diff options
Diffstat (limited to 'arch/arm/include/asm')
| -rw-r--r-- | arch/arm/include/asm/cacheflush.h | 4 | ||||
| -rw-r--r-- | arch/arm/include/asm/cputype.h | 2 | ||||
| -rw-r--r-- | arch/arm/include/asm/div64.h | 2 | ||||
| -rw-r--r-- | arch/arm/include/asm/glue-proc.h | 9 | ||||
| -rw-r--r-- | arch/arm/include/asm/io.h | 8 | ||||
| -rw-r--r-- | arch/arm/include/asm/mmu_context.h | 23 | ||||
| -rw-r--r-- | arch/arm/include/asm/percpu.h | 11 | ||||
| -rw-r--r-- | arch/arm/include/asm/smp_plat.h | 2 | ||||
| -rw-r--r-- | arch/arm/include/asm/spinlock.h | 25 | ||||
| -rw-r--r-- | arch/arm/include/asm/thread_info.h | 2 | ||||
| -rw-r--r-- | arch/arm/include/asm/tlb.h | 27 | ||||
| -rw-r--r-- | arch/arm/include/asm/tls.h | 40 |
12 files changed, 91 insertions, 64 deletions
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index bff71388e72a..17d0ae8672fa 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -320,9 +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) diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 7652712d1d14..dba62cb1ad08 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -32,6 +32,8 @@ #define MPIDR_HWID_BITMASK 0xFFFFFF +#define MPIDR_INVALID (~MPIDR_HWID_BITMASK) + #define MPIDR_LEVEL_BITS 8 #define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1) diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h index fe92ccf1d0b0..191ada6e4d2d 100644 --- a/arch/arm/include/asm/div64.h +++ b/arch/arm/include/asm/div64.h @@ -46,7 +46,7 @@ __rem; \ }) -#if __GNUC__ < 4 +#if __GNUC__ < 4 || !defined(CONFIG_AEABI) /* * gcc versions earlier than 4.0 are simply too problematic for the diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h index ac1dd54724b6..8017e94acc5e 100644 --- a/arch/arm/include/asm/glue-proc.h +++ b/arch/arm/include/asm/glue-proc.h @@ -230,6 +230,15 @@ # endif #endif +#ifdef CONFIG_CPU_PJ4B +# ifdef CPU_NAME +# undef MULTI_CPU +# define MULTI_CPU +# else +# define CPU_NAME cpu_pj4b +# endif +#endif + #ifndef MULTI_CPU #define cpu_proc_init __glue(CPU_NAME,_proc_init) #define cpu_proc_fin __glue(CPU_NAME,_proc_fin) diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 652b56086de7..d070741b2b37 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -130,16 +130,16 @@ static inline u32 __raw_readl(const volatile void __iomem *addr) */ extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long, size_t, unsigned int, void *); -extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int, +extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int, void *); extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int); -extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int); -extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached); +extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int); +extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached); extern void __iounmap(volatile void __iomem *addr); extern void __arm_iounmap(volatile void __iomem *addr); -extern void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, +extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *); extern void (*arch_iounmap)(volatile void __iomem *); diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index a7b85e0d0cc1..b5792b7fd8d3 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -18,6 +18,7 @@ #include <asm/cacheflush.h> #include <asm/cachetype.h> #include <asm/proc-fns.h> +#include <asm/smp_plat.h> #include <asm-generic/mm_hooks.h> void __check_vmalloc_seq(struct mm_struct *mm); @@ -27,7 +28,15 @@ void __check_vmalloc_seq(struct mm_struct *mm); void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk); #define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) -DECLARE_PER_CPU(atomic64_t, active_asids); +#ifdef