diff options
Diffstat (limited to 'arch/arm/include/asm')
139 files changed, 4478 insertions, 1644 deletions
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index d3db39860b9..f5a35760198 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -7,23 +7,28 @@ generic-y += current.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h +generic-y += hash.h generic-y += ioctl.h generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += kdebug.h generic-y += local.h generic-y += local64.h +generic-y += mcs_spinlock.h generic-y += msgbuf.h generic-y += param.h generic-y += parport.h generic-y += poll.h +generic-y += preempt.h generic-y += resource.h +generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += sembuf.h generic-y += serial.h generic-y += shmbuf.h generic-y += siginfo.h +generic-y += simd.h generic-y += sizes.h generic-y += socket.h generic-y += sockios.h @@ -31,5 +36,4 @@ generic-y += termbits.h generic-y += termios.h generic-y += timex.h generic-y += trace_clock.h -generic-y += types.h generic-y += unaligned.h diff --git a/arch/arm/include/asm/a.out-core.h b/arch/arm/include/asm/a.out-core.h deleted file mode 100644 index 92f10cb5c70..00000000000 --- a/arch/arm/include/asm/a.out-core.h +++ /dev/null @@ -1,45 +0,0 @@ -/* a.out coredump register dumper - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#ifndef _ASM_A_OUT_CORE_H -#define _ASM_A_OUT_CORE_H - -#ifdef __KERNEL__ - -#include <linux/user.h> -#include <linux/elfcore.h> - -/* - * fill in the user structure for an a.out core dump - */ -static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) -{ - struct task_struct *tsk = current; - - dump->magic = CMAGIC; - dump->start_code = tsk->mm->start_code; - dump->start_stack = regs->ARM_sp & ~(PAGE_SIZE - 1); - - dump->u_tsize = (tsk->mm->end_code - tsk->mm->start_code) >> PAGE_SHIFT; - dump->u_dsize = (tsk->mm->brk - tsk->mm->start_data + PAGE_SIZE - 1) >> PAGE_SHIFT; - dump->u_ssize = 0; - - memset(dump->u_debugreg, 0, sizeof(dump->u_debugreg)); - - if (dump->start_stack < 0x04000000) - dump->u_ssize = (0x04000000 - dump->start_stack) >> PAGE_SHIFT; - - dump->regs = *regs; - dump->u_fpvalid = dump_fpu (regs, &dump->u_fp); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_A_OUT_CORE_H */ diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h index d40229d9a1c..0704e0cf557 100644 --- a/arch/arm/include/asm/arch_timer.h +++ b/arch/arm/include/asm/arch_timer.h @@ -1,28 +1,129 @@ #ifndef __ASMARM_ARCH_TIMER_H #define __ASMARM_ARCH_TIMER_H +#include <asm/barrier.h> #include <asm/errno.h> #include <linux/clocksource.h> +#include <linux/init.h> +#include <linux/types.h> + +#include <clocksource/arm_arch_timer.h> #ifdef CONFIG_ARM_ARCH_TIMER -int arch_timer_of_register(void); -int arch_timer_sched_clock_init(void); -struct timecounter *arch_timer_get_timecounter(void); -#else -static inline int arch_timer_of_register(void) +int arch_timer_arch_init(void); + +/* + * These register accessors are marked inline so the compiler can + * nicely work out which register we want, and chuck away the rest of + * the code. At least it does so with a recent GCC (4.6.3). + */ +static __always_inline +void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) +{ + if (access == ARCH_TIMER_PHYS_ACCESS) { + switch (reg) { + case ARCH_TIMER_REG_CTRL: + asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val)); + break; + case ARCH_TIMER_REG_TVAL: + asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val)); + break; + } + } else if (access == ARCH_TIMER_VIRT_ACCESS) { + switch (reg) { + case ARCH_TIMER_REG_CTRL: + asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val)); + break; + case ARCH_TIMER_REG_TVAL: + asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val)); + break; + } + } + + isb(); +} + +static __always_inline +u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) { - return -ENXIO; + u32 val = 0; + + if (access == ARCH_TIMER_PHYS_ACCESS) { + switch (reg) { + case ARCH_TIMER_REG_CTRL: + asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val)); + break; + case ARCH_TIMER_REG_TVAL: + asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val)); + break; + } + } else if (access == ARCH_TIMER_VIRT_ACCESS) { + switch (reg) { + case ARCH_TIMER_REG_CTRL: + asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val)); + break; + case ARCH_TIMER_REG_TVAL: + asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val)); + break; + } + } + + return val; +} + +static inline u32 arch_timer_get_cntfrq(void) +{ + u32 val; + asm volatile("mrc p15, 0, %0, c14, c0, 0" : "=r" (val)); + return val; } -static inline int arch_timer_sched_clock_init(void) +static inline u64 arch_counter_get_cntvct(void) { - return -ENXIO; + u64 cval; + + isb(); + asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (cval)); + return cval; } -static inline struct timecounter *arch_timer_get_timecounter(void) +static inline u32 arch_timer_get_cntkctl(void) { - return NULL; + u32 cntkctl; + asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl)); + return cntkctl; } + +static inline void arch_timer_set_cntkctl(u32 cntkctl) +{ + asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl)); +} + +static inline void arch_counter_set_user_access(void) +{ + u32 cntkctl = arch_timer_get_cntkctl(); + + /* Disable user access to both physical/virtual counters/timers */ + /* Also disable virtual event stream */ + cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN + | ARCH_TIMER_USR_VT_ACCESS_EN + | ARCH_TIMER_VIRT_EVT_EN + | ARCH_TIMER_USR_VCT_ACCESS_EN + | ARCH_TIMER_USR_PCT_ACCESS_EN); + arch_timer_set_cntkctl(cntkctl); +} + +static inline void arch_timer_evtstrm_enable(int divider) +{ + u32 cntkctl = arch_timer_get_cntkctl(); + cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK; + /* Set the divider and enable virtual event stream */ + cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT) + | ARCH_TIMER_VIRT_EVT_EN; + arch_timer_set_cntkctl(cntkctl); + elf_hwcap |= HWCAP_EVTSTRM; +} + #endif #endif diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index eb87200aa4b..57f0584e8d9 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -23,6 +23,7 @@ #include <asm/ptrace.h> #include <asm/domain.h> #include <asm/opcodes-virt.h> +#include <asm/asm-offsets.h> #define IOMEM(x) (x) @@ -30,8 +31,8 @@ * Endian independent macros for shifting bytes within registers. */ #ifndef __ARMEB__ -#define pull lsr -#define push lsl +#define lspull lsr +#define lspush lsl #define get_byte_0 lsl #0 #define get_byte_1 lsr #8 #define get_byte_2 lsr #16 @@ -41,8 +42,8 @@ #define put_byte_2 lsl #16 #define put_byte_3 lsl #24 #else -#define pull lsl -#define push lsr +#define lspull lsl +#define lspush lsr #define get_byte_0 lsr #24 #define get_byte_1 lsr #16 #define get_byte_2 lsr #8 @@ -53,6 +54,13 @@ #define put_byte_3 lsl #0 #endif +/* Select code for any configuration running in BE8 mode */ +#ifdef CONFIG_CPU_ENDIAN_BE8 +#define ARM_BE8(code...) code +#else +#define ARM_BE8(code...) +#endif + /* * Data preload for architectures that support it */ @@ -136,7 +144,11 @@ * assumes FIQs are enabled, and that the processor is in SVC mode. */ .macro save_and_disable_irqs, oldcpsr +#ifdef CONFIG_CPU_V7M + mrs \oldcpsr, primask +#else mrs \oldcpsr, cpsr +#endif disable_irq .endm @@ -150,7 +162,11 @@ * guarantee that this will preserve the flags. */ .macro restore_irqs_notrace, oldcpsr +#ifdef CONFIG_CPU_V7M + msr primask, \oldcpsr +#else msr cpsr_c, \oldcpsr +#endif .endm .macro restore_irqs, oldcpsr @@ -159,6 +175,47 @@ restore_irqs_notrace \oldcpsr .endm +/* + * Get current thread_info. + */ + .macro get_thread_info, rd + ARM( mov \rd, sp, lsr #13 ) + THUMB( mov \rd, sp ) + THUMB( lsr \rd, \rd, #13 ) + mov \rd, \rd, lsl #13 + .endm + +/* + * Increment/decrement the preempt count. + */ +#ifdef CONFIG_PREEMPT_COUNT + .macro inc_preempt_count, ti, tmp + ldr \tmp, [\ti, #TI_PREEMPT] @ get preempt count + add \tmp, \tmp, #1 @ increment it + str \tmp, [\ti, #TI_PREEMPT] + .endm + + .macro dec_preempt_count, ti, tmp + ldr \tmp, [\ti, #TI_PREEMPT] @ get preempt count + sub \tmp, \tmp, #1 @ decrement it + str \tmp, [\ti, #TI_PREEMPT] + .endm + + .macro dec_preempt_count_ti, ti, tmp + get_thread_info \ti + dec_preempt_count \ti, \tmp + .endm +#else + .macro inc_preempt_count, ti, tmp + .endm + + .macro dec_preempt_count, ti, tmp + .endm + + .macro dec_preempt_count_ti, ti, tmp + .endm +#endif + #define USER(x...) \ 9999: x; \ .pushsection __ex_table,"a"; \ @@ -212,9 +269,9 @@ #ifdef CONFIG_SMP #if __LINUX_ARM_ARCH__ >= 7 .ifeqs "\mode","arm" - ALT_SMP(dmb) + ALT_SMP(dmb ish) .else - ALT_SMP(W(dmb)) + ALT_SMP(W(dmb) ish) .endif #elif __LINUX_ARM_ARCH__ == 6 ALT_SMP(mcr p15, 0, r0, c7, c10, 5) @ dmb @@ -229,7 +286,14 @@ #endif .endm -#ifdef CONFIG_THUMB2_KERNEL +#if defined(CONFIG_CPU_V7M) + /* + * setmode is used to assert to be in svc mode during boot. For v7-M + * this is done in __v7m_setup, so setmode can be empty here. + */ + .macro setmode, mode, reg + .endm +#elif defined(CONFIG_THUMB2_KERNEL) .macro setmode, mode, reg mov \reg, #\mode msr cpsr_c, \reg @@ -246,18 +310,14 @@ * * This macro is intended for forcing the CPU into SVC mode at boot time. * you cannot return to the original mode. - * - * Beware, it also clobers LR. */ .macro safe_svcmode_maskall reg:req -#if __LINUX_ARM_ARCH__ >= 6 +#if __LINUX_ARM_ARCH__ >= 6 && !defined(CONFIG_CPU_V7M) mrs \reg , cpsr - mov lr , \reg - and lr , lr , #MODE_MASK - cmp lr , #HYP_MODE - orr \reg , \reg , #PSR_I_BIT | PSR_F_BIT + eor \reg, \reg, #HYP_MODE + tst \reg, #MODE_MASK bic \reg , \reg , #MODE_MASK - orr \reg , \reg , #SVC_MODE + orr \reg , \reg , #PSR_I_BIT | PSR_F_BIT | SVC_MODE THUMB( orr \reg , \reg , #PSR_T_BIT ) bne 1f orr \reg, \reg, #PSR_A_BIT diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index c79f61faa3a..3040359094d 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -12,6 +12,7 @@ #define __ASM_ARM_ATOMIC_H #include <linux/compiler.h> +#include <linux/prefetch.h> #include <linux/types.h> #include <linux/irqflags.h> #include <asm/barrier.h> @@ -41,6 +42,7 @@ static inline void atomic_add(int i, atomic_t *v) unsigned long tmp; int result; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic_add\n" "1: ldrex %0, [%3]\n" " add %0, %0, %4\n" @@ -58,6 +60,7 @@ static inline int atomic_add_return(int i, atomic_t *v) int result; smp_mb(); + prefetchw(&v->counter); __asm__ __volatile__("@ atomic_add_return\n" "1: ldrex %0, [%3]\n" @@ -79,6 +82,7 @@ static inline void atomic_sub(int i, atomic_t *v) unsigned long tmp; int result; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic_sub\n" "1: ldrex %0, [%3]\n" " sub %0, %0, %4\n" @@ -96,6 +100,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) int result; smp_mb(); + prefetchw(&v->counter); __asm__ __volatile__("@ atomic_sub_return\n" "1: ldrex %0, [%3]\n" @@ -114,9 +119,11 @@ static inline int atomic_sub_return(int i, atomic_t *v) static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) { - unsigned long oldval, res; + int oldval; + unsigned long res; smp_mb(); + prefetchw(&ptr->counter); do { __asm__ __volatile__("@ atomic_cmpxchg\n" @@ -134,19 +141,31 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) return oldval; } -static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr) +static inline int __atomic_add_unless(atomic_t *v, int a, int u) { - unsigned long tmp, tmp2; + int oldval, newval; + unsigned long tmp; - __asm__ __volatile__("@ atomic_clear_mask\n" -"1: ldrex %0, [%3]\n" -" bic %0, %0, %4\n" -" strex %1, %0, [%3]\n" -" teq %1, #0\n" -" bne 1b" - : "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr) - : "r" (addr), "Ir" (mask) + smp_mb(); + prefetchw(&v->counter); + + __asm__ __volatile__ ("@ atomic_add_unless\n" +"1: ldrex %0, [%4]\n" +" teq %0, %5\n" +" beq 2f\n" +" add %1, %0, %6\n" +" strex %2, %1, [%4]\n" +" teq %2, #0\n" +" bne 1b\n" +"2:" + : "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter) + : "r" (&v->counter), "r" (u), "r" (a) : "cc"); + + if (oldval != u) + smp_mb(); + + return oldval; } #else /* ARM_ARCH_6 */ @@ -197,19 +216,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr) -{ - unsigned long flags; - - raw_local_irq_save(flags); - *addr &= ~mask; - raw_local_irq_restore(flags); -} - -#endif /* __LINUX_ARM_ARCH__ */ - -#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) - static inline int __atomic_add_unless(atomic_t *v, int a, int u) { int c, old; @@ -220,6 +226,10 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return c; } +#endif /* __LINUX_ARM_ARCH__ */ + +#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) + #define atomic_inc(v) atomic_add(1, v) #define atomic_dec(v) atomic_sub(1, v) @@ -231,21 +241,39 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0) -#define smp_mb__before_atomic_dec() smp_mb() -#define smp_mb__after_atomic_dec() smp_mb() -#define smp_mb__before_atomic_inc() smp_mb() -#define smp_mb__after_atomic_inc() smp_mb() - #ifndef CONFIG_GENERIC_ATOMIC64 typedef struct { - u64 __aligned(8) counter; + long long counter; } atomic64_t; #define ATOMIC64_INIT(i) { (i) } -static inline u64 atomic64_read(const atomic64_t *v) +#ifdef CONFIG_ARM_LPAE +static inline long long atomic64_read(const atomic64_t *v) { - u64 result; + long long result; + + __asm__ __volatile__("@ atomic64_read\n" +" ldrd %0, %H0, [%1]" + : "=&r" (result) + : "r" (&v->counter), "Qo" (v->counter) + ); + + return result; +} + +static inline void atomic64_set(atomic64_t *v, long long i) +{ + __asm__ __volatile__("@ atomic64_set\n" +" strd %2, %H2, [%1]" + : "=Qo" (v->counter) + : "r" (&v->counter), "r" (i) + ); +} +#else +static inline long long atomic64_read(const atomic64_t *v) +{ + long long result; __asm__ __volatile__("@ atomic64_read\n" " ldrexd %0, %H0, [%1]" @@ -256,10 +284,11 @@ static inline u64 atomic64_read(const atomic64_t *v) return result; } -static inline void atomic64_set(atomic64_t *v, u64 i) +static inline void atomic64_set(atomic64_t *v, long long i) { - u64 tmp; + long long tmp; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_set\n" "1: ldrexd %0, %H0, [%2]\n" " strexd %0, %3, %H3, [%2]\n" @@ -269,16 +298,18 @@ static inline void atomic64_set(atomic64_t *v, u64 i) : "r" (&v->counter), "r" (i) : "cc"); } +#endif -static inline void atomic64_add(u64 i, atomic64_t *v) +static inline void atomic64_add(long long i, atomic64_t *v) { - u64 result; + long long result; unsigned long tmp; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_add\n" "1: ldrexd %0, %H0, [%3]\n" -" adds %0, %0, %4\n" -" adc %H0, %H0, %H4\n" +" adds %Q0, %Q0, %Q4\n" +" adc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -287,17 +318,18 @@ static inline void atomic64_add(u64 i, atomic64_t *v) : "cc"); } -static inline u64 atomic64_add_return(u64 i, atomic64_t *v) +static inline long long atomic64_add_return(long long i, atomic64_t *v) { - u64 result; + long long result; unsigned long tmp; smp_mb(); + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_add_return\n" "1: ldrexd %0, %H0, [%3]\n" -" adds %0, %0, %4\n" -" adc %H0, %H0, %H4\n" +" adds %Q0, %Q0, %Q4\n" +" adc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -310,15 +342,16 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v) return result; } -static inline void atomic64_sub(u64 i, atomic64_t *v) +static inline void atomic64_sub(long long i, atomic64_t *v) { - u64 result; + long long result; unsigned long tmp; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_sub\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, %4\n" -" sbc %H0, %H0, %H4\n" +" subs %Q0, %Q0, %Q4\n" +" sbc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -327,17 +360,18 @@ static inline void atomic64_sub(u64 i, atomic64_t *v) : "cc"); } -static inline u64 atomic64_sub_return(u64 i, atomic64_t *v) +static inline long long atomic64_sub_return(long long i, atomic64_t *v) { - u64 result; + long long result; unsigned long tmp; smp_mb(); + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_sub_return\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, %4\n" -" sbc %H0, %H0, %H4\n" +" subs %Q0, %Q0, %Q4\n" +" sbc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -350,12 +384,14 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v) return result; } -static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new) +static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old, + long long new) { - u64 oldval; + long long oldval; unsigned long res; smp_mb(); + prefetchw(&ptr->counter); do { __asm__ __volatile__("@ atomic64_cmpxchg\n" @@ -374,12 +410,13 @@ static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new) return oldval; } -static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new) +static inline long long atomic64_xchg(atomic64_t *ptr, long long new) { - u64 result; + long long result; unsigned long tmp; smp_mb(); + prefetchw(&ptr->counter); __asm__ __volatile__("@ atomic64_xchg\n" "1: ldrexd %0, %H0, [%3]\n" @@ -395,18 +432,19 @@ static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new) return result; } -static inline u64 atomic64_dec_if_positive(atomic64_t *v) +static inline long long atomic64_dec_if_positive(atomic64_t *v) { - u64 result; + long long result; unsigned long tmp; smp_mb(); + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_dec_if_positive\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, #1\n" -" sbc %H0, %H0, #0\n" -" teq %H0, #0\n" +" subs %Q0, %Q0, #1\n" +" sbc %R0, %R0, #0\n" +" teq %R0, #0\n" " bmi 2f\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" @@ -421,13 +459,14 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v) return result; } -static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u) +static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) { - u64 val; + long long val; unsigned long tmp; int ret = 1; smp_mb(); + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_add_unless\n" "1: ldrexd %0, %H0, [%4]\n" @@ -435,8 +474,8 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u) " teqeq %H0, %H5\n" " moveq %1, #0\n" " beq 2f\n" -" adds %0, %0, %6\n" -" adc %H0, %H0, %H6\n" +" adds %Q0, %Q0, %Q6\n" +" adc %R0, %R0, %R6\n" " strexd %2, %0, %H0, [%4]\n" " teq %2, #0\n" " bne 1b\n" diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h new file mode 100644 index 00000000000..1714800fa11 --- /dev/null +++ b/arch/arm/include/asm/bL_switcher.h @@ -0,0 +1,77 @@ +/* + * arch/arm/include/asm/bL_switcher.h + * + * Created by: Nicolas Pitre, April 2012 + * Copyright: (C) 2012-2013 Linaro Limited + * + * 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. + */ + +#ifndef ASM_BL_SWITCHER_H +#define ASM_BL_SWITCHER_H + +#include <linux/compiler.h> +#include <linux/types.h> + +typedef void (*bL_switch_completion_handler)(void *cookie); + +int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id, + bL_switch_completion_handler completer, + void *completer_cookie); +static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id) +{ + return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL); +} + +/* + * Register here to be notified about runtime enabling/disabling of + * the switcher. + * + * The notifier chain is called with the switcher activation lock held: + * the switcher will not be enabled or disabled during callbacks. + * Callbacks must not call bL_switcher_{get,put}_enabled(). + */ +#define BL_NOTIFY_PRE_ENABLE 0 +#define BL_NOTIFY_POST_ENABLE 1 +#define BL_NOTIFY_PRE_DISABLE 2 +#define BL_NOTIFY_POST_DISABLE 3 + +#ifdef CONFIG_BL_SWITCHER + +int bL_switcher_register_notifier(struct notifier_block *nb); +int bL_switcher_unregister_notifier(struct notifier_block *nb); + +/* + * Use these functions to temporarily prevent enabling/disabling of + * the switcher. + * bL_switcher_get_enabled() returns true if the switcher is currently + * enabled. Each call to bL_switcher_get_enabled() must be followed + * by a call to bL_switcher_put_enabled(). These functions are not + * recursive. + */ +bool bL_switcher_get_enabled(void); +void bL_switcher_put_enabled(void); + +int bL_switcher_trace_trigger(void); +int bL_switcher_get_logical_index(u32 mpidr); + +#else +static inline int bL_switcher_register_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int bL_switcher_unregister_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline bool bL_switcher_get_enabled(void) { return false; } +static inline void bL_switcher_put_enabled(void) { } +static inline int bL_switcher_trace_trigger(void) { return 0; } +static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; } +#endif /* CONFIG_BL_SWITCHER */ + +#endif diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h index 8dcd9c702d9..c6a3e73a6e2 100644 --- a/arch/arm/include/asm/barrier.h +++ b/arch/arm/include/asm/barrier.h @@ -14,27 +14,27 @@ #endif #if __LINUX_ARM_ARCH__ >= 7 -#define isb() __asm__ __volatile__ ("isb" : : : "memory") -#define dsb() __asm__ __volatile__ ("dsb" : : : "memory") -#define dmb() __asm__ __volatile__ ("dmb" : : : "memory") +#define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory") +#define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory") +#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory") #elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6 -#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ +#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ : : "r" (0) : "memory") -#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ +#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ : : "r" (0) : "memory") -#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \ +#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \ : : "r" (0) : "memory") #elif defined(CONFIG_CPU_FA526) -#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ +#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \ : : "r" (0) : "memory") -#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ +#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ : : "r" (0) : "memory") -#define dmb() __asm__ __volatile__ ("" : : : "memory") +#define dmb(x) __asm__ __volatile__ ("" : : : "memory") #else -#define isb() __asm__ __volatile__ ("" : : : "memory") -#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ +#define isb(x) __asm__ __volatile__ ("" : : : "memory") +#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \ : : "r" (0) : "memory") -#define dmb() __asm__ __volatile__ ("" : : : "memory") +#define dmb(x) __asm__ __volatile__ ("" : : : "memory") #endif #ifdef CONFIG_ARCH_HAS_BARRIERS @@ -42,7 +42,7 @@ #elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP) #define mb() do { dsb(); outer_sync(); } while (0) #define rmb() dsb() -#define wmb() mb() +#define wmb() do { dsb(st); outer_sync(); } while (0) #else #define mb() barrier() #define rmb() barrier() @@ -54,15 +54,33 @@ #define smp_rmb() barrier() #define smp_wmb() barrier() #else -#define smp_mb() dmb() -#define smp_rmb() dmb() -#define smp_wmb() dmb() +#define smp_mb() dmb(ish) +#define smp_rmb() smp_mb() +#define smp_wmb() dmb(ishst) #endif +#define smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + smp_mb(); \ + ACCESS_ONCE(*p) = (v); \ +} while (0) + +#define smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + smp_mb(); \ + ___p1; \ +}) + #define read_barrier_depends() do { } while(0) #define smp_read_barrier_depends() do { } while(0) #define set_mb(var, value) do { var = value; smp_mb(); } while (0) +#define smp_mb__before_atomic() smp_mb() +#define smp_mb__after_atomic() smp_mb() + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_BARRIER_H */ diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h index e691ec91e4d..56380995f4c 100644 --- a/arch/arm/include/asm/bitops.h +++ b/arch/arm/include/asm/bitops.h @@ -25,9 +25,7 @@ #include <linux/compiler.h> #include <linux/irqflags.h> - -#define smp_mb__before_clear_bit() smp_mb() -#define smp_mb__after_clear_bit() smp_mb() +#include <asm/barrier.h> /* * These functions are the basis of our bit ops. @@ -254,25 +252,59 @@ static inline int constant_fls(int x) } /* - * On ARMv5 and above those functions can be implemented around - * the clz instruction for much better code efficiency. + * On ARMv5 and above those functions can be implemented around the + * clz instruction for much better code efficiency. __clz returns + * the number of leading zeros, zero input will return 32, and + * 0x80000000 will return 0. */ +static inline unsigned int __clz(unsigned int x) +{ + unsigned int ret; + + asm("clz\t%0, %1" : "=r" (ret) : "r" (x)); + + return ret; +} +/* + * fls() returns zero if the input is zero, otherwise returns the bit + * position of the last set bit, where the LSB is 1 and MSB is 32. + */ static inline int fls(int x) { - int ret; - if (__builtin_constant_p(x)) return constant_fls(x); - asm("clz\t%0, %1" : "=r" (ret) : "r" (x)); - ret = 32 - ret; - return ret; + return 32 - __clz(x); +} + +/* + * __fls() returns the bit position of the last bit set, where the + * LSB is 0 and MSB is 31. Zero input is undefined. + */ +static inline unsigned long __fls(unsigned long x) +{ + return fls(x) - 1; +} + +/* + * ffs() returns zero if the input was zero, otherwise returns the bit + * position of the first set bit, where the LSB is 1 and MSB is 32. + */ +static inline int ffs(int x) +{ + return fls(x & -x); +} + +/* + * __ffs() returns the bit position of the first bit set, where the + * LSB is 0 and MSB is 31. Zero input is undefined. + */ +static inline unsigned long __ffs(unsigned long x) +{ + return ffs(x) - 1; } -#define __fls(x) (fls(x) - 1) -#define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); }) -#define __ffs(x) (ffs(x) - 1) #define ffz(x) __ffs( ~(x) ) #endif diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index 7af5c6c3653..b274bde2490 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -2,6 +2,8 @@ #define _ASMARM_BUG_H #include <linux/linkage.h> +#include <linux/types.h> +#include <asm/opcodes.h> #ifdef CONFIG_BUG @@ -12,10 +14,10 @@ */ #ifdef CONFIG_THUMB2_KERNEL #define BUG_INSTR_VALUE 0xde02 -#define BUG_INSTR_TYPE ".hword " +#define BUG_INSTR(__value) __inst_thumb16(__value) #else #define BUG_INSTR_VALUE 0xe7f001f2 -#define BUG_INSTR_TYPE ".word " +#define BUG_INSTR(__value) __inst_arm(__value) #endif @@ -33,7 +35,7 @@ #define __BUG(__file, __line, __value) \ do { \ - asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \ + asm volatile("1:\t" BUG_INSTR(__value) "\n" \ ".