + return NULL; +} + +static int __free_from_pool(void *cpu_addr, size_t size) +{ + unsigned long start = (unsigned long)cpu_addr; + unsigned long end = start + size; + struct arm_vmregion *c; + + if (start < coherent_head.vm_start || end > coherent_head.vm_end) + return 0; + + c = arm_vmregion_find_remove(&coherent_head, (unsigned long)start); + + if ((c->vm_end - c->vm_start) != size) { + printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n", + __func__, c->vm_end - c->vm_start, size); + dump_stack(); + size = c->vm_end - c->vm_start; + } + + arm_vmregion_free(&coherent_head, c); + return 1; +} + +static void *__alloc_from_contiguous(struct device *dev, size_t size, + pgprot_t prot, struct page **ret_page) +{ + unsigned long order = get_order(size); + size_t count = size >> PAGE_SHIFT; + struct page *page; + + page = dma_alloc_from_contiguous(dev, count, order); + if (!page) + return NULL; + + __dma_clear_buffer(page, size); + __dma_remap(page, size, prot); + + *ret_page = page; + return page_address(page); +} + +static void __free_from_contiguous(struct device *dev, struct page *page, + size_t size) +{ + __dma_remap(page, size, pgprot_kernel); + dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); +} + +static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot) +{ + prot = dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs) ? + pgprot_writecombine(prot) : + pgprot_dmacoherent(prot); + return prot; +} + +#define nommu() 0 + #else /* !CONFIG_MMU */ -#define __dma_alloc_remap(page, size, gfp, prot, c) page_address(page) -#define __dma_free_remap(addr, size) do { } while (0) +#define nommu() 1 + +#define __get_dma_pgprot(attrs, prot) __pgprot(0) +#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c) NULL +#define __alloc_from_pool(dev, size, ret_page, c) NULL +#define __alloc_from_contiguous(dev, size, prot, ret) NULL +#define __free_from_pool(cpu_addr, size) 0 +#define __free_from_contiguous(dev, page, size) do { } while (0) +#define __dma_free_remap(cpu_addr, size) do { } while (0) #endif /* CONFIG_MMU */ -static void * -__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, - pgprot_t prot, const void *caller) +static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp, + struct page **ret_page) +{ + struct page *page; + page = __dma_alloc_buffer(dev, size, gfp); + if (!page) + return NULL; + + *ret_page = page; + return page_address(page); +} + + + +static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, pgprot_t prot, const void *caller) { + u64 mask = get_coherent_dma_mask(dev); struct page *page; void *addr; +#ifdef CONFIG_DMA_API_DEBUG + u64 limit = (mask + 1) & ~mask; + if (limit && size >= limit) { + dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n", + size, mask); + return NULL; + } +#endif + + if (!mask) + return NULL; + + 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 @@ -342,22 +697,20 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, */ gfp &= ~(__GFP_COMP); - *handle = ~0; + *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - page = __dma_alloc_buffer(dev, size, gfp); - if (!page) - return NULL; - - if (!arch_is_coherent()) - addr = __dma_alloc_remap(page, size, gfp, prot, caller); + if (arch_is_coherent() || nommu()) + addr = __alloc_simple_buffer(dev, size, gfp, &page); + else if (!IS_ENABLED(CONFIG_CMA)) + addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); + else if (gfp & GFP_ATOMIC) + addr = __alloc_from_pool(dev, size, &page, caller); else - addr = page_address(page); + addr = __alloc_from_contiguous(dev, size, prot, &page); if (addr) *handle = pfn_to_dma(dev, page_to_pfn(page)); - else - __dma_free_buffer(page, size); return addr; } @@ -366,138 +719,71 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, * Allocate DMA-coherent memory space and return both the kernel remapped * virtual and bus address for that space. */ -void * -dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp) +void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, struct dma_attrs *attrs) { + pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); void *memory; if (dma_alloc_from_coherent(dev, size, handle, &memory)) return memory; - return __dma_alloc(dev, size, handle, gfp, - pgprot_dmacoherent(pgprot_kernel), + return __dma_alloc(dev, size, handle, gfp, prot, __builtin_return_address(0)); } -EXPORT_SYMBOL(dma_alloc_coherent); /* - * Allocate a writecombining region, in much the same way as - * dma_alloc_coherent above. + * Create userspace mapping for the DMA-coherent memory. */ -void * -dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp) -{ - return __dma_alloc(dev, size, handle, gfp, - pgprot_writecombine(pgprot_kernel), - __builtin_return_address(0)); -} -EXPORT_SYMBOL(dma_alloc_writecombine); - -static int dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size) +int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) { int ret = -ENXIO; #ifdef CONFIG_MMU - unsigned long user_size, kern_size; - struct arm_vmregion *c; + unsigned long pfn = dma_to_pfn(dev, dma_addr); + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); - user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; - c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr); - if (c) { - unsigned long off = vma->vm_pgoff; - - kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT; - - if (off < kern_size && - user_size <= (kern_size - off)) { - ret = remap_pfn_range(vma, vma->vm_start, - page_to_pfn(c->vm_pages) + off, - user_size << PAGE_SHIFT, - vma->vm_page_prot); - } - } + ret = remap_pfn_range(vma, vma->vm_start, + pfn + vma->vm_pgoff, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); #endif /* CONFIG_MMU */ return ret; } -int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size) -{ - vma->vm_page_prot = pgprot_dmacoherent(vma->vm_page_prot); - return dma_mmap(dev, vma, cpu_addr, dma_addr, size); -} -EXPORT_SYMBOL(dma_mmap_coherent); - -int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size) -{ - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - return dma_mmap(dev, vma, cpu_addr, dma_addr, size); -} -EXPORT_SYMBOL(dma_mmap_writecombine); - /* - * free a page as defined by the above mapping. - * Must not be called with IRQs disabled. + * Free a buffer as defined by the above mapping. */ -void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle) +void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs) { - WARN_ON(irqs_disabled()); + struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); if (dma_release_from_coherent(dev, get_order(size), cpu_addr)) return; size = PAGE_ALIGN(size); - if (!arch_is_coherent()) + if (arch_is_coherent() || nommu()) { + __dma_free_buffer(page, size); + } else if (!IS_ENABLED(CONFIG_CMA)) { __dma_free_remap(cpu_addr, size); - - __dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size); -} -EXPORT_SYMBOL(dma_free_coherent); - -/* - * Make an area consistent for devices. - * Note: Drivers should NOT use this function directly, as it will break - * platforms with CONFIG_DMABOUNCE. - * Use the driver DMA support - see dma-mapping.h (dma_sync_*) - */ -void ___dma_single_cpu_to_dev(const void *kaddr, size_t size, - enum dma_data_direction dir) -{ - unsigned long paddr; - - BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1)); - - dmac_map_area(kaddr, size, dir); - - paddr = __pa(kaddr); - if (dir == DMA_FROM_DEVICE) { - outer_inv_range(paddr, paddr + size); + __dma_free_buffer(page, size); } else { - outer_clean_range(paddr, paddr + size); - } - /* FIXME: non-speculating: flush on bidirectional mappings? */ -} -EXPORT_SYMBOL(___dma_single_cpu_to_dev); - -void ___dma_single_dev_to_cpu(const void *kaddr, size_t size, - enum dma_data_direction dir) -{ - BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1)); - - /* FIXME: non-speculating: not required */ - /* don't bother invalidating if DMA to device */ - if (dir != DMA_TO_DEVICE) { - unsigned long paddr = __pa(kaddr); - outer_inv_range(paddr, paddr + size); + if (__free_from_pool(cpu_addr, size)) + return; + /* + * Non-atomic allocations cannot be freed with IRQs disabled + */ + WARN_ON(irqs_disabled()); + __free_from_contiguous(dev, page, size); } - - dmac_unmap_area(kaddr, size, dir); } -EXPORT_SYMBOL(___dma_single_dev_to_cpu); static void dma_cache_maint_page(struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, @@ -543,7 +829,13 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, } while (left); } -void ___dma_page_cpu_to_dev(struct page *page, unsigned long off, +/* + * Make an area consistent for devices. + * Note: Drivers should NOT use this function directly, as it will break + * platforms with CONFIG_DMABOUNCE. + * Use the driver DMA support - see dma-mapping.h (dma_sync_*) + */ +static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { unsigned long paddr; @@ -558,9 +850,8 @@ void ___dma_page_cpu_to_dev(struct page *page, unsigned long off, } /* FIXME: non-speculating: flush on bidirectional mappings? */ } -EXPORT_SYMBOL(___dma_page_cpu_to_dev); -void ___dma_page_dev_to_cpu(struct page *page, unsigned long off, +static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { unsigned long paddr = page_to_phys(page) + off; @@ -578,10 +869,9 @@ void ___dma_page_dev_to_cpu(struct page *page, unsigned long off, if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE) set_bit(PG_dcache_clean, &page->flags); } -EXPORT_SYMBOL(___dma_page_dev_to_cpu); /** - * dma_map_sg - map a set of SG buffers for streaming mode DMA + * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to map @@ -596,32 +886,32 @@ EXPORT_SYMBOL(___dma_page_dev_to_cpu); * Device ownership issues as mentioned for dma_map_single are the same * here. */ -int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir) +int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i, j; - BUG_ON(!valid_dma_direction(dir)); - for_each_sg(sg, s, nents, i) { - s->dma_address = __dma_map_page(dev, sg_page(s), s->offset, - s->length, dir); +#ifdef CONFIG_NEED_SG_DMA_LENGTH + s->dma_length = s->length; +#endif + s->dma_address = ops->map_page(dev, sg_page(s), s->offset, + s->length, dir, attrs); if (dma_mapping_error(dev, s->dma_address)) goto bad_mapping; } - debug_dma_map_sg(dev, sg, nents, nents, dir); return nents; bad_mapping: for_each_sg(sg, s, i, j) - __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir); + ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); return 0; } -EXPORT_SYMBOL(dma_map_sg); /** - * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg + * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to unmap (same as was passed to dma_map_sg) @@ -630,70 +920,55 @@ EXPORT_SYMBOL(dma_map_sg); * Unmap a set of streaming mode DMA translations. Again, CPU access * rules concerning calls here are the same as for dma_unmap_single(). */ -void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir) +void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; - int i; - debug_dma_unmap_sg(dev, sg, nents, dir); + int i; for_each_sg(sg, s, nents, i) - __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir); + ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs); } -EXPORT_SYMBOL(dma_unmap_sg); /** - * dma_sync_sg_for_cpu + * arm_dma_sync_sg_for_cpu * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to map (returned from dma_map_sg) * @dir: DMA transfer direction (same as was passed to dma_map_sg) */ -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, +void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i; - for_each_sg(sg, s, nents, i) { - if (!dmabounce_sync_for_cpu(dev, sg_dma_address(s), 0, - sg_dma_len(s), dir)) - continue; - - __dma_page_dev_to_cpu(sg_page(s), s->offset, - s->length, dir); - } - - debug_dma_sync_sg_for_cpu(dev, sg, nents, dir); + for_each_sg(sg, s, nents, i) + ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length, + dir); } -EXPORT_SYMBOL(dma_sync_sg_for_cpu); /** - * dma_sync_sg_for_device + * arm_dma_sync_sg_for_device * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @sg: list of buffers * @nents: number of buffers to map (returned from dma_map_sg) * @dir: DMA transfer direction (same as was passed to dma_map_sg) */ -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { + struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; int i; - for_each_sg(sg, s, nents, i) { - if (!dmabounce_sync_for_device(dev, sg_dma_address(s), 0, - sg_dma_len(s), dir)) - continue; - - __dma_page_cpu_to_dev(sg_page(s), s->offset, - s->length, dir); - } - - debug_dma_sync_sg_for_device(dev, sg, nents, dir); + for_each_sg(sg, s, nents, i) + ops->sync_single_for_device(dev, sg_dma_address(s), s->length, + dir); } -EXPORT_SYMBOL(dma_sync_sg_for_device); /* * Return whether the given device DMA address mask can be supported @@ -709,18 +984,15 @@ int dma_supported(struct device *dev, u64 mask) } EXPORT_SYMBOL(dma_supported); -int dma_set_mask(struct device *dev, u64 dma_mask) +static int arm_dma_set_mask(struct device *dev, u64 dma_mask) { if (!dev->dma_mask || !dma_supported(dev, dma_mask)) return -EIO; -#ifndef CONFIG_DMABOUNCE *dev->dma_mask = dma_mask; -#endif return 0; } -EXPORT_SYMBOL(dma_set_mask); #define PREALLOC_DMA_DEBUG_ENTRIES 4096 @@ -733,3 +1005,679 @@ static int __init dma_debug_do_init(void) return 0; } fs_initcall(dma_debug_do_init); + +#ifdef CONFIG_ARM_DMA_USE_IOMMU + +/* IOMMU */ + +static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping, + size_t size) +{ + unsigned int order = get_order(size); + unsigned int align = 0; + unsigned int count, start; + unsigned long flags; + + count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) + + (1 << mapping->order) - 1) >> mapping->order; + + if (order > mapping->order) + align = (1 << (order - mapping->order)) - 1; + + spin_lock_irqsave(&mapping->lock, flags); + start = bitmap_find_next_zero_area(mapping->bitmap, mapping->bits, 0, + count, align); + if (start > mapping->bits) { + spin_unlock_irqrestore(&mapping->lock, flags); + return DMA_ERROR_CODE; + } + + bitmap_set(mapping->bitmap, start, count); + spin_unlock_irqrestore(&mapping->lock, flags); + + return mapping->base + (start << (mapping->order + PAGE_SHIFT)); +} + +static inline void __free_iova(struct dma_iommu_mapping *mapping, + dma_addr_t addr, size_t size) +{ + unsigned int start = (addr - mapping->base) >> + (mapping->order + PAGE_SHIFT); + unsigned int count = ((size >> PAGE_SHIFT) + + (1 << mapping->order) - 1) >> mapping->order; + unsigned long flags; + + spin_lock_irqsave(&mapping->lock, flags); + bitmap_clear(mapping->bitmap, start, count); + spin_unlock_irqrestore(&mapping->lock, flags); +} + +static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t gfp) +{ + struct page **pages; + int count = size >> PAGE_SHIFT; + int array_size = count * sizeof(struct page *); + int i = 0; + + if (array_size <= PAGE_SIZE) + pages = kzalloc(array_size, gfp); + else + pages = vzalloc(array_size); + if (!pages) + return NULL; + + while (count) { + int j, order = __ffs(count); + + pages[i] = alloc_pages(gfp | __GFP_NOWARN, order); + while (!pages[i] && order) + pages[i] = alloc_pages(gfp | __GFP_NOWARN, --order); + if (!pages[i]) + goto error; + + if (order) + split_page(pages[i], order); + j = 1 << order; + while (--j) + pages[i + j] = pages[i] + j; + + __dma_clear_buffer(pages[i], PAGE_SIZE << order); + i += 1 << order; + count -= 1 << order; + } + + return pages; +error: + while (--i) + if (pages[i]) + __free_pages(pages[i], 0); + if (array_size < PAGE_SIZE) + kfree(pages); + else + vfree(pages); + return NULL; +} + +static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t size) +{ + int count = size >> PAGE_SHIFT; + int array_size = count * sizeof(struct page *); + int i; + for (i = 0; i < count; i++) + if (pages[i]) + __free_pages(pages[i], 0); + if (array_size < PAGE_SIZE) + kfree(pages); + else + vfree(pages); + return 0; +} + +/* + * Create a CPU mapping for a specified pages + */ +static void * +__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot) +{ + struct arm_vmregion *c; + size_t align; + size_t count = size >> PAGE_SHIFT; + int bit; + + if (!consistent_pte[0]) { + pr_err("%s: not initialised\n", __func__); + dump_stack(); + return NULL; + } + + /* + * Align the virtual region allocation - maximum alignment is + * a section size, minimum is a page size. This helps reduce + * fragmentation of the DMA space, and also prevents allocations + * smaller than a section from crossing a section boundary. + */ + bit = fls(size - 1); + if (bit > SECTION_SHIFT) + bit = SECTION_SHIFT; + align = 1 << bit; + + /* + * Allocate a virtual address in the consistent mapping region. + */ + c = arm_vmregion_alloc(&consistent_head, align, size, + gfp & ~(__GFP_DMA | __GFP_HIGHMEM), NULL); + if (c) { + pte_t *pte; + int idx = CONSISTENT_PTE_INDEX(c->vm_start); + int i = 0; + u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1); + + pte = consistent_pte[idx] + off; + c->priv = pages; + + do { + BUG_ON(!pte_none(*pte)); + + set_pte_ext(pte, mk_pte(pages[i], prot), 