diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2015-02-10 11:35:36 -0800 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2015-02-10 11:35:36 -0800 |
| commit | 4ba24fef3eb3b142197135223b90ced2f319cd53 (patch) | |
| tree | a20c125b27740ec7b4c761b11d801108e1b316b2 /arch/arm64/include | |
| parent | 47c1ffb2b6b630894e9a16442611c056ab21c057 (diff) | |
| parent | 98a4a59ee31a12105a2b84f5b8b515ac2cb208ef (diff) | |
Merge branch 'next' into for-linus
Prepare first round of input updates for 3.20.
Diffstat (limited to 'arch/arm64/include')
53 files changed, 1306 insertions, 492 deletions
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 0b3fcf86e6ba..55103e50c51b 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -9,11 +9,11 @@ generic-y += current.h generic-y += delay.h generic-y += div64.h generic-y += dma.h -generic-y += emergency-restart.h +generic-y += dma-contiguous.h generic-y += early_ioremap.h +generic-y += emergency-restart.h generic-y += errno.h generic-y += ftrace.h -generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ioctls.h @@ -27,8 +27,10 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mman.h generic-y += msgbuf.h +generic-y += msi.h generic-y += mutex.h generic-y += pci.h +generic-y += pci-bridge.h generic-y += poll.h generic-y += preempt.h generic-y += resource.h diff --git a/arch/arm64/include/asm/alternative-asm.h b/arch/arm64/include/asm/alternative-asm.h new file mode 100644 index 000000000000..919a67855b63 --- /dev/null +++ b/arch/arm64/include/asm/alternative-asm.h @@ -0,0 +1,29 @@ +#ifndef __ASM_ALTERNATIVE_ASM_H +#define __ASM_ALTERNATIVE_ASM_H + +#ifdef __ASSEMBLY__ + +.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len + .word \orig_offset - . + .word \alt_offset - . + .hword \feature + .byte \orig_len + .byte \alt_len +.endm + +.macro alternative_insn insn1 insn2 cap +661: \insn1 +662: .pushsection .altinstructions, "a" + altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f + .popsection + .pushsection .altinstr_replacement, "ax" +663: \insn2 +664: .popsection + .if ((664b-663b) != (662b-661b)) + .error "Alternatives instruction length mismatch" + .endif +.endm + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_ALTERNATIVE_ASM_H */ diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h new file mode 100644 index 000000000000..d261f01e2bae --- /dev/null +++ b/arch/arm64/include/asm/alternative.h @@ -0,0 +1,44 @@ +#ifndef __ASM_ALTERNATIVE_H +#define __ASM_ALTERNATIVE_H + +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/stringify.h> + +struct alt_instr { + s32 orig_offset; /* offset to original instruction */ + s32 alt_offset; /* offset to replacement instruction */ + u16 cpufeature; /* cpufeature bit set for replacement */ + u8 orig_len; /* size of original instruction(s) */ + u8 alt_len; /* size of new instruction(s), <= orig_len */ +}; + +void apply_alternatives_all(void); +void apply_alternatives(void *start, size_t length); +void free_alternatives_memory(void); + +#define ALTINSTR_ENTRY(feature) \ + " .word 661b - .\n" /* label */ \ + " .word 663f - .\n" /* new instruction */ \ + " .hword " __stringify(feature) "\n" /* feature bit */ \ + " .byte 662b-661b\n" /* source len */ \ + " .byte 664f-663f\n" /* replacement len */ + +/* alternative assembly primitive: */ +#define ALTERNATIVE(oldinstr, newinstr, feature) \ + "661:\n\t" \ + oldinstr "\n" \ + "662:\n" \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feature) \ + ".popsection\n" \ + ".pushsection .altinstr_replacement, \"a\"\n" \ + "663:\n\t" \ + newinstr "\n" \ + "664:\n\t" \ + ".popsection\n\t" \ + ".if ((664b-663b) != (662b-661b))\n\t" \ + " .error \"Alternatives instruction length mismatch\"\n\t"\ + ".endif\n" + +#endif /* __ASM_ALTERNATIVE_H */ diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index 9400596a0f39..fbe0ca31a99c 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -21,6 +21,7 @@ #include <asm/barrier.h> +#include <linux/bug.h> #include <linux/init.h> #include <linux/types.h> @@ -104,35 +105,13 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl) asm volatile("msr cntkctl_el1, %0" : : "r" (cntkctl)); } -static inline void arch_counter_set_user_access(void) +static inline u64 arch_counter_get_cntpct(void) { - u32 cntkctl = arch_timer_get_cntkctl(); - - /* Disable user access to the timers and the physical counter */ - /* 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_PCT_ACCESS_EN); - - /* Enable user access to the virtual counter */ - cntkctl |= ARCH_TIMER_USR_VCT_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; -#ifdef CONFIG_COMPAT - compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM; -#endif + /* + * AArch64 kernel and user space mandate the use of CNTVCT. + */ + BUG(); + return 0; } static inline u64 arch_counter_get_cntvct(void) diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 65f1569ac96e..7047051ded40 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -35,7 +35,7 @@ * strex/ldrex monitor on some implementations. The reason we can use it for * atomic_set() is the clrex or dummy strex done on every exception return. */ -#define atomic_read(v) (*(volatile int *)&(v)->counter) +#define atomic_read(v) ACCESS_ONCE((v)->counter) #define atomic_set(v,i) (((v)->counter) = (i)) /* @@ -43,69 +43,51 @@ * store exclusive to ensure that these are atomic. We may loop * to ensure that the update happens. */ -static inline void atomic_add(int i, atomic_t *v) -{ - unsigned long tmp; - int result; - - asm volatile("// atomic_add\n" -"1: ldxr %w0, %2\n" -" add %w0, %w0, %w3\n" -" stxr %w1, %w0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i)); -} - -static inline int atomic_add_return(int i, atomic_t *v) -{ - unsigned long tmp; - int result; - - asm volatile("// atomic_add_return\n" -"1: ldxr %w0, %2\n" -" add %w0, %w0, %w3\n" -" stlxr %w1, %w0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "memory"); - - smp_mb(); - return result; -} - -static inline void atomic_sub(int i, atomic_t *v) -{ - unsigned long tmp; - int result; - asm volatile("// atomic_sub\n" -"1: ldxr %w0, %2\n" -" sub %w0, %w0, %w3\n" -" stxr %w1, %w0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i)); +#define ATOMIC_OP(op, asm_op) \ +static inline void atomic_##op(int i, atomic_t *v) \ +{ \ + unsigned long tmp; \ + int result; \ + \ + asm volatile("// atomic_" #op "\n" \ +"1: ldxr %w0, %2\n" \ +" " #asm_op " %w0, %w0, %w3\n" \ +" stxr %w1, %w0, %2\n" \ +" cbnz %w1, 1b" \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i)); \ +} \ + +#define ATOMIC_OP_RETURN(op, asm_op) \ +static inline int atomic_##op##_return(int i, atomic_t *v) \ +{ \ + unsigned long tmp; \ + int result; \ + \ + asm volatile("// atomic_" #op "_return\n" \ +"1: ldxr %w0, %2\n" \ +" " #asm_op " %w0, %w0, %w3\n" \ +" stlxr %w1, %w0, %2\n" \ +" cbnz %w1, 1b" \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i) \ + : "memory"); \ + \ + smp_mb(); \ + return result; \ } -static inline int atomic_sub_return(int i, atomic_t *v) -{ - unsigned long tmp; - int result; +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_OP_RETURN(op, asm_op) - asm volatile("// atomic_sub_return\n" -"1: ldxr %w0, %2\n" -" sub %w0, %w0, %w3\n" -" stlxr %w1, %w0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "memory"); +ATOMIC_OPS(add, add) +ATOMIC_OPS(sub, sub) - smp_mb(); - return result; -} +#undef ATOMIC_OPS +#undef ATOMIC_OP_RETURN +#undef ATOMIC_OP static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) { @@ -157,72 +139,53 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) */ #define ATOMIC64_INIT(i) { (i) } -#define atomic64_read(v) (*(volatile long *)&(v)->counter) +#define atomic64_read(v) ACCESS_ONCE((v)->counter) #define atomic64_set(v,i) (((v)->counter) = (i)) -static inline void atomic64_add(u64 i, atomic64_t *v) -{ - long result; - unsigned long tmp; - - asm volatile("// atomic64_add\n" -"1: ldxr %0, %2\n" -" add %0, %0, %3\n" -" stxr %w1, %0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i)); +#define ATOMIC64_OP(op, asm_op) \ +static inline void atomic64_##op(long i, atomic64_t *v) \ +{ \ + long result; \ + unsigned long tmp; \ + \ + asm volatile("// atomic64_" #op "\n" \ +"1: ldxr %0, %2\n" \ +" " #asm_op " %0, %0, %3\n" \ +" stxr %w1, %0, %2\n" \ +" cbnz %w1, 1b" \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i)); \ +} \ + +#define ATOMIC64_OP_RETURN(op, asm_op) \ +static inline long atomic64_##op##_return(long i, atomic64_t *v) \ +{ \ + long result; \ + unsigned long tmp; \ + \ + asm volatile("// atomic64_" #op "_return\n" \ +"1: ldxr %0, %2\n" \ +" " #asm_op " %0, %0, %3\n" \ +" stlxr %w1, %0, %2\n" \ +" cbnz %w1, 1b" \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i) \ + : "memory"); \ + \ + smp_mb(); \ + return result; \ } -static inline long atomic64_add_return(long i, atomic64_t *v) -{ - long result; - unsigned long tmp; +#define ATOMIC64_OPS(op, asm_op) \ + ATOMIC64_OP(op, asm_op) \ + ATOMIC64_OP_RETURN(op, asm_op) - asm volatile("// atomic64_add_return\n" -"1: ldxr %0, %2\n" -" add %0, %0, %3\n" -" stlxr %w1, %0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "memory"); +ATOMIC64_OPS(add, add) +ATOMIC64_OPS(sub, sub) - smp_mb(); - return result; -} - -static inline void atomic64_sub(u64 i, atomic64_t *v) -{ - long result; - unsigned long tmp; - - asm volatile("// atomic64_sub\n" -"1: ldxr %0, %2\n" -" sub %0, %0, %3\n" -" stxr %w1, %0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i)); -} - -static inline long atomic64_sub_return(long i, atomic64_t *v) -{ - long result; - unsigned long tmp; - - asm volatile("// atomic64_sub_return\n" -"1: ldxr %0, %2\n" -" sub %0, %0, %3\n" -" stlxr %w1, %0, %2\n" -" cbnz %w1, 1b" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "memory"); - - smp_mb(); - return result; -} +#undef ATOMIC64_OPS +#undef ATOMIC64_OP_RETURN +#undef ATOMIC64_OP static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new) { diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 6389d60574d9..a5abb0062d6e 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -32,6 +32,9 @@ #define rmb() dsb(ld) #define wmb() dsb(st) +#define dma_rmb() dmb(oshld) +#define dma_wmb() dmb(oshst) + #ifndef CONFIG_SMP #define smp_mb() barrier() #define smp_rmb() barrier() diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 88cc05b5f3ac..bde449936e2f 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -32,6 +32,8 @@ #ifndef __ASSEMBLY__ +#define __read_mostly __attribute__((__section__(".data..read_mostly"))) + static inline int cache_line_size(void) { u32 cwg = cache_type_cwg(); diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index f2defe1c380c..7ae31a2cc6c0 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -73,7 +73,7 @@ extern void flush_cache_all(void); extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); -extern void __flush_cache_user_range(unsigned long start, unsigned long end); +extern long __flush_cache_user_range(unsigned long start, unsigned long end); static inline void flush_cache_mm(struct mm_struct *mm) { @@ -148,4 +148,8 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) { } +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); #endif diff --git a/arch/arm64/include/asm/cachetype.h b/arch/arm64/include/asm/cachetype.h index 7a2e0762cb40..4c631a0a3609 100644 --- a/arch/arm64/include/asm/cachetype.h +++ b/arch/arm64/include/asm/cachetype.h @@ -39,6 +39,26 @@ extern unsigned long __icache_flags; +#define CCSIDR_EL1_LINESIZE_MASK 0x7 +#define CCSIDR_EL1_LINESIZE(x) ((x) & CCSIDR_EL1_LINESIZE_MASK) + +#define CCSIDR_EL1_NUMSETS_SHIFT 13 +#define CCSIDR_EL1_NUMSETS_MASK (0x7fff << CCSIDR_EL1_NUMSETS_SHIFT) +#define CCSIDR_EL1_NUMSETS(x) \ + (((x) & CCSIDR_EL1_NUMSETS_MASK) >> CCSIDR_EL1_NUMSETS_SHIFT) + +extern u64 __attribute_const__ icache_get_ccsidr(void); + +static inline int icache_get_linesize(void) +{ + return 16 << CCSIDR_EL1_LINESIZE(icache_get_ccsidr()); +} + +static inline int icache_get_numsets(void) +{ + return 1 + CCSIDR_EL1_NUMSETS(icache_get_ccsidr()); +} + /* * Whilst the D-side always behaves as PIPT on AArch64, aliasing is * permitted in the I-cache. diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index ddb9d7830558..cb9593079f29 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -19,6 +19,7 @@ #define __ASM_CMPXCHG_H #include <linux/bug.h> +#include <linux/mmdebug.h> #include <asm/barrier.h> @@ -152,6 +153,51 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, return oldval; } +#define system_has_cmpxchg_double() 1 + +static inline int __cmpxchg_double(volatile void *ptr1, volatile void *ptr2, + unsigned long old1, unsigned long old2, + unsigned long new1, unsigned long new2, int size) +{ + unsigned long loop, lost; + + switch (size) { + case 8: + VM_BUG_ON((unsigned long *)ptr2 - (unsigned long *)ptr1 != 1); + do { + asm volatile("// __cmpxchg_double8\n" + " ldxp %0, %1, %2\n" + " eor %0, %0, %3\n" + " eor %1, %1, %4\n" + " orr %1, %0, %1\n" + " mov %w0, #0\n" + " cbnz %1, 1f\n" + " stxp %w0, %5, %6, %2\n" + "1:\n" + : "=&r"(loop), "=&r"(lost), "+Q" (*(u64 *)ptr1) + : "r" (old1), "r"(old2), "r"(new1), "r"(new2)); + } while (loop); + break; + default: + BUILD_BUG(); + } + + return !lost; +} + +static inline int __cmpxchg_double_mb(volatile void *ptr1, volatile void *ptr2, + unsigned long old1, unsigned long old2, + unsigned long new1, unsigned long new2, int size) +{ + int ret; + + smp_mb(); + ret = __cmpxchg_double(ptr1, ptr2, old1, old2, new1, new2, size); + smp_mb(); + + return ret; +} + static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, unsigned long new, int size) { @@ -182,6 +228,33 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, __ret; \ }) +#define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \ +({\ + int __ret;\ + __ret = __cmpxchg_double_mb((ptr1), (ptr2), (unsigned long)(o1), \ + (unsigned long)(o2), (unsigned long)(n1), \ + (unsigned long)(n2), sizeof(*(ptr1)));\ + __ret; \ +}) + +#define cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2) \ +({\ + int __ret;\ + __ret = __cmpxchg_double((ptr1), (ptr2), (unsigned long)(o1), \ + (unsigned long)(o2), (unsigned long)(n1), \ + (unsigned long)(n2), sizeof(*(ptr1)));\ + __ret; \ +}) + +#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) +#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) +#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) +#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) + +#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ + cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \ + o1, o2, n1, n2) + #define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n)) #define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n)) diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 253e33bc94fb..3fb053fa6e98 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -37,8 +37,8 @@ typedef s32 compat_ssize_t; typedef s32 compat_time_t; typedef s32 compat_clock_t; typedef s32 compat_pid_t; -typedef u32 __compat_uid_t; -typedef u32 __compat_gid_t; +typedef u16 __compat_uid_t; +typedef u16 __compat_gid_t; typedef u16 __compat_uid16_t; typedef u16 __compat_gid16_t; typedef u32 __compat_uid32_t; @@ -205,6 +205,13 @@ typedef struct compat_siginfo { compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; + + /* SIGSYS */ + struct { + compat_uptr_t _call_addr; /* calling user insn */ + int _syscall; /* triggering system call number */ + compat_uint_t _arch; /* AUDIT_ARCH_* of syscall */ + } _sigsys; } _sifields; } compat_siginfo_t; diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index 056443086019..8e797b2fcc01 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -30,6 +30,8 @@ struct cpuinfo_arm64 { u32 reg_dczid; u32 reg_midr; + u64 reg_id_aa64dfr0; + u64 reg_id_aa64dfr1; u64 reg_id_aa64isar0; u64 reg_id_aa64isar1; u64 reg_id_aa64mmfr0; @@ -37,6 +39,7 @@ struct cpuinfo_arm64 { u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; + u32 reg_id_dfr0; u32 reg_id_isar0; u32 reg_id_isar1; u32 reg_id_isar2; @@ -49,6 +52,10 @@ struct cpuinfo_arm64 { u32 reg_id_mmfr3; u32 reg_id_pfr0; u32 reg_id_pfr1; + + u32 reg_mvfr0; + u32 reg_mvfr1; + u32 reg_mvfr2; }; DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data); diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h index d7b4b38a8e86..6f8e2ef9094a 100644 --- a/arch/arm64/include/asm/cpu_ops.h +++ b/arch/arm64/include/asm/cpu_ops.h @@ -28,6 +28,8 @@ struct device_node; * enable-method property. * @cpu_init: Reads any data necessary for a specific enable-method from the * devicetree, for a given cpu node and proposed logical id. + * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from + * devicetree, for a given cpu node and proposed logical id. * @cpu_prepare: Early one-time preparation step for a cpu. If there is a * mechanism for doing so, tests whether it is possible to boot * the given CPU. @@ -47,6 +49,7 @@ struct device_node; struct cpu_operations { const char *name; int (*cpu_init)(struct device_node *, unsigned int); + int (*cpu_init_idle)(struct device_node *, unsigned int); int (*cpu_prepare)(unsigned int); int (*cpu_boot)(unsigned int); void (*cpu_postboot)(void); @@ -61,7 +64,7 @@ struct cpu_operations { }; extern const struct cpu_operations *cpu_ops[NR_CPUS]; -extern int __init cpu_read_ops(struct device_node *dn, int cpu); -extern void __init cpu_read_bootcpu_ops(void); +int __init cpu_read_ops(struct device_node *dn, int cpu); +void __init cpu_read_bootcpu_ops(void); #endif /* ifndef __ASM_CPU_OPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index cd4ac0516488..07547ccc1f2b 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -21,9 +21,38 @@ #define MAX_CPU_FEATURES (8 * sizeof(elf_hwcap)) #define cpu_feature(x) ilog2(HWCAP_ ## x) +#define ARM64_WORKAROUND_CLEAN_CACHE 0 +#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1 + +#define ARM64_NCAPS 2 + +#ifndef __ASSEMBLY__ + +extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); + static inline bool cpu_have_feature(unsigned int num) { return elf_hwcap & (1UL << num); } +static inline bool cpus_have_cap(unsigned int num) +{ + if (num >= ARM64_NCAPS) + return false; + return test_bit(num, cpu_hwcaps); +} + +static inline void cpus_set_cap(unsigned int num) +{ + if (num >= ARM64_NCAPS) + pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n", + num, ARM64_NCAPS); + else + __set_bit(num, cpu_hwcaps); +} + +void check_local_cpu_errata(void); + +#endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h new file mode 100644 index 000000000000..b52a9932e2b1 --- /dev/null +++ b/arch/arm64/include/asm/cpuidle.h @@ -0,0 +1,13 @@ +#ifndef __ASM_CPUIDLE_H +#define __ASM_CPUIDLE_H + +#ifdef CONFIG_CPU_IDLE +extern int cpu_init_idle(unsigned int cpu); +#else +static inline int cpu_init_idle(unsigned int cpu) +{ + return -EOPNOTSUPP; +} +#endif + +#endif diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 379d0b874328..8adb986a3086 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -57,6 +57,11 @@ #define MIDR_IMPLEMENTOR(midr) \ (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) +#define MIDR_CPU_PART(imp, partnum) \ + (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \ + (0xf << MIDR_ARCHITECTURE_SHIFT) | \ + ((partnum) << MIDR_PARTNUM_SHIFT)) + #define ARM_CPU_IMP_ARM 