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \ "2:\t.asciz " #__file "\n" \ ".popsection\n" \ @@ -48,7 +50,7 @@ do { \ #define __BUG(__file, __line, __value) \ do { \ - asm volatile(BUG_INSTR_TYPE #__value); \ + asm volatile(BUG_INSTR(__value) "\n"); \ unreachable(); \ } while (0) #endif /* CONFIG_DEBUG_BUGVERBOSE */ diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e1489c54cd1..fd43f7f55b7 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -212,6 +212,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, static inline void __flush_icache_all(void) { __flush_icache_preferred(); + dsb(ishst); } /* @@ -268,8 +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(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 @@ -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) @@ -354,7 +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) @@ -363,4 +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 diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h index 6dcc1643086..52331511547 100644 --- a/arch/arm/include/asm/checksum.h +++ b/arch/arm/include/asm/checksum.h @@ -87,19 +87,33 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len, unsigned short proto, __wsum sum) { - __asm__( - "adds %0, %1, %2 @ csum_tcpudp_nofold \n\ - adcs %0, %0, %3 \n" + u32 lenprot = len | proto << 16; + if (__builtin_constant_p(sum) && sum == 0) { + __asm__( + "adds %0, %1, %2 @ csum_tcpudp_nofold0 \n\t" #ifdef __ARMEB__ - "adcs %0, %0, %4 \n" + "adcs %0, %0, %3 \n\t" #else - "adcs %0, %0, %4, lsl #8 \n" + "adcs %0, %0, %3, ror #8 \n\t" #endif - "adcs %0, %0, %5 \n\ - adc %0, %0, #0" - : "=&r"(sum) - : "r" (sum), "r" (daddr), "r" (saddr), "r" (len), "Ir" (htons(proto)) - : "cc"); + "adc %0, %0, #0" + : "=&r" (sum) + : "r" (daddr), "r" (saddr), "r" (lenprot) + : "cc"); + } else { + __asm__( + "adds %0, %1, %2 @ csum_tcpudp_nofold \n\t" + "adcs %0, %0, %3 \n\t" +#ifdef __ARMEB__ + "adcs %0, %0, %4 \n\t" +#else + "adcs %0, %0, %4, ror #8 \n\t" +#endif + "adc %0, %0, #0" + : "=&r"(sum) + : "r" (sum), "r" (daddr), "r" (saddr), "r" (lenprot) + : "cc"); + } return sum; } /* diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h index 80751c15c30..4e8a4b27d7c 100644 --- a/arch/arm/include/asm/clkdev.h +++ b/arch/arm/include/asm/clkdev.h @@ -14,12 +14,14 @@ #include <linux/slab.h> +#ifndef CONFIG_COMMON_CLK #ifdef CONFIG_HAVE_MACH_CLKDEV #include <mach/clkdev.h> #else #define __clk_get(clk) ({ 1; }) #define __clk_put(clk) do { } while (0) #endif +#endif static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size) { diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h index 7eb18c1d8d6..abb2c3769b0 100644 --- a/arch/arm/include/asm/cmpxchg.h +++ b/arch/arm/include/asm/cmpxchg.h @@ -2,6 +2,7 @@ #define __ASM_ARM_CMPXCHG_H #include <linux/irqflags.h> +#include <linux/prefetch.h> #include <asm/barrier.h> #if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110) @@ -35,6 +36,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size #endif smp_mb(); + prefetchw((const void *)ptr); switch (size) { #if __LINUX_ARM_ARCH__ >= 6 @@ -138,6 +140,8 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, { unsigned long oldval, res; + prefetchw((const void *)ptr); + switch (size) { #ifndef CONFIG_CPU_V6 /* min ARCH >= ARMv6K */ case 1: @@ -223,6 +227,44 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, return ret; } +static inline unsigned long long __cmpxchg64(unsigned long long *ptr, + unsigned long long old, + unsigned long long new) +{ + unsigned long long oldval; + unsigned long res; + + prefetchw(ptr); + + __asm__ __volatile__( +"1: ldrexd %1, %H1, [%3]\n" +" teq %1, %4\n" +" teqeq %H1, %H4\n" +" bne 2f\n" +" strexd %0, %5, %H5, [%3]\n" +" teq %0, #0\n" +" bne 1b\n" +"2:" + : "=&r" (res), "=&r" (oldval), "+Qo" (*ptr) + : "r" (ptr), "r" (old), "r" (new) + : "cc"); + + return oldval; +} + +static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr, + unsigned long long old, + unsigned long long new) +{ + unsigned long long ret; + + smp_mb(); + ret = __cmpxchg64(ptr, old, new); + smp_mb(); + + return ret; +} + #define cmpxchg_local(ptr,o,n) \ ((__typeof__(*(ptr)))__cmpxchg_local((ptr), \ (unsigned long)(o), \ @@ -230,18 +272,16 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, sizeof(*(ptr)))) #define cmpxchg64(ptr, o, n) \ - ((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr), \ - atomic64_t, \ - counter), \ - (unsigned long)(o), \ - (unsigned long)(n))) - -#define cmpxchg64_local(ptr, o, n) \ - ((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr), \ - local64_t, \ - a), \ - (unsigned long)(o), \ - (unsigned long)(n))) + ((__typeof__(*(ptr)))__cmpxchg64_mb((ptr), \ + (unsigned long long)(o), \ + (unsigned long long)(n))) + +#define cmpxchg64_relaxed(ptr, o, n) \ + ((__typeof__(*(ptr)))__cmpxchg64((ptr), \ + (unsigned long long)(o), \ + (unsigned long long)(n))) + +#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n)) #endif /* __LINUX_ARM_ARCH__ >= 6 */ diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index 5ef4d8015a6..c3f11524f10 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -23,6 +23,11 @@ #define CR_RR (1 << 14) /* Round Robin cache replacement */ #define CR_L4 (1 << 15) /* LDR pc can set T bit */ #define CR_DT (1 << 16) +#ifdef CONFIG_MMU +#define CR_HA (1 << 17) /* Hardware management of Access Flag */ +#else +#define CR_BR (1 << 17) /* MPU Background region enable (PMSA) */ +#endif #define CR_IT (1 << 18) #define CR_ST (1 << 19) #define CR_FI (1 << 21) /* Fast interrupt (lower latency mode) */ @@ -37,31 +42,42 @@ #ifndef __ASSEMBLY__ #if __LINUX_ARM_ARCH__ >= 4 -#define vectors_high() (cr_alignment & CR_V) +#define vectors_high() (get_cr() & CR_V) #else #define vectors_high() (0) #endif -extern unsigned long cr_no_alignment; /* defined in entry-armv.S */ +#ifdef CONFIG_CPU_CP15 + extern unsigned long cr_alignment; /* defined in entry-armv.S */ -static inline unsigned int get_cr(void) +static inline unsigned long get_cr(void) { - unsigned int val; + unsigned long val; asm("mrc p15, 0, %0, c1, c0, 0 @ get CR" : "=r" (val) : : "cc"); return val; } -static inline void set_cr(unsigned int val) +static inline void set_cr(unsigned long val) { asm volatile("mcr p15, 0, %0, c1, c0, 0 @ set CR" : : "r" (val) : "cc"); isb(); } -#ifndef CONFIG_SMP -extern void adjust_cr(unsigned long mask, unsigned long set); -#endif +static inline unsigned int get_auxcr(void) +{ + unsigned int val; + asm("mrc p15, 0, %0, c1, c0, 1 @ get AUXCR" : "=r" (val)); + return val; +} + +static inline void set_auxcr(unsigned int val) +{ + asm volatile("mcr p15, 0, %0, c1, c0, 1 @ set AUXCR" + : : "r" (val)); + isb(); +} #define CPACC_FULL(n) (3 << (n * 2)) #define CPACC_SVC(n) (1 << (n * 2)) @@ -82,6 +98,22 @@ static inline void set_copro_access(unsigned int val) isb(); } -#endif +#else /* ifdef CONFIG_CPU_CP15 */ + +/* + * cr_alignment is tightly coupled to cp15 (at least in the minds of the + * developers). Yielding 0 for machines without a cp15 (and making it + * read-only) is fine for most cases and saves quite some #ifdeffery. + */ +#define cr_alignment UL(0) + +static inline unsigned long get_cr(void) +{ + return 0; +} + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + +#endif /* ifndef __ASSEMBLY__ */ #endif diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index a59dcb5ab5f..8c2b7321a47 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -8,8 +8,26 @@ #define CPUID_CACHETYPE 1 #define CPUID_TCM 2 #define CPUID_TLBTYPE 3 +#define CPUID_MPUIR 4 #define CPUID_MPIDR 5 - +#define CPUID_REVIDR 6 + +#ifdef CONFIG_CPU_V7M +#define CPUID_EXT_PFR0 0x40 +#define CPUID_EXT_PFR1 0x44 +#define CPUID_EXT_DFR0 0x48 +#define CPUID_EXT_AFR0 0x4c +#define CPUID_EXT_MMFR0 0x50 +#define CPUID_EXT_MMFR1 0x54 +#define CPUID_EXT_MMFR2 0x58 +#define CPUID_EXT_MMFR3 0x5c +#define CPUID_EXT_ISAR0 0x60 +#define CPUID_EXT_ISAR1 0x64 +#define CPUID_EXT_ISAR2 0x68 +#define CPUID_EXT_ISAR3 0x6c +#define CPUID_EXT_ISAR4 0x70 +#define CPUID_EXT_ISAR5 0x74 +#else #define CPUID_EXT_PFR0 "c1, 0" #define CPUID_EXT_PFR1 "c1, 1" #define CPUID_EXT_DFR0 "c1, 2" @@ -24,6 +42,7 @@ #define CPUID_EXT_ISAR3 "c2, 3" #define CPUID_EXT_ISAR4 "c2, 4" #define CPUID_EXT_ISAR5 "c2, 5" +#endif #define MPIDR_SMP_BITMASK (0x3 << 30) #define MPIDR_SMP_VALUE (0x2 << 30) @@ -32,12 +51,34 @@ #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) #define MPIDR_AFFINITY_LEVEL(mpidr, level) \ ((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK) +#define ARM_CPU_IMP_ARM 0x41 +#define ARM_CPU_IMP_INTEL 0x69 + +#define ARM_CPU_PART_ARM1136 0xB360 +#define ARM_CPU_PART_ARM1156 0xB560 +#define ARM_CPU_PART_ARM1176 0xB760 +#define ARM_CPU_PART_ARM11MPCORE 0xB020 +#define ARM_CPU_PART_CORTEX_A8 0xC080 +#define ARM_CPU_PART_CORTEX_A9 0xC090 +#define ARM_CPU_PART_CORTEX_A5 0xC050 +#define ARM_CPU_PART_CORTEX_A15 0xC0F0 +#define ARM_CPU_PART_CORTEX_A7 0xC070 +#define ARM_CPU_PART_CORTEX_A12 0xC0D0 +#define ARM_CPU_PART_CORTEX_A17 0xC0E0 + +#define ARM_CPU_XSCALE_ARCH_MASK 0xe000 +#define ARM_CPU_XSCALE_ARCH_V1 0x2000 +#define ARM_CPU_XSCALE_ARCH_V2 0x4000 +#define ARM_CPU_XSCALE_ARCH_V3 0x6000 + extern unsigned int processor_id; #ifdef CONFIG_CPU_CP15 @@ -50,21 +91,56 @@ extern unsigned int processor_id; : "cc"); \ __val; \ }) + +/* + * The memory clobber prevents gcc 4.5 from reordering the mrc before + * any is_smp() tests, which can cause undefined instruction aborts on + * ARM1136 r0 due to the missing extended CP15 registers. + */ #define read_cpuid_ext(ext_reg) \ ({ \ unsigned int __val; \ asm("mrc p15, 0, %0, c0, " ext_reg \ : "=r" (__val) \ : \ - : "cc"); \ + : "memory"); \ __val; \ }) -#else -#define read_cpuid(reg) (processor_id) -#define read_cpuid_ext(reg) 0 -#endif + +#elif defined(CONFIG_CPU_V7M) + +#include <asm/io.h> +#include <asm/v7m.h> + +#define read_cpuid(reg) \ + ({ \ + WARN_ON_ONCE(1); \ + 0; \ + }) + +static inline unsigned int __attribute_const__ read_cpuid_ext(unsigned offset) +{ + return readl(BASEADDR_V7M_SCB + offset); +} + +#else /* ifdef CONFIG_CPU_CP15 / elif defined (CONFIG_CPU_V7M) */ /* + * read_cpuid and read_cpuid_ext should only ever be called on machines that + * have cp15 so warn on other usages. + */ +#define read_cpuid(reg) \ + ({ \ + WARN_ON_ONCE(1); \ + 0; \ + }) + +#define read_cpuid_ext(reg) read_cpuid(reg) + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + +#ifdef CONFIG_CPU_CP15 +/* * The CPU ID never changes at run time, so we might as well tell the * compiler that it's constant. Use this function to read the CPU ID * rather than directly reading processor_id or read_cpuid() directly. @@ -74,6 +150,37 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void) return read_cpuid(CPUID_ID); } +#elif defined(CONFIG_CPU_V7M) + +static inline unsigned int __attribute_const__ read_cpuid_id(void) +{ + return readl(BASEADDR_V7M_SCB + V7M_SCB_CPUID); +} + +#else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */ + +static inline unsigned int __attribute_const__ read_cpuid_id(void) +{ + return processor_id; +} + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + +static inline unsigned int __attribute_const__ read_cpuid_implementor(void) +{ + return (read_cpuid_id() & 0xFF000000) >> 24; +} + +static inline unsigned int __attribute_const__ read_cpuid_part_number(void) +{ + return read_cpuid_id() & 0xFFF0; +} + +static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void) +{ + return read_cpuid_part_number() & ARM_CPU_XSCALE_ARCH_MASK; +} + static inline unsigned int __attribute_const__ read_cpuid_cachetype(void) { return read_cpuid(CPUID_CACHETYPE); @@ -115,4 +222,23 @@ static inline int cpu_is_xsc3(void) #define cpu_is_xscale() 1 #endif +/* + * Marvell's PJ4 and PJ4B cores are based on V7 version, + * but require a specical sequence for enabling coprocessors. + * For this reason, we need a way to distinguish them. + */ +#if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) +static inline int cpu_is_pj4(void) +{ + unsigned int id; + + id = read_cpuid_id(); + if ((id & 0xff0fff00) == 0x560f5800) + return 1; + + return 0; +} +#else +#define cpu_is_pj4() 0 +#endif #endif diff --git a/arch/arm/include/asm/cti.h b/arch/arm/include/asm/cti.h index f2e5cad3f30..2381199acb7 100644 --- a/arch/arm/include/asm/cti.h +++ b/arch/arm/include/asm/cti.h @@ -2,6 +2,7 @@ #define __ASMARM_CTI_H #include <asm/io.h> +#include <asm/hardware/coresight.h> /* The registers' definition is from section 3.2 of * Embedded Cross Trigger Revision: r0p0 @@ -35,11 +36,6 @@ #define LOCKACCESS 0xFB0 #define LOCKSTATUS 0xFB4 -/* write this value to LOCKACCESS will unlock the module, and - * other value will lock the module - */ -#define LOCKCODE 0xC5ACCE55 - /** * struct cti - cross trigger interface struct * @base: mapped virtual address for the cti base @@ -146,7 +142,7 @@ static inline void cti_irq_ack(struct cti *cti) */ static inline void cti_unlock(struct cti *cti) { - __raw_writel(LOCKCODE, cti->base + LOCKACCESS); + __raw_writel(CS_LAR_KEY, cti->base + LOCKACCESS); } /** @@ -158,6 +154,6 @@ static inline void cti_unlock(struct cti *cti) */ static inline void cti_lock(struct cti *cti) { - __raw_writel(~LOCKCODE, cti->base + LOCKACCESS); + __raw_writel(~CS_LAR_KEY, cti->base + LOCKACCESS); } #endif diff --git a/arch/arm/include/asm/dcc.h b/arch/arm/include/asm/dcc.h new file mode 100644 index 00000000000..b74899de077 --- /dev/null +++ b/arch/arm/include/asm/dcc.h @@ -0,0 +1,41 @@ +/* Copyright (c) 2010, 2014 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <asm/barrier.h> + +static inline u32 __dcc_getstatus(void) +{ + u32 __ret; + asm volatile("mrc p14, 0, %0, c0, c1, 0 @ read comms ctrl reg" + : "=r" (__ret) : : "cc"); + + return __ret; +} + +static inline char __dcc_getchar(void) +{ + char __c; + + asm volatile("mrc p14, 0, %0, c0, c5, 0 @ read comms data reg" + : "=r" (__c)); + isb(); + + return __c; +} + +static inline void __dcc_putchar(char c) +{ + asm volatile("mcr p14, 0, %0, c0, c5, 0 @ write a char" + : /* no output register */ + : "r" (c)); + isb(); +} diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h index ab98fdd083b..dff714d886d 100644 --- a/arch/arm/include/asm/delay.h +++ b/arch/arm/include/asm/delay.h @@ -24,6 +24,7 @@ extern struct arm_delay_ops { void (*delay)(unsigned long); void (*const_udelay)(unsigned long); void (*udelay)(unsigned long); + unsigned long ticks_per_jiffy; } arm_delay_ops; #define __delay(n) arm_delay_ops.delay(n) diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index b69c0d3285f..dc662fca923 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -27,4 +27,10 @@ struct pdev_archdata { #endif }; +#ifdef CONFIG_ARM_DMA_USE_IOMMU +#define to_dma_iommu_mapping(dev) ((dev)->archdata.mapping) +#else +#define to_dma_iommu_mapping(dev) NULL +#endif + #endif diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h index fe92ccf1d0b..662c7bd0610 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 @@ -156,7 +156,7 @@ /* Select the best insn combination to perform the */ \ /* actual __m * __n / (__p << 64) operation. */ \ if (!__c) { \ - asm ( "umull %Q0, %R0, %1, %Q2\n\t" \ + asm ( "umull %Q0, %R0, %Q1, %Q2\n\t" \ "mov %Q0, #0" \ : "=&r" (__res) \ : "r" (__m), "r" (__n) \ diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h index 3ed37b4d93d..4f8e9e5514b 100644 --- a/arch/arm/include/asm/dma-contiguous.h +++ b/arch/arm/include/asm/dma-contiguous.h @@ -2,10 +2,9 @@ #define ASMARM_DMA_CONTIGUOUS_H #ifdef __KERNEL__ -#ifdef CONFIG_CMA +#ifdef CONFIG_DMA_CMA #include <linux/types.h> -#include <asm-generic/dma-contiguous.h> void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size); diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h index 799b09409fa..8e3fcb924db 100644 --- a/arch/arm/include/asm/dma-iommu.h +++ b/arch/arm/include/asm/dma-iommu.h @@ -7,14 +7,17 @@ #include <linux/scatterlist.h> #include <linux/dma-debug.h> #include <linux/kmemcheck.h> +#include <linux/kref.h> struct dma_iommu_mapping { /* iommu specific data */ struct iommu_domain *domain; - void *bitmap; - size_t bits; - unsigned int order; + unsigned long **bitmaps; /* array of bitmaps */ + unsigned int nr_bitmaps; /* nr of elements in array */ + unsigned int extensions; + size_t bitmap_size; /* size of a single bitmap */ + size_t bits; /* per bitmap */ dma_addr_t base; spinlock_t lock; @@ -22,13 +25,13 @@ struct dma_iommu_mapping { }; struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size, - int order); +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size); void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping); int arm_iommu_attach_device(struct device *dev, struct dma_iommu_mapping *mapping); +void arm_iommu_detach_device(struct device *dev); #endif /* __KERNEL__ */ #endif diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 5b579b95150..c45b61a4b4a 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -11,17 +11,28 @@ #include <asm-generic/dma-coherent.h> #include <asm/memory.h> +#include <xen/xen.h> +#include <asm/xen/hypervisor.h> + #define DMA_ERROR_CODE (~0) extern struct dma_map_ops arm_dma_ops; extern struct dma_map_ops arm_coherent_dma_ops; -static inline struct dma_map_ops *get_dma_ops(struct device *dev) +static inline struct dma_map_ops *__generic_dma_ops(struct device *dev) { if (dev && dev->archdata.dma_ops) return dev->archdata.dma_ops; return &arm_dma_ops; } +static inline struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (xen_initial_domain()) + return xen_dma_ops; + else + return __generic_dma_ops(dev); +} + static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) { BUG_ON(!dev); @@ -47,23 +58,40 @@ static inline int dma_set_mask(struct device *dev, u64 mask) #ifndef __arch_pfn_to_dma static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn) { + if (dev) + pfn -= dev->dma_pfn_offset; return (dma_addr_t)__pfn_to_bus(pfn); } static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr) { - return __bus_to_pfn(addr); + unsigned long pfn = __bus_to_pfn(addr); + + if (dev) + pfn += dev->dma_pfn_offset; + + return pfn; } static inline void *dma_to_virt(struct device *dev, dma_addr_t addr) { + if (dev) { + unsigned long pfn = dma_to_pfn(dev, addr); + + return phys_to_virt(__pfn_to_phys(pfn)); + } + return (void *)__bus_to_virt((unsigned long)addr); } static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) { + if (dev) + return pfn_to_dma(dev, virt_to_pfn(addr)); + return (dma_addr_t)__virt_to_bus((unsigned long)(addr)); } + #else static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn) { @@ -86,6 +114,53 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) } #endif +/* The ARM override for dma_max_pfn() */ +static inline unsigned long dma_max_pfn(struct device *dev) +{ + return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask); +} +#define dma_max_pfn(dev) dma_max_pfn(dev) + +static inline int set_arch_dma_coherent_ops(struct device *dev) +{ + set_dma_ops(dev, &arm_coherent_dma_ops); + return 0; +} +#define set_arch_dma_coherent_ops(dev) set_arch_dma_coherent_ops(dev) + +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + unsigned int offset = paddr & ~PAGE_MASK; + return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset; +} + +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) +{ + unsigned int offset = dev_addr & ~PAGE_MASK; + return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset; +} + +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +{ + u64 limit, mask; + + if (!dev->dma_mask) + return 0; + + mask = *dev->dma_mask; + + limit = (mask + 1) & ~mask; + if (limit && size > limit) + return 0; + + if ((addr | (addr + size - 1)) & ~mask) + return 0; + + return 1; +} + +static inline void dma_mark_clean(void *addr, size_t size) { } + /* * DMA errors are defined by all-bits-set in the DMA address. */ diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h index 5694a0d6576..99084431d6a 100644 --- a/arch/arm/include/asm/dma.h +++ b/arch/arm/include/asm/dma.h @@ -8,8 +8,8 @@ #define MAX_DMA_ADDRESS 0xffffffffUL #else #define MAX_DMA_ADDRESS ({ \ - extern unsigned long arm_dma_zone_size; \ - arm_dma_zone_size ? \ + extern phys_addr_t arm_dma_zone_size; \ + arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \ (PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; }) #endif @@ -105,7 +105,7 @@ extern void set_dma_sg(unsigned int chan, struct scatterlist *sg, int nr_sg); */ extern void __set_dma_addr(unsigned int chan, void *addr); #define set_dma_addr(chan, addr) \ - __set_dma_addr(chan, bus_to_virt(addr)) + __set_dma_addr(chan, (void *)__bus_to_virt(addr)) /* Set the DMA byte count for this channel * diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index 38050b1c480..f4b46d39b9c 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -19,8 +19,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG]; typedef struct user_fp elf_fpregset_t; -#define EM_ARM 40 - #define EF_ARM_EABI_MASK 0xff000000 #define EF_ARM_EABI_UNKNOWN 0x00000000 #define EF_ARM_EABI_VER1 0x01000000 @@ -130,4 +128,10 @@ struct mm_struct; extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define arch_randomize_brk arch_randomize_brk +#ifdef CONFIG_MMU +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 +struct linux_binprm; +int arch_setup_additional_pages(struct linux_binprm *, int); +#endif + #endif diff --git a/arch/arm/include/asm/firmware.h b/arch/arm/include/asm/firmware.h new file mode 100644 index 00000000000..2c9f10df756 --- /dev/null +++ b/arch/arm/include/asm/firmware.h @@ -0,0 +1,70 @@ +/* + * Copyright (C) 2012 Samsung Electronics. + * Kyungmin Park <kyungmin.park@samsung.com> + * Tomasz Figa <t.figa@samsung.com> + * + * 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. + */ + +#ifndef __ASM_ARM_FIRMWARE_H +#define __ASM_ARM_FIRMWARE_H + +#include <linux/bug.h> + +/* + * struct firmware_ops + * + * A structure to specify available firmware operations. + * + * A filled up structure can be registered with register_firmware_ops(). + */ +struct firmware_ops { + /* + * Inform the firmware we intend to enter CPU idle mode + */ + int (*prepare_idle)(void); + /* + * Enters CPU idle mode + */ + int (*do_idle)(void); + /* + * Sets boot address of specified physical CPU + */ + int (*set_cpu_boot_addr)(int cpu, unsigned long boot_addr); + /* + * Boots specified physical CPU + */ + int (*cpu_boot)(int cpu); + /* + * Initializes L2 cache + */ + int (*l2x0_init)(void); +}; + +/* Global pointer for current firmware_ops structure, can't be NULL. */ +extern const struct firmware_ops *firmware_ops; + +/* + * call_firmware_op(op, ...) + * + * Checks if firmware operation is present and calls it, + * otherwise returns -ENOSYS + */ +#define call_firmware_op(op, ...) \ + ((firmware_ops->op) ? firmware_ops->op(__VA_ARGS__) : (-ENOSYS)) + +/* + * register_firmware_ops(ops) + * + * A function to register platform firmware_ops struct. + */ +static inline void register_firmware_ops(const struct firmware_ops *ops) +{ + BUG_ON(!ops); + + firmware_ops = ops; +} + +#endif diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index bbae919bceb..74124b0d0d7 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -1,24 +1,11 @@ #ifndef _ASM_FIXMAP_H #define _ASM_FIXMAP_H -/* - * Nothing too fancy for now. - * - * On ARM we already have well known fixed virtual addresses imposed by - * the architecture such as the vector page which is located at 0xffff0000, - * therefore a second level page table is already allocated covering - * 0xfff00000 upwards. - * - * The cache flushing code in proc-xscale.S uses the virtual area between - * 0xfffe0000 and 0xfffeffff. - */ - -#define FIXADDR_START 0xfff00000UL -#define FIXADDR_TOP 0xfffe0000UL +#define FIXADDR_START 0xffc00000UL +#define FIXADDR_TOP 0xffe00000UL #define FIXADDR_SIZE (FIXADDR_TOP - FIXADDR_START) -#define FIX_KMAP_BEGIN 0 -#define FIX_KMAP_END (FIXADDR_SIZE >> PAGE_SHIFT) +#define FIX_KMAP_NR_PTES (FIXADDR_SIZE >> PAGE_SHIFT) #define __fix_to_virt(x) (FIXADDR_START + ((x) << PAGE_SHIFT)) #define __virt_to_fix(x) (((x) - FIXADDR_START) >> PAGE_SHIFT) @@ -27,7 +14,7 @@ extern void __this_fixmap_does_not_exist(void); static inline unsigned long fix_to_virt(const unsigned int idx) { - if (idx >= FIX_KMAP_END) + if (idx >= FIX_KMAP_NR_PTES) __this_fixmap_does_not_exist(); return __fix_to_virt(idx); } diff --git a/arch/arm/include/asm/floppy.h b/arch/arm/include/asm/floppy.h index c9f03eccc9d..f4882553fbb 100644 --- a/arch/arm/include/asm/floppy.h +++ b/arch/arm/include/asm/floppy.h @@ -25,7 +25,7 @@ #define fd_inb(port) inb((port)) #define fd_request_irq() request_irq(IRQ_FLOPPYDISK,floppy_interrupt,\ - IRQF_DISABLED,"floppy",NULL) + 0,"floppy",NULL) #define fd_free_irq() free_irq(IRQ_FLOPPYDISK,NULL) #define fd_disable_irq() disable_irq(IRQ_FLOPPYDISK) #define fd_enable_irq() enable_irq(IRQ_FLOPPYDISK) diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h index f89515adac6..39eb16b0066 100644 --- a/arch/arm/include/asm/ftrace.h +++ b/arch/arm/include/asm/ftrace.h @@ -52,15 +52,7 @@ extern inline void *return_address(unsigned int level) #endif -#define HAVE_ARCH_CALLER_ADDR - -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#define CALLER_ADDR1 ((unsigned long)return_address(1)) -#define CALLER_ADDR2 ((unsigned long)return_address(2)) -#define CALLER_ADDR3 ((unsigned long)return_address(3)) -#define CALLER_ADDR4 ((unsigned long)return_address(4)) -#define CALLER_ADDR5 ((unsigned long)return_address(5)) -#define CALLER_ADDR6 ((unsigned long)return_address(6)) +#define ftrace_return_address(n) return_address(n) #endif /* ifndef __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index e42cf597f6e..53e69dae796 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -3,11 +3,6 @@ #ifdef __KERNEL__ -#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP) -/* ARM doesn't provide unprivileged exclusive memory accessors */ -#include <asm-generic/futex.h> -#else - #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/errno.h> @@ -28,6 +23,7 @@ #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ smp_mb(); \ + prefetchw(uaddr); \ __asm__ __volatile__( \ "1: ldrex %1, [%3]\n" \ " " insn "\n" \ @@ -51,6 +47,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; smp_mb(); + /* Prefetching cannot fault */ + prefetchw(uaddr); __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" "1: ldrex %1, [%4]\n" " teq %1, %2\n" @@ -164,6 +162,5 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) return ret; } -#endif /* !(CPU_USE_DOMAINS && SMP) */ #endif /* __KERNEL__ */ #endif /* _ASM_ARM_FUTEX_H */ diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index cca9f15704e..a3c24cd5b7c 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -19,14 +19,6 @@ #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 @@ -125,10 +117,37 @@ # endif #endif +#if defined(CONFIG_CPU_V7M) +# ifdef _CACHE +# define MULTI_CACHE 1 +# else +# define _CACHE nop +# endif +#endif + #if !defined(_CACHE) && !defined(MULTI_CACHE) #error Unknown cache maintenance model #endif +#ifndef __ASSEMBLER__ +static inline void nop_flush_icache_all(void) { } +static inline void nop_flush_kern_cache_all(void) { } +static inline void nop_flush_kern_cache_louis(void) { } +static inline void nop_flush_user_cache_all(void) { } +static inline void nop_flush_user_cache_range(unsigned long a, + unsigned long b, unsigned int c) { } + +static inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { } +static inline int nop_coherent_user_range(unsigned long a, + unsigned long b) { return 0; } +static inline void nop_flush_kern_dcache_area(void *a, size_t s) { } + +static inline void nop_dma_flush_range(const void *a, const void *b) { } + +static inline void nop_dma_map_area(const void *s, size_t l, int f) { } +static inline void nop_dma_unmap_area(const void *s, size_t l, int f) { } +#endif + #ifndef MULTI_CACHE #define __cpuc_flush_icache_all __glue(_CACHE,_flush_icache_all) #define __cpuc_flush_kern_all __glue(_CACHE,_flush_kern_cache_all) diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h index 8cacbcda76d..04e18b65665 100644 --- a/arch/arm/include/asm/glue-df.h +++ b/arch/arm/include/asm/glue-df.h @@ -18,12 +18,12 @@ * ================ * * We have the following to choose from: - * arm6 - ARM6 style * arm7 - ARM7 style * v4_early - ARMv4 without Thumb early abort handler * v4t_late - ARMv4 with Thumb late abort handler * v4t_early - ARMv4 with Thumb early abort handler - * v5tej_early - ARMv5 with Thumb and Java early abort handler + * v5t_early - ARMv5 with Thumb early abort handler + * v5tj_early - ARMv5 with Thumb and Java early abort handler * xscale - ARMv5 with Thumb with Xscale extensions * v6_early - ARMv6 generic early abort handler * v7_early - ARMv7 generic early abort handler @@ -31,11 +31,11 @@ #undef CPU_DABORT_HANDLER #undef MULTI_DABORT -#if defined(CONFIG_CPU_ARM710) +#ifdef CONFIG_CPU_ABRT_EV4 # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER cpu_arm7_data_abort +# define CPU_DABORT_HANDLER v4_early_abort # endif #endif @@ -47,19 +47,19 @@ # endif #endif -#ifdef CONFIG_CPU_ABRT_EV4 +#ifdef CONFIG_CPU_ABRT_EV4T # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v4_early_abort +# define CPU_DABORT_HANDLER v4t_early_abort # endif #endif -#ifdef CONFIG_CPU_ABRT_EV4T +#ifdef CONFIG_CPU_ABRT_EV5T # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v4t_early_abort +# define CPU_DABORT_HANDLER v5t_early_abort # endif #endif @@ -71,27 +71,27 @@ # endif #endif -#ifdef CONFIG_CPU_ABRT_EV5T +#ifdef CONFIG_CPU_ABRT_EV6 # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v5t_early_abort +# define CPU_DABORT_HANDLER v6_early_abort # endif #endif -#ifdef CONFIG_CPU_ABRT_EV6 +#ifdef CONFIG_CPU_ABRT_EV7 # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v6_early_abort +# define CPU_DABORT_HANDLER v7_early_abort # endif #endif -#ifdef CONFIG_CPU_ABRT_EV7 +#ifdef CONFIG_CPU_ABRT_NOMMU # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v7_early_abort +# define CPU_DABORT_HANDLER nommu_early_abort # endif #endif diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h index ac1dd54724b..74a8b84f3cb 100644 --- a/arch/arm/include/asm/glue-proc.h +++ b/arch/arm/include/asm/glue-proc.h @@ -230,6 +230,24 @@ # endif #endif +#ifdef CONFIG_CPU_V7M +# ifdef CPU_NAME +# undef MULTI_CPU +# define MULTI_CPU +# else +# define CPU_NAME cpu_v7m +# 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/hardirq.h b/arch/arm/include/asm/hardirq.h index 2740c2a2df6..fe3ea776dc3 100644 --- a/arch/arm/include/asm/hardirq.h +++ b/arch/arm/include/asm/hardirq.h @@ -5,7 +5,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 6 +#define NR_IPI 8 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm/include/asm/hardware/cache-feroceon-l2.h b/arch/arm/include/asm/hardware/cache-feroceon-l2.h new file mode 100644 index 00000000000..12e1588dc4f --- /dev/null +++ b/arch/arm/include/asm/hardware/cache-feroceon-l2.h @@ -0,0 +1,13 @@ +/* + * arch/arm/include/asm/hardware/cache-feroceon-l2.h + * + * Copyright (C) 2008 Marvell Semiconductor + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +extern void __init feroceon_l2_init(int l2_wt_override); +extern int __init feroceon_of_init(void); + diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 3b2c40b5bfa..3a5ec1c2565 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -26,8 +26,8 @@ #define L2X0_CACHE_TYPE 0x004 #define L2X0_CTRL 0x100 #define L2X0_AUX_CTRL 0x104 -#define L2X0_TAG_LATENCY_CTRL 0x108 -#define L2X0_DATA_LATENCY_CTRL 0x10C +#define L310_TAG_LATENCY_CTRL 0x108 +#define L310_DATA_LATENCY_CTRL 0x10C #define L2X0_EVENT_CNT_CTRL 0x200 #define L2X0_EVENT_CNT1_CFG 0x204 #define L2X0_EVENT_CNT0_CFG 0x208 @@ -54,53 +54,93 @@ #define L2X0_LOCKDOWN_WAY_D_BASE 0x900 #define L2X0_LOCKDOWN_WAY_I_BASE 0x904 #define L2X0_LOCKDOWN_STRIDE 0x08 -#define L2X0_ADDR_FILTER_START 0xC00 -#define L2X0_ADDR_FILTER_END 0xC04 +#define L310_ADDR_FILTER_START 0xC00 +#define L310_ADDR_FILTER_END 0xC04 #define L2X0_TEST_OPERATION 0xF00 #define L2X0_LINE_DATA 0xF10 #define L2X0_LINE_TAG 0xF30 #define L2X0_DEBUG_CTRL 0xF40 -#define L2X0_PREFETCH_CTRL 0xF60 -#define L2X0_POWER_CTRL 0xF80 -#define L2X0_DYNAMIC_CLK_GATING_EN (1 << 1) -#define L2X0_STNDBY_MODE_EN (1 << 0) +#define L310_PREFETCH_CTRL 0xF60 +#define L310_POWER_CTRL 0xF80 +#define L310_DYNAMIC_CLK_GATING_EN (1 << 1) +#define L310_STNDBY_MODE_EN (1 << 0) /* Registers shifts and masks */ #define L2X0_CACHE_ID_PART_MASK (0xf << 6) #define L2X0_CACHE_ID_PART_L210 (1 << 6) +#define L2X0_CACHE_ID_PART_L220 (2 << 6) #define L2X0_CACHE_ID_PART_L310 (3 << 6) #define L2X0_CACHE_ID_RTL_MASK 0x3f -#define L2X0_CACHE_ID_RTL_R0P0 0x0 -#define L2X0_CACHE_ID_RTL_R1P0 0x2 -#define L2X0_CACHE_ID_RTL_R2P0 0x4 -#define L2X0_CACHE_ID_RTL_R3P0 0x5 -#define L2X0_CACHE_ID_RTL_R3P1 0x6 -#define