CONFIG_ARM_ERRATA_798181 +void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask); +#else /* !CONFIG_ARM_ERRATA_798181 */ +static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, + cpumask_t *mask) +{ +} +#endif /* CONFIG_ARM_ERRATA_798181 */ #else /* !CONFIG_CPU_HAS_ASID */ @@ -98,12 +107,16 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, #ifdef CONFIG_MMU unsigned int cpu = smp_processor_id(); -#ifdef CONFIG_SMP - /* check for possible thread migration */ - if (!cpumask_empty(mm_cpumask(next)) && + /* + * __sync_icache_dcache doesn't broadcast the I-cache invalidation, + * so check for possible thread migration and invalidate the I-cache + * if we're new to this CPU. + */ + if (cache_ops_need_broadcast() && + !cpumask_empty(mm_cpumask(next)) && !cpumask_test_cpu(cpu, mm_cpumask(next))) __flush_icache_all(); -#endif + if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) { check_and_switch_context(next, tsk); if (cache_is_vivt()) diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index 968c0a14e0a3..209e6504922e 100644 --- a/arch/arm/include/asm/percpu.h +++ b/arch/arm/include/asm/percpu.h @@ -30,8 +30,15 @@ static inline void set_my_cpu_offset(unsigned long off) static inline unsigned long __my_cpu_offset(void) { unsigned long off; - /* Read TPIDRPRW */ - asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : : "memory"); + register unsigned long *sp asm ("sp"); + + /* + * Read TPIDRPRW. + * We want to allow caching the value, so avoid using volatile and + * instead use a fake stack read to hazard against barrier(). + */ + asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : "Q" (*sp)); + return off; } #define __my_cpu_offset __my_cpu_offset() diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h index aaa61b6f50ff..e78983202737 100644 --- a/arch/arm/include/asm/smp_plat.h +++ b/arch/arm/include/asm/smp_plat.h @@ -49,7 +49,7 @@ static inline int cache_ops_need_broadcast(void) /* * Logical CPU mapping. */ -extern int __cpu_logical_map[]; +extern u32 __cpu_logical_map[]; #define cpu_logical_map(cpu) __cpu_logical_map[cpu] /* * Retrieve logical cpu index corresponding to a given MPIDR[23:0] diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 6220e9fdf4c7..f8b8965666e9 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -97,19 +97,22 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) static inline int arch_spin_trylock(arch_spinlock_t *lock) { - unsigned long tmp; + unsigned long contended, res; u32 slock; - __asm__ __volatile__( -" ldrex %0, [%2]\n" -" subs %1, %0, %0, ror #16\n" -" addeq %0, %0, %3\n" -" strexeq %1, %0, [%2]" - : "=&r" (slock), "=&r" (tmp) - : "r" (&lock->slock), "I" (1 << TICKET_SHIFT) - : "cc"); - - if (tmp == 0) { + do { + __asm__ __volatile__( + " ldrex %0, [%3]\n" + " mov %2, #0\n" + " subs %1, %0, %0, ror #16\n" + " addeq %0, %0, %4\n" + " strexeq %2, %0, [%3]" + : "=&r" (slock), "=&r" (contended), "=r" (res) + : "r" (&lock->slock), "I" (1 << TICKET_SHIFT) + : "cc"); + } while (res); + + if (!contended) { smp_mb(); return 1; } else { diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 1995d1a84060..214d4158089a 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -58,7 +58,7 @@ struct thread_info { struct cpu_context_save cpu_context; /* cpu context */ __u32 syscall; /* syscall number */ __u8 used_cp[16]; /* thread used copro */ - unsigned long tp_value; + unsigned long tp_value[2]; /* TLS registers */ #ifdef CONFIG_CRUNCH struct crunch_state crunchstate; #endif diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index 99a19512ee26..bdf2b8458ec1 