0x41 #define ARM_CPU_IMP_APM 0x50 diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 7fb343779498..40ec68aa6870 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -48,11 +48,13 @@ /* * #imm16 values used for BRK instruction generation * Allowed values for kgbd are 0x400 - 0x7ff + * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction * 0x401: for compile time BRK instruction */ -#define KGDB_DYN_DGB_BRK_IMM 0x400 -#define KDBG_COMPILED_DBG_BRK_IMM 0x401 +#define FAULT_BRK_IMM 0x100 +#define KGDB_DYN_DBG_BRK_IMM 0x400 +#define KGDB_COMPILED_DBG_BRK_IMM 0x401 /* * BRK instruction encoding @@ -61,24 +63,30 @@ #define AARCH64_BREAK_MON 0xd4200000 /* + * BRK instruction for provoking a fault on purpose + * Unlike kgdb, #imm16 value with unallocated handler is used for faulting. + */ +#define AARCH64_BREAK_FAULT (AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5)) + +/* * Extract byte from BRK instruction */ -#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \ +#define KGDB_DYN_DBG_BRK_INS_BYTE(x) \ ((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff) /* * Extract byte from BRK #imm16 */ -#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \ - (((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff) +#define KGBD_DYN_DBG_BRK_IMM_BYTE(x) \ + (((((KGDB_DYN_DBG_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff) -#define KGDB_DYN_DGB_BRK_BYTE(x) \ - (KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x)) +#define KGDB_DYN_DBG_BRK_BYTE(x) \ + (KGDB_DYN_DBG_BRK_INS_BYTE(x) | KGBD_DYN_DBG_BRK_IMM_BYTE(x)) -#define KGDB_DYN_BRK_INS_BYTE0 KGDB_DYN_DGB_BRK_BYTE(0) -#define KGDB_DYN_BRK_INS_BYTE1 KGDB_DYN_DGB_BRK_BYTE(1) -#define KGDB_DYN_BRK_INS_BYTE2 KGDB_DYN_DGB_BRK_BYTE(2) -#define KGDB_DYN_BRK_INS_BYTE3 KGDB_DYN_DGB_BRK_BYTE(3) +#define KGDB_DYN_BRK_INS_BYTE0 KGDB_DYN_DBG_BRK_BYTE(0) +#define KGDB_DYN_BRK_INS_BYTE1 KGDB_DYN_DBG_BRK_BYTE(1) +#define KGDB_DYN_BRK_INS_BYTE2 KGDB_DYN_DBG_BRK_BYTE(2) +#define KGDB_DYN_BRK_INS_BYTE3 KGDB_DYN_DBG_BRK_BYTE(3) #define CACHE_FLUSH_IS_SAFE 1 diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h index cf98b362094b..243ef256b8c9 100644 --- a/arch/arm64/include/asm/device.h +++ b/arch/arm64/include/asm/device.h @@ -21,6 +21,7 @@ struct dev_archdata { #ifdef CONFIG_IOMMU_API void *iommu; /* private IOMMU data */ #endif + bool dma_coherent; }; struct pdev_archdata { diff --git a/arch/arm64/include/asm/dma-contiguous.h b/arch/arm64/include/asm/dma-contiguous.h deleted file mode 100644 index 14c4c0ca7f2a..000000000000 --- a/arch/arm64/include/asm/dma-contiguous.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * Copyright (c) 2013, 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. - */ - -#ifndef _ASM_DMA_CONTIGUOUS_H -#define _ASM_DMA_CONTIGUOUS_H - -#ifdef __KERNEL__ -#ifdef CONFIG_DMA_CMA - -#include <linux/types.h> - -static inline void -dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { } - -#endif -#endif - -#endif diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index dc82e52acdb3..9ce3e680ae1c 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -52,6 +52,21 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) dev->archdata.dma_ops = ops; } +static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + struct iommu_ops *iommu, bool coherent) +{ + dev->archdata.dma_coherent = coherent; + if (coherent) + set_dma_ops(dev, &coherent_swiotlb_dma_ops); +} +#define arch_setup_dma_ops arch_setup_dma_ops + +/* do not use this function in a driver */ +static inline bool is_device_dma_coherent(struct device *dev) +{ + return dev->archdata.dma_coherent; +} + #include <asm-generic/dma-mapping-common.h> static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) diff --git a/arch/arm64/include/asm/dmi.h b/arch/arm64/include/asm/dmi.h new file mode 100644 index 000000000000..69d37d87b159 --- /dev/null +++ b/arch/arm64/include/asm/dmi.h @@ -0,0 +1,31 @@ +/* + * arch/arm64/include/asm/dmi.h + * + * Copyright (C) 2013 Linaro Limited. + * Written by: Yi Li (yi.li@linaro.org) + * + * based on arch/ia64/include/asm/dmi.h + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#ifndef __ASM_DMI_H +#define __ASM_DMI_H + +#include <linux/io.h> +#include <linux/slab.h> + +/* + * According to section 2.3.6 of the UEFI spec, the firmware should not + * request a virtual mapping for configuration tables such as SMBIOS. + * This means we have to map them before use. + */ +#define dmi_early_remap(x, l) ioremap_cache(x, l) +#define dmi_early_unmap(x, l) iounmap(x) +#define dmi_remap(x, l) ioremap_cache(x, l) +#define dmi_unmap(x) iounmap(x) +#define dmi_alloc(l) kzalloc(l, GFP_KERNEL) + +#endif diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 01d3aab64b79..1f65be393139 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -126,7 +126,7 @@ typedef struct user_fpsimd_state elf_fpregset_t; * that it will "exec", and that there is sufficient room for the brk. */ extern unsigned long randomize_et_dyn(unsigned long base); -#define ELF_ET_DYN_BASE (randomize_et_dyn(2 * TASK_SIZE_64 / 3)) +#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3) /* * When the program starts, a1 contains a pointer to a function to be @@ -169,7 +169,7 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define COMPAT_ELF_PLATFORM ("v8l") #endif -#define COMPAT_ELF_ET_DYN_BASE (randomize_et_dyn(2 * TASK_SIZE_32 / 3)) +#define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3) /* AArch32 registers. */ #define COMPAT_ELF_NGREG 18 diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 5f7bfe6df723..9ef6eca905ca 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -31,6 +31,7 @@ * */ enum fixed_addresses { + FIX_HOLE, FIX_EARLYCON_MEM_BASE, __end_of_permanent_fixed_addresses, @@ -56,10 +57,11 @@ enum fixed_addresses { #define FIXMAP_PAGE_IO __pgprot(PROT_DEVICE_nGnRE) -extern void __early_set_fixmap(enum fixed_addresses idx, - phys_addr_t phys, pgprot_t flags); +void __init early_fixmap_init(void); -#define __set_fixmap __early_set_fixmap +#define __early_set_fixmap __set_fixmap + +extern void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot); #include <asm-generic/fixmap.h> diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 0be67821f9ce..e8a3268a891c 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -47,8 +47,6 @@ static inline void ack_bad_irq(unsigned int irq) irq_err_count++; } -extern void handle_IRQ(unsigned int, struct pt_regs *); - /* * No arch-specific IRQ flags. */ diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 024c46183c3c..0ad735166d9f 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -30,6 +30,7 @@ #define COMPAT_HWCAP_IDIVA (1 << 17) #define COMPAT_HWCAP_IDIVT (1 << 18) #define COMPAT_HWCAP_IDIV (COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT) +#define COMPAT_HWCAP_LPAE (1 << 20) #define COMPAT_HWCAP_EVTSTRM (1 << 21) #define COMPAT_HWCAP2_AES (1 << 0) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index dc1f73b13e74..e2ff32a93b5c 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -2,6 +2,8 @@ * Copyright (C) 2013 Huawei Ltd. * Author: Jiang Liu <liuj97@gmail.com> * + * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.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. @@ -64,12 +66,155 @@ enum aarch64_insn_imm_type { AARCH64_INSN_IMM_14, AARCH64_INSN_IMM_12, AARCH64_INSN_IMM_9, + AARCH64_INSN_IMM_7, + AARCH64_INSN_IMM_6, + AARCH64_INSN_IMM_S, + AARCH64_INSN_IMM_R, AARCH64_INSN_IMM_MAX }; +enum aarch64_insn_register_type { + AARCH64_INSN_REGTYPE_RT, + AARCH64_INSN_REGTYPE_RN, + AARCH64_INSN_REGTYPE_RT2, + AARCH64_INSN_REGTYPE_RM, + AARCH64_INSN_REGTYPE_RD, + AARCH64_INSN_REGTYPE_RA, +}; + +enum aarch64_insn_register { + AARCH64_INSN_REG_0 = 0, + AARCH64_INSN_REG_1 = 1, + AARCH64_INSN_REG_2 = 2, + AARCH64_INSN_REG_3 = 3, + AARCH64_INSN_REG_4 = 4, + AARCH64_INSN_REG_5 = 5, + AARCH64_INSN_REG_6 = 6, + AARCH64_INSN_REG_7 = 7, + AARCH64_INSN_REG_8 = 8, + AARCH64_INSN_REG_9 = 9, + AARCH64_INSN_REG_10 = 10, + AARCH64_INSN_REG_11 = 11, + AARCH64_INSN_REG_12 = 12, + AARCH64_INSN_REG_13 = 13, + AARCH64_INSN_REG_14 = 14, + AARCH64_INSN_REG_15 = 15, + AARCH64_INSN_REG_16 = 16, + AARCH64_INSN_REG_17 = 17, + AARCH64_INSN_REG_18 = 18, + AARCH64_INSN_REG_19 = 19, + AARCH64_INSN_REG_20 = 20, + AARCH64_INSN_REG_21 = 21, + AARCH64_INSN_REG_22 = 22, + AARCH64_INSN_REG_23 = 23, + AARCH64_INSN_REG_24 = 24, + AARCH64_INSN_REG_25 = 25, + AARCH64_INSN_REG_26 = 26, + AARCH64_INSN_REG_27 = 27, + AARCH64_INSN_REG_28 = 28, + AARCH64_INSN_REG_29 = 29, + AARCH64_INSN_REG_FP = 29, /* Frame pointer */ + AARCH64_INSN_REG_30 = 30, + AARCH64_INSN_REG_LR = 30, /* Link register */ + AARCH64_INSN_REG_ZR = 31, /* Zero: as source register */ + AARCH64_INSN_REG_SP = 31 /* Stack pointer: as load/store base reg */ +}; + +enum aarch64_insn_variant { + AARCH64_INSN_VARIANT_32BIT, + AARCH64_INSN_VARIANT_64BIT +}; + +enum aarch64_insn_condition { + AARCH64_INSN_COND_EQ = 0x0, /* == */ + AARCH64_INSN_COND_NE = 0x1, /* != */ + AARCH64_INSN_COND_CS = 0x2, /* unsigned >= */ + AARCH64_INSN_COND_CC = 0x3, /* unsigned < */ + AARCH64_INSN_COND_MI = 0x4, /* < 0 */ + AARCH64_INSN_COND_PL = 0x5, /* >= 0 */ + AARCH64_INSN_COND_VS = 0x6, /* overflow */ + AARCH64_INSN_COND_VC = 0x7, /* no overflow */ + AARCH64_INSN_COND_HI = 0x8, /* unsigned > */ + AARCH64_INSN_COND_LS = 0x9, /* unsigned <= */ + AARCH64_INSN_COND_GE = 0xa, /* signed >= */ + AARCH64_INSN_COND_LT = 0xb, /* signed < */ + AARCH64_INSN_COND_GT = 0xc, /* signed > */ + AARCH64_INSN_COND_LE = 0xd, /* signed <= */ + AARCH64_INSN_COND_AL = 0xe, /* always */ +}; + enum aarch64_insn_branch_type { AARCH64_INSN_BRANCH_NOLINK, AARCH64_INSN_BRANCH_LINK, + AARCH64_INSN_BRANCH_RETURN, + AARCH64_INSN_BRANCH_COMP_ZERO, + AARCH64_INSN_BRANCH_COMP_NONZERO, +}; + +enum aarch64_insn_size_type { + AARCH64_INSN_SIZE_8, + AARCH64_INSN_SIZE_16, + AARCH64_INSN_SIZE_32, + AARCH64_INSN_SIZE_64, +}; + +enum aarch64_insn_ldst_type { + AARCH64_INSN_LDST_LOAD_REG_OFFSET, + AARCH64_INSN_LDST_STORE_REG_OFFSET, + AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX, + AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX, + AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX, + AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX, +}; + +enum aarch64_insn_adsb_type { + AARCH64_INSN_ADSB_ADD, + AARCH64_INSN_ADSB_SUB, + AARCH64_INSN_ADSB_ADD_SETFLAGS, + AARCH64_INSN_ADSB_SUB_SETFLAGS +}; + +enum aarch64_insn_movewide_type { + AARCH64_INSN_MOVEWIDE_ZERO, + AARCH64_INSN_MOVEWIDE_KEEP, + AARCH64_INSN_MOVEWIDE_INVERSE +}; + +enum aarch64_insn_bitfield_type { + AARCH64_INSN_BITFIELD_MOVE, + AARCH64_INSN_BITFIELD_MOVE_UNSIGNED, + AARCH64_INSN_BITFIELD_MOVE_SIGNED +}; + +enum aarch64_insn_data1_type { + AARCH64_INSN_DATA1_REVERSE_16, + AARCH64_INSN_DATA1_REVERSE_32, + AARCH64_INSN_DATA1_REVERSE_64, +}; + +enum aarch64_insn_data2_type { + AARCH64_INSN_DATA2_UDIV, + AARCH64_INSN_DATA2_SDIV, + AARCH64_INSN_DATA2_LSLV, + AARCH64_INSN_DATA2_LSRV, + AARCH64_INSN_DATA2_ASRV, + AARCH64_INSN_DATA2_RORV, +}; + +enum aarch64_insn_data3_type { + AARCH64_INSN_DATA3_MADD, + AARCH64_INSN_DATA3_MSUB, +}; + +enum aarch64_insn_logic_type { + AARCH64_INSN_LOGIC_AND, + AARCH64_INSN_LOGIC_BIC, + AARCH64_INSN_LOGIC_ORR, + AARCH64_INSN_LOGIC_ORN, + AARCH64_INSN_LOGIC_EOR, + AARCH64_INSN_LOGIC_EON, + AARCH64_INSN_LOGIC_AND_SETFLAGS, + AARCH64_INSN_LOGIC_BIC_SETFLAGS }; #define __AARCH64_INSN_FUNCS(abbr, mask, val) \ @@ -78,13 +223,58 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ { return (val); } +__AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) +__AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) +__AARCH64_INSN_FUNCS(stp_post, 0x7FC00000, 0x28800000) +__AARCH64_INSN_FUNCS(ldp_post, 0x7FC00000, 0x28C00000) +__AARCH64_INSN_FUNCS(stp_pre, 0x7FC00000, 0x29800000) +__AARCH64_INSN_FUNCS(ldp_pre, 0x7FC00000, 0x29C00000) +__AARCH64_INSN_FUNCS(add_imm, 0x7F000000, 0x11000000) +__AARCH64_INSN_FUNCS(adds_imm, 0x7F000000, 0x31000000) +__AARCH64_INSN_FUNCS(sub_imm, 0x7F000000, 0x51000000) +__AARCH64_INSN_FUNCS(subs_imm, 0x7F000000, 0x71000000) +__AARCH64_INSN_FUNCS(movn, 0x7F800000, 0x12800000) +__AARCH64_INSN_FUNCS(sbfm, 0x7F800000, 0x13000000) +__AARCH64_INSN_FUNCS(bfm, 0x7F800000, 0x33000000) +__AARCH64_INSN_FUNCS(movz, 0x7F800000, 0x52800000) +__AARCH64_INSN_FUNCS(ubfm, 0x7F800000, 0x53000000) +__AARCH64_INSN_FUNCS(movk, 0x7F800000, 0x72800000) +__AARCH64_INSN_FUNCS(add, 0x7F200000, 0x0B000000) +__AARCH64_INSN_FUNCS(adds, 0x7F200000, 0x2B000000) +__AARCH64_INSN_FUNCS(sub, 0x7F200000, 0x4B000000) +__AARCH64_INSN_FUNCS(subs, 0x7F200000, 0x6B000000) +__AARCH64_INSN_FUNCS(madd, 0x7FE08000, 0x1B000000) +__AARCH64_INSN_FUNCS(msub, 0x7FE08000, 0x1B008000) +__AARCH64_INSN_FUNCS(udiv, 0x7FE0FC00, 0x1AC00800) +__AARCH64_INSN_FUNCS(sdiv, 0x7FE0FC00, 0x1AC00C00) +__AARCH64_INSN_FUNCS(lslv, 0x7FE0FC00, 0x1AC02000) +__AARCH64_INSN_FUNCS(lsrv, 0x7FE0FC00, 0x1AC02400) +__AARCH64_INSN_FUNCS(asrv, 0x7FE0FC00, 0x1AC02800) +__AARCH64_INSN_FUNCS(rorv, 0x7FE0FC00, 0x1AC02C00) +__AARCH64_INSN_FUNCS(rev16, 0x7FFFFC00, 0x5AC00400) +__AARCH64_INSN_FUNCS(rev32, 0x7FFFFC00, 0x5AC00800) +__AARCH64_INSN_FUNCS(rev64, 0x7FFFFC00, 0x5AC00C00) +__AARCH64_INSN_FUNCS(and, 0x7F200000, 0x0A000000) +__AARCH64_INSN_FUNCS(bic, 0x7F200000, 0x0A200000) +__AARCH64_INSN_FUNCS(orr, 0x7F200000, 0x2A000000) +__AARCH64_INSN_FUNCS(orn, 0x7F200000, 0x2A200000) +__AARCH64_INSN_FUNCS(eor, 0x7F200000, 0x4A000000) +__AARCH64_INSN_FUNCS(eon, 0x7F200000, 0x4A200000) +__AARCH64_INSN_FUNCS(ands, 0x7F200000, 0x6A000000) +__AARCH64_INSN_FUNCS(bics, 0x7F200000, 0x6A200000) __AARCH64_INSN_FUNCS(b, 0xFC000000, 0x14000000) __AARCH64_INSN_FUNCS(bl, 0xFC000000, 0x94000000) +__AARCH64_INSN_FUNCS(cbz, 0xFE000000, 0x34000000) +__AARCH64_INSN_FUNCS(cbnz, 0xFE000000, 0x35000000) +__AARCH64_INSN_FUNCS(bcond, 0xFF000010, 0x54000000) __AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001) __AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002) __AARCH64_INSN_FUNCS(smc, 0xFFE0001F, 0xD4000003) __AARCH64_INSN_FUNCS(brk, 0xFFE0001F, 0xD4200000) __AARCH64_INSN_FUNCS(hint, 0xFFFFF01F, 0xD503201F) +__AARCH64_INSN_FUNCS(br, 0xFFFFFC1F, 0xD61F0000) +__AARCH64_INSN_FUNCS(blr, 0xFFFFFC1F, 0xD63F0000) +__AARCH64_INSN_FUNCS(ret, 0xFFFFFC1F, 0xD65F0000) #undef __AARCH64_INSN_FUNCS @@ -97,14 +287,83 @@ u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type, u32 insn, u64 imm); u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr, enum aarch64_insn_branch_type type); +u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr, + enum aarch64_insn_register reg, + enum aarch64_insn_variant variant, + enum aarch64_insn_branch_type type); +u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr, + enum aarch64_insn_condition cond); u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_op op); u32 aarch64_insn_gen_nop(void); +u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg, + enum aarch64_insn_branch_type type); +u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg, + enum aarch64_insn_register base, + enum aarch64_insn_register offset, + enum aarch64_insn_size_type size, + enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1, + enum aarch64_insn_register reg2, + enum aarch64_insn_register base, + int offset, + enum aarch64_insn_variant variant, + enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + int imm, enum aarch64_insn_variant variant, + enum aarch64_insn_adsb_type type); +u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + int immr, int imms, + enum aarch64_insn_variant variant, + enum aarch64_insn_bitfield_type type); +u32 aarch64_insn_gen_movewide(enum aarch64_insn_register dst, + int imm, int shift, + enum aarch64_insn_variant variant, + enum aarch64_insn_movewide_type type); +u32 aarch64_insn_gen_add_sub_shifted_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_register reg, + int shift, + enum aarch64_insn_variant variant, + enum aarch64_insn_adsb_type type); +u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant, + enum aarch64_insn_data1_type type); +u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_register reg, + enum aarch64_insn_variant variant, + enum aarch64_insn_data2_type type); +u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_register reg1, + enum aarch64_insn_register reg2, + enum aarch64_insn_variant variant, + enum aarch64_insn_data3_type type); +u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_register reg, + int shift, + enum aarch64_insn_variant variant, + enum aarch64_insn_logic_type type); bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn); int aarch64_insn_patch_text_nosync(void *addr, u32 insn); int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt); int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt); + +bool aarch32_insn_is_wide(u32 insn); + +#define A32_RN_OFFSET 16 +#define A32_RT_OFFSET 12 +#define A32_RT2_OFFSET 0 + +u32 aarch32_insn_extract_reg_num(u32 insn, int offset); +u32 aarch32_insn_mcr_extract_opc2(u32 insn); +u32 aarch32_insn_mcr_extract_crm(u32 insn); #endif /* __ASSEMBLY__ */ #endif /* __ASM_INSN_H */ diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index e0ecdcf6632d..949c406d4df4 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -28,57 +28,80 @@ #include <asm/barrier.h> #include <asm/pgtable.h> #include <asm/early_ioremap.h> +#include <asm/alternative.h> +#include <asm/cpufeature.h> #include <xen/xen.h> /* * Generic IO read/write. These perform native-endian accesses. */ +#define __raw_writeb __raw_writeb static inline void __raw_writeb(u8 val, volatile void __iomem *addr) { asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr)); } +#define __raw_writew __raw_writew static inline void __raw_writew(u16 val, volatile void __iomem *addr) { asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr)); } +#define __raw_writel __raw_writel static inline void __raw_writel(u32 val, volatile void __iomem *addr) { asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr)); } +#define __raw_writeq __raw_writeq static inline void __raw_writeq(u64 val, volatile void __iomem *addr) { asm volatile("str %0, [%1]" : : "r" (val), "r" (addr)); } +#define __raw_readb __raw_readb static inline u8 __raw_readb(const volatile void __iomem *addr) { u8 val; - asm volatile("ldrb %w0, [%1]" : "=r" (val) : "r" (addr)); + asm volatile(ALTERNATIVE("ldrb %w0, [%1]", + "ldarb %w0, [%1]", + ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) + : "=r" (val) : "r" (addr)); return val; } +#define __raw_readw __raw_readw static inline u16 __raw_readw(const volatile void __iomem *addr) { u16 val; - asm volatile("ldrh %w0, [%1]" : "=r" (val) : "r" (addr)); + + asm volatile(ALTERNATIVE("ldrh %w0, [%1]", + "ldarh %w0, [%1]", + ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) + : "=r" (val) : "r" (addr)); return val; } +#define __raw_readl __raw_readl static inline u32 __raw_readl(const volatile void __iomem *addr) { u32 val; - asm volatile("ldr %w0, [%1]" : "=r" (val) : "r" (addr)); + asm volatile(ALTERNATIVE("ldr %w0, [%1]", + "ldar %w0, [%1]", + ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) + : "=r" (val) : "r" (addr)); return val; } +#define __raw_readq __raw_readq static inline u64 __raw_readq(const volatile void __iomem *addr) { u64 val; - asm volatile("ldr %0, [%1]" : "=r" (val) : "r" (addr)); + asm volatile(ALTERNATIVE("ldr %0, [%1]", + "ldar %0, [%1]", + ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) + : "=r" (val) : "r" (addr)); return val; } @@ -121,97 +144,10 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) /* * I/O port access primitives. */ -#define IO_SPACE_LIMIT 0xffff +#define arch_has_dev_port() (1) +#define IO_SPACE_LIMIT (SZ_32M - 1) #define PCI_IOBASE ((void __iomem *)(MODULES_VADDR - SZ_32M)) -static inline u8 inb(unsigned long addr) -{ - return readb(addr + PCI_IOBASE); -} - -static inline u16 inw(unsigned long addr) -{ - return readw(addr + PCI_IOBASE); -} - -static inline u32 inl(unsigned long addr) -{ - return readl(addr + PCI_IOBASE); -} - -static inline void outb(u8 b, unsigned long addr) -{ - writeb(b, addr + PCI_IOBASE); -} - -static inline void outw(u16 b, unsigned long addr) -{ - writew(b, addr + PCI_IOBASE); -} - -static inline void outl(u32 b, unsigned long addr) -{ - writel(b, addr + PCI_IOBASE); -} - -#define inb_p(addr) inb(addr) -#define inw_p(addr) inw(addr) -#define inl_p(addr) inl(addr) - -#define outb_p(x, addr) outb((x), (addr)) -#define outw_p(x, addr) outw((x), (addr)) -#define outl_p(x, addr) outl((x), (addr)) - -static inline void insb(unsigned long addr, void *buffer, int count) -{ - u8 *buf = buffer; - while (count--) - *buf++ = __raw_readb(addr + PCI_IOBASE); -} - -static inline void insw(unsigned long addr, void *buffer, int count) -{ - u16 *buf = buffer; - while (count--) - *buf++ = __raw_readw(addr + PCI_IOBASE); -} - -static inline void insl(unsigned long addr, void *buffer, int count) -{ - u32 *buf = buffer; - while (count--) - *buf++ = __raw_readl(addr + PCI_IOBASE); -} - -static inline void outsb(unsigned long addr, const void *buffer, int count) -{ - const u8 *buf = buffer; - while (count--) - __raw_writeb(*buf++, addr + PCI_IOBASE); -} - -static inline void outsw(unsigned long addr, const void *buffer, int count) -{ - const u16 *buf = buffer; - while (count--) - __raw_writew(*buf++, addr + PCI_IOBASE); -} - -static inline void outsl(unsigned long addr, const void *buffer, int count) -{ - const u32 *buf = buffer; - while (count--) - __raw_writel(*buf++, addr + PCI_IOBASE); -} - -#define insb_p(port,to,len) insb(port,to,len) -#define insw_p(port,to,len) insw(port,to,len) -#define insl_p(port,to,len) insl(port,to,len) - -#define outsb_p(port,from,len) outsb(port,from,len) -#define outsw_p(port,from,len) outsw(port,from,len) -#define outsl_p(port,from,len) outsl(port,from,len) - /* * String version of I/O memory access operations. */ @@ -235,18 +171,14 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); #define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC)) #define iounmap __iounmap -#define ARCH_HAS_IOREMAP_WC -#include <asm-generic/iomap.h> - /* - * More restrictive address range checking than the default implementation - * (PHYS_OFFSET and PHYS_MASK taken into account). + * io{read,write}{16,32}be() macros */ -#define ARCH_HAS_VALID_PHYS_ADDR_RANGE -extern int valid_phys_addr_range(unsigned long addr, size_t size); -extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) -extern int devmem_is_allowed(unsigned long pfn); +#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); }) /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem @@ -259,6 +191,18 @@ extern int devmem_is_allowed(unsigned long pfn); */ #define xlate_dev_kmem_ptr(p) p +#include <asm-generic/io.h> + +/* + * More restrictive address range checking than the default implementation + * (PHYS_OFFSET and PHYS_MASK taken into account). + */ +#define ARCH_HAS_VALID_PHYS_ADDR_RANGE +extern int valid_phys_addr_range(phys_addr_t addr, size_t size); +extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); + +extern int devmem_is_allowed(unsigned long pfn); + struct bio_vec; extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, const struct bio_vec *vec2); diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index e1f7ecdde11f..94c53674a31d 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -3,7 +3,8 @@ #include <asm-generic/irq.h> -extern void (*handle_arch_irq)(struct pt_regs *); +struct pt_regs; + extern void migrate_irqs(void); extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h new file mode 100644 index 000000000000..b4f6b19a8a68 --- /dev/null +++ b/arch/arm64/include/asm/irq_work.h @@ -0,0 +1,22 @@ +#ifndef __ASM_IRQ_WORK_H +#define __ASM_IRQ_WORK_H + +#ifdef CONFIG_SMP + +#include <asm/smp.h> + +static inline bool arch_irq_work_has_interrupt(void) +{ + return !!__smp_cross_call; +} + +#else + +static inline bool arch_irq_work_has_interrupt(void) +{ + return false; +} + +#endif + +#endif /* __ASM_IRQ_WORK_H */ diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h index 3c8aafc1082f..f69f69c8120c 100644 --- a/arch/arm64/include/asm/kgdb.h +++ b/arch/arm64/include/asm/kgdb.h @@ -29,7 +29,7 @@ static inline void arch_kgdb_breakpoint(void) { - asm ("brk %0" : : "I" (KDBG_COMPILED_DBG_BRK_IMM)); + asm ("brk %0" : : "I" (KGDB_COMPILED_DBG_BRK_IMM)); } extern void kgdb_handle_bus_error(void); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index cc83520459ed..8afb863f5a9e 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -18,6 +18,7 @@ #ifndef __ARM64_KVM_ARM_H__ #define __ARM64_KVM_ARM_H__ +#include <asm/memory.h> #include <asm/types.h> /* Hyp Configuration Register (HCR) bits */ @@ -122,6 +123,17 @@ #define VTCR_EL2_T0SZ_MASK 0x3f #define VTCR_EL2_T0SZ_40B 24 +/* + * We configure the Stage-2 page tables to always restrict the IPA space to be + * 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are + * not known to exist and will break with this configuration. + * + * Note that when using 4K pages, we concatenate two first level page tables + * together. + * + * The magic numbers used for VTTBR_X in this patch can be found in Tables + * D4-23 and D4-25 in ARM DDI 0487A.b. + */ #ifdef CONFIG_ARM64_64K_PAGES /* * Stage2 translation configuration: @@ -149,9 +161,9 @@ #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) +#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_VMID_SHIFT (UL(48)) +#define VTTBR_VMID_MASK (UL(0xFF) << VTTBR_VMID_SHIFT) /* Hyp System Trap Register */ #define HSTR_EL2_TTEE (1 << 16) @@ -174,13 +186,13 @@ /* Exception Syndrome Register (ESR) bits */ #define ESR_EL2_EC_SHIFT (26) -#define ESR_EL2_EC (0x3fU << ESR_EL2_EC_SHIFT) -#define ESR_EL2_IL (1U << 25) +#define ESR_EL2_EC (UL(0x3f) << ESR_EL2_EC_SHIFT) +#define ESR_EL2_IL (UL(1) << 25) #define ESR_EL2_ISS (ESR_EL2_IL - 1) #define ESR_EL2_ISV_SHIFT (24) -#define ESR_EL2_ISV (1U << ESR_EL2_ISV_SHIFT) +#define ESR_EL2_ISV (UL(1) << ESR_EL2_ISV_SHIFT) #define ESR_EL2_SAS_SHIFT (22) -#define ESR_EL2_SAS (3U << ESR_EL2_SAS_SHIFT) +#define ESR_EL2_SAS (UL(3) << ESR_EL2_SAS_SHIFT) #define ESR_EL2_SSE (1 << 21) #define ESR_EL2_SRT_SHIFT (16) #define ESR_EL2_SRT_MASK (0x1f << ESR_EL2_SRT_SHIFT) @@ -194,16 +206,16 @@ #define ESR_EL2_FSC_TYPE (0x3c) #define ESR_EL2_CV_SHIFT (24) -#define ESR_EL2_CV (1U << ESR_EL2_CV_SHIFT) +#define ESR_EL2_CV (UL(1) << ESR_EL2_CV_SHIFT) #define ESR_EL2_COND_SHIFT (20) -#define ESR_EL2_COND (0xfU << ESR_EL2_COND_SHIFT) +#define ESR_EL2_COND (UL(0xf) << ESR_EL2_COND_SHIFT) #define FSC_FAULT (0x04) #define FSC_PERM (0x0c) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ -#define HPFAR_MASK (~0xFUL) +#define HPFAR_MASK (~UL(0xf)) #define ESR_EL2_EC_UNKNOWN (0x00) #define ESR_EL2_EC_WFI (0x01) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index fdc3e21abd8d..8127e45e2637 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -38,6 +38,11 @@ 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 void vcpu_reset_hcr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; +} + static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; @@ -174,6 +179,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { + return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC; +} + +static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) +{ return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE; } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e10c45a578e3..0b7dfdb931df 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -22,6 +22,8 @@ #ifndef __ARM64_KVM_HOST_H__ #define __ARM64_KVM_HOST_H__ +#include <linux/types.h> +#include <linux/kvm_types.