diff options
Diffstat (limited to 'arch/arm64/include/asm')
68 files changed, 1539 insertions, 1049 deletions
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index c52e151afab0..98a5405c8558 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -4,6 +4,7 @@ generic-y += delay.h generic-y += div64.h generic-y += dma.h generic-y += dma-contiguous.h +generic-y += dma-mapping.h generic-y += early_ioremap.h generic-y += emergency-restart.h generic-y += hw_irq.h diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index ada0bc480a1b..b263e239cb59 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -38,6 +38,9 @@ (!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \ (unsigned long)(entry) + (entry)->header.length > (end)) +#define ACPI_MADT_GICC_SPE (ACPI_OFFSET(struct acpi_madt_generic_interrupt, \ + spe_interrupt) + sizeof(u16)) + /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI pgprot_t __acpi_get_mem_attribute(phys_addr_t addr); diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 2247908e55d6..89e4c8b79349 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -152,7 +152,15 @@ static inline bool gic_prio_masking_enabled(void) static inline void gic_pmr_mask_irqs(void) { - BUILD_BUG_ON(GICD_INT_DEF_PRI <= GIC_PRIO_IRQOFF); + BUILD_BUG_ON(GICD_INT_DEF_PRI < (GIC_PRIO_IRQOFF | + GIC_PRIO_PSR_I_SET)); + BUILD_BUG_ON(GICD_INT_DEF_PRI >= GIC_PRIO_IRQON); + /* + * Need to make sure IRQON allows IRQs when SCR_EL3.FIQ is cleared + * and non-secure PMR accesses are not subject to the shifts that + * are applied to IRQ priorities + */ + BUILD_BUG_ON((0x80 | (GICD_INT_DEF_PRI >> 1)) >= GIC_PRIO_IRQON); gic_write_pmr(GIC_PRIO_IRQOFF); } diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index 6756178c27db..7ae54d7d333a 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -9,6 +9,7 @@ #define __ASM_ARCH_TIMER_H #include <asm/barrier.h> +#include <asm/hwcap.h> #include <asm/sysreg.h> #include <linux/bug.h> @@ -229,4 +230,16 @@ static inline int arch_timer_arch_init(void) return 0; } +static inline void arch_timer_set_evtstrm_feature(void) +{ + cpu_set_named_feature(EVTSTRM); +#ifdef CONFIG_COMPAT + compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM; +#endif +} + +static inline bool arch_timer_have_evtstrm_feature(void) +{ + return cpu_have_named_feature(EVTSTRM); +} #endif diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 570d195a184d..b8cf7c85ffa2 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -96,7 +96,11 @@ * RAS Error Synchronization barrier */ .macro esb +#ifdef CONFIG_ARM64_RAS_EXTN hint #16 +#else + nop +#endif .endm /* @@ -120,17 +124,6 @@ alternative_endif .endm /* - * Sanitise a 64-bit bounded index wrt speculation, returning zero if out - * of bounds. - */ - .macro mask_nospec64, idx, limit, tmp - sub \tmp, \idx, \limit - bic \tmp, \tmp, \idx - and \idx, \idx, \tmp, asr #63 - csdb - .endm - -/* * NOP sequence */ .macro nops, num @@ -346,6 +339,13 @@ alternative_endif .endm /* + * tcr_set_t1sz - update TCR.T1SZ + */ + .macro tcr_set_t1sz, valreg, t1sz + bfi \valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH + .endm + +/* * tcr_compute_pa_size - set TCR.(I)PS to the highest supported * ID_AA64MMFR0_EL1.PARange value * @@ -534,9 +534,13 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU * In future this may be nop'ed out when dealing with 52-bit kernel VAs. * ttbr: Value of ttbr to set, modified. */ - .macro offset_ttbr1, ttbr -#ifdef CONFIG_ARM64_USER_VA_BITS_52 + .macro offset_ttbr1, ttbr, tmp +#ifdef CONFIG_ARM64_VA_BITS_52 + mrs_s \tmp, SYS_ID_AA64MMFR2_EL1 + and \tmp, \tmp, #(0xf << ID_AA64MMFR2_LVA_SHIFT) + cbnz \tmp, .Lskipoffs_\@ orr \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET +.Lskipoffs_\@ : #endif .endm @@ -546,7 +550,7 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU * to be nop'ed out when dealing with 52-bit kernel VAs. */ .macro restore_ttbr1, ttbr -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#ifdef CONFIG_ARM64_VA_BITS_52 bic \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET #endif .endm diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 657b0457d83c..9543b5e0534d 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -13,21 +13,91 @@ #include <linux/types.h> #include <asm/barrier.h> +#include <asm/cmpxchg.h> #include <asm/lse.h> -#ifdef __KERNEL__ - -#define __ARM64_IN_ATOMIC_IMPL - -#if defined(CONFIG_ARM64_LSE_ATOMICS) && defined(CONFIG_AS_LSE) -#include <asm/atomic_lse.h> -#else -#include <asm/atomic_ll_sc.h> -#endif - -#undef __ARM64_IN_ATOMIC_IMPL - -#include <asm/cmpxchg.h> +#define ATOMIC_OP(op) \ +static inline void arch_##op(int i, atomic_t *v) \ +{ \ + __lse_ll_sc_body(op, i, v); \ +} + +ATOMIC_OP(atomic_andnot) +ATOMIC_OP(atomic_or) +ATOMIC_OP(atomic_xor) +ATOMIC_OP(atomic_add) +ATOMIC_OP(atomic_and) +ATOMIC_OP(atomic_sub) + +#undef ATOMIC_OP + +#define ATOMIC_FETCH_OP(name, op) \ +static inline int arch_##op##name(int i, atomic_t *v) \ +{ \ + return __lse_ll_sc_body(op##name, i, v); \ +} + +#define ATOMIC_FETCH_OPS(op) \ + ATOMIC_FETCH_OP(_relaxed, op) \ + ATOMIC_FETCH_OP(_acquire, op) \ + ATOMIC_FETCH_OP(_release, op) \ + ATOMIC_FETCH_OP( , op) + +ATOMIC_FETCH_OPS(atomic_fetch_andnot) +ATOMIC_FETCH_OPS(atomic_fetch_or) +ATOMIC_FETCH_OPS(atomic_fetch_xor) +ATOMIC_FETCH_OPS(atomic_fetch_add) +ATOMIC_FETCH_OPS(atomic_fetch_and) +ATOMIC_FETCH_OPS(atomic_fetch_sub) +ATOMIC_FETCH_OPS(atomic_add_return) +ATOMIC_FETCH_OPS(atomic_sub_return) + +#undef ATOMIC_FETCH_OP +#undef ATOMIC_FETCH_OPS + +#define ATOMIC64_OP(op) \ +static inline void arch_##op(long i, atomic64_t *v) \ +{ \ + __lse_ll_sc_body(op, i, v); \ +} + +ATOMIC64_OP(atomic64_andnot) +ATOMIC64_OP(atomic64_or) +ATOMIC64_OP(atomic64_xor) +ATOMIC64_OP(atomic64_add) +ATOMIC64_OP(atomic64_and) +ATOMIC64_OP(atomic64_sub) + +#undef ATOMIC64_OP + +#define ATOMIC64_FETCH_OP(name, op) \ +static inline long arch_##op##name(long i, atomic64_t *v) \ +{ \ + return __lse_ll_sc_body(op##name, i, v); \ +} + +#define ATOMIC64_FETCH_OPS(op) \ + ATOMIC64_FETCH_OP(_relaxed, op) \ + ATOMIC64_FETCH_OP(_acquire, op) \ + ATOMIC64_FETCH_OP(_release, op) \ + ATOMIC64_FETCH_OP( , op) + +ATOMIC64_FETCH_OPS(atomic64_fetch_andnot) +ATOMIC64_FETCH_OPS(atomic64_fetch_or) +ATOMIC64_FETCH_OPS(atomic64_fetch_xor) +ATOMIC64_FETCH_OPS(atomic64_fetch_add) +ATOMIC64_FETCH_OPS(atomic64_fetch_and) +ATOMIC64_FETCH_OPS(atomic64_fetch_sub) +ATOMIC64_FETCH_OPS(atomic64_add_return) +ATOMIC64_FETCH_OPS(atomic64_sub_return) + +#undef ATOMIC64_FETCH_OP +#undef ATOMIC64_FETCH_OPS + +static inline long arch_atomic64_dec_if_positive(atomic64_t *v) +{ + return __lse_ll_sc_body(atomic64_dec_if_positive, v); +} #define ATOMIC_INIT(i) { (i) } @@ -157,5 +227,4 @@ #include <asm-generic/atomic-instrumented.h> -#endif -#endif +#endif /* __ASM_ATOMIC_H */ diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 23c378606aed..7b012148bfd6 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -10,83 +10,92 @@ #ifndef __ASM_ATOMIC_LL_SC_H #define __ASM_ATOMIC_LL_SC_H -#ifndef __ARM64_IN_ATOMIC_IMPL -#error "please don't include this file directly" +#include <linux/stringify.h> + +#if IS_ENABLED(CONFIG_ARM64_LSE_ATOMICS) && IS_ENABLED(CONFIG_AS_LSE) +#define __LL_SC_FALLBACK(asm_ops) \ +" b 3f\n" \ +" .subsection 1\n" \ +"3:\n" \ +asm_ops "\n" \ +" b 4f\n" \ +" .previous\n" \ +"4:\n" +#else +#define __LL_SC_FALLBACK(asm_ops) asm_ops +#endif + +#ifndef CONFIG_CC_HAS_K_CONSTRAINT +#define K #endif /* * AArch64 UP and SMP safe atomic ops. We use load exclusive and * store exclusive to ensure that these are atomic. We may loop * to ensure that the update happens. - * - * NOTE: these functions do *not* follow the PCS and must explicitly - * save any clobbered registers other than x0 (regardless of return - * value). This is achieved through -fcall-saved-* compiler flags for - * this file, which unfortunately don't work on a per-function basis - * (the optimize attribute silently ignores these options). */ -#define ATOMIC_OP(op, asm_op) \ -__LL_SC_INLINE void \ -__LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v)) \ +#define ATOMIC_OP(op, asm_op, constraint) \ +static inline void \ +__ll_sc_atomic_##op(int i, atomic_t *v) \ { \ unsigned long tmp; \ int result; \ \ asm volatile("// atomic_" #op "\n" \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ldxr %w0, %2\n" \ " " #asm_op " %w0, %w0, %w3\n" \ " stxr %w1, %w0, %2\n" \ -" cbnz %w1, 1b" \ +" cbnz %w1, 1b\n") \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ -} \ -__LL_SC_EXPORT(arch_atomic_##op); + : __stringify(constraint) "r" (i)); \ +} -#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ -__LL_SC_INLINE int \ -__LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v)) \ +#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ +static inline int \ +__ll_sc_atomic_##op##_return##name(int i, atomic_t *v) \ { \ unsigned long tmp; \ int result; \ \ asm volatile("// atomic_" #op "_return" #name "\n" \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr %w0, %2\n" \ " " #asm_op " %w0, %w0, %w3\n" \ " st" #rel "xr %w1, %w0, %2\n" \ " cbnz %w1, 1b\n" \ -" " #mb \ +" " #mb ) \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ -} \ -__LL_SC_EXPORT(arch_atomic_##op##_return##name); +} -#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ -__LL_SC_INLINE int \ -__LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v)) \ +#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \ +static inline int \ +__ll_sc_atomic_fetch_##op##name(int i, atomic_t *v) \ { \ unsigned long tmp; \ int val, result; \ \ asm volatile("// atomic_fetch_" #op #name "\n" \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %3\n" \ "1: ld" #acq "xr %w0, %3\n" \ " " #asm_op " %w1, %w0, %w4\n" \ " st" #rel "xr %w2, %w1, %3\n" \ " cbnz %w2, 1b\n" \ -" " #mb \ +" " #mb ) \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ -} \ -__LL_SC_EXPORT(arch_atomic_fetch_##op##name); +} #define ATOMIC_OPS(...) \ ATOMIC_OP(__VA_ARGS__) \ @@ -99,8 +108,8 @@ __LL_SC_EXPORT(arch_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(...) \ @@ -110,77 +119,82 @@ 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, K) +ATOMIC_OPS(or, orr, K) +ATOMIC_OPS(xor, eor, K) +/* + * GAS converts the mysterious and undocumented BIC (immediate) alias to + * an AND (immediate) instruction with the immediate inverted. We don't + * have a constraint for this, so fall back to register. + */ +ATOMIC_OPS(andnot, bic, ) #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define ATOMIC64_OP(op, asm_op) \ -__LL_SC_INLINE void \ -__LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v)) \ +#define ATOMIC64_OP(op, asm_op, constraint) \ +static inline void \ +__ll_sc_atomic64_##op(s64 i, atomic64_t *v) \ { \ - long result; \ + s64 result; \ unsigned long tmp; \ \ asm volatile("// atomic64_" #op "\n" \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ldxr %0, %2\n" \ " " #asm_op " %0, %0, %3\n" \ " stxr %w1, %0, %2\n" \ -" cbnz %w1, 1b" \ +" cbnz %w1, 1b") \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ -} \ -__LL_SC_EXPORT(arch_atomic64_##op); + : __stringify(constraint) "r" (i)); \ +} -#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ -__LL_SC_INLINE long \ -__LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\ +#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ +static inline long \ +__ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v) \ { \ - long result; \ + s64 result; \ unsigned long tmp; \ \ asm volatile("// atomic64_" #op "_return" #name "\n" \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr %0, %2\n" \ " " #asm_op " %0, %0, %3\n" \ " st" #rel "xr %w1, %0, %2\n" \ " cbnz %w1, 1b\n" \ -" " #mb \ +" " #mb ) \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ -} \ -__LL_SC_EXPORT(arch_atomic64_##op##_return##name); +} -#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ -__LL_SC_INLINE long \ -__LL_SC_PREFIX(arch_atomic64_fetch_##op##name(long i, atomic64_t *v)) \ +#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ +static inline long \ +__ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ { \ - long result, val; \ + s64 result, val; \ unsigned long tmp; \ \ asm volatile("// atomic64_fetch_" #op #name "\n" \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %3\n" \ "1: ld" #acq "xr %0, %3\n" \ " " #asm_op " %1, %0, %4\n" \ " st" #rel "xr %w2, %1, %3\n" \ " cbnz %w2, 1b\n" \ -" " #mb \ +" " #mb ) \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ -} \ -__LL_SC_EXPORT(arch_atomic64_fetch_##op##name); +} #define ATOMIC64_OPS(...) \ ATOMIC64_OP(__VA_ARGS__) \ @@ -193,8 +207,8 @@ __LL_SC_EXPORT(arch_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(...) \ @@ -204,23 +218,29 @@ 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(or, orr, L) +ATOMIC64_OPS(xor, eor, L) +/* + * GAS converts the mysterious and undocumented BIC (immediate) alias to + * an AND (immediate) instruction with the immediate inverted. We don't + * have a constraint for this, so fall back to register. + */ +ATOMIC64_OPS(andnot, bic, ) #undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP -__LL_SC_INLINE long -__LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v)) +static inline s64 +__ll_sc_atomic64_dec_if_positive(atomic64_t *v) { - long result; + s64 result; unsigned long tmp; asm volatile("// atomic64_dec_if_positive\n" + __LL_SC_FALLBACK( " prfm pstl1strm, %2\n" "1: ldxr %0, %2\n" " subs %0, %0, #1\n" @@ -228,20 +248,19 @@ __LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v)) " stlxr %w1, %0, %2\n" " cbnz %w1, 1b\n" " dmb ish\n" -"2:" +"2:") : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : : "cc", "memory"); return result; } -__LL_SC_EXPORT(arch_atomic64_dec_if_positive); -#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl) \ -__LL_SC_INLINE u##sz \ -__LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint) \ +static inline u##sz \ +__ll_sc__cmpxchg_case_##name##sz(volatile void *ptr, \ unsigned long old, \ - u##sz new)) \ + u##sz new) \ { \ unsigned long tmp; \ u##sz oldval; \ @@ -255,6 +274,7 @@ __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ old = (u##sz)old; \ \ asm volatile( \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %[v]\n" \ "1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \ " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ @@ -262,46 +282,51 @@ __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ " st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ - "2:" \ + "2:") \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ [v] "+Q" (*(u##sz *)ptr) \ - : [old] "Kr" (old), [new] "r" (new) \ + : [old] __stringify(constraint) "r" (old), [new] "r" (new) \ : cl); \ \ return oldval; \ -} \ -__LL_SC_EXPORT(__cmpxchg_case_##name##sz); +} -__CMPXCHG_CASE(w, b, , 8, , , , ) -__CMPXCHG_CASE(w, h, , 16, , , , ) -__CMPXCHG_CASE(w, , , 32, , , , ) -__CMPXCHG_CASE( , , , 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( , , 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( , , rel_, 64, , , l, "memory") -__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") +/* + * 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, , , , , K) +__CMPXCHG_CASE(w, h, , 16, , , , , K) +__CMPXCHG_CASE(w, , , 32, , , , , K) +__CMPXCHG_CASE( , , , 64, , , , , L) +__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory", K) +__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory", K) +__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory", K) +__CMPXCHG_CASE( , , acq_, 64, , a, , "memory", L) +__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory", K) +__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory", K) +__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory", K) +__CMPXCHG_CASE( , , rel_, 64, , , l, "memory", L) +__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory", K) +__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory", K) +__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory", K) +__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory", L) #undef __CMPXCHG_CASE #define __CMPXCHG_DBL(name, mb, rel, cl) \ -__LL_SC_INLINE long \ -__LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1, \ +static inline long \ +__ll_sc__cmpxchg_double##name(unsigned long old1, \ unsigned long old2, \ unsigned long new1, \ unsigned long new2, \ - volatile void *ptr)) \ + volatile void *ptr) \ { \ unsigned long tmp, ret; \ \ asm volatile("// __cmpxchg_double" #name "\n" \ + __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ldxp %0, %1, %2\n" \ " eor %0, %0, %3\n" \ @@ -311,18 +336,18 @@ __LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1, \ " st" #rel "xp %w0, %5, %6, %2\n" \ " cbnz %w0, 1b\n" \ " " #mb "\n" \ - "2:" \ + "2:") \ : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \ : "r" (old1), "r" (old2), "r" (new1), "r" (new2) \ : cl); \ \ return ret; \ -} \ -__LL_SC_EXPORT(__cmpxchg_double##name); +} __CMPXCHG_DBL( , , , ) __CMPXCHG_DBL(_mb, dmb ish, l, "memory") #undef __CMPXCHG_DBL +#undef K #endif /* __ASM_ATOMIC_LL_SC_H */ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index 45e030d54332..c6bd87d2915b 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -10,22 +10,13 @@ #ifndef __ASM_ATOMIC_LSE_H #define __ASM_ATOMIC_LSE_H -#ifndef __ARM64_IN_ATOMIC_IMPL -#error "please don't include this file directly" -#endif - -#define __LL_SC_ATOMIC(op) __LL_SC_CALL(arch_atomic_##op) #define ATOMIC_OP(op, asm_op) \ -static inline void arch_atomic_##op(int i, atomic_t *v) \ +static inline void __lse_atomic_##op(int i, atomic_t *v) \ { \ - register int w0 asm ("w0") = i; \ - register atomic_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(op), \ -" " #asm_op " %w[i], %[v]\n") \ - : [i] "+r" (w0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS); \ + asm volatile( \ +" " #asm_op " %w[i], %[v]\n" \ + : [i] "+r" (i), [v] "+Q" (v->counter) \ + : "r" (v)); \ } ATOMIC_OP(andnot, stclr) @@ -36,21 +27,15 @@ ATOMIC_OP(add, stadd) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...) \ -static inline int arch_atomic_fetch_##op##name(int i, atomic_t *v) \ +static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v) \ { \ - register int w0 asm ("w0") = i; \ - register atomic_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC(fetch_##op##name), \ - /* LSE atomics */ \ -" " #asm_op #mb " %w[i], %w[i], %[v]") \ - : [i] "+r" (w0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + asm volatile( \ +" " #asm_op #mb " %w[i], %w[i], %[v]" \ + : [i] "+r" (i), [v] "+Q" (v->counter) \ + : "r" (v) \ + : cl); \ \ - return w0; \ + return i; \ } #define ATOMIC_FETCH_OPS(op, asm_op) \ @@ -68,23 +53,18 @@ ATOMIC_FETCH_OPS(add, ldadd) #undef ATOMIC_FETCH_OPS #define ATOMIC_OP_ADD_RETURN(name, mb, cl...) \ -static inline int arch_atomic_add_return##name(int i, atomic_t *v) \ +static inline int __lse_atomic_add_return##name(int i, atomic_t *v) \ { \ - register int w0 asm ("w0") = i; \ - register atomic_t *x1 asm ("x1") = v; \ + u32 tmp; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC(add_return##name) \ - __nops(1), \ - /* LSE atomics */ \ - " ldadd" #mb " %w[i], w30, %[v]\n" \ - " add %w[i], %w[i], w30") \ - : [i] "+r" (w0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + asm volatile( \ + " ldadd" #mb " %w[i], %w[tmp], %[v]\n" \ + " add %w[i], %w[i], %w[tmp]" \ + : [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ + : "r" (v) \ + : cl); \ \ - return w0; \ + return i; \ } ATOMIC_OP_ADD_RETURN(_relaxed, ) @@ -94,41 +74,26 @@ ATOMIC_OP_ADD_RETURN( , al, "memory") #undef ATOMIC_OP_ADD_RETURN -static inline void arch_atomic_and(int i, atomic_t *v) +static inline void __lse_atomic_and(int i, atomic_t *v) { - register int w0 asm ("w0") = i; - register atomic_t *x1 asm ("x1") = v; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - __LL_SC_ATOMIC(and) - __nops(1), - /* LSE atomics */ + asm volatile( " mvn %w[i], %w[i]\n" - " stclr %w[i], %[v]") - : [i] "+&r" (w0), [v] "+Q" (v->counter) - : "r" (x1) - : __LL_SC_CLOBBERS); + " stclr %w[i], %[v]" + : [i] "+&r" (i), [v] "+Q" (v->counter) + : "r" (v)); } #define ATOMIC_FETCH_OP_AND(name, mb, cl...) \ -static inline int arch_atomic_fetch_and##name(int i, atomic_t *v) \ +static inline int __lse_atomic_fetch_and##name(int i, atomic_t *v) \ { \ - register int w0 asm ("w0") = i; \ - register atomic_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC(fetch_and##name) \ - __nops(1), \ - /* LSE atomics */ \ + asm volatile( \ " mvn %w[i], %w[i]\n" \ - " ldclr" #mb " %w[i], %w[i], %[v]") \ - : [i] "+&r" (w0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + " ldclr" #mb " %w[i], %w[i], %[v]" \ + : [i] "+&r" (i), [v] "+Q" (v->counter) \ + : "r" (v) \ + : cl); \ \ - return w0; \ + return i; \ } ATOMIC_FETCH_OP_AND(_relaxed, ) @@ -138,42 +103,29 @@ ATOMIC_FETCH_OP_AND( , al, "memory") #undef ATOMIC_FETCH_OP_AND -static inline void arch_atomic_sub(int i, atomic_t *v) +static inline void __lse_atomic_sub(int i, atomic_t *v) { - register int w0 asm ("w0") = i; - register atomic_t *x1 asm ("x1") = v; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - __LL_SC_ATOMIC(sub) - __nops(1), - /* LSE atomics */ + asm volatile( " neg %w[i], %w[i]\n" - " stadd %w[i], %[v]") - : [i] "+&r" (w0), [v] "+Q" (v->counter) - : "r" (x1) - : __LL_SC_CLOBBERS); + " stadd %w[i], %[v]" + : [i] "+&r" (i), [v] "+Q" (v->counter) + : "r" (v)); } #define ATOMIC_OP_SUB_RETURN(name, mb, cl...) \ -static inline int arch_atomic_sub_return##name(int i, atomic_t *v) \ +static inline int __lse_atomic_sub_return##name(int i, atomic_t *v) \ { \ - register int w0 asm ("w0") = i; \ - register atomic_t *x1 asm ("x1") = v; \ + u32 tmp; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC(sub_return##name) \ - __nops(2), \ - /* LSE atomics */ \ + asm volatile( \ " neg %w[i], %w[i]\n" \ - " ldadd" #mb " %w[i], w30, %[v]\n" \ - " add %w[i], %w[i], w30") \ - : [i] "+&r" (w0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS , ##cl); \ + " ldadd" #mb " %w[i], %w[tmp], %[v]\n" \ + " add %w[i], %w[i], %w[tmp]" \ + : [i] "+&r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ + : "r" (v) \ + : cl); \ \ - return w0; \ + return i; \ } ATOMIC_OP_SUB_RETURN(_relaxed, ) @@ -184,23 +136,16 @@ ATOMIC_OP_SUB_RETURN( , al, "memory") #undef ATOMIC_OP_SUB_RETURN #define ATOMIC_FETCH_OP_SUB(name, mb, cl...) \ -static inline int arch_atomic_fetch_sub##name(int i, atomic_t *v) \ +static inline int __lse_atomic_fetch_sub##name(int i, atomic_t *v) \ { \ - register int w0 asm ("w0") = i; \ - register atomic_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC(fetch_sub##name) \ - __nops(1), \ - /* LSE atomics */ \ + asm volatile( \ " neg %w[i], %w[i]\n" \ - " ldadd" #mb " %w[i], %w[i], %[v]") \ - : [i] "+&r" (w0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + " ldadd" #mb " %w[i], %w[i], %[v]" \ + : [i] "+&r" (i), [v] "+Q" (v->counter) \ + : "r" (v) \ + : cl); \ \ - return w0; \ + return i; \ } ATOMIC_FETCH_OP_SUB(_relaxed, ) @@ -209,20 +154,14 @@ ATOMIC_FETCH_OP_SUB(_release, l, "memory") ATOMIC_FETCH_OP_SUB( , al, "memory") #undef ATOMIC_FETCH_OP_SUB -#undef __LL_SC_ATOMIC -#define __LL_SC_ATOMIC64(op) __LL_SC_CALL(arch_atomic64_##op) #define ATOMIC64_OP(op, asm_op) \ -static inline void arch_atomic64_##op(long i, atomic64_t *v) \ +static inline void __lse_atomic64_##op(s64 i, atomic64_t *v) \ { \ - register long x0 asm ("x0") = i; \ - register atomic64_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op), \ -" " #asm_op " %[i], %[v]\n") \ - : [i] "+r" (x0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS); \ + asm volatile( \ +" " #asm_op " %[i], %[v]\n" \ + : [i] "+r" (i), [v] "+Q" (v->counter) \ + : "r" (v)); \ } ATOMIC64_OP(andnot, stclr) @@ -233,21 +172,15 @@ ATOMIC64_OP(add, stadd) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...) \ -static inline long arch_atomic64_fetch_##op##name(long i, atomic64_t *v)\ +static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\ { \ - register long x0 asm ("x0") = i; \ - register atomic64_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC64(fetch_##op##name), \ - /* LSE atomics */ \ -" " #asm_op #mb " %[i], %[i], %[v]") \ - : [i] "+r" (x0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + asm volatile( \ +" " #asm_op #mb " %[i], %[i], %[v]" \ + : [i] "+r" (i), [v] "+Q" (v->counter) \ + : "r" (v) \ + : cl); \ \ - return x0; \ + return i; \ } #define ATOMIC64_FETCH_OPS(op, asm_op) \ @@ -265,23 +198,18 @@ ATOMIC64_FETCH_OPS(add, ldadd) #undef ATOMIC64_FETCH_OPS #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...) \ -static inline long arch_atomic64_add_return##name(long i, atomic64_t *v)\ +static inline long __lse_atomic64_add_return##name(s64 i, atomic64_t *v)\ { \ - register long x0 asm ("x0") = i; \ - register atomic64_t *x1 asm ("x1") = v; \ + unsigned long tmp; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC64(add_return##name) \ - __nops(1), \ - /* LSE atomics */ \ - " ldadd" #mb " %[i], x30, %[v]\n" \ - " add %[i], %[i], x30") \ - : [i] "+r" (x0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + asm volatile( \ + " ldadd" #mb " %[i], %x[tmp], %[v]\n" \ + " add %[i], %[i], %x[tmp]" \ + : [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ + : "r" (v) \ + : cl); \ \ - return x0; \ + return i; \ } ATOMIC64_OP_ADD_RETURN(_relaxed, ) @@ -291,41 +219,26 @@ ATOMIC64_OP_ADD_RETURN( , al, "memory") #undef ATOMIC64_OP_ADD_RETURN -static inline void arch_atomic64_and(long i, atomic64_t *v) +static inline void __lse_atomic64_and(s64 i, atomic64_t *v) { - register long x0 asm ("x0") = i; - register atomic64_t *x1 asm ("x1") = v; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - __LL_SC_ATOMIC64(and) - __nops(1), - /* LSE atomics */ + asm volatile( " mvn %[i], %[i]\n" - " stclr %[i], %[v]") - : [i] "+&r" (x0), [v] "+Q" (v->counter) - : "r" (x1) - : __LL_SC_CLOBBERS); + " stclr %[i], %[v]" + : [i] "+&r" (i), [v] "+Q" (v->counter) + : "r" (v)); } #define ATOMIC64_FETCH_OP_AND(name, mb, cl...) \ -static inline long arch_atomic64_fetch_and##name(long i, atomic64_t *v) \ +static inline long __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v) \ { \ - register long x0 asm ("x0") = i; \ - register atomic64_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC64(fetch_and##name) \ - __nops(1), \ - /* LSE atomics */ \ + asm volatile( \ " mvn %[i], %[i]\n" \ - " ldclr" #mb " %[i], %[i], %[v]") \ - : [i] "+&r" (x0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + " ldclr" #mb " %[i], %[i], %[v]" \ + : [i] "+&r" (i), [v] "+Q" (v->counter) \ + : "r" (v) \ + : cl); \ \ - return x0; \ + return i; \ } ATOMIC64_FETCH_OP_AND(_relaxed, ) @@ -335,42 +248,29 @@ ATOMIC64_FETCH_OP_AND( , al, "memory") #undef ATOMIC64_FETCH_OP_AND -static inline void arch_atomic64_sub(long i, atomic64_t *v) +static inline void __lse_atomic64_sub(s64 i, atomic64_t *v) { - register long x0 asm ("x0") = i; - register atomic64_t *x1 asm ("x1") = v; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - __LL_SC_ATOMIC64(sub) - __nops(1), - /* LSE atomics */ + asm volatile( " neg %[i], %[i]\n" - " stadd %[i], %[v]") - : [i] "+&r" (x0), [v] "+Q" (v->counter) - : "r" (x1) - : __LL_SC_CLOBBERS); + " stadd %[i], %[v]" + : [i] "+&r" (i), [v] "+Q" (v->counter) + : "r" (v)); } #define ATOMIC64_OP_SUB_RETURN(name, mb, cl...) \ -static inline long arch_atomic64_sub_return##name(long i, atomic64_t *v)\ +static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v) \ { \ - register long x0 asm ("x0") = i; \ - register atomic64_t *x1 asm ("x1") = v; \ + unsigned long tmp; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC64(sub_return##name) \ - __nops(2), \ - /* LSE atomics */ \ + asm volatile( \ " neg %[i], %[i]\n" \ - " ldadd" #mb " %[i], x30, %[v]\n" \ - " add %[i], %[i], x30") \ - : [i] "+&r" (x0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + " ldadd" #mb " %[i], %x[tmp], %[v]\n" \ + " add %[i], %[i], %x[tmp]" \ + : [i] "+&r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ + : "r" (v) \ + : cl); \ \ - return x0; \ + return i; \ } ATOMIC64_OP_SUB_RETURN(_relaxed, ) @@ -381,23 +281,16 @@ ATOMIC64_OP_SUB_RETURN( , al, "memory") #undef ATOMIC64_OP_SUB_RETURN #define ATOMIC64_FETCH_OP_SUB(name, mb, cl...) \ -static inline long arch_atomic64_fetch_sub##name(long i, atomic64_t *v) \ +static inline long __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v) \ { \ - register long x0 asm ("x0") = i; \ - register atomic64_t *x1 asm ("x1") = v; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_ATOMIC64(fetch_sub##name) \ - __nops(1), \ - /* LSE atomics */ \ + asm volatile( \ " neg %[i], %[i]\n" \ - " ldadd" #mb " %[i], %[i], %[v]") \ - : [i] "+&r" (x0), [v] "+Q" (v->counter) \ - : "r" (x1) \ - : __LL_SC_CLOBBERS, ##cl); \ + " ldadd" #mb " %[i], %[i], %[v]" \ + : [i] "+&r" (i), [v] "+Q" (v->counter) \ + : "r" (v) \ + : cl); \ \ - return x0; \ + return i; \ } ATOMIC64_FETCH_OP_SUB(_relaxed, ) @@ -407,54 +300,44 @@ ATOMIC64_FETCH_OP_SUB( , al, "memory") #undef ATOMIC64_FETCH_OP_SUB -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) +static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v) { - register long x0 asm ("x0") = (long)v; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - __LL_SC_ATOMIC64(dec_if_positive) - __nops(6), - /* LSE atomics */ - "1: ldr x30, %[v]\n" - " subs %[ret], x30, #1\n" + unsigned long tmp; + + asm volatile( + "1: ldr %x[tmp], %[v]\n" + " subs %[ret], %x[tmp], #1\n" " b.lt 2f\n" - " casal x30, %[ret], %[v]\n" - " sub x30, x30, #1\n" - " sub x30, x30, %[ret]\n" - " cbnz x30, 1b\n" - "2:") - : [ret] "+&r" (x0), [v] "+Q" (v->counter) + " casal %x[tmp], %[ret], %[v]\n" + " sub %x[tmp], %x[tmp], #1\n" + " sub %x[tmp], %x[tmp], %[ret]\n" + " cbnz %x[tmp], 1b\n" + "2:" + : [ret] "+&r" (v), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) : - : __LL_SC_CLOBBERS, "cc", "memory"); + : "cc", "memory"); - return x0; + return (long)v; } -#undef __LL_SC_ATOMIC64 - -#define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op) - #define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ -static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ +static inline u##sz __lse__cmpxchg_case_##name##sz(volatile void *ptr, \ u##sz old, \ u##sz new) \ { \ register unsigned long x0 asm ("x0") = (unsigned long)ptr; \ register u##sz x1 asm ("x1") = old; \ register u##sz x2 asm ("x2") = new; \ + unsigned long tmp; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_CMPXCHG(name##sz) \ - __nops(2), \ - /* LSE atomics */ \ - " mov " #w "30, %" #w "[old]\n" \ - " cas" #mb #sfx "\t" #w "30, %" #w "[new], %[v]\n" \ - " mov %" #w "[ret], " #w "30") \ - : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \ + asm volatile( \ + " mov %" #w "[tmp], %" #w "[old]\n" \ + " cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n" \ + " mov %" #w "[ret], %" #w "[tmp]" \ + : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr), \ + [tmp] "=&r" (tmp) \ : [old] "r" (x1), [new] "r" (x2) \ - : __LL_SC_CLOBBERS, ##cl); \ + : cl); \ \ return x0; \ } @@ -476,13 +359,10 @@ __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 -#define __LL_SC_CMPXCHG_DBL(op) __LL_SC_CALL(__cmpxchg_double##op) - #define __CMPXCHG_DBL(name, mb, cl...) \ -static inline long __cmpxchg_double##name(unsigned long old1, \ +static inline long __lse__cmpxchg_double##name(unsigned long old1, \ unsigned long old2, \ unsigned long new1, \ unsigned long new2, \ @@ -496,20 +376,16 @@ static inline long __cmpxchg_double##name(unsigned long old1, \ register unsigned long x3 asm ("x3") = new2; \ register unsigned long x4 asm ("x4") = (unsigned long)ptr; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - __LL_SC_CMPXCHG_DBL(name) \ - __nops(3), \ - /* LSE atomics */ \ + asm volatile( \ " casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\ " eor %[old1], %[old1], %[oldval1]\n" \ " eor %[old2], %[old2], %[oldval2]\n" \ - " orr %[old1], %[old1], %[old2]") \ + " orr %[old1], %[old1], %[old2]" \ : [old1] "+&r" (x0), [old2] "+&r" (x1), \ [v] "+Q" (*(unsigned long *)ptr) \ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ [oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \ - : __LL_SC_CLOBBERS, ##cl); \ + : cl); \ \ return x0; \ } @@ -517,7 +393,6 @@ static inline long __cmpxchg_double##name(unsigned long old1, \ __CMPXCHG_DBL( , ) __CMPXCHG_DBL(_mb, al, "memory") -#undef __LL_SC_CMPXCHG_DBL #undef __CMPXCHG_DBL #endif /* __ASM_ATOMIC_LSE_H */ diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index a05db636981a..43da6dd29592 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -78,14 +78,17 @@ static inline u32 cache_type_cwg(void) return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK; } -#define __read_mostly __attribute__((__section__(".data..read_mostly"))) +#define __read_mostly __section(.data..read_mostly) -static inline int cache_line_size(void) +static inline int cache_line_size_of_cpu(void) { u32 cwg = cache_type_cwg(); + return cwg ? 