L2X0_CACHE_ID_RTL_R3P2 0x8 +#define L210_CACHE_ID_RTL_R0P2_02 0x00 +#define L210_CACHE_ID_RTL_R0P1 0x01 +#define L210_CACHE_ID_RTL_R0P2_01 0x02 +#define L210_CACHE_ID_RTL_R0P3 0x03 +#define L210_CACHE_ID_RTL_R0P4 0x0b +#define L210_CACHE_ID_RTL_R0P5 0x0f +#define L220_CACHE_ID_RTL_R1P7_01REL0 0x06 +#define L310_CACHE_ID_RTL_R0P0 0x00 +#define L310_CACHE_ID_RTL_R1P0 0x02 +#define L310_CACHE_ID_RTL_R2P0 0x04 +#define L310_CACHE_ID_RTL_R3P0 0x05 +#define L310_CACHE_ID_RTL_R3P1 0x06 +#define L310_CACHE_ID_RTL_R3P1_50REL0 0x07 +#define L310_CACHE_ID_RTL_R3P2 0x08 +#define L310_CACHE_ID_RTL_R3P3 0x09 -#define L2X0_AUX_CTRL_MASK 0xc0000fff +/* L2C auxiliary control register - bits common to L2C-210/220/310 */ +#define L2C_AUX_CTRL_WAY_SIZE_SHIFT 17 +#define L2C_AUX_CTRL_WAY_SIZE_MASK (7 << 17) +#define L2C_AUX_CTRL_WAY_SIZE(n) ((n) << 17) +#define L2C_AUX_CTRL_EVTMON_ENABLE BIT(20) +#define L2C_AUX_CTRL_PARITY_ENABLE BIT(21) +#define L2C_AUX_CTRL_SHARED_OVERRIDE BIT(22) +/* L2C-210/220 common bits */ #define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT 0 -#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK 0x7 +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK (7 << 0) #define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT 3 -#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK (0x7 << 3) +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK (7 << 3) #define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT 6 -#define L2X0_AUX_CTRL_TAG_LATENCY_MASK (0x7 << 6) +#define L2X0_AUX_CTRL_TAG_LATENCY_MASK (7 << 6) #define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT 9 -#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK (0x7 << 9) -#define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT 16 -#define L2X0_AUX_CTRL_WAY_SIZE_SHIFT 17 -#define L2X0_AUX_CTRL_WAY_SIZE_MASK (0x7 << 17) -#define L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT 22 -#define L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT 26 -#define L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT 27 -#define L2X0_AUX_CTRL_DATA_PREFETCH_SHIFT 28 -#define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT 29 -#define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT 30 +#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK (7 << 9) +#define L2X0_AUX_CTRL_ASSOC_SHIFT 13 +#define L2X0_AUX_CTRL_ASSOC_MASK (15 << 13) +/* L2C-210 specific bits */ +#define L210_AUX_CTRL_WRAP_DISABLE BIT(12) +#define L210_AUX_CTRL_WA_OVERRIDE BIT(23) +#define L210_AUX_CTRL_EXCLUSIVE_ABORT BIT(24) +/* L2C-220 specific bits */ +#define L220_AUX_CTRL_EXCLUSIVE_CACHE BIT(12) +#define L220_AUX_CTRL_FWA_SHIFT 23 +#define L220_AUX_CTRL_FWA_MASK (3 << 23) +#define L220_AUX_CTRL_NS_LOCKDOWN BIT(26) +#define L220_AUX_CTRL_NS_INT_CTRL BIT(27) +/* L2C-310 specific bits */ +#define L310_AUX_CTRL_FULL_LINE_ZERO BIT(0) /* R2P0+ */ +#define L310_AUX_CTRL_HIGHPRIO_SO_DEV BIT(10) /* R2P0+ */ +#define L310_AUX_CTRL_STORE_LIMITATION BIT(11) /* R2P0+ */ +#define L310_AUX_CTRL_EXCLUSIVE_CACHE BIT(12) +#define L310_AUX_CTRL_ASSOCIATIVITY_16 BIT(16) +#define L310_AUX_CTRL_CACHE_REPLACE_RR BIT(25) /* R2P0+ */ +#define L310_AUX_CTRL_NS_LOCKDOWN BIT(26) +#define L310_AUX_CTRL_NS_INT_CTRL BIT(27) +#define L310_AUX_CTRL_DATA_PREFETCH BIT(28) +#define L310_AUX_CTRL_INSTR_PREFETCH BIT(29) +#define L310_AUX_CTRL_EARLY_BRESP BIT(30) /* R2P0+ */ -#define L2X0_LATENCY_CTRL_SETUP_SHIFT 0 -#define L2X0_LATENCY_CTRL_RD_SHIFT 4 -#define L2X0_LATENCY_CTRL_WR_SHIFT 8 +#define L310_LATENCY_CTRL_SETUP(n) ((n) << 0) +#define L310_LATENCY_CTRL_RD(n) ((n) << 4) +#define L310_LATENCY_CTRL_WR(n) ((n) << 8) -#define L2X0_ADDR_FILTER_EN 1 +#define L310_ADDR_FILTER_EN 1 + +#define L310_PREFETCH_CTRL_OFFSET_MASK 0x1f +#define L310_PREFETCH_CTRL_DBL_LINEFILL_INCR BIT(23) +#define L310_PREFETCH_CTRL_PREFETCH_DROP BIT(24) +#define L310_PREFETCH_CTRL_DBL_LINEFILL_WRAP BIT(27) +#define L310_PREFETCH_CTRL_DATA_PREFETCH BIT(28) +#define L310_PREFETCH_CTRL_INSTR_PREFETCH BIT(29) +#define L310_PREFETCH_CTRL_DBL_LINEFILL BIT(30) #define L2X0_CTRL_EN 1 @@ -131,6 +171,7 @@ struct l2x0_regs { unsigned long prefetch_ctrl; unsigned long pwr_ctrl; unsigned long ctrl; + unsigned long aux2_ctrl; }; extern struct l2x0_regs l2x0_saved_regs; diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h index 7ecd793b8f5..ad774f37c47 100644 --- a/arch/arm/include/asm/hardware/coresight.h +++ b/arch/arm/include/asm/hardware/coresight.h @@ -24,8 +24,8 @@ #define TRACER_TIMEOUT 10000 #define etm_writel(t, v, x) \ - (__raw_writel((v), (t)->etm_regs + (x))) -#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x))) + (writel_relaxed((v), (t)->etm_regs + (x))) +#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x))) /* CoreSight Management Registers */ #define CSMR_LOCKACCESS 0xfb0 @@ -36,7 +36,7 @@ /* CoreSight Component Registers */ #define CSCR_CLASS 0xff4 -#define UNLOCK_MAGIC 0xc5acce55 +#define CS_LAR_KEY 0xc5acce55 /* ETM control register, "ETM Architecture", 3.3.1 */ #define ETMR_CTRL 0 @@ -142,16 +142,16 @@ #define ETBFF_TRIGFL BIT(10) #define etb_writel(t, v, x) \ - (__raw_writel((v), (t)->etb_regs + (x))) -#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x))) + (writel_relaxed((v), (t)->etb_regs + (x))) +#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x))) #define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0) #define etm_unlock(t) \ - do { etm_writel((t), UNLOCK_MAGIC, CSMR_LOCKACCESS); } while (0) + do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0) #define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0) #define etb_unlock(t) \ - do { etb_writel((t), UNLOCK_MAGIC, CSMR_LOCKACCESS); } while (0) + do { etb_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0) #endif /* __ASM_HARDWARE_CORESIGHT_H */ diff --git a/arch/arm/include/asm/hardware/debug-8250.S b/arch/arm/include/asm/hardware/debug-8250.S deleted file mode 100644 index 22c689255e6..00000000000 --- a/arch/arm/include/asm/hardware/debug-8250.S +++ /dev/null @@ -1,29 +0,0 @@ -/* - * arch/arm/include/asm/hardware/debug-8250.S - * - * Copyright (C) 1994-1999 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/serial_reg.h> - - .macro senduart,rd,rx - strb \rd, [\rx, #UART_TX << UART_SHIFT] - .endm - - .macro busyuart,rd,rx -1002: ldrb \rd, [\rx, #UART_LSR << UART_SHIFT] - and \rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE - teq \rd, #UART_LSR_TEMT | UART_LSR_THRE - bne 1002b - .endm - - .macro waituart,rd,rx -#ifdef FLOW_CONTROL -1001: ldrb \rd, [\rx, #UART_MSR << UART_SHIFT] - tst \rd, #UART_MSR_CTS - beq 1001b -#endif - .endm diff --git a/arch/arm/include/asm/hardware/debug-pl01x.S b/arch/arm/include/asm/hardware/debug-pl01x.S deleted file mode 100644 index f9fd083eff6..00000000000 --- a/arch/arm/include/asm/hardware/debug-pl01x.S +++ /dev/null @@ -1,29 +0,0 @@ -/* arch/arm/include/asm/hardware/debug-pl01x.S - * - * Debugging macro include header - * - * Copyright (C) 1994-1999 Russell King - * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks - * - * 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/amba/serial.h> - - .macro senduart,rd,rx - strb \rd, [\rx, #UART01x_DR] - .endm - - .macro waituart,rd,rx -1001: ldr \rd, [\rx, #UART01x_FR] - tst \rd, #UART01x_FR_TXFF - bne 1001b - .endm - - .macro busyuart,rd,rx -1001: ldr \rd, [\rx, #UART01x_FR] - tst \rd, #UART01x_FR_BUSY - bne 1001b - .endm diff --git a/arch/arm/include/asm/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h deleted file mode 100644 index 4b1ce6cd477..00000000000 --- a/arch/arm/include/asm/hardware/gic.h +++ /dev/null @@ -1,57 +0,0 @@ -/* - * arch/arm/include/asm/hardware/gic.h - * - * Copyright (C) 2002 ARM Limited, All Rights Reserved. - * - * 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. - */ -#ifndef __ASM_ARM_HARDWARE_GIC_H -#define __ASM_ARM_HARDWARE_GIC_H - -#include <linux/compiler.h> - -#define GIC_CPU_CTRL 0x00 -#define GIC_CPU_PRIMASK 0x04 -#define GIC_CPU_BINPOINT 0x08 -#define GIC_CPU_INTACK 0x0c -#define GIC_CPU_EOI 0x10 -#define GIC_CPU_RUNNINGPRI 0x14 -#define GIC_CPU_HIGHPRI 0x18 - -#define GIC_DIST_CTRL 0x000 -#define GIC_DIST_CTR 0x004 -#define GIC_DIST_ENABLE_SET 0x100 -#define GIC_DIST_ENABLE_CLEAR 0x180 -#define GIC_DIST_PENDING_SET 0x200 -#define GIC_DIST_PENDING_CLEAR 0x280 -#define GIC_DIST_ACTIVE_BIT 0x300 -#define GIC_DIST_PRI 0x400 -#define GIC_DIST_TARGET 0x800 -#define GIC_DIST_CONFIG 0xc00 -#define GIC_DIST_SOFTINT 0xf00 - -#ifndef __ASSEMBLY__ -#include <linux/irqdomain.h> -struct device_node; - -extern struct irq_chip gic_arch_extn; - -void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *, - u32 offset, struct device_node *); -int gic_of_init(struct device_node *node, struct device_node *parent); -void gic_secondary_init(unsigned int); -void gic_handle_irq(struct pt_regs *regs); -void gic_cascade_irq(unsigned int gic_nr, unsigned int irq); -void gic_raise_softirq(const struct cpumask *mask, unsigned int irq); - -static inline void gic_init(unsigned int nr, int start, - void __iomem *dist , void __iomem *cpu) -{ - gic_init_bases(nr, start, dist, cpu, 0, NULL); -} - -#endif - -#endif diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h index 9b28f1243bd..240b29ef17d 100644 --- a/arch/arm/include/asm/hardware/iop3xx-adma.h +++ b/arch/arm/include/asm/hardware/iop3xx-adma.h @@ -393,36 +393,6 @@ static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt, return slot_cnt; } -static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc) -{ - return 0; -} - -static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc, - struct iop_adma_chan *chan) -{ - union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, }; - - switch (chan->device->id) { - case DMA0_ID: - case DMA1_ID: - return hw_desc.dma->dest_addr; - case AAU_ID: - return hw_desc.aau->dest_addr; - default: - BUG(); - } - return 0; -} - - -static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc, - struct iop_adma_chan *chan) -{ - BUG(); - return 0; -} - static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc, struct iop_adma_chan *chan) { diff --git a/arch/arm/include/asm/hardware/iop3xx-gpio.h b/arch/arm/include/asm/hardware/iop3xx-gpio.h deleted file mode 100644 index 9eda7dc92ad..00000000000 --- a/arch/arm/include/asm/hardware/iop3xx-gpio.h +++ /dev/null @@ -1,75 +0,0 @@ -/* - * arch/arm/include/asm/hardware/iop3xx-gpio.h - * - * IOP3xx GPIO wrappers - * - * Copyright (c) 2008 Arnaud Patard <arnaud.patard@rtp-net.org> - * Based on IXP4XX gpio.h file - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - */ - -#ifndef __ASM_ARM_HARDWARE_IOP3XX_GPIO_H -#define __ASM_ARM_HARDWARE_IOP3XX_GPIO_H - -#include <mach/hardware.h> -#include <asm-generic/gpio.h> - -#define __ARM_GPIOLIB_COMPLEX - -#define IOP3XX_N_GPIOS 8 - -static inline int gpio_get_value(unsigned gpio) -{ - if (gpio > IOP3XX_N_GPIOS) - return __gpio_get_value(gpio); - - return gpio_line_get(gpio); -} - -static inline void gpio_set_value(unsigned gpio, int value) -{ - if (gpio > IOP3XX_N_GPIOS) { - __gpio_set_value(gpio, value); - return; - } - gpio_line_set(gpio, value); -} - -static inline int gpio_cansleep(unsigned gpio) -{ - if (gpio < IOP3XX_N_GPIOS) - return 0; - else - return __gpio_cansleep(gpio); -} - -/* - * The GPIOs are not generating any interrupt - * Note : manuals are not clear about this - */ -static inline int gpio_to_irq(int gpio) -{ - return -EINVAL; -} - -static inline int irq_to_gpio(int gpio) -{ - return -EINVAL; -} - -#endif - diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h index 02fe2fbe247..2594a95ff19 100644 --- a/arch/arm/include/asm/hardware/iop3xx.h +++ b/arch/arm/include/asm/hardware/iop3xx.h @@ -18,16 +18,9 @@ /* * IOP3XX GPIO handling */ -#define GPIO_IN 0 -#define GPIO_OUT 1 -#define GPIO_LOW 0 -#define GPIO_HIGH 1 #define IOP3XX_GPIO_LINE(x) (x) #ifndef __ASSEMBLY__ -extern void gpio_line_config(int line, int direction); -extern int gpio_line_get(int line); -extern void gpio_line_set(int line, int value); extern int init_atu; extern int iop3xx_get_init_atu(void); #endif @@ -37,7 +30,7 @@ extern int iop3xx_get_init_atu(void); * IOP3XX processor registers */ #define IOP3XX_PERIPHERAL_PHYS_BASE 0xffffe000 -#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfeffe000 +#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfedfe000 #define IOP3XX_PERIPHERAL_SIZE 0x00002000 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\ IOP3XX_PERIPHERAL_SIZE - 1) @@ -168,11 +161,6 @@ extern int iop3xx_get_init_atu(void); /* PERCR0 DOESN'T EXIST - index from 1! */ #define IOP3XX_PERCR0 (volatile u32 *)IOP3XX_REG_ADDR(0x0710) -/* General Purpose I/O */ -#define IOP3XX_GPOE (volatile u32 *)IOP3XX_GPIO_REG(0x0000) -#define IOP3XX_GPID (volatile u32 *)IOP3XX_GPIO_REG(0x0004) -#define IOP3XX_GPOD (volatile u32 *)IOP3XX_GPIO_REG(0x0008) - /* Timers */ #define IOP3XX_TU_TMR0 (volatile u32 *)IOP3XX_TIMER_REG(0x0000) #define IOP3XX_TU_TMR1 (volatile u32 *)IOP3XX_TIMER_REG(0x0004) @@ -223,11 +211,12 @@ extern int iop3xx_get_init_atu(void); #ifndef __ASSEMBLY__ #include <linux/types.h> +#include <linux/reboot.h> void iop3xx_map_io(void); void iop_init_cp6_handler(void); void iop_init_time(unsigned long tickrate); -void iop3xx_restart(char, const char *); +void iop3xx_restart(enum reboot_mode, const char *); static inline u32 read_tmr0(void) { diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h index 122f86d8c99..250760e0810 100644 --- a/arch/arm/include/asm/hardware/iop_adma.h +++ b/arch/arm/include/asm/hardware/iop_adma.h @@ -82,8 +82,6 @@ struct iop_adma_chan { * @slot_cnt: total slots used in an transaction (group of operations) * @slots_per_op: number of slots per operation * @idx: pool index - * @unmap_src_cnt: number of xor sources - * @unmap_len: transaction bytecount * @tx_list: list of descriptors that are associated with one operation * @async_tx: support for the async_tx api * @group_list: list of slots that make up a multi-descriptor transaction @@ -99,8 +97,6 @@ struct iop_adma_desc_slot { u16 slot_cnt; u16 slots_per_op; u16 idx; - u16 unmap_src_cnt; - size_t unmap_len; struct list_head tx_list; struct dma_async_tx_descriptor async_tx; union { diff --git a/arch/arm/include/asm/hardware/pci_v3.h b/arch/arm/include/asm/hardware/pci_v3.h deleted file mode 100644 index 2811c7e2cfd..00000000000 --- a/arch/arm/include/asm/hardware/pci_v3.h +++ /dev/null @@ -1,186 +0,0 @@ -/* - * arch/arm/include/asm/hardware/pci_v3.h - * - * Internal header file PCI V3 chip - * - * Copyright (C) ARM Limited - * Copyright (C) 2000-2001 Deep Blue Solutions Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#ifndef ASM_ARM_HARDWARE_PCI_V3_H -#define ASM_ARM_HARDWARE_PCI_V3_H - -/* ------------------------------------------------------------------------------- - * V3 Local Bus to PCI Bridge definitions - * ------------------------------------------------------------------------------- - * Registers (these are taken from page 129 of the EPC User's Manual Rev 1.04 - * All V3 register names are prefaced by V3_ to avoid clashing with any other - * PCI definitions. Their names match the user's manual. - * - * I'm assuming that I20 is disabled. - * - */ -#define V3_PCI_VENDOR 0x00000000 -#define V3_PCI_DEVICE 0x00000002 -#define V3_PCI_CMD 0x00000004 -#define V3_PCI_STAT 0x00000006 -#define V3_PCI_CC_REV 0x00000008 -#define V3_PCI_HDR_CFG 0x0000000C -#define V3_PCI_IO_BASE 0x00000010 -#define V3_PCI_BASE0 0x00000014 -#define V3_PCI_BASE1 0x00000018 -#define V3_PCI_SUB_VENDOR 0x0000002C -#define V3_PCI_SUB_ID 0x0000002E -#define V3_PCI_ROM 0x00000030 -#define V3_PCI_BPARAM 0x0000003C -#define V3_PCI_MAP0 0x00000040 -#define V3_PCI_MAP1 0x00000044 -#define V3_PCI_INT_STAT 0x00000048 -#define V3_PCI_INT_CFG 0x0000004C -#define V3_LB_BASE0 0x00000054 -#define V3_LB_BASE1 0x00000058 -#define V3_LB_MAP0 0x0000005E -#define V3_LB_MAP1 0x00000062 -#define V3_LB_BASE2 0x00000064 -#define V3_LB_MAP2 0x00000066 -#define V3_LB_SIZE 0x00000068 -#define V3_LB_IO_BASE 0x0000006E -#define V3_FIFO_CFG 0x00000070 -#define V3_FIFO_PRIORITY 0x00000072 -#define V3_FIFO_STAT 0x00000074 -#define V3_LB_ISTAT 0x00000076 -#define V3_LB_IMASK 0x00000077 -#define V3_SYSTEM 0x00000078 -#define V3_LB_CFG 0x0000007A -#define V3_PCI_CFG 0x0000007C -#define V3_DMA_PCI_ADR0 0x00000080 -#define V3_DMA_PCI_ADR1 0x00000090 -#define V3_DMA_LOCAL_ADR0 0x00000084 -#define V3_DMA_LOCAL_ADR1 0x00000094 -#define V3_DMA_LENGTH0 0x00000088 -#define V3_DMA_LENGTH1 0x00000098 -#define V3_DMA_CSR0 0x0000008B -#define V3_DMA_CSR1 0x0000009B -#define V3_DMA_CTLB_ADR0 0x0000008C -#define V3_DMA_CTLB_ADR1 0x0000009C -#define V3_DMA_DELAY 0x000000E0 -#define V3_MAIL_DATA 0x000000C0 -#define V3_PCI_MAIL_IEWR 0x000000D0 -#define V3_PCI_MAIL_IERD 0x000000D2 -#define V3_LB_MAIL_IEWR 0x000000D4 -#define V3_LB_MAIL_IERD 0x000000D6 -#define V3_MAIL_WR_STAT 0x000000D8 -#define V3_MAIL_RD_STAT 0x000000DA -#define V3_QBA_MAP 0x000000DC - -/* PCI COMMAND REGISTER bits - */ -#define V3_COMMAND_M_FBB_EN (1 << 9) -#define V3_COMMAND_M_SERR_EN (1 << 8) -#define V3_COMMAND_M_PAR_EN (1 << 6) -#define V3_COMMAND_M_MASTER_EN (1 << 2) -#define V3_COMMAND_M_MEM_EN (1 << 1) -#define V3_COMMAND_M_IO_EN (1 << 0) - -/* SYSTEM REGISTER bits - */ -#define V3_SYSTEM_M_RST_OUT (1 << 15) -#define V3_SYSTEM_M_LOCK (1 << 14) - -/* PCI_CFG bits - */ -#define V3_PCI_CFG_M_I2O_EN (1 << 15) -#define V3_PCI_CFG_M_IO_REG_DIS (1 << 14) -#define V3_PCI_CFG_M_IO_DIS (1 << 13) -#define V3_PCI_CFG_M_EN3V (1 << 12) -#define V3_PCI_CFG_M_RETRY_EN (1 << 10) -#define V3_PCI_CFG_M_AD_LOW1 (1 << 9) -#define V3_PCI_CFG_M_AD_LOW0 (1 << 8) - -/* PCI_BASE register bits (PCI -> Local Bus) - */ -#define V3_PCI_BASE_M_ADR_BASE 0xFFF00000 -#define V3_PCI_BASE_M_ADR_BASEL 0x000FFF00 -#define V3_PCI_BASE_M_PREFETCH (1 << 3) -#define V3_PCI_BASE_M_TYPE (3 << 1) -#define V3_PCI_BASE_M_IO (1 << 0) - -/* PCI MAP register bits (PCI -> Local bus) - */ -#define V3_PCI_MAP_M_MAP_ADR 0xFFF00000 -#define V3_PCI_MAP_M_RD_POST_INH (1 << 15) -#define V3_PCI_MAP_M_ROM_SIZE (3 << 10) -#define V3_PCI_MAP_M_SWAP (3 << 8) -#define V3_PCI_MAP_M_ADR_SIZE 0x000000F0 -#define V3_PCI_MAP_M_REG_EN (1 << 1) -#define V3_PCI_MAP_M_ENABLE (1 << 0) - -/* - * LB_BASE0,1 register bits (Local bus -> PCI) - */ -#define V3_LB_BASE_ADR_BASE 0xfff00000 -#define V3_LB_BASE_SWAP (3 << 8) -#define V3_LB_BASE_ADR_SIZE (15 << 4) -#define V3_LB_BASE_PREFETCH (1 << 3) -#define V3_LB_BASE_ENABLE (1 << 0) - -#define V3_LB_BASE_ADR_SIZE_1MB (0 << 4) -#define V3_LB_BASE_ADR_SIZE_2MB (1 << 4) -#define V3_LB_BASE_ADR_SIZE_4MB (2 << 4) -#define V3_LB_BASE_ADR_SIZE_8MB (3 << 4) -#define V3_LB_BASE_ADR_SIZE_16MB (4 << 4) -#define V3_LB_BASE_ADR_SIZE_32MB (5 << 4) -#define V3_LB_BASE_ADR_SIZE_64MB (6 << 4) -#define V3_LB_BASE_ADR_SIZE_128MB (7 << 4) -#define V3_LB_BASE_ADR_SIZE_256MB (8 << 4) -#define V3_LB_BASE_ADR_SIZE_512MB (9 << 4) -#define V3_LB_BASE_ADR_SIZE_1GB (10 << 4) -#define V3_LB_BASE_ADR_SIZE_2GB (11 << 4) - -#define v3_addr_to_lb_base(a) ((a) & V3_LB_BASE_ADR_BASE) - -/* - * LB_MAP0,1 register bits (Local bus -> PCI) - */ -#define V3_LB_MAP_MAP_ADR 0xfff0 -#define V3_LB_MAP_TYPE (7 << 1) -#define V3_LB_MAP_AD_LOW_EN (1 << 0) - -#define V3_LB_MAP_TYPE_IACK (0 << 1) -#define V3_LB_MAP_TYPE_IO (1 << 1) -#define V3_LB_MAP_TYPE_MEM (3 << 1) -#define V3_LB_MAP_TYPE_CONFIG (5 << 1) -#define V3_LB_MAP_TYPE_MEM_MULTIPLE (6 << 1) - -#define v3_addr_to_lb_map(a) (((a) >> 16) & V3_LB_MAP_MAP_ADR) - -/* - * LB_BASE2 register bits (Local bus -> PCI IO) - */ -#define V3_LB_BASE2_ADR_BASE 0xff00 -#define V3_LB_BASE2_SWAP (3 << 6) -#define V3_LB_BASE2_ENABLE (1 << 0) - -#define v3_addr_to_lb_base2(a) (((a) >> 16) & V3_LB_BASE2_ADR_BASE) - -/* - * LB_MAP2 register bits (Local bus -> PCI IO) - */ -#define V3_LB_MAP2_MAP_ADR 0xff00 - -#define v3_addr_to_lb_map2(a) (((a) >> 16) & V3_LB_MAP2_MAP_ADR) - -#endif diff --git a/arch/arm/include/asm/hardware/pl080.h b/arch/arm/include/asm/hardware/pl080.h deleted file mode 100644 index 4eea2107214..00000000000 --- a/arch/arm/include/asm/hardware/pl080.h +++ /dev/null @@ -1,146 +0,0 @@ -/* arch/arm/include/asm/hardware/pl080.h - * - * Copyright 2008 Openmoko, Inc. - * Copyright 2008 Simtec Electronics - * http://armlinux.simtec.co.uk/ - * Ben Dooks <ben@simtec.co.uk> - * - * ARM PrimeCell PL080 DMA controller - * - * 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. -*/ - -/* Note, there are some Samsung updates to this controller block which - * make it not entierly compatible with the PL080 specification from - * ARM. When in doubt, check the Samsung documentation first. - * - * The Samsung defines are PL080S, and add an extra control register, - * the ability to move more than 2^11 counts of data and some extra - * OneNAND features. -*/ - -#ifndef ASM_PL080_H -#define ASM_PL080_H - -#define PL080_INT_STATUS (0x00) -#define PL080_TC_STATUS (0x04) -#define PL080_TC_CLEAR (0x08) -#define PL080_ERR_STATUS (0x0C) -#define PL080_ERR_CLEAR (0x10) -#define PL080_RAW_TC_STATUS (0x14) -#define PL080_RAW_ERR_STATUS (0x18) -#define PL080_EN_CHAN (0x1c) -#define PL080_SOFT_BREQ (0x20) -#define PL080_SOFT_SREQ (0x24) -#define PL080_SOFT_LBREQ (0x28) -#define PL080_SOFT_LSREQ (0x2C) - -#define PL080_CONFIG (0x30) -#define PL080_CONFIG_M2_BE (1 << 2) -#define PL080_CONFIG_M1_BE (1 << 1) -#define PL080_CONFIG_ENABLE (1 << 0) - -#define PL080_SYNC (0x34) - -/* Per channel configuration registers */ - -#define PL080_Cx_STRIDE (0x20) -#define PL080_Cx_BASE(x) ((0x100 + (x * 0x20))) -#define PL080_Cx_SRC_ADDR(x) ((0x100 + (x * 0x20))) -#define PL080_Cx_DST_ADDR(x) ((0x104 + (x * 0x20))) -#define PL080_Cx_LLI(x) ((0x108 + (x * 0x20))) -#define PL080_Cx_CONTROL(x) ((0x10C + (x * 0x20))) -#define PL080_Cx_CONFIG(x) ((0x110 + (x * 0x20))) -#define PL080S_Cx_CONTROL2(x) ((0x110 + (x * 0x20))) -#define PL080S_Cx_CONFIG(x) ((0x114 + (x * 0x20))) - -#define PL080_CH_SRC_ADDR (0x00) -#define PL080_CH_DST_ADDR (0x04) -#define PL080_CH_LLI (0x08) -#define PL080_CH_CONTROL (0x0C) -#define PL080_CH_CONFIG (0x10) -#define PL080S_CH_CONTROL2 (0x10) -#define PL080S_CH_CONFIG (0x14) - -#define PL080_LLI_ADDR_MASK (0x3fffffff << 2) -#define PL080_LLI_ADDR_SHIFT (2) -#define PL080_LLI_LM_AHB2 (1 << 0) - -#define PL080_CONTROL_TC_IRQ_EN (1 << 31) -#define PL080_CONTROL_PROT_MASK (0x7 << 28) -#define PL080_CONTROL_PROT_SHIFT (28) -#define PL080_CONTROL_PROT_CACHE (1 << 30) -#define PL080_CONTROL_PROT_BUFF (1 << 29) -#define PL080_CONTROL_PROT_SYS (1 << 28) -#define PL080_CONTROL_DST_INCR (1 << 27) -#define PL080_CONTROL_SRC_INCR (1 << 26) -#define PL080_CONTROL_DST_AHB2 (1 << 25) -#define PL080_CONTROL_SRC_AHB2 (1 << 24) -#define PL080_CONTROL_DWIDTH_MASK (0x7 << 21) -#define PL080_CONTROL_DWIDTH_SHIFT (21) -#define PL080_CONTROL_SWIDTH_MASK (0x7 << 18) -#define PL080_CONTROL_SWIDTH_SHIFT (18) -#define PL080_CONTROL_DB_SIZE_MASK (0x7 << 15) -#define PL080_CONTROL_DB_SIZE_SHIFT (15) -#define PL080_CONTROL_SB_SIZE_MASK (0x7 << 12) -#define PL080_CONTROL_SB_SIZE_SHIFT (12) -#define PL080_CONTROL_TRANSFER_SIZE_MASK (0xfff << 0) -#define PL080_CONTROL_TRANSFER_SIZE_SHIFT (0) - -#define PL080_BSIZE_1 (0x0) -#define PL080_BSIZE_4 (0x1) -#define PL080_BSIZE_8 (0x2) -#define PL080_BSIZE_16 (0x3) -#define PL080_BSIZE_32 (0x4) -#define PL080_BSIZE_64 (0x5) -#define PL080_BSIZE_128 (0x6) -#define PL080_BSIZE_256 (0x7) - -#define PL080_WIDTH_8BIT (0x0) -#define PL080_WIDTH_16BIT (0x1) -#define PL080_WIDTH_32BIT (0x2) - -#define PL080N_CONFIG_ITPROT (1 << 20) -#define PL080N_CONFIG_SECPROT (1 << 19) -#define PL080_CONFIG_HALT (1 << 18) -#define PL080_CONFIG_ACTIVE (1 << 17) /* RO */ -#define PL080_CONFIG_LOCK (1 << 16) -#define PL080_CONFIG_TC_IRQ_MASK (1 << 15) -#define PL080_CONFIG_ERR_IRQ_MASK (1 << 14) -#define PL080_CONFIG_FLOW_CONTROL_MASK (0x7 << 11) -#define PL080_CONFIG_FLOW_CONTROL_SHIFT (11) -#define PL080_CONFIG_DST_SEL_MASK (0xf << 6) -#define PL080_CONFIG_DST_SEL_SHIFT (6) -#define PL080_CONFIG_SRC_SEL_MASK (0xf << 1) -#define PL080_CONFIG_SRC_SEL_SHIFT (1) -#define PL080_CONFIG_ENABLE (1 << 0) - -#define PL080_FLOW_MEM2MEM (0x0) -#define PL080_FLOW_MEM2PER (0x1) -#define PL080_FLOW_PER2MEM (0x2) -#define PL080_FLOW_SRC2DST (0x3) -#define PL080_FLOW_SRC2DST_DST (0x4) -#define PL080_FLOW_MEM2PER_PER (0x5) -#define PL080_FLOW_PER2MEM_PER (0x6) -#define PL080_FLOW_SRC2DST_SRC (0x7) - -/* DMA linked list chain structure */ - -struct pl080_lli { - u32 src_addr; - u32 dst_addr; - u32 next_lli; - u32 control0; -}; - -struct pl080s_lli { - u32 src_addr; - u32 dst_addr; - u32 next_lli; - u32 control0; - u32 control1; -}; - -#endif /* ASM_PL080_H */ diff --git a/arch/arm/include/asm/hardware/sp810.h b/arch/arm/include/asm/hardware/sp810.h deleted file mode 100644 index 6636430dd0e..00000000000 --- a/arch/arm/include/asm/hardware/sp810.h +++ /dev/null @@ -1,64 +0,0 @@ -/* - * arch/arm/include/asm/hardware/sp810.h - * - * ARM PrimeXsys System Controller SP810 header file - * - * Copyright (C) 2009 ST Microelectronics - * Viresh Kumar <viresh.linux@gmail.com> - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - */ - -#ifndef __ASM_ARM_SP810_H -#define __ASM_ARM_SP810_H - -#include <linux/io.h> - -/* sysctl registers offset */ -#define SCCTRL 0x000 -#define SCSYSSTAT 0x004 -#define SCIMCTRL 0x008 -#define SCIMSTAT 0x00C -#define SCXTALCTRL 0x010 -#define SCPLLCTRL 0x014 -#define SCPLLFCTRL 0x018 -#define SCPERCTRL0 0x01C -#define SCPERCTRL1 0x020 -#define SCPEREN 0x024 -#define SCPERDIS 0x028 -#define SCPERCLKEN 0x02C -#define SCPERSTAT 0x030 -#define SCSYSID0 0xEE0 -#define SCSYSID1 0xEE4 -#define SCSYSID2 0xEE8 -#define SCSYSID3 0xEEC -#define SCITCR 0xF00 -#define SCITIR0 0xF04 -#define SCITIR1 0xF08 -#define SCITOR 0xF0C -#define SCCNTCTRL 0xF10 -#define SCCNTDATA 0xF14 -#define SCCNTSTEP 0xF18 -#define SCPERIPHID0 0xFE0 -#define SCPERIPHID1 0xFE4 -#define SCPERIPHID2 0xFE8 -#define SCPERIPHID3 0xFEC -#define SCPCELLID0 0xFF0 -#define SCPCELLID1 0xFF4 -#define SCPCELLID2 0xFF8 -#define SCPCELLID3 0xFFC - -#define SCCTRL_TIMERENnSEL_SHIFT(n) (15 + ((n) * 2)) - -static inline void sysctl_soft_reset(void __iomem *base) -{ - /* switch to slow mode */ - writel(0x2, base + SCCTRL); - - /* writing any value to SCSYSSTAT reg will reset system */ - writel(0, base + SCSYSSTAT); -} - -#endif /* __ASM_ARM_SP810_H */ diff --git a/arch/arm/include/asm/hardware/timer-sp.h b/arch/arm/include/asm/hardware/timer-sp.h index 2dd9d3f83f2..bb28af7c32d 100644 --- a/arch/arm/include/asm/hardware/timer-sp.h +++ b/arch/arm/include/asm/hardware/timer-sp.h @@ -1,15 +1,23 @@ +struct clk; + void __sp804_clocksource_and_sched_clock_init(void __iomem *, - const char *, int); + const char *, struct clk *, int); +void __sp804_clockevents_init(void __iomem *, unsigned int, + struct clk *, const char *); static inline void sp804_clocksource_init(void __iomem *base, const char *name) { - __sp804_clocksource_and_sched_clock_init(base, name, 0); + __sp804_clocksource_and_sched_clock_init(base, name, NULL, 0); } static inline void sp804_clocksource_and_sched_clock_init(void __iomem *base, const char *name) { - __sp804_clocksource_and_sched_clock_init(base, name, 1); + __sp804_clocksource_and_sched_clock_init(base, name, NULL, 1); } -void sp804_clockevents_init(void __iomem *, unsigned int, const char *); +static inline void sp804_clockevents_init(void __iomem *base, unsigned int irq, const char *name) +{ + __sp804_clockevents_init(base, irq, NULL, name); + +} diff --git a/arch/arm/include/asm/hardware/vic.h b/arch/arm/include/asm/hardware/vic.h deleted file mode 100644 index 2bebad36fc8..00000000000 --- a/arch/arm/include/asm/hardware/vic.h +++ /dev/null @@ -1,57 +0,0 @@ -/* - * arch/arm/include/asm/hardware/vic.h - * - * Copyright (c) ARM Limited 2003. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#ifndef __ASM_ARM_HARDWARE_VIC_H -#define __ASM_ARM_HARDWARE_VIC_H - -#define VIC_IRQ_STATUS 0x00 -#define VIC_FIQ_STATUS 0x04 -#define VIC_RAW_STATUS 0x08 -#define VIC_INT_SELECT 0x0c /* 1 = FIQ, 0 = IRQ */ -#define VIC_INT_ENABLE 0x10 /* 1 = enable, 0 = disable */ -#define VIC_INT_ENABLE_CLEAR 0x14 -#define VIC_INT_SOFT 0x18 -#define VIC_INT_SOFT_CLEAR 0x1c -#define VIC_PROTECT 0x20 -#define VIC_PL190_VECT_ADDR 0x30 /* PL190 only */ -#define VIC_PL190_DEF_VECT_ADDR 0x34 /* PL190 only */ - -#define VIC_VECT_ADDR0 0x100 /* 0 to 15 (0..31 PL192) */ -#define VIC_VECT_CNTL0 0x200 /* 0 to 15 (0..31 PL192) */ -#define VIC_ITCR 0x300 /* VIC test control register */ - -#define VIC_VECT_CNTL_ENABLE (1 << 5) - -#define VIC_PL192_VECT_ADDR 0xF00 - -#ifndef __ASSEMBLY__ -#include <linux/compiler.h> -#include <linux/types.h> - -struct device_node; -struct pt_regs; - -void __vic_init(void __iomem *base, int irq_start, u32 vic_sources, - u32 resume_sources, struct device_node *node); -void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources); -int vic_of_init(struct device_node *node, struct device_node *parent); -void vic_handle_irq(struct pt_regs *regs); - -#endif /* __ASSEMBLY__ */ -#endif diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 8c5e828f484..535579511ed 100644 --- a/arch/arm/include/asm/highmem.h +++ b/arch/arm/include/asm/highmem.h @@ -18,6 +18,7 @@ } while (0) extern pte_t *pkmap_page_table; +extern pte_t *fixmap_page_table; extern void *kmap_high(struct page *page); extern void kunmap_high(struct page *page); @@ -41,6 +42,13 @@ extern void kunmap_high(struct page *page); #endif #endif +/* + * Needed to be able to broadcast the TLB invalidation for kmap. + */ +#ifdef CONFIG_ARM_ERRATA_798181 +#undef ARCH_NEEDS_KMAP_HIGH_GET +#endif + #ifdef ARCH_NEEDS_KMAP_HIGH_GET extern void *kmap_high_get(struct page *page); #else diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h new file mode 100644 index 00000000000..d4014fbe5ea --- /dev/null +++ b/arch/arm/include/asm/hugetlb-3level.h @@ -0,0 +1,71 @@ +/* + * arch/arm/include/asm/hugetlb-3level.h + * + * Copyright (C) 2012 ARM Ltd. + * + * Based on arch/x86/include/asm/hugetlb.h. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _ASM_ARM_HUGETLB_3LEVEL_H +#define _ASM_ARM_HUGETLB_3LEVEL_H + + +/* + * If our huge pte is non-zero then mark the valid bit. + * This allows pte_present(huge_ptep_get(ptep)) to return true for non-zero + * ptes. + * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes). + */ +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + pte_t retval = *ptep; + if (pte_val(retval)) + pte_val(retval) |= L_PTE_VALID; + return retval; +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + set_pte_at(mm, addr, ptep, pte); +} + +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + ptep_clear_flush(vma, addr, ptep); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + ptep_set_wrprotect(mm, addr, ptep); +} + +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + return ptep_get_and_clear(mm, addr, ptep); +} + +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); +} + +#endif /* _ASM_ARM_HUGETLB_3LEVEL_H */ diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h new file mode 100644 index 00000000000..1f1b1cd112f --- /dev/null +++ b/arch/arm/include/asm/hugetlb.h @@ -0,0 +1,84 @@ +/* + * arch/arm/include/asm/hugetlb.h + * + * Copyright (C) 2012 ARM Ltd. + * + * Based on arch/x86/include/asm/hugetlb.h + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _ASM_ARM_HUGETLB_H +#define _ASM_ARM_HUGETLB_H + +#include <asm/page.h> +#include <asm-generic/hugetlb.h> + +#include <asm/hugetlb-3level.h> + +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, + unsigned long ceiling) +{ + free_pgd_range(tlb, addr, end, floor, ceiling); +} + + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) +{ + struct hstate *h = hstate_file(file); + if (len & ~huge_page_mask(h)) + return -EINVAL; + if (addr & ~huge_page_mask(h)) + return -EINVAL; + return 0; +} + +static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) +{ +} + +static inline int huge_pte_none(pte_t pte) +{ + return pte_none(pte); +} + +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} + +static inline int arch_prepare_hugepage(struct page *page) +{ + return 0; +} + +static inline void arch_release_hugepage(struct page *page) +{ +} + +static inline void arch_clear_hugepage_flags(struct page *page) +{ + clear_bit(PG_dcache_clean, &page->flags); +} + +#endif /* _ASM_ARM_HUGETLB_H */ diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h index 01169dd723f..8e427c7b442 100644 --- a/arch/arm/include/asm/hw_breakpoint.h +++ b/arch/arm/include/asm/hw_breakpoint.h @@ -51,6 +51,7 @@ static inline void decode_ctrl_reg(u32 reg, #define ARM_DEBUG_ARCH_V7_ECP14 3 #define ARM_DEBUG_ARCH_V7_MM 4 #define ARM_DEBUG_ARCH_V7_1 5 +#define ARM_DEBUG_ARCH_V8 6 /* Breakpoint */ #define ARM_BREAKPOINT_EXECUTE 0 @@ -85,6 +86,9 @@ static inline void decode_ctrl_reg(u32 reg, #define ARM_DSCR_HDBGEN (1 << 14) #define ARM_DSCR_MDBGEN (1 << 15) +/* OSLSR os lock model bits */ +#define ARM_OSLSR_OSLM0 (1 << 0) + /* opcode2 numbers for the co-processor instructions. */ #define ARM_OP2_BVR 4 #define ARM_OP2_BCR 5 diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h index 6ff56eca3f1..6e183fd269f 100644 --- a/arch/arm/include/asm/hwcap.h +++ b/arch/arm/include/asm/hwcap.h @@ -9,6 +9,7 @@ * instruction set this cpu supports. */ #define ELF_HWCAP (elf_hwcap) -extern unsigned int elf_hwcap; +#define ELF_HWCAP2 (elf_hwcap2) +extern unsigned int elf_hwcap, elf_hwcap2; #endif #endif diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 652b56086de..3d23418cbdd 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -24,9 +24,11 @@ #ifdef __KERNEL__ #include <linux/types.h> +#include <linux/blk_types.h> #include <asm/byteorder.h> #include <asm/memory.h> #include <asm-generic/pci_iomap.h> +#include <xen/xen.h> /* * ISA I/O bus memory addresses are 1:1 with the physical address. @@ -36,6 +38,12 @@ #define isa_bus_to_virt phys_to_virt /* + * Atomic MMIO-wide IO modify + */ +extern void atomic_io_modify(void __iomem *reg, u32 mask, u32 set); +extern void atomic_io_modify_relaxed(void __iomem *reg, u32 mask, u32 set); + +/* * Generic IO read/write. These perform native-endian accesses. Note * that some architectures will want to re-define __raw_{read,write}w. */ @@ -130,16 +138,16 @@ 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 *); @@ -171,6 +179,12 @@ static inline void __iomem *__typesafe_io(unsigned long addr) /* PCI fixed i/o mapping */ #define PCI_IO_VIRT_BASE 0xfee00000 +#if defined(CONFIG_PCI) +void pci_ioremap_set_mem_type(int mem_type); +#else +static inline void pci_ioremap_set_mem_type(int mem_type) {} +#endif + extern int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr); /* @@ -327,7 +341,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t); */ #define ioremap(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) #define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) -#define ioremap_cached(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED) +#define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED) #define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC) #define iounmap __arm_iounmap @@ -372,6 +386,13 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr); #define BIOVEC_MERGEABLE(vec1, vec2) \ ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) +struct bio_vec; +extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, + const struct bio_vec *vec2); +#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \ + (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2))) + #ifdef CONFIG_MMU #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index 35c21c375d8..53c15dec7af 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -30,6 +30,11 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); void init_IRQ(void); +#ifdef CONFIG_MULTI_IRQ_HANDLER +extern void (*handle_arch_irq)(struct pt_regs *); +extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); +#endif + #endif #endif diff --git a/arch/arm/include/asm/irqflags.h b/arch/arm/include/asm/irqflags.h index 1e6cca55c75..3b763d6652a 100644 --- a/arch/arm/include/asm/irqflags.h +++ b/arch/arm/include/asm/irqflags.h @@ -8,6 +8,16 @@ /* * CPU interrupt mask handling. */ +#ifdef CONFIG_CPU_V7M +#define IRQMASK_REG_NAME_R "primask" +#define IRQMASK_REG_NAME_W "primask" +#define IRQMASK_I_BIT 1 +#else +#define IRQMASK_REG_NAME_R "cpsr" +#define IRQMASK_REG_NAME_W "cpsr_c" +#define IRQMASK_I_BIT PSR_I_BIT +#endif + #if __LINUX_ARM_ARCH__ >= 6 static inline unsigned long arch_local_irq_save(void) @@ -15,7 +25,7 @@ static inline unsigned long arch_local_irq_save(void) unsigned long flags; asm volatile( - " mrs %0, cpsr @ arch_local_irq_save\n" + " mrs %0, " IRQMASK_REG_NAME_R " @ arch_local_irq_save\n" " cpsid i" : "=r" (flags) : : "memory", "cc"); return flags; @@ -129,7 +139,7 @@ static inline unsigned long arch_local_save_flags(void) { unsigned long flags; asm volatile( - " mrs %0, cpsr @ local_save_flags" + " mrs %0, " IRQMASK_REG_NAME_R " @ local_save_flags" : "=r" (flags) : : "memory", "cc"); return flags; } @@ -140,7 +150,7 @@ static inline unsigned long arch_local_save_flags(void) static inline void arch_local_irq_restore(unsigned long flags) { asm volatile( - " msr cpsr_c, %0 @ local_irq_restore" + " msr " IRQMASK_REG_NAME_W ", %0 @ local_irq_restore" : : "r" (flags) : "memory", "cc"); @@ -148,8 +158,8 @@ static inline void arch_local_irq_restore(unsigned long flags) static inline int arch_irqs_disabled_flags(unsigned long flags) { - return flags & PSR_I_BIT; + return flags & IRQMASK_I_BIT; } -#endif -#endif +#endif /* ifdef __KERNEL__ */ +#endif /* ifndef __ASM_ARM_IRQFLAGS_H */ diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index bfc198c7591..70f9b9bfb1f 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -4,7 +4,6 @@ #ifdef __KERNEL__ #include <linux/types.h> -#include <asm/system.h> #define JUMP_LABEL_NOP_SIZE 4 @@ -16,7 +15,7 @@ static __always_inline bool arch_static_branch(struct static_key *key) { - asm goto("1:\n\t" + asm_volatile_goto("1:\n\t" JUMP_LABEL_NOP "\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h index 48066ce9ea3..0a9d5dd9329 100644 --- a/arch/arm/include/asm/kgdb.h +++ b/arch/arm/include/asm/kgdb.h @@ -11,6 +11,7 @@ #define __ARM_KGDB_H__ #include <linux/ptrace.h> +#include <asm/opcodes.h> /* * GDB assumes that we're a user process being debugged, so @@ -41,7 +42,7 @@ static inline void arch_kgdb_breakpoint(void) { - asm(".word 0xe7ffdeff"); + asm(__inst_arm(0xe7ffdeff)); } extern void kgdb_handle_bus_error(void); diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index f82ec22eeb1..49fa0dfaad3 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -18,7 +18,7 @@ #include <linux/types.h> #include <linux/ptrace.h> -#include <linux/percpu.h> +#include <linux/notifier.h> #define __ARCH_WANT_KPROBES_INSN_SLOT #define MAX_INSN_SIZE 2 @@ -28,21 +28,10 @@ #define kretprobe_blacklist_size 0 typedef u32 kprobe_opcode_t; - struct kprobe; -typedef void (kprobe_insn_handler_t)(struct kprobe *, struct pt_regs *); -typedef unsigned long (kprobe_check_cc)(unsigned long); -typedef void (kprobe_insn_singlestep_t)(struct kprobe *, struct pt_regs *); -typedef void (kprobe_insn_fn_t)(void); +#include <asm/probes.h> -/* Architecture specific copy of original instruction. */ -struct arch_specific_insn { - kprobe_opcode_t *insn; - kprobe_insn_handler_t *insn_handler; - kprobe_check_cc *insn_check_cc; - kprobe_insn_singlestep_t *insn_singlestep; - kprobe_insn_fn_t *insn_fn; -}; +#define arch_specific_insn arch_probes_insn struct prev_kprobe { struct kprobe *kp; diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h new file mode 100644 index 00000000000..816db0bf2dd --- /dev/null +++ b/arch/arm/include/asm/kvm_arm.h @@ -0,0 +1,220 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_ARM_H__ +#define __ARM_KVM_ARM_H__ + +#include <linux/types.h> + +/* Hyp Configuration Register (HCR) bits */ +#define HCR_TGE (1 << 27) +#define HCR_TVM (1 << 26) +#define HCR_TTLB (1 << 25) +#define HCR_TPU (1 << 24) +#define HCR_TPC (1 << 23) +#define HCR_TSW (1 << 22) +#define HCR_TAC (1 << 21) +#define HCR_TIDCP (1 << 20) +#define HCR_TSC (1 << 19) +#define HCR_TID3 (1 << 18) +#define HCR_TID2 (1 << 17) +#define HCR_TID1 (1 << 16) +#define HCR_TID0 (1 << 15) +#define HCR_TWE (1 << 14) +#define HCR_TWI (1 << 13) +#define HCR_DC (1 << 12) +#define HCR_BSU (3 << 10) +#define HCR_BSU_IS (1 << 10) +#define HCR_FB (1 << 9) +#define HCR_VA (1 << 8) +#define HCR_VI (1 << 7) +#define HCR_VF (1 << 6) +#define HCR_AMO (1 << 5) +#define HCR_IMO (1 << 4) +#define HCR_FMO (1 << 3) +#define HCR_PTW (1 << 2) +#define HCR_SWIO (1 << 1) +#define HCR_VM 1 + +/* + * The bits we set in HCR: + * TAC: Trap ACTLR + * TSC: Trap SMC + * TVM: Trap VM ops (until MMU and caches are on) + * TSW: Trap cache operations by set/way + * TWI: Trap WFI + * TWE: Trap WFE + * TIDCP: Trap L2CTLR/L2ECTLR + * BSU_IS: Upgrade barriers to the inner shareable domain + * FB: Force broadcast of all maintainance operations + * AMO: Override CPSR.A and enable signaling with VA + * IMO: Override CPSR.I and enable signaling with VI + * FMO: Override CPSR.F and enable signaling with VF + * SWIO: Turn set/way invalidates into set/way clean+invalidate + */ +#define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ + HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ + HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP) + +/* System Control Register (SCTLR) bits */ +#define SCTLR_TE (1 << 30) +#define SCTLR_EE (1 << 25) +#define SCTLR_V (1 << 13) + +/* Hyp System Control Register (HSCTLR) bits */ +#define HSCTLR_TE (1 << 30) +#define HSCTLR_EE (1 << 25) +#define HSCTLR_FI (1 << 21) +#define HSCTLR_WXN (1 << 19) +#define HSCTLR_I (1 << 12) +#define HSCTLR_C (1 << 2) +#define HSCTLR_A (1 << 1) +#define HSCTLR_M 1 +#define HSCTLR_MASK (HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I | \ + HSCTLR_WXN | HSCTLR_FI | HSCTLR_EE | HSCTLR_TE) + +/* TTBCR and HTCR Registers bits */ +#define TTBCR_EAE (1 << 31) +#define TTBCR_IMP (1 << 30) +#define TTBCR_SH1 (3 << 28) +#define TTBCR_ORGN1 (3 << 26) +#define TTBCR_IRGN1 (3 << 24) +#define TTBCR_EPD1 (1 << 23) +#define TTBCR_A1 (1 << 22) +#define TTBCR_T1SZ (7 << 16) +#define TTBCR_SH0 (3 << 12) +#define TTBCR_ORGN0 (3 << 10) +#define TTBCR_IRGN0 (3 << 8) +#define TTBCR_EPD0 (1 << 7) +#define TTBCR_T0SZ (7 << 0) +#define HTCR_MASK (TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0) + +/* Hyp System Trap Register */ +#define HSTR_T(x) (1 << x) +#define HSTR_TTEE (1 << 16) +#define HSTR_TJDBX (1 << 17) + +/* Hyp Coprocessor Trap Register */ +#define HCPTR_TCP(x) (1 << x) +#define HCPTR_TCP_MASK (0x3fff) +#define HCPTR_TASE (1 << 15) +#define HCPTR_TTA (1 << 20) +#define HCPTR_TCPAC (1 << 31) + +/* Hyp Debug Configuration Register bits */ +#define HDCR_TDRA (1 << 11) +#define HDCR_TDOSA (1 << 10) +#define HDCR_TDA (1 << 9) +#define HDCR_TDE (1 << 8) +#define HDCR_HPME (1 << 7) +#define HDCR_TPM (1 << 6) +#define HDCR_TPMCR (1 << 5) +#define HDCR_HPMN_MASK (0x1F) + +/* + * The architecture supports 40-bit IPA as input to the 2nd stage translations + * and PTRS_PER_S2_PGD becomes 1024, because each entry covers 1GB of address + * space. + */ +#define KVM_PHYS_SHIFT (40) +#define KVM_PHYS_SIZE (1ULL << KVM_PHYS_SHIFT) +#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1ULL) +#define PTRS_PER_S2_PGD (1ULL << (KVM_PHYS_SHIFT - 30)) +#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) + +/* Virtualization Translation Control Register (VTCR) bits */ +#define VTCR_SH0 (3 << 12) +#define VTCR_ORGN0 (3 << 10) +#define VTCR_IRGN0 (3 << 8) +#define VTCR_SL0 (3 << 6) +#define VTCR_S (1 << 4) +#define VTCR_T0SZ (0xf) +#define VTCR_MASK (VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0 | VTCR_SL0 | \ + VTCR_S | VTCR_T0SZ) +#define VTCR_HTCR_SH (VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0) +#define VTCR_SL_L2 (0 << 6) /* Starting-level: 2 */ +#define VTCR_SL_L1 (1 << 6) /* Starting-level: 1 */ +#define KVM_VTCR_SL0 VTCR_SL_L1 +/* stage-2 input address range defined as 2^(32-T0SZ) */ +#define KVM_T0SZ (32 - KVM_PHYS_SHIFT) +#define KVM_VTCR_T0SZ (KVM_T0SZ & VTCR_T0SZ) +#define KVM_VTCR_S ((KVM_VTCR_T0SZ << 1) & VTCR_S) + +/* Virtualization Translation Table Base Register (VTTBR) bits */ +#if KVM_VTCR_SL0 == VTCR_SL_L2 /* see ARM DDI 0406C: B4-1720 */ +#define VTTBR_X (14 - KVM_T0SZ) +#else +#define VTTBR_X (5 - KVM_T0SZ) +#endif +#define VTTBR_BADDR_SHIFT (VTTBR_X - 1) +#define VTTBR_BADDR_MASK (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_VMID_SHIFT (48LLU) +#define VTTBR_VMID_MASK (0xffLLU << VTTBR_VMID_SHIFT) + +/* Hyp Syndrome Register (HSR) bits */ +#define HSR_EC_SHIFT (26) +#define HSR_EC (0x3fU << HSR_EC_SHIFT) +#define HSR_IL (1U << 25) +#define HSR_ISS (HSR_IL - 1) +#define HSR_ISV_SHIFT (24) +#define HSR_ISV (1U << HSR_ISV_SHIFT) +#define HSR_SRT_SHIFT (16) +#define HSR_SRT_MASK (0xf << HSR_SRT_SHIFT) +#define HSR_FSC (0x3f) +#define HSR_FSC_TYPE (0x3c) +#define HSR_SSE (1 << 21) +#define HSR_WNR (1 << 6) +#define HSR_CV_SHIFT (24) +#define HSR_CV (1U << HSR_CV_SHIFT) +#define HSR_COND_SHIFT (20) +#define HSR_COND (0xfU << HSR_COND_SHIFT) + +#define FSC_FAULT (0x04) +#define FSC_PERM (0x0c) + +/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ +#define HPFAR_MASK (~0xf) + +#define HSR_EC_UNKNOWN (0x00) +#define HSR_EC_WFI (0x01) +#define HSR_EC_CP15_32 (0x03) +#define HSR_EC_CP15_64 (0x04) +#define HSR_EC_CP14_MR (0x05) +#define HSR_EC_CP14_LS (0x06) +#define HSR_EC_CP_0_13 (0x07) +#define HSR_EC_CP10_ID (0x08) +#define HSR_EC_JAZELLE (0x09) +#define HSR_EC_BXJ (0x0A) +#define HSR_EC_CP14_64 (0x0C) +#define HSR_EC_SVC_HYP (0x11) +#define HSR_EC_HVC (0x12) +#define HSR_EC_SMC (0x13) +#define HSR_EC_IABT (0x20) +#define HSR_EC_IABT_HYP (0x21) +#define HSR_EC_DABT (0x24) +#define HSR_EC_DABT_HYP (0x25) + +#define HSR_WFI_IS_WFE (1U << 0) + +#define HSR_HVC_IMM_MASK ((1UL << 16) - 1) + +#define HSR_DABT_S1PTW (1U << 7) +#define HSR_DABT_CM (1U << 8) +#define HSR_DABT_EA (1U << 9) + +#endif /* __ARM_KVM_ARM_H__ */ diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h new file mode 100644 index 00000000000..53b3c4a50d5 --- /dev/null +++ b/arch/arm/include/asm/kvm_asm.h @@ -0,0 +1,85 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_ASM_H__ +#define __ARM_KVM_ASM_H__ + +/* 0 is reserved as an invalid value. */ +#define c0_MPIDR 1 /* MultiProcessor ID Register */ +#define c0_CSSELR 2 /* Cache Size Selection Register */ +#define c1_SCTLR 3 /* System Control Register */ +#define c1_ACTLR 4 /* Auxilliary Control Register */ +#define c1_CPACR 5 /* Coprocessor Access Control */ +#define c2_TTBR0 6 /* Translation Table Base Register 0 */ +#define c2_TTBR0_high 7 /* TTBR0 top 32 bits */ +#define c2_TTBR1 8 /* Translation Table Base Register 1 */ +#define c2_TTBR1_high 9 /* TTBR1 top 32 bits */ +#define c2_TTBCR 10 /* Translation Table Base Control R. */ +#define c3_DACR 11 /* Domain Access Control Register */ +#define c5_DFSR 12 /* Data Fault Status Register */ +#define c5_IFSR 13 /* Instruction Fault Status Register */ +#define c5_ADFSR 14 /* Auxilary Data Fault Status R */ +#define c5_AIFSR 15 /* Auxilary Instrunction Fault Status R */ +#define c6_DFAR 16 /* Data Fault Address Register */ +#define c6_IFAR 17 /* Instruction Fault Address Register */ +#define c7_PAR 18 /* Physical Address Register */ +#define c7_PAR_high 19 /* PAR top 32 bits */ +#define c9_L2CTLR 20 /* Cortex A15/A7 L2 Control Register */ +#define c10_PRRR 21 /* Primary Region Remap Register */ +#define c10_NMRR 22 /* Normal Memory Remap Register */ +#define c12_VBAR 23 /* Vector Base Address Register */ +#define c13_CID 24 /* Context ID Register */ +#define c13_TID_URW 25 /* Thread ID, User R/W */ +#define c13_TID_URO 26 /* Thread ID, User R/O */ +#define c13_TID_PRIV 27 /* Thread ID, Privileged */ +#define c14_CNTKCTL 28 /* Timer Control Register (PL1) */ +#define c10_AMAIR0 29 /* Auxilary Memory Attribute Indirection Reg0 */ +#define c10_AMAIR1 30 /* Auxilary Memory Attribute Indirection Reg1 */ +#define NR_CP15_REGS 31 /* Number of regs (incl. invalid) */ + +#define ARM_EXCEPTION_RESET 0 +#define ARM_EXCEPTION_UNDEFINED 1 +#define ARM_EXCEPTION_SOFTWARE 2 +#define ARM_EXCEPTION_PREF_ABORT 3 +#define ARM_EXCEPTION_DATA_ABORT 4 +#define ARM_EXCEPTION_IRQ 5 +#define ARM_EXCEPTION_FIQ 6 +#define ARM_EXCEPTION_HVC 7 + +#ifndef __ASSEMBLY__ +struct kvm; +struct kvm_vcpu; + +extern char __kvm_hyp_init[]; +extern char __kvm_hyp_init_end[]; + +extern char __kvm_hyp_exit[]; +extern char __kvm_hyp_exit_end[]; + +extern char __kvm_hyp_vector[]; + +extern char __kvm_hyp_code_start[]; +extern char __kvm_hyp_code_end[]; + +extern void __kvm_flush_vm_context(void); +extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); + +extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); +#endif + +#endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm/include/asm/kvm_coproc.h b/arch/arm/include/asm/kvm_coproc.h new file mode 100644 index 00000000000..4917c2f7e45 --- /dev/null +++ b/arch/arm/include/asm/kvm_coproc.h @@ -0,0 +1,47 @@ +/* + * Copyright (C) 2012 Rusty Russell IBM Corporation + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_COPROC_H__ +#define __ARM_KVM_COPROC_H__ +#include <linux/kvm_host.h> + +void kvm_reset_coprocs(struct kvm_vcpu *vcpu); + +struct kvm_coproc_target_table { + unsigned target; + const struct coproc_reg *table; + size_t num; +}; +void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table); + +int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run); + +unsigned long kvm_arm_num_guest_msrs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_msrindices(struct kvm_vcpu *vcpu, u64 __user *uindices); +void kvm_coproc_table_init(void); + +struct kvm_one_reg; +int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu); +#endif /* __ARM_KVM_COPROC_H__ */ diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h new file mode 100644 index 00000000000..0fa90c962ac --- /dev/null +++ b/arch/arm/include/asm/kvm_emulate.h @@ -0,0 +1,211 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_EMULATE_H__ +#define __ARM_KVM_EMULATE_H__ + +#include <linux/kvm_host.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmio.h> +#include <asm/kvm_arm.h> + +unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); +unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu); + +bool kvm_condition_valid(struct kvm_vcpu *vcpu); +void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr); +void kvm_inject_undefined(struct kvm_vcpu *vcpu); +void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); + +static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) +{ + return 1; +} + +static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.regs.usr_regs.ARM_pc; +} + +static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.regs.usr_regs.ARM_cpsr; +} + +static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) +{ + *vcpu_cpsr(vcpu) |= PSR_T_BIT; +} + +static inline bool mode_has_spsr(struct kvm_vcpu *vcpu) +{ + unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK; + return (cpsr_mode > USR_MODE && cpsr_mode < SYSTEM_MODE); +} + +static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu) +{ + unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK; + return cpsr_mode > USR_MODE;; +} + +static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hsr; +} + +static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hxfar; +} + +static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu) +{ + return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8; +} + +static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hyp_pc; +} + +static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_ISV; +} + +static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_WNR; +} + +static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_SSE; +} + +static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) +{ + return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; +} + +static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_EA; +} + +static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; +} + +/* Get Access Size from a data abort */ +static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu) +{ + switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) { + case 0: + return 1; + case 1: + return 2; + case 2: + return 4; + default: + kvm_err("Hardware is weird: SAS 0b11 is reserved\n"); + return -EFAULT; + } +} + +/* This one is not specific to Data Abort */ +static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_IL; +} + +static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; +} + +static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; +} + +static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE; +} + +static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; +} + +static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cp15[c0_MPIDR]; +} + +static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) +{ + *vcpu_cpsr(vcpu) |= PSR_E_BIT; +} + +static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) +{ + return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT); +} + +static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return be16_to_cpu(data & 0xffff); + default: + return be32_to_cpu(data); + } + } + + return data; /* Leave LE untouched */ +} + +static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return cpu_to_be16(data & 0xffff); + default: + return cpu_to_be32(data); + } + } + + return data; /* Leave LE untouched */ +} + +#endif /* __ARM_KVM_EMULATE_H__ */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h new file mode 100644 index 00000000000..193ceaf01bf --- /dev/null +++ b/arch/arm/include/asm/kvm_host.h @@ -0,0 +1,234 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_HOST_H__ +#define __ARM_KVM_HOST_H__ + +#include <asm/kvm.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmio.h> +#include <asm/fpstate.h> +#include <kvm/arm_arch_timer.h> + +#if defined(CONFIG_KVM_ARM_MAX_VCPUS) +#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS +#else +#define KVM_MAX_VCPUS 0 +#endif + +#define KVM_USER_MEM_SLOTS 32 +#define KVM_PRIVATE_MEM_SLOTS 4 +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_HAVE_ONE_REG + +#define KVM_VCPU_MAX_FEATURES 2 + +#include <kvm/arm_vgic.h> + +struct kvm_vcpu; +u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); +int kvm_target_cpu(void); +int kvm_reset_vcpu(struct kvm_vcpu *vcpu); +void kvm_reset_coprocs(struct kvm_vcpu *vcpu); + +struct kvm_arch { + /* VTTBR value associated with below pgd and vmid */ + u64 vttbr; + + /* Timer */ + struct arch_timer_kvm timer; + + /* + * Anything that is not used directly from assembly code goes + * here. + */ + + /* The VMID generation used for the virt. memory system */ + u64 vmid_gen; + u32 vmid; + + /* Stage-2 page table */ + pgd_t *pgd; + + /* Interrupt controller */ + struct vgic_dist vgic; +}; + +#define KVM_NR_MEM_OBJS 40 + +/* + * We don't want allocation failures within the mmu code, so we preallocate + * enough memory for a single page fault in a cache. + */ +struct kvm_mmu_memory_cache { + int nobjs; + void *objects[KVM_NR_MEM_OBJS]; +}; + +struct kvm_vcpu_fault_info { + u32 hsr; /* Hyp Syndrome Register */ + u32 hxfar; /* Hyp Data/Inst. Fault Address Register */ + u32 hpfar; /* Hyp IPA Fault Address Register */ + u32 hyp_pc; /* PC when exception was taken from Hyp mode */ +}; + +typedef struct vfp_hard_struct kvm_cpu_context_t; + +struct kvm_vcpu_arch { + struct kvm_regs regs; + + int target; /* Processor target */ + DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); + + /* System control coprocessor (cp15) */ + u32 cp15[NR_CP15_REGS]; + + /* The CPU type we expose to the VM */ + u32 midr; + + /* HYP trapping configuration */ + u32 hcr; + + /* Interrupt related fields */ + u32 irq_lines; /* IRQ and FIQ levels */ + + /* Exception Information */ + struct kvm_vcpu_fault_info fault; + + /* Floating point registers (VFP and Advanced SIMD/NEON) */ + struct vfp_hard_struct vfp_guest; + + /* Host FP context */ + kvm_cpu_context_t *host_cpu_context; + + /* VGIC state */ + struct vgic_cpu vgic_cpu; + struct arch_timer_cpu timer_cpu; + + /* + * Anything that is not used directly from assembly code goes + * here. + */ + /* dcache set/way operation pending */ + int last_pcpu; + cpumask_t require_dcache_flush; + + /* Don't run the guest on this vcpu */ + bool pause; + + /* IO related fields */ + struct kvm_decode mmio_decode; + + /* Cache some mmu pages needed inside spinlock regions */ + struct kvm_mmu_memory_cache mmu_page_cache; + + /* Detect first run of a vcpu */ + bool has_run_once; +}; + +struct kvm_vm_stat { + u32 remote_tlb_flush; +}; + +struct kvm_vcpu_stat { + u32 halt_wakeup; +}; + +struct kvm_vcpu_init; +int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, + const struct kvm_vcpu_init *init); +int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); +unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); +struct kvm_one_reg; +int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +u64 kvm_call_hyp(void *hypfn, ...); +void force_vm_exit(const cpumask_t *mask); + +#define KVM_ARCH_WANT_MMU_NOTIFIER +struct kvm; +int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); +int kvm_unmap_hva_range(struct kvm *kvm, + unsigned long start, unsigned long end); +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); + +unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); + +/* We do not have shadow page tables, hence the empty hooks */ +static inline int kvm_age_hva(struct kvm *kvm, unsigned long hva) +{ + return 0; +} + +static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + return 0; +} + +struct kvm_vcpu *kvm_arm_get_running_vcpu(void); +struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); + +int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu); +struct kvm_one_reg; +int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); + +int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + int exception_index); + +static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr, + phys_addr_t pgd_ptr, + unsigned long hyp_stack_ptr, + unsigned long vector_ptr) +{ + /* + * Call initialization code, and switch to the full blown HYP + * code. The init code doesn't need to preserve these + * registers as r0-r3 are already callee saved according to + * the AAPCS. + * Note that we slightly misuse the prototype by casing the + * stack pointer to a void *. + * + * We don't have enough registers to perform the full init in + * one go. Install the boot PGD first, and then install the + * runtime PGD, stack pointer and vectors. The PGDs are always + * passed as the third argument, in order to be passed into + * r2-r3 to the init code (yes, this is compliant with the + * PCS!). + */ + + kvm_call_hyp(NULL, 0, boot_pgd_ptr); + + kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr); +} + +static inline int kvm_arch_dev_ioctl_check_extension(long ext) +{ + return 0; +} + +int kvm_perf_init(void); +int kvm_perf_teardown(void); + +u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid); +int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value); + +#endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h new file mode 100644 index 00000000000..adcc0d7d317 --- /dev/null +++ b/arch/arm/include/asm/kvm_mmio.h @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_MMIO_H__ +#define __ARM_KVM_MMIO_H__ + +#include <linux/kvm_host.