diff options
Diffstat (limited to 'arch/arm/include/asm/cacheflush.h')
| -rw-r--r-- | arch/arm/include/asm/cacheflush.h | 301 |
1 files changed, 159 insertions, 142 deletions
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 3acd8fa25e3..fd43f7f55b7 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -12,7 +12,7 @@ #include <linux/mm.h> -#include <asm/glue.h> +#include <asm/glue-cache.h> #include <asm/shmparam.h> #include <asm/cachetype.h> #include <asm/outercache.h> @@ -20,123 +20,6 @@ #define CACHE_COLOUR(vaddr) ((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT) /* - * Cache Model - * =========== - */ -#undef _CACHE -#undef MULTI_CACHE - -#if defined(CONFIG_CPU_CACHE_V3) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v3 -# endif -#endif - -#if defined(CONFIG_CPU_CACHE_V4) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v4 -# endif -#endif - -#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \ - defined(CONFIG_CPU_ARM925T) || defined(CONFIG_CPU_ARM1020) || \ - defined(CONFIG_CPU_ARM1026) -# define MULTI_CACHE 1 -#endif - -#if defined(CONFIG_CPU_FA526) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE fa -# endif -#endif - -#if defined(CONFIG_CPU_ARM926T) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE arm926 -# endif -#endif - -#if defined(CONFIG_CPU_ARM940T) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE arm940 -# endif -#endif - -#if defined(CONFIG_CPU_ARM946E) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE arm946 -# endif -#endif - -#if defined(CONFIG_CPU_CACHE_V4WB) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v4wb -# endif -#endif - -#if defined(CONFIG_CPU_XSCALE) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE xscale -# endif -#endif - -#if defined(CONFIG_CPU_XSC3) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE xsc3 -# endif -#endif - -#if defined(CONFIG_CPU_MOHAWK) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE mohawk -# endif -#endif - -#if defined(CONFIG_CPU_FEROCEON) -# define MULTI_CACHE 1 -#endif - -#if defined(CONFIG_CPU_V6) -//# ifdef _CACHE -# define MULTI_CACHE 1 -//# else -//# define _CACHE v6 -//# endif -#endif - -#if defined(CONFIG_CPU_V7) -//# ifdef _CACHE -# define MULTI_CACHE 1 -//# else -//# define _CACHE v7 -//# endif -#endif - -#if !defined(_CACHE) && !defined(MULTI_CACHE) -#error Unknown cache maintainence model -#endif - -/* * This flag is used to indicate that the page pointed to by a pte is clean * and does not require cleaning before returning it to the user. */ @@ -166,6 +49,13 @@ * * Unconditionally clean and invalidate the entire cache. * + * flush_kern_louis() + * + * Flush data cache levels up to the level of unification + * inner shareable and invalidate the I-cache. + * Only needed from v7 onwards, falls back to flush_cache_all() + * for all other processor versions. + * * flush_user_all() * * Clean and invalidate all user space cache entries @@ -214,11 +104,12 @@ struct cpu_cache_fns { void (*flush_icache_all)(void); void (*flush_kern_all)(void); + void (*flush_kern_louis)(void); void (*flush_user_all)(void); void (*flush_user_range)(unsigned long, unsigned long, unsigned int); void (*coherent_kern_range)(unsigned long, unsigned long); - void (*coherent_user_range)(unsigned long, unsigned long); + int (*coherent_user_range)(unsigned long, unsigned long); void (*flush_kern_dcache_area)(void *, size_t); void (*dma_map_area)(const void *, size_t, int); @@ -236,6 +127,7 @@ extern struct cpu_cache_fns cpu_cache; #define __cpuc_flush_icache_all cpu_cache.flush_icache_all #define __cpuc_flush_kern_all cpu_cache.flush_kern_all +#define __cpuc_flush_kern_louis cpu_cache.flush_kern_louis #define __cpuc_flush_user_all cpu_cache.flush_user_all #define __cpuc_flush_user_range cpu_cache.flush_user_range #define __cpuc_coherent_kern_range cpu_cache.coherent_kern_range @@ -249,25 +141,18 @@ extern struct cpu_cache_fns cpu_cache; * visible to the CPU. */ #define dmac_map_area cpu_cache.dma_map_area -#define dmac_unmap_area cpu_cache.dma_unmap_area +#define dmac_unmap_area cpu_cache.dma_unmap_area #define dmac_flush_range cpu_cache.dma_flush_range #else -#define __cpuc_flush_icache_all __glue(_CACHE,_flush_icache_all) -#define __cpuc_flush_kern_all __glue(_CACHE,_flush_kern_cache_all) -#define __cpuc_flush_user_all __glue(_CACHE,_flush_user_cache_all) -#define __cpuc_flush_user_range __glue(_CACHE,_flush_user_cache_range) -#define __cpuc_coherent_kern_range __glue(_CACHE,_coherent_kern_range) -#define __cpuc_coherent_user_range __glue(_CACHE,_coherent_user_range) -#define __cpuc_flush_dcache_area __glue(_CACHE,_flush_kern_dcache_area) - extern void __cpuc_flush_icache_all(void); extern void __cpuc_flush_kern_all(void); +extern void __cpuc_flush_kern_louis(void); extern void __cpuc_flush_user_all(void); extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int); extern void __cpuc_coherent_kern_range(unsigned long, unsigned long); -extern void __cpuc_coherent_user_range(unsigned long, unsigned long); +extern int __cpuc_coherent_user_range(unsigned long, unsigned long); extern void __cpuc_flush_dcache_area(void *, size_t); /* @@ -276,10 +161,6 @@ extern void __cpuc_flush_dcache_area(void *, size_t); * is visible to DMA, or data written by DMA to system memory is * visible to the CPU. */ -#define dmac_map_area __glue(_CACHE,_dma_map_area) -#define dmac_unmap_area __glue(_CACHE,_dma_unmap_area) -#define dmac_flush_range __glue(_CACHE,_dma_flush_range) - extern void dmac_map_area(const void *, size_t, int); extern void dmac_unmap_area(const void *, size_t, int); extern void dmac_flush_range(const void *, const void *); @@ -316,7 +197,8 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, * Optimized __flush_icache_all for the common cases. Note that UP ARMv7 * will fall through to use __flush_icache_all_generic. */ -#if (defined(CONFIG_CPU_V7) && defined(CONFIG_CPU_V6)) || \ +#if (defined(CONFIG_CPU_V7) && \ + (defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K))) || \ defined(CONFIG_SMP_ON_UP) #define __flush_icache_preferred __cpuc_flush_icache_all #elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP) @@ -330,8 +212,14 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, static inline void __flush_icache_all(void) { __flush_icache_preferred(); + dsb(ishst); } +/* + * Flush caches up to Level of Unification Inner Shareable + */ +#define flush_cache_louis() __cpuc_flush_kern_louis() + #define flush_cache_all() __cpuc_flush_kern_all() static inline void vivt_flush_cache_mm(struct mm_struct *mm) @@ -343,7 +231,9 @@ static inline void vivt_flush_cache_mm(struct mm_struct *mm) static inline void vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) __cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end), vma->vm_flags); } @@ -351,7 +241,9 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned static inline void vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) { unsigned long addr = user_addr & PAGE_MASK; __cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags); } @@ -377,8 +269,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr * Harvard caches are synchronised for the user space address range. * This is used for the ARM private sys_cacheflush system call. */ -#define flush_cache_user_range(vma,start,end) \ - __cpuc_coherent_user_range((start) & PAGE_MASK, PAGE_ALIGN(end)) +#define flush_cache_user_range(s,e) __cpuc_coherent_user_range(s,e) /* * Perform necessary cache operations to ensure that data previously @@ -429,9 +320,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma, } #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -static inline void flush_kernel_dcache_page(struct page *page) -{ -} +extern void flush_kernel_dcache_page(struct page *); #define flush_dcache_mmap_lock(mapping) \ spin_lock_irq(&(mapping)->tree_lock) @@ -463,7 +352,7 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) * set_pte_at() called from vmap_pte_range() does not * have a DSB after cleaning the cache line. */ - dsb(); + dsb(ishst); } static inline void flush_cache_vunmap(unsigned long start, unsigned long end) @@ -472,4 +361,132 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) flush_cache_all(); } +/* + * Memory synchronization helpers for mixed cached vs non cached accesses. + * + * Some synchronization algorithms have to set states in memory with the + * cache enabled or disabled depending on the code path. It is crucial + * to always ensure proper cache maintenance to update main memory right + * away in that case. + * + * Any cached write must be followed