4 << cwg : ARCH_DMA_MINALIGN; } +int cache_line_size(void); + /* * Read the effective value of CTR_EL0. * diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 1fe4467442aa..665c78e0665a 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -176,4 +176,7 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) int set_memory_valid(unsigned long addr, int numpages, int enable); +int set_direct_map_invalid_noflush(struct page *page); +int set_direct_map_default_noflush(struct page *page); + #endif diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 7a299a20f6dc..f9bef42c1411 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -10,7 +10,6 @@ #include <linux/build_bug.h> #include <linux/compiler.h> -#include <asm/atomic.h> #include <asm/barrier.h> #include <asm/lse.h> @@ -63,7 +62,7 @@ __XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE #define __XCHG_GEN(sfx) \ -static inline unsigned long __xchg##sfx(unsigned long x, \ +static __always_inline unsigned long __xchg##sfx(unsigned long x, \ volatile void *ptr, \ int size) \ { \ @@ -104,8 +103,52 @@ __XCHG_GEN(_mb) #define arch_xchg_release(...) __xchg_wrapper(_rel, __VA_ARGS__) #define arch_xchg(...) __xchg_wrapper( _mb, __VA_ARGS__) +#define __CMPXCHG_CASE(name, sz) \ +static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ + u##sz old, \ + u##sz new) \ +{ \ + return __lse_ll_sc_body(_cmpxchg_case_##name##sz, \ + ptr, old, new); \ +} + +__CMPXCHG_CASE( , 8) +__CMPXCHG_CASE( , 16) +__CMPXCHG_CASE( , 32) +__CMPXCHG_CASE( , 64) +__CMPXCHG_CASE(acq_, 8) +__CMPXCHG_CASE(acq_, 16) +__CMPXCHG_CASE(acq_, 32) +__CMPXCHG_CASE(acq_, 64) +__CMPXCHG_CASE(rel_, 8) +__CMPXCHG_CASE(rel_, 16) +__CMPXCHG_CASE(rel_, 32) +__CMPXCHG_CASE(rel_, 64) +__CMPXCHG_CASE(mb_, 8) +__CMPXCHG_CASE(mb_, 16) +__CMPXCHG_CASE(mb_, 32) +__CMPXCHG_CASE(mb_, 64) + +#undef __CMPXCHG_CASE + +#define __CMPXCHG_DBL(name) \ +static inline long __cmpxchg_double##name(unsigned long old1, \ + unsigned long old2, \ + unsigned long new1, \ + unsigned long new2, \ + volatile void *ptr) \ +{ \ + return __lse_ll_sc_body(_cmpxchg_double##name, \ + old1, old2, new1, new2, ptr); \ +} + +__CMPXCHG_DBL( ) +__CMPXCHG_DBL(_mb) + +#undef __CMPXCHG_DBL + #define __CMPXCHG_GEN(sfx) \ -static inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ +static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ unsigned long old, \ unsigned long new, \ int size) \ @@ -212,7 +255,7 @@ __CMPWAIT_CASE( , , 64); #undef __CMPWAIT_CASE #define __CMPWAIT_GEN(sfx) \ -static inline void __cmpwait##sfx(volatile void *ptr, \ +static __always_inline void __cmpwait##sfx(volatile void *ptr, \ unsigned long val, \ int size) \ { \ diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index fb8ad4616b3b..b0d53a265f1d 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -4,7 +4,6 @@ */ #ifndef __ASM_COMPAT_H #define __ASM_COMPAT_H -#ifdef __KERNEL__ #ifdef CONFIG_COMPAT /* @@ -215,5 +214,4 @@ static inline int is_compat_thread(struct thread_info *thread) } #endif /* CONFIG_COMPAT */ -#endif /* __KERNEL__ */ #endif /* __ASM_COMPAT_H */ diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h index c09d633c3109..86aabf1e0199 100644 --- a/arch/arm64/include/asm/cpu_ops.h +++ b/arch/arm64/include/asm/cpu_ops.h @@ -23,6 +23,8 @@ * @cpu_boot: Boots a cpu into the kernel. * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary * synchronisation. Called from the cpu being booted. + * @cpu_can_disable: Determines whether a CPU can be disabled based on + * mechanism-specific information. * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific * reason, which will cause the hot unplug to be aborted. Called * from the cpu to be killed. @@ -42,6 +44,7 @@ struct cpu_operations { int (*cpu_boot)(unsigned int); void (*cpu_postboot)(void); #ifdef CONFIG_HOTPLUG_CPU + bool (*cpu_can_disable)(unsigned int cpu); int (*cpu_disable)(unsigned int cpu); void (*cpu_die)(unsigned int cpu); int (*cpu_kill)(unsigned int cpu); diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 373799b7982f..9cde5d2e768f 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -35,9 +35,10 @@ */ enum ftr_type { - FTR_EXACT, /* Use a predefined safe value */ - FTR_LOWER_SAFE, /* Smaller value is safe */ - FTR_HIGHER_SAFE,/* Bigger value is safe */ + FTR_EXACT, /* Use a predefined safe value */ + FTR_LOWER_SAFE, /* Smaller value is safe */ + FTR_HIGHER_SAFE, /* Bigger value is safe */ + FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ }; #define FTR_STRICT true /* SANITY check strict matching required */ @@ -288,9 +289,16 @@ struct arm64_cpu_capabilities { u16 type; bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope); /* - * Take the appropriate actions to enable this capability for this CPU. - * For each successfully booted CPU, this method is called for each - * globally detected capability. + * Take the appropriate actions to configure this capability + * for this CPU. If the capability is detected by the kernel + * this will be called on all the CPUs in the system, + * including the hotplugged CPUs, regardless of whether the + * capability is available on that specific CPU. This is + * useful for some capabilities (e.g, working around CPU + * errata), where all the CPUs must take some action (e.g, + * changing system control/configuration). Thus, if an action + * is required only if the CPU has the capability, then the + * routine must check it before taking any action. */ void (*cpu_enable)(const struct arm64_cpu_capabilities *cap); union { @@ -362,21 +370,6 @@ cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, return false; } -/* - * Take appropriate action for all matching entries in the shared capability - * entry. - */ -static inline void -cpucap_multi_entry_cap_cpu_enable(const struct arm64_cpu_capabilities *entry) -{ - const struct arm64_cpu_capabilities *caps; - - for (caps = entry->match_list; caps->matches; caps++) - if (caps->matches(caps, SCOPE_LOCAL_CPU) && - caps->cpu_enable) - caps->cpu_enable(caps); -} - extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; extern struct static_key_false arm64_const_caps_ready; @@ -614,6 +607,18 @@ static inline bool system_uses_irq_prio_masking(void) cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING); } +static inline bool system_has_prio_mask_debugging(void) +{ + return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) && + system_uses_irq_prio_masking(); +} + +#define ARM64_BP_HARDEN_UNKNOWN -1 +#define ARM64_BP_HARDEN_WA_NEEDED 0 +#define ARM64_BP_HARDEN_NOT_REQUIRED 1 + +int get_spectre_v2_workaround_state(void); + #define ARM64_SSBD_UNKNOWN -1 #define ARM64_SSBD_FORCE_DISABLE 0 #define ARM64_SSBD_KERNEL 1 diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index e7d46631cc42..b1454d117cd2 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -51,14 +51,6 @@ #define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \ MIDR_ARCHITECTURE_MASK) -#define MIDR_IS_CPU_MODEL_RANGE(midr, model, rv_min, rv_max) \ -({ \ - u32 _model = (midr) & MIDR_CPU_MODEL_MASK; \ - u32 rv = (midr) & (MIDR_REVISION_MASK | MIDR_VARIANT_MASK); \ - \ - _model == (model) && rv >= (rv_min) && rv <= (rv_max); \ - }) - #define ARM_CPU_IMP_ARM 0x41 #define ARM_CPU_IMP_APM 0x50 #define ARM_CPU_IMP_CAVIUM 0x43 @@ -159,10 +151,19 @@ struct midr_range { #define MIDR_REV(m, v, r) MIDR_RANGE(m, v, r, v, r) #define MIDR_ALL_VERSIONS(m) MIDR_RANGE(m, 0, 0, 0xf, 0xf) +static inline bool midr_is_cpu_model_range(u32 midr, u32 model, u32 rv_min, + u32 rv_max) +{ + u32 _model = midr & MIDR_CPU_MODEL_MASK; + u32 rv = midr & (MIDR_REVISION_MASK | MIDR_VARIANT_MASK); + + return _model == model && rv >= rv_min && rv <= rv_max; +} + static inline bool is_midr_in_range(u32 midr, struct midr_range const *range) { - return MIDR_IS_CPU_MODEL_RANGE(midr, range->model, - range->rv_min, range->rv_max); + return midr_is_cpu_model_range(midr, range->model, + range->rv_min, range->rv_max); } static inline bool diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 6dd8a8723525..063c964af705 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -7,20 +7,32 @@ #include <linux/irqflags.h> +#include <asm/arch_gicv3.h> #include <asm/cpufeature.h> #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ PSR_I_BIT #define DAIF_ERRCTX (PSR_I_BIT | PSR_A_BIT) +#define DAIF_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) + /* mask/save/unmask/restore all exceptions, including interrupts. */ static inline void local_daif_mask(void) { + WARN_ON(system_has_prio_mask_debugging() && + (read_sysreg_s(SYS_ICC_PMR_EL1) == (GIC_PRIO_IRQOFF | + GIC_PRIO_PSR_I_SET))); + asm volatile( "msr daifset, #0xf // local_daif_mask\n" : : : "memory"); + + /* Don't really care for a dsb here, we don't intend to enable IRQs */ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + trace_hardirqs_off(); } @@ -32,7 +44,7 @@ static inline unsigned long local_daif_save(void) if (system_uses_irq_prio_masking()) { /* If IRQs are masked with PMR, reflect it in the flags */ - if (read_sysreg_s(SYS_ICC_PMR_EL1) <= GIC_PRIO_IRQOFF) + if (read_sysreg_s(SYS_ICC_PMR_EL1) != GIC_PRIO_IRQON) flags |= PSR_I_BIT; } @@ -45,39 +57,50 @@ static inline void local_daif_restore(unsigned long flags) { bool irq_disabled = flags & PSR_I_BIT; + WARN_ON(system_has_prio_mask_debugging() && + !(read_sysreg(daif) & PSR_I_BIT)); + if (!irq_disabled) { trace_hardirqs_on(); - if (system_uses_irq_prio_masking()) - arch_local_irq_enable(); - } else if (!(flags & PSR_A_BIT)) { - /* - * If interrupts are disabled but we can take - * asynchronous errors, we can take NMIs - */ if (system_uses_irq_prio_masking()) { - flags &= ~PSR_I_BIT; + gic_write_pmr(GIC_PRIO_IRQON); + dsb(sy); + } + } else if (system_uses_irq_prio_masking()) { + u64 pmr; + + if (!(flags & PSR_A_BIT)) { /* - * There has been concern that the write to daif - * might be reordered before this write to PMR. - * From the ARM ARM DDI 0487D.a, section D1.7.1 - * "Accessing PSTATE fields": - * Writes to the PSTATE fields have side-effects on - * various aspects of the PE operation. All of these - * side-effects are guaranteed: - * - Not to be visible to earlier instructions in - * the execution stream. - * - To be visible to later instructions in the - * execution stream - * - * Also, writes to PMR are self-synchronizing, so no - * interrupts with a lower priority than PMR is signaled - * to the PE after the write. - * - * So we don't need additional synchronization here. + * If interrupts are disabled but we can take + * asynchronous errors, we can take NMIs */ - arch_local_irq_disable(); + flags &= ~PSR_I_BIT; + pmr = GIC_PRIO_IRQOFF; + } else { + pmr = GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET; } + + /* + * There has been concern that the write to daif + * might be reordered before this write to PMR. + * From the ARM ARM DDI 0487D.a, section D1.7.1 + * "Accessing PSTATE fields": + * Writes to the PSTATE fields have side-effects on + * various aspects of the PE operation. All of these + * side-effects are guaranteed: + * - Not to be visible to earlier instructions in + * the execution stream. + * - To be visible to later instructions in the + * execution stream + * + * Also, writes to PMR are self-synchronizing, so no + * interrupts with a lower priority than PMR is signaled + * to the PE after the write. + * + * So we don't need additional synchronization here. + */ + gic_write_pmr(pmr); } write_sysreg(flags, daif); diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index d8ec5bb881c2..7619f473155f 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -5,8 +5,6 @@ #ifndef __ASM_DEBUG_MONITORS_H #define __ASM_DEBUG_MONITORS_H -#ifdef __KERNEL__ - #include <linux/errno.h> #include <linux/types.h> #include <asm/brk-imm.h> @@ -128,5 +126,4 @@ static inline int reinstall_suspended_bps(struct pt_regs *regs) int aarch32_break_handler(struct pt_regs *regs); #endif /* __ASSEMBLY */ -#endif /* __KERNEL__ */ #endif /* __ASM_DEBUG_MONITORS_H */ diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h deleted file mode 100644 index bdcb0922a40c..000000000000 --- a/arch/arm64/include/asm/dma-mapping.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 ARM Ltd. - */ -#ifndef __ASM_DMA_MAPPING_H -#define __ASM_DMA_MAPPING_H - -#ifdef __KERNEL__ - -#include <linux/types.h> -#include <linux/vmalloc.h> - -#include <xen/xen.h> -#include <asm/xen/hypervisor.h> - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return NULL; -} - -/* - * Do not use this function in a driver, it is only provided for - * arch/arm/mm/xen.c, which is used by arm64 as well. - */ -static inline bool is_device_dma_coherent(struct device *dev) -{ - return dev->dma_coherent; -} - -#endif /* __KERNEL__ */ -#endif /* __ASM_DMA_MAPPING_H */ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index c9e9a6978e73..b54d3a86c444 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -79,18 +79,18 @@ static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base) /* * On arm64, we have to ensure that the initrd ends up in the linear region, - * which is a 1 GB aligned region of size '1UL << (VA_BITS - 1)' that is + * which is a 1 GB aligned region of size '1UL << (VA_BITS_MIN - 1)' that is * guaranteed to cover the kernel Image. * * Since the EFI stub is part of the kernel Image, we can relax the - * usual requirements in Documentation/arm64/booting.txt, which still + * usual requirements in Documentation/arm64/booting.rst, which still * apply to other bootloaders, and are required for some kernel * configurations. */ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, unsigned long image_addr) { - return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS - 1)); + return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS_MIN - 1)); } #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) @@ -105,7 +105,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) #define alloc_screen_info(x...) &screen_info -#define free_screen_info(x...) + +static inline void free_screen_info(efi_system_table_t *sys_table_arg, + struct screen_info *si) +{ +} /* redeclare as 'hidden' so the compiler will generate relative references */ extern struct screen_info screen_info __attribute__((__visibility__("hidden"))); diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 325d9515c0f8..b618017205a3 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -202,7 +202,21 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; ({ \ set_thread_flag(TIF_32BIT); \ }) +#ifdef CONFIG_COMPAT_VDSO +#define COMPAT_ARCH_DLINFO \ +do { \ + /* \ + * Note that we use Elf64_Off instead of elf_addr_t because \ + * elf_addr_t in compat is defined as Elf32_Addr and casting \ + * current->mm->context.vdso to it triggers a cast warning of \ + * cast from pointer to integer of different size. \ + */ \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, \ + (Elf64_Off)current->mm->context.vdso); \ +} while (0) +#else #define COMPAT_ARCH_DLINFO +#endif extern int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); #define compat_arch_setup_additional_pages \ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 65ac18400979..cb29253ae86b 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -34,7 +34,8 @@ #define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ #define ESR_ELx_EC_SYS64 (0x18) #define ESR_ELx_EC_SVE (0x19) -/* Unallocated EC: 0x1A - 0x1E */ +#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +/* Unallocated EC: 0x1b - 0x1E */ #define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ #define ESR_ELx_EC_IABT_LOW (0x20) #define ESR_ELx_EC_IABT_CUR (0x21) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index ed57b760f38c..a17393ff6677 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -30,4 +30,6 @@ static inline u32 disr_to_esr(u64 disr) return esr; } +asmlinkage void enter_from_user_mode(void); + #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 897029c8e9b5..59f10dd13f12 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -21,7 +21,7 @@ #include <linux/stddef.h> #include <linux/types.h> -#if defined(__KERNEL__) && defined(CONFIG_COMPAT) +#ifdef CONFIG_COMPAT /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 @@ -37,8 +37,6 @@ struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); extern void fpsimd_load_state(struct user_fpsimd_state *state); -extern void fpsimd_save(void); - extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); @@ -52,8 +50,7 @@ extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, void *sve_state, unsigned int sve_vl); extern void fpsimd_flush_task_state(struct task_struct *target); -extern void fpsimd_flush_cpu_state(void); -extern void sve_flush_cpu_state(void); +extern void fpsimd_save_and_flush_cpu_state(void); /* Maximum VL that SVE VL-agnostic software can transparently support */ #define SVE_VL_ARCH_MAX 0x100 diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 5ab5200b2bdc..d48667b04c41 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -14,6 +14,19 @@ #define MCOUNT_ADDR ((unsigned long)_mcount) #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE +/* + * Currently, gcc tends to save the link register after the local variables + * on the stack. This causes the max stack tracer to report the function + * frame sizes for the wrong functions. By defining + * ARCH_FTRACE_SHIFT_STACK_TRACER, it will tell the stack tracer to expect + * to find the return address on the stack after the local variables have + * been set up. + * + * Note, this may change in the future, and we will need to deal with that + * if it were to happen. + */ +#define ARCH_FTRACE_SHIFT_STACK_TRACER 1 + #ifndef __ASSEMBLY__ #include <linux/compat.h> diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 6211e3105491..6cc26a127819 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -5,8 +5,6 @@ #ifndef __ASM_FUTEX_H #define __ASM_FUTEX_H -#ifdef __KERNEL__ - #include <linux/futex.h> #include <linux/uaccess.h> @@ -129,5 +127,4 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, return ret; } -#endif /* __KERNEL__ */ #endif /* __ASM_FUTEX_H */ diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index db9ab760e6fd..bc7aaed4b34e 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -10,8 +10,6 @@ #include <asm/sysreg.h> #include <asm/virt.h> -#ifdef __KERNEL__ - struct arch_hw_breakpoint_ctrl { u32 __reserved : 19, len : 8, @@ -156,5 +154,4 @@ static inline int get_num_wrps(void) ID_AA64DFR0_WRPS_SHIFT); } -#endif /* __KERNEL__ */ #endif /* __ASM_BREAKPOINT_H */ diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index e5d9420cd258..3d2f2472a36c 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -84,6 +84,8 @@ #define KERNEL_HWCAP_SVEBITPERM __khwcap2_feature(SVEBITPERM) #define KERNEL_HWCAP_SVESHA3 __khwcap2_feature(SVESHA3) #define KERNEL_HWCAP_SVESM4 __khwcap2_feature(SVESM4) +#define KERNEL_HWCAP_FLAGM2 __khwcap2_feature(FLAGM2) +#define KERNEL_HWCAP_FRINT __khwcap2_feature(FRINT) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/image.h b/arch/arm64/include/asm/image.h index e2c27a2278e9..c2b13213c720 100644 --- a/arch/arm64/include/asm/image.h +++ b/arch/arm64/include/asm/image.h @@ -27,7 +27,7 @@ /* * struct arm64_image_header - arm64 kernel image header - * See Documentation/arm64/booting.txt for details + * See Documentation/arm64/booting.rst for details * * @code0: Executable code, or * @mz_header alternatively used for part of MZ header diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 7ed92626949d..323cb306bd28 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -8,8 +8,6 @@ #ifndef __ASM_IO_H #define __ASM_IO_H -#ifdef __KERNEL__ - #include <linux/types.h> #include <asm/byteorder.h> @@ -97,7 +95,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) ({ \ unsigned long tmp; \ \ - rmb(); \ + dma_rmb(); \ \ /* \ * Create a dummy control dependency from the IO read to any \ @@ -111,7 +109,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) }) #define __io_par(v) __iormb(v) -#define __iowmb() wmb() +#define __iowmb() dma_wmb() /* * Relaxed I/O memory access primitives. These follow the Device memory @@ -165,14 +163,13 @@ extern void __memset_io(volatile void __iomem *, int, size_t); * I/O memory mapping functions. */ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot); -extern void __iounmap(volatile void __iomem *addr); +extern void iounmap(volatile void __iomem *addr); extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); #define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define ioremap_nocache(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC)) #define ioremap_wt(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) -#define iounmap __iounmap /* * PCI configuration space mapping function. @@ -207,5 +204,4 @@ extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); extern int devmem_is_allowed(unsigned long pfn); -#endif /* __KERNEL__ */ #endif /* __ASM_IO_H */ diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 66853fde60f9..1a59f0ed1ae3 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -5,8 +5,6 @@ #ifndef __ASM_IRQFLAGS_H #define __ASM_IRQFLAGS_H -#ifdef __KERNEL__ - #include <asm/alternative.h> #include <asm/ptrace.h> #include <asm/sysreg.h> @@ -29,6 +27,12 @@ */ static inline void arch_local_irq_enable(void) { + if (system_has_prio_mask_debugging()) { + u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); + + WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); + } + asm volatile(ALTERNATIVE( "msr daifclr, #2 // arch_local_irq_enable\n" "nop", @@ -42,6 +46,12 @@ static inline void arch_local_irq_enable(void) static inline void arch_local_irq_disable(void) { + if (system_has_prio_mask_debugging()) { + u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); + + WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); + } + asm volatile(ALTERNATIVE( "msr daifset, #2 // arch_local_irq_disable", __msr_s(SYS_ICC_PMR_EL1, "%0"), @@ -56,43 +66,46 @@ static inline void arch_local_irq_disable(void) */ static inline unsigned long arch_local_save_flags(void) { - unsigned long daif_bits; unsigned long flags; - daif_bits = read_sysreg(daif); - - /* - * The asm is logically equivalent to: - * - * if (system_uses_irq_prio_masking()) - * flags = (daif_bits & PSR_I_BIT) ? - * GIC_PRIO_IRQOFF : - * read_sysreg_s(SYS_ICC_PMR_EL1); - * else - * flags = daif_bits; - */ asm volatile(ALTERNATIVE( - "mov %0, %1\n" - "nop\n" - "nop", - __mrs_s("%0", SYS_ICC_PMR_EL1) - "ands %1, %1, " __stringify(PSR_I_BIT) "\n" - "csel %0, %0, %2, eq", - ARM64_HAS_IRQ_PRIO_MASKING) - : "=&r" (flags), "+r" (daif_bits) - : "r" ((unsigned long) GIC_PRIO_IRQOFF) + "mrs %0, daif", + __mrs_s("%0", SYS_ICC_PMR_EL1), + ARM64_HAS_IRQ_PRIO_MASKING) + : "=&r" (flags) + : : "memory"); return flags; } +static inline int arch_irqs_disabled_flags(unsigned long flags) +{ + int res; + + asm volatile(ALTERNATIVE( + "and %w0, %w1, #" __stringify(PSR_I_BIT), + "eor %w0, %w1, #" __stringify(GIC_PRIO_IRQON), + ARM64_HAS_IRQ_PRIO_MASKING) + : "=&r" (res) + : "r" ((int) flags) + : "memory"); + + return res; +} + static inline unsigned long arch_local_irq_save(void) { unsigned long flags; flags = arch_local_save_flags(); - arch_local_irq_disable(); + /* + * There are too many states with IRQs disabled, just keep the current + * state if interrupts are already disabled/masked. + */ + if (!arch_irqs_disabled_flags(flags)) + arch_local_irq_disable(); return flags; } @@ -108,26 +121,9 @@ static inline void arch_local_irq_restore(unsigned long flags) __msr_s(SYS_ICC_PMR_EL1, "%0") "dsb sy", ARM64_HAS_IRQ_PRIO_MASKING) - : "+r" (flags) : + : "r" (flags) : "memory"); } -static inline int arch_irqs_disabled_flags(unsigned long flags) -{ - int res; - - asm volatile(ALTERNATIVE( - "and %w0, %w1, #" __stringify(PSR_I_BIT) "\n" - "nop", - "cmp %w1, #" __stringify(GIC_PRIO_IRQOFF) "\n" - "cset %w0, ls", - ARM64_HAS_IRQ_PRIO_MASKING) - : "=&r" (res) - : "r" ((int) flags) - : "memory"); - - return res; -} -#endif -#endif +#endif /* __ASM_IRQFLAGS_H */ diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index b52aacd2c526..b0dc4abc3589 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -18,11 +18,8 @@ * KASAN_SHADOW_START: beginning of the kernel virtual addresses. * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses, * where N = (1 << KASAN_SHADOW_SCALE_SHIFT). - */ -#define KASAN_SHADOW_START (VA_START) -#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) - -/* + * + * KASAN_SHADOW_OFFSET: * This value is used to map an address to the corresponding shadow * address by the following formula: * shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET @@ -33,8 +30,8 @@ * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - * (1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT)) */ -#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \ - (64 - KASAN_SHADOW_SCALE_SHIFT))) +#define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT))) +#define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual) void kasan_init(void); void kasan_copy_shadow(pgd_t *pgdir); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index a8b205e5c4a8..ddf9d762ac62 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -316,9 +316,10 @@ #define kvm_arm_exception_class \ ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \ - ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(CP14_64), ECN(SVC64), \ - ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(IMP_DEF), ECN(IABT_LOW), \ - ECN(IABT_CUR), ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ + ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \ + ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \ + ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \ + ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 2ca437ef59fa..44a243754c1b 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -30,6 +30,12 @@ {ARM_EXCEPTION_TRAP, "TRAP" }, \ {ARM_EXCEPTION_HYP_GONE, "HYP_GONE" } +/* + * Size of the HYP vectors preamble. kvm_patch_vector_branch() generates code + * that jumps over this. + */ +#define KVM_VECTOR_PREAMBLE (2 * AARCH64_INSN_SIZE) + #ifndef __ASSEMBLY__ #include <linux/mm.h> diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 034dadec7168..d69c1efc63e7 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -126,7 +126,7 @@ static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu) static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu) { if (vcpu->arch.sysregs_loaded_on_cpu) - return read_sysreg_el1(elr); + return read_sysreg_el1(SYS_ELR); else return *__vcpu_elr_el1(vcpu); } @@ -134,7 +134,7 @@ static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu) static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v) { if (vcpu->arch.sysregs_loaded_on_cpu) - write_sysreg_el1(v, elr); + write_sysreg_el1(v, SYS_ELR); else *__vcpu_elr_el1(vcpu) = v; } @@ -186,7 +186,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu) return vcpu_read_spsr32(vcpu); if (vcpu->arch.sysregs_loaded_on_cpu) - return read_sysreg_el1(spsr); + return read_sysreg_el1(SYS_SPSR); else return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1]; } @@ -199,7 +199,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) } if (vcpu->arch.sysregs_loaded_on_cpu) - write_sysreg_el1(v, spsr); + write_sysreg_el1(v, SYS_SPSR); else vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v; } @@ -353,6 +353,20 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK; } +static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG; +} + +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu, + bool flag) +{ + if (flag) + vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; + else + vcpu->arch.workaround_flags &= ~VCPU_WORKAROUND_2_FLAG; +} + static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { @@ -451,13 +465,13 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) */ static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) { - *vcpu_pc(vcpu) = read_sysreg_el2(elr); - vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr); + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); + vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr); - write_sysreg_el2(*vcpu_pc(vcpu), elr); + write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, SYS_SPSR); + write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index c328191aa202..f656169db8c3 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -19,12 +19,12 @@ #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/cputype.h> #include <asm/daifflags.h> #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> -#include <asm/smp_plat.h> #include <asm/thread_info.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -484,11 +484,10 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data); -static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt, - int cpu) +static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ - cpu_ctxt->sys_regs[MPIDR_EL1] = cpu_logical_map(cpu); + cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr(); } void __kvm_enable_ssbs(void); @@ -597,11 +596,12 @@ static inline void kvm_arm_vhe_guest_enter(void) * will not signal the CPU of interrupts of lower priority, and the * only way to get out will be via guest exceptions. * Naturally, we want to avoid this. + * + * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a + * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ - if (system_uses_irq_prio_masking()) { - gic_write_pmr(GIC_PRIO_IRQON); + if (system_uses_irq_prio_masking()) dsb(sy); - } } static inline void kvm_arm_vhe_guest_exit(void) @@ -620,9 +620,21 @@ static inline void kvm_arm_vhe_guest_exit(void) isb(); } -static inline bool kvm_arm_harden_branch_predictor(void) +#define KVM_BP_HARDEN_UNKNOWN -1 +#define KVM_BP_HARDEN_WA_NEEDED 0 +#define KVM_BP_HARDEN_NOT_REQUIRED 1 + +static inline int kvm_arm_harden_branch_predictor(void) { - return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR); + switch (get_spectre_v2_workaround_state()) { + case ARM64_BP_HARDEN_WA_NEEDED: + return KVM_BP_HARDEN_WA_NEEDED; + case ARM64_BP_HARDEN_NOT_REQUIRED: + return KVM_BP_HARDEN_NOT_REQUIRED; + case ARM64_BP_HARDEN_UNKNOWN: + default: + return KVM_BP_HARDEN_UNKNOWN; + } } #define KVM_SSBD_UNKNOWN -1 diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 286f7e7e1be4..86825aa20852 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -18,7 +18,7 @@ #define read_sysreg_elx(r,nvh,vh) \ ({ \ u64 reg; \ - asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\ + asm volatile(ALTERNATIVE(__mrs_s("%0", r##nvh), \ __mrs_s("%0", r##vh), \ ARM64_HAS_VIRT_HOST_EXTN) \ : "=r" (reg)); \ @@ -28,7 +28,7 @@ #define write_sysreg_elx(v,r,nvh,vh) \ do { \ u64 __val = (u64)(v); \ - asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\ + asm volatile(ALTERNATIVE(__msr_s(r##nvh, "%x0"), \ __msr_s(r##vh, "%x0"), \ ARM64_HAS_VIRT_HOST_EXTN) \ : : "rZ" (__val)); \ @@ -37,55 +37,15 @@ /* * Unified accessors for registers that have a different encoding * between VHE and non-VHE. They must be specified without their "ELx" - * encoding. + * encoding, but with the SYS_ prefix, as defined in asm/sysreg.h. */ -#define read_sysreg_el2(r) \ - ({ \ - u64 reg; \ - asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##_EL2),\ - "mrs %0, " __stringify(r##_EL1),\ - ARM64_HAS_VIRT_HOST_EXTN) \ - : "=r" (reg)); \ - reg; \ - }) - -#define write_sysreg_el2(v,r) \ - do { \ - u64 __val = (u64)(v); \ - asm volatile(ALTERNATIVE("msr " __stringify(r##_EL2) ", %x0",\ - "msr " __stringify(r##_EL1) ", %x0",\ - ARM64_HAS_VIRT_HOST_EXTN) \ - : : "rZ" (__val)); \ - } while (0) #define read_sysreg_el0(r) read_sysreg_elx(r, _EL0, _EL02) #define write_sysreg_el0(v,r) write_sysreg_elx(v, r, _EL0, _EL02) #define read_sysreg_el1(r) read_sysreg_elx(r, _EL1, _EL12) #define write_sysreg_el1(v,r) write_sysreg_elx(v, r, _EL1, _EL12) - -/* The VHE specific system registers and their encoding */ -#define sctlr_EL12 sys_reg(3, 5, 1, 0, 0) -#define cpacr_EL12 sys_reg(3, 5, 1, 0, 2) -#define ttbr0_EL12 sys_reg(3, 5, 2, 0, 0) -#define ttbr1_EL12 sys_reg(3, 5, 2, 0, 1) -#define tcr_EL12 sys_reg(3, 5, 2, 0, 2) -#define afsr0_EL12 sys_reg(3, 5, 5, 1, 0) -#define afsr1_EL12 sys_reg(3, 5, 5, 1, 1) -#define esr_EL12 sys_reg(3, 5, 5, 2, 0) -#define far_EL12 sys_reg(3, 5, 6, 0, 0) -#define mair_EL12 sys_reg(3, 5, 10, 2, 0) -#define amair_EL12 sys_reg(3, 5, 10, 3, 0) -#define vbar_EL12 sys_reg(3, 5, 12, 0, 0) -#define contextidr_EL12 sys_reg(3, 5, 13, 0, 1) -#define cntkctl_EL12 sys_reg(3, 5, 14, 1, 0) -#define cntp_tval_EL02 sys_reg(3, 5, 14, 2, 0) -#define cntp_ctl_EL02 sys_reg(3, 5, 14, 2, 1) -#define cntp_cval_EL02 sys_reg(3, 5, 14, 2, 2) -#define cntv_tval_EL02 sys_reg(3, 5, 14, 3, 0) -#define cntv_ctl_EL02 sys_reg(3, 5, 14, 3, 1) -#define cntv_cval_EL02 sys_reg(3, 5, 14, 3, 2) -#define spsr_EL12 sys_reg(3, 5, 4, 0, 0) -#define elr_EL12 sys_reg(3, 5, 4, 0, 1) +#define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) +#define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) /** * hyp_alternate_select - Generates patchable code sequences that are diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index 8262325e2fc6..80b388278149 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -2,56 +2,47 @@ #ifndef __ASM_LSE_H #define __ASM_LSE_H +#include <asm/atomic_ll_sc.h> + #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) #include <linux/compiler_types.h> #include <linux/export.h> +#include <linux/jump_label.h> #include <linux/stringify.h> #include <asm/alternative.h> +#include <asm/atomic_lse.h> #include <asm/cpucaps.h> -#ifdef __ASSEMBLER__ - -.arch_extension lse - -.macro alt_lse, llsc, lse - alternative_insn "\llsc", "\lse", ARM64_HAS_LSE_ATOMICS -.endm - -#else /* __ASSEMBLER__ */ - __asm__(".arch_extension lse"); -/* Move the ll/sc atomics out-of-line */ -#define __LL_SC_INLINE notrace -#define __LL_SC_PREFIX(x) __ll_sc_##x -#define __LL_SC_EXPORT(x) EXPORT_SYMBOL(__LL_SC_PREFIX(x)) +extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; +extern struct static_key_false arm64_const_caps_ready; + +static inline bool system_uses_lse_atomics(void) +{ + return (static_branch_likely(&arm64_const_caps_ready)) && + static_branch_likely(&cpu_hwcap_keys[ARM64_HAS_LSE_ATOMICS]); +} -/* Macro for constructing calls to out-of-line ll/sc atomics */ -#define __LL_SC_CALL(op) "bl\t" __stringify(__LL_SC_PREFIX(op)) "\n" -#define __LL_SC_CLOBBERS "x16", "x17", "x30" +#define __lse_ll_sc_body(op, ...) \ +({ \ + system_uses_lse_atomics() ? \ + __lse_##op(__VA_ARGS__) : \ + __ll_sc_##op(__VA_ARGS__); \ +}) /* In-line patching at runtime */ #define ARM64_LSE_ATOMIC_INSN(llsc, lse) \ ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS) -#endif /* __ASSEMBLER__ */ #else /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ -#ifdef __ASSEMBLER__ - -.macro alt_lse, llsc, lse - \llsc -.endm - -#else /* __ASSEMBLER__ */ +static inline bool system_uses_lse_atomics(void) { return false; } -#define __LL_SC_INLINE static inline -#define __LL_SC_PREFIX(x) x -#define __LL_SC_EXPORT(x) +#define __lse_ll_sc_body(op, ...) __ll_sc_##op(__VA_ARGS__) #define ARM64_LSE_ATOMIC_INSN(llsc, lse) llsc -#endif /* __ASSEMBLER__ */ #endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ #endif /* __ASM_LSE_H */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b7ba75809751..b61b50bf68b1 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -12,10 +12,10 @@ #include <linux/compiler.h> #include <linux/const.h> +#include <linux/sizes.h> #include <linux/types.h> #include <asm/bug.h> #include <asm/page-def.h> -#include <linux/sizes.h> /* * Size of the PCI I/O space. This must remain a power of two so that @@ -26,37 +26,50 @@ /* * VMEMMAP_SIZE - allows the whole linear region to be covered by * a struct page array + * + * If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE + * needs to cover the memory region from the beginning of the 52-bit + * PAGE_OFFSET all the way to PAGE_END for 48-bit. This allows us to + * keep a constant PAGE_OFFSET and "fallback" to using the higher end + * of the VMEMMAP where 52-bit support is not available in hardware. */ -#define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)) +#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) \ + >> (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT)) /* - * PAGE_OFFSET - the virtual address of the start of the linear map (top - * (VA_BITS - 1)) - * KIMAGE_VADDR - the virtual address of the start of the kernel image + * PAGE_OFFSET - the virtual address of the start of the linear map, at the + * start of the TTBR1 address space. + * PAGE_END - the end of the linear map, where all other kernel mappings begin. + * KIMAGE_VADDR - the virtual address of the start of the kernel image. * VA_BITS - the maximum number of bits for virtual addresses. - * VA_START - the first kernel virtual address. */ #define VA_BITS (CONFIG_ARM64_VA_BITS) -#define VA_START (UL(0xffffffffffffffff) - \ - (UL(1) << VA_BITS) + 1) -#define PAGE_OFFSET (UL(0xffffffffffffffff) - \ - (UL(1) << (VA_BITS - 1)) + 1) +#define _PAGE_OFFSET(va) (-(UL(1) << (va))) +#define PAGE_OFFSET (_PAGE_OFFSET(VA_BITS)) #define KIMAGE_VADDR (MODULES_END) -#define BPF_JIT_REGION_START (VA_START + KASAN_SHADOW_SIZE) +#define BPF_JIT_REGION_START (KASAN_SHADOW_END) #define BPF_JIT_REGION_SIZE (SZ_128M) #define BPF_JIT_REGION_END (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE) #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (BPF_JIT_REGION_END) #define MODULES_VSIZE (SZ_128M) -#define VMEMMAP_START (PAGE_OFFSET - VMEMMAP_SIZE) +#define VMEMMAP_START (-VMEMMAP_SIZE - SZ_2M) #define PCI_IO_END (VMEMMAP_START - SZ_2M) #define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) #define FIXADDR_TOP (PCI_IO_START - SZ_2M) -#define KERNEL_START _text -#define KERNEL_END _end +#if VA_BITS > 48 +#define VA_BITS_MIN (48) +#else +#define VA_BITS_MIN (VA_BITS) +#endif + +#define _PAGE_END(va) (-(UL(1) << ((va) - 1))) + +#define KERNEL_START _text +#define KERNEL_END _end -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#ifdef CONFIG_ARM64_VA_BITS_52 #define MAX_USER_VA_BITS 52 #else #define MAX_USER_VA_BITS VA_BITS @@ -68,12 +81,14 @@ * significantly, so double the (minimum) stack size when they are in use. */ #ifdef CONFIG_KASAN -#define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT)) +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) +#define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \ + + KASAN_SHADOW_OFFSET) #define KASAN_THREAD_SHIFT 1 #else -#define KASAN_SHADOW_SIZE (0) #define KASAN_THREAD_SHIFT 0 -#endif +#define KASAN_SHADOW_END (_PAGE_END(VA_BITS_MIN)) +#endif /* CONFIG_KASAN */ #define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) @@ -117,14 +132,14 @@ * 16 KB granule: 128 level 3 entries, with contiguous bit * 64 KB granule: 32 level 3 entries, with contiguous bit */ -#define SEGMENT_ALIGN SZ_2M +#define SEGMENT_ALIGN SZ_2M #else /* * 4 KB granule: 16 level 3 entries, with contiguous bit * 16 KB granule: 4 level 3 entries, without contiguous bit * 64 KB granule: 1 level 3 entry */ -#define SEGMENT_ALIGN SZ_64K +#define SEGMENT_ALIGN SZ_64K #endif /* @@ -157,10 +172,13 @@ #endif #ifndef __ASSEMBLY__ +extern u64 vabits_actual; +#define PAGE_END (_PAGE_END(vabits_actual)) #include <linux/bitops.h> #include <linux/mmdebug.h> +extern s64 physvirt_offset; extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ #define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) @@ -176,9 +194,6 @@ static inline unsigned long kaslr_offset(void) return kimage_vaddr - KIMAGE_VADDR; } -/* the actual size of a user virtual address */ -extern u64 vabits_user; - /* * Allow all memory at the discovery stage. We will clip it later. */ @@ -201,19 +216,23 @@ extern u64 vabits_user; * pass on to access_ok(), for instance. */ #define untagged_addr(addr) \ - ((__typeof__(addr))sign_extend64((u64)(addr), 55)) + ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #ifdef CONFIG_KASAN_SW_TAGS #define __tag_shifted(tag) ((u64)(tag) << 56) -#define __tag_set(addr, tag) (__typeof__(addr))( \ - ((u64)(addr) & ~__tag_shifted(0xff)) | __tag_shifted(tag)) #define __tag_reset(addr) untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else -#define __tag_set(addr, tag) (addr) +#define __tag_shifted(tag) 0UL #define __tag_reset(addr) (addr) #define __tag_get(addr) 0 -#endif +#endif /* CONFIG_KASAN_SW_TAGS */ + +static inline const void *__tag_set(const void *addr, u8 tag) +{ + u64 __addr = (u64)addr & ~__tag_shifted(0xff); + return (const void *)(__addr | __tag_shifted(tag)); +} /* * Physical vs virtual RAM address space conversion. These are @@ -223,19 +242,18 @@ extern u64 vabits_user; /* - * The linear kernel range starts in the middle of the virtual adddress + * The linear kernel range starts at the bottom of the virtual address * space. Testing the top bit for the start of the region is a - * sufficient check. + * sufficient check and avoids having to worry about the tag. */ -#define __is_lm_address(addr) (!!((addr) & BIT(VA_BITS - 1))) +#define __is_lm_address(addr) (!(((u64)addr) & BIT(vabits_actual - 1))) -#define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) +#define __lm_to_phys(addr) (((addr) + physvirt_offset)) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ - phys_addr_t __x = (phys_addr_t)(x); \ - __is_lm_address(__x) ? __lm_to_phys(__x) : \ - __kimg_to_phys(__x); \ + phys_addr_t __x = (phys_addr_t)(__tag_reset(x)); \ + __is_lm_address(__x) ? __lm_to_phys(__x) : __kimg_to_phys(__x); \ }) #define __pa_symbol_nodebug(x) __kimg_to_phys((phys_addr_t)(x)) @@ -246,9 +264,9 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #else #define __virt_to_phys(x) __virt_to_phys_nodebug(x) #define __phys_addr_symbol(x) __pa_symbol_nodebug(x) -#endif +#endif /* CONFIG_DEBUG_VIRTUAL */ -#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) +#define __phys_to_virt(x) ((unsigned long)((x) - physvirt_offset)) #define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* @@ -282,41 +300,38 @@ static inline void *phys_to_virt(phys_addr_t x) #define __pa_nodebug(x) __virt_to_phys_nodebug((unsigned long)(x)) #define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys((unsigned long)(x))) -#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) +#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys((unsigned long)(x))) +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) /* - * virt_to_page(k) convert a _valid_ virtual address to struct page * - * virt_addr_valid(k) indicates whether a virtual address is valid + * virt_to_page(x) convert a _valid_ virtual address to struct page * + * virt_addr_valid(x) indicates whether a virtual address is valid */ #define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET) #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL) -#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) +#define virt_to_page(x) pfn_to_page(virt_to_pfn(x)) #else -#define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page)) -#define __page_to_voff(kaddr) (((u64)(kaddr) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page)) - -#define page_to_virt(page) ({ \ - unsigned long __addr = \ - ((__page_to_voff(page)) | PAGE_OFFSET); \ - unsigned long __addr_tag = \ - __tag_set(__addr, page_kasan_tag(page)); \ - ((void *)__addr_tag); \ +#define page_to_virt(x) ({ \ + __typeof__(x) __page = x; \ + u64 __idx = ((u64)__page - VMEMMAP_START) / sizeof(struct page);\ + u64 __addr = PAGE_OFFSET + (__idx * PAGE_SIZE); \ + (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\ }) -#define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START)) +#define virt_to_page(x) ({ \ + u64 __idx = (__tag_reset((u64)x) - PAGE_OFFSET) / PAGE_SIZE; \ + u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page)); \ + (struct page *)__addr; \ +}) +#endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */ -#define _virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \ - + PHYS_OFFSET) >> PAGE_SHIFT) -#endif -#endif +#define virt_addr_valid(addr) ({ \ + __typeof__(addr) __addr = addr; \ + __is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr)); \ +}) -#define _virt_addr_is_linear(kaddr) \ - (__tag_reset((u64)(kaddr)) >= PAGE_OFFSET) -#define virt_addr_valid(kaddr) \ - (_virt_addr_is_linear(kaddr) && _virt_addr_valid(kaddr)) +#endif /* !ASSEMBLY */ /* * Given that the GIC architecture permits ITS implementations that can only be @@ -331,4 +346,4 @@ static inline void *phys_to_virt(phys_addr_t x) #include <asm-generic/memory_model.h> -#endif +#endif /* __ASM_MEMORY_H */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index fd6161336653..f217e3292919 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -126,7 +126,7 @@ extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only); -extern void *fixmap_remap_fdt(phys_addr_t dt_phys); +extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); #define INIT_MM_CONTEXT(name) \ diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 7ed0adb187a8..3827ff4040a3 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -63,7 +63,7 @@ extern u64 idmap_ptrs_per_pgd; static inline bool __cpu_uses_extended_idmap(void) { - if (IS_ENABLED(CONFIG_ARM64_USER_VA_BITS_52)) + if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52)) return false; return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)); @@ -95,7 +95,7 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) isb(); } -#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS)) +#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual)) #define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz) /* diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h index 9e690686e8aa..70b323cf8300 100644 --- a/arch/arm64/include/asm/pci.h +++ b/arch/arm64/include/asm/pci.