diff options
Diffstat (limited to 'arch/arm/mm')
| -rw-r--r-- | arch/arm/mm/Kconfig | 21 | ||||
| -rw-r--r-- | arch/arm/mm/cache-v6.S | 18 | ||||
| -rw-r--r-- | arch/arm/mm/copypage-feroceon.c | 4 | ||||
| -rw-r--r-- | arch/arm/mm/copypage-v4wb.c | 4 | ||||
| -rw-r--r-- | arch/arm/mm/copypage-v4wt.c | 4 | ||||
| -rw-r--r-- | arch/arm/mm/copypage-xsc3.c | 4 | ||||
| -rw-r--r-- | arch/arm/mm/dma-mapping.c | 18 | ||||
| -rw-r--r-- | arch/arm/mm/fault.c | 3 | ||||
| -rw-r--r-- | arch/arm/mm/highmem.c | 11 | ||||
| -rw-r--r-- | arch/arm/mm/init.c | 6 |
10 files changed, 68 insertions, 25 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 346ae14824a5..101105e52610 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -735,6 +735,25 @@ config NEEDS_SYSCALL_FOR_CMPXCHG Forget about fast user space cmpxchg support. It is just not possible. +config DMA_CACHE_RWFO + bool "Enable read/write for ownership DMA cache maintenance" + depends on CPU_V6 && SMP + default y + help + The Snoop Control Unit on ARM11MPCore does not detect the + cache maintenance operations and the dma_{map,unmap}_area() + functions may leave stale cache entries on other CPUs. By + enabling this option, Read or Write For Ownership in the ARMv6 + DMA cache maintenance functions is performed. These LDR/STR + instructions change the cache line state to shared or modified + so that the cache operation has the desired effect. + + Note that the workaround is only valid on processors that do + not perform speculative loads into the D-cache. For such + processors, if cache maintenance operations are not broadcast + in hardware, other workarounds are needed (e.g. cache + maintenance broadcasting in software via FIQ). + config OUTER_CACHE bool @@ -794,6 +813,8 @@ config ARM_L1_CACHE_SHIFT config ARM_DMA_MEM_BUFFERABLE bool "Use non-cacheable memory for DMA" if CPU_V6 && !CPU_V7 + depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \ + MACH_REALVIEW_PB11MP) default y if CPU_V6 || CPU_V7 help Historically, the kernel has used strongly ordered mappings to diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index e46ecd847138..86aa689ef1aa 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -211,8 +211,9 @@ v6_dma_inv_range: mcrne p15, 0, r1, c7, c15, 1 @ clean & invalidate unified line #endif 1: -#ifdef CONFIG_SMP - str r0, [r0] @ write for ownership +#ifdef CONFIG_DMA_CACHE_RWFO + ldr r2, [r0] @ read for ownership + str r2, [r0] @ write for ownership #endif #ifdef HARVARD_CACHE mcr p15, 0, r0, c7, c6, 1 @ invalidate D line @@ -234,7 +235,7 @@ v6_dma_inv_range: v6_dma_clean_range: bic r0, r0, #D_CACHE_LINE_SIZE - 1 1: -#ifdef CONFIG_SMP +#ifdef CONFIG_DMA_CACHE_RWFO ldr r2, [r0] @ read for ownership #endif #ifdef HARVARD_CACHE @@ -257,7 +258,7 @@ v6_dma_clean_range: ENTRY(v6_dma_flush_range) bic r0, r0, #D_CACHE_LINE_SIZE - 1 1: -#ifdef CONFIG_SMP +#ifdef CONFIG_DMA_CACHE_RWFO ldr r2, [r0] @ read for ownership str r2, [r0] @ write for ownership #endif @@ -283,9 +284,13 @@ ENTRY(v6_dma_map_area) add r1, r1, r0 teq r2, #DMA_FROM_DEVICE beq v6_dma_inv_range +#ifndef CONFIG_DMA_CACHE_RWFO + b v6_dma_clean_range +#else teq r2, #DMA_TO_DEVICE beq v6_dma_clean_range b v6_dma_flush_range +#endif ENDPROC(v6_dma_map_area) /* @@ -295,6 +300,11 @@ ENDPROC(v6_dma_map_area) * - dir - DMA direction */ ENTRY(v6_dma_unmap_area) +#ifndef CONFIG_DMA_CACHE_RWFO + add r1, r1, r0 + teq r2, #DMA_TO_DEVICE + bne v6_dma_inv_range +#endif mov pc, lr ENDPROC(v6_dma_unmap_area) diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c index 5eb4fd93893d..ac163de7dc01 100644 --- a/arch/arm/mm/copypage-feroceon.c +++ b/arch/arm/mm/copypage-feroceon.c @@ -18,7 +18,7 @@ feroceon_copy_user_page(void *kto, const void *kfrom) { asm("\ stmfd sp!, {r4-r9, lr} \n\ - mov ip, %0 \n\ + mov ip, %2 \n\ 1: mov lr, r1 \n\ ldmia r1!, {r2 - r9} \n\ pld [lr, #32] \n\ @@ -64,7 +64,7 @@ feroceon_copy_user_page(void *kto, const void *kfrom) mcr p15, 0, ip, c7, c10, 4 @ drain WB\n\ ldmfd sp!, {r4-r9, pc}" : - : "I" (PAGE_SIZE)); + : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE)); } void feroceon_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c index 7c2eb55cd4a9..cb589cbb2b6c 100644 --- a/arch/arm/mm/copypage-v4wb.c +++ b/arch/arm/mm/copypage-v4wb.c @@ -27,7 +27,7 @@ v4wb_copy_user_page(void *kto, const void *kfrom) { asm("\ stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %0 @ 1\n\ + mov r2, %2 @ 1\n\ ldmia r1!, {r3, r4, ip, lr} @ 4\n\ 1: mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ stmia r0!, {r3, r4, ip, lr} @ 4\n\ @@ -44,7 +44,7 @@ v4wb_copy_user_page(void *kto, const void *kfrom) mcr p15, 0, r1, c7, c10, 4 @ 1 drain WB\n\ ldmfd sp!, {r4, pc} @ 3" : - : "I" (PAGE_SIZE / 64)); + : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); } void v4wb_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c index 172e6a55458e..30c7d048a324 100644 --- a/arch/arm/mm/copypage-v4wt.c +++ b/arch/arm/mm/copypage-v4wt.c @@ -25,7 +25,7 @@ v4wt_copy_user_page(void *kto, const void *kfrom) { asm("\ stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %0 @ 1\n\ + mov r2, %2 @ 1\n\ ldmia r1!, {r3, r4, ip, lr} @ 4\n\ 1: stmia r0!, {r3, r4, ip, lr} @ 4\n\ ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ @@ -40,7 +40,7 @@ v4wt_copy_user_page(void *kto, const void *kfrom) mcr p15, 0, r2, c7, c7, 0 @ flush ID cache\n\ ldmfd sp!, {r4, pc} @ 3" : - : "I" (PAGE_SIZE / 64)); + : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); } void v4wt_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c index 747ad4140fc7..f9cde0702f1e 100644 --- a/arch/arm/mm/copypage-xsc3.c +++ b/arch/arm/mm/copypage-xsc3.c @@ -34,7 +34,7 @@ xsc3_mc_copy_user_page(void *kto, const void *kfrom) { asm("\ stmfd sp!, {r4, r5, lr} \n\ - mov lr, %0 \n\ + mov lr, %2 \n\ \n\ pld [r1, #0] \n\ pld [r1, #32] \n\ @@ -67,7 +67,7 @@ xsc3_mc_copy_user_page(void *kto, const void *kfrom) \n\ ldmfd sp!, {r4, r5, pc}" : - : "I" (PAGE_SIZE / 64 - 1)); + : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64 - 1)); } void xsc3_mc_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 13fa536d82e6..9e7742f0a102 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -24,15 +24,6 @@ #include <asm/tlbflush.h> #include <asm/sizes.h> -/* Sanity check size */ -#if (CONSISTENT_DMA_SIZE % SZ_2M) -#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB" -#endif - -#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT) -#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT) -#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT) - static u64 get_coherent_dma_mask(struct device *dev) { u64 mask = ISA_DMA_THRESHOLD; @@ -123,6 +114,15 @@ static void __dma_free_buffer(struct page *page, size_t size) } #ifdef CONFIG_MMU +/* Sanity check size */ +#if (CONSISTENT_DMA_SIZE % SZ_2M) +#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB" +#endif + +#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT) +#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT) +#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT) + /* * These are the page tables (2MB each) covering uncached, DMA consistent allocations */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 92f5801f99c1..cbfb2edcf7d1 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -393,6 +393,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, if (addr < TASK_SIZE) return do_page_fault(addr, fsr, regs); + if (user_mode(regs)) + goto bad_area; + index = pgd_index(addr); /* diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 77b030f5ec09..086816b205b8 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -48,7 +48,16 @@ void *kmap_atomic(struct page *page, enum km_type type) debug_kmap_atomic(type); - kmap = kmap_high_get(page); +#ifdef CONFIG_DEBUG_HIGHMEM + /* + * There is no cache coherency issue when non VIVT, so force the + * dedicated kmap usage for better debugging purposes in that case. + */ + if (!cache_is_vivt()) + kmap = NULL; + else +#endif + kmap = kmap_high_get(page); if (kmap) return kmap; diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 1ba6cf5a2c02..f6a999465323 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -678,10 +678,10 @@ void __init mem_init(void) void free_initmem(void) { #ifdef CONFIG_HAVE_TCM - extern char *__tcm_start, *__tcm_end; + extern char __tcm_start, __tcm_end; - totalram_pages += free_area(__phys_to_pfn(__pa(__tcm_start)), - __phys_to_pfn(__pa(__tcm_end)), + totalram_pages += free_area(__phys_to_pfn(__pa(&__tcm_start)), + __phys_to_pfn(__pa(&__tcm_end)), "TCM link"); #endif |