0); + pte++; + off++; + i++; + if (off >= PTRS_PER_PTE) { + off = 0; + pte = consistent_pte[++idx]; + } + } while (i < count); + + dsb(); + + return (void *)c->vm_start; + } + return NULL; +} + +/* + * Create a mapping in device IO address space for specified pages + */ +static dma_addr_t +__iommu_create_mapping(struct device *dev, struct page **pages, size_t size) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + dma_addr_t dma_addr, iova; + int i, ret = DMA_ERROR_CODE; + + dma_addr = __alloc_iova(mapping, size); + if (dma_addr == DMA_ERROR_CODE) + return dma_addr; + + iova = dma_addr; + for (i = 0; i < count; ) { + unsigned int next_pfn = page_to_pfn(pages[i]) + 1; + phys_addr_t phys = page_to_phys(pages[i]); + unsigned int len, j; + + for (j = i + 1; j < count; j++, next_pfn++) + if (page_to_pfn(pages[j]) != next_pfn) + break; + + len = (j - i) << PAGE_SHIFT; + ret = iommu_map(mapping->domain, iova, phys, len, 0); + if (ret < 0) + goto fail; + iova += len; + i = j; + } + return dma_addr; +fail: + iommu_unmap(mapping->domain, dma_addr, iova-dma_addr); + __free_iova(mapping, dma_addr, size); + return DMA_ERROR_CODE; +} + +static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + + /* + * add optional in-page offset from iova to size and align + * result to page size + */ + size = PAGE_ALIGN((iova & ~PAGE_MASK) + size); + iova &= PAGE_MASK; + + iommu_unmap(mapping->domain, iova, size); + __free_iova(mapping, iova, size); + return 0; +} + +static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) +{ + pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + struct page **pages; + void *addr = NULL; + + *handle = DMA_ERROR_CODE; + size = PAGE_ALIGN(size); + + pages = __iommu_alloc_buffer(dev, size, gfp); + if (!pages) + return NULL; + + *handle = __iommu_create_mapping(dev, pages, size); + if (*handle == DMA_ERROR_CODE) + goto err_buffer; + + addr = __iommu_alloc_remap(pages, size, gfp, prot); + if (!addr) + goto err_mapping; + + return addr; + +err_mapping: + __iommu_remove_mapping(dev, *handle, size); +err_buffer: + __iommu_free_buffer(dev, pages, size); + return NULL; +} + +static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) +{ + struct arm_vmregion *c; + + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); + c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr); + + if (c) { + struct page **pages = c->priv; + + unsigned long uaddr = vma->vm_start; + unsigned long usize = vma->vm_end - vma->vm_start; + int i = 0; + + do { + int ret; + + ret = vm_insert_page(vma, uaddr, pages[i++]); + if (ret) { + pr_err("Remapping memory, error: %d\n", ret); + return ret; + } + + uaddr += PAGE_SIZE; + usize -= PAGE_SIZE; + } while (usize > 0); + } + return 0; +} + +/* + * free a page as defined by the above mapping. + * Must not be called with IRQs disabled. + */ +void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs) +{ + struct arm_vmregion *c; + size = PAGE_ALIGN(size); + + c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr); + if (c) { + struct page **pages = c->priv; + __dma_free_remap(cpu_addr, size); + __iommu_remove_mapping(dev, handle, size); + __iommu_free_buffer(dev, pages, size); + } +} + +/* + * Map a part of the scatter-gather list into contiguous io address space + */ +static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, + size_t size, dma_addr_t *handle, + enum dma_data_direction dir) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova, iova_base; + int ret = 0; + unsigned int count; + struct scatterlist *s; + + size = PAGE_ALIGN(size); + *handle = DMA_ERROR_CODE; + + iova_base = iova = __alloc_iova(mapping, size); + if (iova == DMA_ERROR_CODE) + return -ENOMEM; + + for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) { + phys_addr_t phys = page_to_phys(sg_page(s)); + unsigned int len = PAGE_ALIGN(s->offset + s->length); + + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); + + ret = iommu_map(mapping->domain, iova, phys, len, 0); + if (ret < 0) + goto fail; + count += len >> PAGE_SHIFT; + iova += len; + } + *handle = iova_base; + + return 0; +fail: + iommu_unmap(mapping->domain, iova_base, count * PAGE_SIZE); + __free_iova(mapping, iova_base, size); + return ret; +} + +/** + * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map + * @dir: DMA transfer direction + * + * Map a set of buffers described by scatterlist in streaming mode for DMA. + * The scatter gather list elements are merged together (if possible) and + * tagged with the appropriate dma address and length. They are obtained via + * sg_dma_{address,length}. + */ +int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + struct scatterlist *s = sg, *dma = sg, *start = sg; + int i, count = 0; + unsigned int offset = s->offset; + unsigned int size = s->offset + s->length; + unsigned int max = dma_get_max_seg_size(dev); + + for (i = 1; i < nents; i++) { + s = sg_next(s); + + s->dma_address = DMA_ERROR_CODE; + s->dma_length = 0; + + if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) { + if (__map_sg_chunk(dev, start, size, &dma->dma_address, + dir) < 0) + goto bad_mapping; + + dma->dma_address += offset; + dma->dma_length = size - offset; + + size = offset = s->offset; + start = s; + dma = sg_next(dma); + count += 1; + } + size += s->length; + } + if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir) < 0) + goto bad_mapping; + + dma->dma_address += offset; + dma->dma_length = size - offset; + + return count+1; + +bad_mapping: + for_each_sg(sg, s, count, i) + __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s)); + return 0; +} + +/** + * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to unmap (same as was passed to dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + * + * Unmap a set of streaming mode DMA translations. Again, CPU access + * rules concerning calls here are the same as for dma_unmap_single(). + */ +void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) { + if (sg_dma_len(s)) + __iommu_remove_mapping(dev, sg_dma_address(s), + sg_dma_len(s)); + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(sg_page(s), s->offset, + s->length, dir); + } +} + +/** + * arm_iommu_sync_sg_for_cpu + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map (returned from dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + */ +void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); + +} + +/** + * arm_iommu_sync_sg_for_device + * @dev: valid struct device pointer + * @sg: list of buffers + * @nents: number of buffers to map (returned from dma_map_sg) + * @dir: DMA transfer direction (same as was passed to dma_map_sg) + */ +void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); +} + + +/** + * arm_iommu_map_page + * @dev: valid struct device pointer + * @page: page that buffer resides in + * @offset: offset into page for start of buffer + * @size: size of buffer to map + * @dir: DMA transfer direction + * + * IOMMU aware version of arm_dma_map_page() + */ +static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t dma_addr; + int ret, len = PAGE_ALIGN(size + offset); + + if (!arch_is_coherent()) + __dma_page_cpu_to_dev(page, offset, size, dir); + + dma_addr = __alloc_iova(mapping, len); + if (dma_addr == DMA_ERROR_CODE) + return dma_addr; + + ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, 0); + if (ret < 0) + goto fail; + + return dma_addr + offset; +fail: + __free_iova(mapping, dma_addr, len); + return DMA_ERROR_CODE; +} + +/** + * arm_iommu_unmap_page + * @dev: valid struct device pointer + * @handle: DMA address of buffer + * @size: size of buffer (same as passed to dma_map_page) + * @dir: DMA transfer direction (same as passed to dma_map_page) + * + * IOMMU aware version of arm_dma_unmap_page() + */ +static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova = handle & PAGE_MASK; + struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + int offset = handle & ~PAGE_MASK; + int len = PAGE_ALIGN(size + offset); + + if (!iova) + return; + + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(page, offset, size, dir); + + iommu_unmap(mapping->domain, iova, len); + __free_iova(mapping, iova, len); +} + +static void arm_iommu_sync_single_for_cpu(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova = handle & PAGE_MASK; + struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + unsigned int offset = handle & ~PAGE_MASK; + + if (!iova) + return; + + if (!arch_is_coherent()) + __dma_page_dev_to_cpu(page, offset, size, dir); +} + +static void arm_iommu_sync_single_for_device(struct device *dev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + struct dma_iommu_mapping *mapping = dev->archdata.mapping; + dma_addr_t iova = handle & PAGE_MASK; + struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova)); + unsigned int offset = handle & ~PAGE_MASK; + + if (!iova) + return; + + __dma_page_cpu_to_dev(page, offset, size, dir); +} + +struct dma_map_ops iommu_ops = { + .alloc = arm_iommu_alloc_attrs, + .free = arm_iommu_free_attrs, + .mmap = arm_iommu_mmap_attrs, + + .map_page = arm_iommu_map_page, + .unmap_page = arm_iommu_unmap_page, + .sync_single_for_cpu = arm_iommu_sync_single_for_cpu, + .sync_single_for_device = arm_iommu_sync_single_for_device, + + .map_sg = arm_iommu_map_sg, + .unmap_sg = arm_iommu_unmap_sg, + .sync_sg_for_cpu = arm_iommu_sync_sg_for_cpu, + .sync_sg_for_device = arm_iommu_sync_sg_for_device, +}; + +/** + * arm_iommu_create_mapping + * @bus: pointer to the bus holding the client device (for IOMMU calls) + * @base: start address of the valid IO address space + * @size: size of the valid IO address space + * @order: accuracy of the IO addresses allocations + * + * Creates a mapping structure which holds information about used/unused + * IO address ranges, which is required to perform memory allocation and + * mapping with IOMMU aware functions. + * + * The client device need to be attached to the mapping with + * arm_iommu_attach_device function. + */ +struct dma_iommu_mapping * +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size, + int order) +{ + unsigned int count = size >> (PAGE_SHIFT + order); + unsigned int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + struct dma_iommu_mapping *mapping; + int err = -ENOMEM; + + if (!count) + return ERR_PTR(-EINVAL); + + mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL); + if (!mapping) + goto err; + + mapping->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!mapping->bitmap) + goto err2; + + mapping->base = base; + mapping->bits = BITS_PER_BYTE * bitmap_size; + mapping->order = order; + spin_lock_init(&mapping->lock); + + mapping->domain = iommu_domain_alloc(bus); + if (!mapping->domain) + goto err3; + + kref_init(&mapping->kref); + return mapping; +err3: + kfree(mapping->bitmap); +err2: + kfree(mapping); +err: + return ERR_PTR(err); +} + +static void release_iommu_mapping(struct kref *kref) +{ + struct dma_iommu_mapping *mapping = + container_of(kref, struct dma_iommu_mapping, kref); + + iommu_domain_free(mapping->domain); + kfree(mapping->bitmap); + kfree(mapping); +} + +void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping) +{ + if (mapping) + kref_put(&mapping->kref, release_iommu_mapping); +} + +/** + * arm_iommu_attach_device + * @dev: valid struct device pointer + * @mapping: io address space mapping structure (returned from + * arm_iommu_create_mapping) + * + * Attaches specified io address space mapping to the provided device, + * this replaces the dma operations (dma_map_ops pointer) with the + * IOMMU aware version. More than one client might be attached to + * the same io address space mapping. + */ +int arm_iommu_attach_device(struct device *dev, + struct dma_iommu_mapping *mapping) +{ + int err; + + err = iommu_attach_device(mapping->domain, dev); + if (err) + return err; + + kref_get(&mapping->kref); + dev->archdata.mapping = mapping; + set_dma_ops(dev, &iommu_ops); + + pr_info("Attached IOMMU controller to %s device.\n", dev_name(dev)); + return 0; +} + +#endif diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 5bb48356d217..c3bd83450227 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -432,9 +432,6 @@ do_translation_fault(unsigned long addr, unsigned int fsr, index = pgd_index(addr); - /* - * FIXME: CP15 C1 is write only on ARMv3 architectures. - */ pgd = cpu_get_pgd() + index; pgd_k = init_mm.pgd + index; diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 8f5813bbffb5..c21d06c7dd7e 100644 --- a/arch/arm/mm/init.c +++ b/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(); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 27f4a619b35d..93dc0c17cdcb 100644 --- a/arch/arm/mm/mm.h +++ b/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); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index aa78de8bfdd3..e5dad60b558b 100644 --- a/arch/arm/mm/mmu.c +++ b/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(); diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index 234951345eb3..0650bb87c1e3 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -241,6 +241,7 @@ ENTRY(arm1020_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index c244b06caac9..4188478325a6 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -235,6 +235,7 @@ ENTRY(arm1020e_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S index 38fe22efd18f..33c68824bff0 100644 --- a/arch/arm/mm/proc-arm1022.S +++ b/arch/arm/mm/proc-arm1022.S @@ -224,6 +224,7 @@ ENTRY(arm1022_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S index 3eb9c3c26c75..fbc1d5fc24dc 100644 --- a/arch/arm/mm/proc-arm1026.S +++ b/arch/arm/mm/proc-arm1026.S @@ -218,6 +218,7 @@ ENTRY(arm1026_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S deleted file mode 100644 index 4fbeb5b8e6c2..000000000000 --- a/arch/arm/mm/proc-arm6_7.S +++ /dev/null @@ -1,327 +0,0 @@ -/* - * linux/arch/arm/mm/proc-arm6,7.S - * - * Copyright (C) 1997-2000 Russell King - * hacked for non-paged-MM by Hyok S. Choi, 2003. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * These are the low level assembler for performing cache and TLB - * functions on the ARM610 & ARM710. - */ -#include <linux/linkage.h> -#include <linux/init.h> -#include <asm/assembler.h> -#include <asm/asm-offsets.h> -#include <asm/hwcap.h> -#include <asm/pgtable-hwdef.h> -#include <asm/pgtable.h> -#include <asm/ptrace.h> - -#include "proc-macros.S" - -ENTRY(cpu_arm6_dcache_clean_area) -ENTRY(cpu_arm7_dcache_clean_area) - mov pc, lr - -/* - * Function: arm6_7_data_abort () - * - * Params : r2 = pt_regs - * : r4 = aborted context pc - * : r5 = aborted context psr - * - * Purpose : obtain information about current aborted instruction - * - * Returns : r4-r5, r10-r11, r13 preserved - */ - -ENTRY(cpu_arm7_data_abort) - mrc p15, 0, r1, c5, c0, 0 @ get FSR - mrc p15, 0, r0, c6, c0, 0 @ get FAR - ldr r8, [r4] @ read arm instruction - tst r8, #1 << 20 @ L = 0 -> write? - orreq r1, r1, #1 << 11 @ yes. - and r7, r8, #15 << 24 - add pc, pc, r7, lsr #22 @ Now branch to the relevant processing routine - nop - -/* 0 */ b .data_unknown -/* 1 */ b do_DataAbort @ swp -/* 2 */ b .data_unknown -/* 3 */ b .data_unknown -/* 4 */ b .data_arm_lateldrpostconst @ ldr rd, [rn], #m -/* 5 */ b .data_arm_lateldrpreconst @ ldr rd, [rn, #m] -/* 6 */ b .data_arm_lateldrpostreg @ ldr rd, [rn], rm -/* 7 */ b .data_arm_lateldrprereg @ ldr rd, [rn, rm] -/* 8 */ b .data_arm_ldmstm @ ldm*a rn, <rlist> -/* 9 */ b .data_arm_ldmstm @ ldm*b rn, <rlist> -/* a */ b .data_unknown -/* b */ b .data_unknown -/* c */ b do_DataAbort @ ldc rd, [rn], #m @ Same as ldr rd, [rn], #m -/* d */ b do_DataAbort @ ldc rd, [rn, #m] -/* e */ b .data_unknown -/* f */ -.data_unknown: @ Part of jumptable - mov r0, r4 - mov r1, r8 - b baddataabort - -ENTRY(cpu_arm6_data_abort) - mrc p15, 0, r1, c5, c0, 0 @ get FSR - mrc p15, 0, r0, c6, c0, 0 @ get FAR - ldr r8, [r4] @ read arm instruction - tst r8, #1 << 20 @ L = 0 -> write? - orreq r1, r1, #1 << 11 @ yes. - and r7, r8, #14 << 24 - teq r7, #8 << 24 @ was it ldm/stm - bne do_DataAbort - -.data_arm_ldmstm: - tst r8, #1 << 21 @ check writeback bit - beq do_DataAbort @ no writeback -> no fixup - mov r7, #0x11 - orr r7, r7, #0x1100 - and r6, r8, r7 - and r9, r8, r7, lsl #1 - add r6, r6, r9, lsr #1 - and r9, r8, r7, lsl #2 - add r6, r6, r9, lsr #2 - and r9, r8, r7, lsl #3 - add r6, r6, r9, lsr #3 - add r6, r6, r6, lsr #8 - add r6, r6, r6, lsr #4 - and r6, r6, #15 @ r6 = no. of registers to transfer. - and r9, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' - tst r8, #1 << 23 @ Check U bit - subne r7, r7, r6, lsl #2 @ Undo increment - addeq r7, r7, r6, lsl #2 @ Undo decrement - str r7, [r2, r9, lsr #14] @ Put register 'Rn' - b do_DataAbort - -.data_arm_apply_r6_and_rn: - and r9, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' - tst r8, #1 << 23 @ Check U bit - subne r7, r7, r6 @ Undo incrmenet - addeq r7, r7, r6 @ Undo decrement - str r7, [r2, r9, lsr #14] @ Put register 'Rn' - b do_DataAbort - -.data_arm_lateldrpreconst: - tst r8, #1 << 21 @ check writeback bit - beq do_DataAbort @ no writeback -> no fixup -.data_arm_lateldrpostconst: - movs r6, r8, lsl #20 @ Get offset - beq do_DataAbort @ zero -> no fixup - and r9, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' - tst r8, #1 << 23 @ Check U bit - subne r7, r7, r6, lsr #20 @ Undo increment - addeq r7, r7, r6, lsr #20 @ Undo decrement - str r7, [r2, r9, lsr #14] @ Put register 'Rn' - b do_DataAbort - -.data_arm_lateldrprereg: - tst r8, #1 << 21 @ check writeback bit - beq do_DataAbort @ no writeback -> no fixup -.data_arm_lateldrpostreg: - and r7, r8, #15 @ Extract 'm' from instruction - ldr r6, [r2, r7, lsl #2] @ Get register 'Rm' - mov r9, r8, lsr #7 @ get shift count - ands r9, r9, #31 - and r7, r8, #0x70 @ get shift type - orreq r7, r7, #8 @ shift count = 0 - add pc, pc, r7 - nop - - mov r6, r6, lsl r9 @ 0: LSL #!0 - b .data_arm_apply_r6_and_rn - b .data_arm_apply_r6_and_rn @ 1: LSL #0 - nop - b .data_unknown @ 2: MUL? - nop - b .data_unknown @ 3: MUL? - nop - mov r6, r6, lsr r9 @ 4: LSR #!0 - b .data_arm_apply_r6_and_rn - mov r6, r6, lsr #32 @ 5: LSR #32 - b .data_arm_apply_r6_and_rn - b .data_unknown @ 6: MUL? - nop - b .data_unknown @ 7: MUL? - nop - mov r6, r6, asr r9 @ 8: ASR #!0 - b .data_arm_apply_r6_and_rn - mov r6, r6, asr #32 @ 9: ASR #32 - b .data_arm_apply_r6_and_rn - b .data_unknown @ A: MUL? - nop - b .data_unknown @ B: MUL? - nop - mov r6, r6, ror r9 @ C: ROR #!0 - b .data_arm_apply_r6_and_rn - mov r6, r6, rrx @ D: RRX - b .data_arm_apply_r6_and_rn - b .data_unknown @ E: MUL? - nop - b .data_unknown @ F: MUL? - -/* - * Function: arm6_7_proc_init (void) - * : arm6_7_proc_fin (void) - * - * Notes : This processor does not require these - */ -ENTRY(cpu_arm6_proc_init) -ENTRY(cpu_arm7_proc_init) - mov pc, lr - -ENTRY(cpu_arm6_proc_fin) -ENTRY(cpu_arm7_proc_fin) - mov r0, #0x31 @ ....S..DP...M - mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr - -ENTRY(cpu_arm6_do_idle) -ENTRY(cpu_arm7_do_idle) - mov pc, lr - -/* - * Function: arm6_7_switch_mm(unsigned long pgd_phys) - * Params : pgd_phys Physical address of page table - * Purpose : Perform a task switch, saving the old processes state, and restoring - * the new. - */ -ENTRY(cpu_arm6_switch_mm) -ENTRY(cpu_arm7_switch_mm) -#ifdef CONFIG_MMU - mov r1, #0 - mcr p15, 0, r1, c7, c0, 0 @ flush cache - mcr p15, 0, r0, c2, c0, 0 @ update page table ptr - mcr p15, 0, r1, c5, c0, 0 @ flush TLBs -#endif - mov pc, lr - -/* - * Function: arm6_7_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext) - * Params : r0 = Address to set - * : r1 = value to set - * Purpose : Set a PTE and flush it out of any WB cache - */ - .align 5 -ENTRY(cpu_arm6_set_pte_ext) -ENTRY(cpu_arm7_set_pte_ext) -#ifdef CONFIG_MMU - armv3_set_pte_ext wc_disable=0 -#endif /* CONFIG_MMU */ - mov pc, lr - -/* - * Function: _arm6_7_reset - * Params : r0 = address to jump to - * Notes : This sets up everything for a reset - */ - .pushsection .idmap.text, "ax" -ENTRY(cpu_arm6_reset) -ENTRY(cpu_arm7_reset) - mov r1, #0 - mcr p15, 0, r1, c7, c0, 0 @ flush cache -#ifdef CONFIG_MMU - mcr p15, 0, r1, c5, c0, 0 @ flush TLB -#endif - mov r1, #0x30 - mcr p15, 0, r1, c1, c0, 0 @ turn off MMU etc - mov pc, r0 -ENDPROC(cpu_arm6_reset) -ENDPROC(cpu_arm7_reset) - .popsection - - __CPUINIT - - .type __arm6_setup, #function -__arm6_setup: mov r0, #0 - mcr p15, 0, r0, c7, c0 @ flush caches on v3 -#ifdef CONFIG_MMU - mcr p15, 0, r0, c5, c0 @ flush TLBs on v3 - mov r0, #0x3d @ . ..RS BLDP WCAM - orr r0, r0, #0x100 @ . ..01 0011 1101 -#else - mov r0, #0x3c @ . ..RS BLDP WCA. -#endif - mov pc, lr - .size __arm6_setup, . - __arm6_setup - - .type __arm7_setup, #function -__arm7_setup: mov r0, #0 - mcr p15, 0, r0, c7, c0 @ flush caches on v3 -#ifdef CONFIG_MMU - mcr p15, 0, r0, c5, c0 @ flush TLBs on v3 - mcr p15, 0, r0, c3, c0 @ load domain access register - mov r0, #0x7d @ . ..RS BLDP WCAM - orr r0, r0, #0x100 @ . ..01 0111 1101 -#else - mov r0, #0x7c @ . ..RS BLDP WCA. -#endif - mov pc, lr - .size __arm7_setup, . - __arm7_setup - - __INITDATA - - @ define struct processor (see <asm/proc-fns.h> and proc-macros.S) - define_processor_functions arm6, dabort=cpu_arm6_data_abort, pabort=legacy_pabort - define_processor_functions arm7, dabort=cpu_arm7_data_abort, pabort=legacy_pabort - - .section ".rodata" - - string cpu_arch_name, "armv3" - string cpu_elf_name, "v3" - string cpu_arm6_name, "ARM6" - string cpu_arm610_name, "ARM610" - string cpu_arm7_name, "ARM7" - string cpu_arm710_name, "ARM710" - - .align - - .section ".proc.info.init", #alloc, #execinstr - -.macro arm67_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, \ - cpu_mm_mmu_flags:req, cpu_flush:req, cpu_proc_funcs:req - .type __\name\()_proc_info, #object -__\name\()_proc_info: - .long \cpu_val - .long \cpu_mask - .long \cpu_mm_mmu_flags - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b \cpu_flush - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_26BIT - .long \cpu_name - .long \cpu_proc_funcs - .long v3_tlb_fns - .long v3_user_fns - .long v3_cache_fns - .size __\name\()_proc_info, . - __\name\()_proc_info -.endm - - arm67_proc_info arm6, 0x41560600, 0xfffffff0, cpu_arm6_name, \ - 0x00000c1e, __arm6_setup, arm6_processor_functions - arm67_proc_info arm610, 0x41560610, 0xfffffff0, cpu_arm610_name, \ - 0x00000c1e, __arm6_setup, arm6_processor_functions - arm67_proc_info arm7, 0x41007000, 0xffffff00, cpu_arm7_name, \ - 0x00000c1e, __arm7_setup, arm7_processor_functions - arm67_proc_info arm710, 0x41007100, 0xfff8ff00, cpu_arm710_name, \ - PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ, \ - __arm7_setup, arm7_processor_functions diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index