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PCI_H #define __ASM_PCI_H -#ifdef __KERNEL__ #include <linux/types.h> #include <linux/slab.h> @@ -35,5 +34,4 @@ static inline int pci_proc_domain(struct pci_bus *bus) } #endif /* CONFIG_PCI */ -#endif /* __KERNEL__ */ #endif /* __ASM_PCI_H */ diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index cdced518378d..172d76fa0245 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -13,18 +13,21 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> -#define check_pgt_cache() do { } while (0) +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ -#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { + gfp_t gfp = GFP_PGTABLE_USER; struct page *page; - page = alloc_page(PGALLOC_GFP); + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + + page = alloc_page(gfp); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { @@ -61,7 +64,7 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)__get_free_page(PGALLOC_GFP); + return (pud_t *)__get_free_page(GFP_PGTABLE_USER); } static inline void pud_free(struct mm_struct *mm, pud_t *pudp) @@ -89,42 +92,6 @@ static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); -static inline pte_t * -pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_page(PGALLOC_GFP); -} - -static inline pgtable_t -pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(PGALLOC_GFP, 0); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - -/* - * Free a PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep) -{ - if (ptep) - free_page((unsigned long)ptep); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 30e5e67749e5..3df60f97da1f 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -115,7 +115,6 @@ * Level 2 descriptor (PMD). */ #define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) -#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) #define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0) #define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0) #define PMD_TABLE_BIT (_AT(pmdval_t, 1) << 1) @@ -142,8 +141,8 @@ /* * Level 3 descriptor (PTE). */ +#define PTE_VALID (_AT(pteval_t, 1) << 0) #define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0) -#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0) #define PTE_TYPE_PAGE (_AT(pteval_t, 3) << 0) #define PTE_TABLE_BIT (_AT(pteval_t, 1) << 1) #define PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */ @@ -305,7 +304,7 @@ #define TTBR_BADDR_MASK_52 (((UL(1) << 46) - 1) << 2) #endif -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#ifdef CONFIG_ARM64_VA_BITS_52 /* Must be at least 64-byte aligned to prevent corruption of the TTBR */ #define TTBR1_BADDR_4852_OFFSET (((UL(1) << (52 - PGDIR_SHIFT)) - \ (UL(1) << (48 - PGDIR_SHIFT))) * 8) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index c81583be034b..9a21b84536f2 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -13,10 +13,10 @@ /* * Software defined PTE bits definition. */ -#define PTE_VALID (_AT(pteval_t, 1) << 0) #define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) +#define PTE_DEVMAP (_AT(pteval_t, 1) << 57) #define PTE_PROT_NONE (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */ #ifndef __ASSEMBLY__ @@ -77,7 +77,7 @@ }) #define PAGE_S2 __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(NORMAL) | PTE_S2_RDONLY | PAGE_S2_XN) -#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PAGE_S2_XN) +#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index fca26759081a..7576df00eb50 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -21,9 +21,7 @@ * and fixed mappings */ #define VMALLOC_START (MODULES_END) -#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) - -#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) +#define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K) #define FIRST_USER_ADDRESS 0UL @@ -35,6 +33,8 @@ #include <linux/mm_types.h> #include <linux/sched.h> +extern struct page *vmemmap; + extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); @@ -79,6 +79,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#define pte_devmap(pte) (!!(pte_val(pte) & PTE_DEVMAP)) #define pte_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK; \ @@ -206,6 +207,11 @@ static inline pmd_t pmd_mkcont(pmd_t pmd) return __pmd(pmd_val(pmd) | PMD_SECT_CONT); } +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); +} + static inline void set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); @@ -214,8 +220,10 @@ static inline void set_pte(pte_t *ptep, pte_t pte) * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ - if (pte_valid_not_user(pte)) + if (pte_valid_not_user(pte)) { dsb(ishst); + isb(); + } } extern void __sync_icache_dcache(pte_t pteval); @@ -235,29 +243,42 @@ extern void __sync_icache_dcache(pte_t pteval); * * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) */ -static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + +static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep, + pte_t pte) { pte_t old_pte; - if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) - __sync_icache_dcache(pte); + if (!IS_ENABLED(CONFIG_DEBUG_VM)) + return; + + old_pte = READ_ONCE(*ptep); + + if (!pte_valid(old_pte) || !pte_valid(pte)) + return; + if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1) + return; /* - * If the existing pte is valid, check for potential race with - * hardware updates of the pte (ptep_set_access_flags safely changes - * valid ptes without going through an invalid entry). + * Check for potential race with hardware updates of the pte + * (ptep_set_access_flags safely changes valid ptes without going + * through an invalid entry). */ - old_pte = READ_ONCE(*ptep); - if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) && - (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) { - VM_WARN_ONCE(!pte_young(pte), - "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(old_pte), pte_val(pte)); - VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), - "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(old_pte), pte_val(pte)); - } + VM_WARN_ONCE(!pte_young(pte), + "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(old_pte), pte_val(pte)); + VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), + "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(old_pte), pte_val(pte)); +} + +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) + __sync_icache_dcache(pte); + + __check_racy_pte_update(mm, ptep, pte); set_pte(ptep, pte); } @@ -282,7 +303,6 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) /* * Huge pte definitions. */ -#define pte_huge(pte) (!(pte_val(pte) & PTE_TABLE_BIT)) #define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) /* @@ -324,9 +344,14 @@ static inline pmd_t pte_pmd(pte_t pte) return __pmd(pte_val(pte)); } -static inline pgprot_t mk_sect_prot(pgprot_t prot) +static inline pgprot_t mk_pud_sect_prot(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT); +} + +static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) { - return __pgprot(pgprot_val(prot) & ~PTE_TABLE_BIT); + return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } #ifdef CONFIG_NUMA_BALANCING @@ -370,6 +395,14 @@ static inline int pmd_protnone(pmd_t pmd) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd)) +#endif +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP))); +} + #define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd)) #define __phys_to_pmd_val(phys) __phys_to_pte_val(phys) #define pmd_pfn(pmd) ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT) @@ -404,6 +437,18 @@ static inline int pmd_protnone(pmd_t pmd) __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) +/* + * DMA allocations for non-coherent devices use what the Arm architecture calls + * "Normal non-cacheable" memory, which permits speculation, unaligned accesses + * and merging of writes. This is different from "Device-nGnR[nE]" memory which + * is intended for MMIO and thus forbids speculation, preserves access size, + * requires strict alignment and can also force write responses to come from the + * endpoint. + */ +#define pgprot_dmacoherent(prot) \ + __pgprot_modify(prot, PTE_ATTRINDX_MASK, \ + PTE_ATTRINDX(MT_NORMAL_NC) | 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, @@ -419,8 +464,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_SECT) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 -#define pud_sect(pud) (0) -#define pud_table(pud) (1) +static inline bool pud_sect(pud_t pud) { return false; } +static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) @@ -453,8 +498,10 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) WRITE_ONCE(*pmdp, pmd); - if (pmd_valid(pmd)) + if (pmd_valid(pmd)) { dsb(ishst); + isb(); + } } static inline void pmd_clear(pmd_t *pmdp) @@ -512,8 +559,10 @@ static inline void set_pud(pud_t *pudp, pud_t pud) WRITE_ONCE(*pudp, pud); - if (pud_valid(pud)) + if (pud_valid(pud)) { dsb(ishst); + isb(); + } } static inline void pud_clear(pud_t *pudp) @@ -571,6 +620,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) WRITE_ONCE(*pgdp, pgd); dsb(ishst); + isb(); } static inline void pgd_clear(pgd_t *pgdp) @@ -655,6 +705,16 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma, { return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); } + +static inline int pud_devmap(pud_t pud) +{ + return 0; +} + +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} #endif /* @@ -801,8 +861,6 @@ extern int kern_addr_valid(unsigned long addr); #include <asm-generic/pgtable.h> -static inline void pgtable_cache_init(void) { } - /* * On AArch64, the cache coherency is handled via the set_pte_at() function. */ @@ -818,8 +876,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) -#define kc_vaddr_to_offset(v) ((v) & ~VA_START) -#define kc_offset_to_vaddr(o) ((o) | VA_START) +#define kc_vaddr_to_offset(v) ((v) & ~PAGE_END) +#define kc_offset_to_vaddr(o) ((o) | PAGE_END) #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index d328540cb85e..7a24bad1a58b 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -69,7 +69,7 @@ extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg); * The EL0 pointer bits used by a pointer authentication code. * This is dependent on TBI0 being enabled, or bits 63:56 would also apply. */ -#define ptrauth_user_pac_mask() GENMASK(54, vabits_user) +#define ptrauth_user_pac_mask() GENMASK(54, vabits_actual) /* Only valid for EL0 TTBR0 instruction pointers */ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr) diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h index 368d90a9d0e5..a2ce65a0c1fa 100644 --- a/arch/arm64/include/asm/proc-fns.h +++ b/arch/arm64/include/asm/proc-fns.h @@ -9,7 +9,6 @@ #ifndef __ASM_PROCFNS_H #define __ASM_PROCFNS_H -#ifdef __KERNEL__ #ifndef __ASSEMBLY__ #include <asm/page.h> @@ -25,5 +24,4 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr); #include <asm/memory.h> #endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ #endif /* __ASM_PROCFNS_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fd5b1a4efc70..5623685c7d13 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -20,7 +20,6 @@ #define NET_IP_ALIGN 0 #ifndef __ASSEMBLY__ -#ifdef __KERNEL__ #include <linux/build_bug.h> #include <linux/cache.h> @@ -42,8 +41,8 @@ * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. */ -#define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS) -#define TASK_SIZE_64 (UL(1) << vabits_user) +#define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS_MIN) +#define TASK_SIZE_64 (UL(1) << vabits_actual) #ifdef CONFIG_COMPAT #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS) @@ -193,6 +192,16 @@ static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) regs->pmr_save = GIC_PRIO_IRQON; } +static inline void set_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_SSBS_BIT; +} + +static inline void set_compat_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_AA32_SSBS_BIT; +} + static inline void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { @@ -200,7 +209,7 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, regs->pstate = PSR_MODE_EL0t; if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) - regs->pstate |= PSR_SSBS_BIT; + set_ssbs_bit(regs); regs->sp = sp; } @@ -219,7 +228,7 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, #endif if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) - regs->pstate |= PSR_AA32_SSBS_BIT; + set_compat_ssbs_bit(regs); regs->compat_sp = sp; } @@ -271,10 +280,6 @@ static inline void spin_lock_prefetch(const void *ptr) "nop") : : "p" (ptr)); } -#define HAVE_ARCH_PICK_MMAP_LAYOUT - -#endif - extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */ extern void __init minsigstksz_setup(void); @@ -296,6 +301,14 @@ extern void __init minsigstksz_setup(void); /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) +#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI +/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */ +long set_tagged_addr_ctrl(unsigned long arg); +long get_tagged_addr_ctrl(void); +#define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(arg) +#define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl() +#endif + /* * For CONFIG_GCC_PLUGIN_STACKLEAK * diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index dad858b6adc6..fbebb411ae20 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -24,9 +24,15 @@ * means masking more IRQs (or at least that the same IRQs remain masked). * * To mask interrupts, we clear the most significant bit of PMR. + * + * Some code sections either automatically switch back to PSR.I or explicitly + * require to not use priority masking. If bit GIC_PRIO_PSR_I_SET is included + * in the the priority mask, it indicates that PSR.I should be set and + * interrupt disabling temporarily does not rely on IRQ priorities. */ -#define GIC_PRIO_IRQON 0xf0 -#define GIC_PRIO_IRQOFF (GIC_PRIO_IRQON & ~0x80) +#define GIC_PRIO_IRQON 0xe0 +#define GIC_PRIO_IRQOFF (GIC_PRIO_IRQON & ~0x80) +#define GIC_PRIO_PSR_I_SET (1 << 4) /* Additional SPSR bits not exposed in the UABI */ #define PSR_IL_BIT (1 << 20) @@ -217,11 +223,12 @@ static inline void forget_syscall(struct pt_regs *regs) #define fast_interrupts_enabled(regs) \ (!((regs)->pstate & PSR_F_BIT)) -#define GET_USP(regs) \ - (!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp) - -#define SET_USP(ptregs, value) \ - (!compat_user_mode(regs) ? ((regs)->sp = value) : ((regs)->compat_sp = value)) +static inline unsigned long user_stack_pointer(struct pt_regs *regs) +{ + if (compat_user_mode(regs)) + return regs->compat_sp; + return regs->sp; +} extern int regs_query_register_offset(const char *name); extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, @@ -294,6 +301,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->regs[0]; } +static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +{ + regs->regs[0] = rc; +} + /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context @@ -320,13 +332,20 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, struct task_struct; int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task); -#define GET_IP(regs) ((unsigned long)(regs)->pc) -#define SET_IP(regs, value) ((regs)->pc = ((u64) (value))) - -#define GET_FP(ptregs) ((unsigned long)(ptregs)->regs[29]) -#define SET_FP(ptregs, value) ((ptregs)->regs[29] = ((u64) (value))) +static inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return regs->pc; +} +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->pc = val; +} -#include <asm-generic/ptrace.h> +static inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return regs->regs[29]; +} #define procedure_link_pointer(regs) ((regs)->regs[30]) @@ -336,7 +355,6 @@ static inline void procedure_link_pointer_set(struct pt_regs *regs, procedure_link_pointer(regs) = val; } -#undef profile_pc extern unsigned long profile_pc(struct pt_regs *regs); #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h index 0418c67f2b8b..7e9f163d02ec 100644 --- a/arch/arm64/include/asm/signal32.h +++ b/arch/arm64/include/asm/signal32.h @@ -5,10 +5,55 @@ #ifndef __ASM_SIGNAL32_H #define __ASM_SIGNAL32_H -#ifdef __KERNEL__ #ifdef CONFIG_COMPAT #include <linux/compat.h> +struct compat_sigcontext { + /* We always set these two fields to 0 */ + compat_ulong_t trap_no; + compat_ulong_t error_code; + + compat_ulong_t oldmask; + compat_ulong_t arm_r0; + compat_ulong_t arm_r1; + compat_ulong_t arm_r2; + compat_ulong_t arm_r3; + compat_ulong_t arm_r4; + compat_ulong_t arm_r5; + compat_ulong_t arm_r6; + compat_ulong_t arm_r7; + compat_ulong_t arm_r8; + compat_ulong_t arm_r9; + compat_ulong_t arm_r10; + compat_ulong_t arm_fp; + compat_ulong_t arm_ip; + compat_ulong_t arm_sp; + compat_ulong_t arm_lr; + compat_ulong_t arm_pc; + compat_ulong_t arm_cpsr; + compat_ulong_t fault_address; +}; + +struct compat_ucontext { + compat_ulong_t uc_flags; + compat_uptr_t uc_link; + compat_stack_t uc_stack; + struct compat_sigcontext uc_mcontext; + compat_sigset_t uc_sigmask; + int __unused[32 - (sizeof(compat_sigset_t) / sizeof(int))]; + compat_ulong_t uc_regspace[128] __attribute__((__aligned__(8))); +}; + +struct compat_sigframe { + struct compat_ucontext uc; + compat_ulong_t retcode[2]; +}; + +struct compat_rt_sigframe { + struct compat_siginfo info; + struct compat_sigframe sig; +}; + int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set, struct pt_regs *regs); int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, @@ -33,5 +78,4 @@ static inline void compat_setup_restart_syscall(struct pt_regs *regs) { } #endif /* CONFIG_COMPAT */ -#endif /* __KERNEL__ */ #endif /* __ASM_SIGNAL32_H */ diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index 7e245b9e03a5..7434844036d3 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -12,9 +12,9 @@ #include <linux/preempt.h> #include <linux/types.h> -#ifdef CONFIG_KERNEL_MODE_NEON +DECLARE_PER_CPU(bool, fpsimd_context_busy); -DECLARE_PER_CPU(bool, kernel_neon_busy); +#ifdef CONFIG_KERNEL_MODE_NEON /* * may_use_simd - whether it is allowable at this time to issue SIMD @@ -26,15 +26,15 @@ DECLARE_PER_CPU(bool, kernel_neon_busy); static __must_check inline bool may_use_simd(void) { /* - * kernel_neon_busy is only set while preemption is disabled, + * fpsimd_context_busy is only set while preemption is disabled, * and is clear whenever preemption is enabled. Since - * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy + * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy * cannot change under our feet -- if it's set we cannot be * migrated, and if it's clear we cannot be migrated to a CPU * where it is set. */ return !in_irq() && !irqs_disabled() && !in_nmi() && - !this_cpu_read(kernel_neon_busy); + !this_cpu_read(fpsimd_context_busy); } #else /* ! CONFIG_KERNEL_MODE_NEON */ diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index df45af931459..4d9b1f48dc39 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -8,19 +8,12 @@ #include <linux/percpu.