by a cache clean operation. + * Any cached read must be preceded by a cache invalidate operation. + * Yet, in the read case, a cache flush i.e. atomic clean+invalidate + * operation is needed to avoid discarding possible concurrent writes to the + * accessed memory. + * + * Also, in order to prevent a cached writer from interfering with an + * adjacent non-cached writer, each state variable must be located to + * a separate cache line. + */ + +/* + * This needs to be >= the max cache writeback size of all + * supported platforms included in the current kernel configuration. + * This is used to align state variables to their own cache lines. + */ +#define __CACHE_WRITEBACK_ORDER 6 /* guessed from existing platforms */ +#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER) + +/* + * There is no __cpuc_clean_dcache_area but we use it anyway for + * code intent clarity, and alias it to __cpuc_flush_dcache_area. + */ +#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area + +/* + * Ensure preceding writes to *p by this CPU are visible to + * subsequent reads by other CPUs: + */ +static inline void __sync_cache_range_w(volatile void *p, size_t size) +{ + char *_p = (char *)p; + + __cpuc_clean_dcache_area(_p, size); + outer_clean_range(__pa(_p), __pa(_p + size)); +} + +/* + * Ensure preceding writes to *p by other CPUs are visible to + * subsequent reads by this CPU. We must be careful not to + * discard data simultaneously written by another CPU, hence the + * usage of flush rather than invalidate operations. + */ +static inline void __sync_cache_range_r(volatile void *p, size_t size) +{ + char *_p = (char *)p; + +#ifdef CONFIG_OUTER_CACHE + if (outer_cache.flush_range) { + /* + * Ensure dirty data migrated from other CPUs into our cache + * are cleaned out safely before the outer cache is cleaned: + */ + __cpuc_clean_dcache_area(_p, size); + + /* Clean and invalidate stale data for *p from outer ... */ + outer_flush_range(__pa(_p), __pa(_p + size)); + } +#endif + + /* ... and inner cache: */ + __cpuc_flush_dcache_area(_p, size); +} + +#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr)) +#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr)) + +/* + * Disabling cache access for one CPU in an ARMv7 SMP system is tricky. + * To do so we must: + * + * - Clear the SCTLR.C bit to prevent further cache allocations + * - Flush the desired level of cache + * - Clear the ACTLR "SMP" bit to disable local coherency + * + * ... and so without any intervening memory access in between those steps, + * not even to the stack. + * + * WARNING -- After this has been called: + * + * - No ldrex/strex (and similar) instructions must be used. + * - The CPU is obviously no longer coherent with the other CPUs. + * - This is unlikely to work as expected if Linux is running non-secure. + * + * Note: + * + * - This is known to apply to several ARMv7 processor implementations, + * however some exceptions may exist. Caveat emptor. + * + * - The clobber list is dictated by the call to v7_flush_dcache_*. + * fp is preserved to the stack explicitly prior disabling the cache + * since adding it to the clobber list is incompatible with having + * CONFIG_FRAME_POINTER=y. ip is saved as well if ever r12-clobbering + * trampoline are inserted by the linker and to keep sp 64-bit aligned. + */ +#define v7_exit_coherency_flush(level) \ + asm volatile( \ + "stmfd sp!, {fp, ip} \n\t" \ + "mrc p15, 0, r0, c1, c0, 0 @ get SCTLR \n\t" \ + "bic r0, r0, #"__stringify(CR_C)" \n\t" \ + "mcr p15, 0, r0, c1, c0, 0 @ set SCTLR \n\t" \ + "isb \n\t" \ + "bl v7_flush_dcache_"__stringify(level)" \n\t" \ + "clrex \n\t" \ + "mrc p15, 0, r0, c1, c0, 1 @ get ACTLR \n\t" \ + "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" \ + "mcr p15, 0, r0, c1, c0, 1 @ set ACTLR \n\t" \ + "isb \n\t" \ + "dsb \n\t" \ + "ldmfd sp!, {fp, ip}" \ + : : : "r0","r1","r2","r3","r4","r5","r6","r7", \ + "r9","r10","lr","memory" ) + +int set_memory_ro(unsigned long addr, int numpages); +int set_memory_rw(unsigned long addr, int numpages); +int set_memory_x(unsigned long addr, int numpages); +int set_memory_nx(unsigned long addr, int numpages); + +void flush_uprobe_xol_access(struct page *page, unsigned long uaddr, + void *kaddr, unsigned long len); #endif |