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -33,18 +33,6 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> -/* - * We need to delay page freeing for SMP as other CPUs can access pages - * which have been removed but not yet had their TLB entries invalidated. - * Also, as ARMv7 speculative prefetch can drag new entries into the TLB, - * we need to apply this same delaying tactic to ensure correct operation. - */ -#if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7) -#define tlb_fast_mode(tlb) 0 -#else -#define tlb_fast_mode(tlb) 1 -#endif - #define MMU_GATHER_BUNDLE 8 /* @@ -112,12 +100,10 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb) static inline void tlb_flush_mmu(struct mmu_gather *tlb) { tlb_flush(tlb); - if (!tlb_fast_mode(tlb)) { - free_pages_and_swap_cache(tlb->pages, tlb->nr); - tlb->nr = 0; - if (tlb->pages == tlb->local) - __tlb_alloc_page(tlb); - } + free_pages_and_swap_cache(tlb->pages, tlb->nr); + tlb->nr = 0; + if (tlb->pages == tlb->local) + __tlb_alloc_page(tlb); } static inline void @@ -178,11 +164,6 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { - if (tlb_fast_mode(tlb)) { - free_page_and_swap_cache(page); - return 1; /* avoid calling tlb_flush_mmu */ - } - tlb->pages[tlb->nr++] = page; VM_BUG_ON(tlb->nr > tlb->max); return tlb->max - tlb->nr; diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h index 73409e6c0251..83259b873333 100644 --- a/arch/arm/include/asm/tls.h +++ b/arch/arm/include/asm/tls.h @@ -2,27 +2,30 @@ #define __ASMARM_TLS_H #ifdef __ASSEMBLY__ - .macro set_tls_none, tp, tmp1, tmp2 +#include <asm/asm-offsets.h> + .macro switch_tls_none, base, tp, tpuser, tmp1, tmp2 .endm - .macro set_tls_v6k, tp, tmp1, tmp2 + .macro switch_tls_v6k, base, tp, tpuser, tmp1, tmp2 + mrc p15, 0, \tmp2, c13, c0, 2 @ get the user r/w register mcr p15, 0, \tp, c13, c0, 3 @ set TLS register - mov \tmp1, #0 - mcr p15, 0, \tmp1, c13, c0, 2 @ clear user r/w TLS register + mcr p15, 0, \tpuser, c13, c0, 2 @ and the user r/w register + str \tmp2, [\base, #TI_TP_VALUE + 4] @ save it .endm - .macro set_tls_v6, tp, tmp1, tmp2 + .macro switch_tls_v6, base, tp, tpuser, tmp1, tmp2 ldr \tmp1, =elf_hwcap ldr \tmp1, [\tmp1, #0] mov \tmp2, #0xffff0fff tst \tmp1, #HWCAP_TLS @ hardware TLS available? - mcrne p15, 0, \tp, c13, c0, 3 @ yes, set TLS register - movne \tmp1, #0 - mcrne p15, 0, \tmp1, c13, c0, 2 @ clear user r/w TLS register streq \tp, [\tmp2, #-15] @ set TLS value at 0xffff0ff0 + mrcne p15, 0, \tmp2, c13, c0, 2 @ get the user r/w register + mcrne p15, 0, \tp, c13, c0, 3 @ yes, set TLS register + mcrne p15, 0, \tpuser, c13, c0, 2 @ set user r/w register + strne \tmp2, [\base, #TI_TP_VALUE + 4] @ save it .endm - .macro set_tls_software, tp, tmp1, tmp2 + .macro switch_tls_software, base, tp, tpuser, tmp1, tmp2 mov \tmp1, #0xffff0fff str \tp, [\tmp1, #-15] @ set TLS value at 0xffff0ff0 .endm @@ -31,19 +34,30 @@ #ifdef CONFIG_TLS_REG_EMUL #define tls_emu 1 #define has_tls_reg 1 -#define set_tls set_tls_none +#define switch_tls switch_tls_none #elif defined(CONFIG_CPU_V6) #define tls_emu 0 #define has_tls_reg (elf_hwcap & HWCAP_TLS) -#define set_tls set_tls_v6 +#define switch_tls switch_tls_v6 #elif defined(CONFIG_CPU_32v6K) #define tls_emu 0 #define has_tls_reg 1 -#define set_tls set_tls_v6k +#define switch_tls switch_tls_v6k #else #define tls_emu 0 #define has_tls_reg 0 -#define set_tls set_tls_software +#define switch_tls switch_tls_software #endif +#ifndef __ASSEMBLY__ +static inline unsigned long get_tpuser(void) +{ + unsigned long reg = 0; + + if (has_tls_reg && !tls_emu) + __asm__("mrc p15, 0, %0, c13, c0, 2" : "=r" (reg)); + + return reg; +} +#endif #endif /* __ASMARM_TLS_H */ |