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> +#include <linux/types.h> #include <asm/memory.h> #include <asm/ptrace.h> #include <asm/sdei.h> -struct stackframe { - unsigned long fp; - unsigned long pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - int graph; -#endif -}; - enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, @@ -28,6 +21,7 @@ enum stack_type { STACK_TYPE_OVERFLOW, STACK_TYPE_SDEI_NORMAL, STACK_TYPE_SDEI_CRITICAL, + __NR_STACK_TYPES }; struct stack_info { @@ -36,6 +30,37 @@ struct stack_info { enum stack_type type; }; +/* + * A snapshot of a frame record or fp/lr register values, along with some + * accounting information necessary for robust unwinding. + * + * @fp: The fp value in the frame record (or the real fp) + * @pc: The fp value in the frame record (or the real lr) + * + * @stacks_done: Stacks which have been entirely unwound, for which it is no + * longer valid to unwind to. + * + * @prev_fp: The fp that pointed to this frame record, or a synthetic value + * of 0. This is used to ensure that within a stack, each + * subsequent frame record is at an increasing address. + * @prev_type: The type of stack this frame record was on, or a synthetic + * value of STACK_TYPE_UNKNOWN. This is used to detect a + * transition from one stack to another. + * + * @graph: When FUNCTION_GRAPH_TRACER is selected, holds the index of a + * replacement lr value in the ftrace graph stack. + */ +struct stackframe { + unsigned long fp; + unsigned long pc; + DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); + unsigned long prev_fp; + enum stack_type prev_type; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + int graph; +#endif +}; + extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); @@ -64,8 +89,9 @@ static inline bool on_irq_stack(unsigned long sp, return true; } -static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp, - struct stack_info *info) +static inline bool on_task_stack(const struct task_struct *tsk, + unsigned long sp, + struct stack_info *info) { unsigned long low = (unsigned long)task_stack_page(tsk); unsigned long high = low + THREAD_SIZE; @@ -112,10 +138,13 @@ static inline bool on_overflow_stack(unsigned long sp, * We can only safely access per-cpu stacks from current in a non-preemptible * context. */ -static inline bool on_accessible_stack(struct task_struct *tsk, - unsigned long sp, - struct stack_info *info) +static inline bool on_accessible_stack(const struct task_struct *tsk, + unsigned long sp, + struct stack_info *info) { + if (info) + info->type = STACK_TYPE_UNKNOWN; + if (on_task_stack(tsk, sp, info)) return true; if (tsk != current || preemptible()) @@ -130,4 +159,27 @@ static inline bool on_accessible_stack(struct task_struct *tsk, return false; } +static inline void start_backtrace(struct stackframe *frame, + unsigned long fp, unsigned long pc) +{ + frame->fp = fp; + frame->pc = pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame->graph = 0; +#endif + + /* + * Prime the first unwind. + * + * In unwind_frame() we'll check that the FP points to a valid stack, + * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be + * treated as a transition to whichever stack that happens to be. The + * prev_fp value won't be used, but we set it to 0 such that it is + * definitely not an accessible stack address. + */ + bitmap_zero(frame->stacks_done, __NR_STACK_TYPES); + frame->prev_fp = 0; + frame->prev_type = STACK_TYPE_UNKNOWN; +} + #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index 507d0ee6bc69..06d880b3526c 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -8,6 +8,8 @@ #ifndef __ASM_SYSCALL_WRAPPER_H #define __ASM_SYSCALL_WRAPPER_H +struct pt_regs; + #define SC_ARM64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ ,,regs->regs[0],,regs->regs[1],,regs->regs[2] \ @@ -35,8 +37,11 @@ ALLOW_ERROR_INJECTION(__arm64_compat_sys_##sname, ERRNO); \ asmlinkage long __arm64_compat_sys_##sname(const struct pt_regs *__unused) -#define COND_SYSCALL_COMPAT(name) \ - cond_syscall(__arm64_compat_sys_##name); +#define COND_SYSCALL_COMPAT(name) \ + asmlinkage long __weak __arm64_compat_sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } #define COMPAT_SYS_NI(name) \ SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers); @@ -70,7 +75,11 @@ #endif #ifndef COND_SYSCALL -#define COND_SYSCALL(name) cond_syscall(__arm64_sys_##name) +#define COND_SYSCALL(name) \ + asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } #endif #ifndef SYS_NI diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index cd7f7ce1a56a..972d196c7714 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -9,7 +9,7 @@ #ifndef __ASM_SYSREG_H #define __ASM_SYSREG_H -#include <linux/const.h> +#include <linux/bits.h> #include <linux/stringify.h> /* @@ -191,6 +191,9 @@ #define SYS_APGAKEYLO_EL1 sys_reg(3, 0, 2, 3, 0) #define SYS_APGAKEYHI_EL1 sys_reg(3, 0, 2, 3, 1) +#define SYS_SPSR_EL1 sys_reg(3, 0, 4, 0, 0) +#define SYS_ELR_EL1 sys_reg(3, 0, 4, 0, 1) + #define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) #define SYS_AFSR0_EL1 sys_reg(3, 0, 5, 1, 0) @@ -209,6 +212,9 @@ #define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0) #define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0) +#define SYS_PAR_EL1_F BIT(1) +#define SYS_PAR_EL1_FST GENMASK(6, 1) + /*** Statistical Profiling Extension ***/ /* ID registers */ #define SYS_PMSIDR_EL1 sys_reg(3, 0, 9, 9, 7) @@ -382,6 +388,9 @@ #define SYS_CNTP_CTL_EL0 sys_reg(3, 3, 14, 2, 1) #define SYS_CNTP_CVAL_EL0 sys_reg(3, 3, 14, 2, 2) +#define SYS_CNTV_CTL_EL0 sys_reg(3, 3, 14, 3, 1) +#define SYS_CNTV_CVAL_EL0 sys_reg(3, 3, 14, 3, 2) + #define SYS_AARCH32_CNTP_TVAL sys_reg(0, 0, 14, 2, 0) #define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1) #define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0) @@ -392,14 +401,17 @@ #define __TYPER_CRm(n) (0xc | (((n) >> 3) & 0x3)) #define SYS_PMEVTYPERn_EL0(n) sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n)) -#define SYS_PMCCFILTR_EL0 sys_reg (3, 3, 14, 15, 7) +#define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7) #define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0) - #define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0) +#define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) +#define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1) #define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1) +#define SYS_ESR_EL2 sys_reg(3, 4, 5, 2, 0) #define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3) #define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0) +#define SYS_FAR_EL2 sys_reg(3, 4, 6, 0, 0) #define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1) #define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x) @@ -444,80 +456,80 @@ #define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7) /* VHE encodings for architectural EL0/1 system registers */ +#define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) +#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) #define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) +#define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) +#define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) +#define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) +#define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0) +#define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1) +#define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0) +#define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1) +#define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0) +#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0) +#define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0) +#define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0) +#define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0) +#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1) +#define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0) +#define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0) +#define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1) +#define SYS_CNTP_CVAL_EL02 sys_reg(3, 5, 14, 2, 2) +#define SYS_CNTV_TVAL_EL02 sys_reg(3, 5, 14, 3, 0) +#define SYS_CNTV_CTL_EL02 sys_reg(3, 5, 14, 3, 1) +#define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2) /* Common SCTLR_ELx flags. */ -#define SCTLR_ELx_DSSBS (_BITUL(44)) -#define SCTLR_ELx_ENIA (_BITUL(31)) -#define SCTLR_ELx_ENIB (_BITUL(30)) -#define SCTLR_ELx_ENDA (_BITUL(27)) -#define SCTLR_ELx_EE (_BITUL(25)) -#define SCTLR_ELx_IESB (_BITUL(21)) -#define SCTLR_ELx_WXN (_BITUL(19)) -#define SCTLR_ELx_ENDB (_BITUL(13)) -#define SCTLR_ELx_I (_BITUL(12)) -#define SCTLR_ELx_SA (_BITUL(3)) -#define SCTLR_ELx_C (_BITUL(2)) -#define SCTLR_ELx_A (_BITUL(1)) -#define SCTLR_ELx_M (_BITUL(0)) +#define SCTLR_ELx_DSSBS (BIT(44)) +#define SCTLR_ELx_ENIA (BIT(31)) +#define SCTLR_ELx_ENIB (BIT(30)) +#define SCTLR_ELx_ENDA (BIT(27)) +#define SCTLR_ELx_EE (BIT(25)) +#define SCTLR_ELx_IESB (BIT(21)) +#define SCTLR_ELx_WXN (BIT(19)) +#define SCTLR_ELx_ENDB (BIT(13)) +#define SCTLR_ELx_I (BIT(12)) +#define SCTLR_ELx_SA (BIT(3)) +#define SCTLR_ELx_C (BIT(2)) +#define SCTLR_ELx_A (BIT(1)) +#define SCTLR_ELx_M (BIT(0)) #define SCTLR_ELx_FLAGS (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \ SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB) /* SCTLR_EL2 specific flags. */ -#define SCTLR_EL2_RES1 ((_BITUL(4)) | (_BITUL(5)) | (_BITUL(11)) | (_BITUL(16)) | \ - (_BITUL(18)) | (_BITUL(22)) | (_BITUL(23)) | (_BITUL(28)) | \ - (_BITUL(29))) -#define SCTLR_EL2_RES0 ((_BITUL(6)) | (_BITUL(7)) | (_BITUL(8)) | (_BITUL(9)) | \ - (_BITUL(10)) | (_BITUL(13)) | (_BITUL(14)) | (_BITUL(15)) | \ - (_BITUL(17)) | (_BITUL(20)) | (_BITUL(24)) | (_BITUL(26)) | \ - (_BITUL(27)) | (_BITUL(30)) | (_BITUL(31)) | \ - (0xffffefffUL << 32)) +#define SCTLR_EL2_RES1 ((BIT(4)) | (BIT(5)) | (BIT(11)) | (BIT(16)) | \ + (BIT(18)) | (BIT(22)) | (BIT(23)) | (BIT(28)) | \ + (BIT(29))) #ifdef CONFIG_CPU_BIG_ENDIAN #define ENDIAN_SET_EL2 SCTLR_ELx_EE -#define ENDIAN_CLEAR_EL2 0 #else #define ENDIAN_SET_EL2 0 -#define ENDIAN_CLEAR_EL2 SCTLR_ELx_EE -#endif - -/* SCTLR_EL2 value used for the hyp-stub */ -#define SCTLR_EL2_SET (SCTLR_ELx_IESB | ENDIAN_SET_EL2 | SCTLR_EL2_RES1) -#define SCTLR_EL2_CLEAR (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \ - SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_WXN | \ - SCTLR_ELx_DSSBS | ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0) - -#if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffffUL -#error "Inconsistent SCTLR_EL2 set/clear bits" #endif /* SCTLR_EL1 specific flags. */ -#define SCTLR_EL1_UCI (_BITUL(26)) -#define SCTLR_EL1_E0E (_BITUL(24)) -#define SCTLR_EL1_SPAN (_BITUL(23)) -#define SCTLR_EL1_NTWE (_BITUL(18)) -#define SCTLR_EL1_NTWI (_BITUL(16)) -#define SCTLR_EL1_UCT (_BITUL(15)) -#define SCTLR_EL1_DZE (_BITUL(14)) -#define SCTLR_EL1_UMA (_BITUL(9)) -#define SCTLR_EL1_SED (_BITUL(8)) -#define SCTLR_EL1_ITD (_BITUL(7)) -#define SCTLR_EL1_CP15BEN (_BITUL(5)) -#define SCTLR_EL1_SA0 (_BITUL(4)) - -#define SCTLR_EL1_RES1 ((_BITUL(11)) | (_BITUL(20)) | (_BITUL(22)) | (_BITUL(28)) | \ - (_BITUL(29))) -#define SCTLR_EL1_RES0 ((_BITUL(6)) | (_BITUL(10)) | (_BITUL(13)) | (_BITUL(17)) | \ - (_BITUL(27)) | (_BITUL(30)) | (_BITUL(31)) | \ - (0xffffefffUL << 32)) +#define SCTLR_EL1_UCI (BIT(26)) +#define SCTLR_EL1_E0E (BIT(24)) +#define SCTLR_EL1_SPAN (BIT(23)) +#define SCTLR_EL1_NTWE (BIT(18)) +#define SCTLR_EL1_NTWI (BIT(16)) +#define SCTLR_EL1_UCT (BIT(15)) +#define SCTLR_EL1_DZE (BIT(14)) +#define SCTLR_EL1_UMA (BIT(9)) +#define SCTLR_EL1_SED (BIT(8)) +#define SCTLR_EL1_ITD (BIT(7)) +#define SCTLR_EL1_CP15BEN (BIT(5)) +#define SCTLR_EL1_SA0 (BIT(4)) + +#define SCTLR_EL1_RES1 ((BIT(11)) | (BIT(20)) | (BIT(22)) | (BIT(28)) | \ + (BIT(29))) #ifdef CONFIG_CPU_BIG_ENDIAN #define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE) -#define ENDIAN_CLEAR_EL1 0 #else #define ENDIAN_SET_EL1 0 -#define ENDIAN_CLEAR_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE) #endif #define SCTLR_EL1_SET (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA |\ @@ -525,13 +537,6 @@ SCTLR_EL1_DZE | SCTLR_EL1_UCT |\ SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\ ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_RES1) -#define SCTLR_EL1_CLEAR (SCTLR_ELx_A | SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD |\ - SCTLR_EL1_UMA | SCTLR_ELx_WXN | ENDIAN_CLEAR_EL1 |\ - SCTLR_ELx_DSSBS | SCTLR_EL1_NTWI | SCTLR_EL1_RES0) - -#if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffffUL -#error "Inconsistent SCTLR_EL1 set/clear bits" -#endif /* id_aa64isar0 */ #define ID_AA64ISAR0_TS_SHIFT 52 @@ -549,6 +554,7 @@ /* id_aa64isar1 */ #define ID_AA64ISAR1_SB_SHIFT 36 +#define ID_AA64ISAR1_FRINTTS_SHIFT 32 #define ID_AA64ISAR1_GPI_SHIFT 28 #define ID_AA64ISAR1_GPA_SHIFT 24 #define ID_AA64ISAR1_LRCPC_SHIFT 20 @@ -724,13 +730,13 @@ #define ZCR_ELx_LEN_SIZE 9 #define ZCR_ELx_LEN_MASK 0x1ff -#define CPACR_EL1_ZEN_EL1EN (_BITUL(16)) /* enable EL1 access */ -#define CPACR_EL1_ZEN_EL0EN (_BITUL(17)) /* enable EL0 access, if EL1EN set */ +#define CPACR_EL1_ZEN_EL1EN (BIT(16)) /* enable EL1 access */ +#define CPACR_EL1_ZEN_EL0EN (BIT(17)) /* enable EL0 access, if EL1EN set */ #define CPACR_EL1_ZEN (CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN) /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ -#define SYS_MPIDR_SAFE_VAL (_BITUL(31)) +#define SYS_MPIDR_SAFE_VAL (BIT(31)) #ifdef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 2372e97db29c..f0cec4160136 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -8,8 +8,6 @@ #ifndef __ASM_THREAD_INFO_H #define __ASM_THREAD_INFO_H -#ifdef __KERNEL__ - #include <linux/compiler.h> #ifndef __ASSEMBLY__ @@ -59,27 +57,18 @@ void arch_release_task_struct(struct task_struct *tsk); #endif -/* - * thread information flags: - * TIF_SYSCALL_TRACE - syscall trace active - * TIF_SYSCALL_TRACEPOINT - syscall tracepoint for ftrace - * TIF_SYSCALL_AUDIT - syscall auditing - * TIF_SECCOMP - syscall secure computing - * TIF_SIGPENDING - signal pending - * TIF_NEED_RESCHED - rescheduling necessary - * TIF_NOTIFY_RESUME - callback before returning to user - */ -#define TIF_SIGPENDING 0 -#define TIF_NEED_RESCHED 1 +#define TIF_SIGPENDING 0 /* signal pending */ +#define TIF_NEED_RESCHED 1 /* rescheduling necessary */ #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ #define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ #define TIF_NOHZ 7 -#define TIF_SYSCALL_TRACE 8 -#define TIF_SYSCALL_AUDIT 9 -#define TIF_SYSCALL_TRACEPOINT 10 -#define TIF_SECCOMP 11 +#define TIF_SYSCALL_TRACE 8 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ +#define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ +#define TIF_SECCOMP 11 /* syscall secure computing */ +#define TIF_SYSCALL_EMU 12 /* syscall emulation active */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_FREEZE 19 #define TIF_RESTORE_SIGMASK 20 @@ -88,6 +77,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_SVE 23 /* Scalable Vector Extension in use */ #define TIF_SVE_VL_INHERIT 24 /* Inherit sve_vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ +#define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) @@ -98,6 +88,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_FSCHECK (1 << TIF_FSCHECK) #define _TIF_32BIT (1 << TIF_32BIT) @@ -109,7 +100,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ - _TIF_NOHZ) + _TIF_NOHZ | _TIF_SYSCALL_EMU) #define INIT_THREAD_INFO(tsk) \ { \ @@ -118,5 +109,4 @@ void arch_release_task_struct(struct task_struct *tsk); .addr_limit = KERNEL_DS, \ } -#endif /* __KERNEL__ */ #endif /* __ASM_THREAD_INFO_H */ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index a95d1fcb7e21..b76df828e6b7 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -44,7 +44,7 @@ static inline void tlb_flush(struct mmu_gather *tlb) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); tlb_remove_table(tlb, pte); } diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 8af7a85f76bd..bc3949064725 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -251,6 +251,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr) dsb(ishst); __tlbi(vaae1is, addr); dsb(ish); + isb(); } #endif diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 0524f2438649..a4d945db95a2 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -4,29 +4,6 @@ #include <linux/cpumask.h> -struct cpu_topology { - int thread_id; - int core_id; - int package_id; - int llc_id; - cpumask_t thread_sibling; - cpumask_t core_sibling; - cpumask_t llc_sibling; -}; - -extern struct cpu_topology cpu_topology[NR_CPUS]; - -#define topology_physical_package_id(cpu) (cpu_topology[cpu].package_id) -#define topology_core_id(cpu) (cpu_topology[cpu].core_id) -#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) -#define topology_llc_cpumask(cpu) (&cpu_topology[cpu].llc_sibling) - -void init_cpu_topology(void); -void store_cpu_topology(unsigned int cpuid); -void remove_cpu_topology(unsigned int cpuid); -const struct cpumask *cpu_coregroup_mask(int cpu); - #ifdef CONFIG_NUMA struct pci_bus; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 5a1c32260c1f..097d6bfac0b7 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -62,6 +62,10 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si { unsigned long ret, limit = current_thread_info()->addr_limit; + if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) && + test_thread_flag(TIF_TAGGED_ADDR)) + addr = untagged_addr(addr); + __chk_user_ptr(addr); asm volatile( // A + B <= C + 1 for all A,B,C, in four easy steps: @@ -215,7 +219,8 @@ static inline void uaccess_enable_not_uao(void) /* * Sanitise a uaccess pointer such that it becomes NULL if above the - * current addr_limit. + * current addr_limit. In case the pointer is tagged (has the top byte set), + * untag the pointer before checking. */ #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) static inline void __user *__uaccess_mask_ptr(const void __user *ptr) @@ -223,10 +228,11 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) void __user *safe_ptr; asm volatile( - " bics xzr, %1, %2\n" + " bics xzr, %3, %2\n" " csel %0, %1, xzr, eq\n" : "=&r" (safe_ptr) - : "r" (ptr), "r" (current_thread_info()->addr_limit) + : "r" (ptr), "r" (current_thread_info()->addr_limit), + "r" (untagged_addr(ptr)) : "cc"); csdb(); diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index c9f8dd421c5f..2629a68b8724 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -22,8 +22,13 @@ #define __NR_compat_exit 1 #define __NR_compat_read 3 #define __NR_compat_write 4 +#define __NR_compat_gettimeofday 78 #define __NR_compat_sigreturn 119 #define __NR_compat_rt_sigreturn 173 +#define __NR_compat_clock_getres 247 +#define __NR_compat_clock_gettime 263 +#define __NR_compat_clock_gettime64 403 +#define __NR_compat_clock_getres_time64 406 /* * The following SVCs are ARM private. @@ -33,10 +38,11 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 434 +#define __NR_compat_syscalls 436 #endif #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #ifndef __COMPAT_SYSCALL_NR #include <uapi/asm/unistd.h> diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index aa995920bd34..94ab29cf4f00 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -875,6 +875,10 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) +#define __NR_clone3 435 +__SYSCALL(__NR_clone3, sys_clone3) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h index 1f94ec19903c..07468428fd29 100644 --- a/arch/arm64/include/asm/vdso.h +++ b/arch/arm64/include/asm/vdso.h @@ -5,8 +5,6 @@ #ifndef __ASM_VDSO_H #define __ASM_VDSO_H -#ifdef __KERNEL__ - /* * Default link address for the vDSO. * Since we randomise the VDSO mapping, there's little point in trying @@ -17,6 +15,9 @@ #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> +#ifdef CONFIG_COMPAT_VDSO +#include <generated/vdso32-offsets.h> +#endif #define VDSO_SYMBOL(base, name) \ ({ \ @@ -25,6 +26,4 @@ #endif /* !__ASSEMBLY__ */ -#endif /* __KERNEL__ */ - #endif /* __ASM_VDSO_H */ diff --git a/arch/arm64/include/asm/vdso/compat_barrier.h b/arch/arm64/include/asm/vdso/compat_barrier.h new file mode 100644 index 000000000000..fb60a88b5ed4 --- /dev/null +++ b/arch/arm64/include/asm/vdso/compat_barrier.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 ARM Limited + */ +#ifndef __COMPAT_BARRIER_H +#define __COMPAT_BARRIER_H + +#ifndef __ASSEMBLY__ +/* + * Warning: This code is meant to be used with + * ENABLE_COMPAT_VDSO only. + */ +#ifndef ENABLE_COMPAT_VDSO +#error This header is meant to be used with ENABLE_COMPAT_VDSO only +#endif + +#ifdef dmb +#undef dmb +#endif + +#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory") + +#if __LINUX_ARM_ARCH__ >= 8 +#define aarch32_smp_mb() dmb(ish) +#define aarch32_smp_rmb() dmb(ishld) +#define aarch32_smp_wmb() dmb(ishst) +#else +#define aarch32_smp_mb() dmb(ish) +#define aarch32_smp_rmb() aarch32_smp_mb() +#define aarch32_smp_wmb() dmb(ishst) +#endif + + +#undef smp_mb +#undef smp_rmb +#undef smp_wmb + +#define smp_mb() aarch32_smp_mb() +#define smp_rmb() aarch32_smp_rmb() +#define smp_wmb() aarch32_smp_wmb() + +#endif /* !__ASSEMBLY__ */ + +#endif /* __COMPAT_BARRIER_H */ diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h new file mode 100644 index 000000000000..c50ee1b7d5cd --- /dev/null +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 ARM Limited + */ +#ifndef __ASM_VDSO_GETTIMEOFDAY_H +#define __ASM_VDSO_GETTIMEOFDAY_H + +#ifndef __ASSEMBLY__ + +#include <asm/unistd.h> +#include <uapi/linux/time.h> + +#include <asm/vdso/compat_barrier.h> + +#define __VDSO_USE_SYSCALL ULLONG_MAX + +#define VDSO_HAS_CLOCK_GETRES 1 + +#define VDSO_HAS_32BIT_FALLBACK 1 + +static __always_inline +int gettimeofday_fallback(struct __kernel_old_timeval *_tv, + struct timezone *_tz) +{ + register struct timezone *tz asm("r1") = _tz; + register struct __kernel_old_timeval *tv asm("r0") = _tv; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_gettimeofday; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (tv), "r" (tz), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline +long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + register struct __kernel_timespec *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_gettime64; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline +long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + register struct old_timespec32 *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_gettime; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + register struct __kernel_timespec *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_getres_time64; + + /* The checks below are required for ABI consistency with arm */ + if ((_clkid >= MAX_CLOCKS) && (_ts == NULL)) + return -EINVAL; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline +int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + register struct old_timespec32 *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_getres; + + /* The checks below are required for ABI consistency with arm */ + if ((_clkid >= MAX_CLOCKS) && (_ts == NULL)) + return -EINVAL; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) +{ + u64 res; + + /* + * clock_mode == 0 implies that vDSO are enabled otherwise + * fallback on syscall. + */ + if (clock_mode) + return __VDSO_USE_SYSCALL; + + /* + * This isb() is required to prevent that the counter value + * is speculated. + */ + isb(); + asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (res)); + /* + * This isb() is required to prevent that the seq lock is + * speculated. + */ + isb(); + + return res; +} + +static __always_inline const struct vdso_data *__arch_get_vdso_data(void) +{ + const struct vdso_data *ret; + + /* + * This simply puts &_vdso_data into ret. The reason why we don't use + * `ret = _vdso_data` is that the compiler tends to optimise this in a + * very suboptimal way: instead of keeping &_vdso_data in a register, + * it goes through a relocation almost every time _vdso_data must be + * accessed (even in subfunctions). This is both time and space + * consuming: each relocation uses a word in the code section, and it + * has to be loaded at runtime. + * + * This trick hides the assignment from the compiler. Since it cannot + * track where the pointer comes from, it will only use one relocation + * where __arch_get_vdso_data() is called, and then keep the result in + * a register. + */ + asm volatile("mov %0, %1" : "=r"(ret) : "r"(_vdso_data)); + + return ret; +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h new file mode 100644 index 000000000000..b08f476b72b4 --- /dev/null +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 ARM Limited + */ +#ifndef __ASM_VDSO_GETTIMEOFDAY_H +#define __ASM_VDSO_GETTIMEOFDAY_H + +#ifndef __ASSEMBLY__ + +#include <asm/unistd.h> +#include <uapi/linux/time.h> + +#define __VDSO_USE_SYSCALL ULLONG_MAX + +#define VDSO_HAS_CLOCK_GETRES 1 + +static __always_inline +int gettimeofday_fallback(struct __kernel_old_timeval *_tv, + struct timezone *_tz) +{ + register struct timezone *tz asm("x1") = _tz; + register struct __kernel_old_timeval *tv asm("x0") = _tv; + register long ret asm ("x0"); + register long nr asm("x8") = __NR_gettimeofday; + + asm volatile( + " svc #0\n" + : "=r" (ret) + : "r" (tv), "r" (tz), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline +long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + register struct __kernel_timespec *ts asm("x1") = _ts; + register clockid_t clkid asm("x0") = _clkid; + register long ret asm ("x0"); + register long nr asm("x8") = __NR_clock_gettime; + + asm volatile( + " svc #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + register struct __kernel_timespec *ts asm("x1") = _ts; + register clockid_t clkid asm("x0") = _clkid; + register long ret asm ("x0"); + register long nr asm("x8") = __NR_clock_getres; + + asm volatile( + " svc #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) +{ + u64 res; + + /* + * clock_mode == 0 implies that vDSO are enabled otherwise + * fallback on syscall. + */ + if (clock_mode) + return __VDSO_USE_SYSCALL; + + /* + * This isb() is required to prevent that the counter value + * is speculated. + */ + isb(); + asm volatile("mrs %0, cntvct_el0" : "=r" (res) :: "memory"); + /* + * This isb() is required to prevent that the seq lock is + * speculated.# + */ + isb(); + + return res; +} + +static __always_inline +const struct vdso_data *__arch_get_vdso_data(void) +{ + return _vdso_data; +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h new file mode 100644 index 000000000000..0c731bfc7c8c --- /dev/null +++ b/arch/arm64/include/asm/vdso/vsyscall.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_VSYSCALL_H +#define __ASM_VDSO_VSYSCALL_H + +#ifndef __ASSEMBLY__ + +#include <linux/timekeeper_internal.h> +#include <vdso/datapage.h> + +#define VDSO_PRECISION_MASK ~(0xFF00ULL<<48) + +extern struct vdso_data *vdso_data; + +/* + * Update the vDSO data page to keep in sync with kernel timekeeping. + */ +static __always_inline +struct vdso_data *__arm64_get_k_vdso_data(void) +{ + return vdso_data; +} +#define __arch_get_k_vdso_data __arm64_get_k_vdso_data + +static __always_inline +int __arm64_get_clock_mode(struct timekeeper *tk) +{ + u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct; + + return use_syscall; +} +#define __arch_get_clock_mode __arm64_get_clock_mode + +static __always_inline +int __arm64_use_vsyscall(struct vdso_data *vdata) +{ + return !vdata[CS_HRES_COARSE].clock_mode; +} +#define __arch_use_vsyscall __arm64_use_vsyscall + +static __always_inline +void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk) +{ + vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK; + vdata[CS_RAW].mask = VDSO_PRECISION_MASK; +} +#define __arch_update_vsyscall __arm64_update_vsyscall + +/* The asm-generic header needs to be included after the definitions above */ +#include <asm-generic/vdso/vsyscall.h> + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_VDSO_VSYSCALL_H */ diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h index ba6dbc3de864..1f38bf330a6e 100644 --- a/arch/arm64/include/asm/vdso_datapage.h +++ b/arch/arm64/include/asm/vdso_datapage.h @@ -5,8 +5,6 @@ #ifndef __ASM_VDSO_DATAPAGE_H #define __ASM_VDSO_DATAPAGE_H -#ifdef __KERNEL__ - #ifndef __ASSEMBLY__ struct vdso_data { @@ -32,6 +30,4 @@ struct vdso_data { #endif /* !__ASSEMBLY__ */ -#endif /* __KERNEL__ */ - #endif /* __ASM_VDSO_DATAPAGE_H */ diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h index d88e56b90b93..27e984977402 100644 --- a/arch/arm64/include/asm/xen/page-coherent.h +++ b/arch/arm64/include/asm/xen/page-coherent.h @@ -1,77 +1,2 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H -#define _ASM_ARM64_XEN_PAGE_COHERENT_H - -#include <linux/dma-mapping.h> -#include <asm/page.h> #include <xen/arm/page-coherent.h> - -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) -{ - return dma_direct_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, unsigned long attrs) -{ - dma_direct_free(hwdev, size, cpu_addr, dma_handle, 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) -{ - unsigned long pfn = PFN_DOWN(handle); - - if (pfn_valid(pfn)) - dma_direct_sync_single_for_cpu(hwdev, handle, size, dir); - else - __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir); -} - -static inline void xen_dma_sync_single_for_device(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned long pfn = PFN_DOWN(handle); - if (pfn_valid(pfn)) - dma_direct_sync_single_for_device(hwdev, handle, size, dir); - else - __xen_dma_sync_single_for_device(hwdev, handle, size, dir); -} - -static inline void xen_dma_map_page(struct device *hwdev, struct page *page, - dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long page_pfn = page_to_xen_pfn(page); - unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); - unsigned long compound_pages = - (1<<compound_order(page)) * XEN_PFN_PER_PAGE; - bool local = (page_pfn <= dev_pfn) && - (dev_pfn - page_pfn < compound_pages); - - if (local) - dma_direct_map_page(hwdev, page, offset, size, dir, attrs); - else - __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs); -} - -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long pfn = PFN_DOWN(handle); - /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a - * foreign mfn will always return false. If the page is local we can - * safely call the native dma_ops function, otherwise we call the xen - * specific function. - */ - if (pfn_valid(pfn)) - dma_direct_unmap_page(hwdev, handle, size, dir, attrs); - else - __xen_dma_unmap_page(hwdev, handle, size, dir, attrs); -} - -#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */ |