diff options
Diffstat (limited to 'arch/arm64/include')
-rw-r--r-- | arch/arm64/include/asm/alternative.h | 24 | ||||
-rw-r--r-- | arch/arm64/include/asm/atomic_ll_sc.h | 108 | ||||
-rw-r--r-- | arch/arm64/include/asm/atomic_lse.h | 46 | ||||
-rw-r--r-- | arch/arm64/include/asm/checksum.h | 5 | ||||
-rw-r--r-- | arch/arm64/include/asm/cmpxchg.h | 116 | ||||
-rw-r--r-- | arch/arm64/include/asm/debug-monitors.h | 2 | ||||
-rw-r--r-- | arch/arm64/include/asm/kvm_arm.h | 4 | ||||
-rw-r--r-- | arch/arm64/include/asm/kvm_asm.h | 43 | ||||
-rw-r--r-- | arch/arm64/include/asm/kvm_host.h | 8 | ||||
-rw-r--r-- | arch/arm64/include/asm/numa.h | 3 | ||||
-rw-r--r-- | arch/arm64/include/asm/pgtable-prot.h | 2 | ||||
-rw-r--r-- | arch/arm64/include/asm/pgtable.h | 34 | ||||
-rw-r--r-- | arch/arm64/include/asm/word-at-a-time.h | 10 |
13 files changed, 234 insertions, 171 deletions
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 4ed869845a23..ad986cfa592d 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -68,13 +68,13 @@ void apply_alternatives(void *start, size_t length); ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature) \ ".popsection\n" \ - ".pushsection .altinstr_replacement, \"a\"\n" \ + ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".popsection\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ - ".org . - (662b-661b) + (664b-663b)\n" \ + ".org . - (662b-661b) + (664b-663b)\n\t" \ + ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ @@ -112,11 +112,11 @@ void apply_alternatives(void *start, size_t length); 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 663: \insn2 -664: .popsection - .org . - (664b-663b) + (662b-661b) +664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) + .previous .endif .endm @@ -155,7 +155,7 @@ void apply_alternatives(void *start, size_t length); .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm @@ -174,9 +174,9 @@ void apply_alternatives(void *start, size_t length); .macro alternative_else 662: .if .Lasm_alt_mode==0 - .pushsection .altinstr_replacement, "ax" + .subsection 1 .else - .popsection + .previous .endif 663: .endm @@ -186,11 +186,11 @@ void apply_alternatives(void *start, size_t length); */ .macro alternative_endif 664: - .if .Lasm_alt_mode==0 - .popsection - .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) + .if .Lasm_alt_mode==0 + .previous + .endif .endm /* diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index f5a2d09afb38..1cc42441bc67 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -37,7 +37,7 @@ * (the optimize attribute silently ignores these options). */ -#define ATOMIC_OP(op, asm_op) \ +#define ATOMIC_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v)) \ { \ @@ -51,11 +51,11 @@ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v)) \ " stxr %w1, %w0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(atomic_##op); -#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE int \ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \ { \ @@ -70,14 +70,14 @@ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(atomic_##op##_return##name); -#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \ __LL_SC_INLINE int \ __LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v)) \ { \ @@ -92,7 +92,7 @@ __LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -110,8 +110,8 @@ __LL_SC_EXPORT(atomic_fetch_##op##name); ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(add, add) -ATOMIC_OPS(sub, sub) +ATOMIC_OPS(add, add, I) +ATOMIC_OPS(sub, sub, J) #undef ATOMIC_OPS #define ATOMIC_OPS(...) \ @@ -121,17 +121,17 @@ ATOMIC_OPS(sub, sub) ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(and, and) -ATOMIC_OPS(andnot, bic) -ATOMIC_OPS(or, orr) -ATOMIC_OPS(xor, eor) +ATOMIC_OPS(and, and, ) +ATOMIC_OPS(andnot, bic, ) +ATOMIC_OPS(or, orr, ) +ATOMIC_OPS(xor, eor, ) #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define ATOMIC64_OP(op, asm_op) \ +#define ATOMIC64_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v)) \ { \ @@ -145,11 +145,11 @@ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v)) \ " stxr %w1, %0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(atomic64_##op); -#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \ { \ @@ -164,14 +164,14 @@ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(atomic64_##op##_return##name); -#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v)) \ { \ @@ -186,7 +186,7 @@ __LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -204,8 +204,8 @@ __LL_SC_EXPORT(atomic64_fetch_##op##name); ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(add, add) -ATOMIC64_OPS(sub, sub) +ATOMIC64_OPS(add, add, I) +ATOMIC64_OPS(sub, sub, J) #undef ATOMIC64_OPS #define ATOMIC64_OPS(...) \ @@ -215,10 +215,10 @@ ATOMIC64_OPS(sub, sub) ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(and, and) -ATOMIC64_OPS(andnot, bic) -ATOMIC64_OPS(or, orr) -ATOMIC64_OPS(xor, eor) +ATOMIC64_OPS(and, and, L) +ATOMIC64_OPS(andnot, bic, ) +ATOMIC64_OPS(or, orr, L) +ATOMIC64_OPS(xor, eor, L) #undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP @@ -248,48 +248,54 @@ __LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v)) } __LL_SC_EXPORT(atomic64_dec_if_positive); -#define __CMPXCHG_CASE(w, sz, name, mb, acq, rel, cl) \ -__LL_SC_INLINE unsigned long \ -__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new)) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint) \ +__LL_SC_INLINE u##sz \ +__LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ + unsigned long old, \ + u##sz new)) \ { \ - unsigned long tmp, oldval; \ + unsigned long tmp; \ + u##sz oldval; \ \ asm volatile( \ " prfm pstl1strm, %[v]\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "[oldval], %[v]\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \ " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ " cbnz %" #w "[tmp], 2f\n" \ - " st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \ + " st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ - [v] "+Q" (*(unsigned long *)ptr) \ - : [old] "Lr" (old), [new] "r" (new) \ + [v] "+Q" (*(u##sz *)ptr) \ + : [old] #constraint "r" (old), [new] "r" (new) \ : cl); \ \ return oldval; \ } \ -__LL_SC_EXPORT(__cmpxchg_case_##name); +__LL_SC_EXPORT(__cmpxchg_case_##name##sz); -__CMPXCHG_CASE(w, b, 1, , , , ) -__CMPXCHG_CASE(w, h, 2, , , , ) -__CMPXCHG_CASE(w, , 4, , , , ) -__CMPXCHG_CASE( , , 8, , , , ) -__CMPXCHG_CASE(w, b, acq_1, , a, , "memory") -__CMPXCHG_CASE(w, h, acq_2, , a, , "memory") -__CMPXCHG_CASE(w, , acq_4, , a, , "memory") -__CMPXCHG_CASE( , , acq_8, , a, , "memory") -__CMPXCHG_CASE(w, b, rel_1, , , l, "memory") -__CMPXCHG_CASE(w, h, rel_2, , , l, "memory") -__CMPXCHG_CASE(w, , rel_4, , , l, "memory") -__CMPXCHG_CASE( , , rel_8, , , l, "memory") -__CMPXCHG_CASE(w, b, mb_1, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, h, mb_2, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, , mb_4, dmb ish, , l, "memory") -__CMPXCHG_CASE( , , mb_8, dmb ish, , l, "memory") +/* + * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly + * handle the 'K' constraint for the value 4294967295 - thus we use no + * constraint for 32 bit operations. + */ +__CMPXCHG_CASE(w, b, , 8, , , , , ) +__CMPXCHG_CASE(w, h, , 16, , , , , ) +__CMPXCHG_CASE(w, , , 32, , , , , ) +__CMPXCHG_CASE( , , , 64, , , , , L) +__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory", ) +__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory", ) +__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory", ) +__CMPXCHG_CASE( , , acq_, 64, , a, , "memory", L) +__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory", ) +__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory", ) +__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory", ) +__CMPXCHG_CASE( , , rel_, 64, , , l, "memory", L) +__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory", ) +__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory", L) #undef __CMPXCHG_CASE diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index