diff options
Diffstat (limited to 'arch/arm64/include/asm')
100 files changed, 2610 insertions, 1594 deletions
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 64202010b700..5c8ee5a541d2 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -3,6 +3,8 @@ generic-y += early_ioremap.h generic-y += mcs_spinlock.h generic-y += qrwlock.h generic-y += qspinlock.h +generic-y += parport.h generic-y += user.h generated-y += cpucaps.h +generated-y += sysreg-defs.h diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 7e157ab6cd50..3622e9f4fb44 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -2,10 +2,22 @@ #ifndef __ASM_ALTERNATIVE_MACROS_H #define __ASM_ALTERNATIVE_MACROS_H +#include <linux/const.h> +#include <vdso/bits.h> + #include <asm/cpucaps.h> #include <asm/insn-def.h> -#define ARM64_CB_PATCH ARM64_NCAPS +/* + * Binutils 2.27.0 can't handle a 'UL' suffix on constants, so for the assembly + * macros below we must use we must use `(1 << ARM64_CB_SHIFT)`. + */ +#define ARM64_CB_SHIFT 15 +#define ARM64_CB_BIT BIT(ARM64_CB_SHIFT) + +#if ARM64_NCAPS >= ARM64_CB_BIT +#error "cpucaps have overflown ARM64_CB_BIT" +#endif #ifndef __ASSEMBLY__ @@ -73,8 +85,8 @@ #define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...) \ __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg)) -#define ALTERNATIVE_CB(oldinstr, cb) \ - __ALTERNATIVE_CFG_CB(oldinstr, ARM64_CB_PATCH, 1, cb) +#define ALTERNATIVE_CB(oldinstr, feature, cb) \ + __ALTERNATIVE_CFG_CB(oldinstr, (1 << ARM64_CB_SHIFT) | (feature), 1, cb) #else #include <asm/assembler.h> @@ -82,7 +94,7 @@ .macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len .word \orig_offset - . .word \alt_offset - . - .hword \feature + .hword (\feature) .byte \orig_len .byte \alt_len .endm @@ -141,10 +153,10 @@ 661: .endm -.macro alternative_cb cb +.macro alternative_cb cap, cb .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" - altinstruction_entry 661f, \cb, ARM64_CB_PATCH, 662f-661f, 0 + altinstruction_entry 661f, \cb, (1 << ARM64_CB_SHIFT) | \cap, 662f-661f, 0 .popsection 661: .endm @@ -207,4 +219,46 @@ alternative_endif #define ALTERNATIVE(oldinstr, newinstr, ...) \ _ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1) +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +static __always_inline bool +alternative_has_feature_likely(unsigned long feature) +{ + compiletime_assert(feature < ARM64_NCAPS, + "feature must be < ARM64_NCAPS"); + + asm_volatile_goto( + ALTERNATIVE_CB("b %l[l_no]", %[feature], alt_cb_patch_nops) + : + : [feature] "i" (feature) + : + : l_no); + + return true; +l_no: + return false; +} + +static __always_inline bool +alternative_has_feature_unlikely(unsigned long feature) +{ + compiletime_assert(feature < ARM64_NCAPS, + "feature must be < ARM64_NCAPS"); + + asm_volatile_goto( + ALTERNATIVE("nop", "b %l[l_yes]", %[feature]) + : + : [feature] "i" (feature) + : + : l_yes); + + return false; +l_yes: + return true; +} + +#endif /* __ASSEMBLY__ */ + #endif /* __ASM_ALTERNATIVE_MACROS_H */ diff --git a/arch/arm64/include/asm/apple_m1_pmu.h b/arch/arm64/include/asm/apple_m1_pmu.h new file mode 100644 index 000000000000..99483b19b99f --- /dev/null +++ b/arch/arm64/include/asm/apple_m1_pmu.h @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef __ASM_APPLE_M1_PMU_h +#define __ASM_APPLE_M1_PMU_h + +#include <linux/bits.h> +#include <asm/sysreg.h> + +/* Counters */ +#define SYS_IMP_APL_PMC0_EL1 sys_reg(3, 2, 15, 0, 0) +#define SYS_IMP_APL_PMC1_EL1 sys_reg(3, 2, 15, 1, 0) +#define SYS_IMP_APL_PMC2_EL1 sys_reg(3, 2, 15, 2, 0) +#define SYS_IMP_APL_PMC3_EL1 sys_reg(3, 2, 15, 3, 0) +#define SYS_IMP_APL_PMC4_EL1 sys_reg(3, 2, 15, 4, 0) +#define SYS_IMP_APL_PMC5_EL1 sys_reg(3, 2, 15, 5, 0) +#define SYS_IMP_APL_PMC6_EL1 sys_reg(3, 2, 15, 6, 0) +#define SYS_IMP_APL_PMC7_EL1 sys_reg(3, 2, 15, 7, 0) +#define SYS_IMP_APL_PMC8_EL1 sys_reg(3, 2, 15, 9, 0) +#define SYS_IMP_APL_PMC9_EL1 sys_reg(3, 2, 15, 10, 0) + +/* Core PMC control register */ +#define SYS_IMP_APL_PMCR0_EL1 sys_reg(3, 1, 15, 0, 0) +#define PMCR0_CNT_ENABLE_0_7 GENMASK(7, 0) +#define PMCR0_IMODE GENMASK(10, 8) +#define PMCR0_IMODE_OFF 0 +#define PMCR0_IMODE_PMI 1 +#define PMCR0_IMODE_AIC 2 +#define PMCR0_IMODE_HALT 3 +#define PMCR0_IMODE_FIQ 4 +#define PMCR0_IACT BIT(11) +#define PMCR0_PMI_ENABLE_0_7 GENMASK(19, 12) +#define PMCR0_STOP_CNT_ON_PMI BIT(20) +#define PMCR0_CNT_GLOB_L2C_EVT BIT(21) +#define PMCR0_DEFER_PMI_TO_ERET BIT(22) +#define PMCR0_ALLOW_CNT_EN_EL0 BIT(30) +#define PMCR0_CNT_ENABLE_8_9 GENMASK(33, 32) +#define PMCR0_PMI_ENABLE_8_9 GENMASK(45, 44) + +#define SYS_IMP_APL_PMCR1_EL1 sys_reg(3, 1, 15, 1, 0) +#define PMCR1_COUNT_A64_EL0_0_7 GENMASK(15, 8) +#define PMCR1_COUNT_A64_EL1_0_7 GENMASK(23, 16) +#define PMCR1_COUNT_A64_EL0_8_9 GENMASK(41, 40) +#define PMCR1_COUNT_A64_EL1_8_9 GENMASK(49, 48) + +#define SYS_IMP_APL_PMCR2_EL1 sys_reg(3, 1, 15, 2, 0) +#define SYS_IMP_APL_PMCR3_EL1 sys_reg(3, 1, 15, 3, 0) +#define SYS_IMP_APL_PMCR4_EL1 sys_reg(3, 1, 15, 4, 0) + +#define SYS_IMP_APL_PMESR0_EL1 sys_reg(3, 1, 15, 5, 0) +#define PMESR0_EVT_CNT_2 GENMASK(7, 0) +#define PMESR0_EVT_CNT_3 GENMASK(15, 8) +#define PMESR0_EVT_CNT_4 GENMASK(23, 16) +#define PMESR0_EVT_CNT_5 GENMASK(31, 24) + +#define SYS_IMP_APL_PMESR1_EL1 sys_reg(3, 1, 15, 6, 0) +#define PMESR1_EVT_CNT_6 GENMASK(7, 0) +#define PMESR1_EVT_CNT_7 GENMASK(15, 8) +#define PMESR1_EVT_CNT_8 GENMASK(23, 16) +#define PMESR1_EVT_CNT_9 GENMASK(31, 24) + +#define SYS_IMP_APL_PMSR_EL1 sys_reg(3, 1, 15, 13, 0) +#define PMSR_OVERFLOW GENMASK(9, 0) + +#endif /* __ASM_APPLE_M1_PMU_h */ diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 4ad22c3135db..48d4473e8eee 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -26,12 +26,6 @@ * sets the GP register's most significant bits to 0 with an explicit cast. */ -static inline void gic_write_eoir(u32 irq) -{ - write_sysreg_s(irq, SYS_ICC_EOIR1_EL1); - isb(); -} - static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); @@ -53,17 +47,36 @@ static inline u64 gic_read_iar_common(void) * The gicv3 of ThunderX requires a modified version for reading the * IAR status to ensure data synchronization (access to icc_iar1_el1 * is not sync'ed before and after). + * + * Erratum 38545 + * + * When a IAR register read races with a GIC interrupt RELEASE event, + * GIC-CPU interface could wrongly return a valid INTID to the CPU + * for an interrupt that is already released(non activated) instead of 0x3ff. + * + * To workaround this, return a valid interrupt ID only if there is a change + * in the active priority list after the IAR read. + * + * Common function used for both the workarounds since, + * 1. On Thunderx 88xx 1.x both erratas are applicable. + * 2. Having extra nops doesn't add any side effects for Silicons where + * erratum 23154 is not applicable. */ static inline u64 gic_read_iar_cavium_thunderx(void) { - u64 irqstat; + u64 irqstat, apr; + apr = read_sysreg_s(SYS_ICC_AP1R0_EL1); nops(8); irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1); nops(4); mb(); - return irqstat; + /* Max priority groups implemented is only 32 */ + if (likely(apr != read_sysreg_s(SYS_ICC_AP1R0_EL1))) + return irqstat; + + return 0x3ff; } static inline void gic_write_ctlr(u32 val) diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h index 09e43272ccb0..109e2a4454be 100644 --- a/arch/arm64/include/asm/archrandom.h +++ b/arch/arm64/include/asm/archrandom.h @@ -2,8 +2,6 @@ #ifndef _ASM_ARCHRANDOM_H #define _ASM_ARCHRANDOM_H -#ifdef CONFIG_ARCH_RANDOM - #include <linux/arm-smccc.h> #include <linux/bug.h> #include <linux/kernel.h> @@ -42,19 +40,41 @@ static inline bool __arm64_rndr(unsigned long *v) return ok; } -static inline bool __must_check arch_get_random_long(unsigned long *v) +static inline bool __arm64_rndrrs(unsigned long *v) { - return false; + bool ok; + + /* + * Reads of RNDRRS set PSTATE.NZCV to 0b0000 on success, + * and set PSTATE.NZCV to 0b0100 otherwise. + */ + asm volatile( + __mrs_s("%0", SYS_RNDRRS_EL0) "\n" + " cset %w1, ne\n" + : "=r" (*v), "=r" (ok) + : + : "cc"); + + return ok; } -static inline bool __must_check arch_get_random_int(unsigned int *v) +static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) { - return false; + /* + * Only support the generic interface after we have detected + * the system wide capability, avoiding complexity with the + * cpufeature code and with potential scheduling between CPUs + * with and without the feature. + */ + if (max_longs && cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndr(v)) + return 1; + return 0; } -static inline bool __must_check arch_get_random_seed_long(unsigned long *v) +static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) { - struct arm_smccc_res res; + if (!max_longs) + return 0; /* * We prefer the SMCCC call, since its semantics (return actual @@ -63,83 +83,78 @@ static inline bool __must_check arch_get_random_seed_long(unsigned long *v) * (the output of a pseudo RNG freshly seeded by a TRNG). */ if (smccc_trng_available) { - arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 64, &res); + struct arm_smccc_res res; + + max_longs = min_t(size_t, 3, max_longs); + arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, max_longs * 64, &res); if ((int)res.a0 >= 0) { - *v = res.a3; - return true; + switch (max_longs) { + case 3: + *v++ = res.a1; + fallthrough; + case 2: + *v++ = res.a2; + fallthrough; + case 1: + *v++ = res.a3; + break; + } + return max_longs; } } /* - * Only support the generic interface after we have detected - * the system wide capability, avoiding complexity with the - * cpufeature code and with potential scheduling between CPUs - * with and without the feature. + * RNDRRS is not backed by an entropy source but by a DRBG that is + * reseeded after each invocation. This is not a 100% fit but good + * enough to implement this API if no other entropy source exists. */ - if (cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndr(v)) - return true; - - return false; -} - -static inline bool __must_check arch_get_random_seed_int(unsigned int *v) -{ - struct arm_smccc_res res; - unsigned long val; - - if (smccc_trng_available) { - arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 32, &res); - if ((int)res.a0 >= 0) { - *v = res.a3 & GENMASK(31, 0); - return true; - } - } - - if (cpus_have_const_cap(ARM64_HAS_RNG)) { - if (__arm64_rndr(&val)) { - *v = val; - return true; - } - } + if (cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndrrs(v)) + return 1; - return false; + return 0; } static inline bool __init __early_cpu_has_rndr(void) { /* Open code as we run prior to the first call to cpufeature. */ unsigned long ftr = read_sysreg_s(SYS_ID_AA64ISAR0_EL1); - return (ftr >> ID_AA64ISAR0_RNDR_SHIFT) & 0xf; + return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf; } -static inline bool __init __must_check -arch_get_random_seed_long_early(unsigned long *v) +static inline size_t __init __must_check +arch_get_random_seed_longs_early(unsigned long *v, size_t max_longs) { WARN_ON(system_state != SYSTEM_BOOTING); + if (!max_longs) + return 0; + if (smccc_trng_available) { struct arm_smccc_res res; - arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, 64, &res); + max_longs = min_t(size_t, 3, max_longs); + arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, max_longs * 64, &res); if ((int)res.a0 >= 0) { - *v = res.a3; - return true; + switch (max_longs) { + case 3: + *v++ = res.a1; + fallthrough; + case 2: + *v++ = res.a2; + fallthrough; + case 1: + *v++ = res.a3; + break; + } + return max_longs; } } if (__early_cpu_has_rndr() && __arm64_rndr(v)) - return true; + return 1; - return false; -} -#define arch_get_random_seed_long_early arch_get_random_seed_long_early - -#else /* !CONFIG_ARCH_RANDOM */ - -static inline bool __init smccc_probe_trng(void) -{ - return false; + return 0; } +#define arch_get_random_seed_longs_early arch_get_random_seed_longs_early -#endif /* CONFIG_ARCH_RANDOM */ #endif /* _ASM_ARCHRANDOM_H */ diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h index 03f52f84a4f3..c762038ba400 100644 --- a/arch/arm64/include/asm/asm-bug.h +++ b/arch/arm64/include/asm/asm-bug.h @@ -14,7 +14,7 @@ 14472: .string file; \ .popsection; \ \ - .long 14472b - 14470b; \ + .long 14472b - .; \ .short line; #else #define _BUGVERBOSE_LOCATION(file, line) @@ -25,7 +25,7 @@ #define __BUG_ENTRY(flags) \ .pushsection __bug_table,"aw"; \ .align 2; \ - 14470: .long 14471f - 14470b; \ + 14470: .long 14471f - .; \ _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ .short flags; \ .popsection; \ diff --git a/arch/arm64/include/asm/asm-extable.h b/arch/arm64/include/asm/asm-extable.h index c39f2437e08e..980d1dd8e1a3 100644 --- a/arch/arm64/include/asm/asm-extable.h +++ b/arch/arm64/include/asm/asm-extable.h @@ -2,12 +2,27 @@ #ifndef __ASM_ASM_EXTABLE_H #define __ASM_ASM_EXTABLE_H +#include <linux/bits.h> +#include <asm/gpr-num.h> + #define EX_TYPE_NONE 0 -#define EX_TYPE_FIXUP 1 -#define EX_TYPE_BPF 2 -#define EX_TYPE_UACCESS_ERR_ZERO 3 +#define EX_TYPE_BPF 1 +#define EX_TYPE_UACCESS_ERR_ZERO 2 +#define EX_TYPE_KACCESS_ERR_ZERO 3 #define EX_TYPE_LOAD_UNALIGNED_ZEROPAD 4 +/* Data fields for EX_TYPE_UACCESS_ERR_ZERO */ +#define EX_DATA_REG_ERR_SHIFT 0 +#define EX_DATA_REG_ERR GENMASK(4, 0) +#define EX_DATA_REG_ZERO_SHIFT 5 +#define EX_DATA_REG_ZERO GENMASK(9, 5) + +/* Data fields for EX_TYPE_LOAD_UNALIGNED_ZEROPAD */ +#define EX_DATA_REG_DATA_SHIFT 0 +#define EX_DATA_REG_DATA GENMASK(4, 0) +#define EX_DATA_REG_ADDR_SHIFT 5 +#define EX_DATA_REG_ADDR GENMASK(9, 5) + #ifdef __ASSEMBLY__ #define __ASM_EXTABLE_RAW(insn, fixup, type, data) \ @@ -19,31 +34,45 @@ .short (data); \ .popsection; +#define EX_DATA_REG(reg, gpr) \ + (.L__gpr_num_##gpr << EX_DATA_REG_##reg##_SHIFT) + +#define _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero) \ + __ASM_EXTABLE_RAW(insn, fixup, \ + EX_TYPE_UACCESS_ERR_ZERO, \ + ( \ + EX_DATA_REG(ERR, err) | \ + EX_DATA_REG(ZERO, zero) \ + )) + +#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, wzr) + +#define _ASM_EXTABLE_UACCESS(insn, fixup) \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, wzr, wzr) + /* - * Create an exception table entry for `insn`, which will branch to `fixup` + * Create an exception table entry for uaccess `insn`, which will branch to `fixup` * when an unhandled fault is taken. */ - .macro _asm_extable, insn, fixup - __ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0) + .macro _asm_extable_uaccess, insn, fixup + _ASM_EXTABLE_UACCESS(\insn, \fixup) .endm /* * Create an exception table entry for `insn` if `fixup` is provided. Otherwise * do nothing. */ - .macro _cond_extable, insn, fixup - .ifnc \fixup, - _asm_extable \insn, \fixup + .macro _cond_uaccess_extable, insn, fixup + .ifnc \fixup, + _asm_extable_uaccess \insn, \fixup .endif .endm #else /* __ASSEMBLY__ */ -#include <linux/bits.h> #include <linux/stringify.h> -#include <asm/gpr-num.h> - #define __ASM_EXTABLE_RAW(insn, fixup, type, data) \ ".pushsection __ex_table, \"a\"\n" \ ".align 2\n" \ @@ -53,14 +82,6 @@ ".short (" data ")\n" \ ".popsection\n" -#define _ASM_EXTABLE(insn, fixup) \ - __ASM_EXTABLE_RAW(#insn, #fixup, __stringify(EX_TYPE_FIXUP), "0") - -#define EX_DATA_REG_ERR_SHIFT 0 -#define EX_DATA_REG_ERR GENMASK(4, 0) -#define EX_DATA_REG_ZERO_SHIFT 5 -#define EX_DATA_REG_ZERO GENMASK(9, 5) - #define EX_DATA_REG(reg, gpr) \ "((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")" @@ -73,13 +94,23 @@ EX_DATA_REG(ZERO, zero) \ ")") +#define _ASM_EXTABLE_KACCESS_ERR_ZERO(insn, fixup, err, zero) \ + __DEFINE_ASM_GPR_NUMS \ + __ASM_EXTABLE_RAW(#insn, #fixup, \ + __stringify(EX_TYPE_KACCESS_ERR_ZERO), \ + "(" \ + EX_DATA_REG(ERR, err) " | " \ + EX_DATA_REG(ZERO, zero) \ + ")") + #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \ _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, wzr) -#define EX_DATA_REG_DATA_SHIFT 0 -#define EX_DATA_REG_DATA GENMASK(4, 0) -#define EX_DATA_REG_ADDR_SHIFT 5 -#define EX_DATA_REG_ADDR GENMASK(9, 5) +#define _ASM_EXTABLE_UACCESS(insn, fixup) \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, wzr, wzr) + +#define _ASM_EXTABLE_KACCESS_ERR(insn, fixup, err) \ + _ASM_EXTABLE_KACCESS_ERR_ZERO(insn, fixup, err, wzr) #define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr) \ __DEFINE_ASM_GPR_NUMS \ diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index 0557af834e03..75b211c98dea 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -61,7 +61,7 @@ alternative_else_nop_endif #define USER(l, x...) \ 9999: x; \ - _asm_extable 9999b, l + _asm_extable_uaccess 9999b, l /* * Generate the assembly for LDTR/STTR with exception table entries. @@ -73,8 +73,8 @@ alternative_else_nop_endif 8889: ldtr \reg2, [\addr, #8]; add \addr, \addr, \post_inc; - _asm_extable 8888b,\l; - _asm_extable 8889b,\l; + _asm_extable_uaccess 8888b, \l; + _asm_extable_uaccess 8889b, \l; .endm .macro user_stp l, reg1, reg2, addr, post_inc @@ -82,14 +82,14 @@ alternative_else_nop_endif 8889: sttr \reg2, [\addr, #8]; add \addr, \addr, \post_inc; - _asm_extable 8888b,\l; - _asm_extable 8889b,\l; + _asm_extable_uaccess 8888b,\l; + _asm_extable_uaccess 8889b,\l; .endm .macro user_ldst l, inst, reg, addr, post_inc 8888: \inst \reg, [\addr]; add \addr, \addr, \post_inc; - _asm_extable 8888b,\l; + _asm_extable_uaccess 8888b, \l; .endm #endif diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h index f1bba5fc61c4..13ecc79854ee 100644 --- a/arch/arm64/include/asm/asm_pointer_auth.h +++ b/arch/arm64/include/asm/asm_pointer_auth.h @@ -59,7 +59,10 @@ alternative_else_nop_endif .macro __ptrauth_keys_init_cpu tsk, tmp1, tmp2, tmp3 mrs \tmp1, id_aa64isar1_el1 - ubfx \tmp1, \tmp1, #ID_AA64ISAR1_APA_SHIFT, #8 + ubfx \tmp1, \tmp1, #ID_AA64ISAR1_EL1_APA_SHIFT, #8 + mrs_s \tmp2, SYS_ID_AA64ISAR2_EL1 + ubfx \tmp2, \tmp2, #ID_AA64ISAR2_EL1_APA3_SHIFT, #4 + orr \tmp1, \tmp1, \tmp2 cbz \tmp1, .Lno_addr_auth\@ mov_q \tmp1, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \ SCTLR_ELx_ENDA | SCTLR_ELx_ENDB) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index e8bd0af0141c..e5957a53be39 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -109,6 +109,13 @@ .endm /* + * Clear Branch History instruction + */ + .macro clearbhb + hint #22 + .endm + +/* * Speculation barrier */ .macro sb @@ -286,7 +293,7 @@ alternative_endif alternative_if_not ARM64_KVM_PROTECTED_MODE ASM_BUG() alternative_else_nop_endif -alternative_cb kvm_compute_final_ctr_el0 +alternative_cb ARM64_ALWAYS_SYSTEM, kvm_compute_final_ctr_el0 movz \reg, #0 movk \reg, #0, lsl #16 movk \reg, #0, lsl #32 @@ -353,6 +360,20 @@ alternative_cb_end .endm /* + * idmap_get_t0sz - get the T0SZ value needed to cover the ID map + * + * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the + * entire ID map region can be mapped. As T0SZ == (64 - #bits used), + * this number conveniently equals the number of leading zeroes in + * the physical address of _end. + */ + .macro idmap_get_t0sz, reg + adrp \reg, _end + orr \reg, \reg, #(1 << VA_BITS_MIN) - 1 + clz \reg, \reg + .endm + +/* * tcr_compute_pa_size - set TCR.(I)PS to the highest supported * ID_AA64MMFR0_EL1.PARange value * @@ -363,8 +384,8 @@ alternative_cb_end .macro tcr_compute_pa_size, tcr, pos, tmp0, tmp1 mrs \tmp0, ID_AA64MMFR0_EL1 // Narrow PARange to fit the PS field in TCR_ELx - ubfx \tmp0, \tmp0, #ID_AA64MMFR0_PARANGE_SHIFT, #3 - mov \tmp1, #ID_AA64MMFR0_PARANGE_MAX + ubfx \tmp0, \tmp0, #ID_AA64MMFR0_EL1_PARANGE_SHIFT, #3 + mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_MAX cmp \tmp0, \tmp1 csel \tmp0, \tmp1, \tmp0, hi bfi \tcr, \tmp0, \pos, #3 @@ -416,7 +437,7 @@ alternative_endif b.lo .Ldcache_op\@ dsb \domain - _cond_extable .Ldcache_op\@, \fixup + _cond_uaccess_extable .Ldcache_op\@, \fixup .endm /* @@ -455,7 +476,19 @@ alternative_endif dsb ish isb - _cond_extable .Licache_op\@, \fixup + _cond_uaccess_extable .Licache_op\@, \fixup + .endm + +/* + * load_ttbr1 - install @pgtbl as a TTBR1 page table + * pgtbl preserved + * tmp1/tmp2 clobbered, either may overlap with pgtbl + */ + .macro load_ttbr1, pgtbl, tmp1, tmp2 + phys_to_ttbr \tmp1, \pgtbl + offset_ttbr1 \tmp1, \tmp2 + msr ttbr1_el1, \tmp1 + isb .endm /* @@ -471,10 +504,7 @@ alternative_endif isb tlbi vmalle1 dsb nsh - phys_to_ttbr \tmp, \page_table - offset_ttbr1 \tmp, \tmp2 - msr ttbr1_el1, \tmp - isb + load_ttbr1 \page_table, \tmp, \tmp2 .endm /* @@ -482,7 +512,7 @@ alternative_endif */ .macro reset_pmuserenr_el0, tmpreg mrs \tmpreg, id_aa64dfr0_el1 - sbfx \tmpreg, \tmpreg, #ID_AA64DFR0_PMUVER_SHIFT, #4 + sbfx \tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4 cmp \tmpreg, #1 // Skip if no PMU present b.lt 9000f msr pmuserenr_el0, xzr // Disable PMU access from EL0 @@ -494,7 +524,7 @@ alternative_endif */ .macro reset_amuserenr_el0, tmpreg mrs \tmpreg, id_aa64pfr0_el1 // Check ID_AA64PFR0_EL1 - ubfx \tmpreg, \tmpreg, #ID_AA64PFR0_AMU_SHIFT, #4 + ubfx \tmpreg, \tmpreg, #ID_AA64PFR0_EL1_AMU_SHIFT, #4 cbz \tmpreg, .Lskip_\@ // Skip if no AMU present msr_s SYS_AMUSERENR_EL0, xzr // Disable AMU access from EL0 .Lskip_\@: @@ -535,11 +565,6 @@ alternative_endif #define EXPORT_SYMBOL_NOKASAN(name) EXPORT_SYMBOL(name) #endif -#ifdef CONFIG_KASAN_HW_TAGS -#define EXPORT_SYMBOL_NOHWKASAN(name) -#else -#define EXPORT_SYMBOL_NOHWKASAN(name) EXPORT_SYMBOL_NOKASAN(name) -#endif /* * Emit a 64-bit absolute little endian symbol reference in a way that * ensures that it will be resolved at build time, even when building a @@ -587,7 +612,7 @@ alternative_endif .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) + and \tmp, \tmp, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT) cbnz \tmp, .Lskipoffs_\@ orr \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET .Lskipoffs_\@ : @@ -850,4 +875,50 @@ alternative_endif #endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */ + .macro __mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_loop_iter + mov \tmp, #32 // Patched to correct the immediate +alternative_cb_end +.Lspectre_bhb_loop\@: + b . + 4 + subs \tmp, \tmp, #1 + b.ne .Lspectre_bhb_loop\@ + sb +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_loop_mitigation_enable + b .L_spectre_bhb_loop_done\@ // Patched to NOP +alternative_cb_end + __mitigate_spectre_bhb_loop \tmp +.L_spectre_bhb_loop_done\@: +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + /* Save/restores x0-x3 to the stack */ + .macro __mitigate_spectre_bhb_fw +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + stp x0, x1, [sp, #-16]! + stp x2, x3, [sp, #-16]! + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_3 +alternative_cb ARM64_ALWAYS_SYSTEM, smccc_patch_fw_mitigation_conduit + nop // Patched to SMC/HVC #0 +alternative_cb_end + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_clear_insn +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_clearbhb + /* Patched to NOP when not supported */ + clearbhb + isb +alternative_cb_end +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index fe0db8d416fb..0890e4f568fb 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -12,19 +12,6 @@ #include <linux/stringify.h> -#ifdef CONFIG_ARM64_LSE_ATOMICS -#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 @@ -36,38 +23,36 @@ asm_ops "\n" \ */ #define ATOMIC_OP(op, asm_op, constraint) \ -static inline void \ +static __always_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\n") \ + " cbnz %w1, 1b\n" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i)); \ } #define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ -static inline int \ +static __always_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) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -76,20 +61,19 @@ __ll_sc_atomic_##op##_return##name(int i, atomic_t *v) \ } #define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \ -static inline int \ +static __always_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) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -135,38 +119,36 @@ ATOMIC_OPS(andnot, bic, ) #undef ATOMIC_OP #define ATOMIC64_OP(op, asm_op, constraint) \ -static inline void \ +static __always_inline void \ __ll_sc_atomic64_##op(s64 i, atomic64_t *v) \ { \ 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) \ : __stringify(constraint) "r" (i)); \ } #define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ -static inline long \ +static __always_inline long \ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v) \ { \ 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) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -175,20 +157,19 @@ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v) \ } #define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ -static inline long \ +static __always_inline long \ __ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ { \ 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) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -233,14 +214,13 @@ ATOMIC64_OPS(andnot, bic, ) #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP -static inline s64 +static __always_inline s64 __ll_sc_atomic64_dec_if_positive(atomic64_t *v) { 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" @@ -248,7 +228,7 @@ __ll_sc_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"); @@ -257,7 +237,7 @@ __ll_sc_atomic64_dec_if_positive(atomic64_t *v) } #define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint) \ -static inline u##sz \ +static __always_inline u##sz \ __ll_sc__cmpxchg_case_##name##sz(volatile void *ptr, \ unsigned long old, \ u##sz new) \ @@ -274,7 +254,6 @@ __ll_sc__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" \ @@ -282,7 +261,7 @@ __ll_sc__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] __stringify(constraint) "r" (old), [new] "r" (new) \ @@ -316,7 +295,7 @@ __CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory", L) #undef __CMPXCHG_CASE #define __CMPXCHG_DBL(name, mb, rel, cl) \ -static inline long \ +static __always_inline long \ __ll_sc__cmpxchg_double##name(unsigned long old1, \ unsigned long old2, \ unsigned long new1, \ @@ -326,7 +305,6 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \ 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" \ @@ -336,7 +314,7 @@ __ll_sc__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); \ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index d955ade5df7c..52075e93de6c 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -11,7 +11,8 @@ #define __ASM_ATOMIC_LSE_H #define ATOMIC_OP(op, asm_op) \ -static inline void __lse_atomic_##op(int i, atomic_t *v) \ +static __always_inline void \ +__lse_atomic_##op(int i, atomic_t *v) \ { \ asm volatile( \ __LSE_PREAMBLE \ @@ -25,7 +26,7 @@ ATOMIC_OP(or, stset) ATOMIC_OP(xor, steor) ATOMIC_OP(add, stadd) -static inline void __lse_atomic_sub(int i, atomic_t *v) +static __always_inline void __lse_atomic_sub(int i, atomic_t *v) { __lse_atomic_add(-i, v); } @@ -33,7 +34,8 @@ static inline void __lse_atomic_sub(int i, atomic_t *v) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...) \ -static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v) \ +static __always_inline int \ +__lse_atomic_fetch_##op##name(int i, atomic_t *v) \ { \ int old; \ \ @@ -63,7 +65,8 @@ ATOMIC_FETCH_OPS(add, ldadd) #undef ATOMIC_FETCH_OPS #define ATOMIC_FETCH_OP_SUB(name) \ -static inline int __lse_atomic_fetch_sub##name(int i, atomic_t *v) \ +static __always_inline int \ +__lse_atomic_fetch_sub##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_add##name(-i, v); \ } @@ -76,12 +79,14 @@ ATOMIC_FETCH_OP_SUB( ) #undef ATOMIC_FETCH_OP_SUB #define ATOMIC_OP_ADD_SUB_RETURN(name) \ -static inline int __lse_atomic_add_return##name(int i, atomic_t *v) \ +static __always_inline int \ +__lse_atomic_add_return##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_add##name(i, v) + i; \ } \ \ -static inline int __lse_atomic_sub_return##name(int i, atomic_t *v) \ +static __always_inline int \ +__lse_atomic_sub_return##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_sub(i, v) - i; \ } @@ -93,13 +98,14 @@ ATOMIC_OP_ADD_SUB_RETURN( ) #undef ATOMIC_OP_ADD_SUB_RETURN -static inline void __lse_atomic_and(int i, atomic_t *v) +static __always_inline void __lse_atomic_and(int i, atomic_t *v) { return __lse_atomic_andnot(~i, v); } #define ATOMIC_FETCH_OP_AND(name, mb, cl...) \ -static inline int __lse_atomic_fetch_and##name(int i, atomic_t *v) \ +static __always_inline int \ +__lse_atomic_fetch_and##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_andnot##name(~i, v); \ } @@ -112,7 +118,8 @@ ATOMIC_FETCH_OP_AND( , al, "memory") #undef ATOMIC_FETCH_OP_AND #define ATOMIC64_OP(op, asm_op) \ -static inline void __lse_atomic64_##op(s64 i, atomic64_t *v) \ +static __always_inline void \ +__lse_atomic64_##op(s64 i, atomic64_t *v) \ { \ asm volatile( \ __LSE_PREAMBLE \ @@ -126,7 +133,7 @@ ATOMIC64_OP(or, stset) ATOMIC64_OP(xor, steor) ATOMIC64_OP(add, stadd) -static inline void __lse_atomic64_sub(s64 i, atomic64_t *v) +static __always_inline void __lse_atomic64_sub(s64 i, atomic64_t *v) { __lse_atomic64_add(-i, v); } @@ -134,7 +141,8 @@ static inline void __lse_atomic64_sub(s64 i, atomic64_t *v) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...) \ -static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\ +static __always_inline long \ +__lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ { \ s64 old; \ \ @@ -164,7 +172,8 @@ ATOMIC64_FETCH_OPS(add, ldadd) #undef ATOMIC64_FETCH_OPS #define ATOMIC64_FETCH_OP_SUB(name) \ -static inline long __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v) \ +static __always_inline long \ +__lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_add##name(-i, v); \ } @@ -177,12 +186,14 @@ ATOMIC64_FETCH_OP_SUB( ) #undef ATOMIC64_FETCH_OP_SUB #define ATOMIC64_OP_ADD_SUB_RETURN(name) \ -static inline long __lse_atomic64_add_return##name(s64 i, atomic64_t *v)\ +static __always_inline long \ +__lse_atomic64_add_return##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_add##name(i, v) + i; \ } \ \ -static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v)\ +static __always_inline long \ +__lse_atomic64_sub_return##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_sub##name(i, v) - i; \ } @@ -194,13 +205,14 @@ ATOMIC64_OP_ADD_SUB_RETURN( ) #undef ATOMIC64_OP_ADD_SUB_RETURN -static inline void __lse_atomic64_and(s64 i, atomic64_t *v) +static __always_inline void __lse_atomic64_and(s64 i, atomic64_t *v) { return __lse_atomic64_andnot(~i, v); } #define ATOMIC64_FETCH_OP_AND(name, mb, cl...) \ -static inline long __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v) \ +static __always_inline long \ +__lse_atomic64_fetch_and##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_andnot##name(~i, v); \ } @@ -212,7 +224,7 @@ ATOMIC64_FETCH_OP_AND( , al, "memory") #undef ATOMIC64_FETCH_OP_AND -static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v) +static __always_inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v) { unsigned long tmp; @@ -249,7 +261,7 @@ __lse__cmpxchg_case_##name##sz(volatile void *ptr, \ " 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), \ + : [ret] "+r" (x0), [v] "+Q" (*(u##sz *)ptr), \ [tmp] "=&r" (tmp) \ : [old] "r" (x1), [new] "r" (x2) \ : cl); \ diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 62217be36217..2cfc4245d2e2 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -16,7 +16,11 @@ #define sev() asm volatile("sev" : : : "memory") #define wfe() asm volatile("wfe" : : : "memory") +#define wfet(val) asm volatile("msr s0_3_c1_c0_0, %0" \ + : : "r" (val) : "memory") #define wfi() asm volatile("wfi" : : : "memory") +#define wfit(val) asm volatile("msr s0_3_c1_c0_1, %0" \ + : : "r" (val) : "memory") #define isb() asm volatile("isb" : : : "memory") #define dmb(opt) asm volatile("dmb " #opt : : : "memory") @@ -46,13 +50,13 @@ #define pmr_sync() do {} while (0) #endif -#define mb() dsb(sy) -#define rmb() dsb(ld) -#define wmb() dsb(st) +#define __mb() dsb(sy) +#define __rmb() dsb(ld) +#define __wmb() dsb(st) -#define dma_mb() dmb(osh) -#define dma_rmb() dmb(oshld) -#define dma_wmb() dmb(oshst) +#define __dma_mb() dmb(osh) +#define __dma_rmb() dmb(oshld) +#define __dma_wmb() dmb(oshst) #define io_stop_wc() dgh() diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h index 81a3e519b07d..9b3c787132d2 100644 --- a/arch/arm64/include/asm/bitops.h +++ b/arch/arm64/include/asm/bitops.h @@ -18,7 +18,6 @@ #include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/fls64.h> -#include <asm-generic/bitops/find.h> #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/hweight.h> diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index ec7720dbe2c8..6e000113e508 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -17,6 +17,7 @@ * 0x401: for compile time BRK instruction * 0x800: kernel-mode BUG() and WARN() traps * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff) + * 0x8xxx: Control-Flow Integrity traps */ #define KPROBES_BRK_IMM 0x004 #define UPROBES_BRK_IMM 0x005 @@ -28,4 +29,9 @@ #define KASAN_BRK_IMM 0x900 #define KASAN_BRK_MASK 0x0ff +#define CFI_BRK_IMM_TARGET GENMASK(4, 0) +#define CFI_BRK_IMM_TYPE GENMASK(9, 5) +#define CFI_BRK_IMM_BASE 0x8000 +#define CFI_BRK_IMM_MASK (CFI_BRK_IMM_TARGET | CFI_BRK_IMM_TYPE) + #endif diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index a074459f8f2f..c0b178d1bb4f 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -5,33 +5,9 @@ #ifndef __ASM_CACHE_H #define __ASM_CACHE_H -#include <asm/cputype.h> - -#define CTR_L1IP_SHIFT 14 -#define CTR_L1IP_MASK 3 -#define CTR_DMINLINE_SHIFT 16 -#define CTR_IMINLINE_SHIFT 0 -#define CTR_IMINLINE_MASK 0xf -#define CTR_ERG_SHIFT 20 -#define CTR_CWG_SHIFT 24 -#define CTR_CWG_MASK 15 -#define CTR_IDC_SHIFT 28 -#define CTR_DIC_SHIFT 29 - -#define CTR_CACHE_MINLINE_MASK \ - (0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT) - -#define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) - -#define ICACHE_POLICY_VPIPT 0 -#define ICACHE_POLICY_RESERVED 1 -#define ICACHE_POLICY_VIPT 2 -#define ICACHE_POLICY_PIPT 3 - #define L1_CACHE_SHIFT (6) #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) - #define CLIDR_LOUU_SHIFT 27 #define CLIDR_LOC_SHIFT 24 #define CLIDR_LOUIS_SHIFT 21 @@ -49,15 +25,27 @@ */ #define ARCH_DMA_MINALIGN (128) +#ifndef __ASSEMBLY__ + +#include <linux/bitops.h> +#include <linux/kasan-enabled.h> + +#include <asm/cputype.h> +#include <asm/mte-def.h> +#include <asm/sysreg.h> + #ifdef CONFIG_KASAN_SW_TAGS #define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT) #elif defined(CONFIG_KASAN_HW_TAGS) -#define ARCH_SLAB_MINALIGN MTE_GRANULE_SIZE +static inline unsigned int arch_slab_minalign(void) +{ + return kasan_hw_tags_enabled() ? MTE_GRANULE_SIZE : + __alignof__(unsigned long long); +} +#define arch_slab_minalign() arch_slab_minalign() #endif -#ifndef __ASSEMBLY__ - -#include <linux/bitops.h> +#define CTR_L1IP(ctr) SYS_FIELD_GET(CTR_EL0, L1Ip, ctr) #define ICACHEF_ALIASING 0 #define ICACHEF_VPIPT 1 @@ -79,7 +67,7 @@ static __always_inline int icache_is_vpipt(void) static inline u32 cache_type_cwg(void) { - return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK; + return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype()); } #define __read_mostly __section(".data..read_mostly") @@ -113,12 +101,12 @@ static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void) { u32 ctr = read_cpuid_cachetype(); - if (!(ctr & BIT(CTR_IDC_SHIFT))) { + if (!(ctr & BIT(CTR_EL0_IDC_SHIFT))) { u64 clidr = read_sysreg(clidr_el1); if (CLIDR_LOC(clidr) == 0 || (CLIDR_LOUIS(clidr) == 0 && CLIDR_LOUU(clidr) == 0)) - ctr |= BIT(CTR_IDC_SHIFT); + ctr |= BIT(CTR_EL0_IDC_SHIFT); } return ctr; diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 5a228e203ef9..37185e978aeb 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -105,13 +105,6 @@ static inline void flush_icache_range(unsigned long start, unsigned long end) #define flush_icache_range flush_icache_range /* - * Cache maintenance functions used by the DMA API. No to be used directly. - */ -extern void __dma_map_area(const void *, size_t, int); -extern void __dma_unmap_area(const void *, size_t, int); -extern void __dma_flush_area(const void *, size_t); - -/* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user * space" model to handle this. diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index f9bef42c1411..497acf134d99 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -243,7 +243,7 @@ static inline void __cmpwait_case_##sz(volatile void *ptr, \ " cbnz %" #w "[tmp], 1f\n" \ " wfe\n" \ "1:" \ - : [tmp] "=&r" (tmp), [v] "+Q" (*(unsigned long *)ptr) \ + : [tmp] "=&r" (tmp), [v] "+Q" (*(u##sz *)ptr) \ : [val] "r" (val)); \ } diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index eaa6ca062d89..9f362274a4f7 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -8,6 +8,15 @@ #define compat_mode_t compat_mode_t typedef u16 compat_mode_t; +#define __compat_uid_t __compat_uid_t +typedef u16 __compat_uid_t; +typedef u16 __compat_gid_t; + +#define compat_ipc_pid_t compat_ipc_pid_t +typedef u16 compat_ipc_pid_t; + +#define compat_statfs compat_statfs + #include <asm-generic/compat.h> #ifdef CONFIG_COMPAT @@ -19,21 +28,15 @@ typedef u16 compat_mode_t; #include <linux/sched.h> #include <linux/sched/task_stack.h> -#define COMPAT_USER_HZ 100 #ifdef __AARCH64EB__ #define COMPAT_UTS_MACHINE "armv8b\0\0" #else #define COMPAT_UTS_MACHINE "armv8l\0\0" #endif -typedef u16 __compat_uid_t; -typedef u16 __compat_gid_t; typedef u16 __compat_uid16_t; typedef u16 __compat_gid16_t; -typedef u32 compat_dev_t; typedef s32 compat_nlink_t; -typedef u16 compat_ipc_pid_t; -typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { #ifdef __AARCH64EB__ @@ -65,26 +68,6 @@ struct compat_stat { compat_ulong_t __unused4[2]; }; -struct compat_flock { - short l_type; - short l_whence; - compat_off_t l_start; - compat_off_t l_len; - compat_pid_t l_pid; -}; - -#define F_GETLK64 12 /* using 'struct flock64' */ -#define F_SETLK64 13 -#define F_SETLKW64 14 - -struct compat_flock64 { - short l_type; - short l_whence; - compat_loff_t l_start; - compat_loff_t l_len; - compat_pid_t l_pid; -}; - struct compat_statfs { int f_type; int f_bsize; @@ -107,64 +90,6 @@ struct compat_statfs { #define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) #define COMPAT_MINSIGSTKSZ 2048 -struct compat_ipc64_perm { - compat_key_t key; - __compat_uid32_t uid; - __compat_gid32_t gid; - __compat_uid32_t cuid; - __compat_gid32_t cgid; - unsigned short mode; - unsigned short __pad1; - unsigned short seq; - unsigned short __pad2; - compat_ulong_t unused1; - compat_ulong_t unused2; -}; - -struct compat_semid64_ds { - struct compat_ipc64_perm sem_perm; - compat_ulong_t sem_otime; - compat_ulong_t sem_otime_high; - compat_ulong_t sem_ctime; - compat_ulong_t sem_ctime_high; - compat_ulong_t sem_nsems; - compat_ulong_t __unused3; - compat_ulong_t __unused4; -}; - -struct compat_msqid64_ds { - struct compat_ipc64_perm msg_perm; - compat_ulong_t msg_stime; - compat_ulong_t msg_stime_high; - compat_ulong_t msg_rtime; - compat_ulong_t msg_rtime_high; - compat_ulong_t msg_ctime; - compat_ulong_t msg_ctime_high; - compat_ulong_t msg_cbytes; - compat_ulong_t msg_qnum; - compat_ulong_t msg_qbytes; - compat_pid_t msg_lspid; - compat_pid_t msg_lrpid; - compat_ulong_t __unused4; - compat_ulong_t __unused5; -}; - -struct compat_shmid64_ds { - struct compat_ipc64_perm shm_perm; - compat_size_t shm_segsz; - compat_ulong_t shm_atime; - compat_ulong_t shm_atime_high; - compat_ulong_t shm_dtime; - compat_ulong_t shm_dtime_high; - compat_ulong_t shm_ctime; - compat_ulong_t shm_ctime_high; - compat_pid_t shm_cpid; - compat_pid_t shm_lpid; - compat_ulong_t shm_nattch; - compat_ulong_t __unused4; - compat_ulong_t __unused5; -}; - static inline int is_compat_task(void) { return test_thread_flag(TIF_32BIT); diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h index dc3ea4080e2e..6fb2e6bcc392 100644 --- a/arch/arm64/include/asm/compiler.h +++ b/arch/arm64/include/asm/compiler.h @@ -23,20 +23,4 @@ #define __builtin_return_address(val) \ (void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val))) -#ifdef CONFIG_CFI_CLANG -/* - * With CONFIG_CFI_CLANG, the compiler replaces function address - * references with the address of the function's CFI jump table - * entry. The function_nocfi macro always returns the address of the - * actual function instead. - */ -#define function_nocfi(x) ({ \ - void *addr; \ - asm("adrp %0, " __stringify(x) "\n\t" \ - "add %0, %0, :lo12:" __stringify(x) \ - : "=r" (addr)); \ - addr; \ -}) -#endif - #endif /* __ASM_COMPILER_H */ diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index a58e366f0b07..fd7a92219eea 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -46,6 +46,7 @@ struct cpuinfo_arm64 { u64 reg_midr; u64 reg_revidr; u64 reg_gmid; + u64 reg_smidr; u64 reg_id_aa64dfr0; u64 reg_id_aa64dfr1; @@ -58,11 +59,15 @@ struct cpuinfo_arm64 { u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; u64 reg_id_aa64zfr0; + u64 reg_id_aa64smfr0; struct cpuinfo_32bit aarch32; /* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */ u64 reg_zcr; + + /* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */ + u64 reg_smcr; }; DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data); diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h index e95c4df83911..a444c8915e88 100644 --- a/arch/arm64/include/asm/cpu_ops.h +++ b/arch/arm64/include/asm/cpu_ops.h @@ -31,11 +31,6 @@ * @cpu_die: Makes a cpu leave the kernel. Must not fail. Called from the * cpu being killed. * @cpu_kill: Ensures a cpu has left the kernel. Called from another cpu. - * @cpu_init_idle: Reads any data necessary to initialize CPU idle states for - * a proposed logical id. - * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing - * to wrong parameters or error conditions. Called from the - * CPU being suspended. Must be called with IRQs disabled. */ struct cpu_operations { const char *name; @@ -49,10 +44,6 @@ struct cpu_operations { void (*cpu_die)(unsigned int cpu); int (*cpu_kill)(unsigned int cpu); #endif -#ifdef CONFIG_CPU_IDLE - int (*cpu_init_idle)(unsigned int); - int (*cpu_suspend)(unsigned long); -#endif }; int __init init_cpu_ops(int cpu); diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index ef6be92b1921..f73f11b55042 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -6,12 +6,13 @@ #ifndef __ASM_CPUFEATURE_H #define __ASM_CPUFEATURE_H +#include <asm/alternative-macros.h> #include <asm/cpucaps.h> #include <asm/cputype.h> #include <asm/hwcap.h> #include <asm/sysreg.h> -#define MAX_CPU_FEATURES 64 +#define MAX_CPU_FEATURES 128 #define cpu_feature(x) KERNEL_HWCAP_ ## x #ifndef __ASSEMBLY__ @@ -356,6 +357,7 @@ struct arm64_cpu_capabilities { struct { /* Feature register checking */ u32 sys_reg; u8 field_pos; + u8 field_width; u8 min_field_value; u8 hwcap_type; bool sign; @@ -418,12 +420,8 @@ static __always_inline bool is_hyp_code(void) } 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; -/* ARM64 CAPS + alternative_cb */ -#define ARM64_NPATCHABLE (ARM64_NCAPS + 1) -extern DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); +extern DECLARE_BITMAP(boot_capabilities, ARM64_NCAPS); #define for_each_available_cap(cap) \ for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS) @@ -439,7 +437,7 @@ unsigned long cpu_get_elf_hwcap2(void); static __always_inline bool system_capabilities_finalized(void) { - return static_branch_likely(&arm64_const_caps_ready); + return alternative_has_feature_likely(ARM64_ALWAYS_SYSTEM); } /* @@ -447,11 +445,11 @@ static __always_inline bool system_capabilities_finalized(void) * * Before the capability is detected, this returns false. */ -static inline bool cpus_have_cap(unsigned int num) +static __always_inline bool cpus_have_cap(unsigned int num) { if (num >= ARM64_NCAPS) return false; - return test_bit(num, cpu_hwcaps); + return arch_test_bit(num, cpu_hwcaps); } /* @@ -466,7 +464,7 @@ static __always_inline bool __cpus_have_const_cap(int num) { if (num >= ARM64_NCAPS) return false; - return static_branch_unlikely(&cpu_hwcap_keys[num]); + return alternative_has_feature_unlikely(num); } /* @@ -552,7 +550,7 @@ cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap) u64 mask = GENMASK_ULL(field + 3, field); /* Treat IMPLEMENTATION DEFINED functionality as unimplemented */ - if (val == ID_AA64DFR0_PMUVER_IMP_DEF) + if (val == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) val = 0; if (val > cap) { @@ -576,6 +574,8 @@ static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg) static inline int __attribute_const__ cpuid_feature_extract_field_width(u64 features, int field, int width, bool sign) { + if (WARN_ON_ONCE(!width)) + width = 4; return (sign) ? cpuid_feature_extract_signed_field_width(features, field, width) : cpuid_feature_extract_unsigned_field_width(features, field, width); @@ -594,36 +594,43 @@ static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val) static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0) { - return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_BIGENDEL_SHIFT) == 0x1 || - cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_BIGENDEL0_SHIFT) == 0x1; + return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT) == 0x1 || + cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT) == 0x1; } static inline bool id_aa64pfr0_32bit_el1(u64 pfr0) { - u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SHIFT); + u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL1_SHIFT); - return val == ID_AA64PFR0_ELx_32BIT_64BIT; + return val == ID_AA64PFR0_EL1_ELx_32BIT_64BIT; } static inline bool id_aa64pfr0_32bit_el0(u64 pfr0) { - u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL0_SHIFT); + u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL0_SHIFT); - return val == ID_AA64PFR0_ELx_32BIT_64BIT; + return val == ID_AA64PFR0_EL1_ELx_32BIT_64BIT; } static inline bool id_aa64pfr0_sve(u64 pfr0) { - u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_SVE_SHIFT); + u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SVE_SHIFT); + + return val > 0; +} + +static inline bool id_aa64pfr1_sme(u64 pfr1) +{ + u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_SME_SHIFT); return val > 0; } static inline bool id_aa64pfr1_mte(u64 pfr1) { - u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT); + u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT); - return val >= ID_AA64PFR1_MTE; + return val >= ID_AA64PFR1_EL1_MTE_MTE2; } void __init setup_cpu_features(void); @@ -637,6 +644,35 @@ static inline bool cpu_supports_mixed_endian_el0(void) return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); } + +static inline bool supports_csv2p3(int scope) +{ + u64 pfr0; + u8 csv2_val; + + if (scope == SCOPE_LOCAL_CPU) + pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1); + else + pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + + csv2_val = cpuid_feature_extract_unsigned_field(pfr0, + ID_AA64PFR0_EL1_CSV2_SHIFT); + return csv2_val == 3; +} + +static inline bool supports_clearbhb(int scope) +{ + u64 isar2; + + if (scope == SCOPE_LOCAL_CPU) + isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); + else + isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); + + return cpuid_feature_extract_unsigned_field(isar2, + ID_AA64ISAR2_EL1_BC_SHIFT); +} + const struct cpumask *system_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); @@ -655,10 +691,10 @@ static inline bool system_supports_4kb_granule(void) mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, - ID_AA64MMFR0_TGRAN4_SHIFT); + ID_AA64MMFR0_EL1_TGRAN4_SHIFT); - return (val >= ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN) && - (val <= ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX); + return (val >= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX); } static inline bool system_supports_64kb_granule(void) @@ -668,10 +704,10 @@ static inline bool system_supports_64kb_granule(void) mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, - ID_AA64MMFR0_TGRAN64_SHIFT); + ID_AA64MMFR0_EL1_TGRAN64_SHIFT); - return (val >= ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN) && - (val <= ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX); + return (val >= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX); } static inline bool system_supports_16kb_granule(void) @@ -681,10 +717,10 @@ static inline bool system_supports_16kb_granule(void) mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, - ID_AA64MMFR0_TGRAN16_SHIFT); + ID_AA64MMFR0_EL1_TGRAN16_SHIFT); - return (val >= ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN) && - (val <= ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX); + return (val >= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN) && + (val <= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX); } static inline bool system_supports_mixed_endian_el0(void) @@ -699,7 +735,7 @@ static inline bool system_supports_mixed_endian(void) mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, - ID_AA64MMFR0_BIGENDEL_SHIFT); + ID_AA64MMFR0_EL1_BIGEND_SHIFT); return val == 0x1; } @@ -727,6 +763,23 @@ static __always_inline bool system_supports_sve(void) cpus_have_const_cap(ARM64_SVE); } +static __always_inline bool system_supports_sme(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME); +} + +static __always_inline bool system_supports_fa64(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME_FA64); +} + +static __always_inline bool system_supports_tpidr2(void) +{ + return system_supports_sme(); +} + static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && @@ -784,13 +837,13 @@ extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) { switch (parange) { - case ID_AA64MMFR0_PARANGE_32: return 32; - case ID_AA64MMFR0_PARANGE_36: return 36; - case ID_AA64MMFR0_PARANGE_40: return 40; - case ID_AA64MMFR0_PARANGE_42: return 42; - case ID_AA64MMFR0_PARANGE_44: return 44; - case ID_AA64MMFR0_PARANGE_48: return 48; - case ID_AA64MMFR0_PARANGE_52: return 52; + case ID_AA64MMFR0_EL1_PARANGE_32: return 32; + case ID_AA64MMFR0_EL1_PARANGE_36: return 36; + case ID_AA64MMFR0_EL1_PARANGE_40: return 40; + case ID_AA64MMFR0_EL1_PARANGE_42: return 42; + case ID_AA64MMFR0_EL1_PARANGE_44: return 44; + case ID_AA64MMFR0_EL1_PARANGE_48: return 48; + case ID_AA64MMFR0_EL1_PARANGE_52: return 52; /* * A future PE could use a value unknown to the kernel. * However, by the "D10.1.4 Principles of the ID scheme @@ -812,14 +865,14 @@ static inline bool cpu_has_hw_af(void) mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, - ID_AA64MMFR1_HADBS_SHIFT); + ID_AA64MMFR1_EL1_HAFDBS_SHIFT); } static inline bool cpu_has_pan(void) { u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, - ID_AA64MMFR1_PAN_SHIFT); + ID_AA64MMFR1_EL1_PAN_SHIFT); } #ifdef CONFIG_ARM64_AMU_EXTN @@ -840,8 +893,8 @@ static inline unsigned int get_vmid_bits(u64 mmfr1) int vmid_bits; vmid_bits = cpuid_feature_extract_unsigned_field(mmfr1, - ID_AA64MMFR1_VMIDBITS_SHIFT); - if (vmid_bits == ID_AA64MMFR1_VMIDBITS_16) + ID_AA64MMFR1_EL1_VMIDBits_SHIFT); + if (vmid_bits == ID_AA64MMFR1_EL1_VMIDBits_16) return 16; /* @@ -851,9 +904,15 @@ static inline unsigned int get_vmid_bits(u64 mmfr1) return 8; } +struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); + extern struct arm64_ftr_override id_aa64mmfr1_override; +extern struct arm64_ftr_override id_aa64pfr0_override; extern struct arm64_ftr_override id_aa64pfr1_override; +extern struct arm64_ftr_override id_aa64zfr0_override; +extern struct arm64_ftr_override id_aa64smfr0_override; extern struct arm64_ftr_override id_aa64isar1_override; +extern struct arm64_ftr_override id_aa64isar2_override; u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h index 14a19d1141bd..2047713e097d 100644 --- a/arch/arm64/include/asm/cpuidle.h +++ b/arch/arm64/include/asm/cpuidle.h @@ -4,21 +4,6 @@ #include <asm/proc-fns.h> -#ifdef CONFIG_CPU_IDLE -extern int arm_cpuidle_init(unsigned int cpu); -extern int arm_cpuidle_suspend(int index); -#else -static inline int arm_cpuidle_init(unsigned int cpu) -{ - return -EOPNOTSUPP; -} - -static inline int arm_cpuidle_suspend(int index) -{ - return -EOPNOTSUPP; -} -#endif - #ifdef CONFIG_ARM64_PSEUDO_NMI #include <asm/arch_gicv3.h> diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 19b8441aa8f2..65e53ef5a396 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -36,12 +36,12 @@ #define MIDR_VARIANT(midr) \ (((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT) #define MIDR_IMPLEMENTOR_SHIFT 24 -#define MIDR_IMPLEMENTOR_MASK (0xff << MIDR_IMPLEMENTOR_SHIFT) +#define MIDR_IMPLEMENTOR_MASK (0xffU << MIDR_IMPLEMENTOR_SHIFT) #define MIDR_IMPLEMENTOR(midr) \ (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) #define MIDR_CPU_MODEL(imp, partnum) \ - (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \ + ((_AT(u32, imp) << MIDR_IMPLEMENTOR_SHIFT) | \ (0xf << MIDR_ARCHITECTURE_SHIFT) | \ ((partnum) << MIDR_PARTNUM_SHIFT)) @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -73,8 +74,15 @@ #define ARM_CPU_PART_CORTEX_A76 0xD0B #define ARM_CPU_PART_NEOVERSE_N1 0xD0C #define ARM_CPU_PART_CORTEX_A77 0xD0D +#define ARM_CPU_PART_NEOVERSE_V1 0xD40 +#define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 +#define ARM_CPU_PART_CORTEX_X1 0xD44 +#define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 +#define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 +#define ARM_CPU_PART_CORTEX_A78C 0xD4B #define APM_CPU_PART_POTENZA 0x000 @@ -82,6 +90,13 @@ #define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 #define CAVIUM_CPU_PART_THUNDERX_83XX 0x0A3 #define CAVIUM_CPU_PART_THUNDERX2 0x0AF +/* OcteonTx2 series */ +#define CAVIUM_CPU_PART_OCTX2_98XX 0x0B1 +#define CAVIUM_CPU_PART_OCTX2_96XX 0x0B2 +#define CAVIUM_CPU_PART_OCTX2_95XX 0x0B3 +#define CAVIUM_CPU_PART_OCTX2_95XXN 0x0B4 +#define CAVIUM_CPU_PART_OCTX2_95XXMM 0x0B5 +#define CAVIUM_CPU_PART_OCTX2_95XXO 0x0B6 #define BRCM_CPU_PART_BRAHMA_B53 0x100 #define BRCM_CPU_PART_VULCAN 0x516 @@ -104,6 +119,12 @@ #define APPLE_CPU_PART_M1_ICESTORM 0x022 #define APPLE_CPU_PART_M1_FIRESTORM 0x023 +#define APPLE_CPU_PART_M1_ICESTORM_PRO 0x024 +#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025 +#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 +#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 + +#define AMPERE_CPU_PART_AMPERE1 0xAC3 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -115,11 +136,24 @@ #define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1) #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) +#define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) +#define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) +#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) +#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) +#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) +#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) +#define MIDR_OCTX2_98XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_98XX) +#define MIDR_OCTX2_96XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_96XX) +#define MIDR_OCTX2_95XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XX) +#define MIDR_OCTX2_95XXN MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXN) +#define MIDR_OCTX2_95XXMM MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXMM) +#define MIDR_OCTX2_95XXO MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXO) #define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2) #define MIDR_BRAHMA_B53 MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_BRAHMA_B53) #define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN) @@ -137,6 +171,11 @@ #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM) #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM) +#define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO) +#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) +#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) +#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 657c921fd784..7b7e05c02691 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -34,18 +34,6 @@ */ #define BREAK_INSTR_SIZE AARCH64_INSN_SIZE -/* - * BRK instruction encoding - * The #imm16 value should be placed at bits[20:5] within BRK ins - */ -#define AARCH64_BREAK_MON 0xd4200000 - -/* - * BRK instruction for provoking a fault on purpose - * Unlike kgdb, #imm16 value with unallocated handler is used for faulting. - */ -#define AARCH64_BREAK_FAULT (AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5)) - #define AARCH64_BREAK_KGDB_DYN_DBG \ (AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5)) @@ -76,7 +64,7 @@ struct task_struct; struct step_hook { struct list_head node; - int (*fn)(struct pt_regs *regs, unsigned int esr); + int (*fn)(struct pt_regs *regs, unsigned long esr); }; void register_user_step_hook(struct step_hook *hook); @@ -87,7 +75,7 @@ void unregister_kernel_step_hook(struct step_hook *hook); struct break_hook { struct list_head node; - int (*fn)(struct pt_regs *regs, unsigned int esr); + int (*fn)(struct pt_regs *regs, unsigned long esr); u16 imm; u16 mask; /* These bits are ignored when comparing with imm */ }; diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index ad55079abe47..d6cf535d8352 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,8 +14,16 @@ #ifdef CONFIG_EFI extern void efi_init(void); + +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg); #else #define efi_init() + +static inline +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) +{ + return false; +} #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); @@ -27,12 +35,9 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); __efi_fpsimd_begin(); \ }) +#undef arch_efi_call_virt #define arch_efi_call_virt(p, f, args...) \ -({ \ - efi_##f##_t *__f; \ - __f = p->f; \ - __efi_rt_asm_wrapper(__f, #f, args); \ -}) + __efi_rt_asm_wrapper((p)->f, #f, args) #define arch_efi_call_virt_teardown() \ ({ \ diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 3198acb2aad8..668569adf4d3 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -40,7 +40,7 @@ .macro __init_el2_debug mrs x1, id_aa64dfr0_el1 - sbfx x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4 + sbfx x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4 cmp x0, #1 b.lt .Lskip_pmu_\@ // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps @@ -49,7 +49,7 @@ csel x2, xzr, x0, lt // all PMU counters from EL1 /* Statistical profiling */ - ubfx x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 + ubfx x0, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4 cbz x0, .Lskip_spe_\@ // Skip if SPE not present mrs_s x0, SYS_PMBIDR_EL1 // If SPE available at EL2, @@ -65,7 +65,7 @@ .Lskip_spe_\@: /* Trace buffer */ - ubfx x0, x1, #ID_AA64DFR0_TRBE_SHIFT, #4 + ubfx x0, x1, #ID_AA64DFR0_EL1_TraceBuffer_SHIFT, #4 cbz x0, .Lskip_trace_\@ // Skip if TraceBuffer is not present mrs_s x0, SYS_TRBIDR_EL1 @@ -83,7 +83,7 @@ /* LORegions */ .macro __init_el2_lor mrs x1, id_aa64mmfr1_el1 - ubfx x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4 + ubfx x0, x1, #ID_AA64MMFR1_EL1_LO_SHIFT, 4 cbz x0, .Lskip_lor_\@ msr_s SYS_LORC_EL1, xzr .Lskip_lor_\@: @@ -97,7 +97,7 @@ /* GICv3 system register access */ .macro __init_el2_gicv3 mrs x0, id_aa64pfr0_el1 - ubfx x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4 + ubfx x0, x0, #ID_AA64PFR0_EL1_GIC_SHIFT, #4 cbz x0, .Lskip_gicv3_\@ mrs_s x0, SYS_ICC_SRE_EL2 @@ -106,8 +106,8 @@ msr_s SYS_ICC_SRE_EL2, x0 isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, - tbz x0, #0, 1f // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm @@ -129,43 +129,40 @@ msr cptr_el2, x0 // Disable copro. traps to EL2 .endm -/* SVE register access */ -.macro __init_el2_nvhe_sve - mrs x1, id_aa64pfr0_el1 - ubfx x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4 - cbz x1, .Lskip_sve_\@ - - bic x0, x0, #CPTR_EL2_TZ // Also disable SVE traps - msr cptr_el2, x0 // Disable copro. traps to EL2 - isb - mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector - msr_s SYS_ZCR_EL2, x1 // length for EL1. -.Lskip_sve_\@: -.endm - /* Disable any fine grained traps */ .macro __init_el2_fgt mrs x1, id_aa64mmfr0_el1 - ubfx x1, x1, #ID_AA64MMFR0_FGT_SHIFT, #4 + ubfx x1, x1, #ID_AA64MMFR0_EL1_FGT_SHIFT, #4 cbz x1, .Lskip_fgt_\@ mov x0, xzr mrs x1, id_aa64dfr0_el1 - ubfx x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 + ubfx x1, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4 cmp x1, #3 - b.lt .Lset_fgt_\@ + b.lt .Lset_debug_fgt_\@ /* Disable PMSNEVFR_EL1 read and write traps */ orr x0, x0, #(1 << 62) -.Lset_fgt_\@: +.Lset_debug_fgt_\@: msr_s SYS_HDFGRTR_EL2, x0 msr_s SYS_HDFGWTR_EL2, x0 - msr_s SYS_HFGRTR_EL2, xzr - msr_s SYS_HFGWTR_EL2, xzr + + mov x0, xzr + mrs x1, id_aa64pfr1_el1 + ubfx x1, x1, #ID_AA64PFR1_EL1_SME_SHIFT, #4 + cbz x1, .Lset_fgt_\@ + + /* Disable nVHE traps of TPIDR2 and SMPRI */ + orr x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK + orr x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK + +.Lset_fgt_\@: + msr_s SYS_HFGRTR_EL2, x0 + msr_s SYS_HFGWTR_EL2, x0 msr_s SYS_HFGITR_EL2, xzr mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU - ubfx x1, x1, #ID_AA64PFR0_AMU_SHIFT, #4 + ubfx x1, x1, #ID_AA64PFR0_EL1_AMU_SHIFT, #4 cbz x1, .Lskip_fgt_\@ msr_s SYS_HAFGRTR_EL2, xzr @@ -195,7 +192,6 @@ __init_el2_hstr __init_el2_nvhe_idregs __init_el2_nvhe_cptr - __init_el2_nvhe_sve __init_el2_fgt __init_el2_nvhe_prepare_eret .endm diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index d52a0b269ee8..15b34fbfca66 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -37,7 +37,8 @@ #define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ #define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ -/* Unallocated EC: 0x1D - 0x1E */ +#define ESR_ELx_EC_SME (0x1D) +/* Unallocated EC: 0x1E */ #define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ #define ESR_ELx_EC_IABT_LOW (0x20) #define ESR_ELx_EC_IABT_CUR (0x21) @@ -75,6 +76,7 @@ #define ESR_ELx_IL_SHIFT (25) #define ESR_ELx_IL (UL(1) << ESR_ELx_IL_SHIFT) #define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1) +#define ESR_ELx_ISS(esr) ((esr) & ESR_ELx_ISS_MASK) /* ISS field definitions shared by different classes */ #define ESR_ELx_WNR_SHIFT (6) @@ -133,10 +135,13 @@ #define ESR_ELx_CV (UL(1) << 24) #define ESR_ELx_COND_SHIFT (20) #define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT) -#define ESR_ELx_WFx_ISS_TI (UL(1) << 0) +#define ESR_ELx_WFx_ISS_RN (UL(0x1F) << 5) +#define ESR_ELx_WFx_ISS_RV (UL(1) << 2) +#define ESR_ELx_WFx_ISS_TI (UL(3) << 0) +#define ESR_ELx_WFx_ISS_WFxT (UL(2) << 0) #define ESR_ELx_WFx_ISS_WFI (UL(0) << 0) #define ESR_ELx_WFx_ISS_WFE (UL(1) << 0) -#define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1) +#define ESR_ELx_xVC_IMM_MASK ((UL(1) << 16) - 1) #define DISR_EL1_IDS (UL(1) << 24) /* @@ -146,7 +151,8 @@ #define DISR_EL1_ESR_MASK (ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC) /* ESR value templates for specific events */ -#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | ESR_ELx_WFx_ISS_TI) +#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | \ + (ESR_ELx_WFx_ISS_TI & ~ESR_ELx_WFx_ISS_WFxT)) #define ESR_ELx_WFx_WFI_VAL ((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) | \ ESR_ELx_WFx_ISS_WFI) @@ -327,17 +333,26 @@ #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ (ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\ ESR_ELx_CP15_32_ISS_DIR_READ) +/* + * ISS values for SME traps + */ + +#define ESR_ELx_SME_ISS_SME_DISABLED 0 +#define ESR_ELx_SME_ISS_ILL 1 +#define ESR_ELx_SME_ISS_SM_DISABLED 2 +#define ESR_ELx_SME_ISS_ZA_DISABLED 3 + #ifndef __ASSEMBLY__ #include <asm/types.h> -static inline bool esr_is_data_abort(u32 esr) +static inline bool esr_is_data_abort(unsigned long esr) { - const u32 ec = ESR_ELx_EC(esr); + const unsigned long ec = ESR_ELx_EC(esr); return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR; } -const char *esr_get_class_string(u32 esr); +const char *esr_get_class_string(unsigned long esr); #endif /* __ASSEMBLY */ #endif /* __ASM_ESR_H */ diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 339477dca551..19713d0f013b 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -19,9 +19,9 @@ #define __exception_irq_entry __kprobes #endif -static inline u32 disr_to_esr(u64 disr) +static inline unsigned long disr_to_esr(u64 disr) { - unsigned int esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT; + unsigned long esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT; if ((disr & DISR_EL1_IDS) == 0) esr |= (disr & DISR_EL1_ESR_MASK); @@ -57,23 +57,27 @@ asmlinkage void call_on_irq_stack(struct pt_regs *regs, void (*func)(struct pt_regs *)); asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs); -void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs); -void do_undefinstr(struct pt_regs *regs); -void do_bti(struct pt_regs *regs); -void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, +void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs); +void do_undefinstr(struct pt_regs *regs, unsigned long esr); +void do_el0_bti(struct pt_regs *regs); +void do_el1_bti(struct pt_regs *regs, unsigned long esr); +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs); -void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); -void do_sve_acc(unsigned int esr, struct pt_regs *regs); -void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); -void do_sysinstr(unsigned int esr, struct pt_regs *regs); -void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); -void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); -void do_cp15instr(unsigned int esr, struct pt_regs *regs); +void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs); +void do_sve_acc(unsigned long esr, struct pt_regs *regs); +void do_sme_acc(unsigned long esr, struct pt_regs *regs); +void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs); +void do_sysinstr(unsigned long esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs); +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr); +void do_cp15instr(unsigned long esr, struct pt_regs *regs); +int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs); void do_el0_svc(struct pt_regs *regs); void do_el0_svc_compat(struct pt_regs *regs); -void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr); -void do_serror(struct pt_regs *regs, unsigned int esr); +void do_el0_fpac(struct pt_regs *regs, unsigned long esr); +void do_el1_fpac(struct pt_regs *regs, unsigned long esr); +void do_serror(struct pt_regs *regs, unsigned long esr); void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags); -void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far); +void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 4335800201c9..71ed5fdf718b 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -62,9 +62,13 @@ enum fixed_addresses { #endif /* CONFIG_ACPI_APEI_GHES */ #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - FIX_ENTRY_TRAMP_DATA, - FIX_ENTRY_TRAMP_TEXT, -#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT)) +#ifdef CONFIG_RELOCATABLE + FIX_ENTRY_TRAMP_TEXT4, /* one extra slot for the data page */ +#endif + FIX_ENTRY_TRAMP_TEXT3, + FIX_ENTRY_TRAMP_TEXT2, + FIX_ENTRY_TRAMP_TEXT1, +#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT1)) #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ __end_of_permanent_fixed_addresses, diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index cb24385e3632..6f86b7ab6c28 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -32,6 +32,18 @@ #define VFP_STATE_SIZE ((32 * 8) + 4) #endif +/* + * When we defined the maximum SVE vector length we defined the ABI so + * that the maximum vector length included all the reserved for future + * expansion bits in ZCR rather than those just currently defined by + * the architecture. While SME follows a similar pattern the fact that + * it includes a square matrix means that any allocations that attempt + * to cover the maximum potential vector length (such as happen with + * the regset used for ptrace) end up being extremely large. Define + * the much lower actual limit for use in such situations. + */ +#define SME_VQ_MAX 16 + struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); @@ -46,11 +58,23 @@ extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, - void *sve_state, unsigned int sve_vl); + void *sve_state, unsigned int sve_vl, + void *za_state, unsigned int sme_vl, + u64 *svcr); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); +static inline bool thread_sm_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SVCR_SM_MASK); +} + +static inline bool thread_za_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK); +} + /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 @@ -62,7 +86,14 @@ static inline size_t sve_ffr_offset(int vl) static inline void *sve_pffr(struct thread_struct *thread) { - return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread)); + unsigned int vl; + + if (system_supports_sme() && thread_sm_enabled(thread)) + vl = thread_get_sme_vl(thread); + else + vl = thread_get_sve_vl(thread); + + return (char *)thread->sve_state + sve_ffr_offset(vl); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); @@ -71,11 +102,17 @@ extern void sve_load_state(void const *state, u32 const *pfpsr, extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); +extern void sme_set_vq(unsigned long vq_minus_1); +extern void za_save_state(void *state); +extern void za_load_state(void const *state); struct arm64_cpu_capabilities; extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern u64 read_zcr_features(void); +extern u64 read_smcr_features(void); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and @@ -116,9 +153,10 @@ struct vl_info { #ifdef CONFIG_ARM64_SVE -extern void sve_alloc(struct task_struct *task); +extern void sve_alloc(struct task_struct *task, bool flush); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); +extern void fpsimd_force_sync_to_sve(struct task_struct *task); extern void sve_sync_to_fpsimd(struct task_struct *task); extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); @@ -171,6 +209,12 @@ static inline void write_vl(enum vec_type type, u64 val) write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif +#ifdef CONFIG_ARM64_SME + case ARM64_VEC_SME: + tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; + write_sysreg_s(tmp | val, SYS_SMCR_EL1); + break; +#endif default: WARN_ON_ONCE(1); break; @@ -208,9 +252,11 @@ static inline bool sve_vq_available(unsigned int vq) return vq_available(ARM64_VEC_SVE, vq); } +size_t sve_state_size(struct task_struct const *task); + #else /* ! CONFIG_ARM64_SVE */ -static inline void sve_alloc(struct task_struct *task) { } +static inline void sve_alloc(struct task_struct *task, bool flush) { } static inline void fpsimd_release_task(struct task_struct *task) { } static inline void sve_sync_to_fpsimd(struct task_struct *task) { } static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } @@ -247,8 +293,93 @@ static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } +static inline size_t sve_state_size(struct task_struct const *task) +{ + return 0; +} + #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static inline void sme_user_disable(void) +{ + sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); +} + +static inline void sme_user_enable(void) +{ + sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); +} + +static inline void sme_smstart_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); +} + +static inline void sme_smstop_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); +} + +static inline void sme_smstop(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); +} + +extern void __init sme_setup(void); + +static inline int sme_max_vl(void) +{ + return vec_max_vl(ARM64_VEC_SME); +} + +static inline int sme_max_virtualisable_vl(void) +{ + return vec_max_virtualisable_vl(ARM64_VEC_SME); +} + +extern void sme_alloc(struct task_struct *task); +extern unsigned int sme_get_vl(void); +extern int sme_set_current_vl(unsigned long arg); +extern int sme_get_current_vl(void); + +/* + * Return how many bytes of memory are required to store the full SME + * specific state (currently just ZA) for task, given task's currently + * configured vector length. + */ +static inline size_t za_state_size(struct task_struct const *task) +{ + unsigned int vl = task_get_sme_vl(task); + + return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); +} + +#else + +static inline void sme_user_disable(void) { BUILD_BUG(); } +static inline void sme_user_enable(void) { BUILD_BUG(); } + +static inline void sme_smstart_sm(void) { } +static inline void sme_smstop_sm(void) { } +static inline void sme_smstop(void) { } + +static inline void sme_alloc(struct task_struct *task) { } +static inline void sme_setup(void) { } +static inline unsigned int sme_get_vl(void) { return 0; } +static inline int sme_max_vl(void) { return 0; } +static inline int sme_max_virtualisable_vl(void) { return 0; } +static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } +static inline int sme_get_current_vl(void) { return -EINVAL; } + +static inline size_t za_state_size(struct task_struct const *task) +{ + return 0; +} + +#endif /* ! CONFIG_ARM64_SME */ + /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 2509d7dde55a..5e0910cf4832 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -93,6 +93,12 @@ .endif .endm +.macro _sme_check_wv v + .if (\v) < 12 || (\v) > 15 + .error "Bad vector select register \v." + .endif +.endm + /* SVE instruction encodings for non-SVE-capable assemblers */ /* (pre binutils 2.28, all kernel capable clang versions support SVE) */ @@ -174,6 +180,54 @@ | (\np) .endm +/* SME instruction encodings for non-SME-capable assemblers */ +/* (pre binutils 2.38/LLVM 13) */ + +/* RDSVL X\nx, #\imm */ +.macro _sme_rdsvl nx, imm + _check_general_reg \nx + _check_num (\imm), -0x20, 0x1f + .inst 0x04bf5800 \ + | (\nx) \ + | (((\imm) & 0x3f) << 5) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_str_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_ldr_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * Zero the entire ZA array + * ZERO ZA + */ +.macro zero_za + .inst 0xc00800ff +.endm + .macro __for from:req, to:req .if (\from) == (\to) _for__body %\from @@ -208,6 +262,17 @@ 921: .endm +/* Update SMCR_EL1.LEN with the new VQ */ +.macro sme_load_vq xvqminus1, xtmp, xtmp2 + mrs_s \xtmp, SYS_SMCR_EL1 + bic \xtmp2, \xtmp, SMCR_ELx_LEN_MASK + orr \xtmp2, \xtmp2, \xvqminus1 + cmp \xtmp2, \xtmp + b.eq 921f + msr_s SYS_SMCR_EL1, \xtmp2 //self-synchronising +921: +.endm + /* Preserve the first 128-bits of Znz and zero the rest. */ .macro _sve_flush_z nz _sve_check_zreg \nz @@ -254,3 +319,25 @@ ldr w\nxtmp, [\xpfpsr, #4] msr fpcr, x\nxtmp .endm + +.macro sme_save_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_str_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm + +.macro sme_load_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_ldr_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 1494cfa8639b..329dbbd4d50b 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -26,7 +26,7 @@ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS #define ARCH_SUPPORTS_FTRACE_OPS 1 #else -#define MCOUNT_ADDR ((unsigned long)function_nocfi(_mcount)) +#define MCOUNT_ADDR ((unsigned long)_mcount) #endif /* The BL at the callsite's adjusted rec->ip */ @@ -80,8 +80,15 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS struct dyn_ftrace; +struct ftrace_ops; +struct ftrace_regs; + int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); #define ftrace_init_nop ftrace_init_nop + +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#define ftrace_graph_func ftrace_graph_func #endif #define ftrace_return_address(n) return_address(n) diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 1242f71937f8..d20f5da2d76f 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -39,14 +39,13 @@ extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, extern void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -extern void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +extern pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_HUGE_PTE_CLEAR extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz); -extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz); -#define set_huge_swap_pte_at set_huge_swap_pte_at +#define __HAVE_ARCH_HUGE_PTEP_GET +extern pte_t huge_ptep_get(pte_t *ptep); void __init arm64_hugetlb_cma_reserve(void); diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index bc7aaed4b34e..fa4c6ff3aa9b 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -142,7 +142,7 @@ static inline int get_num_brps(void) u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); return 1 + cpuid_feature_extract_unsigned_field(dfr0, - ID_AA64DFR0_BRPS_SHIFT); + ID_AA64DFR0_EL1_BRPs_SHIFT); } /* Determine number of WRP registers available. */ @@ -151,7 +151,7 @@ static inline int get_num_wrps(void) u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); return 1 + cpuid_feature_extract_unsigned_field(dfr0, - ID_AA64DFR0_WRPS_SHIFT); + ID_AA64DFR0_EL1_WRPs_SHIFT); } #endif /* __ASM_BREAKPOINT_H */ diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index f68fbb207473..298b386d3ebe 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -85,7 +85,7 @@ #define KERNEL_HWCAP_PACA __khwcap_feature(PACA) #define KERNEL_HWCAP_PACG __khwcap_feature(PACG) -#define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 32) +#define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 64) #define KERNEL_HWCAP_DCPODP __khwcap2_feature(DCPODP) #define KERNEL_HWCAP_SVE2 __khwcap2_feature(SVE2) #define KERNEL_HWCAP_SVEAES __khwcap2_feature(SVEAES) @@ -108,6 +108,18 @@ #define KERNEL_HWCAP_ECV __khwcap2_feature(ECV) #define KERNEL_HWCAP_AFP __khwcap2_feature(AFP) #define KERNEL_HWCAP_RPRES __khwcap2_feature(RPRES) +#define KERNEL_HWCAP_MTE3 __khwcap2_feature(MTE3) +#define KERNEL_HWCAP_SME __khwcap2_feature(SME) +#define KERNEL_HWCAP_SME_I16I64 __khwcap2_feature(SME_I16I64) +#define KERNEL_HWCAP_SME_F64F64 __khwcap2_feature(SME_F64F64) +#define KERNEL_HWCAP_SME_I8I32 __khwcap2_feature(SME_I8I32) +#define KERNEL_HWCAP_SME_F16F32 __khwcap2_feature(SME_F16F32) +#define KERNEL_HWCAP_SME_B16F32 __khwcap2_feature(SME_B16F32) +#define KERNEL_HWCAP_SME_F32F32 __khwcap2_feature(SME_F32F32) +#define KERNEL_HWCAP_SME_FA64 __khwcap2_feature(SME_FA64) +#define KERNEL_HWCAP_WFXT __khwcap2_feature(WFXT) +#define KERNEL_HWCAP_EBF16 __khwcap2_feature(EBF16) +#define KERNEL_HWCAP_SVE_EBF16 __khwcap2_feature(SVE_EBF16) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/hyperv-tlfs.h b/arch/arm64/include/asm/hyperv-tlfs.h index 4d964a7f02ee..bc6c7ac934a1 100644 --- a/arch/arm64/include/asm/hyperv-tlfs.h +++ b/arch/arm64/include/asm/hyperv-tlfs.h @@ -64,6 +64,15 @@ #define HV_REGISTER_STIMER0_CONFIG 0x000B0000 #define HV_REGISTER_STIMER0_COUNT 0x000B0001 +union hv_msi_entry { + u64 as_uint64[2]; + struct { + u64 address; + u32 data; + u32 reserved; + } __packed; +}; + #include <asm-generic/hyperv-tlfs.h> #endif diff --git a/arch/arm64/include/asm/insn-def.h b/arch/arm64/include/asm/insn-def.h index 2c075f615c6a..1a7d0d483698 100644 --- a/arch/arm64/include/asm/insn-def.h +++ b/arch/arm64/include/asm/insn-def.h @@ -3,7 +3,21 @@ #ifndef __ASM_INSN_DEF_H #define __ASM_INSN_DEF_H +#include <asm/brk-imm.h> + /* A64 instructions are always 32 bits. */ #define AARCH64_INSN_SIZE 4 +/* + * BRK instruction encoding + * The #imm16 value should be placed at bits[20:5] within BRK ins + */ +#define AARCH64_BREAK_MON 0xd4200000 + +/* + * BRK instruction for provoking a fault on purpose + * Unlike kgdb, #imm16 value with unallocated handler is used for faulting. + */ +#define AARCH64_BREAK_FAULT (AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5)) + #endif /* __ASM_INSN_DEF_H */ diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 6b776c8667b2..834bff720582 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -65,6 +65,7 @@ enum aarch64_insn_hint_cr_op { AARCH64_INSN_HINT_PSB = 0x11 << 5, AARCH64_INSN_HINT_TSB = 0x12 << 5, AARCH64_INSN_HINT_CSDB = 0x14 << 5, + AARCH64_INSN_HINT_CLEARBHB = 0x16 << 5, AARCH64_INSN_HINT_BTI = 0x20 << 5, AARCH64_INSN_HINT_BTIC = 0x22 << 5, @@ -200,12 +201,16 @@ enum aarch64_insn_size_type { enum aarch64_insn_ldst_type { AARCH64_INSN_LDST_LOAD_REG_OFFSET, AARCH64_INSN_LDST_STORE_REG_OFFSET, + AARCH64_INSN_LDST_LOAD_IMM_OFFSET, + AARCH64_INSN_LDST_STORE_IMM_OFFSET, AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX, AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX, AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX, AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX, AARCH64_INSN_LDST_LOAD_EX, + AARCH64_INSN_LDST_LOAD_ACQ_EX, AARCH64_INSN_LDST_STORE_EX, + AARCH64_INSN_LDST_STORE_REL_EX, }; enum aarch64_insn_adsb_type { @@ -280,6 +285,36 @@ enum aarch64_insn_adr_type { AARCH64_INSN_ADR_TYPE_ADR, }; +enum aarch64_insn_mem_atomic_op { + AARCH64_INSN_MEM_ATOMIC_ADD, + AARCH64_INSN_MEM_ATOMIC_CLR, + AARCH64_INSN_MEM_ATOMIC_EOR, + AARCH64_INSN_MEM_ATOMIC_SET, + AARCH64_INSN_MEM_ATOMIC_SWP, +}; + +enum aarch64_insn_mem_order_type { + AARCH64_INSN_MEM_ORDER_NONE, + AARCH64_INSN_MEM_ORDER_ACQ, + AARCH64_INSN_MEM_ORDER_REL, + AARCH64_INSN_MEM_ORDER_ACQREL, +}; + +enum aarch64_insn_mb_type { + AARCH64_INSN_MB_SY, + AARCH64_INSN_MB_ST, + AARCH64_INSN_MB_LD, + AARCH64_INSN_MB_ISH, + AARCH64_INSN_MB_ISHST, + AARCH64_INSN_MB_ISHLD, + AARCH64_INSN_MB_NSH, + AARCH64_INSN_MB_NSHST, + AARCH64_INSN_MB_NSHLD, + AARCH64_INSN_MB_OSH, + AARCH64_INSN_MB_OSHST, + AARCH64_INSN_MB_OSHLD, +}; + #define __AARCH64_INSN_FUNCS(abbr, mask, val) \ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ { \ @@ -302,8 +337,15 @@ __AARCH64_INSN_FUNCS(load_pre, 0x3FE00C00, 0x38400C00) __AARCH64_INSN_FUNCS(store_post, 0x3FE00C00, 0x38000400) __AARCH64_INSN_FUNCS(load_post, 0x3FE00C00, 0x38400400) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) +__AARCH64_INSN_FUNCS(str_imm, 0x3FC00000, 0x39000000) __AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0x38200000) +__AARCH64_INSN_FUNCS(ldclr, 0x3F20FC00, 0x38201000) +__AARCH64_INSN_FUNCS(ldeor, 0x3F20FC00, 0x38202000) +__AARCH64_INSN_FUNCS(ldset, 0x3F20FC00, 0x38203000) +__AARCH64_INSN_FUNCS(swp, 0x3F20FC00, 0x38208000) +__AARCH64_INSN_FUNCS(cas, 0x3FA07C00, 0x08A07C00) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) +__AARCH64_INSN_FUNCS(ldr_imm, 0x3FC00000, 0x39400000) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) __AARCH64_INSN_FUNCS(exclusive, 0x3F800000, 0x08000000) @@ -463,6 +505,14 @@ u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg, enum aarch64_insn_register offset, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_load_store_imm(enum aarch64_insn_register reg, + enum aarch64_insn_register base, + unsigned int imm, + enum aarch64_insn_size_type size, + enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_load_literal(unsigned long pc, unsigned long addr, + enum aarch64_insn_register reg, + bool is64bit); u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1, enum aarch64_insn_register reg2, enum aarch64_insn_register base, @@ -474,13 +524,6 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register state, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type); -u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, - enum aarch64_insn_register address, - enum aarch64_insn_register value, - enum aarch64_insn_size_type size); -u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, - enum aarch64_insn_register value, - enum aarch64_insn_size_type size); u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, @@ -541,6 +584,42 @@ u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base, enum aarch64_insn_prfm_type type, enum aarch64_insn_prfm_target target, enum aarch64_insn_prfm_policy policy); +#ifdef CONFIG_ARM64_LSE_ATOMICS +u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_atomic_op op, + enum aarch64_insn_mem_order_type order); +u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_order_type order); +#else +static inline +u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_atomic_op op, + enum aarch64_insn_mem_order_type order) +{ + return AARCH64_BREAK_FAULT; +} + +static inline +u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size, + enum aarch64_insn_mem_order_type order) +{ + return AARCH64_BREAK_FAULT; +} +#endif +u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type); + s32 aarch64_get_branch_offset(u32 insn); u32 aarch64_set_branch_offset(u32 insn, s32 offset); diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 7fd836bea7eb..877495a0fd0c 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -91,7 +91,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) } /* IO barriers */ -#define __iormb(v) \ +#define __io_ar(v) \ ({ \ unsigned long tmp; \ \ @@ -108,39 +108,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) : "memory"); \ }) -#define __io_par(v) __iormb(v) -#define __iowmb() dma_wmb() -#define __iomb() dma_mb() - -/* - * Relaxed I/O memory access primitives. These follow the Device memory - * ordering rules but do not guarantee any ordering relative to Normal memory - * accesses. - */ -#define readb_relaxed(c) ({ u8 __r = __raw_readb(c); __r; }) -#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; }) -#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; }) -#define readq_relaxed(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; }) - -#define writeb_relaxed(v,c) ((void)__raw_writeb((v),(c))) -#define writew_relaxed(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c))) -#define writel_relaxed(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c))) -#define writeq_relaxed(v,c) ((void)__raw_writeq((__force u64)cpu_to_le64(v),(c))) - -/* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. - */ -#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(__v); __v; }) -#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(__v); __v; }) -#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; }) -#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(__v); __v; }) +#define __io_bw() dma_wmb() +#define __io_br(v) +#define __io_aw(v) -#define writeb(v,c) ({ __iowmb(); writeb_relaxed((v),(c)); }) -#define writew(v,c) ({ __iowmb(); writew_relaxed((v),(c)); }) -#define writel(v,c) ({ __iowmb(); writel_relaxed((v),(c)); }) -#define writeq(v,c) ({ __iowmb(); writeq_relaxed((v),(c)); }) +/* arm64-specific, don't use in portable drivers */ +#define __iormb(v) __io_ar(v) +#define __iowmb() __io_bw() +#define __iomb() dma_mb() /* * I/O port access primitives. @@ -163,13 +138,16 @@ 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 __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); -#define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) -#define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC)) -#define ioremap_np(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRnE)) +bool ioremap_allowed(phys_addr_t phys_addr, size_t size, unsigned long prot); +#define ioremap_allowed ioremap_allowed + +#define _PAGE_IOREMAP PROT_DEVICE_nGnRE + +#define ioremap_wc(addr, size) \ + ioremap_prot((addr), (size), PROT_NORMAL_NC) +#define ioremap_np(addr, size) \ + ioremap_prot((addr), (size), PROT_DEVICE_nGnRnE) /* * io{read,write}{16,32,64}be() macros @@ -184,6 +162,15 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); #include <asm-generic/io.h> +#define ioremap_cache ioremap_cache +static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size) +{ + if (pfn_is_map_memory(__phys_to_pfn(addr))) + return (void __iomem *)__phys_to_virt(addr); + + return ioremap_prot(addr, size, PROT_NORMAL); +} + /* * More restrictive address range checking than the default implementation * (PHYS_OFFSET and PHYS_MASK taken into account). @@ -192,4 +179,8 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + #endif /* __ASM_IO_H */ diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 96dc0f7da258..32d14f481f0c 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -8,6 +8,7 @@ #ifndef __ASM_KERNEL_PGTABLE_H #define __ASM_KERNEL_PGTABLE_H +#include <asm/boot.h> #include <asm/pgtable-hwdef.h> #include <asm/sparsemem.h> @@ -35,10 +36,8 @@ */ #if ARM64_KERNEL_USES_PMD_MAPS #define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1) -#define IDMAP_PGTABLE_LEVELS (ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT) - 1) #else #define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) -#define IDMAP_PGTABLE_LEVELS (ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT)) #endif @@ -65,29 +64,36 @@ #define EARLY_KASLR (0) #endif -#define EARLY_ENTRIES(vstart, vend, shift) \ - ((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + EARLY_KASLR) +#define EARLY_ENTRIES(vstart, vend, shift, add) \ + ((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + add) -#define EARLY_PGDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT)) +#define EARLY_PGDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT, add)) #if SWAPPER_PGTABLE_LEVELS > 3 -#define EARLY_PUDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT)) +#define EARLY_PUDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT, add)) #else -#define EARLY_PUDS(vstart, vend) (0) +#define EARLY_PUDS(vstart, vend, add) (0) #endif #if SWAPPER_PGTABLE_LEVELS > 2 -#define EARLY_PMDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT)) +#define EARLY_PMDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT, add)) #else -#define EARLY_PMDS(vstart, vend) (0) +#define EARLY_PMDS(vstart, vend, add) (0) #endif -#define EARLY_PAGES(vstart, vend) ( 1 /* PGDIR page */ \ - + EARLY_PGDS((vstart), (vend)) /* each PGDIR needs a next level page table */ \ - + EARLY_PUDS((vstart), (vend)) /* each PUD needs a next level page table */ \ - + EARLY_PMDS((vstart), (vend))) /* each PMD needs a next level page table */ -#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end)) -#define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE) +#define EARLY_PAGES(vstart, vend, add) ( 1 /* PGDIR page */ \ + + EARLY_PGDS((vstart), (vend), add) /* each PGDIR needs a next level page table */ \ + + EARLY_PUDS((vstart), (vend), add) /* each PUD needs a next level page table */ \ + + EARLY_PMDS((vstart), (vend), add)) /* each PMD needs a next level page table */ +#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EARLY_KASLR)) + +/* the initial ID map may need two extra pages if it needs to be extended */ +#if VA_BITS < 48 +#define INIT_IDMAP_DIR_SIZE ((INIT_IDMAP_DIR_PAGES + 2) * PAGE_SIZE) +#else +#define INIT_IDMAP_DIR_SIZE (INIT_IDMAP_DIR_PAGES * PAGE_SIZE) +#endif +#define INIT_IDMAP_DIR_PAGES EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1) /* Initial memory map size */ #if ARM64_KERNEL_USES_PMD_MAPS @@ -107,9 +113,11 @@ #define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) #if ARM64_KERNEL_USES_PMD_MAPS -#define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS) +#define SWAPPER_RW_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS) +#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY) #else -#define SWAPPER_MM_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS) +#define SWAPPER_RW_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS) +#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PTE_RDONLY) #endif /* diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 9839bfc163d7..559bfae26715 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -84,16 +84,30 @@ static inline void crash_setup_regs(struct pt_regs *newregs, extern bool crash_is_nosave(unsigned long pfn); extern void crash_prepare_suspend(void); extern void crash_post_resume(void); + +void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); +#define crash_free_reserved_phys_range crash_free_reserved_phys_range #else static inline bool crash_is_nosave(unsigned long pfn) {return false; } static inline void crash_prepare_suspend(void) {} static inline void crash_post_resume(void) {} #endif +struct kimage; + #if defined(CONFIG_KEXEC_CORE) void cpu_soft_restart(unsigned long el2_switch, unsigned long entry, unsigned long arg0, unsigned long arg1, unsigned long arg2); + +int machine_kexec_post_load(struct kimage *image); +#define machine_kexec_post_load machine_kexec_post_load + +void arch_kexec_protect_crashkres(void); +#define arch_kexec_protect_crashkres arch_kexec_protect_crashkres + +void arch_kexec_unprotect_crashkres(void); +#define arch_kexec_unprotect_crashkres arch_kexec_unprotect_crashkres #endif #define ARCH_HAS_KIMAGE_ARCH @@ -113,9 +127,9 @@ struct kimage_arch { #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops kexec_image_ops; -struct kimage; +int arch_kimage_file_post_load_cleanup(struct kimage *image); +#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup -extern int arch_kimage_file_post_load_cleanup(struct kimage *image); extern int load_other_segments(struct kimage *image, unsigned long kernel_load_addr, unsigned long kernel_size, char *initrd, unsigned long initrd_len, diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 01d47c5886dc..8aa8492dafc0 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -80,11 +80,12 @@ * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate * PTW: Take a stage2 fault if a stage1 walk steps in device memory + * TID3: Trap EL1 reads of group 3 ID registers */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_BSU_IS | HCR_FB | HCR_TACR | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO | HCR_PTW ) + HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA) #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) @@ -279,6 +280,7 @@ #define CPTR_EL2_TCPAC (1U << 31) #define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) +#define CPTR_EL2_TSM (1 << 12) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) #define CPTR_EL2_TZ (1 << 8) #define CPTR_NVHE_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */ @@ -355,8 +357,8 @@ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ ECN(BKPT32), ECN(VECTOR32), ECN(BRK64) -#define CPACR_EL1_FPEN (3 << 20) #define CPACR_EL1_TTA (1 << 28) -#define CPACR_EL1_DEFAULT (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN) +#define CPACR_EL1_DEFAULT (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |\ + CPACR_EL1_ZEN_EL1EN) #endif /* __ARM64_KVM_ARM_H__ */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 50d5e4de244c..53035763e48e 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -63,6 +63,7 @@ enum __kvm_host_smccc_func { /* Hypercalls available after pKVM finalisation */ __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, + __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp, __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run, __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context, @@ -168,12 +169,29 @@ struct kvm_nvhe_init_params { unsigned long tcr_el2; unsigned long tpidr_el2; unsigned long stack_hyp_va; + unsigned long stack_pa; phys_addr_t pgd_pa; unsigned long hcr_el2; unsigned long vttbr; unsigned long vtcr; }; +/* + * Used by the host in EL1 to dump the nVHE hypervisor backtrace on + * hyp_panic() in non-protected mode. + * + * @stack_base: hyp VA of the hyp_stack base. + * @overflow_stack_base: hyp VA of the hyp_overflow_stack base. + * @fp: hyp FP where the backtrace begins. + * @pc: hyp PC where the backtrace begins. + */ +struct kvm_nvhe_stacktrace_info { + unsigned long stack_base; + unsigned long overflow_stack_base; + unsigned long fp; + unsigned long pc; +}; + /* Translate a kernel address @ptr into its equivalent linear mapping */ #define kvm_ksym_ref(ptr) \ ({ \ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f4871e47b2d0..9bdba47f7e14 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -40,11 +40,26 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_inject_size_fault(struct kvm_vcpu *vcpu); +void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); + +#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__) static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); } +#else +static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, + &kvm->arch.flags)); + + return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); +} +#endif static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { @@ -70,17 +85,9 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_TVM; } - if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) + if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; - /* - * TID3: trap feature register accesses that we virtualise. - * For now this is conditional, since no AArch32 feature regs - * are currently virtualised. - */ - if (!vcpu_el1_is_32bit(vcpu)) - vcpu->arch.hcr_el2 |= HCR_TID3; - if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 |= HCR_TID2; @@ -222,14 +229,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) return mode != PSR_MODE_EL0t; } -static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu) +static __always_inline u64 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.esr_el2; } static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); if (esr & ESR_ELx_CV) return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT; @@ -360,7 +367,7 @@ static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); return ESR_ELx_SYS64_ISS_RT(esr); } @@ -386,7 +393,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) *vcpu_cpsr(vcpu) |= PSR_AA32_E_BIT; } else { u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); - sctlr |= (1 << 25); + sctlr |= SCTLR_ELx_EE; vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1); } } @@ -466,9 +473,18 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) { - vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC; + WARN_ON(vcpu_get_flag(vcpu, PENDING_EXCEPTION)); + vcpu_set_flag(vcpu, INCREMENT_PC); } +#define kvm_pend_exception(v, e) \ + do { \ + WARN_ON(vcpu_get_flag((v), INCREMENT_PC)); \ + vcpu_set_flag((v), PENDING_EXCEPTION); \ + vcpu_set_flag((v), e); \ + } while (0) + + static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) { return test_bit(feature, vcpu->arch.features); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2a5f7f38006f..45e2136322ba 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -26,7 +26,6 @@ #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> -#include <asm/thread_info.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -47,10 +46,13 @@ #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) #define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) #define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5) +#define KVM_REQ_SUSPEND KVM_ARCH_REQ(6) #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) +#define KVM_HAVE_MMU_RWLOCK + /* * Mode of operation configurable with kvm-arm.mode early param. * See Documentation/admin-guide/kernel-parameters.txt for more information. @@ -72,9 +74,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); struct kvm_vmid { - /* The VMID generation used for the virt. memory system */ - u64 vmid_gen; - u32 vmid; + atomic64_t id; }; struct kvm_s2_mmu { @@ -102,15 +102,25 @@ struct kvm_s2_mmu { struct kvm_arch_memory_slot { }; +/** + * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests + * + * @std_bmap: Bitmap of standard secure service calls + * @std_hyp_bmap: Bitmap of standard hypervisor service calls + * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls + */ +struct kvm_smccc_features { + unsigned long std_bmap; + unsigned long std_hyp_bmap; + unsigned long vendor_hyp_bmap; +}; + struct kvm_arch { struct kvm_s2_mmu mmu; /* VTCR_EL2 value for this VM */ u64 vtcr; - /* The maximum number of vCPUs depends on the used GIC model */ - int max_vcpus; - /* Interrupt controller */ struct vgic_dist vgic; @@ -123,24 +133,43 @@ struct kvm_arch { * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is * supported. */ - bool return_nisv_io_abort_to_user; +#define KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER 0 + /* Memory Tagging Extension enabled for the guest */ +#define KVM_ARCH_FLAG_MTE_ENABLED 1 + /* At least one vCPU has ran in the VM */ +#define KVM_ARCH_FLAG_HAS_RAN_ONCE 2 + /* + * The following two bits are used to indicate the guest's EL1 + * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT + * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set. + * Otherwise, the guest's EL1 register width has not yet been + * determined yet. + */ +#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3 +#define KVM_ARCH_FLAG_EL1_32BIT 4 + /* PSCI SYSTEM_SUSPEND enabled for the guest */ +#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 + + unsigned long flags; /* * VM-wide PMU filter, implemented as a bitmap and big enough for * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+). */ unsigned long *pmu_filter; - unsigned int pmuver; + struct arm_pmu *arm_pmu; + + cpumask_var_t supported_cpus; u8 pfr0_csv2; u8 pfr0_csv3; - /* Memory Tagging Extension enabled for the guest */ - bool mte_enabled; + /* Hypercall features firmware registers' descriptor */ + struct kvm_smccc_features smccc_feat; }; struct kvm_vcpu_fault_info { - u32 esr_el2; /* Hyp Syndrom Register */ + u64 esr_el2; /* Hyp Syndrom Register */ u64 far_el2; /* Hyp Fault Address Register */ u64 hpfar_el2; /* Hyp IPA Fault Address Register */ u64 disr_el1; /* Deferred [SError] Status Register */ @@ -172,6 +201,7 @@ enum vcpu_sysreg { PAR_EL1, /* Physical Address Register */ MDSCR_EL1, /* Monitor Debug System Control Register */ MDCCINT_EL1, /* Monitor Debug Comms Channel Interrupt Enable Reg */ + OSLSR_EL1, /* OS Lock Status Register */ DISR_EL1, /* Deferred Interrupt Status Register */ /* Performance Monitors Registers */ @@ -240,14 +270,8 @@ struct kvm_cpu_context { struct kvm_vcpu *__hyp_running_vcpu; }; -struct kvm_pmu_events { - u32 events_host; - u32 events_guest; -}; - struct kvm_host_data { struct kvm_cpu_context host_ctxt; - struct kvm_pmu_events pmu_events; }; struct kvm_host_psci_config { @@ -281,8 +305,11 @@ struct vcpu_reset_state { struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; + + /* Guest floating point state */ void *sve_state; unsigned int sve_max_vl; + u64 svcr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; @@ -298,11 +325,30 @@ struct kvm_vcpu_arch { /* Exception Information */ struct kvm_vcpu_fault_info fault; - /* State of various workarounds, see kvm_asm.h for bit assignment */ - u64 workaround_flags; + /* Ownership of the FP regs */ + enum { + FP_STATE_FREE, + FP_STATE_HOST_OWNED, + FP_STATE_GUEST_OWNED, + } fp_state; - /* Miscellaneous vcpu state flags */ - u64 flags; + /* Configuration flags, set once and for all before the vcpu can run */ + u8 cflags; + + /* Input flags to the hypervisor code, potentially cleared after use */ + u8 iflags; + + /* State flags for kernel bookkeeping, unused by the hypervisor code */ + u8 sflags; + + /* + * Don't run the guest (internal implementation need). + * + * Contrary to the flags above, this is set/cleared outside of + * a vcpu context, and thus cannot be mixed with the flags + * themselves (or the flag accesses need to be made atomic). + */ + bool pause; /* * We maintain more than a single set of debug registers to support @@ -321,8 +367,8 @@ struct kvm_vcpu_arch { struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; - struct thread_info *host_thread_info; /* hyp VA */ struct user_fpsimd_state *host_fpsimd_state; /* hyp VA */ + struct task_struct *parent_task; struct { /* {Break,watch}point registers */ @@ -339,11 +385,6 @@ struct kvm_vcpu_arch { struct kvm_pmu pmu; /* - * Anything that is not used directly from assembly code goes - * here. - */ - - /* * Guest registers we preserve during guest debugging. * * These shadow registers are updated by the kvm_handle_sys_reg @@ -352,13 +393,11 @@ struct kvm_vcpu_arch { */ struct { u32 mdscr_el1; + bool pstate_ss; } guest_debug_preserved; - /* vcpu power-off state */ - bool power_off; - - /* Don't run the guest (internal implementation need) */ - bool pause; + /* vcpu power state */ + struct kvm_mp_state mp_state; /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; @@ -367,19 +406,12 @@ struct kvm_vcpu_arch { int target; DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); - /* Detect first run of a vcpu */ - bool has_run_once; - /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; /* Additional reset state */ struct vcpu_reset_state reset_state; - /* True when deferrable sysregs are loaded on the physical CPU, - * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */ - bool sysregs_loaded_on_cpu; - /* Guest PV state */ struct { u64 last_steal; @@ -387,6 +419,127 @@ struct kvm_vcpu_arch { } steal; }; +/* + * Each 'flag' is composed of a comma-separated triplet: + * + * - the flag-set it belongs to in the vcpu->arch structure + * - the value for that flag + * - the mask for that flag + * + * __vcpu_single_flag() builds such a triplet for a single-bit flag. + * unpack_vcpu_flag() extract the flag value from the triplet for + * direct use outside of the flag accessors. + */ +#define __vcpu_single_flag(_set, _f) _set, (_f), (_f) + +#define __unpack_flag(_set, _f, _m) _f +#define unpack_vcpu_flag(...) __unpack_flag(__VA_ARGS__) + +#define __build_check_flag(v, flagset, f, m) \ + do { \ + typeof(v->arch.flagset) *_fset; \ + \ + /* Check that the flags fit in the mask */ \ + BUILD_BUG_ON(HWEIGHT(m) != HWEIGHT((f) | (m))); \ + /* Check that the flags fit in the type */ \ + BUILD_BUG_ON((sizeof(*_fset) * 8) <= __fls(m)); \ + } while (0) + +#define __vcpu_get_flag(v, flagset, f, m) \ + ({ \ + __build_check_flag(v, flagset, f, m); \ + \ + v->arch.flagset & (m); \ + }) + +#define __vcpu_set_flag(v, flagset, f, m) \ + do { \ + typeof(v->arch.flagset) *fset; \ + \ + __build_check_flag(v, flagset, f, m); \ + \ + fset = &v->arch.flagset; \ + if (HWEIGHT(m) > 1) \ + *fset &= ~(m); \ + *fset |= (f); \ + } while (0) + +#define __vcpu_clear_flag(v, flagset, f, m) \ + do { \ + typeof(v->arch.flagset) *fset; \ + \ + __build_check_flag(v, flagset, f, m); \ + \ + fset = &v->arch.flagset; \ + *fset &= ~(m); \ + } while (0) + +#define vcpu_get_flag(v, ...) __vcpu_get_flag((v), __VA_ARGS__) +#define vcpu_set_flag(v, ...) __vcpu_set_flag((v), __VA_ARGS__) +#define vcpu_clear_flag(v, ...) __vcpu_clear_flag((v), __VA_ARGS__) + +/* SVE exposed to guest */ +#define GUEST_HAS_SVE __vcpu_single_flag(cflags, BIT(0)) +/* SVE config completed */ +#define VCPU_SVE_FINALIZED __vcpu_single_flag(cflags, BIT(1)) +/* PTRAUTH exposed to guest */ +#define GUEST_HAS_PTRAUTH __vcpu_single_flag(cflags, BIT(2)) + +/* Exception pending */ +#define PENDING_EXCEPTION __vcpu_single_flag(iflags, BIT(0)) +/* + * PC increment. Overlaps with EXCEPT_MASK on purpose so that it can't + * be set together with an exception... + */ +#define INCREMENT_PC __vcpu_single_flag(iflags, BIT(1)) +/* Target EL/MODE (not a single flag, but let's abuse the macro) */ +#define EXCEPT_MASK __vcpu_single_flag(iflags, GENMASK(3, 1)) + +/* Helpers to encode exceptions with minimum fuss */ +#define __EXCEPT_MASK_VAL unpack_vcpu_flag(EXCEPT_MASK) +#define __EXCEPT_SHIFT __builtin_ctzl(__EXCEPT_MASK_VAL) +#define __vcpu_except_flags(_f) iflags, (_f << __EXCEPT_SHIFT), __EXCEPT_MASK_VAL + +/* + * When PENDING_EXCEPTION is set, EXCEPT_MASK can take the following + * values: + * + * For AArch32 EL1: + */ +#define EXCEPT_AA32_UND __vcpu_except_flags(0) +#define EXCEPT_AA32_IABT __vcpu_except_flags(1) +#define EXCEPT_AA32_DABT __vcpu_except_flags(2) +/* For AArch64: */ +#define EXCEPT_AA64_EL1_SYNC __vcpu_except_flags(0) +#define EXCEPT_AA64_EL1_IRQ __vcpu_except_flags(1) +#define EXCEPT_AA64_EL1_FIQ __vcpu_except_flags(2) +#define EXCEPT_AA64_EL1_SERR __vcpu_except_flags(3) +/* For AArch64 with NV (one day): */ +#define EXCEPT_AA64_EL2_SYNC __vcpu_except_flags(4) +#define EXCEPT_AA64_EL2_IRQ __vcpu_except_flags(5) +#define EXCEPT_AA64_EL2_FIQ __vcpu_except_flags(6) +#define EXCEPT_AA64_EL2_SERR __vcpu_except_flags(7) +/* Guest debug is live */ +#define DEBUG_DIRTY __vcpu_single_flag(iflags, BIT(4)) +/* Save SPE context if active */ +#define DEBUG_STATE_SAVE_SPE __vcpu_single_flag(iflags, BIT(5)) +/* Save TRBE context if active */ +#define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6)) + +/* SVE enabled for host EL0 */ +#define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) +/* SME enabled for EL0 */ +#define HOST_SME_ENABLED __vcpu_single_flag(sflags, BIT(1)) +/* Physical CPU not in supported_cpus */ +#define ON_UNSUPPORTED_CPU __vcpu_single_flag(sflags, BIT(2)) +/* WFIT instruction trapped */ +#define IN_WFIT __vcpu_single_flag(sflags, BIT(3)) +/* vcpu system registers loaded on physical CPU */ +#define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(4)) +/* Software step state is Active-pending */ +#define DBG_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(5)) + + /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) + \ sve_ffr_offset((vcpu)->arch.sve_max_vl)) @@ -407,59 +560,32 @@ struct kvm_vcpu_arch { __size_ret; \ }) -/* vcpu_arch flags field values: */ -#define KVM_ARM64_DEBUG_DIRTY (1 << 0) -#define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */ -#define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */ -#define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */ -#define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */ -#define KVM_ARM64_GUEST_HAS_SVE (1 << 5) /* SVE exposed to guest */ -#define KVM_ARM64_VCPU_SVE_FINALIZED (1 << 6) /* SVE config completed */ -#define KVM_ARM64_GUEST_HAS_PTRAUTH (1 << 7) /* PTRAUTH exposed to guest */ -#define KVM_ARM64_PENDING_EXCEPTION (1 << 8) /* Exception pending */ -#define KVM_ARM64_EXCEPT_MASK (7 << 9) /* Target EL/MODE */ -#define KVM_ARM64_DEBUG_STATE_SAVE_SPE (1 << 12) /* Save SPE context if active */ -#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ - #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ KVM_GUESTDBG_USE_HW | \ KVM_GUESTDBG_SINGLESTEP) -/* - * When KVM_ARM64_PENDING_EXCEPTION is set, KVM_ARM64_EXCEPT_MASK can - * take the following values: - * - * For AArch32 EL1: - */ -#define KVM_ARM64_EXCEPT_AA32_UND (0 << 9) -#define KVM_ARM64_EXCEPT_AA32_IABT (1 << 9) -#define KVM_ARM64_EXCEPT_AA32_DABT (2 << 9) -/* For AArch64: */ -#define KVM_ARM64_EXCEPT_AA64_ELx_SYNC (0 << 9) -#define KVM_ARM64_EXCEPT_AA64_ELx_IRQ (1 << 9) -#define KVM_ARM64_EXCEPT_AA64_ELx_FIQ (2 << 9) -#define KVM_ARM64_EXCEPT_AA64_ELx_SERR (3 << 9) -#define KVM_ARM64_EXCEPT_AA64_EL1 (0 << 11) -#define KVM_ARM64_EXCEPT_AA64_EL2 (1 << 11) - -/* - * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be - * set together with an exception... - */ -#define KVM_ARM64_INCREMENT_PC (1 << 9) /* Increment PC */ #define vcpu_has_sve(vcpu) (system_supports_sve() && \ - ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE)) + vcpu_get_flag(vcpu, GUEST_HAS_SVE)) #ifdef CONFIG_ARM64_PTR_AUTH #define vcpu_has_ptrauth(vcpu) \ ((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || \ cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && \ - (vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH) + vcpu_get_flag(vcpu, GUEST_HAS_PTRAUTH)) #else #define vcpu_has_ptrauth(vcpu) false #endif +#define vcpu_on_unsupported_cpu(vcpu) \ + vcpu_get_flag(vcpu, ON_UNSUPPORTED_CPU) + +#define vcpu_set_on_unsupported_cpu(vcpu) \ + vcpu_set_flag(vcpu, ON_UNSUPPORTED_CPU) + +#define vcpu_clear_on_unsupported_cpu(vcpu) \ + vcpu_clear_flag(vcpu, ON_UNSUPPORTED_CPU) + #define vcpu_gp_regs(v) (&(v)->arch.ctxt.regs) /* @@ -592,8 +718,6 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu); int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); @@ -606,6 +730,8 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); +#define vcpu_has_run_once(vcpu) !!rcu_access_pointer((vcpu)->pid) + #ifndef __KVM_NVHE_HYPERVISOR__ #define kvm_call_hyp_nvhe(f, ...) \ ({ \ @@ -663,10 +789,11 @@ int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); +int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); -void kvm_sys_reg_table_init(void); +int kvm_sys_reg_table_init(void); /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); @@ -675,8 +802,15 @@ unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); int kvm_handle_mmio_return(struct kvm_vcpu *vcpu); int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa); -int kvm_perf_init(void); -int kvm_perf_teardown(void); +/* + * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event, + * arrived in guest context. For arm64, any event that arrives while a vCPU is + * loaded is considered to be "in guest". + */ +static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) +{ + return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; +} long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); @@ -690,6 +824,12 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); +extern unsigned int kvm_arm_vmid_bits; +int kvm_arm_vmid_alloc_init(void); +void kvm_arm_vmid_alloc_free(void); +void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); +void kvm_arm_vmid_clear_active(void); + static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) { vcpu_arch->steal.base = GPA_INVALID; @@ -712,18 +852,26 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr(); } +static inline bool kvm_system_needs_idmapped_vectors(void) +{ + return cpus_have_const_cap(ARM64_SPECTRE_V3A); +} + void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} void kvm_arm_init_debug(void); void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); + +#define kvm_vcpu_os_lock_enabled(vcpu) \ + (!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & SYS_OSLSR_OSLK)) + int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, @@ -737,8 +885,10 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu); +void kvm_vcpu_unshare_task_fp(struct kvm_vcpu *vcpu); static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) { @@ -749,17 +899,9 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); -#ifdef CONFIG_KVM /* Avoid conflicts with core headers if CONFIG_KVM=n */ -static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) -{ - return kvm_arch_vcpu_run_map_fp(vcpu); -} - +#ifdef CONFIG_KVM void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u32 clr); - -void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu); -void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); #else static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} @@ -785,12 +927,15 @@ void kvm_init_protected_traps(struct kvm_vcpu *vcpu); int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature); bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); -#define kvm_arm_vcpu_sve_finalized(vcpu) \ - ((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED) +#define kvm_arm_vcpu_sve_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_SVE_FINALIZED) -#define kvm_has_mte(kvm) (system_supports_mte() && (kvm)->arch.mte_enabled) -#define kvm_vcpu_has_pmu(vcpu) \ - (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) +#define kvm_has_mte(kvm) \ + (system_supports_mte() && \ + test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags)) + +#define kvm_supports_32bit_el0() \ + (system_supports_32bit_el0() && \ + !static_branch_unlikely(&arm64_mismatched_32bit_el0)) int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM @@ -801,4 +946,7 @@ void __init kvm_hyp_reserve(void); static inline void kvm_hyp_reserve(void) { } #endif +void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu); +bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 5afd14ab15b9..aa7fa2a08f06 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -90,7 +90,6 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu); void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); -void __sve_save_state(void *sve_pffr, u32 *fpsr); void __sve_restore_state(void *sve_pffr, u32 *fpsr); #ifndef __KVM_NVHE_HYPERVISOR__ @@ -119,6 +118,7 @@ extern u64 kvm_nvhe_sym(id_aa64pfr0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64pfr1_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64isar0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64isar1_el1_sys_val); +extern u64 kvm_nvhe_sym(id_aa64isar2_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 02d378887743..7784081088e7 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -63,7 +63,7 @@ * specific registers encoded in the instructions). */ .macro kern_hyp_va reg -alternative_cb kvm_update_va_mask +alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask and \reg, \reg, #1 /* mask with va_mask */ ror \reg, \reg, #1 /* rotate to the first tag bit */ add \reg, \reg, #0 /* insert the low 12 bits of the tag */ @@ -97,7 +97,7 @@ alternative_cb_end hyp_pa \reg, \tmp /* Load kimage_voffset. */ -alternative_cb kvm_get_kimage_voffset +alternative_cb ARM64_ALWAYS_SYSTEM, kvm_get_kimage_voffset movz \tmp, #0 movk \tmp, #0, lsl #16 movk \tmp, #0, lsl #32 @@ -115,6 +115,7 @@ alternative_cb_end #include <asm/cache.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> +#include <asm/kvm_host.h> void kvm_update_va_mask(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); @@ -130,6 +131,7 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) "add %0, %0, #0\n" "add %0, %0, #0, lsl 12\n" "ror %0, %0, #63\n", + ARM64_ALWAYS_SYSTEM, kvm_update_va_mask) : "+r" (v)); return v; @@ -150,7 +152,12 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> +int kvm_share_hyp(void *from, void *to); +void kvm_unshare_hyp(void *from, void *to); int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot); +int __create_hyp_mappings(unsigned long start, unsigned long size, + unsigned long phys, enum kvm_pgtable_prot prot); +int hyp_alloc_private_va_range(size_t size, unsigned long *haddr); int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, void __iomem **haddr); @@ -264,7 +271,8 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu) u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0; baddr = mmu->pgd_phys; - vmid_field = (u64)READ_ONCE(vmid->vmid) << VTTBR_VMID_SHIFT; + vmid_field = atomic64_read(&vmid->id) << VTTBR_VMID_SHIFT; + vmid_field &= VTTBR_VMID_MASK(kvm_arm_vmid_bits); return kvm_phys_to_vttbr(baddr) | vmid_field | cnp; } diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 027783829584..3252eb50ecfe 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -13,12 +13,24 @@ #define KVM_PGTABLE_MAX_LEVELS 4U +/* + * The largest supported block sizes for KVM (no 52-bit PA support): + * - 4K (level 1): 1GB + * - 16K (level 2): 32MB + * - 64K (level 2): 512MB + */ +#ifdef CONFIG_ARM64_4K_PAGES +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1U +#else +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U +#endif + static inline u64 kvm_get_parange(u64 mmfr0) { u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, - ID_AA64MMFR0_PARANGE_SHIFT); - if (parange > ID_AA64MMFR0_PARANGE_MAX) - parange = ID_AA64MMFR0_PARANGE_MAX; + ID_AA64MMFR0_EL1_PARANGE_SHIFT); + if (parange > ID_AA64MMFR0_EL1_PARANGE_MAX) + parange = ID_AA64MMFR0_EL1_PARANGE_MAX; return parange; } @@ -58,11 +70,7 @@ static inline u64 kvm_granule_size(u32 level) static inline bool kvm_level_supports_block_mapping(u32 level) { - /* - * Reject invalid block mappings and don't bother with 4TB mappings for - * 52-bit PAs. - */ - return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1)); + return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL; } /** @@ -252,6 +260,27 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot); /** + * kvm_pgtable_hyp_unmap() - Remove a mapping from a hypervisor stage-1 page-table. + * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). + * @addr: Virtual address from which to remove the mapping. + * @size: Size of the mapping. + * + * The offset of @addr within a page is ignored, @size is rounded-up to + * the next page boundary and @phys is rounded-down to the previous page + * boundary. + * + * TLB invalidation is performed for each page-table entry cleared during the + * unmapping operation and the reference count for the page-table page + * containing the cleared entry is decremented, with unreferenced pages being + * freed. The unmapping operation will stop early if it encounters either an + * invalid page-table entry or a valid block mapping which maps beyond the range + * being unmapped. + * + * Return: Number of bytes unmapped, which may be 0. + */ +u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); + +/** * kvm_get_vtcr() - Helper to construct VTCR_EL2 * @mmfr0: Sanitized value of SYS_ID_AA64MMFR0_EL1 register. * @mmfr1: Sanitized value of SYS_ID_AA64MMFR1_EL1 register. @@ -270,8 +299,7 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift); /** * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table. * @pgt: Uninitialised page-table structure to initialise. - * @arch: Arch-specific KVM structure representing the guest virtual - * machine. + * @mmu: S2 MMU context for this S2 translation * @mm_ops: Memory management callbacks. * @flags: Stage-2 configuration flags. * @force_pte_cb: Function that returns true if page level mappings must @@ -279,13 +307,13 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift); * * Return: 0 on success, negative error code on failure. */ -int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_arch *arch, +int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops, enum kvm_pgtable_stage2_flags flags, kvm_pgtable_force_pte_cb_t force_pte_cb); -#define kvm_pgtable_stage2_init(pgt, arch, mm_ops) \ - __kvm_pgtable_stage2_init(pgt, arch, mm_ops, 0, NULL) +#define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \ + __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL) /** * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table. diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h new file mode 100644 index 000000000000..9f4ad2a8df59 --- /dev/null +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 - Google LLC + * Author: Quentin Perret <qperret@google.com> + */ +#ifndef __ARM64_KVM_PKVM_H__ +#define __ARM64_KVM_PKVM_H__ + +#include <linux/memblock.h> +#include <asm/kvm_pgtable.h> + +#define HYP_MEMBLOCK_REGIONS 128 + +extern struct memblock_region kvm_nvhe_sym(hyp_memory)[]; +extern unsigned int kvm_nvhe_sym(hyp_memblock_nr); + +static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages) +{ + unsigned long total = 0, i; + + /* Provision the worst case scenario */ + for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) { + nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE); + total += nr_pages; + } + + return total; +} + +static inline unsigned long __hyp_pgtable_total_pages(void) +{ + unsigned long res = 0, i; + + /* Cover all of memory with page-granularity */ + for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) { + struct memblock_region *reg = &kvm_nvhe_sym(hyp_memory)[i]; + res += __hyp_pgtable_max_pages(reg->size >> PAGE_SHIFT); + } + + return res; +} + +static inline unsigned long hyp_s1_pgtable_pages(void) +{ + unsigned long res; + + res = __hyp_pgtable_total_pages(); + + /* Allow 1 GiB for private mappings */ + res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); + + return res; +} + +static inline unsigned long host_s2_pgtable_pages(void) +{ + unsigned long res; + + /* + * Include an extra 16 pages to safely upper-bound the worst case of + * concatenated pgds. + */ + res = __hyp_pgtable_total_pages() + 16; + + /* Allow 1 GiB for MMIO mappings */ + res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); + + return res; +} + +#endif /* __ARM64_KVM_PKVM_H__ */ diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h index 8ac6ee77437c..87e10d9a635b 100644 --- a/arch/arm64/include/asm/kvm_ras.h +++ b/arch/arm64/include/asm/kvm_ras.h @@ -14,7 +14,7 @@ * Was this synchronous external abort a RAS notification? * Returns '0' for errors handled by some RAS subsystem, or -ENOENT. */ -static inline int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr) +static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr) { /* apei_claim_sea(NULL) expects to mask interrupts itself */ lockdep_assert_irqs_enabled(); diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index b77e9b3f5371..1436fa1cde24 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -39,28 +39,8 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \ bti c ; -/* - * Annotate a function as position independent, i.e., safe to be called before - * the kernel virtual mapping is activated. - */ -#define SYM_FUNC_START_PI(x) \ - SYM_FUNC_START_ALIAS(__pi_##x); \ - SYM_FUNC_START(x) - -#define SYM_FUNC_START_WEAK_PI(x) \ - SYM_FUNC_START_ALIAS(__pi_##x); \ - SYM_FUNC_START_WEAK(x) - -#define SYM_FUNC_START_WEAK_ALIAS_PI(x) \ - SYM_FUNC_START_ALIAS(__pi_##x); \ - SYM_START(x, SYM_L_WEAK, SYM_A_ALIGN) - -#define SYM_FUNC_END_PI(x) \ - SYM_FUNC_END(x); \ - SYM_FUNC_END_ALIAS(__pi_##x) - -#define SYM_FUNC_END_ALIAS_PI(x) \ - SYM_FUNC_END_ALIAS(x); \ - SYM_FUNC_END_ALIAS(__pi_##x) +#define SYM_TYPED_FUNC_START(name) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + bti c ; #endif diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index 5d10051c3e62..c503db8e73b0 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -13,16 +13,13 @@ #include <linux/jump_label.h> #include <linux/stringify.h> #include <asm/alternative.h> +#include <asm/alternative-macros.h> #include <asm/atomic_lse.h> #include <asm/cpucaps.h> -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) +static __always_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]); + return alternative_has_feature_likely(ARM64_HAS_LSE_ATOMICS); } #define __lse_ll_sc_body(op, ...) \ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 0af70d9abede..9dd08cd339c3 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -114,6 +114,14 @@ #define OVERFLOW_STACK_SIZE SZ_4K /* + * With the minimum frame size of [x29, x30], exactly half the combined + * sizes of the hyp and overflow stacks is the maximum size needed to + * save the unwinded stacktrace; plus an additional entry to delimit the + * end. + */ +#define NVHE_STACKTRACE_SIZE ((OVERFLOW_STACK_SIZE + PAGE_SIZE) / 2 + sizeof(long)) + +/* * Alignment of kernel segments (e.g. .text, .data). * * 4 KB granule: 16 level 3 entries, with contiguous bit @@ -174,7 +182,11 @@ #include <linux/types.h> #include <asm/bug.h> +#if VA_BITS > 48 extern u64 vabits_actual; +#else +#define vabits_actual ((u64)VA_BITS) +#endif extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ @@ -351,6 +363,11 @@ static inline void *phys_to_virt(phys_addr_t x) }) void dump_mem_limit(void); + +static inline bool defer_reserve_crashkernel(void) +{ + return IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32); +} #endif /* !ASSEMBLY */ /* @@ -364,6 +381,15 @@ void dump_mem_limit(void); # define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1) #endif +/* + * memory regions which marked with flag MEMBLOCK_NOMAP(for example, the memory + * of the EFI_UNUSABLE_MEMORY type) may divide a continuous memory block into + * multiple parts. As a result, the number of memory regions is large. + */ +#ifdef CONFIG_EFI +#define INIT_MEMBLOCK_MEMORY_REGIONS (INIT_MEMBLOCK_REGIONS * 8) +#endif + #include <asm-generic/memory_model.h> #endif /* __ASM_MEMORY_H */ diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index e3e28f7daf62..5966ee4a6154 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -35,30 +35,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) } #define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) -static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) -{ - pteval_t prot = 0; - - if (vm_flags & VM_ARM64_BTI) - prot |= PTE_GP; - - /* - * There are two conditions required for returning a Normal Tagged - * memory type: (1) the user requested it via PROT_MTE passed to - * mmap() or mprotect() and (2) the corresponding vma supports MTE. We - * register (1) as VM_MTE in the vma->vm_flags and (2) as - * VM_MTE_ALLOWED. Note that the latter can only be set during the - * mmap() call since mprotect() does not accept MAP_* flags. - * Checking for VM_MTE only is sufficient since arch_validate_flags() - * does not permit (VM_MTE & !VM_MTE_ALLOWED). - */ - if (vm_flags & VM_MTE) - prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED); - - return __pgprot(prot); -} -#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) - static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) { diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index e9c30859f80c..48f8466a4be9 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -15,6 +15,7 @@ #ifndef __ASSEMBLY__ #include <linux/refcount.h> +#include <asm/cpufeature.h> typedef struct { atomic64_t id; diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 6770667b34a3..d3f8b5df0c1f 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -60,8 +60,7 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in * physical memory, in which case it will be smaller. */ -extern u64 idmap_t0sz; -extern u64 idmap_ptrs_per_pgd; +extern int idmap_t0sz; /* * Ensure TCR.T0SZ is set to the provided value. @@ -106,13 +105,18 @@ static inline void cpu_uninstall_idmap(void) cpu_switch_mm(mm->pgd, mm); } -static inline void cpu_install_idmap(void) +static inline void __cpu_install_idmap(pgd_t *idmap) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); - cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); + cpu_switch_mm(lm_alias(idmap), &init_mm); +} + +static inline void cpu_install_idmap(void) +{ + __cpu_install_idmap(idmap_pg_dir); } /* @@ -143,7 +147,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgdp) +static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; @@ -164,9 +168,9 @@ static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgdp) ttbr1 |= TTBR_CNP_BIT; } - replace_phys = (void *)__pa_symbol(function_nocfi(idmap_cpu_replace_ttbr1)); + replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); - cpu_install_idmap(); + __cpu_install_idmap(idmap); replace_phys(ttbr1); cpu_uninstall_idmap(); } diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index 4e7fa2623896..18734fed3bdd 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -58,11 +58,20 @@ static inline bool is_forbidden_offset_for_adrp(void *place) } struct plt_entry get_plt_entry(u64 dst, void *pc); -bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b); -static inline bool plt_entry_is_initialized(const struct plt_entry *e) +static inline const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) { - return e->adrp || e->add || e->br; + const Elf_Shdr *s, *se; + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; + } + + return NULL; } #endif /* __ASM_MODULE_H */ diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h index a11ccadd47d2..094701ec5500 100644 --- a/arch/arm64/include/asm/module.lds.h +++ b/arch/arm64/include/asm/module.lds.h @@ -1,8 +1,8 @@ SECTIONS { #ifdef CONFIG_ARM64_MODULE_PLTS - .plt 0 (NOLOAD) : { BYTE(0) } - .init.plt 0 (NOLOAD) : { BYTE(0) } - .text.ftrace_trampoline 0 (NOLOAD) : { BYTE(0) } + .plt 0 : { BYTE(0) } + .init.plt 0 : { BYTE(0) } + .text.ftrace_trampoline 0 : { BYTE(0) } #endif #ifdef CONFIG_KASAN_SW_TAGS diff --git a/arch/arm64/include/asm/mte-def.h b/arch/arm64/include/asm/mte-def.h index 626d359b396e..14ee86b019c2 100644 --- a/arch/arm64/include/asm/mte-def.h +++ b/arch/arm64/include/asm/mte-def.h @@ -11,6 +11,7 @@ #define MTE_TAG_SHIFT 56 #define MTE_TAG_SIZE 4 #define MTE_TAG_MASK GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT) +#define MTE_PAGE_TAG_STORAGE (MTE_GRANULES_PER_PAGE * MTE_TAG_SIZE / 8) #define __MTE_PREAMBLE ARM64_ASM_PREAMBLE ".arch_extension memtag\n" diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index e4704a403237..9f79425fc65a 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -5,6 +5,8 @@ #ifndef __ASM_MTE_KASAN_H #define __ASM_MTE_KASAN_H +#include <asm/compiler.h> +#include <asm/cputype.h> #include <asm/mte-def.h> #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 075539f5f1c8..760c62f8e22f 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -11,7 +11,9 @@ #ifndef __ASSEMBLY__ #include <linux/bitfield.h> +#include <linux/kasan-enabled.h> #include <linux/page-flags.h> +#include <linux/sched.h> #include <linux/types.h> #include <asm/pgtable-types.h> @@ -40,11 +42,14 @@ void mte_sync_tags(pte_t old_pte, pte_t pte); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); +void mte_cpu_setup(void); void mte_suspend_enter(void); +void mte_suspend_exit(void); long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data); +size_t mte_probe_user_range(const char __user *uaddr, size_t size); #else /* CONFIG_ARM64_MTE */ @@ -69,6 +74,9 @@ static inline void mte_thread_switch(struct task_struct *next) static inline void mte_suspend_enter(void) { } +static inline void mte_suspend_exit(void) +{ +} static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg) { return 0; @@ -86,6 +94,26 @@ static inline int mte_ptrace_copy_tags(struct task_struct *child, #endif /* CONFIG_ARM64_MTE */ +static inline void mte_disable_tco_entry(struct task_struct *task) +{ + if (!system_supports_mte()) + return; + + /* + * Re-enable tag checking (TCO set on exception entry). This is only + * necessary if MTE is enabled in either the kernel or the userspace + * task in synchronous or asymmetric mode (SCTLR_EL1.TCF0 bit 0 is set + * for both). With MTE disabled in the kernel and disabled or + * asynchronous in userspace, tag check faults (including in uaccesses) + * are not reported, therefore there is no need to re-enable checking. + * This is beneficial on microarchitectures where re-enabling TCO is + * expensive. + */ + if (kasan_hw_tags_enabled() || + (task->thread.sctlr_user & (1UL << SCTLR_EL1_TCF0_SHIFT))) + asm volatile(SET_PSTATE_TCO(0)); +} + #ifdef CONFIG_KASAN_HW_TAGS /* Whether the MTE asynchronous mode is enabled. */ DECLARE_STATIC_KEY_FALSE(mte_async_or_asymm_mode); diff --git a/arch/arm64/include/asm/paravirt_api_clock.h b/arch/arm64/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..65ac7cee0dad --- /dev/null +++ b/arch/arm64/include/asm/paravirt_api_clock.h @@ -0,0 +1 @@ +#include <asm/paravirt.h> diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h index b33ca260e3c9..016eb6b46dc0 100644 --- a/arch/arm64/include/asm/pci.h +++ b/arch/arm64/include/asm/pci.h @@ -9,7 +9,6 @@ #include <asm/io.h> #define PCIBIOS_MIN_IO 0x1000 -#define PCIBIOS_MIN_MEM 0 /* * Set to 1 if the kernel should re-assign all PCI bus numbers @@ -18,21 +17,8 @@ (pci_has_flag(PCI_REASSIGN_ALL_BUS)) #define arch_can_pci_mmap_wc() 1 -#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1 -extern int isa_dma_bridge_buggy; - -#ifdef CONFIG_PCI -static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) -{ - /* no legacy IRQ on arm64 */ - return -ENODEV; -} - -static inline int pci_proc_domain(struct pci_bus *bus) -{ - return 1; -} -#endif /* CONFIG_PCI */ +/* Generic PCI */ +#include <asm-generic/pci.h> #endif /* __ASM_PCI_H */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 8f1661603b78..b9ba19dbdb69 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -10,6 +10,7 @@ #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/stack_pointer.h> +#include <asm/sysreg.h> static inline void set_my_cpu_offset(unsigned long off) { diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h index 4ef6f19331f9..3eaf462f5752 100644 --- a/arch/arm64/include/asm/perf_event.h +++ b/arch/arm64/include/asm/perf_event.h @@ -15,70 +15,70 @@ /* * Common architectural and microarchitectural event numbers. */ -#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x00 -#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL 0x01 -#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL 0x02 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x03 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x04 -#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL 0x05 -#define ARMV8_PMUV3_PERFCTR_LD_RETIRED 0x06 -#define ARMV8_PMUV3_PERFCTR_ST_RETIRED 0x07 -#define ARMV8_PMUV3_PERFCTR_INST_RETIRED 0x08 -#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN 0x09 -#define ARMV8_PMUV3_PERFCTR_EXC_RETURN 0x0A -#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED 0x0B -#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED 0x0C -#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED 0x0D -#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED 0x0E -#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED 0x0F -#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x10 -#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x11 -#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x12 -#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS 0x13 -#define ARMV8_PMUV3_PERFCTR_L1I_CACHE 0x14 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB 0x15 -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE 0x16 -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL 0x17 -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB 0x18 -#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS 0x19 -#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR 0x1A -#define ARMV8_PMUV3_PERFCTR_INST_SPEC 0x1B -#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED 0x1C -#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES 0x1D -#define ARMV8_PMUV3_PERFCTR_CHAIN 0x1E -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE 0x1F -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE 0x20 -#define ARMV8_PMUV3_PERFCTR_BR_RETIRED 0x21 -#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED 0x22 -#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND 0x23 -#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND 0x24 -#define ARMV8_PMUV3_PERFCTR_L1D_TLB 0x25 -#define ARMV8_PMUV3_PERFCTR_L1I_TLB 0x26 -#define ARMV8_PMUV3_PERFCTR_L2I_CACHE 0x27 -#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL 0x28 -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE 0x29 -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL 0x2A -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE 0x2B -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB 0x2C -#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL 0x2D -#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL 0x2E -#define ARMV8_PMUV3_PERFCTR_L2D_TLB 0x2F -#define ARMV8_PMUV3_PERFCTR_L2I_TLB 0x30 -#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS 0x31 -#define ARMV8_PMUV3_PERFCTR_LL_CACHE 0x32 -#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS 0x33 -#define ARMV8_PMUV3_PERFCTR_DTLB_WALK 0x34 -#define ARMV8_PMUV3_PERFCTR_ITLB_WALK 0x35 -#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD 0x36 -#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD 0x37 -#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD 0x38 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD 0x39 -#define ARMV8_PMUV3_PERFCTR_OP_RETIRED 0x3A -#define ARMV8_PMUV3_PERFCTR_OP_SPEC 0x3B -#define ARMV8_PMUV3_PERFCTR_STALL 0x3C -#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND 0x3D -#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND 0x3E -#define ARMV8_PMUV3_PERFCTR_STALL_SLOT 0x3F +#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x0000 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL 0x0001 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL 0x0002 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x0003 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x0004 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL 0x0005 +#define ARMV8_PMUV3_PERFCTR_LD_RETIRED 0x0006 +#define ARMV8_PMUV3_PERFCTR_ST_RETIRED 0x0007 +#define ARMV8_PMUV3_PERFCTR_INST_RETIRED 0x0008 +#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN 0x0009 +#define ARMV8_PMUV3_PERFCTR_EXC_RETURN 0x000A +#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED 0x000B +#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED 0x000C +#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED 0x000D +#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED 0x000E +#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED 0x000F +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x0010 +#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x0011 +#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x0012 +#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS 0x0013 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE 0x0014 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB 0x0015 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE 0x0016 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL 0x0017 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB 0x0018 +#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS 0x0019 +#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR 0x001A +#define ARMV8_PMUV3_PERFCTR_INST_SPEC 0x001B +#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED 0x001C +#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES 0x001D +#define ARMV8_PMUV3_PERFCTR_CHAIN 0x001E +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE 0x001F +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE 0x0020 +#define ARMV8_PMUV3_PERFCTR_BR_RETIRED 0x0021 +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED 0x0022 +#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND 0x0023 +#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND 0x0024 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB 0x0025 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB 0x0026 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE 0x0027 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL 0x0028 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE 0x0029 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL 0x002A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE 0x002B +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB 0x002C +#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL 0x002D +#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL 0x002E +#define ARMV8_PMUV3_PERFCTR_L2D_TLB 0x002F +#define ARMV8_PMUV3_PERFCTR_L2I_TLB 0x0030 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS 0x0031 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE 0x0032 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS 0x0033 +#define ARMV8_PMUV3_PERFCTR_DTLB_WALK 0x0034 +#define ARMV8_PMUV3_PERFCTR_ITLB_WALK 0x0035 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD 0x0036 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD 0x0037 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD 0x0038 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD 0x0039 +#define ARMV8_PMUV3_PERFCTR_OP_RETIRED 0x003A +#define ARMV8_PMUV3_PERFCTR_OP_SPEC 0x003B +#define ARMV8_PMUV3_PERFCTR_STALL 0x003C +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND 0x003D +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND 0x003E +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT 0x003F /* Statistical profiling extension microarchitectural events */ #define ARMV8_SPE_PERFCTR_SAMPLE_POP 0x4000 @@ -96,6 +96,20 @@ #define ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS 0x400A #define ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD 0x400B +/* Trace buffer events */ +#define ARMV8_PMUV3_PERFCTR_TRB_WRAP 0x400C +#define ARMV8_PMUV3_PERFCTR_TRB_TRIG 0x400E + +/* Trace unit events */ +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT0 0x4010 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT1 0x4011 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT2 0x4012 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT3 0x4013 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4 0x4018 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5 0x4019 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6 0x401A +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7 0x401B + /* additional latency from alignment events */ #define ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT 0x4020 #define ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT 0x4021 @@ -107,91 +121,91 @@ #define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR 0x4026 /* ARMv8 recommended implementation defined event types */ -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD 0x40 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR 0x41 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD 0x42 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR 0x43 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER 0x44 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER 0x45 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM 0x46 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN 0x47 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL 0x48 - -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD 0x4C -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR 0x4D -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD 0x4E -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR 0x4F -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD 0x50 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR 0x51 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD 0x52 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR 0x53 - -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM 0x56 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN 0x57 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL 0x58 - -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD 0x5C -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR 0x5D -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD 0x5E -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR 0x5F -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD 0x60 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR 0x61 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED 0x62 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED 0x63 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL 0x64 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH 0x65 -#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD 0x66 -#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR 0x67 -#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC 0x68 -#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC 0x69 -#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC 0x6A - -#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC 0x6C -#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC 0x6D -#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC 0x6E -#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC 0x6F -#define ARMV8_IMPDEF_PERFCTR_LD_SPEC 0x70 -#define ARMV8_IMPDEF_PERFCTR_ST_SPEC 0x71 -#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC 0x72 -#define ARMV8_IMPDEF_PERFCTR_DP_SPEC 0x73 -#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC 0x74 -#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC 0x75 -#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC 0x76 -#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC 0x77 -#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC 0x78 -#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC 0x79 -#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC 0x7A - -#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC 0x7C -#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC 0x7D -#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC 0x7E - -#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF 0x81 -#define ARMV8_IMPDEF_PERFCTR_EXC_SVC 0x82 -#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT 0x83 -#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT 0x84 - -#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ 0x86 -#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ 0x87 -#define ARMV8_IMPDEF_PERFCTR_EXC_SMC 0x88 - -#define ARMV8_IMPDEF_PERFCTR_EXC_HVC 0x8A -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT 0x8B -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT 0x8C -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER 0x8D -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ 0x8E -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ 0x8F -#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC 0x90 -#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC 0x91 - -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD 0xA0 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR 0xA1 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD 0xA2 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR 0xA3 - -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM 0xA6 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN 0xA7 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL 0xA8 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD 0x0040 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR 0x0041 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD 0x0042 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR 0x0043 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER 0x0044 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER 0x0045 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM 0x0046 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN 0x0047 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL 0x0048 + +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD 0x004C +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR 0x004D +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD 0x004E +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR 0x004F +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD 0x0050 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR 0x0051 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD 0x0052 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR 0x0053 + +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM 0x0056 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN 0x0057 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL 0x0058 + +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD 0x005C +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR 0x005D +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD 0x005E +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR 0x005F +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD 0x0060 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR 0x0061 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED 0x0062 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED 0x0063 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL 0x0064 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH 0x0065 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD 0x0066 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR 0x0067 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC 0x0068 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC 0x0069 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC 0x006A + +#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC 0x006C +#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC 0x006D +#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC 0x006E +#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC 0x006F +#define ARMV8_IMPDEF_PERFCTR_LD_SPEC 0x0070 +#define ARMV8_IMPDEF_PERFCTR_ST_SPEC 0x0071 +#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC 0x0072 +#define ARMV8_IMPDEF_PERFCTR_DP_SPEC 0x0073 +#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC 0x0074 +#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC 0x0075 +#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC 0x0076 +#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC 0x0077 +#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC 0x0078 +#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC 0x0079 +#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC 0x007A + +#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC 0x007C +#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC 0x007D +#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC 0x007E + +#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF 0x0081 +#define ARMV8_IMPDEF_PERFCTR_EXC_SVC 0x0082 +#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT 0x0083 +#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT 0x0084 + +#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ 0x0086 +#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ 0x0087 +#define ARMV8_IMPDEF_PERFCTR_EXC_SMC 0x0088 + +#define ARMV8_IMPDEF_PERFCTR_EXC_HVC 0x008A +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT 0x008B +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT 0x008C +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER 0x008D +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ 0x008E +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ 0x008F +#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC 0x0090 +#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC 0x0091 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD 0x00A0 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR 0x00A1 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD 0x00A2 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR 0x00A3 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM 0x00A6 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN 0x00A7 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL 0x00A8 /* * Per-CPU PMCR: config reg diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 40085e53f573..5ab8d163198f 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -49,7 +49,7 @@ #define PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2) #define PMD_SIZE (_AC(1, UL) << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -#define PTRS_PER_PMD PTRS_PER_PTE +#define PTRS_PER_PMD (1 << (PAGE_SHIFT - 3)) #endif /* @@ -59,7 +59,7 @@ #define PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1) #define PUD_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) -#define PTRS_PER_PUD PTRS_PER_PTE +#define PTRS_PER_PUD (1 << (PAGE_SHIFT - 3)) #endif /* @@ -273,16 +273,17 @@ #define TCR_NFD1 (UL(1) << 54) #define TCR_E0PD0 (UL(1) << 55) #define TCR_E0PD1 (UL(1) << 56) +#define TCR_TCMA0 (UL(1) << 57) +#define TCR_TCMA1 (UL(1) << 58) /* * TTBR. */ #ifdef CONFIG_ARM64_PA_BITS_52 /* - * This should be GENMASK_ULL(47, 2). * TTBR_ELx[1] is RES0 in this configuration. */ -#define TTBR_BADDR_MASK_52 (((UL(1) << 46) - 1) << 2) +#define TTBR_BADDR_MASK_52 GENMASK_ULL(47, 2) #endif #ifdef CONFIG_ARM64_VA_BITS_52 diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 7032f04c8ac6..9b165117a454 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -14,6 +14,7 @@ * Software defined PTE bits definition. */ #define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ +#define PTE_SWP_EXCLUSIVE (_AT(pteval_t, 1) << 2) /* only for swp ptes */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define PTE_DEVMAP (_AT(pteval_t, 1) << 57) @@ -88,24 +89,6 @@ extern bool arm64_use_ng_mappings; #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_READONLY -#define __P011 PAGE_READONLY -#define __P100 PAGE_EXECONLY -#define __P101 PAGE_READONLY_EXEC -#define __P110 PAGE_READONLY_EXEC -#define __P111 PAGE_READONLY_EXEC - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_EXECONLY -#define __S101 PAGE_READONLY_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC - #endif /* __ASSEMBLY__ */ #endif /* __ASM_PGTABLE_PROT_H */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index c4ba047a82d2..71a1af42f0e8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -33,6 +33,7 @@ #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> +#include <linux/page_table_check.h> #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE @@ -44,6 +45,12 @@ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline bool arch_thp_swp_supported(void) +{ + return !system_supports_mte(); +} +#define arch_thp_swp_supported arch_thp_swp_supported + /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page @@ -96,6 +103,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #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)) @@ -312,8 +320,8 @@ static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep, __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) +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); @@ -343,6 +351,13 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + page_table_check_pte_set(mm, addr, ptep, pte); + return __set_pte_at(mm, addr, ptep, pte); +} + /* * Huge pte definitions. */ @@ -402,6 +417,32 @@ static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } +#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return pte_val(pte) & PTE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); +} + +/* + * Select all bits except the pfn + */ +static inline pgprot_t pte_pgprot(pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); + + return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); +} + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/linux/pgtable.h @@ -438,6 +479,8 @@ static inline int pmd_trans_huge(pmd_t pmd) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_valid(pmd) pte_valid(pmd_pte(pmd)) +#define pmd_user(pmd) pte_user(pmd_pte(pmd)) +#define pmd_user_exec(pmd) pte_user_exec(pmd_pte(pmd)) #define pmd_cont(pmd) pte_cont(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) @@ -485,8 +528,19 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) -#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)) -#define set_pud_at(mm, addr, pudp, pud) set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)) +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + page_table_check_pmd_set(mm, addr, pmdp, pmd); + return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); +} + +static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + page_table_check_pud_set(mm, addr, pudp, pud); + return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); +} #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) @@ -535,7 +589,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) -#define pmd_leaf(pmd) pmd_sect(pmd) +#define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) @@ -625,8 +679,10 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) -#define pud_leaf(pud) pud_sect(pud) +#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) +#define pud_user(pud) pte_user(pud_pte(pud)) + static inline void set_pud(pud_t *pudp, pud_t pud) { @@ -799,6 +855,23 @@ static inline int pgd_devmap(pgd_t pgd) } #endif +#ifdef CONFIG_PAGE_TABLE_CHECK +static inline bool pte_user_accessible_page(pte_t pte) +{ + return pte_present(pte) && (pte_user(pte) || pte_user_exec(pte)); +} + +static inline bool pmd_user_accessible_page(pmd_t pmd) +{ + return pmd_present(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); +} + +static inline bool pud_user_accessible_page(pud_t pud) +{ + return pud_present(pud) && pud_user(pud); +} +#endif + /* * Atomic pte/pmd modifications. */ @@ -860,7 +933,11 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { - return __pte(xchg_relaxed(&pte_val(*ptep), 0)); + pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); + + page_table_check_pte_clear(mm, address, pte); + + return pte; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -868,7 +945,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp)); + pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); + + page_table_check_pmd_clear(mm, address, pmd); + + return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -902,6 +983,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { + page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif @@ -909,12 +991,13 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) - * bits 2-7: swap type + * bits 2: remember PG_anon_exclusive + * bits 3-7: swap type * bits 8-57: swap offset * bit 58: PTE_PROT_NONE (must be zero) */ -#define __SWP_TYPE_SHIFT 2 -#define __SWP_TYPE_BITS 6 +#define __SWP_TYPE_SHIFT 3 +#define __SWP_TYPE_BITS 5 #define __SWP_OFFSET_BITS 50 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) @@ -964,10 +1047,10 @@ static inline void arch_swap_invalidate_area(int type) } #define __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct page *page) +static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { - if (system_supports_mte() && mte_restore_tags(entry, page)) - set_bit(PG_mte_tagged, &page->flags); + if (system_supports_mte() && mte_restore_tags(entry, &folio->page)) + set_bit(PG_mte_tagged, &folio->flags); } #endif /* CONFIG_ARM64_MTE */ @@ -999,34 +1082,13 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, * page after fork() + CoW for pfn mappings. We don't always have a * hardware-managed access flag on arm64. */ -static inline bool arch_faults_on_old_pte(void) -{ - WARN_ON(preemptible()); - - return !cpu_has_hw_af(); -} -#define arch_faults_on_old_pte arch_faults_on_old_pte +#define arch_has_hw_pte_young cpu_has_hw_af /* * Experimentally, it's cheap to set the access flag in hardware and we * benefit from prefaulting mappings as 'old' to start with. */ -static inline bool arch_wants_old_prefaulted_pte(void) -{ - return !arch_faults_on_old_pte(); -} -#define arch_wants_old_prefaulted_pte arch_wants_old_prefaulted_pte - -static inline pgprot_t arch_filter_pgprot(pgprot_t prot) -{ - if (cpus_have_const_cap(ARM64_HAS_EPAN)) - return prot; - - if (pgprot_val(prot) != pgprot_val(PAGE_EXECONLY)) - return prot; - - return PAGE_READONLY_EXEC; -} +#define arch_wants_old_prefaulted_pte cpu_has_hw_af static inline bool pud_sect_supported(void) { diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h index e83f0982b99c..0159b625cc7f 100644 --- a/arch/arm64/include/asm/preempt.h +++ b/arch/arm64/include/asm/preempt.h @@ -2,6 +2,7 @@ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H +#include <linux/jump_label.h> #include <linux/thread_info.h> #define PREEMPT_NEED_RESCHED BIT(32) @@ -80,10 +81,24 @@ static inline bool should_resched(int preempt_offset) } #ifdef CONFIG_PREEMPTION + void preempt_schedule(void); -#define __preempt_schedule() preempt_schedule() void preempt_schedule_notrace(void); -#define __preempt_schedule_notrace() preempt_schedule_notrace() + +#ifdef CONFIG_PREEMPT_DYNAMIC + +DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +void dynamic_preempt_schedule(void); +#define __preempt_schedule() dynamic_preempt_schedule() +void dynamic_preempt_schedule_notrace(void); +#define __preempt_schedule_notrace() dynamic_preempt_schedule_notrace() + +#else /* CONFIG_PREEMPT_DYNAMIC */ + +#define __preempt_schedule() preempt_schedule() +#define __preempt_schedule_notrace() preempt_schedule_notrace() + +#endif /* CONFIG_PREEMPT_DYNAMIC */ #endif /* CONFIG_PREEMPTION */ #endif /* __ASM_PREEMPT_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 6f41b65f9962..445aa3af3b76 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -21,6 +21,7 @@ #define MTE_CTRL_TCF_SYNC (1UL << 16) #define MTE_CTRL_TCF_ASYNC (1UL << 17) +#define MTE_CTRL_TCF_ASYMM (1UL << 18) #ifndef __ASSEMBLY__ @@ -91,8 +92,8 @@ #endif /* CONFIG_COMPAT */ #ifndef CONFIG_ARM64_FORCE_52BIT -#define arch_get_mmap_end(addr) ((addr > DEFAULT_MAP_WINDOW) ? TASK_SIZE :\ - DEFAULT_MAP_WINDOW) +#define arch_get_mmap_end(addr, len, flags) \ + (((addr) > DEFAULT_MAP_WINDOW) ? TASK_SIZE : DEFAULT_MAP_WINDOW) #define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \ base + TASK_SIZE - DEFAULT_MAP_WINDOW :\ @@ -117,6 +118,7 @@ struct debug_info { enum vec_type { ARM64_VEC_SVE = 0, + ARM64_VEC_SME, ARM64_VEC_MAX, }; @@ -152,6 +154,7 @@ struct thread_struct { unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ + void *za_state; /* ZA register, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ @@ -167,6 +170,8 @@ struct thread_struct { u64 mte_ctrl; #endif u64 sctlr_user; + u64 svcr; + u64 tpidr2_el0; }; static inline unsigned int thread_get_vl(struct thread_struct *thread, @@ -180,6 +185,19 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) return thread_get_vl(thread, ARM64_VEC_SVE); } +static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) +{ + return thread_get_vl(thread, ARM64_VEC_SME); +} + +static inline unsigned int thread_get_cur_vl(struct thread_struct *thread) +{ + if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK)) + return thread_get_sme_vl(thread); + else + return thread_get_sve_vl(thread); +} + unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); @@ -193,6 +211,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task) return task_get_vl(task, ARM64_VEC_SVE); } +static inline unsigned int task_get_sme_vl(const struct task_struct *task) +{ + return task_get_vl(task, ARM64_VEC_SME); +} + static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); @@ -249,8 +272,9 @@ void tls_preserve_current_state(void); static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) { + s32 previous_syscall = regs->syscallno; memset(regs, 0, sizeof(*regs)); - forget_syscall(regs); + regs->syscallno = previous_syscall; regs->pc = pc; if (system_uses_irq_prio_masking()) @@ -299,9 +323,6 @@ static inline bool is_ttbr1_addr(unsigned long addr) /* Forward declaration, a strange C thing */ struct task_struct; -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - unsigned long __get_wchan(struct task_struct *p); void update_sctlr_el1(u64 sctlr); @@ -353,9 +374,11 @@ extern void __init minsigstksz_setup(void); */ #include <asm/fpsimd.h> -/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ +/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() +#define SME_SET_VL(arg) sme_set_current_vl(arg) +#define SME_GET_VL() sme_get_current_vl() /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) @@ -380,13 +403,11 @@ long get_tagged_addr_ctrl(struct task_struct *task); * of header definitions for the use of task_stack_page. */ -#define current_top_of_stack() \ -({ \ - struct stack_info _info; \ - BUG_ON(!on_accessible_stack(current, current_stack_pointer, 1, &_info)); \ - _info.high; \ -}) -#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1, NULL)) +/* + * The top of the current task's task stack + */ +#define current_top_of_stack() ((unsigned long)current->stack + THREAD_SIZE) +#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1)) #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonce.h index 1bce62fa908a..56f7b1d4d54b 100644 --- a/arch/arm64/include/asm/rwonce.h +++ b/arch/arm64/include/asm/rwonce.h @@ -5,7 +5,7 @@ #ifndef __ASM_RWONCE_H #define __ASM_RWONCE_H -#ifdef CONFIG_LTO +#if defined(CONFIG_LTO) && !defined(__ASSEMBLY__) #include <linux/compiler_types.h> #include <asm/alternative-macros.h> @@ -66,7 +66,7 @@ }) #endif /* !BUILD_VDSO */ -#endif /* CONFIG_LTO */ +#endif /* CONFIG_LTO && !__ASSEMBLY__ */ #include <asm-generic/rwonce.h> diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h index 7bea1d705dd6..4292d9bafb9d 100644 --- a/arch/arm64/include/asm/sdei.h +++ b/arch/arm64/include/asm/sdei.h @@ -43,22 +43,5 @@ unsigned long do_sdei_event(struct pt_regs *regs, unsigned long sdei_arch_get_entry_point(int conduit); #define sdei_arch_get_entry_point(x) sdei_arch_get_entry_point(x) -struct stack_info; - -bool _on_sdei_stack(unsigned long sp, unsigned long size, - struct stack_info *info); -static inline bool on_sdei_stack(unsigned long sp, unsigned long size, - struct stack_info *info) -{ - if (!IS_ENABLED(CONFIG_VMAP_STACK)) - return false; - if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE)) - return false; - if (in_nmi()) - return _on_sdei_stack(sp, size, info); - - return false; -} - #endif /* __ASSEMBLY__ */ #endif /* __ASM_SDEI_H */ diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 152cb35bf9df..40971ac1303f 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -23,4 +23,9 @@ extern char __mmuoff_data_start[], __mmuoff_data_end[]; extern char __entry_tramp_text_start[], __entry_tramp_text_end[]; extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[]; +static inline size_t entry_tramp_text_size(void) +{ + return __entry_tramp_text_end - __entry_tramp_text_start; +} + #endif /* __ASM_SECTIONS_H */ diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h index 6437df661700..f4af547ef54c 100644 --- a/arch/arm64/include/asm/setup.h +++ b/arch/arm64/include/asm/setup.h @@ -3,6 +3,8 @@ #ifndef __ARM64_ASM_SETUP_H #define __ARM64_ASM_SETUP_H +#include <linux/string.h> + #include <uapi/asm/setup.h> void *get_early_fdt_ptr(void); @@ -14,4 +16,19 @@ void early_fdt_map(u64 dt_phys); extern phys_addr_t __fdt_pointer __initdata; extern u64 __cacheline_aligned boot_args[4]; +static inline bool arch_parse_debug_rodata(char *arg) +{ + extern bool rodata_enabled; + extern bool rodata_full; + + if (arg && !strcmp(arg, "full")) { + rodata_enabled = true; + rodata_full = true; + return true; + } + + return false; +} +#define arch_parse_debug_rodata arch_parse_debug_rodata + #endif diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index f62ca39da6c5..aa3d3607d5c8 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -67,7 +67,8 @@ struct bp_hardening_data { DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); -static inline void arm64_apply_bp_hardening(void) +/* Called during entry so must be __always_inline */ +static __always_inline void arm64_apply_bp_hardening(void) { struct bp_hardening_data *d; @@ -93,5 +94,9 @@ void spectre_v4_enable_task_mitigation(struct task_struct *tsk); enum mitigation_state arm64_get_meltdown_state(void); +enum mitigation_state arm64_get_spectre_bhb_state(void); +bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope); +u8 spectre_bhb_loop_affected(int scope); +void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused); #endif /* __ASSEMBLY__ */ #endif /* __ASM_SPECTRE_H */ diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 18782f0c4721..11ab1c077697 100644 --- a/arch/arm64/include/asm/spinlock_types.h +++ b/arch/arm64/include/asm/spinlock_types.h @@ -5,7 +5,7 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) +#if !defined(__LINUX_SPINLOCK_TYPES_RAW_H) && !defined(__ASM_SPINLOCK_H) # error "please don't include this file directly" #endif diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index e77cdef9ca29..5a0edb064ea4 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -8,143 +8,100 @@ #include <linux/percpu.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> -#include <linux/types.h> #include <linux/llist.h> #include <asm/memory.h> +#include <asm/pointer_auth.h> #include <asm/ptrace.h> #include <asm/sdei.h> -enum stack_type { - STACK_TYPE_UNKNOWN, - STACK_TYPE_TASK, - STACK_TYPE_IRQ, - STACK_TYPE_OVERFLOW, - STACK_TYPE_SDEI_NORMAL, - STACK_TYPE_SDEI_CRITICAL, - __NR_STACK_TYPES -}; - -struct stack_info { - unsigned long low; - unsigned long high; - 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 lr 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. - * - * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance - * associated with the most recently encountered replacement lr - * value. - */ -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_KRETPROBES - struct llist_node *kr_cur; -#endif -}; +#include <asm/stacktrace/common.h> extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, const char *loglvl); DECLARE_PER_CPU(unsigned long *, irq_stack_ptr); -static inline bool on_stack(unsigned long sp, unsigned long size, - unsigned long low, unsigned long high, - enum stack_type type, struct stack_info *info) -{ - if (!low) - return false; - - if (sp < low || sp + size < sp || sp + size > high) - return false; - - if (info) { - info->low = low; - info->high = high; - info->type = type; - } - return true; -} - -static inline bool on_irq_stack(unsigned long sp, unsigned long size, - struct stack_info *info) +static inline struct stack_info stackinfo_get_irq(void) { unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr); unsigned long high = low + IRQ_STACK_SIZE; - return on_stack(sp, size, low, high, STACK_TYPE_IRQ, info); + return (struct stack_info) { + .low = low, + .high = high, + }; } -static inline bool on_task_stack(const struct task_struct *tsk, - unsigned long sp, unsigned long size, - struct stack_info *info) +static inline bool on_irq_stack(unsigned long sp, unsigned long size) +{ + struct stack_info info = stackinfo_get_irq(); + return stackinfo_on_stack(&info, sp, size); +} + +static inline struct stack_info stackinfo_get_task(const struct task_struct *tsk) { unsigned long low = (unsigned long)task_stack_page(tsk); unsigned long high = low + THREAD_SIZE; - return on_stack(sp, size, low, high, STACK_TYPE_TASK, info); + return (struct stack_info) { + .low = low, + .high = high, + }; +} + +static inline bool on_task_stack(const struct task_struct *tsk, + unsigned long sp, unsigned long size) +{ + struct stack_info info = stackinfo_get_task(tsk); + return stackinfo_on_stack(&info, sp, size); } #ifdef CONFIG_VMAP_STACK DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); -static inline bool on_overflow_stack(unsigned long sp, unsigned long size, - struct stack_info *info) +static inline struct stack_info stackinfo_get_overflow(void) { unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack); unsigned long high = low + OVERFLOW_STACK_SIZE; - return on_stack(sp, size, low, high, STACK_TYPE_OVERFLOW, info); + return (struct stack_info) { + .low = low, + .high = high, + }; } #else -static inline bool on_overflow_stack(unsigned long sp, unsigned long size, - struct stack_info *info) { return false; } +#define stackinfo_get_overflow() stackinfo_get_unknown() #endif +#if defined(CONFIG_ARM_SDE_INTERFACE) && defined(CONFIG_VMAP_STACK) +DECLARE_PER_CPU(unsigned long *, sdei_stack_normal_ptr); +DECLARE_PER_CPU(unsigned long *, sdei_stack_critical_ptr); -/* - * We can only safely access per-cpu stacks from current in a non-preemptible - * context. - */ -static inline bool on_accessible_stack(const struct task_struct *tsk, - unsigned long sp, unsigned long size, - struct stack_info *info) +static inline struct stack_info stackinfo_get_sdei_normal(void) +{ + unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); + unsigned long high = low + SDEI_STACK_SIZE; + + return (struct stack_info) { + .low = low, + .high = high, + }; +} + +static inline struct stack_info stackinfo_get_sdei_critical(void) { - if (info) - info->type = STACK_TYPE_UNKNOWN; - - if (on_task_stack(tsk, sp, size, info)) - return true; - if (tsk != current || preemptible()) - return false; - if (on_irq_stack(sp, size, info)) - return true; - if (on_overflow_stack(sp, size, info)) - return true; - if (on_sdei_stack(sp, size, info)) - return true; - - return false; + unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr); + unsigned long high = low + SDEI_STACK_SIZE; + + return (struct stack_info) { + .low = low, + .high = high, + }; } +#else +#define stackinfo_get_sdei_normal() stackinfo_get_unknown() +#define stackinfo_get_sdei_critical() stackinfo_get_unknown() +#endif #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h new file mode 100644 index 000000000000..508f734de46e --- /dev/null +++ b/arch/arm64/include/asm/stacktrace/common.h @@ -0,0 +1,176 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Common arm64 stack unwinder code. + * + * See: arch/arm64/kernel/stacktrace.c for the reference implementation. + * + * Copyright (C) 2012 ARM Ltd. + */ +#ifndef __ASM_STACKTRACE_COMMON_H +#define __ASM_STACKTRACE_COMMON_H + +#include <linux/kprobes.h> +#include <linux/types.h> + +struct stack_info { + unsigned long low; + unsigned long high; +}; + +/** + * struct unwind_state - state used for robust unwinding. + * + * @fp: The fp value in the frame record (or the real fp) + * @pc: The lr value in the frame record (or the real lr) + * + * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance + * associated with the most recently encountered replacement lr + * value. + * + * @task: The task being unwound. + * + * @stack: The stack currently being unwound. + * @stacks: An array of stacks which can be unwound. + * @nr_stacks: The number of stacks in @stacks. + */ +struct unwind_state { + unsigned long fp; + unsigned long pc; +#ifdef CONFIG_KRETPROBES + struct llist_node *kr_cur; +#endif + struct task_struct *task; + + struct stack_info stack; + struct stack_info *stacks; + int nr_stacks; +}; + +static inline struct stack_info stackinfo_get_unknown(void) +{ + return (struct stack_info) { + .low = 0, + .high = 0, + }; +} + +static inline bool stackinfo_on_stack(const struct stack_info *info, + unsigned long sp, unsigned long size) +{ + if (!info->low) + return false; + + if (sp < info->low || sp + size < sp || sp + size > info->high) + return false; + + return true; +} + +static inline void unwind_init_common(struct unwind_state *state, + struct task_struct *task) +{ + state->task = task; +#ifdef CONFIG_KRETPROBES + state->kr_cur = NULL; +#endif + + state->stack = stackinfo_get_unknown(); +} + +static struct stack_info *unwind_find_next_stack(const struct unwind_state *state, + unsigned long sp, + unsigned long size) +{ + for (int i = 0; i < state->nr_stacks; i++) { + struct stack_info *info = &state->stacks[i]; + + if (stackinfo_on_stack(info, sp, size)) + return info; + } + + return NULL; +} + +/** + * unwind_consume_stack() - Check if an object is on an accessible stack, + * updating stack boundaries so that future unwind steps cannot consume this + * object again. + * + * @state: the current unwind state. + * @sp: the base address of the object. + * @size: the size of the object. + * + * Return: 0 upon success, an error code otherwise. + */ +static inline int unwind_consume_stack(struct unwind_state *state, + unsigned long sp, + unsigned long size) +{ + struct stack_info *next; + + if (stackinfo_on_stack(&state->stack, sp, size)) + goto found; + + next = unwind_find_next_stack(state, sp, size); + if (!next) + return -EINVAL; + + /* + * Stack transitions are strictly one-way, and once we've + * transitioned from one stack to another, it's never valid to + * unwind back to the old stack. + * + * Remove the current stack from the list of stacks so that it cannot + * be found on a subsequent transition. + * + * Note that stacks can nest in several valid orders, e.g. + * + * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL + * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW + * HYP -> OVERFLOW + * + * ... so we do not check the specific order of stack + * transitions. + */ + state->stack = *next; + *next = stackinfo_get_unknown(); + +found: + /* + * Future unwind steps can only consume stack above this frame record. + * Update the current stack to start immediately above it. + */ + state->stack.low = sp + size; + return 0; +} + +/** + * unwind_next_frame_record() - Unwind to the next frame record. + * + * @state: the current unwind state. + * + * Return: 0 upon success, an error code otherwise. + */ +static inline int +unwind_next_frame_record(struct unwind_state *state) +{ + unsigned long fp = state->fp; + int err; + + if (fp & 0x7) + return -EINVAL; + + err = unwind_consume_stack(state, fp, 16); + if (err) + return err; + + /* + * Record this frame record's values. + */ + state->fp = READ_ONCE(*(unsigned long *)(fp)); + state->pc = READ_ONCE(*(unsigned long *)(fp + 8)); + + return 0; +} + +#endif /* __ASM_STACKTRACE_COMMON_H */ diff --git a/arch/arm64/include/asm/stacktrace/nvhe.h b/arch/arm64/include/asm/stacktrace/nvhe.h new file mode 100644 index 000000000000..25ab83a315a7 --- /dev/null +++ b/arch/arm64/include/asm/stacktrace/nvhe.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * KVM nVHE hypervisor stack tracing support. + * + * The unwinder implementation depends on the nVHE mode: + * + * 1) Non-protected nVHE mode - the host can directly access the + * HYP stack pages and unwind the HYP stack in EL1. This saves having + * to allocate shared buffers for the host to read the unwinded + * stacktrace. + * + * 2) pKVM (protected nVHE) mode - the host cannot directly access + * the HYP memory. The stack is unwinded in EL2 and dumped to a shared + * buffer where the host can read and print the stacktrace. + * + * Copyright (C) 2022 Google LLC + */ +#ifndef __ASM_STACKTRACE_NVHE_H +#define __ASM_STACKTRACE_NVHE_H + +#include <asm/stacktrace/common.h> + +/** + * kvm_nvhe_unwind_init() - Start an unwind from the given nVHE HYP fp and pc + * + * @state : unwind_state to initialize + * @fp : frame pointer at which to start the unwinding. + * @pc : program counter at which to start the unwinding. + */ +static inline void kvm_nvhe_unwind_init(struct unwind_state *state, + unsigned long fp, + unsigned long pc) +{ + unwind_init_common(state, NULL); + + state->fp = fp; + state->pc = pc; +} + +#ifndef __KVM_NVHE_HYPERVISOR__ +/* + * Conventional (non-protected) nVHE HYP stack unwinder + * + * In non-protected mode, the unwinding is done from kernel proper context + * (by the host in EL1). + */ + +DECLARE_KVM_NVHE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); +DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_stacktrace_info, kvm_stacktrace_info); +DECLARE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); + +void kvm_nvhe_dump_backtrace(unsigned long hyp_offset); + +#endif /* __KVM_NVHE_HYPERVISOR__ */ +#endif /* __ASM_STACKTRACE_NVHE_H */ diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index fe341a6578c3..c8dca8ae359c 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -11,13 +11,6 @@ #include <linux/pgtable.h> /* - * PGDIR_SHIFT determines the size a top-level page table entry can map - * and depends on the number of levels in the page table. Compute the - * PGDIR_SHIFT for a given number of levels. - */ -#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls)) - -/* * The hardware supports concatenation of up to 16 tables at stage2 entry * level and we use the feature whenever possible, which means we resolve 4 * additional bits of address at the entry level. @@ -30,11 +23,6 @@ #define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4) #define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr) -/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */ -#define stage2_pgdir_shift(kvm) pt_levels_pgdir_shift(kvm_stage2_levels(kvm)) -#define stage2_pgdir_size(kvm) (1ULL << stage2_pgdir_shift(kvm)) -#define stage2_pgdir_mask(kvm) ~(stage2_pgdir_size(kvm) - 1) - /* * kvm_mmmu_cache_min_pages() is the number of pages required to install * a stage-2 translation. We pre-allocate the entry level page table at @@ -42,12 +30,4 @@ */ #define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1) -static inline phys_addr_t -stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm); - - return (boundary - 1 < end - 1) ? boundary : end; -} - #endif /* __ARM64_S2_PGTABLE_H_ */ diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index 95f7686b728d..3a3264ff47b9 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -12,13 +12,11 @@ extern char *strrchr(const char *, int c); #define __HAVE_ARCH_STRCHR extern char *strchr(const char *, int c); -#ifndef CONFIG_KASAN_HW_TAGS #define __HAVE_ARCH_STRCMP extern int strcmp(const char *, const char *); #define __HAVE_ARCH_STRNCMP extern int strncmp(const char *, const char *, __kernel_size_t); -#endif #define __HAVE_ARCH_STRLEN extern __kernel_size_t strlen(const char *); diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index b383b4802a7b..d30217c21eff 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -8,7 +8,7 @@ #ifndef __ASM_SYSCALL_WRAPPER_H #define __ASM_SYSCALL_WRAPPER_H -struct pt_regs; +#include <asm/ptrace.h> #define SC_ARM64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 4704f5893458..7d301700d1a9 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -115,9 +115,21 @@ #define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2) /* + * Automatically generated definitions for system registers, the + * manual encodings below are in the process of being converted to + * come from here. The header relies on the definition of sys_reg() + * earlier in this file. + */ +#include "asm/sysreg-defs.h" + +/* * System registers, organised loosely by encoding but grouped together * where the architected name contains an index. e.g. ID_MMFR<n>_EL1. */ +#define SYS_SVCR_SMSTOP_SM_EL0 sys_reg(0, 3, 4, 2, 3) +#define SYS_SVCR_SMSTART_SM_EL0 sys_reg(0, 3, 4, 3, 3) +#define SYS_SVCR_SMSTOP_SMZA_EL0 sys_reg(0, 3, 4, 6, 3) + #define SYS_OSDTRRX_EL1 sys_reg(2, 0, 0, 0, 2) #define SYS_MDCCINT_EL1 sys_reg(2, 0, 0, 2, 0) #define SYS_MDSCR_EL1 sys_reg(2, 0, 0, 2, 2) @@ -128,8 +140,16 @@ #define SYS_DBGWVRn_EL1(n) sys_reg(2, 0, 0, n, 6) #define SYS_DBGWCRn_EL1(n) sys_reg(2, 0, 0, n, 7) #define SYS_MDRAR_EL1 sys_reg(2, 0, 1, 0, 0) + #define SYS_OSLAR_EL1 sys_reg(2, 0, 1, 0, 4) +#define SYS_OSLAR_OSLK BIT(0) + #define SYS_OSLSR_EL1 sys_reg(2, 0, 1, 1, 4) +#define SYS_OSLSR_OSLM_MASK (BIT(3) | BIT(0)) +#define SYS_OSLSR_OSLM_NI 0 +#define SYS_OSLSR_OSLM_IMPLEMENTED BIT(3) +#define SYS_OSLSR_OSLK BIT(1) + #define SYS_OSDLR_EL1 sys_reg(2, 0, 1, 3, 4) #define SYS_DBGPRCR_EL1 sys_reg(2, 0, 1, 4, 4) #define SYS_DBGCLAIMSET_EL1 sys_reg(2, 0, 7, 8, 6) @@ -170,35 +190,12 @@ #define SYS_MVFR1_EL1 sys_reg(3, 0, 0, 3, 1) #define SYS_MVFR2_EL1 sys_reg(3, 0, 0, 3, 2) -#define SYS_ID_AA64PFR0_EL1 sys_reg(3, 0, 0, 4, 0) -#define SYS_ID_AA64PFR1_EL1 sys_reg(3, 0, 0, 4, 1) -#define SYS_ID_AA64ZFR0_EL1 sys_reg(3, 0, 0, 4, 4) - -#define SYS_ID_AA64DFR0_EL1 sys_reg(3, 0, 0, 5, 0) -#define SYS_ID_AA64DFR1_EL1 sys_reg(3, 0, 0, 5, 1) - -#define SYS_ID_AA64AFR0_EL1 sys_reg(3, 0, 0, 5, 4) -#define SYS_ID_AA64AFR1_EL1 sys_reg(3, 0, 0, 5, 5) - -#define SYS_ID_AA64ISAR0_EL1 sys_reg(3, 0, 0, 6, 0) -#define SYS_ID_AA64ISAR1_EL1 sys_reg(3, 0, 0, 6, 1) -#define SYS_ID_AA64ISAR2_EL1 sys_reg(3, 0, 0, 6, 2) - -#define SYS_ID_AA64MMFR0_EL1 sys_reg(3, 0, 0, 7, 0) -#define SYS_ID_AA64MMFR1_EL1 sys_reg(3, 0, 0, 7, 1) -#define SYS_ID_AA64MMFR2_EL1 sys_reg(3, 0, 0, 7, 2) - -#define SYS_SCTLR_EL1 sys_reg(3, 0, 1, 0, 0) #define SYS_ACTLR_EL1 sys_reg(3, 0, 1, 0, 1) -#define SYS_CPACR_EL1 sys_reg(3, 0, 1, 0, 2) #define SYS_RGSR_EL1 sys_reg(3, 0, 1, 0, 5) #define SYS_GCR_EL1 sys_reg(3, 0, 1, 0, 6) -#define SYS_ZCR_EL1 sys_reg(3, 0, 1, 2, 0) #define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1) -#define SYS_TTBR0_EL1 sys_reg(3, 0, 2, 0, 0) -#define SYS_TTBR1_EL1 sys_reg(3, 0, 2, 0, 1) #define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2) #define SYS_APIAKEYLO_EL1 sys_reg(3, 0, 2, 1, 0) @@ -234,7 +231,6 @@ #define SYS_TFSR_EL1 sys_reg(3, 0, 5, 6, 0) #define SYS_TFSRE0_EL1 sys_reg(3, 0, 5, 6, 1) -#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(0) @@ -396,12 +392,6 @@ #define SYS_MAIR_EL1 sys_reg(3, 0, 10, 2, 0) #define SYS_AMAIR_EL1 sys_reg(3, 0, 10, 3, 0) -#define SYS_LORSA_EL1 sys_reg(3, 0, 10, 4, 0) -#define SYS_LOREA_EL1 sys_reg(3, 0, 10, 4, 1) -#define SYS_LORN_EL1 sys_reg(3, 0, 10, 4, 2) -#define SYS_LORC_EL1 sys_reg(3, 0, 10, 4, 3) -#define SYS_LORID_EL1 sys_reg(3, 0, 10, 4, 7) - #define SYS_VBAR_EL1 sys_reg(3, 0, 12, 0, 0) #define SYS_DISR_EL1 sys_reg(3, 0, 12, 1, 1) @@ -433,23 +423,11 @@ #define SYS_ICC_IGRPEN0_EL1 sys_reg(3, 0, 12, 12, 6) #define SYS_ICC_IGRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) -#define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1) -#define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4) - -#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7) - #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) -#define SYS_CLIDR_EL1 sys_reg(3, 1, 0, 0, 1) -#define SYS_GMID_EL1 sys_reg(3, 1, 0, 0, 4) #define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) -#define SYS_CSSELR_EL1 sys_reg(3, 2, 0, 0, 0) - -#define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1) -#define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7) - #define SYS_RNDR_EL0 sys_reg(3, 3, 2, 4, 0) #define SYS_RNDRRS_EL0 sys_reg(3, 3, 2, 4, 1) @@ -469,6 +447,7 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_TPIDR2_EL0 sys_reg(3, 3, 13, 0, 5) #define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) @@ -536,9 +515,7 @@ #define SYS_HFGRTR_EL2 sys_reg(3, 4, 1, 1, 4) #define SYS_HFGWTR_EL2 sys_reg(3, 4, 1, 1, 5) #define SYS_HFGITR_EL2 sys_reg(3, 4, 1, 1, 6) -#define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0) #define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) -#define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0) #define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) #define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) @@ -549,7 +526,6 @@ #define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3) #define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0) #define SYS_TFSR_EL2 sys_reg(3, 4, 5, 6, 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) @@ -595,8 +571,6 @@ /* 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) @@ -606,11 +580,9 @@ #define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1) #define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0) #define SYS_TFSR_EL12 sys_reg(3, 5, 5, 6, 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) @@ -620,31 +592,30 @@ #define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2) /* Common SCTLR_ELx flags. */ +#define SCTLR_ELx_ENTP2 (BIT(60)) #define SCTLR_ELx_DSSBS (BIT(44)) #define SCTLR_ELx_ATA (BIT(43)) -#define SCTLR_ELx_TCF_SHIFT 40 -#define SCTLR_ELx_TCF_NONE (UL(0x0) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_SYNC (UL(0x1) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_ASYNC (UL(0x2) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_ASYMM (UL(0x3) << SCTLR_ELx_TCF_SHIFT) -#define SCTLR_ELx_TCF_MASK (UL(0x3) << SCTLR_ELx_TCF_SHIFT) - #define SCTLR_ELx_ENIA_SHIFT 31 -#define SCTLR_ELx_ITFSB (BIT(37)) -#define SCTLR_ELx_ENIA (BIT(SCTLR_ELx_ENIA_SHIFT)) -#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_ITFSB (BIT(37)) +#define SCTLR_ELx_ENIA (BIT(SCTLR_ELx_ENIA_SHIFT)) +#define SCTLR_ELx_ENIB (BIT(30)) +#define SCTLR_ELx_LSMAOE (BIT(29)) +#define SCTLR_ELx_nTLSMD (BIT(28)) +#define SCTLR_ELx_ENDA (BIT(27)) +#define SCTLR_ELx_EE (BIT(25)) +#define SCTLR_ELx_EIS (BIT(22)) +#define SCTLR_ELx_IESB (BIT(21)) +#define SCTLR_ELx_TSCXT (BIT(20)) +#define SCTLR_ELx_WXN (BIT(19)) +#define SCTLR_ELx_ENDB (BIT(13)) +#define SCTLR_ELx_I (BIT(12)) +#define SCTLR_ELx_EOS (BIT(11)) +#define SCTLR_ELx_SA (BIT(3)) +#define SCTLR_ELx_C (BIT(2)) +#define SCTLR_ELx_A (BIT(1)) +#define SCTLR_ELx_M (BIT(0)) /* SCTLR_EL2 specific flags. */ #define SCTLR_EL2_RES1 ((BIT(4)) | (BIT(5)) | (BIT(11)) | (BIT(16)) | \ @@ -666,34 +637,6 @@ (SCTLR_EL2_RES1 | ENDIAN_SET_EL2) /* SCTLR_EL1 specific flags. */ -#define SCTLR_EL1_EPAN (BIT(57)) -#define SCTLR_EL1_ATA0 (BIT(42)) - -#define SCTLR_EL1_TCF0_SHIFT 38 -#define SCTLR_EL1_TCF0_NONE (UL(0x0) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_SYNC (UL(0x1) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_ASYNC (UL(0x2) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_ASYMM (UL(0x3) << SCTLR_EL1_TCF0_SHIFT) -#define SCTLR_EL1_TCF0_MASK (UL(0x3) << SCTLR_EL1_TCF0_SHIFT) - -#define SCTLR_EL1_BT1 (BIT(36)) -#define SCTLR_EL1_BT0 (BIT(35)) -#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) #else @@ -701,13 +644,17 @@ #endif #define INIT_SCTLR_EL1_MMU_OFF \ - (ENDIAN_SET_EL1 | SCTLR_EL1_RES1) + (ENDIAN_SET_EL1 | SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | \ + SCTLR_EL1_EIS | SCTLR_EL1_TSCXT | SCTLR_EL1_EOS) #define INIT_SCTLR_EL1_MMU_ON \ - (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_EL1_SA0 | \ - SCTLR_EL1_SED | SCTLR_ELx_I | SCTLR_EL1_DZE | SCTLR_EL1_UCT | \ - SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \ - ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_EPAN | SCTLR_EL1_RES1) + (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | \ + SCTLR_EL1_SA0 | SCTLR_EL1_SED | SCTLR_ELx_I | \ + SCTLR_EL1_DZE | SCTLR_EL1_UCT | SCTLR_EL1_nTWE | \ + SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \ + ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_EPAN | \ + SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | SCTLR_EL1_EIS | \ + SCTLR_EL1_TSCXT | SCTLR_EL1_EOS) /* MAIR_ELx memory attributes (used by Linux) */ #define MAIR_ATTR_DEVICE_nGnRnE UL(0x00) @@ -720,244 +667,31 @@ /* Position the attr at the correct index */ #define MAIR_ATTRIDX(attr, idx) ((attr) << ((idx) * 8)) -/* id_aa64isar0 */ -#define ID_AA64ISAR0_RNDR_SHIFT 60 -#define ID_AA64ISAR0_TLB_SHIFT 56 -#define ID_AA64ISAR0_TS_SHIFT 52 -#define ID_AA64ISAR0_FHM_SHIFT 48 -#define ID_AA64ISAR0_DP_SHIFT 44 -#define ID_AA64ISAR0_SM4_SHIFT 40 -#define ID_AA64ISAR0_SM3_SHIFT 36 -#define ID_AA64ISAR0_SHA3_SHIFT 32 -#define ID_AA64ISAR0_RDM_SHIFT 28 -#define ID_AA64ISAR0_ATOMICS_SHIFT 20 -#define ID_AA64ISAR0_CRC32_SHIFT 16 -#define ID_AA64ISAR0_SHA2_SHIFT 12 -#define ID_AA64ISAR0_SHA1_SHIFT 8 -#define ID_AA64ISAR0_AES_SHIFT 4 - -#define ID_AA64ISAR0_TLB_RANGE_NI 0x0 -#define ID_AA64ISAR0_TLB_RANGE 0x2 - -/* id_aa64isar1 */ -#define ID_AA64ISAR1_I8MM_SHIFT 52 -#define ID_AA64ISAR1_DGH_SHIFT 48 -#define ID_AA64ISAR1_BF16_SHIFT 44 -#define ID_AA64ISAR1_SPECRES_SHIFT 40 -#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 -#define ID_AA64ISAR1_FCMA_SHIFT 16 -#define ID_AA64ISAR1_JSCVT_SHIFT 12 -#define ID_AA64ISAR1_API_SHIFT 8 -#define ID_AA64ISAR1_APA_SHIFT 4 -#define ID_AA64ISAR1_DPB_SHIFT 0 - -#define ID_AA64ISAR1_APA_NI 0x0 -#define ID_AA64ISAR1_APA_ARCHITECTED 0x1 -#define ID_AA64ISAR1_APA_ARCH_EPAC 0x2 -#define ID_AA64ISAR1_APA_ARCH_EPAC2 0x3 -#define ID_AA64ISAR1_APA_ARCH_EPAC2_FPAC 0x4 -#define ID_AA64ISAR1_APA_ARCH_EPAC2_FPAC_CMB 0x5 -#define ID_AA64ISAR1_API_NI 0x0 -#define ID_AA64ISAR1_API_IMP_DEF 0x1 -#define ID_AA64ISAR1_API_IMP_DEF_EPAC 0x2 -#define ID_AA64ISAR1_API_IMP_DEF_EPAC2 0x3 -#define ID_AA64ISAR1_API_IMP_DEF_EPAC2_FPAC 0x4 -#define ID_AA64ISAR1_API_IMP_DEF_EPAC2_FPAC_CMB 0x5 -#define ID_AA64ISAR1_GPA_NI 0x0 -#define ID_AA64ISAR1_GPA_ARCHITECTED 0x1 -#define ID_AA64ISAR1_GPI_NI 0x0 -#define ID_AA64ISAR1_GPI_IMP_DEF 0x1 - -/* id_aa64isar2 */ -#define ID_AA64ISAR2_RPRES_SHIFT 4 -#define ID_AA64ISAR2_WFXT_SHIFT 0 - -#define ID_AA64ISAR2_RPRES_8BIT 0x0 -#define ID_AA64ISAR2_RPRES_12BIT 0x1 -/* - * Value 0x1 has been removed from the architecture, and is - * reserved, but has not yet been removed from the ARM ARM - * as of ARM DDI 0487G.b. - */ -#define ID_AA64ISAR2_WFXT_NI 0x0 -#define ID_AA64ISAR2_WFXT_SUPPORTED 0x2 - /* id_aa64pfr0 */ -#define ID_AA64PFR0_CSV3_SHIFT 60 -#define ID_AA64PFR0_CSV2_SHIFT 56 -#define ID_AA64PFR0_DIT_SHIFT 48 -#define ID_AA64PFR0_AMU_SHIFT 44 -#define ID_AA64PFR0_MPAM_SHIFT 40 -#define ID_AA64PFR0_SEL2_SHIFT 36 -#define ID_AA64PFR0_SVE_SHIFT 32 -#define ID_AA64PFR0_RAS_SHIFT 28 -#define ID_AA64PFR0_GIC_SHIFT 24 -#define ID_AA64PFR0_ASIMD_SHIFT 20 -#define ID_AA64PFR0_FP_SHIFT 16 -#define ID_AA64PFR0_EL3_SHIFT 12 -#define ID_AA64PFR0_EL2_SHIFT 8 -#define ID_AA64PFR0_EL1_SHIFT 4 -#define ID_AA64PFR0_EL0_SHIFT 0 - -#define ID_AA64PFR0_AMU 0x1 -#define ID_AA64PFR0_SVE 0x1 -#define ID_AA64PFR0_RAS_V1 0x1 -#define ID_AA64PFR0_RAS_V1P1 0x2 -#define ID_AA64PFR0_FP_NI 0xf -#define ID_AA64PFR0_FP_SUPPORTED 0x0 -#define ID_AA64PFR0_ASIMD_NI 0xf -#define ID_AA64PFR0_ASIMD_SUPPORTED 0x0 -#define ID_AA64PFR0_ELx_64BIT_ONLY 0x1 -#define ID_AA64PFR0_ELx_32BIT_64BIT 0x2 - -/* id_aa64pfr1 */ -#define ID_AA64PFR1_MPAMFRAC_SHIFT 16 -#define ID_AA64PFR1_RASFRAC_SHIFT 12 -#define ID_AA64PFR1_MTE_SHIFT 8 -#define ID_AA64PFR1_SSBS_SHIFT 4 -#define ID_AA64PFR1_BT_SHIFT 0 - -#define ID_AA64PFR1_SSBS_PSTATE_NI 0 -#define ID_AA64PFR1_SSBS_PSTATE_ONLY 1 -#define ID_AA64PFR1_SSBS_PSTATE_INSNS 2 -#define ID_AA64PFR1_BT_BTI 0x1 - -#define ID_AA64PFR1_MTE_NI 0x0 -#define ID_AA64PFR1_MTE_EL0 0x1 -#define ID_AA64PFR1_MTE 0x2 -#define ID_AA64PFR1_MTE_ASYMM 0x3 - -/* id_aa64zfr0 */ -#define ID_AA64ZFR0_F64MM_SHIFT 56 -#define ID_AA64ZFR0_F32MM_SHIFT 52 -#define ID_AA64ZFR0_I8MM_SHIFT 44 -#define ID_AA64ZFR0_SM4_SHIFT 40 -#define ID_AA64ZFR0_SHA3_SHIFT 32 -#define ID_AA64ZFR0_BF16_SHIFT 20 -#define ID_AA64ZFR0_BITPERM_SHIFT 16 -#define ID_AA64ZFR0_AES_SHIFT 4 -#define ID_AA64ZFR0_SVEVER_SHIFT 0 - -#define ID_AA64ZFR0_F64MM 0x1 -#define ID_AA64ZFR0_F32MM 0x1 -#define ID_AA64ZFR0_I8MM 0x1 -#define ID_AA64ZFR0_BF16 0x1 -#define ID_AA64ZFR0_SM4 0x1 -#define ID_AA64ZFR0_SHA3 0x1 -#define ID_AA64ZFR0_BITPERM 0x1 -#define ID_AA64ZFR0_AES 0x1 -#define ID_AA64ZFR0_AES_PMULL 0x2 -#define ID_AA64ZFR0_SVEVER_SVE2 0x1 +#define ID_AA64PFR0_EL1_ELx_64BIT_ONLY 0x1 +#define ID_AA64PFR0_EL1_ELx_32BIT_64BIT 0x2 /* id_aa64mmfr0 */ -#define ID_AA64MMFR0_ECV_SHIFT 60 -#define ID_AA64MMFR0_FGT_SHIFT 56 -#define ID_AA64MMFR0_EXS_SHIFT 44 -#define ID_AA64MMFR0_TGRAN4_2_SHIFT 40 -#define ID_AA64MMFR0_TGRAN64_2_SHIFT 36 -#define ID_AA64MMFR0_TGRAN16_2_SHIFT 32 -#define ID_AA64MMFR0_TGRAN4_SHIFT 28 -#define ID_AA64MMFR0_TGRAN64_SHIFT 24 -#define ID_AA64MMFR0_TGRAN16_SHIFT 20 -#define ID_AA64MMFR0_BIGENDEL0_SHIFT 16 -#define ID_AA64MMFR0_SNSMEM_SHIFT 12 -#define ID_AA64MMFR0_BIGENDEL_SHIFT 8 -#define ID_AA64MMFR0_ASID_SHIFT 4 -#define ID_AA64MMFR0_PARANGE_SHIFT 0 - -#define ID_AA64MMFR0_ASID_8 0x0 -#define ID_AA64MMFR0_ASID_16 0x2 - -#define ID_AA64MMFR0_TGRAN4_NI 0xf -#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN 0x0 -#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX 0x7 -#define ID_AA64MMFR0_TGRAN64_NI 0xf -#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN 0x0 -#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX 0x7 -#define ID_AA64MMFR0_TGRAN16_NI 0x0 -#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN 0x1 -#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX 0xf - -#define ID_AA64MMFR0_PARANGE_32 0x0 -#define ID_AA64MMFR0_PARANGE_36 0x1 -#define ID_AA64MMFR0_PARANGE_40 0x2 -#define ID_AA64MMFR0_PARANGE_42 0x3 -#define ID_AA64MMFR0_PARANGE_44 0x4 -#define ID_AA64MMFR0_PARANGE_48 0x5 -#define ID_AA64MMFR0_PARANGE_52 0x6 +#define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN 0x1 +#define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX 0xf #define ARM64_MIN_PARANGE_BITS 32 -#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT 0x0 -#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE 0x1 -#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN 0x2 -#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX 0x7 +#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT 0x0 +#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE 0x1 +#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN 0x2 +#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX 0x7 #ifdef CONFIG_ARM64_PA_BITS_52 -#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_52 +#define ID_AA64MMFR0_EL1_PARANGE_MAX ID_AA64MMFR0_EL1_PARANGE_52 #else -#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_48 +#define ID_AA64MMFR0_EL1_PARANGE_MAX ID_AA64MMFR0_EL1_PARANGE_48 #endif -/* id_aa64mmfr1 */ -#define ID_AA64MMFR1_AFP_SHIFT 44 -#define ID_AA64MMFR1_ETS_SHIFT 36 -#define ID_AA64MMFR1_TWED_SHIFT 32 -#define ID_AA64MMFR1_XNX_SHIFT 28 -#define ID_AA64MMFR1_SPECSEI_SHIFT 24 -#define ID_AA64MMFR1_PAN_SHIFT 20 -#define ID_AA64MMFR1_LOR_SHIFT 16 -#define ID_AA64MMFR1_HPD_SHIFT 12 -#define ID_AA64MMFR1_VHE_SHIFT 8 -#define ID_AA64MMFR1_VMIDBITS_SHIFT 4 -#define ID_AA64MMFR1_HADBS_SHIFT 0 - -#define ID_AA64MMFR1_VMIDBITS_8 0 -#define ID_AA64MMFR1_VMIDBITS_16 2 - -/* id_aa64mmfr2 */ -#define ID_AA64MMFR2_E0PD_SHIFT 60 -#define ID_AA64MMFR2_EVT_SHIFT 56 -#define ID_AA64MMFR2_BBM_SHIFT 52 -#define ID_AA64MMFR2_TTL_SHIFT 48 -#define ID_AA64MMFR2_FWB_SHIFT 40 -#define ID_AA64MMFR2_IDS_SHIFT 36 -#define ID_AA64MMFR2_AT_SHIFT 32 -#define ID_AA64MMFR2_ST_SHIFT 28 -#define ID_AA64MMFR2_NV_SHIFT 24 -#define ID_AA64MMFR2_CCIDX_SHIFT 20 -#define ID_AA64MMFR2_LVA_SHIFT 16 -#define ID_AA64MMFR2_IESB_SHIFT 12 -#define ID_AA64MMFR2_LSM_SHIFT 8 -#define ID_AA64MMFR2_UAO_SHIFT 4 -#define ID_AA64MMFR2_CNP_SHIFT 0 - -/* id_aa64dfr0 */ -#define ID_AA64DFR0_MTPMU_SHIFT 48 -#define ID_AA64DFR0_TRBE_SHIFT 44 -#define ID_AA64DFR0_TRACE_FILT_SHIFT 40 -#define ID_AA64DFR0_DOUBLELOCK_SHIFT 36 -#define ID_AA64DFR0_PMSVER_SHIFT 32 -#define ID_AA64DFR0_CTX_CMPS_SHIFT 28 -#define ID_AA64DFR0_WRPS_SHIFT 20 -#define ID_AA64DFR0_BRPS_SHIFT 12 -#define ID_AA64DFR0_PMUVER_SHIFT 8 -#define ID_AA64DFR0_TRACEVER_SHIFT 4 -#define ID_AA64DFR0_DEBUGVER_SHIFT 0 - -#define ID_AA64DFR0_PMUVER_8_0 0x1 -#define ID_AA64DFR0_PMUVER_8_1 0x4 -#define ID_AA64DFR0_PMUVER_8_4 0x5 -#define ID_AA64DFR0_PMUVER_8_5 0x6 -#define ID_AA64DFR0_PMUVER_IMP_DEF 0xf - -#define ID_AA64DFR0_PMSVER_8_2 0x1 -#define ID_AA64DFR0_PMSVER_8_3 0x2 - #define ID_DFR0_PERFMON_SHIFT 24 #define ID_DFR0_PERFMON_8_0 0x3 @@ -1065,44 +799,33 @@ #define ID_PFR1_PROGMOD_SHIFT 0 #if defined(CONFIG_ARM64_4K_PAGES) -#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX -#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN4_2_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN4_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN +#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX +#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) -#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX -#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN16_2_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN16_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN +#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX +#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT #elif defined(CONFIG_ARM64_64K_PAGES) -#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN -#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX -#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN64_2_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN64_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN +#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX +#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN64_2_SHIFT #endif #define MVFR2_FPMISC_SHIFT 4 #define MVFR2_SIMDMISC_SHIFT 0 -#define DCZID_DZP_SHIFT 4 -#define DCZID_BS_SHIFT 0 +#define CPACR_EL1_FPEN_EL1EN (BIT(20)) /* enable EL1 access */ +#define CPACR_EL1_FPEN_EL0EN (BIT(21)) /* enable EL0 access, if EL1EN set */ -/* - * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which - * are reserved by the SVE architecture for future expansion of the LEN - * field, with compatible semantics. - */ -#define ZCR_ELx_LEN_SHIFT 0 -#define ZCR_ELx_LEN_SIZE 9 -#define ZCR_ELx_LEN_MASK 0x1ff +#define CPACR_EL1_SMEN_EL1EN (BIT(24)) /* enable EL1 access */ +#define CPACR_EL1_SMEN_EL0EN (BIT(25)) /* 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) - -/* TCR EL1 Bit Definitions */ -#define SYS_TCR_EL1_TCMA1 (BIT(58)) -#define SYS_TCR_EL1_TCMA0 (BIT(57)) /* GCR_EL1 Definitions */ #define SYS_GCR_EL1_RRND (BIT(16)) @@ -1129,8 +852,8 @@ #define SYS_RGSR_EL1_SEED_MASK 0xffffUL /* GMID_EL1 field definitions */ -#define SYS_GMID_EL1_BS_SHIFT 0 -#define SYS_GMID_EL1_BS_SIZE 4 +#define GMID_EL1_BS_SHIFT 0 +#define GMID_EL1_BS_SIZE 4 /* TFSR{,E0}_EL1 bit definitions */ #define SYS_TFSR_EL1_TF0_SHIFT 0 @@ -1142,6 +865,7 @@ #define SYS_MPIDR_SAFE_VAL (BIT(31)) #define TRFCR_ELx_TS_SHIFT 5 +#define TRFCR_ELx_TS_MASK ((0x3UL) << TRFCR_ELx_TS_SHIFT) #define TRFCR_ELx_TS_VIRTUAL ((0x1UL) << TRFCR_ELx_TS_SHIFT) #define TRFCR_ELx_TS_GUEST_PHYSICAL ((0x2UL) << TRFCR_ELx_TS_SHIFT) #define TRFCR_ELx_TS_PHYSICAL ((0x3UL) << TRFCR_ELx_TS_SHIFT) @@ -1149,7 +873,6 @@ #define TRFCR_ELx_ExTRE BIT(1) #define TRFCR_ELx_E0TRE BIT(0) - /* GIC Hypervisor interface registers */ /* ICH_MISR_EL2 bit definitions */ #define ICH_MISR_EOI (1 << 0) @@ -1212,6 +935,12 @@ #define ICH_VTR_TDS_SHIFT 19 #define ICH_VTR_TDS_MASK (1 << ICH_VTR_TDS_SHIFT) +/* HFG[WR]TR_EL2 bit definitions */ +#define HFGxTR_EL2_nTPIDR2_EL0_SHIFT 55 +#define HFGxTR_EL2_nTPIDR2_EL0_MASK BIT_MASK(HFGxTR_EL2_nTPIDR2_EL0_SHIFT) +#define HFGxTR_EL2_nSMPRI_EL1_SHIFT 54 +#define HFGxTR_EL2_nSMPRI_EL1_MASK BIT_MASK(HFGxTR_EL2_nSMPRI_EL1_SHIFT) + #define ARM64_FEATURE_FIELD_BITS 4 /* Create a mask for the feature bits of the specified feature. */ @@ -1229,6 +958,7 @@ #else +#include <linux/bitfield.h> #include <linux/build_bug.h> #include <linux/types.h> #include <asm/alternative.h> @@ -1322,6 +1052,15 @@ par; \ }) +#define SYS_FIELD_GET(reg, field, val) \ + FIELD_GET(reg##_##field##_MASK, val) + +#define SYS_FIELD_PREP(reg, field, val) \ + FIELD_PREP(reg##_##field##_MASK, val) + +#define SYS_FIELD_PREP_ENUM(reg, field, val) \ + FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val) + #endif #endif /* __ASM_SYSREG_H */ diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h index 305a7157c6a6..c34344256762 100644 --- a/arch/arm64/include/asm/system_misc.h +++ b/arch/arm64/include/asm/system_misc.h @@ -18,14 +18,14 @@ struct pt_regs; -void die(const char *msg, struct pt_regs *regs, int err); +void die(const char *msg, struct pt_regs *regs, long err); struct siginfo; void arm64_notify_die(const char *str, struct pt_regs *regs, int signo, int sicode, unsigned long far, - int err); + unsigned long err); -void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int, +void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned long, struct pt_regs *), int sig, int code, const char *name); diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index e1317b7c4525..848739c15de8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -82,6 +82,8 @@ int arch_dup_task_struct(struct task_struct *dst, #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_SME 27 /* SME in use */ +#define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index f386b90a79c8..9fab663dd2de 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -24,6 +24,10 @@ void update_freq_counters_refs(void); #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant +#ifdef CONFIG_ACPI_CPPC_LIB +#define arch_init_invariance_cppc topology_init_cpu_capacity_cppc +#endif + /* Replace task scheduler's default cpu-invariant accounting */ #define arch_scale_cpu_capacity topology_get_cpu_scale diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 54f32a0675df..6e5826470bea 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -24,7 +24,7 @@ struct undef_hook { void register_undef_hook(struct undef_hook *hook); void unregister_undef_hook(struct undef_hook *hook); -void force_signal_inject(int signal, int code, unsigned long address, unsigned int err); +void force_signal_inject(int signal, int code, unsigned long address, unsigned long err); void arm64_notify_segfault(unsigned long addr); void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str); void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str); @@ -57,7 +57,7 @@ static inline int in_entry_text(unsigned long ptr) * errors share the same encoding as an all-zeros encoding from a CPU that * doesn't support RAS. */ -static inline bool arm64_is_ras_serror(u32 esr) +static inline bool arm64_is_ras_serror(unsigned long esr) { WARN_ON(preemptible()); @@ -77,9 +77,9 @@ static inline bool arm64_is_ras_serror(u32 esr) * We treat them as Uncontainable. * Non-RAS SError's are reported as Uncontained/Uncategorized. */ -static inline u32 arm64_ras_serror_get_severity(u32 esr) +static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr) { - u32 aet = esr & ESR_ELx_AET; + unsigned long aet = esr & ESR_ELx_AET; if (!arm64_is_ras_serror(esr)) { /* Not a RAS error, we can't interpret the ESR. */ @@ -98,6 +98,6 @@ static inline u32 arm64_ras_serror_get_severity(u32 esr) return aet; } -bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr); -void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr); +bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr); +void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr); #endif diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 3a5ff5e20586..5c7b2f9d5913 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -26,7 +26,7 @@ #include <asm/memory.h> #include <asm/extable.h> -#define HAVE_GET_KERNEL_NOFAULT +static inline int __access_ok(const void __user *ptr, unsigned long size); /* * Test whether a block of memory is a valid user space address. @@ -35,10 +35,8 @@ * This is equivalent to the following test: * (u65)addr + (u65)size <= (u65)TASK_SIZE_MAX */ -static inline unsigned long __range_ok(const void __user *addr, unsigned long size) +static inline int access_ok(const void __user *addr, unsigned long size) { - unsigned long ret, limit = TASK_SIZE_MAX - 1; - /* * Asynchronous I/O running in a kernel thread does not have the * TIF_TAGGED_ADDR flag of the process owning the mm, so always untag @@ -48,28 +46,11 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si (current->flags & PF_KTHREAD || 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: - // 1: X = A + B; X' = X % 2^64 - " adds %0, %3, %2\n" - // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4 - " csel %1, xzr, %1, hi\n" - // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X' - // to compensate for the carry flag being set in step 4. For - // X > 2^64, X' merely has to remain nonzero, which it does. - " csinv %0, %0, xzr, cc\n" - // 4: For X < 2^64, this gives us X' - C - 1 <= 0, where the -1 - // comes from the carry in being clear. Otherwise, we are - // testing X' - C == 0, subject to the previous adjustments. - " sbcs xzr, %0, %1\n" - " cset %0, ls\n" - : "=&r" (ret), "+r" (limit) : "Ir" (size), "0" (addr) : "cc"); - - return ret; + return likely(__access_ok(addr, size)); } +#define access_ok access_ok -#define access_ok(addr, size) __range_ok(addr, size) +#include <asm-generic/access_ok.h> /* * User access enabling/disabling. @@ -222,9 +203,11 @@ static inline void uaccess_enable_privileged(void) } /* - * Sanitise a uaccess pointer such that it becomes NULL if above the maximum - * user address. In case the pointer is tagged (has the top byte set), untag - * the pointer before checking. + * Sanitize a uaccess pointer such that it cannot reach any kernel address. + * + * Clearing bit 55 ensures the pointer cannot address any portion of the TTBR1 + * address range (i.e. any kernel address), and either the pointer falls within + * the TTBR0 address range or must cause a fault. */ #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) static inline void __user *__uaccess_mask_ptr(const void __user *ptr) @@ -232,14 +215,12 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) void __user *safe_ptr; asm volatile( - " bics xzr, %3, %2\n" - " csel %0, %1, xzr, eq\n" - : "=&r" (safe_ptr) - : "r" (ptr), "r" (TASK_SIZE_MAX - 1), - "r" (untagged_addr(ptr)) - : "cc"); - - csdb(); + " bic %0, %1, %2\n" + : "=r" (safe_ptr) + : "r" (ptr), + "i" (BIT(55)) + ); + return safe_ptr; } @@ -251,34 +232,34 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) * The "__xxx_error" versions set the third argument to -EFAULT if an error * occurs, and leave it unchanged on success. */ -#define __get_mem_asm(load, reg, x, addr, err) \ +#define __get_mem_asm(load, reg, x, addr, err, type) \ asm volatile( \ "1: " load " " reg "1, [%2]\n" \ "2:\n" \ - _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 2b, %w0, %w1) \ + _ASM_EXTABLE_##type##ACCESS_ERR_ZERO(1b, 2b, %w0, %w1) \ : "+r" (err), "=&r" (x) \ : "r" (addr)) -#define __raw_get_mem(ldr, x, ptr, err) \ -do { \ - unsigned long __gu_val; \ - switch (sizeof(*(ptr))) { \ - case 1: \ - __get_mem_asm(ldr "b", "%w", __gu_val, (ptr), (err)); \ - break; \ - case 2: \ - __get_mem_asm(ldr "h", "%w", __gu_val, (ptr), (err)); \ - break; \ - case 4: \ - __get_mem_asm(ldr, "%w", __gu_val, (ptr), (err)); \ - break; \ - case 8: \ - __get_mem_asm(ldr, "%x", __gu_val, (ptr), (err)); \ - break; \ - default: \ - BUILD_BUG(); \ - } \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ +#define __raw_get_mem(ldr, x, ptr, err, type) \ +do { \ + unsigned long __gu_val; \ + switch (sizeof(*(ptr))) { \ + case 1: \ + __get_mem_asm(ldr "b", "%w", __gu_val, (ptr), (err), type); \ + break; \ + case 2: \ + __get_mem_asm(ldr "h", "%w", __gu_val, (ptr), (err), type); \ + break; \ + case 4: \ + __get_mem_asm(ldr, "%w", __gu_val, (ptr), (err), type); \ + break; \ + case 8: \ + __get_mem_asm(ldr, "%x", __gu_val, (ptr), (err), type); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) /* @@ -293,7 +274,7 @@ do { \ __chk_user_ptr(ptr); \ \ uaccess_ttbr0_enable(); \ - __raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err); \ + __raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err, U); \ uaccess_ttbr0_disable(); \ \ (x) = __rgu_val; \ @@ -333,40 +314,40 @@ do { \ \ __uaccess_enable_tco_async(); \ __raw_get_mem("ldr", *((type *)(__gkn_dst)), \ - (__force type *)(__gkn_src), __gkn_err); \ + (__force type *)(__gkn_src), __gkn_err, K); \ __uaccess_disable_tco_async(); \ \ if (unlikely(__gkn_err)) \ goto err_label; \ } while (0) -#define __put_mem_asm(store, reg, x, addr, err) \ +#define __put_mem_asm(store, reg, x, addr, err, type) \ asm volatile( \ "1: " store " " reg "1, [%2]\n" \ "2:\n" \ - _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0) \ + _ASM_EXTABLE_##type##ACCESS_ERR(1b, 2b, %w0) \ : "+r" (err) \ : "r" (x), "r" (addr)) -#define __raw_put_mem(str, x, ptr, err) \ -do { \ - __typeof__(*(ptr)) __pu_val = (x); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - __put_mem_asm(str "b", "%w", __pu_val, (ptr), (err)); \ - break; \ - case 2: \ - __put_mem_asm(str "h", "%w", __pu_val, (ptr), (err)); \ - break; \ - case 4: \ - __put_mem_asm(str, "%w", __pu_val, (ptr), (err)); \ - break; \ - case 8: \ - __put_mem_asm(str, "%x", __pu_val, (ptr), (err)); \ - break; \ - default: \ - BUILD_BUG(); \ - } \ +#define __raw_put_mem(str, x, ptr, err, type) \ +do { \ + __typeof__(*(ptr)) __pu_val = (x); \ + switch (sizeof(*(ptr))) { \ + case 1: \ + __put_mem_asm(str "b", "%w", __pu_val, (ptr), (err), type); \ + break; \ + case 2: \ + __put_mem_asm(str "h", "%w", __pu_val, (ptr), (err), type); \ + break; \ + case 4: \ + __put_mem_asm(str, "%w", __pu_val, (ptr), (err), type); \ + break; \ + case 8: \ + __put_mem_asm(str, "%x", __pu_val, (ptr), (err), type); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ } while (0) /* @@ -381,7 +362,7 @@ do { \ __chk_user_ptr(__rpu_ptr); \ \ uaccess_ttbr0_enable(); \ - __raw_put_mem("sttr", __rpu_val, __rpu_ptr, err); \ + __raw_put_mem("sttr", __rpu_val, __rpu_ptr, err, U); \ uaccess_ttbr0_disable(); \ } while (0) @@ -419,7 +400,7 @@ do { \ \ __uaccess_enable_tco_async(); \ __raw_put_mem("str", *((type *)(__pkn_src)), \ - (__force type *)(__pkn_dst), __pkn_err); \ + (__force type *)(__pkn_dst), __pkn_err, K); \ __uaccess_disable_tco_async(); \ \ if (unlikely(__pkn_err)) \ @@ -479,4 +460,19 @@ static inline int __copy_from_user_flushcache(void *dst, const void __user *src, } #endif +#ifdef CONFIG_ARCH_HAS_SUBPAGE_FAULTS + +/* + * Return 0 on success, the number of bytes not probed otherwise. + */ +static inline size_t probe_subpage_writeable(const char __user *uaddr, + size_t size) +{ + if (!system_supports_mte()) + return 0; + return mte_probe_user_range(uaddr, size); +} + +#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ + #endif /* __ASM_UACCESS_H */ diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 6bdb5f5db438..037feba03a51 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -3,6 +3,7 @@ * Copyright (C) 2012 ARM Ltd. */ #ifdef CONFIG_COMPAT +#define __ARCH_WANT_COMPAT_STAT #define __ARCH_WANT_COMPAT_STAT64 #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_PAUSE @@ -38,7 +39,7 @@ #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 450 +#define __NR_compat_syscalls 451 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 41ea1195e44b..604a2053d006 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -905,6 +905,8 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) /* * 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 f99dcb94b438..b4ae32109932 100644 --- a/arch/arm64/include/asm/vdso.h +++ b/arch/arm64/include/asm/vdso.h @@ -26,6 +26,9 @@ (void *)(vdso_offset_##name - VDSO_LBASE + (unsigned long)(base)); \ }) +extern char vdso_start[], vdso_end[]; +extern char vdso32_start[], vdso32_end[]; + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_H */ diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index 4f7a629df81f..764d13e2916c 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -7,8 +7,10 @@ #ifndef __ASSEMBLY__ +#include <asm/alternative.h> #include <asm/barrier.h> #include <asm/unistd.h> +#include <asm/sysreg.h> #define VDSO_HAS_CLOCK_GETRES 1 @@ -78,11 +80,20 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return 0; /* - * This isb() is required to prevent that the counter value + * If FEAT_ECV is available, use the self-synchronizing counter. + * Otherwise the isb is required to prevent that the counter value * is speculated. - */ - isb(); - asm volatile("mrs %0, cntvct_el0" : "=r" (res) :: "memory"); + */ + asm volatile( + ALTERNATIVE("isb\n" + "mrs %0, cntvct_el0", + "nop\n" + __mrs_s("%0", SYS_CNTVCTSS_EL0), + ARM64_HAS_ECV) + : "=r" (res) + : + : "memory"); + arch_counter_enforce_ordering(res); return res; diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h new file mode 100644 index 000000000000..bc9a2145f419 --- /dev/null +++ b/arch/arm64/include/asm/vectors.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 ARM Ltd. + */ +#ifndef __ASM_VECTORS_H +#define __ASM_VECTORS_H + +#include <linux/bug.h> +#include <linux/percpu.h> + +#include <asm/fixmap.h> + +extern char vectors[]; +extern char tramp_vectors[]; +extern char __bp_harden_el1_vectors[]; + +/* + * Note: the order of this enum corresponds to two arrays in entry.S: + * tramp_vecs and __bp_harden_el1_vectors. By default the canonical + * 'full fat' vectors are used directly. + */ +enum arm64_bp_harden_el1_vectors { +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + /* + * Perform the BHB loop mitigation, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_LOOP, + + /* + * Make the SMC call for firmware mitigation, before branching to the + * canonical vectors. + */ + EL1_VECTOR_BHB_FW, + + /* + * Use the ClearBHB instruction, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_CLEAR_INSN, +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + + /* + * Remap the kernel before branching to the canonical vectors. + */ + EL1_VECTOR_KPTI, +}; + +#ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +#define EL1_VECTOR_BHB_LOOP -1 +#define EL1_VECTOR_BHB_FW -1 +#define EL1_VECTOR_BHB_CLEAR_INSN -1 +#endif /* !CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + +/* The vectors to use on return from EL0. e.g. to remap the kernel */ +DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector); + +#ifndef CONFIG_UNMAP_KERNEL_AT_EL0 +#define TRAMP_VALIAS 0ul +#endif + +static inline const char * +arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot) +{ + if (arm64_kernel_unmapped_at_el0()) + return (char *)(TRAMP_VALIAS + SZ_2K * slot); + + WARN_ON_ONCE(slot == EL1_VECTOR_KPTI); + + return __bp_harden_el1_vectors + SZ_2K * slot; +} + +#endif /* __ASM_VECTORS_H */ diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 3c8af033a997..4eb601e7de50 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -36,9 +36,9 @@ #define HVC_RESET_VECTORS 2 /* - * HVC_VHE_RESTART - Upgrade the CPU from EL1 to EL2, if possible + * HVC_FINALISE_EL2 - Upgrade the CPU from EL1 to EL2, if possible */ -#define HVC_VHE_RESTART 3 +#define HVC_FINALISE_EL2 3 /* Max number of HYP stub hypercalls */ #define HVC_STUB_HCALL_NR 4 @@ -49,6 +49,13 @@ #define BOOT_CPU_MODE_EL1 (0xe11) #define BOOT_CPU_MODE_EL2 (0xe12) +/* + * Flags returned together with the boot mode, but not preserved in + * __boot_cpu_mode. Used by the idreg override code to work out the + * boot state. + */ +#define BOOT_CPU_FLAG_E2H BIT_ULL(32) + #ifndef __ASSEMBLY__ #include <asm/ptrace.h> @@ -113,6 +120,9 @@ static __always_inline bool has_vhe(void) /* * Code only run in VHE/NVHE hyp context can assume VHE is present or * absent. Otherwise fall back to caps. + * This allows the compiler to discard VHE-specific code from the + * nVHE object, reducing the number of external symbol references + * needed to link. */ if (is_vhe_hyp_code()) return true; diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h index b9185503feae..38fafffe699f 100644 --- a/arch/arm64/include/asm/vmalloc.h +++ b/arch/arm64/include/asm/vmalloc.h @@ -25,4 +25,10 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) #endif +#define arch_vmap_pgprot_tagged arch_vmap_pgprot_tagged +static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) +{ + return pgprot_tagged(prot); +} + #endif /* _ASM_ARM64_VMALLOC_H */ diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h index 894e031b28d2..20873099c035 100644 --- a/arch/arm64/include/asm/vmap_stack.h +++ b/arch/arm64/include/asm/vmap_stack.h @@ -17,10 +17,13 @@ */ static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node) { + void *p; + BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK)); - return __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node, + p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node, __builtin_return_address(0)); + return kasan_reset_tag(p); } #endif /* __ASM_VMAP_STACK_H */ diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/xen-ops.h index 27e984977402..7ebb7eb0bd93 100644 --- a/arch/arm64/include/asm/xen/page-coherent.h +++ b/arch/arm64/include/asm/xen/xen-ops.h @@ -1,2 +1,2 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#include <xen/arm/page-coherent.h> +#include <xen/arm/xen-ops.h> diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h index 947f6a4f1aa0..befcd8a7abc9 100644 --- a/arch/arm64/include/asm/xor.h +++ b/arch/arm64/include/asm/xor.h @@ -16,7 +16,8 @@ extern struct xor_block_template const xor_block_inner_neon; static void -xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_neon_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { kernel_neon_begin(); xor_block_inner_neon.do_2(bytes, p1, p2); @@ -24,8 +25,9 @@ xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_neon_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { kernel_neon_begin(); xor_block_inner_neon.do_3(bytes, p1, p2, p3); @@ -33,8 +35,10 @@ xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_neon_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { kernel_neon_begin(); xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4); @@ -42,8 +46,11 @@ xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_neon_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { kernel_neon_begin(); xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5); |