cb941ae95f66..1a8c138eb897 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -210,6 +210,7 @@ ENTRY(arm920_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S index 4ec0e074dd55..4c44d7e1c3ca 100644 --- a/arch/arm/mm/proc-arm922.S +++ b/arch/arm/mm/proc-arm922.S @@ -212,6 +212,7 @@ ENTRY(arm922_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index 9dccd9a365b3..ec5b1180994f 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -258,6 +258,7 @@ ENTRY(arm925_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 820259b81a1f..c31e62c606c0 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -221,6 +221,7 @@ ENTRY(arm926_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S index 9fdc0a170974..a613a7dd7146 100644 --- a/arch/arm/mm/proc-arm940.S +++ b/arch/arm/mm/proc-arm940.S @@ -160,7 +160,7 @@ ENTRY(arm940_coherent_user_range) * - size - region size */ ENTRY(arm940_flush_kern_dcache_area) - mov ip, #0 + mov r0, #0 mov r1, #(CACHE_DSEGMENTS - 1) << 4 @ 4 segments 1: orr r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries 2: mcr p15, 0, r3, c7, c14, 2 @ clean/flush D index @@ -168,8 +168,8 @@ ENTRY(arm940_flush_kern_dcache_area) bcs 2b @ entries 63 to 0 subs r1, r1, #1 << 4 bcs 1b @ segments 7 to 0 - mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache - mcr p15, 0, ip, c7, c10, 4 @ drain WB + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mcr p15, 0, r0, c7, c10, 4 @ drain WB mov pc, lr /* diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S index f684cfedcca9..9f4f2999fdd0 100644 --- a/arch/arm/mm/proc-arm946.S +++ b/arch/arm/mm/proc-arm946.S @@ -190,6 +190,7 @@ ENTRY(arm946_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index ba3c500584ac..23a8e4c7f2bd 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -232,6 +232,7 @@ ENTRY(feroceon_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index cdfedc5b8ad8..fbb2124a547d 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -193,6 +193,7 @@ ENTRY(mohawk_coherent_user_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB + mov r0, #0 mov pc, lr /* @@ -344,6 +345,41 @@ ENTRY(cpu_mohawk_set_pte_ext) mcr p15, 0, r0, c7, c10, 4 @ drain WB mov pc, lr +.globl cpu_mohawk_suspend_size +.equ cpu_mohawk_suspend_size, 4 * 6 +#ifdef CONFIG_PM_SLEEP +ENTRY(cpu_mohawk_do_suspend) + stmfd sp!, {r4 - r9, lr} + mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode + mrc p15, 0, r5, c15, c1, 0 @ CP access reg + mrc p15, 0, r6, c13, c0, 0 @ PID + mrc p15, 0, r7, c3, c0, 0 @ domain ID + mrc p15, 0, r8, c1, c0, 1 @ auxiliary control reg + mrc p15, 0, r9, c1, c0, 0 @ control reg + bic r4, r4, #2 @ clear frequency change bit + stmia r0, {r4 - r9} @ store cp regs + ldmia sp!, {r4 - r9, pc} +ENDPROC(cpu_mohawk_do_suspend) + +ENTRY(cpu_mohawk_do_resume) + ldmia r0, {r4 - r9} @ load cp regs + mov ip, #0 + mcr p15, 0, ip, c7, c7, 0 @ invalidate I & D caches, BTB + mcr p15, 0, ip, c7, c10, 4 @ drain write (&fill) buffer + mcr p15, 0, ip, c7, c5, 4 @ flush prefetch buffer + mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs + mcr p14, 0, r4, c6, c0, 0 @ clock configuration, turbo mode. + mcr p15, 0, r5, c15, c1, 0 @ CP access reg + mcr p15, 0, r6, c13, c0, 0 @ PID + mcr p15, 0, r7, c3, c0, 0 @ domain ID + orr r1, r1, #0x18 @ cache the page table in L2 + mcr p15, 0, r1, c2, c0, 0 @ translation table base addr + mcr p15, 0, r8, c1, c0, 1 @ auxiliary control reg + mov r0, r9 @ control register + b cpu_resume_mmu +ENDPROC(cpu_mohawk_do_resume) +#endif + __CPUINIT .type __mohawk_setup, #function diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 3a4b3e7b888c..42ac069c8012 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -49,15 +49,10 @@ ENTRY(cpu_v7_switch_mm) #ifdef CONFIG_ARM_ERRATA_754322 dsb #endif - mcr p15, 0, r2, c13, c0, 1 @ set reserved context ID - isb -1: mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 - isb -#ifdef CONFIG_ARM_ERRATA_754322 - dsb -#endif mcr p15, 0, r1, c13, c0, 1 @ set context ID isb + mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 + isb #endif mov pc, lr ENDPROC(cpu_v7_switch_mm) diff --git a/arch/arm/mm/tlb-v3.S b/arch/arm/mm/tlb-v3.S deleted file mode 100644 index d253995ec4ca..000000000000 --- a/arch/arm/mm/tlb-v3.S +++ /dev/null @@ -1,48 +0,0 @@ -/* - * linux/arch/arm/mm/tlbv3.S - * - * Copyright (C) 1997-2002 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * ARM architecture version 3 TLB handling functions. - * - * Processors: ARM610, ARM710. - */ -#include <linux/linkage.h> -#include <linux/init.h> -#include <asm/asm-offsets.h> -#include <asm/tlbflush.h> -#include "proc-macros.S" - - .align 5 -/* - * v3_flush_user_tlb_range(start, end, mm) - * - * Invalidate a range of TLB entries in the specified address space. - * - * - start - range start address - * - end - range end address - * - mm - mm_struct describing address space - */ - .align 5 -ENTRY(v3_flush_user_tlb_range) - vma_vm_mm r2, r2 - act_mm r3 @ get current->active_mm - teq r2, r3 @ == mm ? - movne pc, lr @ no, we dont do anything -ENTRY(v3_flush_kern_tlb_range) - bic r0, r0, #0x0ff - bic r0, r0, #0xf00 -1: mcr p15, 0, r0, c6, c0, 0 @ invalidate TLB entry - add r0, r0, #PAGE_SZ - cmp r0, r1 - blo 1b - mov pc, lr - - __INITDATA - - /* define struct cpu_tlb_fns (see <asm/tlbflush.h> and proc-macros.S) */ - define_tlb_functions v3, v3_tlb_flags diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h index 162be662c088..bf312c354a21 100644 --- a/arch/arm/mm/vmregion.h +++ b/arch/arm/mm/vmregion.h @@ -17,7 +17,7 @@ struct arm_vmregion { struct list_head vm_list; unsigned long vm_start; unsigned long vm_end; - struct page *vm_pages; + void *priv; int vm_active; const void *caller; }; |