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> @@ -41,8 +43,7 @@ #define KVM_VCPU_MAX_FEATURES 3 -struct kvm_vcpu; -int kvm_target_cpu(void); +int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); int kvm_arch_dev_ioctl_check_extension(long ext); @@ -164,25 +165,21 @@ 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); #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); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long hva) +static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, + unsigned long end) { return 0; } @@ -192,10 +189,16 @@ static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) return 0; } +static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, + unsigned long address) +{ +} + struct kvm_vcpu *kvm_arm_get_running_vcpu(void); -struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); u64 kvm_call_hyp(void *hypfn, ...); +void force_vm_exit(const cpumask_t *mask); int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, int exception_index); @@ -244,4 +247,10 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic) } } +static inline void kvm_arch_hardware_disable(void) {} +static inline void kvm_arch_hardware_unsetup(void) {} +static inline void kvm_arch_sync_events(struct kvm *kvm) {} +static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 8e138c7c53ac..14a74f136272 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -41,6 +41,18 @@ */ #define TRAMPOLINE_VA (HYP_PAGE_OFFSET_MASK & PAGE_MASK) +/* + * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation + * levels in addition to the PGD and potentially the PUD which are + * pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2 + * tables use one level of tables less than the kernel. + */ +#ifdef CONFIG_ARM64_64K_PAGES +#define KVM_MMU_CACHE_MIN_PAGES 1 +#else +#define KVM_MMU_CACHE_MIN_PAGES 2 +#endif + #ifdef __ASSEMBLY__ /* @@ -53,32 +65,29 @@ #else +#include <asm/pgalloc.h> #include <asm/cachetype.h> #include <asm/cacheflush.h> #define KERN_TO_HYP(kva) ((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET) /* - * Align KVM with the kernel's view of physical memory. Should be - * 40bit IPA, with PGD being 8kB aligned in the 4KB page configuration. + * We currently only support a 40bit IPA. */ -#define KVM_PHYS_SHIFT PHYS_MASK_SHIFT +#define KVM_PHYS_SHIFT (40) #define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT) #define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL) -/* Make sure we get the right size, and thus the right alignment */ -#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT)) -#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) - 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); +void stage2_unmap_vm(struct kvm *kvm); 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); + phys_addr_t pa, unsigned long size, bool writable); int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run); @@ -93,20 +102,8 @@ void kvm_clear_hyp_idmap(void); #define kvm_set_pte(ptep, pte) set_pte(ptep, pte) #define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd) -static inline bool kvm_is_write_fault(unsigned long esr) -{ - unsigned long esr_ec = esr >> ESR_EL2_EC_SHIFT; - - if (esr_ec == ESR_EL2_EC_IABT) - return false; - - if ((esr & ESR_EL2_ISV) && !(esr & ESR_EL2_WNR)) - return false; - - return true; -} - static inline void kvm_clean_pgd(pgd_t *pgd) {} +static inline void kvm_clean_pmd(pmd_t *pmd) {} static inline void kvm_clean_pmd_entry(pmd_t *pmd) {} static inline void kvm_clean_pte(pte_t *pte) {} static inline void kvm_clean_pte_entry(pte_t *pte) {} @@ -125,19 +122,116 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) #define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end) #define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end) +/* + * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address + * the entire IPA input range with a single pgd entry, and we would only need + * one pgd entry. Note that in this case, the pgd is actually not used by + * the MMU for Stage-2 translations, but is merely a fake pgd used as a data + * structure for the kernel pgtable macros to work. + */ +#if PGDIR_SHIFT > KVM_PHYS_SHIFT +#define PTRS_PER_S2_PGD_SHIFT 0 +#else +#define PTRS_PER_S2_PGD_SHIFT (KVM_PHYS_SHIFT - PGDIR_SHIFT) +#endif +#define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT) +#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) + +/* + * If we are concatenating first level stage-2 page tables, we would have less + * than or equal to 16 pointers in the fake PGD, because that's what the + * architecture allows. In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS) + * represents the first level for the host, and we add 1 to go to the next + * level (which uses contatenation) for the stage-2 tables. + */ +#if PTRS_PER_S2_PGD <= 16 +#define KVM_PREALLOC_LEVEL (4 - CONFIG_ARM64_PGTABLE_LEVELS + 1) +#else +#define KVM_PREALLOC_LEVEL (0) +#endif + +/** + * kvm_prealloc_hwpgd - allocate inital table for VTTBR + * @kvm: The KVM struct pointer for the VM. + * @pgd: The kernel pseudo pgd + * + * When the kernel uses more levels of page tables than the guest, we allocate + * a fake PGD and pre-populate it to point to the next-level page table, which + * will be the real initial page table pointed to by the VTTBR. + * + * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and + * the kernel will use folded pud. When KVM_PREALLOC_LEVEL==1, we + * allocate 2 consecutive PUD pages. + */ +static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) +{ + unsigned int i; + unsigned long hwpgd; + + if (KVM_PREALLOC_LEVEL == 0) + return 0; + + hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT); + if (!hwpgd) + return -ENOMEM; + + for (i = 0; i < PTRS_PER_S2_PGD; i++) { + if (KVM_PREALLOC_LEVEL == 1) + pgd_populate(NULL, pgd + i, + (pud_t *)hwpgd + i * PTRS_PER_PUD); + else if (KVM_PREALLOC_LEVEL == 2) + pud_populate(NULL, pud_offset(pgd, 0) + i, + (pmd_t *)hwpgd + i * PTRS_PER_PMD); + } + + return 0; +} + +static inline void *kvm_get_hwpgd(struct kvm *kvm) +{ + pgd_t *pgd = kvm->arch.pgd; + pud_t *pud; + + if (KVM_PREALLOC_LEVEL == 0) + return pgd; + + pud = pud_offset(pgd, 0); + if (KVM_PREALLOC_LEVEL == 1) + return pud; + + BUG_ON(KVM_PREALLOC_LEVEL != 2); + return pmd_offset(pud, 0); +} + +static inline void kvm_free_hwpgd(struct kvm *kvm) +{ + if (KVM_PREALLOC_LEVEL > 0) { + unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm); + free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT); + } +} + static inline bool kvm_page_empty(void *ptr) { struct page *ptr_page = virt_to_page(ptr); return page_count(ptr_page) == 1; } -#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep) -#ifndef CONFIG_ARM64_64K_PAGES -#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp) +#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) + +#ifdef __PAGETABLE_PMD_FOLDED +#define kvm_pmd_table_empty(kvm, pmdp) (0) +#else +#define kvm_pmd_table_empty(kvm, pmdp) \ + (kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2)) +#endif + +#ifdef __PAGETABLE_PUD_FOLDED +#define kvm_pud_table_empty(kvm, pudp) (0) #else -#define kvm_pmd_table_empty(pmdp) (0) +#define kvm_pud_table_empty(kvm, pudp) \ + (kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1)) #endif -#define kvm_pud_table_empty(pudp) (0) struct kvm; @@ -150,9 +244,10 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) } static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, - unsigned long size) + unsigned long size, + bool ipa_uncached) { - if (!vcpu_has_cache_enabled(vcpu)) + if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) kvm_flush_dcache_to_poc((void *)hva, size); if (!icache_is_aliasing()) { /* PIPT */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index ccc7087d3c4e..6486b2bfd562 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -120,11 +120,13 @@ extern phys_addr_t memstart_addr; * translation for translating DMA addresses. Use the driver * DMA support - see dma-mapping.h. */ +#define virt_to_phys virt_to_phys static inline phys_addr_t virt_to_phys(const volatile void *x) { return __virt_to_phys((unsigned long)(x)); } +#define phys_to_virt phys_to_virt static inline void *phys_to_virt(phys_addr_t x) { return (void *)(__phys_to_virt(x)); @@ -142,7 +144,7 @@ static inline void *phys_to_virt(phys_addr_t x) * virt_to_page(k) convert a _valid_ virtual address to struct page * * virt_addr_valid(k) indicates whether a virtual address is valid */ -#define ARCH_PFN_OFFSET PHYS_PFN_OFFSET +#define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET) #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h new file mode 100644 index 000000000000..4e603ea36ad3 --- /dev/null +++ b/arch/arm64/include/asm/opcodes.h @@ -0,0 +1 @@ +#include <../../arm/include/asm/opcodes.h> diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h new file mode 100644 index 000000000000..872ba939fcb2 --- /dev/null +++ b/arch/arm64/include/asm/pci.h @@ -0,0 +1,37 @@ +#ifndef __ASM_PCI_H +#define __ASM_PCI_H +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/dma-mapping.h> + +#include <asm/io.h> +#include <asm-generic/pci-bridge.h> +#include <asm-generic/pci-dma-compat.h> + +#define PCIBIOS_MIN_IO 0x1000 +#define PCIBIOS_MIN_MEM 0 + +/* + * Set to 1 if the kernel should re-assign all PCI bus numbers + */ +#define pcibios_assign_all_busses() \ + (pci_has_flag(PCI_REASSIGN_ALL_BUS)) + +/* + * PCI address space differs from physical memory address space + */ +#define PCI_DMA_BUS_IS_PHYS (0) + +extern int isa_dma_bridge_buggy; + +#ifdef CONFIG_PCI +static inline int pci_proc_domain(struct pci_bus *bus) +{ + return 1; +} +#endif /* CONFIG_PCI */ + +#endif /* __KERNEL__ */ +#endif /* __ASM_PCI_H */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 453a179469a3..09da25bc596f 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -26,13 +26,13 @@ static inline void set_my_cpu_offset(unsigned long off) static inline unsigned long __my_cpu_offset(void) { unsigned long off; - register unsigned long *sp asm ("sp"); /* * We want to allow caching the value, so avoid using volatile and * instead use a fake stack read to hazard against barrier(). */ - asm("mrs %0, tpidr_el1" : "=r" (off) : "Q" (*sp)); + asm("mrs %0, tpidr_el1" : "=r" (off) : + "Q" (*(const unsigned long *)current_stack_pointer)); return off; } @@ -44,6 +44,221 @@ static inline unsigned long __my_cpu_offset(void) #endif /* CONFIG_SMP */ +#define PERCPU_OP(op, asm_op) \ +static inline unsigned long __percpu_##op(void *ptr, \ + unsigned long val, int size) \ +{ \ + unsigned long loop, ret; \ + \ + switch (size) { \ + case 1: \ + do { \ + asm ("//__per_cpu_" #op "_1\n" \ + "ldxrb %w[ret], %[ptr]\n" \ + #asm_op " %w[ret], %w[ret], %w[val]\n" \ + "stxrb %w[loop], %w[ret], %[ptr]\n" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u8 *)ptr) \ + : [val] "Ir" (val)); \ + } while (loop); \ + break; \ + case 2: \ + do { \ + asm ("//__per_cpu_" #op "_2\n" \ + "ldxrh %w[ret], %[ptr]\n" \ + #asm_op " %w[ret], %w[ret], %w[val]\n" \ + "stxrh %w[loop], %w[ret], %[ptr]\n" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u16 *)ptr) \ + : [val] "Ir" (val)); \ + } while (loop); \ + break; \ + case 4: \ + do { \ + asm ("//__per_cpu_" #op "_4\n" \ + "ldxr %w[ret], %[ptr]\n" \ + #asm_op " %w[ret], %w[ret], %w[val]\n" \ + "stxr %w[loop], %w[ret], %[ptr]\n" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u32 *)ptr) \ + : [val] "Ir" (val)); \ + } while (loop); \ + break; \ + case 8: \ + do { \ + asm ("//__per_cpu_" #op "_8\n" \ + "ldxr %[ret], %[ptr]\n" \ + #asm_op " %[ret], %[ret], %[val]\n" \ + "stxr %w[loop], %[ret], %[ptr]\n" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u64 *)ptr) \ + : [val] "Ir" (val)); \ + } while (loop); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + \ + return ret; \ +} + +PERCPU_OP(add, add) +PERCPU_OP(and, and) +PERCPU_OP(or, orr) +#undef PERCPU_OP + +static inline unsigned long __percpu_read(void *ptr, int size) +{ + unsigned long ret; + + switch (size) { + case 1: + ret = ACCESS_ONCE(*(u8 *)ptr); + break; + case 2: + ret = ACCESS_ONCE(*(u16 *)ptr); + break; + case 4: + ret = ACCESS_ONCE(*(u32 *)ptr); + break; + case 8: + ret = ACCESS_ONCE(*(u64 *)ptr); + break; + default: + BUILD_BUG(); + } + + return ret; +} + +static inline void __percpu_write(void *ptr, unsigned long val, int size) +{ + switch (size) { + case 1: + ACCESS_ONCE(*(u8 *)ptr) = (u8)val; + break; + case 2: + ACCESS_ONCE(*(u16 *)ptr) = (u16)val; + break; + case 4: + ACCESS_ONCE(*(u32 *)ptr) = (u32)val; + break; + case 8: + ACCESS_ONCE(*(u64 *)ptr) = (u64)val; + break; + default: + BUILD_BUG(); + } +} + +static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, + int size) +{ + unsigned long ret, loop; + + switch (size) { + case 1: + do { + asm ("//__percpu_xchg_1\n" + "ldxrb %w[ret], %[ptr]\n" + "stxrb %w[loop], %w[val], %[ptr]\n" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u8 *)ptr) + : [val] "r" (val)); + } while (loop); + break; + case 2: + do { + asm ("//__percpu_xchg_2\n" + "ldxrh %w[ret], %[ptr]\n" + "stxrh %w[loop], %w[val], %[ptr]\n" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u16 *)ptr) + : [val] "r" (val)); + } while (loop); + break; + case 4: + do { + asm ("//__percpu_xchg_4\n" + "ldxr %w[ret], %[ptr]\n" + "stxr %w[loop], %w[val], %[ptr]\n" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u32 *)ptr) + : [val] "r" (val)); + } while (loop); + break; + case 8: + do { + asm ("//__percpu_xchg_8\n" + "ldxr %[ret], %[ptr]\n" + "stxr %w[loop], %[val], %[ptr]\n" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u64 *)ptr) + : [val] "r" (val)); + } while (loop); + break; + default: + BUILD_BUG(); + } + + return ret; +} + +#define _percpu_add(pcp, val) \ + __percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) + +#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val)) + +#define _percpu_and(pcp, val) \ + __percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) + +#define _percpu_or(pcp, val) \ + __percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) + +#define _percpu_read(pcp) (typeof(pcp)) \ + (__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp))) + +#define _percpu_write(pcp, val) \ + __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)) + +#define _percpu_xchg(pcp, val) (typeof(pcp)) \ + (__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))) + +#define this_cpu_add_1(pcp, val) _percpu_add(pcp, val) +#define this_cpu_add_2(pcp, val) _percpu_add(pcp, val) +#define this_cpu_add_4(pcp, val) _percpu_add(pcp, val) +#define this_cpu_add_8(pcp, val) _percpu_add(pcp, val) + +#define this_cpu_add_return_1(pcp, val) _percpu_add_return(pcp, val) +#define this_cpu_add_return_2(pcp, val) _percpu_add_return(pcp, val) +#define this_cpu_add_return_4(pcp, val) _percpu_add_return(pcp, val) +#define this_cpu_add_return_8(pcp, val) _percpu_add_return(pcp, val) + +#define this_cpu_and_1(pcp, val) _percpu_and(pcp, val) +#define this_cpu_and_2(pcp, val) _percpu_and(pcp, val) +#define this_cpu_and_4(pcp, val) _percpu_and(pcp, val) +#define this_cpu_and_8(pcp, val) _percpu_and(pcp, val) + +#define this_cpu_or_1(pcp, val) _percpu_or(pcp, val) +#define this_cpu_or_2(pcp, val) _percpu_or(pcp, val) +#define this_cpu_or_4(pcp, val) _percpu_or(pcp, val) +#define this_cpu_or_8(pcp, val) _percpu_or(pcp, val) + +#define this_cpu_read_1(pcp) _percpu_read(pcp) +#define this_cpu_read_2(pcp) _percpu_read(pcp) +#define this_cpu_read_4(pcp) _percpu_read(pcp) +#define this_cpu_read_8(pcp) _percpu_read(pcp) + +#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val) +#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val) +#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val) +#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val) + +#define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val) +#define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val) +#define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val) +#define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val) + #include <asm-generic/percpu.h> #endif /* __ASM_PERCPU_H */ diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index d5bed02073d6..e20df38a8ff3 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -26,11 +26,13 @@ #define check_pgt_cache() do { } while (0) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + #if CONFIG_ARM64_PGTABLE_LEVELS > 2 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT); + return (pmd_t *)__get_free_page(PGALLOC_GFP); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) @@ -50,7 +52,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT); + return (pud_t *)__get_free_page(PGALLOC_GFP); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -69,8 +71,6 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) - static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr) { diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index ffe1ba0506d1..210d632aa5ad 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -79,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) #define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) -#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN) +#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) @@ -149,46 +149,51 @@ extern struct page *empty_zero_page; #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -static inline pte_t pte_wrprotect(pte_t pte) +static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { - pte_val(pte) &= ~PTE_WRITE; + pte_val(pte) &= ~pgprot_val(prot); return pte; } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) { - pte_val(pte) |= PTE_WRITE; + pte_val(pte) |= pgprot_val(prot); return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_WRITE)); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_WRITE)); +} + static inline pte_t pte_mkclean(pte_t pte) { - pte_val(pte) &= ~PTE_DIRTY; - return pte; + return clear_pte_bit(pte, __pgprot(PTE_DIRTY)); } static inline pte_t pte_mkdirty(pte_t pte) { - pte_val(pte) |= PTE_DIRTY; - return pte; + return set_pte_bit(pte, __pgprot(PTE_DIRTY)); } static inline pte_t pte_mkold(pte_t pte) { - pte_val(pte) &= ~PTE_AF; - return pte; + return clear_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkyoung(pte_t pte) { - pte_val(pte) |= PTE_AF; - return pte; + return set_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkspecial(pte_t pte) { - pte_val(pte) |= PTE_SPECIAL; - return pte; + return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); } static inline void set_pte(pte_t *ptep, pte_t pte) @@ -239,6 +244,16 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, #define __HAVE_ARCH_PTE_SPECIAL +static inline pte_t pud_pte(pud_t pud) +{ + return __pte(pud_val(pud)); +} + +static inline pmd_t pud_pmd(pud_t pud) +{ + return __pmd(pud_val(pud)); +} + static inline pte_t pmd_pte(pmd_t pmd) { return __pte(pmd_val(pmd)); @@ -256,8 +271,15 @@ static inline pmd_t pte_pmd(pte_t pte) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) #define pmd_trans_splitting(pmd) pte_special(pmd_pte(pmd)) -#endif - +#ifdef CONFIG_HAVE_RCU_TABLE_FREE +#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH +struct vm_area_struct; +void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); +#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd))) @@ -276,7 +298,7 @@ static inline pmd_t pte_pmd(pte_t pte) #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) -#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) +#define pud_write(pud) pte_write(pud_pte(pud)) #define pud_pfn(pud) (((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT) #define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)) @@ -296,6 +318,8 @@ static inline int has_transparent_hugepage(void) __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN) #define pgprot_writecombine(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) +#define pgprot_device(prot) \ + __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN) #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, @@ -376,6 +400,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr); } +#define pud_page(pud) pfn_to_page(__phys_to_pfn(pud_val(pud) & PHYS_MASK)) + #endif /* CONFIG_ARM64_PGTABLE_LEVELS > 2 */ #if CONFIG_ARM64_PGTABLE_LEVELS > 3 @@ -410,6 +436,8 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(addr); } +#define pgd_page(pgd) pfn_to_page(__phys_to_pfn(pgd_val(pgd) & PHYS_MASK)) + #endif /* CONFIG_ARM64_PGTABLE_LEVELS > 3 */ #define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd_val(pgd)) diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h index 0c657bb54597..9a8fd84f8fb2 100644 --- a/arch/arm64/include/asm/proc-fns.h +++ b/arch/arm64/include/asm/proc-fns.h @@ -32,6 +32,8 @@ extern void cpu_cache_off(void); extern void cpu_do_idle(void); extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); extern void cpu_reset(unsigned long addr) __attribute__((noreturn)); +void cpu_soft_restart(phys_addr_t cpu_reset, + unsigned long addr) __attribute__((noreturn)); extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr); extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 286b1bec547c..f9be30ea1cbd 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -31,6 +31,7 @@ #include <asm/fpsimd.h> #include <asm/hw_breakpoint.h> +#include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> #include <asm/types.h> @@ -123,9 +124,6 @@ struct task_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - unsigned long get_wchan(struct task_struct *p); #define cpu_relax() barrier() diff --git a/arch/arm64/include/asm/seccomp.h b/arch/arm64/include/asm/seccomp.h new file mode 100644 index 000000000000..c76fac979629 --- /dev/null +++ b/arch/arm64/include/asm/seccomp.h @@ -0,0 +1,25 @@ +/* + * arch/arm64/include/asm/seccomp.h + * + * Copyright (C) 2014 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@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. + */ +#ifndef _ASM_SECCOMP_H +#define _ASM_SECCOMP_H + +#include <asm/unistd.h> + +#ifdef CONFIG_COMPAT +#define __NR_seccomp_read_32 __NR_compat_read +#define __NR_seccomp_write_32 __NR_compat_write +#define __NR_seccomp_exit_32 __NR_compat_exit +#define __NR_seccomp_sigreturn_32 __NR_compat_rt_sigreturn +#endif /* CONFIG_COMPAT */ + +#include <asm-generic/seccomp.h> + +#endif /* _ASM_SECCOMP_H */ diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index a498f2cd2c2a..780f82c827b6 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -48,6 +48,8 @@ extern void smp_init_cpus(void); */ extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int)); +extern void (*__smp_cross_call)(const struct cpumask *, unsigned int); + /* * Called from the secondary holding pen, this is the secondary CPU entry point. */ diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index c45b7b1b7197..cee128732435 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -99,12 +99,12 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { - return !arch_spin_value_unlocked(ACCESS_ONCE(*lock)); + return !arch_spin_value_unlocked(READ_ONCE(*lock)); } static inline int arch_spin_is_contended(arch_spinlock_t *lock) { - arch_spinlock_t lockval = ACCESS_ONCE(*lock); + arch_spinlock_t lockval = READ_ONCE(*lock); return (lockval.next - lockval.owner) > 1; } #define arch_spin_is_contended arch_spin_is_contended diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index e9c149c042e0..456d67c1f0fa 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -21,6 +21,7 @@ struct sleep_save_sp { phys_addr_t save_ptr_stash_phys; }; +extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)); extern void cpu_resume(void); extern int cpu_suspend(unsigned long); diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 45108d802f5e..459bf8e53208 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -69,14 +69,19 @@ struct thread_info { #define init_stack (init_thread_union.stack) /* + * how to get the current stack pointer from C + */ +register unsigned long current_stack_pointer asm ("sp"); + +/* * how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) __attribute_const__; static inline struct thread_info *current_thread_info(void) { - register unsigned long sp asm ("sp"); - return (struct thread_info *)(sp & ~(THREAD_SIZE - 1)); + return (struct thread_info *) + (current_stack_pointer & ~(THREAD_SIZE - 1)); } #define thread_saved_pc(tsk) \ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 62731ef9749a..c028fe37456f 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -19,84 +19,44 @@ #ifndef __ASM_TLB_H #define __ASM_TLB_H -#define __tlb_remove_pmd_tlb_entry __tlb_remove_pmd_tlb_entry +#include <linux/pagemap.h> +#include <linux/swap.h> + +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + +#define tlb_remove_entry(tlb, entry) tlb_remove_table(tlb, entry) +static inline void __tlb_remove_table(void *_table) +{ + free_page_and_swap_cache((struct page *)_table); +} +#else +#define tlb_remove_entry(tlb, entry) tlb_remove_page(tlb, entry) +#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ #include <asm-generic/tlb.h> -/* - * There's three ways the TLB shootdown code is used: - * 1. Unmapping a range of vmas. See zap_page_range(), unmap_region(). - * tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called. - * 2. Unmapping all vmas. See exit_mmap(). - * tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called. - * Page tables will be freed. - * 3. Unmapping argument pages. See shift_arg_pages(). - * tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called. - */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm) { flush_tlb_mm(tlb->mm); - } else if (tlb->end > 0) { + } else { struct vm_area_struct vma = { .vm_mm = tlb->mm, }; flush_tlb_range(&vma, tlb->start, tlb->end); - tlb->start = TASK_SIZE; - tlb->end = 0; - } -} - -static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr) -{ - if (!tlb->fullmm) { - tlb->start = min(tlb->start, addr); - tlb->end = max(tlb->end, addr + PAGE_SIZE); } } -/* - * Memorize the range for the TLB flush. - */ -static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, - unsigned long addr) -{ - tlb_add_flush(tlb, addr); -} - -/* - * In the case of tlb vma handling, we can optimise these away in the - * case where we're doing a full MM flush. When we're doing a munmap, - * the vmas are adjusted to only cover the region to be torn down. - */ -static inline void tlb_start_vma(struct mmu_gather *tlb, - struct vm_area_struct *vma) -{ - if (!tlb->fullmm) { - tlb->start = TASK_SIZE; - tlb->end = 0; - } -} - -static inline void tlb_end_vma(struct mmu_gather *tlb, - struct vm_area_struct *vma) -{ - if (!tlb->fullmm) - tlb_flush(tlb); -} - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { pgtable_page_dtor(pte); - tlb_add_flush(tlb, addr); - tlb_remove_page(tlb, pte); + tlb_remove_entry(tlb, pte); } #if CONFIG_ARM64_PGTABLE_LEVELS > 2 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { - tlb_add_flush(tlb, addr); - tlb_remove_page(tlb, virt_to_page(pmdp)); + tlb_remove_entry(tlb, virt_to_page(pmdp)); } #endif @@ -104,15 +64,8 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { - tlb_add_flush(tlb, addr); - tlb_remove_page(tlb, virt_to_page(pudp)); + tlb_remove_entry(tlb, virt_to_page(pudp)); } #endif -static inline void __tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, - unsigned long address) -{ - tlb_add_flush(tlb, address); -} - #endif diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 10ca8ff93cc2..232e4ba5d314 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -18,6 +18,22 @@ #ifndef __ASM_TRAP_H #define __ASM_TRAP_H +#include <linux/list.h> + +struct pt_regs; + +struct undef_hook { + struct list_head node; + u32 instr_mask; + u32 instr_val; + u64 pstate_mask; + u64 pstate_val; + int (*fn)(struct pt_regs *regs, u32 instr); +}; + +void register_undef_hook(struct undef_hook *hook); +void unregister_undef_hook(struct undef_hook *hook); + static inline int in_exception_text(unsigned long ptr) { extern char __exception_text_start[]; diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 6d2bf419431d..b780c6c76eec 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -31,6 +31,9 @@ * Compat syscall numbers used by the AArch64 kernel. */ #define __NR_compat_restart_syscall 0 +#define __NR_compat_exit 1 +#define __NR_compat_read 3 +#define __NR_compat_write 4 #define __NR_compat_sigreturn 119 #define __NR_compat_rt_sigreturn 173 @@ -41,7 +44,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 386 +#define __NR_compat_syscalls 387 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index da1f06b535e3..8893cebcea5b 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -787,8 +787,11 @@ __SYSCALL(__NR_sched_setattr, sys_sched_setattr) __SYSCALL(__NR_sched_getattr, sys_sched_getattr) #define __NR_renameat2 382 __SYSCALL(__NR_renameat2, sys_renameat2) - /* 383 for seccomp */ +#define __NR_seccomp 383 +__SYSCALL(__NR_seccomp, sys_seccomp) #define __NR_getrandom 384 __SYSCALL(__NR_getrandom, sys_getrandom) #define __NR_memfd_create 385 __SYSCALL(__NR_memfd_create, sys_memfd_create) +#define __NR_bpf 386 +__SYSCALL(__NR_bpf, sys_bpf) diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h index dde3fc9c49f0..2052102b4e02 100644 --- a/arch/arm64/include/asm/xen/page-coherent.h +++ b/arch/arm64/include/asm/xen/page-coherent.h @@ -1,43 +1 @@ -#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H -#define _ASM_ARM64_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) -{ -} - -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) -{ -} - -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction 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) -{ -} -#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */ +#include <../../arm/include/asm/xen/page-coherent.h> diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index e633ff8cdec8..8e38878c87c6 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -37,6 +37,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE +#define __KVM_HAVE_READONLY_MEM #define KVM_REG_SIZE(id) \ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) @@ -159,6 +160,7 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) +#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 |