f9b0b09153e0..4d6f917b654e 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -446,22 +446,22 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) #define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op) -#define __CMPXCHG_CASE(w, sz, name, mb, cl...) \ -static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ +static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ + unsigned long old, \ + u##sz new) \ { \ register unsigned long x0 asm ("x0") = (unsigned long)ptr; \ register unsigned long x1 asm ("x1") = old; \ - register unsigned long x2 asm ("x2") = new; \ + register u##sz x2 asm ("x2") = new; \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - __LL_SC_CMPXCHG(name) \ + __LL_SC_CMPXCHG(name##sz) \ __nops(2), \ /* LSE atomics */ \ " mov " #w "30, %" #w "[old]\n" \ - " cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \ + " cas" #mb #sfx "\t" #w "30, %" #w "[new], %[v]\n" \ " mov %" #w "[ret], " #w "30") \ : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \ : [old] "r" (x1), [new] "r" (x2) \ @@ -470,22 +470,22 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ return x0; \ } -__CMPXCHG_CASE(w, b, 1, ) -__CMPXCHG_CASE(w, h, 2, ) -__CMPXCHG_CASE(w, , 4, ) -__CMPXCHG_CASE(x, , 8, ) -__CMPXCHG_CASE(w, b, acq_1, a, "memory") -__CMPXCHG_CASE(w, h, acq_2, a, "memory") -__CMPXCHG_CASE(w, , acq_4, a, "memory") -__CMPXCHG_CASE(x, , acq_8, a, "memory") -__CMPXCHG_CASE(w, b, rel_1, l, "memory") -__CMPXCHG_CASE(w, h, rel_2, l, "memory") -__CMPXCHG_CASE(w, , rel_4, l, "memory") -__CMPXCHG_CASE(x, , rel_8, l, "memory") -__CMPXCHG_CASE(w, b, mb_1, al, "memory") -__CMPXCHG_CASE(w, h, mb_2, al, "memory") -__CMPXCHG_CASE(w, , mb_4, al, "memory") -__CMPXCHG_CASE(x, , mb_8, al, "memory") +__CMPXCHG_CASE(w, b, , 8, ) +__CMPXCHG_CASE(w, h, , 16, ) +__CMPXCHG_CASE(w, , , 32, ) +__CMPXCHG_CASE(x, , , 64, ) +__CMPXCHG_CASE(w, b, acq_, 8, a, "memory") +__CMPXCHG_CASE(w, h, acq_, 16, a, "memory") +__CMPXCHG_CASE(w, , acq_, 32, a, "memory") +__CMPXCHG_CASE(x, , acq_, 64, a, "memory") +__CMPXCHG_CASE(w, b, rel_, 8, l, "memory") +__CMPXCHG_CASE(w, h, rel_, 16, l, "memory") +__CMPXCHG_CASE(w, , rel_, 32, l, "memory") +__CMPXCHG_CASE(x, , rel_, 64, l, "memory") +__CMPXCHG_CASE(w, b, mb_, 8, al, "memory") +__CMPXCHG_CASE(w, h, mb_, 16, al, "memory") +__CMPXCHG_CASE(w, , mb_, 32, al, "memory") +__CMPXCHG_CASE(x, , mb_, 64, al, "memory") #undef __LL_SC_CMPXCHG #undef __CMPXCHG_CASE diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index 0b6f5a7d4027..fd11e0d70e44 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -30,16 +30,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; + int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; - ihl -= 4; + n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; - } while (--ihl); + } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force u32)(sum >> 32)); diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 9b2e2e2e728a..ed6a1aae6fbb 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -29,46 +29,46 @@ * barrier case is generated as release+dmb for the former and * acquire+release for the latter. */ -#define __XCHG_CASE(w, sz, name, mb, nop_lse, acq, acq_lse, rel, cl) \ -static inline unsigned long __xchg_case_##name(unsigned long x, \ - volatile void *ptr) \ -{ \ - unsigned long ret, tmp; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - " prfm pstl1strm, %2\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "0, %2\n" \ - " st" #rel "xr" #sz "\t%w1, %" #w "3, %2\n" \ - " cbnz %w1, 1b\n" \ - " " #mb, \ - /* LSE atomics */ \ - " swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \ - __nops(3) \ - " " #nop_lse) \ - : "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr) \ - : "r" (x) \ - : cl); \ - \ - return ret; \ +#define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl) \ +static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr) \ +{ \ + u##sz ret; \ + unsigned long tmp; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " prfm pstl1strm, %2\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "0, %2\n" \ + " st" #rel "xr" #sfx "\t%w1, %" #w "3, %2\n" \ + " cbnz %w1, 1b\n" \ + " " #mb, \ + /* LSE atomics */ \ + " swp" #acq_lse #rel #sfx "\t%" #w "3, %" #w "0, %2\n" \ + __nops(3) \ + " " #nop_lse) \ + : "=&r" (ret), "=&r" (tmp), "+Q" (*(u##sz *)ptr) \ + : "r" (x) \ + : cl); \ + \ + return ret; \ } -__XCHG_CASE(w, b, 1, , , , , , ) -__XCHG_CASE(w, h, 2, , , , , , ) -__XCHG_CASE(w, , 4, , , , , , ) -__XCHG_CASE( , , 8, , , , , , ) -__XCHG_CASE(w, b, acq_1, , , a, a, , "memory") -__XCHG_CASE(w, h, acq_2, , , a, a, , "memory") -__XCHG_CASE(w, , acq_4, , , a, a, , "memory") -__XCHG_CASE( , , acq_8, , , a, a, , "memory") -__XCHG_CASE(w, b, rel_1, , , , , l, "memory") -__XCHG_CASE(w, h, rel_2, , , , , l, "memory") -__XCHG_CASE(w, , rel_4, , , , , l, "memory") -__XCHG_CASE( , , rel_8, , , , , l, "memory") -__XCHG_CASE(w, b, mb_1, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, h, mb_2, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, , mb_4, dmb ish, nop, , a, l, "memory") -__XCHG_CASE( , , mb_8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, b, , 8, , , , , , ) +__XCHG_CASE(w, h, , 16, , , , , , ) +__XCHG_CASE(w, , , 32, , , , , , ) +__XCHG_CASE( , , , 64, , , , , , ) +__XCHG_CASE(w, b, acq_, 8, , , a, a, , "memory") +__XCHG_CASE(w, h, acq_, 16, , , a, a, , "memory") +__XCHG_CASE(w, , acq_, 32, , , a, a, , "memory") +__XCHG_CASE( , , acq_, 64, , , a, a, , "memory") +__XCHG_CASE(w, b, rel_, 8, , , , , l, "memory") +__XCHG_CASE(w, h, rel_, 16, , , , , l, "memory") +__XCHG_CASE(w, , rel_, 32, , , , , l, "memory") +__XCHG_CASE( , , rel_, 64, , , , , l, "memory") +__XCHG_CASE(w, b, mb_, 8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, h, mb_, 16, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, , mb_, 32, dmb ish, nop, , a, l, "memory") +__XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE @@ -79,13 +79,13 @@ static __always_inline unsigned long __xchg##sfx(unsigned long x, \ { \ switch (size) { \ case 1: \ - return __xchg_case##sfx##_1(x, ptr); \ + return __xchg_case##sfx##_8(x, ptr); \ case 2: \ - return __xchg_case##sfx##_2(x, ptr); \ + return __xchg_case##sfx##_16(x, ptr); \ case 4: \ - return __xchg_case##sfx##_4(x, ptr); \ + return __xchg_case##sfx##_32(x, ptr); \ case 8: \ - return __xchg_case##sfx##_8(x, ptr); \ + return __xchg_case##sfx##_64(x, ptr); \ default: \ BUILD_BUG(); \ } \ @@ -122,13 +122,13 @@ static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpxchg_case##sfx##_1(ptr, (u8)old, new); \ + return __cmpxchg_case##sfx##_8(ptr, (u8)old, new); \ case 2: \ - return __cmpxchg_case##sfx##_2(ptr, (u16)old, new); \ + return __cmpxchg_case##sfx##_16(ptr, (u16)old, new); \ case 4: \ - return __cmpxchg_case##sfx##_4(ptr, old, new); \ + return __cmpxchg_case##sfx##_32(ptr, old, new); \ case 8: \ - return __cmpxchg_case##sfx##_8(ptr, old, new); \ + return __cmpxchg_case##sfx##_64(ptr, old, new); \ default: \ BUILD_BUG(); \ } \ @@ -222,16 +222,16 @@ __CMPXCHG_GEN(_mb) __ret; \ }) -#define __CMPWAIT_CASE(w, sz, name) \ -static inline void __cmpwait_case_##name(volatile void *ptr, \ - unsigned long val) \ +#define __CMPWAIT_CASE(w, sfx, sz) \ +static inline void __cmpwait_case_##sz(volatile void *ptr, \ + unsigned long val) \ { \ unsigned long tmp; \ \ asm volatile( \ " sevl\n" \ " wfe\n" \ - " ldxr" #sz "\t%" #w "[tmp], %[v]\n" \ + " ldxr" #sfx "\t%" #w "[tmp], %[v]\n" \ " eor %" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ " cbnz %" #w "[tmp], 1f\n" \ " wfe\n" \ @@ -240,10 +240,10 @@ static inline void __cmpwait_case_##name(volatile void *ptr, \ : [val] "r" (val)); \ } -__CMPWAIT_CASE(w, b, 1); -__CMPWAIT_CASE(w, h, 2); -__CMPWAIT_CASE(w, , 4); -__CMPWAIT_CASE( , , 8); +__CMPWAIT_CASE(w, b, 8); +__CMPWAIT_CASE(w, h, 16); +__CMPWAIT_CASE(w, , 32); +__CMPWAIT_CASE( , , 64); #undef __CMPWAIT_CASE @@ -254,13 +254,13 @@ static __always_inline void __cmpwait##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpwait_case##sfx##_1(ptr, (u8)val); \ + return __cmpwait_case##sfx##_8(ptr, (u8)val); \ case 2: \ - return __cmpwait_case##sfx##_2(ptr, (u16)val); \ + return __cmpwait_case##sfx##_16(ptr, (u16)val); \ case 4: \ - return __cmpwait_case##sfx##_4(ptr, val); \ + return __cmpwait_case##sfx##_32(ptr, val); \ case 8: \ - return __cmpwait_case##sfx##_8(ptr, val); \ + return __cmpwait_case##sfx##_64(ptr, val); \ default: \ BUILD_BUG(); \ } \ diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index a44cf5225429..41b065f1be88 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -119,6 +119,8 @@ void disable_debug_monitors(enum dbg_active_el el); void user_rewind_single_step(struct task_struct *task); void user_fastforward_single_step(struct task_struct *task); +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task); void kernel_enable_single_step(struct pt_regs *regs); void kernel_disable_single_step(void); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 1d6d980f80ac..72ed11292df3 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -78,10 +78,11 @@ * 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 + * PTW: Take a stage2 fault if a stage1 walk steps in device memory */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ - HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW) + HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_PTW) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) @@ -190,6 +191,7 @@ #define CPTR_EL2_DEFAULT 0x000033ff /* Hyp Debug Configuration Register bits */ +#define MDCR_EL2_TTRF (1 << 19) #define MDCR_EL2_TPMS (1 << 14) #define MDCR_EL2_E2PB_MASK (UL(0x3)) #define MDCR_EL2_E2PB_SHIFT (UL(12)) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index c59e81b65132..b0f0fb81f5f5 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -83,6 +83,34 @@ extern u32 __init_stage2_translation(void); *__hyp_this_cpu_ptr(sym); \ }) +#define __KVM_EXTABLE(from, to) \ + " .pushsection __kvm_ex_table, \"a\"\n" \ + " .align 3\n" \ + " .long (" #from " - .), (" #to " - .)\n" \ + " .popsection\n" + + +#define __kvm_at(at_op, addr) \ +( { \ + int __kvm_at_err = 0; \ + u64 spsr, elr; \ + asm volatile( \ + " mrs %1, spsr_el2\n" \ + " mrs %2, elr_el2\n" \ + "1: at "at_op", %3\n" \ + " isb\n" \ + " b 9f\n" \ + "2: msr spsr_el2, %1\n" \ + " msr elr_el2, %2\n" \ + " mov %w0, %4\n" \ + "9:\n" \ + __KVM_EXTABLE(1b, 2b) \ + : "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr) \ + : "r" (addr), "i" (-EFAULT)); \ + __kvm_at_err; \ +} ) + + #else /* __ASSEMBLY__ */ .macro hyp_adr_this_cpu reg, sym, tmp @@ -107,6 +135,21 @@ extern u32 __init_stage2_translation(void); kern_hyp_va \vcpu .endm +/* + * KVM extable for unexpected exceptions. + * In the same format _asm_extable, but output to a different section so that + * it can be mapped to EL2. The KVM version is not sorted. The caller must + * ensure: + * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented + * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup. + */ +.macro _kvm_extable, from, to + .pushsection __kvm_ex_table, "a" + .align 3 + .long (\from - .), (\to - .) + .popsection +.endm + #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f982c9d1d10b..8d94404829f0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -158,6 +158,7 @@ enum vcpu_sysreg { #define c2_TTBR1 (TTBR1_EL1 * 2) /* Translation Table Base Register 1 */ #define c2_TTBR1_high (c2_TTBR1 + 1) /* TTBR1 top 32 bits */ #define c2_TTBCR (TCR_EL1 * 2) /* Translation Table Base Control R. */ +#define c2_TTBCR2 (c2_TTBCR + 1) /* Translation Table Base Control R. 2 */ #define c3_DACR (DACR32_EL2 * 2)/* Domain Access Control Register */ #define c5_DFSR (ESR_EL1 * 2) /* Data Fault Status Register */ #define c5_IFSR (IFSR32_EL2 * 2)/* Instruction Fault Status Register */ @@ -185,6 +186,7 @@ enum vcpu_sysreg { #define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) #define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) #define cp14_DBGDCCINT (MDCCINT_EL1 * 2) +#define cp14_DBGVCR (DBGVCR32_EL2 * 2) #define NR_COPRO_REGS (NR_SYS_REGS * 2) @@ -292,8 +294,10 @@ struct kvm_vcpu_arch { * CP14 and CP15 live in the same array, as they are backed by the * same system registers. */ -#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r)]) -#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r)]) +#define CPx_BIAS IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) + +#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) +#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) #ifdef CONFIG_CPU_BIG_ENDIAN #define vcpu_cp15_64_high(v,r) vcpu_cp15((v),(r)) diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index 01bc46d5b43a..9bde63602767 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -25,6 +25,9 @@ const struct cpumask *cpumask_of_node(int node); /* Returns a pointer to the cpumask of CPUs on Node 'node'. */ static inline const struct cpumask *cpumask_of_node(int node) { + if (node == NUMA_NO_NODE) + return cpu_all_mask; + return node_to_cpumask_map[node]; } #endif diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 26efe251f076..6415677ffe8d 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -65,7 +65,7 @@ #define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN) #define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY) #define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN) -#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) +#define PAGE_HYP_DEVICE __pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN) #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_RDONLY | PTE_UXN) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 324db23b37de..6147e58babf0 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -92,8 +92,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -#define pte_valid_young(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) @@ -101,9 +99,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. + * Note that we can't make any assumptions based on the state of the access + * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * TLB. */ #define pte_accessible(mm, pte) \ - (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (subject to the @@ -129,13 +130,6 @@ static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) return pte; } -static inline pte_t pte_wrprotect(pte_t pte) -{ - pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); - return pte; -} - static inline pte_t pte_mkwrite(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); @@ -161,6 +155,20 @@ static inline pte_t pte_mkdirty(pte_t pte) return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + + pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + return pte; +} + static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); @@ -642,12 +650,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres pte = READ_ONCE(*ptep); do { old_pte = pte; - /* - * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY - * clear), set the PTE_DIRTY bit. - */ - if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h index b0d708ff7f4e..a2601c1ccf43 100644 --- a/arch/arm64/include/asm/word-at-a-time.h +++ b/arch/arm64/include/asm/word-at-a-time.h @@ -64,7 +64,7 @@ static inline unsigned long find_zero(unsigned long mask) */ static inline unsigned long load_unaligned_zeropad(const void *addr) { - unsigned long ret, offset; + unsigned long ret, tmp; /* Load word from unaligned pointer addr */ asm( @@ -72,9 +72,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) "2:\n" " .pushsection .fixup,\"ax\"\n" " .align 2\n" - "3: and %1, %2, #0x7\n" - " bic %2, %2, #0x7\n" - " ldr %0, [%2]\n" + "3: bic %1, %2, #0x7\n" + " ldr %0, [%1]\n" + " and %1, %2, #0x7\n" " lsl %1, %1, #0x3\n" #ifndef __AARCH64EB__ " lsr %0, %0, %1\n" @@ -84,7 +84,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) " b 2b\n" " .popsection\n" _ASM_EXTABLE(1b, 3b) - : "=&r" (ret), "=&r" (offset) + : "=&r" (ret), "=&r" (tmp) : "r" (addr), "Q" (*(unsigned long *)addr)); return ret; |