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_arm.h> + +struct kvm_decode { + unsigned long rt; + bool sign_extend; +}; + +/* + * The in-kernel MMIO emulation code wants to use a copy of run->mmio, + * which is an anonymous type. Use our own type instead. + */ +struct kvm_exit_mmio { + phys_addr_t phys_addr; + u8 data[8]; + u32 len; + bool is_write; +}; + +static inline void kvm_prepare_mmio(struct kvm_run *run, + struct kvm_exit_mmio *mmio) +{ + run->mmio.phys_addr = mmio->phys_addr; + run->mmio.len = mmio->len; + run->mmio.is_write = mmio->is_write; + memcpy(run->mmio.data, mmio->data, mmio->len); + run->exit_reason = KVM_EXIT_MMIO; +} + +int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); +int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, + phys_addr_t fault_ipa); + +#endif /* __ARM_KVM_MMIO_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h new file mode 100644 index 00000000000..5c7aa3c1519 --- /dev/null +++ b/arch/arm/include/asm/kvm_mmu.h @@ -0,0 +1,171 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#ifndef __ARM_KVM_MMU_H__ +#define __ARM_KVM_MMU_H__ + +#include <asm/memory.h> +#include <asm/page.h> + +/* + * We directly use the kernel VA for the HYP, as we can directly share + * the mapping (HTTBR "covers" TTBR1). + */ +#define HYP_PAGE_OFFSET_MASK UL(~0) +#define HYP_PAGE_OFFSET PAGE_OFFSET +#define KERN_TO_HYP(kva) (kva) + +/* + * Our virtual mapping for the boot-time MMU-enable code. Must be + * shared across all the page-tables. Conveniently, we use the vectors + * page, where no kernel data will ever be shared with HYP. + */ +#define TRAMPOLINE_VA UL(CONFIG_VECTORS_BASE) + +#ifndef __ASSEMBLY__ + +#include <asm/cacheflush.h> +#include <asm/pgalloc.h> + +int create_hyp_mappings(void *from, void *to); +int create_hyp_io_mappings(void *from, void *to, phys_addr_t); +void free_boot_hyp_pgd(void); +void free_hyp_pgds(void); + +int kvm_alloc_stage2_pgd(struct kvm *kvm); +void kvm_free_stage2_pgd(struct kvm *kvm); +int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, + phys_addr_t pa, unsigned long size); + +int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run); + +void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu); + +phys_addr_t kvm_mmu_get_httbr(void); +phys_addr_t kvm_mmu_get_boot_httbr(void); +phys_addr_t kvm_get_idmap_vector(void); +int kvm_mmu_init(void); +void kvm_clear_hyp_idmap(void); + +static inline void kvm_set_pmd(pmd_t *pmd, pmd_t new_pmd) +{ + *pmd = new_pmd; + flush_pmd_entry(pmd); +} + +static inline void kvm_set_pte(pte_t *pte, pte_t new_pte) +{ + *pte = new_pte; + /* + * flush_pmd_entry just takes a void pointer and cleans the necessary + * cache entries, so we can reuse the function for ptes. + */ + flush_pmd_entry(pte); +} + +static inline bool kvm_is_write_fault(unsigned long hsr) +{ + unsigned long hsr_ec = hsr >> HSR_EC_SHIFT; + if (hsr_ec == HSR_EC_IABT) + return false; + else if ((hsr & HSR_ISV) && !(hsr & HSR_WNR)) + return false; + else + return true; +} + +static inline void kvm_clean_pgd(pgd_t *pgd) +{ + clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); +} + +static inline void kvm_clean_pmd_entry(pmd_t *pmd) +{ + clean_pmd_entry(pmd); +} + +static inline void kvm_clean_pte(pte_t *pte) +{ + clean_pte_table(pte); +} + +static inline void kvm_set_s2pte_writable(pte_t *pte) +{ + pte_val(*pte) |= L_PTE_S2_RDWR; +} + +static inline void kvm_set_s2pmd_writable(pmd_t *pmd) +{ + pmd_val(*pmd) |= L_PMD_S2_RDWR; +} + +/* Open coded p*d_addr_end that can deal with 64bit addresses */ +#define kvm_pgd_addr_end(addr, end) \ +({ u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +#define kvm_pud_addr_end(addr,end) (end) + +#define kvm_pmd_addr_end(addr, end) \ +({ u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +struct kvm; + +#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l)) + +static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; +} + +static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, + unsigned long size) +{ + if (!vcpu_has_cache_enabled(vcpu)) + kvm_flush_dcache_to_poc((void *)hva, size); + + /* + * If we are going to insert an instruction page and the icache is + * either VIPT or PIPT, there is a potential problem where the host + * (or another VM) may have used the same page as this guest, and we + * read incorrect data from the icache. If we're using a PIPT cache, + * we can invalidate just that page, but if we are using a VIPT cache + * we need to invalidate the entire icache - damn shame - as written + * in the ARM ARM (DDI 0406C.b - Page B3-1393). + * + * VIVT caches are tagged using both the ASID and the VMID and doesn't + * need any kind of flushing (DDI 0406C.b - Page B3-1392). + */ + if (icache_is_pipt()) { + __cpuc_coherent_user_range(hva, hva + size); + } else if (!icache_is_vivt_asid_tagged()) { + /* any kind of VIPT cache */ + __flush_icache_all(); + } +} + +#define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) + +void stage2_flush_vm(struct kvm *kvm); + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/kvm_psci.h b/arch/arm/include/asm/kvm_psci.h new file mode 100644 index 00000000000..6bda945d31f --- /dev/null +++ b/arch/arm/include/asm/kvm_psci.h @@ -0,0 +1,27 @@ +/* + * Copyright (C) 2012 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __ARM_KVM_PSCI_H__ +#define __ARM_KVM_PSCI_H__ + +#define KVM_ARM_PSCI_0_1 1 +#define KVM_ARM_PSCI_0_2 2 + +int kvm_psci_version(struct kvm_vcpu *vcpu); +int kvm_psci_call(struct kvm_vcpu *vcpu); + +#endif /* __ARM_KVM_PSCI_H__ */ diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h deleted file mode 100644 index f77ffc1eb0c..00000000000 --- a/arch/arm/include/asm/localtimer.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * arch/arm/include/asm/localtimer.h - * - * Copyright (C) 2004-2005 ARM Ltd. - * - * 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. - */ -#ifndef __ASM_ARM_LOCALTIMER_H -#define __ASM_ARM_LOCALTIMER_H - -#include <linux/errno.h> - -struct clock_event_device; - -struct local_timer_ops { - int (*setup)(struct clock_event_device *); - void (*stop)(struct clock_event_device *); -}; - -#ifdef CONFIG_LOCAL_TIMERS -/* - * Register a local timer driver - */ -int local_timer_register(struct local_timer_ops *); -#else -static inline int local_timer_register(struct local_timer_ops *ops) -{ - return -ENXIO; -} -#endif - -#endif diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 917d4fcfd9b..0406cb3f1af 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -8,17 +8,20 @@ * published by the Free Software Foundation. */ +#include <linux/types.h> + #ifndef __ASSEMBLY__ +#include <linux/reboot.h> struct tag; -struct meminfo; -struct sys_timer; struct pt_regs; struct smp_operations; #ifdef CONFIG_SMP #define smp_ops(ops) (&(ops)) +#define smp_init_ops(ops) (&(ops)) #else #define smp_ops(ops) (struct smp_operations *)NULL +#define smp_init_ops(ops) (bool (*)(void))NULL #endif struct machine_desc { @@ -31,7 +34,7 @@ struct machine_desc { unsigned int nr_irqs; /* number of IRQs */ #ifdef CONFIG_ZONE_DMA - unsigned long dma_zone_size; /* size of DMA-able area */ + phys_addr_t dma_zone_size; /* size of DMA-able area */ #endif unsigned int video_start; /* start of video RAM */ @@ -40,32 +43,37 @@ struct machine_desc { unsigned char reserve_lp0 :1; /* never has lp0 */ unsigned char reserve_lp1 :1; /* never has lp1 */ unsigned char reserve_lp2 :1; /* never has lp2 */ - char restart_mode; /* default restart mode */ + enum reboot_mode reboot_mode; /* default restart mode */ + unsigned l2c_aux_val; /* L2 cache aux value */ + unsigned l2c_aux_mask; /* L2 cache aux mask */ + void (*l2c_write_sec)(unsigned long, unsigned); struct smp_operations *smp; /* SMP operations */ - void (*fixup)(struct tag *, char **, - struct meminfo *); + bool (*smp_init)(void); + void (*fixup)(struct tag *, char **); + void (*dt_fixup)(void); + void (*init_meminfo)(void); void (*reserve)(void);/* reserve mem blocks */ void (*map_io)(void);/* IO mapping function */ void (*init_early)(void); void (*init_irq)(void); - struct sys_timer *timer; /* system tick timer */ + void (*init_time)(void); void (*init_machine)(void); void (*init_late)(void); #ifdef CONFIG_MULTI_IRQ_HANDLER void (*handle_irq)(struct pt_regs *); #endif - void (*restart)(char, const char *); + void (*restart)(enum reboot_mode, const char *); }; /* * Current machine - only accessible during boot. */ -extern struct machine_desc *machine_desc; +extern const struct machine_desc *machine_desc; /* * Machine type table - also only accessible during boot */ -extern struct machine_desc __arch_info_begin[], __arch_info_end[]; +extern const struct machine_desc __arch_info_begin[], __arch_info_end[]; #define for_each_machine_desc(p) \ for (p = __arch_info_begin; p < __arch_info_end; p++) diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h index 15cb035309f..2092ee1e130 100644 --- a/arch/arm/include/asm/mach/irq.h +++ b/arch/arm/include/asm/mach/irq.h @@ -20,10 +20,6 @@ struct seq_file; extern void init_FIQ(int); extern int show_fiq_list(struct seq_file *, int); -#ifdef CONFIG_MULTI_IRQ_HANDLER -extern void (*handle_arch_irq)(struct pt_regs *); -#endif - /* * This is for easy migration, but should be changed in the source */ @@ -34,35 +30,4 @@ do { \ raw_spin_unlock(&desc->lock); \ } while(0) -#ifndef __ASSEMBLY__ -/* - * Entry/exit functions for chained handlers where the primary IRQ chip - * may implement either fasteoi or level-trigger flow control. - */ -static inline void chained_irq_enter(struct irq_chip *chip, - struct irq_desc *desc) -{ - /* FastEOI controllers require no action on entry. */ - if (chip->irq_eoi) - return; - - if (chip->irq_mask_ack) { - chip->irq_mask_ack(&desc->irq_data); - } else { - chip->irq_mask(&desc->irq_data); - if (chip->irq_ack) - chip->irq_ack(&desc->irq_data); - } -} - -static inline void chained_irq_exit(struct irq_chip *chip, - struct irq_desc *desc) -{ - if (chip->irq_eoi) - chip->irq_eoi(&desc->irq_data); - else - chip->irq_unmask(&desc->irq_data); -} -#endif - #endif diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h index 2fe141fcc8d..f98c7f32c9c 100644 --- a/arch/arm/include/asm/mach/map.h +++ b/arch/arm/include/asm/mach/map.h @@ -22,18 +22,21 @@ struct map_desc { }; /* types 0-3 are defined in asm/io.h */ -#define MT_UNCACHED 4 -#define MT_CACHECLEAN 5 -#define MT_MINICLEAN 6 -#define MT_LOW_VECTORS 7 -#define MT_HIGH_VECTORS 8 -#define MT_MEMORY 9 -#define MT_ROM 10 -#define MT_MEMORY_NONCACHED 11 -#define MT_MEMORY_DTCM 12 -#define MT_MEMORY_ITCM 13 -#define MT_MEMORY_SO 14 -#define MT_MEMORY_DMA_READY 15 +enum { + MT_UNCACHED = 4, + MT_CACHECLEAN, + MT_MINICLEAN, + MT_LOW_VECTORS, + MT_HIGH_VECTORS, + MT_MEMORY_RWX, + MT_MEMORY_RW, + MT_ROM, + MT_MEMORY_RWX_NONCACHED, + MT_MEMORY_RW_DTCM, + MT_MEMORY_RWX_ITCM, + MT_MEMORY_RW_SO, + MT_MEMORY_DMA_READY, +}; #ifdef CONFIG_MMU extern void iotable_init(struct map_desc *, int); diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h index db9fedb57f2..7fc42784bec 100644 --- a/arch/arm/include/asm/mach/pci.h +++ b/arch/arm/include/asm/mach/pci.h @@ -16,6 +16,7 @@ struct pci_sys_data; struct pci_ops; struct pci_bus; +struct device; struct hw_pci { #ifdef CONFIG_PCI_DOMAINS @@ -23,12 +24,20 @@ struct hw_pci { #endif struct pci_ops *ops; int nr_controllers; + void **private_data; int (*setup)(int nr, struct pci_sys_data *); struct pci_bus *(*scan)(int nr, struct pci_sys_data *); void (*preinit)(void); void (*postinit)(void); u8 (*swizzle)(struct pci_dev *dev, u8 *pin); int (*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin); + resource_size_t (*align_resource)(struct pci_dev *dev, + const struct resource *res, + resource_size_t start, + resource_size_t size, + resource_size_t align); + void (*add_bus)(struct pci_bus *bus); + void (*remove_bus)(struct pci_bus *bus); }; /* @@ -50,13 +59,30 @@ struct pci_sys_data { u8 (*swizzle)(struct pci_dev *, u8 *); /* IRQ mapping */ int (*map_irq)(const struct pci_dev *, u8, u8); + /* Resource alignement requirements */ + resource_size_t (*align_resource)(struct pci_dev *dev, + const struct resource *res, + resource_size_t start, + resource_size_t size, + resource_size_t align); + void (*add_bus)(struct pci_bus *bus); + void (*remove_bus)(struct pci_bus *bus); void *private_data; /* platform controller private data */ }; /* * Call this with your hw_pci struct to initialise the PCI system. */ -void pci_common_init(struct hw_pci *); +void pci_common_init_dev(struct device *, struct hw_pci *); + +/* + * Compatibility wrapper for older platforms that do not care about + * passing the parent device. + */ +static inline void pci_common_init(struct hw_pci *hw) +{ + pci_common_init_dev(NULL, hw); +} /* * Setup early fixed I/O mapping. @@ -80,13 +106,4 @@ extern int dc21285_setup(int nr, struct pci_sys_data *); extern void dc21285_preinit(void); extern void dc21285_postinit(void); -extern struct pci_ops via82c505_ops; -extern int via82c505_setup(int nr, struct pci_sys_data *); -extern void via82c505_init(void *sysdata); - -extern struct pci_ops pci_v3_ops; -extern int pci_v3_setup(int nr, struct pci_sys_data *); -extern void pci_v3_preinit(void); -extern void pci_v3_postinit(void); - #endif /* __ASM_MACH_PCI_H */ diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h index 6ca945f534a..90c12e1e695 100644 --- a/arch/arm/include/asm/mach/time.h +++ b/arch/arm/include/asm/mach/time.h @@ -10,36 +10,6 @@ #ifndef __ASM_ARM_MACH_TIME_H #define __ASM_ARM_MACH_TIME_H -/* - * This is our kernel timer structure. - * - * - init - * Initialise the kernels jiffy timer source, claim interrupt - * using setup_irq. This is called early on during initialisation - * while interrupts are still disabled on the local CPU. - * - suspend - * Suspend the kernel jiffy timer source, if necessary. This - * is called with interrupts disabled, after all normal devices - * have been suspended. If no action is required, set this to - * NULL. - * - resume - * Resume the kernel jiffy timer source, if necessary. This - * is called with interrupts disabled before any normal devices - * are resumed. If no action is required, set this to NULL. - * - offset - * Return the timer offset in microseconds since the last timer - * interrupt. Note: this must take account of any unprocessed - * timer interrupt which may be pending. - */ -struct sys_timer { - void (*init)(void); - void (*suspend)(void); - void (*resume)(void); -#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET - unsigned long (*offset)(void); -#endif -}; - extern void timer_tick(void); struct timespec; diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h new file mode 100644 index 00000000000..94060adba17 --- /dev/null +++ b/arch/arm/include/asm/mcpm.h @@ -0,0 +1,259 @@ +/* + * arch/arm/include/asm/mcpm.h + * + * Created by: Nicolas Pitre, April 2012 + * Copyright: (C) 2012-2013 Linaro Limited + * + * 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. + */ + +#ifndef MCPM_H +#define MCPM_H + +/* + * Maximum number of possible clusters / CPUs per cluster. + * + * This should be sufficient for quite a while, while keeping the + * (assembly) code simpler. When this starts to grow then we'll have + * to consider dynamic allocation. + */ +#define MAX_CPUS_PER_CLUSTER 4 +#define MAX_NR_CLUSTERS 2 + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> +#include <asm/cacheflush.h> + +/* + * Platform specific code should use this symbol to set up secondary + * entry location for processors to use when released from reset. + */ +extern void mcpm_entry_point(void); + +/* + * This is used to indicate where the given CPU from given cluster should + * branch once it is ready to re-enter the kernel using ptr, or NULL if it + * should be gated. A gated CPU is held in a WFE loop until its vector + * becomes non NULL. + */ +void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr); + +/* + * This sets an early poke i.e a value to be poked into some address + * from very early assembly code before the CPU is ungated. The + * address must be physical, and if 0 then nothing will happen. + */ +void mcpm_set_early_poke(unsigned cpu, unsigned cluster, + unsigned long poke_phys_addr, unsigned long poke_val); + +/* + * CPU/cluster power operations API for higher subsystems to use. + */ + +/** + * mcpm_is_available - returns whether MCPM is initialized and available + * + * This returns true or false accordingly. + */ +bool mcpm_is_available(void); + +/** + * mcpm_cpu_power_up - make given CPU in given cluster runable + * + * @cpu: CPU number within given cluster + * @cluster: cluster number for the CPU + * + * The identified CPU is brought out of reset. If the cluster was powered + * down then it is brought up as well, taking care not to let the other CPUs + * in the cluster run, and ensuring appropriate cluster setup. + * + * Caller must ensure the appropriate entry vector is initialized with + * mcpm_set_entry_vector() prior to calling this. + * + * This must be called in a sleepable context. However, the implementation + * is strongly encouraged to return early and let the operation happen + * asynchronously, especially when significant delays are expected. + * + * If the operation cannot be performed then an error code is returned. + */ +int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster); + +/** + * mcpm_cpu_power_down - power the calling CPU down + * + * The calling CPU is powered down. + * + * If this CPU is found to be the "last man standing" in the cluster + * then the cluster is prepared for power-down too. + * + * This must be called with interrupts disabled. + * + * On success this does not return. Re-entry in the kernel is expected + * via mcpm_entry_point. + * + * This will return if mcpm_platform_register() has not been called + * previously in which case the caller should take appropriate action. + * + * On success, the CPU is not guaranteed to be truly halted until + * mcpm_wait_for_cpu_powerdown() subsequently returns non-zero for the + * specified cpu. Until then, other CPUs should make sure they do not + * trash memory the target CPU might be executing/accessing. + */ +void mcpm_cpu_power_down(void); + +/** + * mcpm_wait_for_cpu_powerdown - wait for a specified CPU to halt, and + * make sure it is powered off + * + * @cpu: CPU number within given cluster + * @cluster: cluster number for the CPU + * + * Call this function to ensure that a pending powerdown has taken + * effect and the CPU is safely parked before performing non-mcpm + * operations that may affect the CPU (such as kexec trashing the + * kernel text). + * + * It is *not* necessary to call this function if you only need to + * serialise a pending powerdown with mcpm_cpu_power_up() or a wakeup + * event. + * + * Do not call this function unless the specified CPU has already + * called mcpm_cpu_power_down() or has committed to doing so. + * + * @return: + * - zero if the CPU is in a safely parked state + * - nonzero otherwise (e.g., timeout) + */ +int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster); + +/** + * mcpm_cpu_suspend - bring the calling CPU in a suspended state + * + * @expected_residency: duration in microseconds the CPU is expected + * to remain suspended, or 0 if unknown/infinity. + * + * The calling CPU is suspended. The expected residency argument is used + * as a hint by the platform specific backend to implement the appropriate + * sleep state level according to the knowledge it has on wake-up latency + * for the given hardware. + * + * If this CPU is found to be the "last man standing" in the cluster + * then the cluster may be prepared for power-down too, if the expected + * residency makes it worthwhile. + * + * This must be called with interrupts disabled. + * + * On success this does not return. Re-entry in the kernel is expected + * via mcpm_entry_point. + * + * This will return if mcpm_platform_register() has not been called + * previously in which case the caller should take appropriate action. + */ +void mcpm_cpu_suspend(u64 expected_residency); + +/** + * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up + * + * This lets the platform specific backend code perform needed housekeeping + * work. This must be called by the newly activated CPU as soon as it is + * fully operational in kernel space, before it enables interrupts. + * + * If the operation cannot be performed then an error code is returned. + */ +int mcpm_cpu_powered_up(void); + +/* + * Platform specific methods used in the implementation of the above API. + */ +struct mcpm_platform_ops { + int (*power_up)(unsigned int cpu, unsigned int cluster); + void (*power_down)(void); + int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster); + void (*suspend)(u64); + void (*powered_up)(void); +}; + +/** + * mcpm_platform_register - register platform specific power methods + * + * @ops: mcpm_platform_ops structure to register + * + * An error is returned if the registration has been done previously. + */ +int __init mcpm_platform_register(const struct mcpm_platform_ops *ops); + +/* Synchronisation structures for coordinating safe cluster setup/teardown: */ + +/* + * When modifying this structure, make sure you update the MCPM_SYNC_ defines + * to match. + */ +struct mcpm_sync_struct { + /* individual CPU states */ + struct { + s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE); + } cpus[MAX_CPUS_PER_CLUSTER]; + + /* cluster state */ + s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE); + + /* inbound-side state */ + s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE); +}; + +struct sync_struct { + struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS]; +}; + +void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster); +void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster); +void __mcpm_outbound_leave_critical(unsigned int cluster, int state); +bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster); +int __mcpm_cluster_state(unsigned int cluster); + +int __init mcpm_sync_init( + void (*power_up_setup)(unsigned int affinity_level)); + +void __init mcpm_smp_set_ops(void); + +#else + +/* + * asm-offsets.h causes trouble when included in .c files, and cacheflush.h + * cannot be included in asm files. Let's work around the conflict like this. + */ +#include <asm/asm-offsets.h> +#define __CACHE_WRITEBACK_GRANULE CACHE_WRITEBACK_GRANULE + +#endif /* ! __ASSEMBLY__ */ + +/* Definitions for mcpm_sync_struct */ +#define CPU_DOWN 0x11 +#define CPU_COMING_UP 0x12 +#define CPU_UP 0x13 +#define CPU_GOING_DOWN 0x14 + +#define CLUSTER_DOWN 0x21 +#define CLUSTER_UP 0x22 +#define CLUSTER_GOING_DOWN 0x23 + +#define INBOUND_NOT_COMING_UP 0x31 +#define INBOUND_COMING_UP 0x32 + +/* + * Offsets for the mcpm_sync_struct members, for use in asm. + * We don't want to make them global to the kernel via asm-offsets.c. + */ +#define MCPM_SYNC_CLUSTER_CPUS 0 +#define MCPM_SYNC_CPU_SIZE __CACHE_WRITEBACK_GRANULE +#define MCPM_SYNC_CLUSTER_CLUSTER \ + (MCPM_SYNC_CLUSTER_CPUS + MCPM_SYNC_CPU_SIZE * MAX_CPUS_PER_CLUSTER) +#define MCPM_SYNC_CLUSTER_INBOUND \ + (MCPM_SYNC_CLUSTER_CLUSTER + __CACHE_WRITEBACK_GRANULE) +#define MCPM_SYNC_CLUSTER_SIZE \ + (MCPM_SYNC_CLUSTER_INBOUND + __CACHE_WRITEBACK_GRANULE) + +#endif diff --git a/arch/arm/include/asm/memblock.h b/arch/arm/include/asm/memblock.h index 00ca5f92648..bf47a6c110a 100644 --- a/arch/arm/include/asm/memblock.h +++ b/arch/arm/include/asm/memblock.h @@ -1,11 +1,9 @@ #ifndef _ASM_ARM_MEMBLOCK_H #define _ASM_ARM_MEMBLOCK_H -struct meminfo; struct machine_desc; -extern void arm_memblock_init(struct meminfo *, struct machine_desc *); - +void arm_memblock_init(const struct machine_desc *); phys_addr_t arm_memblock_steal(phys_addr_t size, phys_addr_t align); #endif diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 73cf03aa981..2b751464d6f 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -18,6 +18,8 @@ #include <linux/types.h> #include <linux/sizes.h> +#include <asm/cache.h> + #ifdef CONFIG_NEED_MACH_MEMORY_H #include <mach/memory.h> #endif @@ -28,31 +30,32 @@ */ #define UL(x) _AC(x, UL) +/* PAGE_OFFSET - the virtual address of the start of the kernel image */ +#define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) + #ifdef CONFIG_MMU /* - * PAGE_OFFSET - the virtual address of the start of the kernel image * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area */ -#define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) -#define TASK_SIZE (UL(CONFIG_PAGE_OFFSET) - UL(0x01000000)) -#define TASK_UNMAPPED_BASE (UL(CONFIG_PAGE_OFFSET) / 3) +#define TASK_SIZE (UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M)) +#define TASK_UNMAPPED_BASE ALIGN(TASK_SIZE / 3, SZ_16M) /* * The maximum size of a 26-bit user space task. */ -#define TASK_SIZE_26 UL(0x04000000) +#define TASK_SIZE_26 (UL(1) << 26) /* * The module space lives between the addresses given by TASK_SIZE * and PAGE_OFFSET - it must be within 32MB of the kernel text. */ #ifndef CONFIG_THUMB2_KERNEL -#define MODULES_VADDR (PAGE_OFFSET - 16*1024*1024) +#define MODULES_VADDR (PAGE_OFFSET - SZ_16M) #else /* smaller range for Thumb-2 symbols relocation (2^24)*/ -#define MODULES_VADDR (PAGE_OFFSET - 8*1024*1024) +#define MODULES_VADDR (PAGE_OFFSET - SZ_8M) #endif #if TASK_SIZE > MODULES_VADDR @@ -80,8 +83,6 @@ */ #define IOREMAP_MAX_ORDER 24 -#define CONSISTENT_END (0xffe00000UL) - #else /* CONFIG_MMU */ /* @@ -98,23 +99,15 @@ #define TASK_UNMAPPED_BASE UL(0x00000000) #endif -#ifndef PHYS_OFFSET -#define PHYS_OFFSET UL(CONFIG_DRAM_BASE) -#endif - #ifndef END_MEM #define END_MEM (UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE) #endif -#ifndef PAGE_OFFSET -#define PAGE_OFFSET (PHYS_OFFSET) -#endif - /* * The module can be at any place in ram in nommu mode. */ #define MODULES_END (END_MEM) -#define MODULES_VADDR (PHYS_OFFSET) +#define MODULES_VADDR PAGE_OFFSET #define XIP_VIRT_ADDR(physaddr) (physaddr) @@ -141,24 +134,66 @@ #define page_to_phys(page) (__pfn_to_phys(page_to_pfn(page))) #define phys_to_page(phys) (pfn_to_page(__phys_to_pfn(phys))) +/* + * Minimum guaranted alignment in pgd_alloc(). The page table pointers passed + * around in head.S and proc-*.S are shifted by this amount, in order to + * leave spare high bits for systems with physical address extension. This + * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but + * gives us about 38-bits or so. + */ +#ifdef CONFIG_ARM_LPAE +#define ARCH_PGD_SHIFT L1_CACHE_SHIFT +#else +#define ARCH_PGD_SHIFT 0 +#endif +#define ARCH_PGD_MASK ((1 << ARCH_PGD_SHIFT) - 1) + +/* + * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical + * memory. This is used for XIP and NoMMU kernels, or by kernels which + * have their own mach/memory.h. Assembly code must always use + * PLAT_PHYS_OFFSET and not PHYS_OFFSET. + */ +#ifndef PLAT_PHYS_OFFSET +#define PLAT_PHYS_OFFSET UL(CONFIG_PHYS_OFFSET) +#endif + #ifndef __ASSEMBLY__ /* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. + * + * PFNs are used to describe any physical page; this means + * PFN 0 == physical address 0. */ -#ifndef __virt_to_phys -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT +#if defined(__virt_to_phys) +#define PHYS_OFFSET PLAT_PHYS_OFFSET +#define PHYS_PFN_OFFSET ((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT)) + +#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) + +#elif defined(CONFIG_ARM_PATCH_PHYS_VIRT) /* * Constants used to force the right instruction encodings and shifts * so that all we need to do is modify the 8-bit constant field. */ #define __PV_BITS_31_24 0x81000000 +#define __PV_BITS_7_0 0x81 -extern unsigned long __pv_phys_offset; -#define PHYS_OFFSET __pv_phys_offset +extern unsigned long __pv_phys_pfn_offset; +extern u64 __pv_offset; +extern void fixup_pv_table(const void *, unsigned long); +extern const void *__pv_table_begin, *__pv_table_end; + +#define PHYS_OFFSET ((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT) +#define PHYS_PFN_OFFSET (__pv_phys_pfn_offset) + +#define virt_to_pfn(kaddr) \ + ((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \ + PHYS_PFN_OFFSET) #define __pv_stub(from,to,instr,type) \ __asm__("@ __pv_stub\n" \ @@ -169,45 +204,73 @@ extern unsigned long __pv_phys_offset; : "=r" (to) \ : "r" (from), "I" (type)) -static inline unsigned long __virt_to_phys(unsigned long x) +#define __pv_stub_mov_hi(t) \ + __asm__ volatile("@ __pv_stub_mov\n" \ + "1: mov %R0, %1\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 1b\n" \ + " .popsection\n" \ + : "=r" (t) \ + : "I" (__PV_BITS_7_0)) + +#define __pv_add_carry_stub(x, y) \ + __asm__ volatile("@ __pv_add_carry_stub\n" \ + "1: adds %Q0, %1, %2\n" \ + " adc %R0, %R0, #0\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 1b\n" \ + " .popsection\n" \ + : "+r" (y) \ + : "r" (x), "I" (__PV_BITS_31_24) \ + : "cc") + +static inline phys_addr_t __virt_to_phys(unsigned long x) { - unsigned long t; - __pv_stub(x, t, "add", __PV_BITS_31_24); + phys_addr_t t; + + if (sizeof(phys_addr_t) == 4) { + __pv_stub(x, t, "add", __PV_BITS_31_24); + } else { + __pv_stub_mov_hi(t); + __pv_add_carry_stub(x, t); + } return t; } -static inline unsigned long __phys_to_virt(unsigned long x) +static inline unsigned long __phys_to_virt(phys_addr_t x) { unsigned long t; - __pv_stub(x, t, "sub", __PV_BITS_31_24); + + /* + * 'unsigned long' cast discard upper word when + * phys_addr_t is 64 bit, and makes sure that inline + * assembler expression receives 32 bit argument + * in place where 'r' 32 bit operand is expected. + */ + __pv_stub((unsigned long) x, t, "sub", __PV_BITS_31_24); return t; } + #else -#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET) -#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET) -#endif -#endif -#endif /* __ASSEMBLY__ */ -#ifndef PHYS_OFFSET -#ifdef PLAT_PHYS_OFFSET #define PHYS_OFFSET PLAT_PHYS_OFFSET -#else -#define PHYS_OFFSET UL(CONFIG_PHYS_OFFSET) -#endif -#endif +#define PHYS_PFN_OFFSET ((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT)) -#ifndef __ASSEMBLY__ +static inline phys_addr_t __virt_to_phys(unsigned long x) +{ + return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET; +} -/* - * PFNs are used to describe any physical page; this means - * PFN 0 == physical address 0. - * - * This is the PFN of the first RAM page in the kernel - * direct-mapped view. We assume this is the first page - * of RAM in the mem_map as well. - */ -#define PHYS_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT) +static inline unsigned long __phys_to_virt(phys_addr_t x) +{ + return x - PHYS_OFFSET + PAGE_OFFSET; +} + +#define virt_to_pfn(kaddr) \ + ((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \ + PHYS_PFN_OFFSET) + +#endif /* * These are *only* valid on the kernel direct mapped RAM memory. @@ -222,16 +285,33 @@ static inline phys_addr_t virt_to_phys(const volatile void *x) static inline void *phys_to_virt(phys_addr_t x) { - return (void *)(__phys_to_virt((unsigned long)(x))); + return (void *)__phys_to_virt(x); } /* * Drivers should NOT use these either. */ #define __pa(x) __virt_to_phys((unsigned long)(x)) -#define __va(x) ((void *)__phys_to_virt((unsigned long)(x))) +#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) +extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x); + +/* + * These are for systems that have a hardware interconnect supported alias of + * physical memory for idmap purposes. Most cases should leave these + * untouched. + */ +static inline phys_addr_t __virt_to_idmap(unsigned long x) +{ + if (arch_virt_to_idmap) + return arch_virt_to_idmap(x); + else + return __virt_to_phys(x); +} + +#define virt_to_idmap(x) __virt_to_idmap((unsigned long)(x)) + /* * Virtual <-> DMA view memory address translations * Again, these are *only* valid on the kernel direct mapped RAM @@ -245,6 +325,7 @@ static inline void *phys_to_virt(phys_addr_t x) #define __bus_to_pfn(x) __phys_to_pfn(x) #endif +#ifdef CONFIG_VIRT_TO_BUS static inline __deprecated unsigned long virt_to_bus(void *x) { return __virt_to_bus((unsigned long)x); @@ -254,16 +335,11 @@ static inline __deprecated void *bus_to_virt(unsigned long x) { return (void *)__bus_to_virt(x); } +#endif /* * Conversion between a struct page and a physical address. * - * Note: when converting an unknown physical address to a - * struct page, the resulting pointer must be validated - * using VALID_PAGE(). It must return an invalid struct page - * for any physical address not corresponding to a system - * RAM address. - * * page_to_pfn(page) convert a struct page * to a PFN number * pfn_to_page(pfn) convert a _valid_ PFN number to struct page * * @@ -272,8 +348,9 @@ static inline __deprecated void *bus_to_virt(unsigned long x) */ #define ARCH_PFN_OFFSET PHYS_PFN_OFFSET -#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) +#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) +#define virt_addr_valid(kaddr) (((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) \ + && pfn_valid(virt_to_pfn(kaddr))) #endif diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index 9f77e7804f3..64fd15159b7 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -5,15 +5,18 @@ typedef struct { #ifdef CONFIG_CPU_HAS_ASID - u64 id; + atomic64_t id; +#else + int switch_pending; #endif - unsigned int vmalloc_seq; + unsigned int vmalloc_seq; + unsigned long sigpage; } mm_context_t; #ifdef CONFIG_CPU_HAS_ASID #define ASID_BITS 8 #define ASID_MASK ((~0ULL) << ASID_BITS) -#define ASID(mm) ((mm)->context.id & ~ASID_MASK) +#define ASID(mm) ((unsigned int)((mm)->context.id.counter & ~ASID_MASK)) #else #define ASID(mm) (0) #endif @@ -26,7 +29,7 @@ typedef struct { * modified for 2.6 by Hyok S. Choi <hyok.choi@samsung.com> */ typedef struct { - unsigned long end_brk; + unsigned long end_brk; } mm_context_t; #endif diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index e1f644bc7cc..9b32f76bb0d 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); @@ -25,7 +26,17 @@ void __check_vmalloc_seq(struct mm_struct *mm); #ifdef CONFIG_CPU_HAS_ASID void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk); -#define init_new_context(tsk,mm) ({ mm->context.id = 0; }) +#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) + +#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 */ @@ -45,7 +56,7 @@ static inline void check_and_switch_context(struct mm_struct *mm, * on non-ASID CPUs, the old mm will remain valid until the * finish_arch_post_lock_switch() call. */ - set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM); + mm->context.switch_pending = 1; else cpu_switch_mm(mm->pgd, mm); } @@ -54,9 +65,21 @@ static inline void check_and_switch_context(struct mm_struct *mm, finish_arch_post_lock_switch static inline void finish_arch_post_lock_switch(void) { - if (test_and_clear_thread_flag(TIF_SWITCH_MM)) { - struct mm_struct *mm = current->mm; - cpu_switch_mm(mm->pgd, mm); + struct mm_struct *mm = current->mm; + + if (mm && mm->context.switch_pending) { + /* + * Preemption must be disabled during cpu_switch_mm() as we + * have some stateful cache flush implementations. Check + * switch_pending again in case we were preempted and the + * switch to this mm was already done. + */ + preempt_disable(); + if (mm->context.switch_pending) { + mm->context.switch_pending = 0; + cpu_switch_mm(mm->pgd, mm); + } + preempt_enable_no_resched(); } } @@ -96,12 +119,16 @@ 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/module.h b/arch/arm/include/asm/module.h index 0d3a28dbc8e..ed690c49ef9 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -12,6 +12,8 @@ enum { ARM_SEC_CORE, ARM_SEC_EXIT, ARM_SEC_DEVEXIT, + ARM_SEC_HOT, + ARM_SEC_UNLIKELY, ARM_SEC_MAX, }; diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h new file mode 100644 index 00000000000..c3247cc2fe0 --- /dev/null +++ b/arch/arm/include/asm/mpu.h @@ -0,0 +1,76 @@ +#ifndef __ARM_MPU_H +#define __ARM_MPU_H + +#ifdef CONFIG_ARM_MPU + +/* MPUIR layout */ +#define MPUIR_nU 1 +#define MPUIR_DREGION 8 +#define MPUIR_IREGION 16 +#define MPUIR_DREGION_SZMASK (0xFF << MPUIR_DREGION) +#define MPUIR_IREGION_SZMASK (0xFF << MPUIR_IREGION) + +/* ID_MMFR0 data relevant to MPU */ +#define MMFR0_PMSA (0xF << 4) +#define MMFR0_PMSAv7 (3 << 4) + +/* MPU D/I Size Register fields */ +#define MPU_RSR_SZ 1 +#define MPU_RSR_EN 0 + +/* The D/I RSR value for an enabled region spanning the whole of memory */ +#define MPU_RSR_ALL_MEM 63 + +/* Individual bits in the DR/IR ACR */ +#define MPU_ACR_XN (1 << 12) +#define MPU_ACR_SHARED (1 << 2) + +/* C, B and TEX[2:0] bits only have semantic meanings when grouped */ +#define MPU_RGN_CACHEABLE 0xB +#define MPU_RGN_SHARED_CACHEABLE (MPU_RGN_CACHEABLE | MPU_ACR_SHARED) +#define MPU_RGN_STRONGLY_ORDERED 0 + +/* Main region should only be shared for SMP */ +#ifdef CONFIG_SMP +#define MPU_RGN_NORMAL (MPU_RGN_CACHEABLE | MPU_ACR_SHARED) +#else +#define MPU_RGN_NORMAL MPU_RGN_CACHEABLE +#endif + +/* Access permission bits of ACR (only define those that we use)*/ +#define MPU_AP_PL1RW_PL0RW (0x3 << 8) +#define MPU_AP_PL1RW_PL0R0 (0x2 << 8) +#define MPU_AP_PL1RW_PL0NA (0x1 << 8) + +/* For minimal static MPU region configurations */ +#define MPU_PROBE_REGION 0 +#define MPU_BG_REGION 1 +#define MPU_RAM_REGION 2 +#define MPU_VECTORS_REGION 3 + +/* Maximum number of regions Linux is interested in */ +#define MPU_MAX_REGIONS 16 + +#define MPU_DATA_SIDE 0 +#define MPU_INSTR_SIDE 1 + +#ifndef __ASSEMBLY__ + +struct mpu_rgn { + /* Assume same attributes for d/i-side */ + u32 drbar; + u32 drsr; + u32 dracr; +}; + +struct mpu_rgn_info { + u32 mpuir; + struct mpu_rgn rgns[MPU_MAX_REGIONS]; +}; +extern struct mpu_rgn_info mpu_rgn_info; + +#endif /* __ASSEMBLY__ */ + +#endif /* CONFIG_ARM_MPU */ + +#endif diff --git a/arch/arm/include/asm/neon.h b/arch/arm/include/asm/neon.h new file mode 100644 index 00000000000..8f730fe7009 --- /dev/null +++ b/arch/arm/include/asm/neon.h @@ -0,0 +1,36 @@ +/* + * linux/arch/arm/include/asm/neon.h + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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 <asm/hwcap.h> + +#define cpu_has_neon() (!!(elf_hwcap & HWCAP_NEON)) + +#ifdef __ARM_NEON__ + +/* + * If you are affected by the BUILD_BUG below, it probably means that you are + * using NEON code /and/ calling the kernel_neon_begin() function from the same + * compilation unit. To prevent issues that may arise from GCC reordering or + * generating(1) NEON instructions outside of these begin/end functions, the + * only supported way of using NEON code in the kernel is by isolating it in a + * separate compilation unit, and calling it from another unit from inside a + * kernel_neon_begin/kernel_neon_end pair. + * + * (1) Current GCC (4.7) might generate NEON instructions at O3 level if + * -mpfu=neon is set. + */ + +#define kernel_neon_begin() \ + BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code") + +#else +void kernel_neon_begin(void); +#endif +void kernel_neon_end(void); diff --git a/arch/arm/include/asm/opcodes-sec.h b/arch/arm/include/asm/opcodes-sec.h new file mode 100644 index 00000000000..bc3a9174417 --- /dev/null +++ b/arch/arm/include/asm/opcodes-sec.h @@ -0,0 +1,24 @@ +/* + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2012 ARM Limited + */ + +#ifndef __ASM_ARM_OPCODES_SEC_H +#define __ASM_ARM_OPCODES_SEC_H + +#include <asm/opcodes.h> + +#define __SMC(imm4) __inst_arm_thumb32( \ + 0xE1600070 | (((imm4) & 0xF) << 0), \ + 0xF7F08000 | (((imm4) & 0xF) << 16) \ +) + +#endif /* __ASM_ARM_OPCODES_SEC_H */ diff --git a/arch/arm/include/asm/opcodes.h b/arch/arm/include/asm/opcodes.h index 74e211a6fb2..e796c598513 100644 --- a/arch/arm/include/asm/opcodes.h +++ b/arch/arm/include/asm/opcodes.h @@ -10,6 +10,7 @@ #define __ASM_ARM_OPCODES_H #ifndef __ASSEMBLY__ +#include <linux/linkage.h> extern asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr); #endif diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h index 53426c66352..891a56b35bc 100644 --- a/arch/arm/include/asm/outercache.h +++ b/arch/arm/include/asm/outercache.h @@ -28,53 +28,84 @@ struct outer_cache_fns { void (*clean_range)(unsigned long, unsigned long); void (*flush_range)(unsigned long, unsigned long); void (*flush_all)(void); - void (*inv_all)(void); void (*disable)(void); #ifdef CONFIG_OUTER_CACHE_SYNC void (*sync)(void); #endif - void (*set_debug)(unsigned long); void (*resume)(void); -}; -#ifdef CONFIG_OUTER_CACHE + /* This is an ARM L2C thing */ + void (*write_sec)(unsigned long, unsigned); +}; extern struct outer_cache_fns outer_cache; +#ifdef CONFIG_OUTER_CACHE +/** + * outer_inv_range - invalidate range of outer cache lines + * @start: starting physical address, inclusive + * @end: end physical address, exclusive + */ static inline void outer_inv_range(phys_addr_t start, phys_addr_t end) { if (outer_cache.inv_range) outer_cache.inv_range(start, end); } + +/** + * outer_clean_range - clean dirty outer cache lines + * @start: starting physical address, inclusive + * @end: end physical address, exclusive + */ static inline void outer_clean_range(phys_addr_t start, phys_addr_t end) { if (outer_cache.clean_range) outer_cache.clean_range(start, end); } + +/** + * outer_flush_range - clean and invalidate outer cache lines + * @start: starting physical address, inclusive + * @end: end physical address, exclusive + */ static inline void outer_flush_range(phys_addr_t start, phys_addr_t end) { if (outer_cache.flush_range) outer_cache.flush_range(start, end); } +/** + * outer_flush_all - clean and invalidate all cache lines in the outer cache + * + * Note: depending on implementation, this may not be atomic - it must + * only be called with interrupts disabled and no other active outer + * cache masters. + * + * It is intended that this function is only used by implementations + * needing to override the outer_cache.disable() method due to security. + * (Some implementations perform this as a clean followed by an invalidate.) + */ static inline void outer_flush_all(void) { if (outer_cache.flush_all) outer_cache.flush_all(); } -static inline void outer_inv_all(void) -{ - if (outer_cache.inv_all) - outer_cache.inv_all(); -} - -static inline void outer_disable(void) -{ - if (outer_cache.disable) - outer_cache.disable(); -} +/** + * outer_disable - clean, invalidate and disable the outer cache + * + * Disable the outer cache, ensuring that any data contained in the outer + * cache is pushed out to lower levels of system memory. The note and + * conditions above concerning outer_flush_all() applies here. + */ +extern void outer_disable(void); +/** + * outer_resume - restore the cache configuration and re-enable outer cache + * + * Restore any configuration that the cache had when previously enabled, + * and re-enable the outer cache. + */ static inline void outer_resume(void) { if (outer_cache.resume) @@ -90,12 +121,18 @@ static inline void outer_clean_range(phys_addr_t start, phys_addr_t end) static inline void outer_flush_range(phys_addr_t start, phys_addr_t end) { } static inline void outer_flush_all(void) { } -static inline void outer_inv_all(void) { } static inline void outer_disable(void) { } +static inline void outer_resume(void) { } #endif #ifdef CONFIG_OUTER_CACHE_SYNC +/** + * outer_sync - perform a sync point for outer cache + * + * Ensure that all outer cache operations are complete and any store + * buffers are drained. + */ static inline void outer_sync(void) { if (outer_cache.sync) diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index 812a4944e78..4355f0ec44d 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -13,7 +13,7 @@ /* PAGE_SHIFT determines the page size */ #define PAGE_SHIFT 12 #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) #ifndef __ASSEMBLY__ @@ -142,7 +142,9 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from, #define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) extern void copy_page(void *to, const void *from); +#ifdef CONFIG_KUSER_HELPERS #define __HAVE_ARCH_GATE_AREA 1 +#endif #ifdef CONFIG_ARM_LPAE #include <asm/pgtable-3level-types.h> diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h index a98a2e112fa..7e95d8535e2 100644 --- a/arch/arm/include/asm/pci.h +++ b/arch/arm/include/asm/pci.h @@ -31,11 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus) } #endif /* CONFIG_PCI_DOMAINS */ -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - /* * The PCI address space does equal the physical memory address space. * The networking and block device layers use this boolean for bounce @@ -57,12 +52,9 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev, extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine); -/* - * Dummy implementation; always return 0. - */ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) { - return 0; + return channel ? 15 : 14; } #endif /* __KERNEL__ */ diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index 968c0a14e0a..209e6504922 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/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 943504f53f5..78a77936168 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -102,12 +102,14 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) #else pte = alloc_pages(PGALLOC_GFP, 0); #endif - if (pte) { - if (!PageHighMem(pte)) - clean_pte_table(page_address(pte)); - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!PageHighMem(pte)) + clean_pte_table(page_address(pte)); + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; } - return pte; } diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index f97ee02386e..219ac88a954 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -140,6 +140,7 @@ #define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ #define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ #define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ +#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */ #define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) #ifndef __ASSEMBLY__ @@ -160,6 +161,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) return (pmd_t *)pud; } +#define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) #define copy_pmd(pmdpd,pmdps) \ @@ -181,6 +183,13 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext) +/* + * We don't have huge page support for short descriptors, for the moment + * define empty stubs for use by pin_page_for_write. + */ +#define pmd_hugewillfault(pmd) (0) +#define pmd_thp_or_huge(pmd) (0) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_PGTABLE_2LEVEL_H */ diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h index d7952824c5c..626989fec4d 100644 --- a/arch/arm/include/asm/pgtable-3level-hwdef.h +++ b/arch/arm/include/asm/pgtable-3level-hwdef.h @@ -30,20 +30,28 @@ #define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) #define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0) #define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0) +#define PMD_TABLE_BIT (_AT(pmdval_t, 1) << 1) #define PMD_BIT4 (_AT(pmdval_t, 0)) #define PMD_DOMAIN(x) (_AT(pmdval_t, 0)) +#define PMD_APTABLE_SHIFT (61) +#define PMD_APTABLE (_AT(pgdval_t, 3) << PGD_APTABLE_SHIFT) +#define PMD_PXNTABLE (_AT(pgdval_t, 1) << 59) /* * - section */ #define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2) #define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3) +#define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */ +#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) #define PMD_SECT_AF (_AT(pmdval_t, 1) << 10) #define PMD_SECT_nG (_AT(pmdval_t, 1) << 11) +#define PMD_SECT_PXN (_AT(pmdval_t, 1) << 53) #define PMD_SECT_XN (_AT(pmdval_t, 1) << 54) #define PMD_SECT_AP_WRITE (_AT(pmdval_t, 0)) #define PMD_SECT_AP_READ (_AT(pmdval_t, 0)) +#define PMD_SECT_AP1 (_AT(pmdval_t, 1) << 6) #define PMD_SECT_TEX(x) (_AT(pmdval_t, 0)) /* @@ -61,6 +69,7 @@ #define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0) #define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0) #define PTE_TYPE_PAGE (_AT(pteval_t, 3) << 0) +#define PTE_TABLE_BIT (_AT(pteval_t, 1) << 1) #define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) /* AttrIndx[0] */ #define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) /* AttrIndx[1] */ #define PTE_EXT_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */ @@ -74,4 +83,24 @@ #define PHYS_MASK_SHIFT (40) #define PHYS_MASK ((1ULL << PHYS_MASK_SHIFT) - 1) +/* + * TTBR0/TTBR1 split (PAGE_OFFSET): + * 0x40000000: T0SZ = 2, T1SZ = 0 (not used) + * 0x80000000: T0SZ = 0, T1SZ = 1 + * 0xc0000000: T0SZ = 0, T1SZ = 2 + * + * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise + * booting secondary CPUs would end up using TTBR1 for the identity + * mapping set up in TTBR0. + */ +#if defined CONFIG_VMSPLIT_2G +#define TTBR1_OFFSET 16 /* skip two L1 entries */ +#elif defined CONFIG_VMSPLIT_3G +#define TTBR1_OFFSET (4096 * (1 + 3)) /* only L2, skip pgd + 3*pmd */ +#else +#define TTBR1_OFFSET 0 +#endif + +#define TTBR1_SIZE (((PAGE_OFFSET >> 30) - 1) << 16) + #endif diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a3f37929940..85c60adc8b6 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -33,7 +33,7 @@ #define PTRS_PER_PMD 512 #define PTRS_PER_PGD 4 -#define PTE_HWTABLE_PTRS (PTRS_PER_PTE) +#define PTE_HWTABLE_PTRS (0) #define PTE_HWTABLE_OFF (0) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64)) @@ -48,20 +48,28 @@ #define PMD_SHIFT 21 #define PMD_SIZE (1UL << PMD_SHIFT) -#define PMD_MASK (~(PMD_SIZE-1)) +#define PMD_MASK (~((1 << PMD_SHIFT) - 1)) #define PGDIR_SIZE (1UL << PGDIR_SHIFT) -#define PGDIR_MASK (~(PGDIR_SIZE-1)) +#define PGDIR_MASK (~((1 << PGDIR_SHIFT) - 1)) /* * section address mask and size definitions. */ #define SECTION_SHIFT 21 #define SECTION_SIZE (1UL << SECTION_SHIFT) -#define SECTION_MASK (~(SECTION_SIZE-1)) +#define SECTION_MASK (~((1 << SECTION_SHIFT) - 1)) #define USER_PTRS_PER_PGD (PAGE_OFFSET / PGDIR_SIZE) /* + * Hugetlb definitions. + */ +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +/* * "Linux" PTE definitions for LPAE. * * These bits overlap with the hardware bits but the naming is preserved for @@ -79,6 +87,11 @@ #define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56) /* unused */ #define L_PTE_NONE (_AT(pteval_t, 1) << 57) /* PROT_NONE */ +#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) +#define PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55) +#define PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56) +#define PMD_SECT_NONE (_AT(pmdval_t, 1) << 57) + /* * To be used in assembly code with the upper page attributes. */ @@ -104,11 +117,35 @@ */ #define L_PGD_SWAPPER (_AT(pgdval_t, 1) << 55) /* swapper_pg_dir entry */ +/* + * 2nd stage PTE definitions for LPAE. + */ +#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x0) << 2) /* strongly ordered */ +#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* normal inner write-through */ +#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* normal inner write-back */ +#define L_PTE_S2_MT_DEV_SHARED (_AT(pteval_t, 0x1) << 2) /* device */ +#define L_PTE_S2_MT_MASK (_AT(pteval_t, 0xf) << 2) + +#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ + +#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ + +/* + * Hyp-mode PL2 PTE definitions for LPAE. + */ +#define L_PTE_HYP L_PTE_USER + #ifndef __ASSEMBLY__ #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!(pud_val(pud) & 2)) #define pud_present(pud) (pud_val(pud)) +#define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ + PMD_TYPE_TABLE) +#define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ + PMD_TYPE_SECT) +#define pmd_large(pmd) pmd_sect(pmd) #define pud_clear(pudp) \ do { \ @@ -148,8 +185,86 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) clean_pmd_entry(pmdp); \ } while (0) +/* + * For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes + * that are written to a page table but not for ptes created with mk_pte. + * + * In hugetlb_no_page, a new huge pte (new_pte) is generated and passed to + * hugetlb_cow, where it is compared with an entry in a page table. + * This comparison test fails erroneously leading ultimately to a memory leak. + * + * To correct this behaviour, we mask off PTE_EXT_NG for any pte that is + * present before running the comparison. + */ +#define __HAVE_ARCH_PTE_SAME +#define pte_same(pte_a,pte_b) ((pte_present(pte_a) ? pte_val(pte_a) & ~PTE_EXT_NG \ + : pte_val(pte_a)) \ + == (pte_present(pte_b) ? pte_val(pte_b) & ~PTE_EXT_NG \ + : pte_val(pte_b))) + #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext))) +#define pte_huge(pte) (pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT)) +#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) + +#define pmd_young(pmd) (pmd_val(pmd) & PMD_SECT_AF) + +#define __HAVE_ARCH_PMD_WRITE +#define pmd_write(pmd) (!(pmd_val(pmd) & PMD_SECT_RDONLY)) + +#define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd)) +#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) +#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING) +#endif + +#define PMD_BIT_FUNC(fn,op) \ +static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } + +PMD_BIT_FUNC(wrprotect, |= PMD_SECT_RDONLY); +PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF); +PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING); +PMD_BIT_FUNC(mkwrite, &= ~PMD_SECT_RDONLY); +PMD_BIT_FUNC(mkdirty, |= PMD_SECT_DIRTY); +PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); + +#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) + +#define pmd_pfn(pmd) (((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT) +#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) + +/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */ +#define pmd_mknotpresent(pmd) (__pmd(0)) + +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY | + PMD_SECT_VALID | PMD_SECT_NONE; + pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask); + return pmd; +} + +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + BUG_ON(addr >= TASK_SIZE); + + /* create a faulting entry if PROT_NONE protected */ + if (pmd_val(pmd) & PMD_SECT_NONE) + pmd_val(pmd) &= ~PMD_SECT_VALID; + + *pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG); + flush_pmd_entry(pmdp); +} + +static inline int has_transparent_hugepage(void) +{ + return 1; +} + #endif /* __ASSEMBLY__ */ #endif /* _ASM_PGTABLE_3LEVEL_H */ diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h index 7ec60d6075b..0642228ff78 100644 --- a/arch/arm/include/asm/pgtable-nommu.h +++ b/arch/arm/include/asm/pgtable-nommu.h @@ -79,8 +79,6 @@ extern unsigned int kobjsize(const void *objp); * No page table caches to initialise. */ #define pgtable_cache_init() do { } while (0) -#define io_remap_pfn_range remap_pfn_range - /* * All 32bit addresses are effectively valid for vmalloc... diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 9c82f988c0e..5478e5d6ad8 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -24,6 +24,9 @@ #include <asm/memory.h> #include <asm/pgtable-hwdef.h> + +#include <asm/tlbflush.h> + #ifdef CONFIG_ARM_LPAE #include <asm/pgtable-3level.h> #else @@ -58,7 +61,16 @@ extern void __pgd_error(const char *file, int line, pgd_t); * mapping to be mapped at. This is particularly important for * non-high vector CPUs. */ -#define FIRST_USER_ADDRESS PAGE_SIZE +#define FIRST_USER_ADDRESS (PAGE_SIZE * 2) + +/* + * Use TASK_SIZE as the ceiling argument for free_pgtables() and + * free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd + * page shared between user and kernel). + */ +#ifdef CONFIG_ARM_LPAE +#define USER_PGTABLES_CEILING TASK_SIZE +#endif /* * The pgprot_* and protection_map entries will be fixed up in runtime @@ -70,6 +82,9 @@ extern void __pgd_error(const char *file, int line, pgd_t); extern pgprot_t pgprot_user; extern pgprot_t pgprot_kernel; +extern pgprot_t pgprot_hyp_device; +extern pgprot_t pgprot_s2; +extern pgprot_t pgprot_s2_device; #define _MOD_PROT(p, b) __pgprot(pgprot_val(p) | (b)) @@ -82,6 +97,10 @@ extern pgprot_t pgprot_kernel; #define PAGE_READONLY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY) #define PAGE_KERNEL _MOD_PROT(pgprot_kernel, L_PTE_XN) #define PAGE_KERNEL_EXEC pgprot_kernel +#define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP) +#define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP) +#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY) +#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR) #define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE) #define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN) @@ -197,13 +216,16 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pte_none(pte) (!pte_val(pte)) #define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT) +#define pte_valid(pte) (pte_val(pte) & L_PTE_VALID) +#define pte_accessible(mm, pte) (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) #define pte_write(pte) (!(pte_val(pte) & L_PTE_RDONLY)) #define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY) #define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG) #define pte_exec(pte) (!(pte_val(pte) & L_PTE_XN)) #define pte_special(pte) (0) -#define pte_present_user(pte) (pte_present(pte) && (pte_val(pte) & L_PTE_USER)) +#define pte_valid_user(pte) \ + (pte_valid(pte) && (pte_val(pte) & L_PTE_USER) && pte_young(pte)) #if __LINUX_ARM_ARCH__ < 6 static inline void __sync_icache_dcache(pte_t pteval) @@ -218,7 +240,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, { unsigned long ext = 0; - if (addr < TASK_SIZE && pte_present_user(pteval)) { + if (addr < TASK_SIZE && pte_valid_user(pteval)) { __sync_icache_dcache(pteval); ext |= PTE_EXT_NG; } @@ -235,12 +257,15 @@ PTE_BIT_FUNC(mkclean, &= ~L_PTE_DIRTY); PTE_BIT_FUNC(mkdirty, |= L_PTE_DIRTY); PTE_BIT_FUNC(mkold, &= ~L_PTE_YOUNG); PTE_BIT_FUNC(mkyoung, |= L_PTE_YOUNG); +PTE_BIT_FUNC(mkexec, &= ~L_PTE_XN); +PTE_BIT_FUNC(mknexec, |= L_PTE_XN); static inline pte_t pte_mkspecial(pte_t pte) { return pte; } static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | L_PTE_NONE; + const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | + L_PTE_NONE | L_PTE_VALID; pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } @@ -301,13 +326,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -/* - * remap a physical page `pfn' of size `size' with page protection `prot' - * into virtual address `from' - */ -#define io_remap_pfn_range(vma,from,pfn,size,prot) \ - remap_pfn_range(vma, from, pfn, size, prot) - #define pgtable_cache_init() do { } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index f24edad26c7..ae1919be8f9 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -71,6 +71,8 @@ struct arm_pmu { void (*disable)(struct perf_event *event); int (*get_event_idx)(struct pmu_hw_events *hw_events, struct perf_event *event); + void (*clear_event_idx)(struct pmu_hw_events *hw_events, + struct perf_event *event); int (*set_event_filter)(struct hw_perf_event *evt, struct perf_event_attr *attr); u32 (*read_counter)(struct perf_event *event); diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h new file mode 100644 index 00000000000..806cfe622a9 --- /dev/null +++ b/arch/arm/include/asm/probes.h @@ -0,0 +1,43 @@ +/* + * arch/arm/include/asm/probes.h + * + * Original contents copied from arch/arm/include/asm/kprobes.h + * which contains the following notice... + * + * Copyright (C) 2006, 2007 Motorola Inc. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _ASM_PROBES_H +#define _ASM_PROBES_H + +typedef u32 probes_opcode_t; + +struct arch_probes_insn; +typedef void (probes_insn_handler_t)(probes_opcode_t, + struct arch_probes_insn *, + struct pt_regs *); +typedef unsigned long (probes_check_cc)(unsigned long); +typedef void (probes_insn_singlestep_t)(probes_opcode_t, + struct arch_probes_insn *, + struct pt_regs *); +typedef void (probes_insn_fn_t)(void); + +/* Architecture specific copy of original instruction. */ +struct arch_probes_insn { + probes_opcode_t *insn; + probes_insn_handler_t *insn_handler; + probes_check_cc *insn_check_cc; + probes_insn_singlestep_t *insn_singlestep; + probes_insn_fn_t *insn_fn; +}; + +#endif diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h index f3628fb3d2b..5324c1112f3 100644 --- a/arch/arm/include/asm/proc-fns.h +++ b/arch/arm/include/asm/proc-fns.h @@ -60,7 +60,7 @@ extern struct processor { /* * Set the page table */ - void (*switch_mm)(unsigned long pgd_phys, struct mm_struct *mm); + void (*switch_mm)(phys_addr_t pgd_phys, struct mm_struct *mm); /* * Set a possibly extended PTE. Non-extended PTEs should * ignore 'ext'. @@ -82,7 +82,7 @@ extern void cpu_proc_init(void); extern void cpu_proc_fin(void); extern int cpu_do_idle(void); extern void cpu_dcache_clean_area(void *, int); -extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); +extern void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm); #ifdef CONFIG_ARM_LPAE extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte); #else @@ -116,13 +116,25 @@ extern void cpu_resume(void); #define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm) #ifdef CONFIG_ARM_LPAE + +#define cpu_get_ttbr(nr) \ + ({ \ + u64 ttbr; \ + __asm__("mrrc p15, " #nr ", %Q0, %R0, c2" \ + : "=r" (ttbr)); \ + ttbr; \ + }) + +#define cpu_set_ttbr(nr, val) \ + do { \ + u64 ttbr = val; \ + __asm__("mcrr p15, " #nr ", %Q0, %R0, c2" \ + : : "r" (ttbr)); \ + } while (0) + #define cpu_get_pgd() \ ({ \ - unsigned long pg, pg2; \ - __asm__("mrrc p15, 0, %0, %1, c2" \ - : "=r" (pg), "=r" (pg2) \ - : \ - : "cc"); \ + u64 pg = cpu_get_ttbr(0); \ pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1); \ (pgd_t *)phys_to_virt(pg); \ }) @@ -137,6 +149,10 @@ extern void cpu_resume(void); }) #endif +#else /*!CONFIG_MMU */ + +#define cpu_switch_mm(pgd,mm) { } + #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 06e7d509eaa..c3d5fc124a0 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -22,6 +22,7 @@ #include <asm/hw_breakpoint.h> #include <asm/ptrace.h> #include <asm/types.h> +#include <asm/unified.h> #ifdef __KERNEL__ #define STACK_TOP ((current->personality & ADDR_LIMIT_32BIT) ? \ @@ -54,7 +55,6 @@ struct thread_struct { #define start_thread(regs,pc,sp) \ ({ \ - unsigned long *stack = (unsigned long *)sp; \ memset(regs->uregs, 0, sizeof(regs->uregs)); \ if (current->personality & ADDR_LIMIT_32BIT) \ regs->ARM_cpsr = USR_MODE; \ @@ -65,9 +65,6 @@ struct thread_struct { regs->ARM_cpsr |= PSR_ENDSTATE; \ regs->ARM_pc = pc & ~1; /* pc */ \ regs->ARM_sp = sp; /* sp */ \ - regs->ARM_r2 = stack[2]; /* r2 (envp) */ \ - regs->ARM_r1 = stack[1]; /* r1 (argv) */ \ - regs->ARM_r0 = stack[0]; /* r0 (argc) */ \ nommu_start_thread(regs); \ }) @@ -91,6 +88,17 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) task_pt_regs(tsk)->ARM_pc #define KSTK_ESP(tsk) task_pt_regs(tsk)->ARM_sp +#ifdef CONFIG_SMP +#define __ALT_SMP_ASM(smp, up) \ + "9998: " smp "\n" \ + " .pushsection \".alt.smp.init\", \"a\"\n" \ + " .long 9998b\n" \ + " " up "\n" \ + " .popsection\n" +#else +#define __ALT_SMP_ASM(smp, up) up +#endif + /* * Prefetching support - only ARMv5. */ @@ -101,17 +109,22 @@ static inline void prefetch(const void *ptr) { __asm__ __volatile__( "pld\t%a0" - : - : "p" (ptr) - : "cc"); + :: "p" (ptr)); } +#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP) #define ARCH_HAS_PREFETCHW -#define prefetchw(ptr) prefetch(ptr) - -#define ARCH_HAS_SPINLOCK_PREFETCH -#define spin_lock_prefetch(x) do { } while (0) - +static inline void prefetchw(const void *ptr) +{ + __asm__ __volatile__( + ".arch_extension mp\n" + __ALT_SMP_ASM( + WASM(pldw) "\t%a0", + WASM(pld) "\t%a0" + ) + :: "p" (ptr)); +} +#endif #endif #define HAVE_ARCH_PICK_MMAP_LAYOUT diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h index a219227c3e4..cd94ef2ef28 100644 --- a/arch/arm/include/asm/prom.h +++ b/arch/arm/include/asm/prom.h @@ -11,22 +11,18 @@ #ifndef __ASMARM_PROM_H #define __ASMARM_PROM_H -#define HAVE_ARCH_DEVTREE_FIXUPS - #ifdef CONFIG_OF -extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys); -extern void arm_dt_memblock_reserve(void); +extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys); extern void __init arm_dt_init_cpu_maps(void); #else /* CONFIG_OF */ -static inline struct machine_desc *setup_machine_fdt(unsigned int dt_phys) +static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys) { return NULL; } -static inline void arm_dt_memblock_reserve(void) { } static inline void arm_dt_init_cpu_maps(void) { } #endif /* CONFIG_OF */ diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h new file mode 100644 index 00000000000..c25ef3ec6d1 --- /dev/null +++ b/arch/arm/include/asm/psci.h @@ -0,0 +1,48 @@ +/* + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2012 ARM Limited + */ + +#ifndef __ASM_ARM_PSCI_H +#define __ASM_ARM_PSCI_H + +#define PSCI_POWER_STATE_TYPE_STANDBY 0 +#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 + +struct psci_power_state { + u16 id; + u8 type; + u8 affinity_level; +}; + +struct psci_operations { + int (*cpu_suspend)(struct psci_power_state state, + unsigned long entry_point); + int (*cpu_off)(struct psci_power_state state); + int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); + int (*migrate)(unsigned long cpuid); + int (*affinity_info)(unsigned long target_affinity, + unsigned long lowest_affinity_level); + int (*migrate_info_type)(void); +}; + +extern struct psci_operations psci_ops; +extern struct smp_operations psci_smp_ops; + +#ifdef CONFIG_ARM_PSCI +int psci_init(void); +bool psci_smp_available(void); +#else +static inline int psci_init(void) { return 0; } +static inline bool psci_smp_available(void) { return false; } +#endif + +#endif /* __ASM_ARM_PSCI_H */ diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h index 3d52ee1bfb3..c877654fe3b 100644 --- a/arch/arm/include/asm/ptrace.h +++ b/arch/arm/include/asm/ptrace.h @@ -27,9 +27,13 @@ struct pt_regs { #define thumb_mode(regs) (0) #endif +#ifndef CONFIG_CPU_V7M #define isa_mode(regs) \ - ((((regs)->ARM_cpsr & PSR_J_BIT) >> 23) | \ - (((regs)->ARM_cpsr & PSR_T_BIT) >> 5)) + ((((regs)->ARM_cpsr & PSR_J_BIT) >> (__ffs(PSR_J_BIT) - 1)) | \ + (((regs)->ARM_cpsr & PSR_T_BIT) >> (__ffs(PSR_T_BIT)))) +#else +#define isa_mode(regs) 1 /* Thumb */ +#endif #define processor_mode(regs) \ ((regs)->ARM_cpsr & MODE_MASK) @@ -45,6 +49,7 @@ struct pt_regs { */ static inline int valid_user_regs(struct pt_regs *regs) { +#ifndef CONFIG_CPU_V7M unsigned long mode = regs->ARM_cpsr & MODE_MASK; /* @@ -67,6 +72,9 @@ static inline int valid_user_regs(struct pt_regs *regs) regs->ARM_cpsr |= USR_MODE; return 0; +#else /* ifndef CONFIG_CPU_V7M */ + return 1; +#endif } static inline long regs_return_value(struct pt_regs *regs) @@ -76,6 +84,12 @@ static inline long regs_return_value(struct pt_regs *regs) #define instruction_pointer(regs) (regs)->ARM_pc +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + instruction_pointer(regs) = val; +} + #ifdef CONFIG_SMP extern unsigned long profile_pc(struct pt_regs *regs); #else diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h deleted file mode 100644 index e3f75726343..00000000000 --- a/arch/arm/include/asm/sched_clock.h +++ /dev/null @@ -1,14 +0,0 @@ -/* - * sched_clock.h: support for extending counters to full 64-bit ns counter - * - * 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. - */ -#ifndef ASM_SCHED_CLOCK -#define ASM_SCHED_CLOCK - -extern void sched_clock_postinit(void); -extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate); - -#endif diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index c50f0560950..e0adb9f1bf9 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -21,35 +21,7 @@ #define __tagtable(tag, fn) \ static const struct tagtable __tagtable_##fn __tag = { tag, fn } -/* - * Memory map description - */ -#define NR_BANKS CONFIG_ARM_NR_BANKS - -struct membank { - phys_addr_t start; - phys_addr_t size; - unsigned int highmem; -}; - -struct meminfo { - int nr_banks; - struct membank bank[NR_BANKS]; -}; - -extern struct meminfo meminfo; - -#define for_each_bank(iter,mi) \ - for (iter = 0; iter < (mi)->nr_banks; iter++) - -#define bank_pfn_start(bank) __phys_to_pfn((bank)->start) -#define bank_pfn_end(bank) __phys_to_pfn((bank)->start + (bank)->size) -#define bank_pfn_size(bank) ((bank)->size >> PAGE_SHIFT) -#define bank_phys_start(bank) (bank)->start -#define bank_phys_end(bank) ((bank)->start + (bank)->size) -#define bank_phys_size(bank) (bank)->size - -extern int arm_add_memory(phys_addr_t start, phys_addr_t size); +extern int arm_add_memory(u64 start, u64 size); extern void early_print(const char *str, ...); extern void dump_machine_table(void); diff --git a/arch/arm/include/asm/signal.h b/arch/arm/include/asm/signal.h index 9a0ea6ab988..c0eb412aff0 100644 --- a/arch/arm/include/asm/signal.h +++ b/arch/arm/include/asm/signal.h @@ -16,23 +16,7 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; -struct old_sigaction { - __sighandler_t sa_handler; - old_sigset_t sa_mask; - unsigned long sa_flags; - __sigrestore_t sa_restorer; -}; - -struct sigaction { - __sighandler_t sa_handler; - unsigned long sa_flags; - __sigrestore_t sa_restorer; - sigset_t sa_mask; /* mask last for extensibility */ -}; - -struct k_sigaction { - struct sigaction sa; -}; +#define __ARCH_HAS_SA_RESTORER #include <asm/sigcontext.h> #endif diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index d3a22bebe6c..2ec765c39ab 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -65,12 +65,16 @@ asmlinkage void secondary_start_kernel(void); * Initial data for bringing up a secondary CPU. */ struct secondary_data { - unsigned long pgdir; + union { + unsigned long mpu_rgn_szr; + unsigned long pgdir; + }; unsigned long swapper_pg_dir; void *stack; }; extern struct secondary_data secondary_data; extern volatile int pen_release; +extern void secondary_startup(void); extern int __cpu_disable(void); @@ -81,6 +85,8 @@ extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask); +extern int register_ipi_completion(struct completion *completion, int cpu); + struct smp_operations { #ifdef CONFIG_SMP /* @@ -109,6 +115,15 @@ struct smp_operations { #endif }; +struct of_cpu_method { + const char *method; + struct smp_operations *ops; +}; + +#define CPU_METHOD_OF_DECLARE(name, _method, _ops) \ + static const struct of_cpu_method __cpu_method_of_table_##name \ + __used __section(__cpu_method_of_table) \ + = { .method = _method, .ops = _ops } /* * set platform specific SMP operations */ diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h index aaa61b6f50f..a252c0bfacf 100644 --- a/arch/arm/include/asm/smp_plat.h +++ b/arch/arm/include/asm/smp_plat.h @@ -26,6 +26,9 @@ static inline bool is_smp(void) } /* all SMP configurations have the extended CPUID registers */ +#ifndef CONFIG_MMU +#define tlb_ops_need_broadcast() 0 +#else static inline int tlb_ops_need_broadcast(void) { if (!is_smp()) @@ -33,6 +36,7 @@ static inline int tlb_ops_need_broadcast(void) return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2; } +#endif #if !defined(CONFIG_SMP) || __LINUX_ARM_ARCH__ >= 7 #define cache_ops_need_broadcast() 0 @@ -49,7 +53,7 @@ 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] @@ -66,4 +70,25 @@ static inline int get_logical_index(u32 mpidr) return -EINVAL; } +/* + * NOTE ! Assembly code relies on the following + * structure memory layout in order to carry out load + * multiple from its base address. For more + * information check arch/arm/kernel/sleep.S + */ +struct mpidr_hash { + u32 mask; /* used by sleep.S */ + u32 shift_aff[3]; /* used by sleep.S */ + u32 bits; +}; + +extern struct mpidr_hash mpidr_hash; + +static inline u32 mpidr_hash_size(void) +{ + return 1 << mpidr_hash.bits; +} + +extern int platform_can_cpu_hotplug(void); + #endif diff --git a/arch/arm/include/asm/smp_scu.h b/arch/arm/include/asm/smp_scu.h index 4eb6d005ffa..0393fbab8dd 100644 --- a/arch/arm/include/asm/smp_scu.h +++ b/arch/arm/include/asm/smp_scu.h @@ -6,9 +6,43 @@ #define SCU_PM_POWEROFF 3 #ifndef __ASSEMBLER__ + +#include <asm/cputype.h> + +static inline bool scu_a9_has_base(void) +{ + return read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9; +} + +static inline unsigned long scu_a9_get_base(void) +{ + unsigned long pa; + + asm("mrc p15, 4, %0, c15, c0, 0" : "=r" (pa)); + + return pa; +} + +#ifdef CONFIG_HAVE_ARM_SCU unsigned int scu_get_core_count(void __iomem *); -void scu_enable(void __iomem *); int scu_power_mode(void __iomem *, unsigned int); +#else +static inline unsigned int scu_get_core_count(void __iomem *scu_base) +{ + return 0; +} +static inline int scu_power_mode(void __iomem *scu_base, unsigned int mode) +{ + return -EINVAL; +} +#endif + +#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_ARM_SCU) +void scu_enable(void __iomem *scu_base); +#else +static inline void scu_enable(void __iomem *scu_base) {} +#endif + #endif #endif diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h index 0f01f4677bd..7b2899c2f7f 100644 --- a/arch/arm/include/asm/smp_twd.h +++ b/arch/arm/include/asm/smp_twd.h @@ -34,12 +34,4 @@ struct twd_local_timer name __initdata = { \ int twd_local_timer_register(struct twd_local_timer *); -#ifdef CONFIG_HAVE_ARM_TWD -void twd_local_timer_of_register(void); -#else -static inline void twd_local_timer_of_register(void) -{ -} -#endif - #endif diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index b4ca707d0a6..ac4bfae2670 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -5,21 +5,13 @@ #error SMP not supported on pre-ARMv6 CPUs #endif -#include <asm/processor.h> +#include <linux/prefetch.h> /* * sev and wfe are ARMv6K extensions. Uniprocessor ARMv6 may not have the K * extensions, so when running on UP, we have to patch these instructions away. */ -#define ALT_SMP(smp, up) \ - "9998: " smp "\n" \ - " .pushsection \".alt.smp.init\", \"a\"\n" \ - " .long 9998b\n" \ - " " up "\n" \ - " .popsection\n" - #ifdef CONFIG_THUMB2_KERNEL -#define SEV ALT_SMP("sev.w", "nop.w") /* * For Thumb-2, special care is needed to ensure that the conditional WFE * instruction really does assemble to exactly 4 bytes (as required by @@ -31,31 +23,23 @@ * the assembler won't change IT instructions which are explicitly present * in the input. */ -#define WFE(cond) ALT_SMP( \ +#define WFE(cond) __ALT_SMP_ASM( \ "it " cond "\n\t" \ "wfe" cond ".n", \ \ "nop.w" \ ) #else -#define SEV ALT_SMP("sev", "nop") -#define WFE(cond) ALT_SMP("wfe" cond, "nop") +#define WFE(cond) __ALT_SMP_ASM("wfe" cond, "nop") #endif +#define SEV __ALT_SMP_ASM(WASM(sev), WASM(nop)) + static inline void dsb_sev(void) { -#if __LINUX_ARM_ARCH__ >= 7 - __asm__ __volatile__ ( - "dsb\n" - SEV - ); -#else - __asm__ __volatile__ ( - "mcr p15, 0, %0, c7, c10, 4\n" - SEV - : : "r" (0) - ); -#endif + + dsb(ishst); + __asm__(SEV); } /* @@ -77,6 +61,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) u32 newval; arch_spinlock_t lockval; + prefetchw(&lock->slock); __asm__ __volatile__( "1: ldrex %0, [%3]\n" " add %1, %0, %4\n" @@ -97,19 +82,23 @@ 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) { + prefetchw(&lock->slock); + 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 { @@ -119,29 +108,19 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) static inline void arch_spin_unlock(arch_spinlock_t *lock) { - unsigned long tmp; - u32 slock; - smp_mb(); - - __asm__ __volatile__( -" mov %1, #1\n" -"1: ldrex %0, [%2]\n" -" uadd16 %0, %0, %1\n" -" strex %1, %0, [%2]\n" -" teq %1, #0\n" -" bne 1b" - : "=&r" (slock), "=&r" (tmp) - : "r" (&lock->slock) - : "cc"); - + lock->tickets.owner++; dsb_sev(); } +static inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.tickets.owner == lock.tickets.next; +} + static inline int arch_spin_is_locked(arch_spinlock_t *lock) { - struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets); - return tickets.owner != tickets.next; + return !arch_spin_value_unlocked(ACCESS_ONCE(*lock)); } static inline int arch_spin_is_contended(arch_spinlock_t *lock) @@ -163,6 +142,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw) { unsigned long tmp; + prefetchw(&rw->lock); __asm__ __volatile__( "1: ldrex %0, [%1]\n" " teq %0, #0\n" @@ -179,17 +159,21 @@ static inline void arch_write_lock(arch_rwlock_t *rw) static inline int arch_write_trylock(arch_rwlock_t *rw) { - unsigned long tmp; - - __asm__ __volatile__( -" ldrex %0, [%1]\n" -" teq %0, #0\n" -" strexeq %0, %2, [%1]" - : "=&r" (tmp) - : "r" (&rw->lock), "r" (0x80000000) - : "cc"); - - if (tmp == 0) { + unsigned long contended, res; + + prefetchw(&rw->lock); + do { + __asm__ __volatile__( + " ldrex %0, [%2]\n" + " mov %1, #0\n" + " teq %0, #0\n" + " strexeq %1, %3, [%2]" + : "=&r" (contended), "=&r" (res) + : "r" (&rw->lock), "r" (0x80000000) + : "cc"); + } while (res); + + if (!contended) { smp_mb(); return 1; } else { @@ -211,7 +195,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) } /* write_can_lock - would write_trylock() succeed? */ -#define arch_write_can_lock(x) ((x)->lock == 0) +#define arch_write_can_lock(x) (ACCESS_ONCE((x)->lock) == 0) /* * Read locks are a bit more hairy: @@ -229,6 +213,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw) { unsigned long tmp, tmp2; + prefetchw(&rw->lock); __asm__ __volatile__( "1: ldrex %0, [%2]\n" " adds %0, %0, #1\n" @@ -249,6 +234,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) smp_mb(); + prefetchw(&rw->lock); __asm__ __volatile__( "1: ldrex %0, [%2]\n" " sub %0, %0, #1\n" @@ -265,22 +251,31 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) static inline int arch_read_trylock(arch_rwlock_t *rw) { - unsigned long tmp, tmp2 = 1; - - __asm__ __volatile__( -" ldrex %0, [%2]\n" -" adds %0, %0, #1\n" -" strexpl %1, %0, [%2]\n" - : "=&r" (tmp), "+r" (tmp2) - : "r" (&rw->lock) - : "cc"); - - smp_mb(); - return tmp2 == 0; + unsigned long contended, res; + + prefetchw(&rw->lock); + do { + __asm__ __volatile__( + " ldrex %0, [%2]\n" + " mov %1, #0\n" + " adds %0, %0, #1\n" + " strexpl %1, %0, [%2]" + : "=&r" (contended), "=&r" (res) + : "r" (&rw->lock) + : "cc"); + } while (res); + + /* If the lock is negative, then it is already held for write. */ + if (contended < 0x80000000) { + smp_mb(); + return 1; + } else { + return 0; + } } /* read_can_lock - would read_trylock() succeed? */ -#define arch_read_can_lock(x) ((x)->lock < 0x80000000) +#define arch_read_can_lock(x) (ACCESS_ONCE((x)->lock) < 0x80000000) #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h index b262d2f8b47..47663fcb10a 100644 --- a/arch/arm/include/asm/spinlock_types.h +++ b/arch/arm/include/asm/spinlock_types.h @@ -25,7 +25,7 @@ typedef struct { #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } typedef struct { - volatile unsigned int lock; + u32 lock; } arch_rwlock_t; #define __ARCH_RW_LOCK_UNLOCKED { 0 } diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h index 1c0a551ae37..cd20029bcd9 100644 --- a/arch/arm/include/asm/suspend.h +++ b/arch/arm/include/asm/suspend.h @@ -1,6 +1,11 @@ #ifndef __ASM_ARM_SUSPEND_H #define __ASM_ARM_SUSPEND_H +struct sleep_save_sp { + u32 *save_ptr_stash; + u32 save_ptr_stash_phys; +}; + extern void cpu_resume(void); extern int cpu_suspend(unsigned long, int (*)(unsigned long)); diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h index fa09e6b49bf..c99e259469f 100644 --- a/arch/arm/include/asm/switch_to.h +++ b/arch/arm/include/asm/switch_to.h @@ -4,6 +4,16 @@ #include <linux/thread_info.h> /* + * For v7 SMP cores running a preemptible kernel we may be pre-empted + * during a TLB maintenance operation, so execute an inner-shareable dsb + * to ensure that the maintenance completes in case we migrate to another + * CPU. + */ +#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7) +#define finish_arch_switch(prev) dsb(ish) +#endif + +/* * switch_to(prev, next) should switch from task `prev' to `next' * `prev' will never be the same as `next'. schedule() itself * contains the memory barrier to tell GCC not to cache `current'. diff --git a/arch/arm/include/asm/sync_bitops.h b/arch/arm/include/asm/sync_bitops.h index 63479eecbf7..9732b8e11e6 100644 --- a/arch/arm/include/asm/sync_bitops.h +++ b/arch/arm/include/asm/sync_bitops.h @@ -2,7 +2,6 @@ #define __ASM_SYNC_BITOPS_H__ #include <asm/bitops.h> -#include <asm/system.h> /* sync_bitops functions are equivalent to the SMP implementation of the * original functions, independently from CONFIG_SMP being defined. diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index f1d96d4e809..4651f6999b7 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -7,7 +7,7 @@ #ifndef _ASM_ARM_SYSCALL_H #define _ASM_ARM_SYSCALL_H -#include <linux/audit.h> /* for AUDIT_ARCH_* */ +#include <uapi/linux/audit.h> /* for AUDIT_ARCH_* */ #include <linux/elf.h> /* for ELF_EM */ #include <linux/err.h> #include <linux/sched.h> @@ -57,6 +57,9 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned int i, unsigned int n, unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; @@ -81,6 +84,9 @@ static inline void syscall_set_arguments(struct task_struct *task, unsigned int i, unsigned int n, const unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { pr_warning("%s called with max args %d, handling only %d\n", __func__, i + n, SYSCALL_MAX_ARGS); @@ -97,8 +103,7 @@ static inline void syscall_set_arguments(struct task_struct *task, memcpy(®s->ARM_r0 + i, args, n * sizeof(args[0])); } -static inline int syscall_get_arch(struct task_struct *task, - struct pt_regs *regs) +static inline int syscall_get_arch(void) { /* ARM tasks don't change audit architectures on the fly. */ return AUDIT_ARCH_ARM; diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h deleted file mode 100644 index 368165e33c1..00000000000 --- a/arch/arm/include/asm/system.h +++ /dev/null @@ -1,7 +0,0 @@ -/* FILE TO BE DELETED. DO NOT ADD STUFF HERE! */ -#include <asm/barrier.h> -#include <asm/compiler.h> -#include <asm/cmpxchg.h> -#include <asm/switch_to.h> -#include <asm/system_info.h> -#include <asm/system_misc.h> diff --git a/arch/arm/include/asm/system_info.h b/arch/arm/include/asm/system_info.h index dfd386d0c02..720ea0320a6 100644 --- a/arch/arm/include/asm/system_info.h +++ b/arch/arm/include/asm/system_info.h @@ -11,6 +11,7 @@ #define CPU_ARCH_ARMv5TEJ 7 #define CPU_ARCH_ARMv6 8 #define CPU_ARCH_ARMv7 9 +#define CPU_ARCH_ARMv7M 10 #ifndef __ASSEMBLY__ diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h index 5a85f148b60..a3d61ad984a 100644 --- a/arch/arm/include/asm/system_misc.h +++ b/arch/arm/include/asm/system_misc.h @@ -6,11 +6,12 @@ #include <linux/compiler.h> #include <linux/linkage.h> #include <linux/irqflags.h> +#include <linux/reboot.h> extern void cpu_init(void); void soft_restart(unsigned long); -extern void (*arm_pm_restart)(char str, const char *cmd); +extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); extern void (*arm_pm_idle)(void); #define UDBG_UNDEFINED (1 << 0) @@ -21,9 +22,6 @@ extern void (*arm_pm_idle)(void); extern unsigned int user_debug; -extern void disable_hlt(void); -extern void enable_hlt(void); - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_ARM_SYSTEM_MISC_H */ diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index cddda1f41f0..e4e4208a913 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -43,6 +43,16 @@ struct cpu_context_save { __u32 extra[2]; /* Xscale 'acc' register, etc */ }; +struct arm_restart_block { + union { + /* For user cache flushing */ + struct { + unsigned long start; + unsigned long end; + } cache; + }; +}; + /* * low level task data that entry.S needs immediate access to. * __switch_to() assumes cpu_context follows immediately after cpu_domain. @@ -58,7 +68,7 @@ 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 @@ -68,6 +78,7 @@ struct thread_info { unsigned long thumbee_state; /* ThumbEE Handler Base register */ #endif struct restart_block restart_block; + struct arm_restart_block arm_restart_block; }; #define INIT_THREAD_INFO(tsk) \ @@ -103,8 +114,14 @@ static inline struct thread_info *current_thread_info(void) ((unsigned long)(task_thread_info(tsk)->cpu_context.pc)) #define thread_saved_sp(tsk) \ ((unsigned long)(task_thread_info(tsk)->cpu_context.sp)) + +#ifndef CONFIG_THUMB2_KERNEL #define thread_saved_fp(tsk) \ ((unsigned long)(task_thread_info(tsk)->cpu_context.fp)) +#else +#define thread_saved_fp(tsk) \ + ((unsigned long)(task_thread_info(tsk)->cpu_context.r7)) +#endif extern void crunch_task_disable(struct thread_info *); extern void crunch_task_copy(struct thread_info *, void *); @@ -130,12 +147,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #endif /* - * We use bit 30 of the preempt_count to indicate that kernel - * preemption is occurring. See <asm/hardirq.h>. - */ -#define PREEMPT_ACTIVE 0x40000000 - -/* * thread information flags: * TIF_SYSCALL_TRACE - syscall trace active * TIF_SYSCAL_AUDIT - syscall auditing active @@ -148,18 +159,20 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_SIGPENDING 0 #define TIF_NEED_RESCHED 1 #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ +#define TIF_UPROBE 7 #define TIF_SYSCALL_TRACE 8 #define TIF_SYSCALL_AUDIT 9 #define TIF_SYSCALL_TRACEPOINT 10 #define TIF_SECCOMP 11 /* seccomp syscall filtering active */ +#define TIF_NOHZ 12 /* in adaptive nohz mode */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 20 -#define TIF_SWITCH_MM 22 /* deferred switch_mm */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) @@ -173,7 +186,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, /* * Change these and you break ASM code in entry-common.S */ -#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_RESUME) +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_UPROBE) #endif /* __KERNEL__ */ #endif /* __ASM_ARM_THREAD_INFO_H */ diff --git a/arch/arm/include/asm/timex.h b/arch/arm/include/asm/timex.h index 83f2aa83899..f6fcc67ef06 100644 --- a/arch/arm/include/asm/timex.h +++ b/arch/arm/include/asm/timex.h @@ -12,12 +12,6 @@ #ifndef _ASMARM_TIMEX_H #define _ASMARM_TIMEX_H -#ifdef CONFIG_ARCH_MULTIPLATFORM -#define CLOCK_TICK_RATE 1000000 -#else -#include <mach/timex.h> -#endif - typedef unsigned long cycles_t; #define get_cycles() ({ cycles_t c; read_current_timer(&c) ? 0 : c; }) diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index 99a19512ee2..f1a0dace3ef 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 /* @@ -55,6 +43,7 @@ struct mmu_gather { struct mm_struct *mm; unsigned int fullmm; struct vm_area_struct *vma; + unsigned long start, end; unsigned long range_start; unsigned long range_end; unsigned int nr; @@ -109,22 +98,32 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb) } } -static inline void tlb_flush_mmu(struct mmu_gather *tlb) +static inline void tlb_flush_mmu_tlbonly(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); - } +} + +static inline void tlb_flush_mmu_free(struct mmu_gather *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 tlb_flush_mmu(struct mmu_gather *tlb) +{ + tlb_flush_mmu_tlbonly(tlb); + tlb_flush_mmu_free(tlb); } static inline void -tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm) +tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) { tlb->mm = mm; - tlb->fullmm = fullmm; + tlb->fullmm = !(start | (end+1)); + tlb->start = start; + tlb->end = end; tlb->vma = NULL; tlb->max = ARRAY_SIZE(tlb->local); tlb->pages = tlb->local; @@ -178,11 +177,6 @@ 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; @@ -223,6 +217,12 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, #endif } +static inline void +tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) +{ + tlb_add_flush(tlb, addr); +} + #define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr) #define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr) #define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp) diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 6e924d3a77e..def9e570199 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -14,7 +14,6 @@ #include <asm/glue.h> -#define TLB_V3_PAGE (1 << 0) #define TLB_V4_U_PAGE (1 << 1) #define TLB_V4_D_PAGE (1 << 2) #define TLB_V4_I_PAGE (1 << 3) @@ -22,7 +21,6 @@ #define TLB_V6_D_PAGE (1 << 5) #define TLB_V6_I_PAGE (1 << 6) -#define TLB_V3_FULL (1 << 8) #define TLB_V4_U_FULL (1 << 9) #define TLB_V4_D_FULL (1 << 10) #define TLB_V4_I_FULL (1 << 11) @@ -34,10 +32,13 @@ #define TLB_V6_D_ASID (1 << 17) #define TLB_V6_I_ASID (1 << 18) +#define TLB_V6_BP (1 << 19) + /* Unified Inner Shareable TLB operations (ARMv7 MP extensions) */ -#define TLB_V7_UIS_PAGE (1 << 19) -#define TLB_V7_UIS_FULL (1 << 20) -#define TLB_V7_UIS_ASID (1 << 21) +#define TLB_V7_UIS_PAGE (1 << 20) +#define TLB_V7_UIS_FULL (1 << 21) +#define TLB_V7_UIS_ASID (1 << 22) +#define TLB_V7_UIS_BP (1 << 23) #define TLB_BARRIER (1 << 28) #define TLB_L2CLEAN_FR (1 << 29) /* Feroceon */ @@ -49,7 +50,6 @@ * ============= * * We have the following to choose from: - * v3 - ARMv3 * v4 - ARMv4 without write buffer * v4wb - ARMv4 with write buffer without I TLB flush entry instruction * v4wbi - ARMv4 with write buffer with I TLB flush entry instruction @@ -150,7 +150,8 @@ #define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ TLB_V6_I_FULL | TLB_V6_D_FULL | \ TLB_V6_I_PAGE | TLB_V6_D_PAGE | \ - TLB_V6_I_ASID | TLB_V6_D_ASID) + TLB_V6_I_ASID | TLB_V6_D_ASID | \ + TLB_V6_BP) #ifdef CONFIG_CPU_TLB_V6 # define v6wbi_possible_flags v6wbi_tlb_flags @@ -165,10 +166,12 @@ # define v6wbi_always_flags (-1UL) #endif -#define v7wbi_tlb_flags_smp (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ - TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID) +#define v7wbi_tlb_flags_smp (TLB_WB | TLB_BARRIER | \ + TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | \ + TLB_V7_UIS_ASID | TLB_V7_UIS_BP) #define v7wbi_tlb_flags_up (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ - TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID) + TLB_V6_U_FULL | TLB_V6_U_PAGE | \ + TLB_V6_U_ASID | TLB_V6_BP) #ifdef CONFIG_CPU_TLB_V7 @@ -316,72 +319,112 @@ extern struct cpu_tlb_fns cpu_tlb; #define tlb_op(f, regs, arg) __tlb_op(f, "p15, 0, %0, " regs, arg) #define tlb_l2_op(f, regs, arg) __tlb_op(f, "p15, 1, %0, " regs, arg) -static inline void local_flush_tlb_all(void) +static inline void __local_flush_tlb_all(void) { const int zero = 0; const unsigned int __tlb_flag = __cpu_tlb_flags; - if (tlb_flag(TLB_WB)) - dsb(); - - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero); - tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero); +} + +static inline void local_flush_tlb_all(void) +{ + const int zero = 0; + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_all(); + tlb_op(TLB_V7_UIS_FULL, "c8, c7, 0", zero); if (tlb_flag(TLB_BARRIER)) { - dsb(); + dsb(nsh); isb(); } } -static inline void local_flush_tlb_mm(struct mm_struct *mm) +static inline void __flush_tlb_all(void) { const int zero = 0; - const int asid = ASID(mm); const unsigned int __tlb_flag = __cpu_tlb_flags; if (tlb_flag(TLB_WB)) - dsb(); + dsb(ishst); + + __local_flush_tlb_all(); + tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero); - if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { - if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); + if (tlb_flag(TLB_BARRIER)) { + dsb(ish); + isb(); + } +} + +static inline void __local_flush_tlb_mm(struct mm_struct *mm) +{ + const int zero = 0; + const int asid = ASID(mm); + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { + if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) { tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero); } - put_cpu(); } tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid); tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid); tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid); +} + +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + const int asid = ASID(mm); + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_mm(mm); + tlb_op(TLB_V7_UIS_ASID, "c8, c7, 2", asid); + + if (tlb_flag(TLB_BARRIER)) + dsb(nsh); +} + +static inline void __flush_tlb_mm(struct mm_struct *mm) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_WB)) + dsb(ishst); + + __local_flush_tlb_mm(mm); #ifdef CONFIG_ARM_ERRATA_720789 - tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero); + tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", 0); #else - tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid); + tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", ASID(mm)); #endif if (tlb_flag(TLB_BARRIER)) - dsb(); + dsb(ish); } static inline void -local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { const int zero = 0; const unsigned int __tlb_flag = __cpu_tlb_flags; uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm); - if (tlb_flag(TLB_WB)) - dsb(); - - if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && + if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { - tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr); @@ -392,6 +435,36 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr); +} + +static inline void +local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm); + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_page(vma, uaddr); + tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", uaddr); + + if (tlb_flag(TLB_BARRIER)) + dsb(nsh); +} + +static inline void +__flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm); + + if (tlb_flag(TLB_WB)) + dsb(ishst); + + __local_flush_tlb_page(vma, uaddr); #ifdef CONFIG_ARM_ERRATA_720789 tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK); #else @@ -399,20 +472,14 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) #endif if (tlb_flag(TLB_BARRIER)) - dsb(); + dsb(ish); } -static inline void local_flush_tlb_kernel_page(unsigned long kaddr) +static inline void __local_flush_tlb_kernel_page(unsigned long kaddr) { const int zero = 0; const unsigned int __tlb_flag = __cpu_tlb_flags; - kaddr &= PAGE_MASK; - - if (tlb_flag(TLB_WB)) - dsb(); - - tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr); @@ -422,15 +489,78 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr); +} + +static inline void local_flush_tlb_kernel_page(unsigned long kaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + kaddr &= PAGE_MASK; + + if (tlb_flag(TLB_WB)) + dsb(nshst); + + __local_flush_tlb_kernel_page(kaddr); + tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", kaddr); + + if (tlb_flag(TLB_BARRIER)) { + dsb(nsh); + isb(); + } +} + +static inline void __flush_tlb_kernel_page(unsigned long kaddr) +{ + const unsigned int __tlb_flag = __cpu_tlb_flags; + + kaddr &= PAGE_MASK; + + if (tlb_flag(TLB_WB)) + dsb(ishst); + + __local_flush_tlb_kernel_page(kaddr); tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr); if (tlb_flag(TLB_BARRIER)) { - dsb(); + dsb(ish); isb(); } } /* + * Branch predictor maintenance is paired with full TLB invalidation, so + * there is no need for any barriers here. + */ +static inline void __local_flush_bp_all(void) +{ + const int zero = 0; + const unsigned int __tlb_flag = __cpu_tlb_flags; + + if (tlb_flag(TLB_V6_BP)) + asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero)); +} + +static inline void local_flush_bp_all(void) +{ + const int zero = 0; + const unsigned int __tlb_flag = __cpu_tlb_flags; + + __local_flush_bp_all(); + if (tlb_flag(TLB_V7_UIS_BP)) + asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero)); +} + +static inline void __flush_bp_all(void) +{ + const int zero = 0; + const unsigned int __tlb_flag = __cpu_tlb_flags; + + __local_flush_bp_all(); + if (tlb_flag(TLB_V7_UIS_BP)) + asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero)); +} + +/* * flush_pmd_entry * * Flush a PMD entry (word aligned, or double-word aligned) to @@ -451,7 +581,7 @@ static inline void flush_pmd_entry(void *pmd) tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1 @ L2 flush_pmd", pmd); if (tlb_flag(TLB_WB)) - dsb(); + dsb(ishst); } static inline void clean_pmd_entry(void *pmd) @@ -480,6 +610,7 @@ static inline void clean_pmd_entry(void *pmd) #define flush_tlb_kernel_page local_flush_tlb_kernel_page #define flush_tlb_range local_flush_tlb_range #define flush_tlb_kernel_range local_flush_tlb_kernel_range +#define flush_bp_all local_flush_bp_all #else extern void flush_tlb_all(void); extern void flush_tlb_mm(struct mm_struct *mm); @@ -487,6 +618,7 @@ extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr); extern void flush_tlb_kernel_page(unsigned long kaddr); extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void flush_bp_all(void); #endif /* @@ -505,8 +637,50 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, } #endif +#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) + #endif -#endif /* CONFIG_MMU */ +#elif defined(CONFIG_SMP) /* !CONFIG_MMU */ + +#ifndef __ASSEMBLY__ + +#include <linux/mm_types.h> + +static inline void local_flush_tlb_all(void) { } +static inline void local_flush_tlb_mm(struct mm_struct *mm) { } +static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { } +static inline void local_flush_tlb_kernel_page(unsigned long kaddr) { } +static inline void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { } +static inline void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) { } +static inline void local_flush_bp_all(void) { } + +extern void flush_tlb_all(void); +extern void flush_tlb_mm(struct mm_struct *mm); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr); +extern void flush_tlb_kernel_page(unsigned long kaddr); +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void flush_bp_all(void); +#endif /* __ASSEMBLY__ */ + +#endif + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_ARM_ERRATA_798181 +extern void erratum_a15_798181_init(void); +#else +static inline void erratum_a15_798181_init(void) {} +#endif +extern bool (*erratum_a15_798181_handler)(void); + +static inline bool erratum_a15_798181(void) +{ + if (unlikely(IS_ENABLED(CONFIG_ARM_ERRATA_798181) && + erratum_a15_798181_handler)) + return erratum_a15_798181_handler(); + return false; +} +#endif #endif diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h index 73409e6c025..83259b87333 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 */ diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 58b8b84adcd..2fe85fff5cc 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -20,9 +20,6 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) #define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) -#define mc_capable() (cpu_topology[0].socket_id != -1) -#define smt_capable() (cpu_topology[0].thread_id != -1) - void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); diff --git a/arch/arm/include/asm/trusted_foundations.h b/arch/arm/include/asm/trusted_foundations.h new file mode 100644 index 00000000000..624e1d436c6 --- /dev/null +++ b/arch/arm/include/asm/trusted_foundations.h @@ -0,0 +1,74 @@ +/* + * Copyright (c) 2013, NVIDIA Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +/* + * Support for the Trusted Foundations secure monitor. + * + * Trusted Foundation comes active on some ARM consumer devices (most + * Tegra-based devices sold on the market are concerned). Such devices can only + * perform some basic operations, like setting the CPU reset vector, through + * SMC calls to the secure monitor. The calls are completely specific to + * Trusted Foundations, and do *not* follow the SMC calling convention or the + * PSCI standard. + */ + +#ifndef __ASM_ARM_TRUSTED_FOUNDATIONS_H +#define __ASM_ARM_TRUSTED_FOUNDATIONS_H + +#include <linux/kconfig.h> +#include <linux/printk.h> +#include <linux/bug.h> +#include <linux/of.h> +#include <linux/cpu.h> +#include <linux/smp.h> + +struct trusted_foundations_platform_data { + unsigned int version_major; + unsigned int version_minor; +}; + +#if IS_ENABLED(CONFIG_TRUSTED_FOUNDATIONS) + +void register_trusted_foundations(struct trusted_foundations_platform_data *pd); +void of_register_trusted_foundations(void); + +#else /* CONFIG_TRUSTED_FOUNDATIONS */ + +static inline void register_trusted_foundations( + struct trusted_foundations_platform_data *pd) +{ + /* + * If the system requires TF and we cannot provide it, continue booting + * but disable features that cannot be provided. + */ + pr_err("No support for Trusted Foundations, continuing in degraded mode.\n"); + pr_err("Secondary processors as well as CPU PM will be disabled.\n"); +#if IS_ENABLED(CONFIG_SMP) + setup_max_cpus = 0; +#endif + cpu_idle_poll_ctrl(true); +} + +static inline void of_register_trusted_foundations(void) +{ + /* + * If we find the target should enable TF but does not support it, + * fail as the system won't be able to do much anyway + */ + if (of_find_compatible_node(NULL, NULL, "tlm,trusted-foundations")) + register_trusted_foundations(NULL); +} +#endif /* CONFIG_TRUSTED_FOUNDATIONS */ + +#endif diff --git a/arch/arm/include/asm/types.h b/arch/arm/include/asm/types.h new file mode 100644 index 00000000000..a53cdb8f068 --- /dev/null +++ b/arch/arm/include/asm/types.h @@ -0,0 +1,40 @@ +#ifndef _ASM_TYPES_H +#define _ASM_TYPES_H + +#include <asm-generic/int-ll64.h> + +/* + * The C99 types uintXX_t that are usually defined in 'stdint.h' are not as + * unambiguous on ARM as you would expect. For the types below, there is a + * difference on ARM between GCC built for bare metal ARM, GCC built for glibc + * and the kernel itself, which results in build errors if you try to build with + * -ffreestanding and include 'stdint.h' (such as when you include 'arm_neon.h' + * in order to use NEON intrinsics) + * + * As the typedefs for these types in 'stdint.h' are based on builtin defines + * supplied by GCC, we can tweak these to align with the kernel's idea of those + * types, so 'linux/types.h' and 'stdint.h' can be safely included from the same + * source file (provided that -ffreestanding is used). + * + * int32_t uint32_t uintptr_t + * bare metal GCC long unsigned long unsigned int + * glibc GCC int unsigned int unsigned int + * kernel int unsigned int unsigned long + */ + +#ifdef __INT32_TYPE__ +#undef __INT32_TYPE__ +#define __INT32_TYPE__ int +#endif + +#ifdef __UINT32_TYPE__ +#undef __UINT32_TYPE__ +#define __UINT32_TYPE__ unsigned int +#endif + +#ifdef __UINTPTR_TYPE__ +#undef __UINTPTR_TYPE__ +#define __UINTPTR_TYPE__ unsigned long +#endif + +#endif /* _ASM_TYPES_H */ diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 7e1f76027f6..75d95799b6e 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -19,6 +19,13 @@ #include <asm/unified.h> #include <asm/compiler.h> +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS +#include <asm-generic/uaccess-unaligned.h> +#else +#define __get_user_unaligned __get_user +#define __put_user_unaligned __put_user +#endif + #define VERIFY_READ 0 #define VERIFY_WRITE 1 @@ -164,8 +171,9 @@ extern int __put_user_8(void *, unsigned long long); #define __put_user_check(x,p) \ ({ \ unsigned long __limit = current_thread_info()->addr_limit - 1; \ + const typeof(*(p)) __user *__tmp_p = (p); \ register const typeof(*(p)) __r2 asm("r2") = (x); \ - register const typeof(*(p)) __user *__p asm("r0") = (p);\ + register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \ register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ switch (sizeof(*(__p))) { \ diff --git a/arch/arm/include/asm/unified.h b/arch/arm/include/asm/unified.h index f5989f46b4d..b88beaba6b4 100644 --- a/arch/arm/include/asm/unified.h +++ b/arch/arm/include/asm/unified.h @@ -38,6 +38,8 @@ #ifdef __ASSEMBLY__ #define W(instr) instr.w #define BSYM(sym) sym + 1 +#else +#define WASM(instr) #instr ".w" #endif #else /* !CONFIG_THUMB2_KERNEL */ @@ -50,6 +52,8 @@ #ifdef __ASSEMBLY__ #define W(instr) instr #define BSYM(sym) sym +#else +#define WASM(instr) #instr #endif #endif /* CONFIG_THUMB2_KERNEL */ diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 21a2700d295..43876245fc5 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -15,7 +15,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls (380) +#define __NR_syscalls (384) #define __ARM_NR_cmpxchg (__ARM_NR_BASE+0x00fff0) #define __ARCH_WANT_STAT64 @@ -26,8 +26,6 @@ #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK -#define __ARCH_WANT_SYS_RT_SIGACTION -#define __ARCH_WANT_SYS_RT_SIGSUSPEND #define __ARCH_WANT_SYS_OLD_MMAP #define __ARCH_WANT_SYS_OLD_SELECT @@ -46,18 +44,9 @@ #define __ARCH_WANT_SYS_CLONE /* - * "Conditional" syscalls - * - * What we want is __attribute__((weak,alias("sys_ni_syscall"))), - * but it doesn't work on all toolchains, so we just do it by hand - */ -#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") - -/* * Unimplemented (or alternatively implemented) syscalls */ #define __IGNORE_fadvise64_64 #define __IGNORE_migrate_pages -#define __IGNORE_kcmp #endif /* __ASM_ARM_UNISTD_H */ diff --git a/arch/arm/include/asm/uprobes.h b/arch/arm/include/asm/uprobes.h new file mode 100644 index 00000000000..9472c20b7d4 --- /dev/null +++ b/arch/arm/include/asm/uprobes.h @@ -0,0 +1,45 @@ +/* + * Copyright (C) 2012 Rabin Vincent <rabin at rab.in> + * + * 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. + */ + +#ifndef _ASM_UPROBES_H +#define _ASM_UPROBES_H + +#include <asm/probes.h> +#include <asm/opcodes.h> + +typedef u32 uprobe_opcode_t; + +#define MAX_UINSN_BYTES 4 +#define UPROBE_XOL_SLOT_BYTES 64 + +#define UPROBE_SWBP_ARM_INSN 0xe7f001f9 +#define UPROBE_SS_ARM_INSN 0xe7f001fa +#define UPROBE_SWBP_INSN __opcode_to_mem_arm(UPROBE_SWBP_ARM_INSN) +#define UPROBE_SWBP_INSN_SIZE 4 + +struct arch_uprobe_task { + u32 backup; + unsigned long saved_trap_no; +}; + +struct arch_uprobe { + u8 insn[MAX_UINSN_BYTES]; + unsigned long ixol[2]; + uprobe_opcode_t bpinsn; + bool simulate; + u32 pcreg; + void (*prehandler)(struct arch_uprobe *auprobe, + struct arch_uprobe_task *autask, + struct pt_regs *regs); + void (*posthandler)(struct arch_uprobe *auprobe, + struct arch_uprobe_task *autask, + struct pt_regs *regs); + struct arch_probes_insn asi; +}; + +#endif diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h new file mode 100644 index 00000000000..615781c6162 --- /dev/null +++ b/arch/arm/include/asm/v7m.h @@ -0,0 +1,56 @@ +/* + * Common defines for v7m cpus + */ +#define V7M_SCS_ICTR IOMEM(0xe000e004) +#define V7M_SCS_ICTR_INTLINESNUM_MASK 0x0000000f + +#define BASEADDR_V7M_SCB IOMEM(0xe000ed00) + +#define V7M_SCB_CPUID 0x00 + +#define V7M_SCB_ICSR 0x04 +#define V7M_SCB_ICSR_PENDSVSET (1 << 28) +#define V7M_SCB_ICSR_PENDSVCLR (1 << 27) +#define V7M_SCB_ICSR_RETTOBASE (1 << 11) + +#define V7M_SCB_VTOR 0x08 + +#define V7M_SCB_AIRCR 0x0c +#define V7M_SCB_AIRCR_VECTKEY (0x05fa << 16) +#define V7M_SCB_AIRCR_SYSRESETREQ (1 << 2) + +#define V7M_SCB_SCR 0x10 +#define V7M_SCB_SCR_SLEEPDEEP (1 << 2) + +#define V7M_SCB_CCR 0x14 +#define V7M_SCB_CCR_STKALIGN (1 << 9) + +#define V7M_SCB_SHPR2 0x1c +#define V7M_SCB_SHPR3 0x20 + +#define V7M_SCB_SHCSR 0x24 +#define V7M_SCB_SHCSR_USGFAULTENA (1 << 18) +#define V7M_SCB_SHCSR_BUSFAULTENA (1 << 17) +#define V7M_SCB_SHCSR_MEMFAULTENA (1 << 16) + +#define V7M_xPSR_FRAMEPTRALIGN 0x00000200 +#define V7M_xPSR_EXCEPTIONNO 0x000001ff + +/* + * When branching to an address that has bits [31:28] == 0xf an exception return + * occurs. Bits [27:5] are reserved (SBOP). If the processor implements the FP + * extension Bit [4] defines if the exception frame has space allocated for FP + * state information, SBOP otherwise. Bit [3] defines the mode that is returned + * to (0 -> handler mode; 1 -> thread mode). Bit [2] defines which sp is used + * (0 -> msp; 1 -> psp). Bits [1:0] are fixed to 0b01. + */ +#define EXC_RET_STACK_MASK 0x00000004 +#define EXC_RET_THREADMODE_PROCESSSTACK 0xfffffffd + +#ifndef __ASSEMBLY__ + +enum reboot_mode; + +void armv7m_restart(enum reboot_mode mode, const char *cmd); + +#endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h index 86164df86cb..4371f45c578 100644 --- a/arch/arm/include/asm/virt.h +++ b/arch/arm/include/asm/virt.h @@ -24,11 +24,12 @@ /* * Flag indicating that the kernel was not entered in the same mode on every * CPU. The zImage loader stashes this value in an SPSR, so we need an - * architecturally defined flag bit here (the N flag, as it happens) + * architecturally defined flag bit here. */ -#define BOOT_CPU_MODE_MISMATCH (1<<31) +#define BOOT_CPU_MODE_MISMATCH PSR_N_BIT #ifndef __ASSEMBLY__ +#include <asm/cacheflush.h> #ifdef CONFIG_ARM_VIRT_EXT /* @@ -41,10 +42,21 @@ */ extern int __boot_cpu_mode; +static inline void sync_boot_mode(void) +{ + /* + * As secondaries write to __boot_cpu_mode with caches disabled, we + * must flush the corresponding cache entries to ensure the visibility + * of their writes. + */ + sync_cache_r(&__boot_cpu_mode); +} + void __hyp_set_vectors(unsigned long phys_vector_base); unsigned long __hyp_get_vectors(void); #else #define __boot_cpu_mode (SVC_MODE) +#define sync_boot_mode() #endif #ifndef ZIMAGE diff --git a/arch/arm/include/asm/word-at-a-time.h b/arch/arm/include/asm/word-at-a-time.h index 4d52f92967a..a6d0a29861e 100644 --- a/arch/arm/include/asm/word-at-a-time.h +++ b/arch/arm/include/asm/word-at-a-time.h @@ -48,10 +48,14 @@ static inline unsigned long find_zero(unsigned long mask) return ret; } -#ifdef CONFIG_DCACHE_WORD_ACCESS - #define zero_bytemask(mask) (mask) +#else /* __ARMEB__ */ +#include <asm-generic/word-at-a-time.h> +#endif + +#ifdef CONFIG_DCACHE_WORD_ACCESS + /* * Load an unaligned word from kernel space. * @@ -73,7 +77,11 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) " bic %2, %2, #0x3\n" " ldr %0, [%2]\n" " lsl %1, %1, #0x3\n" +#ifndef __ARMEB__ " lsr %0, %0, %1\n" +#else + " lsl %0, %0, %1\n" +#endif " b 2b\n" " .popsection\n" " .pushsection __ex_table,\"a\"\n" @@ -86,11 +94,5 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) return ret; } - #endif /* DCACHE_WORD_ACCESS */ - -#else /* __ARMEB__ */ -#include <asm-generic/word-at-a-time.h> -#endif - #endif /* __ASM_ARM_WORD_AT_A_TIME_H */ diff --git a/arch/arm/include/asm/xen/events.h b/arch/arm/include/asm/xen/events.h index 94b4e9020b0..8b1f37bfeee 100644 --- a/arch/arm/include/asm/xen/events.h +++ b/arch/arm/include/asm/xen/events.h @@ -2,6 +2,7 @@ #define _ASM_ARM_XEN_EVENTS_H #include <asm/ptrace.h> +#include <asm/atomic.h> enum ipi_vector { XEN_PLACEHOLDER_VECTOR, @@ -15,4 +16,8 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) return raw_irqs_disabled_flags(regs->ARM_cpsr); } +#define xchg_xen_ulong(ptr, val) atomic64_xchg(container_of((ptr), \ + atomic64_t, \ + counter), (val)) + #endif /* _ASM_ARM_XEN_EVENTS_H */ diff --git a/arch/arm/include/asm/xen/hypercall.h b/arch/arm/include/asm/xen/hypercall.h index 8a823253d77..712b50e0a6d 100644 --- a/arch/arm/include/asm/xen/hypercall.h +++ b/arch/arm/include/asm/xen/hypercall.h @@ -34,6 +34,7 @@ #define _ASM_ARM_XEN_HYPERCALL_H #include <xen/interface/xen.h> +#include <xen/interface/sched.h> long privcmd_call(unsigned call, unsigned long a1, unsigned long a2, unsigned long a3, @@ -46,6 +47,18 @@ int HYPERVISOR_event_channel_op(int cmd, void *arg); unsigned long HYPERVISOR_hvm_op(int op, void *arg); int HYPERVISOR_memory_op(unsigned int cmd, void *arg); int HYPERVISOR_physdev_op(int cmd, void *arg); +int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args); +int HYPERVISOR_tmem_op(void *arg); +int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr); + +static inline int +HYPERVISOR_suspend(unsigned long start_info_mfn) +{ + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; + + /* start_info_mfn is unused on ARM */ + return HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); +} static inline void MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, @@ -61,9 +74,4 @@ MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, BUG(); } -static inline int -HYPERVISOR_multicall(void *call_list, int nr_calls) -{ - BUG(); -} #endif /* _ASM_ARM_XEN_HYPERCALL_H */ diff --git a/arch/arm/include/asm/xen/hypervisor.h b/arch/arm/include/asm/xen/hypervisor.h index d7ab99a0c9e..1317ee40f4d 100644 --- a/arch/arm/include/asm/xen/hypervisor.h +++ b/arch/arm/include/asm/xen/hypervisor.h @@ -16,4 +16,6 @@ static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return PARAVIRT_LAZY_NONE; } +extern struct dma_map_ops *xen_dma_ops; + #endif /* _ASM_ARM_XEN_HYPERVISOR_H */ diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h index 1151188bcd8..50066006e6b 100644 --- a/arch/arm/include/asm/xen/interface.h +++ b/arch/arm/include/asm/xen/interface.h @@ -40,6 +40,8 @@ typedef uint64_t xen_pfn_t; #define PRI_xen_pfn "llx" typedef uint64_t xen_ulong_t; #define PRI_xen_ulong "llx" +typedef int64_t xen_long_t; +#define PRI_xen_long "llx" /* Guest handles for primitive C types. */ __DEFINE_GUEST_HANDLE(uchar, unsigned char); __DEFINE_GUEST_HANDLE(uint, unsigned int); diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h new file mode 100644 index 00000000000..1109017499e --- /dev/null +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -0,0 +1,50 @@ +#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H +#define _ASM_ARM_XEN_PAGE_COHERENT_H + +#include <asm/page.h> +#include <linux/dma-attrs.h> +#include <linux/dma-mapping.h> + +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) +{ + return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs); +} + +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + __generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs); +} + +static inline void xen_dma_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); +} + +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (__generic_dma_ops(hwdev)->unmap_page) + __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); +} + +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (__generic_dma_ops(hwdev)->sync_single_for_cpu) + __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); +} + +static inline void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (__generic_dma_ops(hwdev)->sync_single_for_device) + __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); +} +#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */ diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index c6b9096cef9..ded062f9b35 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -6,12 +6,12 @@ #include <linux/pfn.h> #include <linux/types.h> +#include <linux/dma-mapping.h> +#include <xen/xen.h> #include <xen/interface/grant_table.h> -#define pfn_to_mfn(pfn) (pfn) #define phys_to_machine_mapping_valid(pfn) (1) -#define mfn_to_pfn(mfn) (mfn) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) #define pte_mfn pte_pfn @@ -32,6 +32,38 @@ typedef struct xpaddr { #define INVALID_P2M_ENTRY (~0UL) +unsigned long __pfn_to_mfn(unsigned long pfn); +unsigned long __mfn_to_pfn(unsigned long mfn); +extern struct rb_root phys_to_mach; + +static inline unsigned long pfn_to_mfn(unsigned long pfn) +{ + unsigned long mfn; + + if (phys_to_mach.rb_node != NULL) { + mfn = __pfn_to_mfn(pfn); + if (mfn != INVALID_P2M_ENTRY) + return mfn; + } + + return pfn; +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (phys_to_mach.rb_node != NULL) { + pfn = __mfn_to_pfn(mfn); + if (pfn != INVALID_P2M_ENTRY) + return pfn; + } + + return mfn; +} + +#define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn) + static inline xmaddr_t phys_to_machine(xpaddr_t phys) { unsigned offset = phys.paddr & ~PAGE_MASK; @@ -45,7 +77,6 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) } /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) -#define virt_to_pfn(v) (PFN_DOWN(__pa(v))) #define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) @@ -65,25 +96,24 @@ static inline pte_t *lookup_address(unsigned long address, unsigned int *level) return NULL; } -static inline int m2p_add_override(unsigned long mfn, struct page *page, - struct gnttab_map_grant_ref *kmap_op) -{ - return 0; -} +extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); -static inline int m2p_remove_override(struct page *page, bool clear_pte) -{ - return 0; -} +extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); -static inline bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return true; -} +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn, + unsigned long nr_pages); static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { return __set_phys_to_machine(pfn, mfn); } + +#define xen_remap(cookie, size) ioremap_cache((cookie), (size)) +#define xen_unmap(cookie) iounmap((cookie)) + #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h index 7604673dc42..4ffb26d4cad 100644 --- a/arch/arm/include/asm/xor.h +++ b/arch/arm/include/asm/xor.h @@ -7,7 +7,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/hardirq.h> #include <asm-generic/xor.h> +#include <asm/hwcap.h> +#include <asm/neon.h> #define __XOR(a1, a2) a1 ^= a2 @@ -138,4 +141,74 @@ static struct xor_block_template xor_block_arm4regs = { xor_speed(&xor_block_arm4regs); \ xor_speed(&xor_block_8regs); \ xor_speed(&xor_block_32regs); \ + NEON_TEMPLATES; \ } while (0) + +#ifdef CONFIG_KERNEL_MODE_NEON + +extern struct xor_block_template const xor_block_neon_inner; + +static void +xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + if (in_interrupt()) { + xor_arm4regs_2(bytes, p1, p2); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_2(bytes, p1, p2); + kernel_neon_end(); + } +} + +static void +xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + if (in_interrupt()) { + xor_arm4regs_3(bytes, p1, p2, p3); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_3(bytes, p1, p2, p3); + kernel_neon_end(); + } +} + +static void +xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + if (in_interrupt()) { + xor_arm4regs_4(bytes, p1, p2, p3, p4); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4); + kernel_neon_end(); + } +} + +static void +xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + if (in_interrupt()) { + xor_arm4regs_5(bytes, p1, p2, p3, p4, p5); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5); + kernel_neon_end(); + } +} + +static struct xor_block_template xor_block_neon = { + .name = "neon", + .do_2 = xor_neon_2, + .do_3 = xor_neon_3, + .do_4 = xor_neon_4, + .do_5 = xor_neon_5 +}; + +#define NEON_TEMPLATES \ + do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0) +#else +#define NEON_TEMPLATES +#endif |