diff options
Diffstat (limited to 'arch/arm64/include/asm')
41 files changed, 1156 insertions, 388 deletions
diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h index ecdb3cfcd0f8..8babfbe31f95 100644 --- a/arch/arm64/include/asm/archrandom.h +++ b/arch/arm64/include/asm/archrandom.h @@ -129,6 +129,4 @@ static inline bool __init __early_cpu_has_rndr(void) return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf; } -u64 kaslr_early_init(void *fdt); - #endif /* _ASM_ARCHRANDOM_H */ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 513787e43329..ab8b396428da 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -38,10 +38,6 @@ msr daifset, #0xf .endm - .macro enable_daif - msr daifclr, #0xf - .endm - /* * Save/restore interrupts. */ @@ -346,20 +342,6 @@ 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 * @@ -590,18 +572,27 @@ alternative_endif .endm /* - * Offset ttbr1 to allow for 48-bit kernel VAs set with 52-bit PTRS_PER_PGD. + * If the kernel is built for 52-bit virtual addressing but the hardware only + * supports 48 bits, we cannot program the pgdir address into TTBR1 directly, + * but we have to add an offset so that the TTBR1 address corresponds with the + * pgdir entry that covers the lowest 48-bit addressable VA. + * + * Note that this trick is only used for LVA/64k pages - LPA2/4k pages uses an + * additional paging level, and on LPA2/16k pages, we would end up with a root + * level table with only 2 entries, which is suboptimal in terms of TLB + * utilization, so there we fall back to 47 bits of translation if LPA2 is not + * supported. + * * orr is used as it can cover the immediate value (and is idempotent). - * In future this may be nop'ed out when dealing with 52-bit kernel VAs. * ttbr: Value of ttbr to set, modified. */ .macro offset_ttbr1, ttbr, tmp -#ifdef CONFIG_ARM64_VA_BITS_52 - mrs_s \tmp, SYS_ID_AA64MMFR2_EL1 - and \tmp, \tmp, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT) - cbnz \tmp, .Lskipoffs_\@ - orr \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET -.Lskipoffs_\@ : +#if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2) + mrs \tmp, tcr_el1 + and \tmp, \tmp, #TCR_T1SZ_MASK + cmp \tmp, #TCR_T1SZ(VA_BITS_MIN) + orr \tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET + csel \ttbr, \tmp, \ttbr, eq #endif .endm @@ -623,25 +614,13 @@ alternative_endif .macro phys_to_pte, pte, phys #ifdef CONFIG_ARM64_PA_BITS_52 - /* - * We assume \phys is 64K aligned and this is guaranteed by only - * supporting this configuration with 64K pages. - */ - orr \pte, \phys, \phys, lsr #36 - and \pte, \pte, #PTE_ADDR_MASK + orr \pte, \phys, \phys, lsr #PTE_ADDR_HIGH_SHIFT + and \pte, \pte, #PHYS_TO_PTE_ADDR_MASK #else mov \pte, \phys #endif .endm - .macro pte_to_phys, phys, pte - and \phys, \pte, #PTE_ADDR_MASK -#ifdef CONFIG_ARM64_PA_BITS_52 - orr \phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT - and \phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT) -#endif - .endm - /* * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU. */ diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index 1abdcd508a11..beb42c62b6ac 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -11,6 +11,7 @@ * 0x004: for installing kprobes * 0x005: for installing uprobes * 0x006: for kprobe software single-step + * 0x007: for kretprobe return * Allowed values for kgdb are 0x400 - 0x7ff * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction @@ -23,6 +24,7 @@ #define KPROBES_BRK_IMM 0x004 #define UPROBES_BRK_IMM 0x005 #define KPROBES_BRK_SS_IMM 0x006 +#define KRETPROBES_BRK_IMM 0x007 #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index b1e43f56ee46..9b73fd0cd721 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -52,14 +52,18 @@ struct cpuinfo_arm64 { u64 reg_id_aa64isar0; u64 reg_id_aa64isar1; u64 reg_id_aa64isar2; + u64 reg_id_aa64isar3; u64 reg_id_aa64mmfr0; u64 reg_id_aa64mmfr1; u64 reg_id_aa64mmfr2; u64 reg_id_aa64mmfr3; + u64 reg_id_aa64mmfr4; u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; + u64 reg_id_aa64pfr2; u64 reg_id_aa64zfr0; u64 reg_id_aa64smfr0; + u64 reg_id_aa64fpfr0; struct cpuinfo_32bit aarch32; }; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index bd8d4ca81a48..8b904a757bd3 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -17,6 +17,7 @@ #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0 #define ARM64_SW_FEATURE_OVERRIDE_HVHE 4 +#define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8 #ifndef __ASSEMBLY__ @@ -363,6 +364,7 @@ struct arm64_cpu_capabilities { u8 field_pos; u8 field_width; u8 min_field_value; + u8 max_field_value; u8 hwcap_type; bool sign; unsigned long hwcap; @@ -768,6 +770,11 @@ static __always_inline bool system_supports_tpidr2(void) return system_supports_sme(); } +static __always_inline bool system_supports_fpmr(void) +{ + return alternative_has_cap_unlikely(ARM64_HAS_FPMR); +} + static __always_inline bool system_supports_cnp(void) { return alternative_has_cap_unlikely(ARM64_HAS_CNP); @@ -905,7 +912,9 @@ static inline unsigned int get_vmid_bits(u64 mmfr1) s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur); struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); +extern struct arm64_ftr_override id_aa64mmfr0_override; extern struct arm64_ftr_override id_aa64mmfr1_override; +extern struct arm64_ftr_override id_aa64mmfr2_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; @@ -915,9 +924,114 @@ extern struct arm64_ftr_override id_aa64isar2_override; extern struct arm64_ftr_override arm64_sw_feature_override; +static inline +u64 arm64_apply_feature_override(u64 val, int feat, int width, + const struct arm64_ftr_override *override) +{ + u64 oval = override->val; + + /* + * When it encounters an invalid override (e.g., an override that + * cannot be honoured due to a missing CPU feature), the early idreg + * override code will set the mask to 0x0 and the value to non-zero for + * the field in question. In order to determine whether the override is + * valid or not for the field we are interested in, we first need to + * disregard bits belonging to other fields. + */ + oval &= GENMASK_ULL(feat + width - 1, feat); + + /* + * The override is valid if all value bits are accounted for in the + * mask. If so, replace the masked bits with the override value. + */ + if (oval == (oval & override->mask)) { + val &= ~override->mask; + val |= oval; + } + + /* Extract the field from the updated value */ + return cpuid_feature_extract_unsigned_field(val, feat); +} + +static inline bool arm64_test_sw_feature_override(int feat) +{ + /* + * Software features are pseudo CPU features that have no underlying + * CPUID system register value to apply the override to. + */ + return arm64_apply_feature_override(0, feat, 4, + &arm64_sw_feature_override); +} + +static inline bool kaslr_disabled_cmdline(void) +{ + return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR); +} + u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); +static inline bool cpu_has_bti(void) +{ + if (!IS_ENABLED(CONFIG_ARM64_BTI)) + return false; + + return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1), + ID_AA64PFR1_EL1_BT_SHIFT, 4, + &id_aa64pfr1_override); +} + +static inline bool cpu_has_pac(void) +{ + u64 isar1, isar2; + + if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) + return false; + + isar1 = read_cpuid(ID_AA64ISAR1_EL1); + isar2 = read_cpuid(ID_AA64ISAR2_EL1); + + if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4, + &id_aa64isar1_override)) + return true; + + if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4, + &id_aa64isar1_override)) + return true; + + return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, + &id_aa64isar2_override); +} + +static inline bool cpu_has_lva(void) +{ + u64 mmfr2; + + mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + mmfr2 &= ~id_aa64mmfr2_override.mask; + mmfr2 |= id_aa64mmfr2_override.val; + return cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_EL1_VARange_SHIFT); +} + +static inline bool cpu_has_lpa2(void) +{ +#ifdef CONFIG_ARM64_LPA2 + u64 mmfr0; + int feat; + + mmfr0 = read_sysreg(id_aa64mmfr0_el1); + mmfr0 &= ~id_aa64mmfr0_override.mask; + mmfr0 |= id_aa64mmfr0_override.val; + feat = cpuid_feature_extract_signed_field(mmfr0, + ID_AA64MMFR0_EL1_TGRAN_SHIFT); + + return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2; +#else + return false; +#endif +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/crash_core.h b/arch/arm64/include/asm/crash_reserve.h index 9f5c8d339f44..4afe027a4e7b 100644 --- a/arch/arm64/include/asm/crash_core.h +++ b/arch/arm64/include/asm/crash_reserve.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _ARM64_CRASH_CORE_H -#define _ARM64_CRASH_CORE_H +#ifndef _ARM64_CRASH_RESERVE_H +#define _ARM64_CRASH_RESERVE_H /* Current arm64 boot protocol requires 2MB alignment */ #define CRASH_ALIGN SZ_2M diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 97932fbf973d..3f93f4eef953 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -201,16 +201,16 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #define COMPAT_ELF_PLATFORM ("v8l") #endif -#ifdef CONFIG_COMPAT - -/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */ -#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL - /* AArch32 registers. */ #define COMPAT_ELF_NGREG 18 typedef unsigned int compat_elf_greg_t; typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; +#ifdef CONFIG_COMPAT + +/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */ +#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL + /* AArch32 EABI. */ #define EF_ARM_EABI_MASK 0xff000000 int compat_elf_check_arch(const struct elf32_hdr *); diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 353fe08546cf..81606bf7d5ac 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -117,15 +117,9 @@ #define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) -#define ESR_ELx_FSC_SEA_TTW0 (0x14) -#define ESR_ELx_FSC_SEA_TTW1 (0x15) -#define ESR_ELx_FSC_SEA_TTW2 (0x16) -#define ESR_ELx_FSC_SEA_TTW3 (0x17) +#define ESR_ELx_FSC_SEA_TTW(n) (0x14 + (n)) #define ESR_ELx_FSC_SECC (0x18) -#define ESR_ELx_FSC_SECC_TTW0 (0x1c) -#define ESR_ELx_FSC_SECC_TTW1 (0x1d) -#define ESR_ELx_FSC_SECC_TTW2 (0x1e) -#define ESR_ELx_FSC_SECC_TTW3 (0x1f) +#define ESR_ELx_FSC_SECC_TTW(n) (0x1c + (n)) /* ISS field definitions for Data Aborts */ #define ESR_ELx_ISV_SHIFT (24) @@ -394,6 +388,9 @@ static inline bool esr_is_data_abort(unsigned long esr) static inline bool esr_fsc_is_translation_fault(unsigned long esr) { + /* Translation fault, level -1 */ + if ((esr & ESR_ELx_FSC) == 0b101011) + return true; return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; } diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index ad688e157c9b..f296662590c7 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -74,7 +74,7 @@ void do_el0_fpac(struct pt_regs *regs, unsigned long esr); void do_el1_fpac(struct pt_regs *regs, unsigned long esr); void do_el0_mops(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 do_signal(struct pt_regs *regs); void __noreturn 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 58c294a96676..87e307804b99 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -87,6 +87,7 @@ enum fixed_addresses { FIX_PTE, FIX_PMD, FIX_PUD, + FIX_P4D, FIX_PGD, __end_of_fixed_addresses @@ -100,7 +101,6 @@ enum fixed_addresses { #define FIXMAP_PAGE_IO __pgprot(PROT_DEVICE_nGnRE) void __init early_fixmap_init(void); -void __init fixmap_copy(pgd_t *pgdir); #define __early_set_fixmap __set_fixmap diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index b67b89c54e1c..bc69ac368d73 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -21,7 +21,6 @@ #include <linux/stddef.h> #include <linux/types.h> -#ifdef CONFIG_COMPAT /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 @@ -30,7 +29,6 @@ * control/status register. */ #define VFP_STATE_SIZE ((32 * 8) + 4) -#endif static inline unsigned long cpacr_save_enable_kernel_sve(void) { @@ -89,6 +87,7 @@ struct cpu_fp_state { void *sve_state; void *sme_state; u64 *svcr; + u64 *fpmr; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; @@ -154,6 +153,7 @@ extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); extern u64 read_smcr_features(void); diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 84055329cd8b..bd81cf17744a 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -59,7 +59,6 @@ static inline void decode_ctrl_reg(u32 reg, /* Watchpoints */ #define ARM_BREAKPOINT_LOAD 1 #define ARM_BREAKPOINT_STORE 2 -#define AARCH64_ESR_ACCESS_MASK (1 << 6) /* Lengths */ #define ARM_BREAKPOINT_LEN_1 0x1 diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index cd71e09ea14d..4edd3b61df11 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -142,6 +142,21 @@ #define KERNEL_HWCAP_SVE_B16B16 __khwcap2_feature(SVE_B16B16) #define KERNEL_HWCAP_LRCPC3 __khwcap2_feature(LRCPC3) #define KERNEL_HWCAP_LSE128 __khwcap2_feature(LSE128) +#define KERNEL_HWCAP_FPMR __khwcap2_feature(FPMR) +#define KERNEL_HWCAP_LUT __khwcap2_feature(LUT) +#define KERNEL_HWCAP_FAMINMAX __khwcap2_feature(FAMINMAX) +#define KERNEL_HWCAP_F8CVT __khwcap2_feature(F8CVT) +#define KERNEL_HWCAP_F8FMA __khwcap2_feature(F8FMA) +#define KERNEL_HWCAP_F8DP4 __khwcap2_feature(F8DP4) +#define KERNEL_HWCAP_F8DP2 __khwcap2_feature(F8DP2) +#define KERNEL_HWCAP_F8E4M3 __khwcap2_feature(F8E4M3) +#define KERNEL_HWCAP_F8E5M2 __khwcap2_feature(F8E5M2) +#define KERNEL_HWCAP_SME_LUTV2 __khwcap2_feature(SME_LUTV2) +#define KERNEL_HWCAP_SME_F8F16 __khwcap2_feature(SME_F8F16) +#define KERNEL_HWCAP_SME_F8F32 __khwcap2_feature(SME_F8F32) +#define KERNEL_HWCAP_SME_SF8FMA __khwcap2_feature(SME_SF8FMA) +#define KERNEL_HWCAP_SME_SF8DP4 __khwcap2_feature(SME_SF8DP4) +#define KERNEL_HWCAP_SME_SF8DP2 __khwcap2_feature(SME_SF8DP2) /* * 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 bc6c7ac934a1..bc30aadedfe9 100644 --- a/arch/arm64/include/asm/hyperv-tlfs.h +++ b/arch/arm64/include/asm/hyperv-tlfs.h @@ -22,14 +22,6 @@ */ /* - * These Hyper-V registers provide information equivalent to the CPUID - * instruction on x86/x64. - */ -#define HV_REGISTER_HYPERVISOR_VERSION 0x00000100 /*CPUID 0x40000002 */ -#define HV_REGISTER_FEATURES 0x00000200 /*CPUID 0x40000003 */ -#define HV_REGISTER_ENLIGHTENMENTS 0x00000201 /*CPUID 0x40000004 */ - -/* * Group C Features. See the asm-generic version of hyperv-tlfs.h * for a description of Feature Groups. */ @@ -41,28 +33,29 @@ #define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(13) /* - * Synthetic register definitions equivalent to MSRs on x86/x64 + * To support arch-generic code calling hv_set/get_register: + * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl + * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall */ -#define HV_REGISTER_CRASH_P0 0x00000210 -#define HV_REGISTER_CRASH_P1 0x00000211 -#define HV_REGISTER_CRASH_P2 0x00000212 -#define HV_REGISTER_CRASH_P3 0x00000213 -#define HV_REGISTER_CRASH_P4 0x00000214 -#define HV_REGISTER_CRASH_CTL 0x00000215 +#define HV_MSR_CRASH_P0 (HV_REGISTER_GUEST_CRASH_P0) +#define HV_MSR_CRASH_P1 (HV_REGISTER_GUEST_CRASH_P1) +#define HV_MSR_CRASH_P2 (HV_REGISTER_GUEST_CRASH_P2) +#define HV_MSR_CRASH_P3 (HV_REGISTER_GUEST_CRASH_P3) +#define HV_MSR_CRASH_P4 (HV_REGISTER_GUEST_CRASH_P4) +#define HV_MSR_CRASH_CTL (HV_REGISTER_GUEST_CRASH_CTL) -#define HV_REGISTER_GUEST_OSID 0x00090002 -#define HV_REGISTER_VP_INDEX 0x00090003 -#define HV_REGISTER_TIME_REF_COUNT 0x00090004 -#define HV_REGISTER_REFERENCE_TSC 0x00090017 +#define HV_MSR_VP_INDEX (HV_REGISTER_VP_INDEX) +#define HV_MSR_TIME_REF_COUNT (HV_REGISTER_TIME_REF_COUNT) +#define HV_MSR_REFERENCE_TSC (HV_REGISTER_REFERENCE_TSC) -#define HV_REGISTER_SINT0 0x000A0000 -#define HV_REGISTER_SCONTROL 0x000A0010 -#define HV_REGISTER_SIEFP 0x000A0012 -#define HV_REGISTER_SIMP 0x000A0013 -#define HV_REGISTER_EOM 0x000A0014 +#define HV_MSR_SINT0 (HV_REGISTER_SINT0) +#define HV_MSR_SCONTROL (HV_REGISTER_SCONTROL) +#define HV_MSR_SIEFP (HV_REGISTER_SIEFP) +#define HV_MSR_SIMP (HV_REGISTER_SIMP) +#define HV_MSR_EOM (HV_REGISTER_EOM) -#define HV_REGISTER_STIMER0_CONFIG 0x000B0000 -#define HV_REGISTER_STIMER0_COUNT 0x000B0001 +#define HV_MSR_STIMER0_CONFIG (HV_REGISTER_STIMER0_CONFIG) +#define HV_MSR_STIMER0_COUNT (HV_REGISTER_STIMER0_COUNT) union hv_msi_entry { u64 as_uint64[2]; diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 3b694511b98f..8d825522c55c 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -24,25 +24,29 @@ #define __raw_writeb __raw_writeb static __always_inline void __raw_writeb(u8 val, volatile void __iomem *addr) { - asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u8 __iomem *ptr = addr; + asm volatile("strb %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writew __raw_writew static __always_inline void __raw_writew(u16 val, volatile void __iomem *addr) { - asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u16 __iomem *ptr = addr; + asm volatile("strh %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writel __raw_writel static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr) { - asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u32 __iomem *ptr = addr; + asm volatile("str %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writeq __raw_writeq static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr) { - asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u64 __iomem *ptr = addr; + asm volatile("str %x0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_readb __raw_readb diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index 7eefc525a9df..e1b57c13f8a4 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -17,11 +17,9 @@ asmlinkage void kasan_early_init(void); void kasan_init(void); -void kasan_copy_shadow(pgd_t *pgdir); #else static inline void kasan_init(void) { } -static inline void kasan_copy_shadow(pgd_t *pgdir) { } #endif #endif diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 83ddb14b95a5..bf05a77873a4 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -13,28 +13,27 @@ #include <asm/sparsemem.h> /* - * The linear mapping and the start of memory are both 2M aligned (per - * the arm64 booting.txt requirements). Hence we can use section mapping - * with 4K (section size = 2M) but not with 16K (section size = 32M) or - * 64K (section size = 512M). + * The physical and virtual addresses of the start of the kernel image are + * equal modulo 2 MiB (per the arm64 booting.txt requirements). Hence we can + * use section mapping with 4K (section size = 2M) but not with 16K (section + * size = 32M) or 64K (section size = 512M). */ - -/* - * The idmap and swapper page tables need some space reserved in the kernel - * image. Both require pgd, pud (4 levels only) and pmd tables to (section) - * map the kernel. With the 64K page configuration, swapper and idmap need to - * map to pte level. The swapper also maps the FDT (see __create_page_tables - * for more information). Note that the number of ID map translation levels - * could be increased on the fly if system RAM is out of reach for the default - * VA range, so pages required to map highest possible PA are reserved in all - * cases. - */ -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1) +#if defined(PMD_SIZE) && PMD_SIZE <= MIN_KIMG_ALIGN +#define SWAPPER_BLOCK_SHIFT PMD_SHIFT +#define SWAPPER_SKIP_LEVEL 1 #else -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) +#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT +#define SWAPPER_SKIP_LEVEL 0 #endif +#define SWAPPER_BLOCK_SIZE (UL(1) << SWAPPER_BLOCK_SHIFT) +#define SWAPPER_TABLE_SHIFT (SWAPPER_BLOCK_SHIFT + PAGE_SHIFT - 3) +#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - SWAPPER_SKIP_LEVEL) +#define INIT_IDMAP_PGTABLE_LEVELS (IDMAP_LEVELS - SWAPPER_SKIP_LEVEL) + +#define IDMAP_VA_BITS 48 +#define IDMAP_LEVELS ARM64_HW_PGTABLE_LEVELS(IDMAP_VA_BITS) +#define IDMAP_ROOT_LEVEL (4 - IDMAP_LEVELS) /* * A relocatable kernel may execute from an address that differs from the one at @@ -50,57 +49,39 @@ #define EARLY_ENTRIES(vstart, vend, shift, add) \ (SPAN_NR_ENTRIES(vstart, vend, shift) + (add)) -#define EARLY_PGDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT, add)) - -#if SWAPPER_PGTABLE_LEVELS > 3 -#define EARLY_PUDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT, add)) -#else -#define EARLY_PUDS(vstart, vend, add) (0) -#endif +#define EARLY_LEVEL(lvl, lvls, vstart, vend, add) \ + (lvls > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0) -#if SWAPPER_PGTABLE_LEVELS > 2 -#define EARLY_PMDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT, add)) -#else -#define EARLY_PMDS(vstart, vend, add) (0) -#endif +#define EARLY_PAGES(lvls, vstart, vend, add) (1 /* PGDIR page */ \ + + EARLY_LEVEL(3, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(2, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(1, (lvls), (vstart), (vend), add))/* each entry needs a next level page table */ +#define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(SWAPPER_PGTABLE_LEVELS, KIMAGE_VADDR, _end, EXTRA_PAGE) \ + + EARLY_SEGMENT_EXTRA_PAGES)) -#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, EXTRA_PAGE)) +#define INIT_IDMAP_DIR_PAGES (EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, KIMAGE_VADDR, _end, 1)) +#define INIT_IDMAP_DIR_SIZE ((INIT_IDMAP_DIR_PAGES + EARLY_IDMAP_EXTRA_PAGES) * PAGE_SIZE) -/* 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) +#define INIT_IDMAP_FDT_PAGES (EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, 0UL, UL(MAX_FDT_SIZE), 1) - 1) +#define INIT_IDMAP_FDT_SIZE ((INIT_IDMAP_FDT_PAGES + EARLY_IDMAP_EXTRA_FDT_PAGES) * PAGE_SIZE) -/* Initial memory map size */ -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_BLOCK_SHIFT PMD_SHIFT -#define SWAPPER_BLOCK_SIZE PMD_SIZE -#define SWAPPER_TABLE_SHIFT PUD_SHIFT -#else -#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT -#define SWAPPER_BLOCK_SIZE PAGE_SIZE -#define SWAPPER_TABLE_SHIFT PMD_SHIFT -#endif +/* The number of segments in the kernel image (text, rodata, inittext, initdata, data+bss) */ +#define KERNEL_SEGMENT_COUNT 5 +#if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN +#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1) /* - * Initial memory map attributes. + * The initial ID map consists of the kernel image, mapped as two separate + * segments, and may appear misaligned wrt the swapper block size. This means + * we need 3 additional pages. The DT could straddle a swapper block boundary, + * so it may need 2. */ -#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED | PTE_UXN) -#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S | PTE_UXN) - -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_RW_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS | PTE_WRITE) -#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY) +#define EARLY_IDMAP_EXTRA_PAGES 3 +#define EARLY_IDMAP_EXTRA_FDT_PAGES 2 #else -#define SWAPPER_RW_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS | PTE_WRITE) -#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PTE_RDONLY) +#define EARLY_SEGMENT_EXTRA_PAGES 0 +#define EARLY_IDMAP_EXTRA_PAGES 0 +#define EARLY_IDMAP_EXTRA_FDT_PAGES 0 #endif #endif /* __ASM_KERNEL_PGTABLE_H */ diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 9ac9572a3bbe..4d9cc7a76d9c 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -80,7 +80,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } } -#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION) +#if defined(CONFIG_CRASH_DUMP) && defined(CONFIG_HIBERNATION) extern bool crash_is_nosave(unsigned long pfn); extern void crash_prepare_suspend(void); extern void crash_post_resume(void); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 3c6f8ba1e479..e01bb5ca13b7 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -102,10 +102,8 @@ #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) -#define HCRX_GUEST_FLAGS \ - (HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \ - (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0)) -#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En) +#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En) +#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM) /* TCR_EL2 Registers bits */ #define TCR_EL2_DS (1UL << 32) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index b804fe832184..975af30af31f 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -209,7 +209,8 @@ static inline bool vcpu_is_el2(const struct kvm_vcpu *vcpu) static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt) { - return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H; + return (!cpus_have_final_cap(ARM64_HAS_HCR_NV1) || + (ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H)); } static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu) @@ -425,15 +426,9 @@ static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { case ESR_ELx_FSC_EXTABT: - case ESR_ELx_FSC_SEA_TTW0: - case ESR_ELx_FSC_SEA_TTW1: - case ESR_ELx_FSC_SEA_TTW2: - case ESR_ELx_FSC_SEA_TTW3: + case ESR_ELx_FSC_SEA_TTW(-1) ... ESR_ELx_FSC_SEA_TTW(3): case ESR_ELx_FSC_SECC: - case ESR_ELx_FSC_SECC_TTW0: - case ESR_ELx_FSC_SECC_TTW1: - case ESR_ELx_FSC_SECC_TTW2: - case ESR_ELx_FSC_SECC_TTW3: + case ESR_ELx_FSC_SECC_TTW(-1) ... ESR_ELx_FSC_SECC_TTW(3): return true; default: return false; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 21c57b812569..9e8a496fb284 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -238,9 +238,32 @@ static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr) return index; } +struct kvm_sysreg_masks; + +enum fgt_group_id { + __NO_FGT_GROUP__, + HFGxTR_GROUP, + HDFGRTR_GROUP, + HDFGWTR_GROUP = HDFGRTR_GROUP, + HFGITR_GROUP, + HAFGRTR_GROUP, + + /* Must be last */ + __NR_FGT_GROUP_IDS__ +}; + struct kvm_arch { struct kvm_s2_mmu mmu; + /* + * Fine-Grained UNDEF, mimicking the FGT layout defined by the + * architecture. We track them globally, as we present the + * same feature-set to all vcpus. + * + * Index 0 is currently spare. + */ + u64 fgu[__NR_FGT_GROUP_IDS__]; + /* Interrupt controller */ struct vgic_dist vgic; @@ -274,6 +297,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE 6 /* Initial ID reg values loaded */ #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 7 + /* Fine-Grained UNDEF initialised */ +#define KVM_ARCH_FLAG_FGU_INITIALIZED 8 unsigned long flags; /* VM-wide vCPU feature set */ @@ -294,6 +319,9 @@ struct kvm_arch { /* PMCR_EL0.N value for the guest */ u8 pmcr_n; + /* Iterator for idreg debugfs */ + u8 idreg_debugfs_iter; + /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; struct maple_tree smccc_filter; @@ -312,6 +340,9 @@ struct kvm_arch { #define KVM_ARM_ID_REG_NUM (IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1) u64 id_regs[KVM_ARM_ID_REG_NUM]; + /* Masks for VNCR-baked sysregs */ + struct kvm_sysreg_masks *sysreg_masks; + /* * For an untrusted host VM, 'pkvm.handle' is used to lookup * the associated pKVM instance in the hypervisor. @@ -474,6 +505,13 @@ enum vcpu_sysreg { NR_SYS_REGS /* Nothing after this line! */ }; +struct kvm_sysreg_masks { + struct { + u64 res0; + u64 res1; + } mask[NR_SYS_REGS - __VNCR_START__]; +}; + struct kvm_cpu_context { struct user_pt_regs regs; /* sp = sp_el0 */ @@ -543,12 +581,14 @@ struct kvm_vcpu_arch { enum fp_type fp_type; unsigned int sve_max_vl; u64 svcr; + u64 fpmr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; /* Values of trap registers for the guest. */ u64 hcr_el2; + u64 hcrx_el2; u64 mdcr_el2; u64 cptr_el2; @@ -868,7 +908,15 @@ static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) #define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r)) -#define __vcpu_sys_reg(v,r) (ctxt_sys_reg(&(v)->arch.ctxt, (r))) +u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg); +#define __vcpu_sys_reg(v,r) \ + (*({ \ + const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \ + u64 *__r = __ctxt_sys_reg(ctxt, (r)); \ + if (vcpu_has_nv((v)) && (r) >= __VNCR_START__) \ + *__r = kvm_vcpu_sanitise_vncr_reg((v), (r)); \ + __r; \ + })) u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg); void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); @@ -1055,14 +1103,20 @@ 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_sys_regs_create_debugfs(struct kvm *kvm); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); int __init kvm_sys_reg_table_init(void); +struct sys_reg_desc; +int __init populate_sysreg_config(const struct sys_reg_desc *sr, + unsigned int idx); int __init populate_nv_trap_config(void); bool lock_all_vcpus(struct kvm *kvm); void unlock_all_vcpus(struct kvm *kvm); +void kvm_init_sysreg(struct kvm_vcpu *); + /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); @@ -1233,4 +1287,48 @@ static inline void kvm_hyp_reserve(void) { } void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu); bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); +#define __expand_field_sign_unsigned(id, fld, val) \ + ((u64)SYS_FIELD_VALUE(id, fld, val)) + +#define __expand_field_sign_signed(id, fld, val) \ + ({ \ + u64 __val = SYS_FIELD_VALUE(id, fld, val); \ + sign_extend64(__val, id##_##fld##_WIDTH - 1); \ + }) + +#define expand_field_sign(id, fld, val) \ + (id##_##fld##_SIGNED ? \ + __expand_field_sign_signed(id, fld, val) : \ + __expand_field_sign_unsigned(id, fld, val)) + +#define get_idreg_field_unsigned(kvm, id, fld) \ + ({ \ + u64 __val = IDREG((kvm), SYS_##id); \ + FIELD_GET(id##_##fld##_MASK, __val); \ + }) + +#define get_idreg_field_signed(kvm, id, fld) \ + ({ \ + u64 __val = get_idreg_field_unsigned(kvm, id, fld); \ + sign_extend64(__val, id##_##fld##_WIDTH - 1); \ + }) + +#define get_idreg_field_enum(kvm, id, fld) \ + get_idreg_field_unsigned(kvm, id, fld) + +#define get_idreg_field(kvm, id, fld) \ + (id##_##fld##_SIGNED ? \ + get_idreg_field_signed(kvm, id, fld) : \ + get_idreg_field_unsigned(kvm, id, fld)) + +#define kvm_has_feat(kvm, id, fld, limit) \ + (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, limit)) + +#define kvm_has_feat_enum(kvm, id, fld, val) \ + (get_idreg_field_unsigned((kvm), id, fld) == __expand_field_sign_unsigned(id, fld, val)) + +#define kvm_has_feat_range(kvm, id, fld, min, max) \ + (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \ + get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max)) + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 145ce73fc16c..3e2a1ac0c9bb 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -70,7 +70,7 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); /* * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the * static inline can allow the compiler to out-of-line this. KVM always wants - * the macro version as its always inlined. + * the macro version as it's always inlined. */ #define __kvm_swab32(x) ___constant_swab32(x) diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index e3e793d0ec30..d5e48d870461 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -54,27 +54,6 @@ #include <asm/alternative.h> /* - * Convert a kernel VA into a HYP VA. - * reg: VA to be converted. - * - * The actual code generation takes place in kvm_update_va_mask, and - * the instructions below are only there to reserve the space and - * perform the register allocation (kvm_update_va_mask uses the - * specific registers encoded in the instructions). - */ -.macro kern_hyp_va reg -#ifndef __KVM_VHE_HYPERVISOR__ -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 */ - add \reg, \reg, #0, lsl 12 /* insert the top 12 bits of the tag */ - ror \reg, \reg, #63 /* rotate back */ -alternative_cb_end -#endif -.endm - -/* * Convert a hypervisor VA to a PA * reg: hypervisor address to be converted in place * tmp: temporary register @@ -127,14 +106,29 @@ void kvm_apply_hyp_relocations(void); #define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset) +/* + * Convert a kernel VA into a HYP VA. + * + * Can be called from hyp or non-hyp context. + * + * The actual code generation takes place in kvm_update_va_mask(), and + * the instructions below are only there to reserve the space and + * perform the register allocation (kvm_update_va_mask() uses the + * specific registers encoded in the instructions). + */ static __always_inline unsigned long __kern_hyp_va(unsigned long v) { +/* + * This #ifndef is an optimisation for when this is called from VHE hyp + * context. When called from a VHE non-hyp context, kvm_update_va_mask() will + * replace the instructions with `nop`s. + */ #ifndef __KVM_VHE_HYPERVISOR__ - asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" - "ror %0, %0, #1\n" - "add %0, %0, #0\n" - "add %0, %0, #0, lsl 12\n" - "ror %0, %0, #63\n", + asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" /* mask with va_mask */ + "ror %0, %0, #1\n" /* rotate to the first tag bit */ + "add %0, %0, #0\n" /* insert the low 12 bits of the tag */ + "add %0, %0, #0, lsl 12\n" /* insert the top 12 bits of the tag */ + "ror %0, %0, #63\n", /* rotate back */ ARM64_ALWAYS_SYSTEM, kvm_update_va_mask) : "+r" (v)); diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 4882905357f4..c77d795556e1 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -60,7 +60,6 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0) return ttbr0 & ~GENMASK_ULL(63, 48); } -extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu); int kvm_init_nv_sysregs(struct kvm *kvm); diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index cfdf40f734b1..19278dfe7978 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -197,6 +197,7 @@ enum kvm_pgtable_stage2_flags { * @KVM_PGTABLE_PROT_W: Write permission. * @KVM_PGTABLE_PROT_R: Read permission. * @KVM_PGTABLE_PROT_DEVICE: Device attributes. + * @KVM_PGTABLE_PROT_NORMAL_NC: Normal noncacheable attributes. * @KVM_PGTABLE_PROT_SW0: Software bit 0. * @KVM_PGTABLE_PROT_SW1: Software bit 1. * @KVM_PGTABLE_PROT_SW2: Software bit 2. @@ -208,6 +209,7 @@ enum kvm_pgtable_prot { KVM_PGTABLE_PROT_R = BIT(2), KVM_PGTABLE_PROT_DEVICE = BIT(3), + KVM_PGTABLE_PROT_NORMAL_NC = BIT(4), KVM_PGTABLE_PROT_SW0 = BIT(55), KVM_PGTABLE_PROT_SW1 = BIT(56), diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index d82305ab420f..54fb014eba05 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -30,8 +30,8 @@ * keep a constant PAGE_OFFSET and "fallback" to using the higher end * of the VMEMMAP where 52-bit support is not available in hardware. */ -#define VMEMMAP_SHIFT (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT) -#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) >> VMEMMAP_SHIFT) +#define VMEMMAP_RANGE (_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) +#define VMEMMAP_SIZE ((VMEMMAP_RANGE >> PAGE_SHIFT) * sizeof(struct page)) /* * PAGE_OFFSET - the virtual address of the start of the linear map, at the @@ -47,14 +47,18 @@ #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (_PAGE_END(VA_BITS_MIN)) #define MODULES_VSIZE (SZ_2G) -#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT))) -#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE) -#define PCI_IO_END (VMEMMAP_START - SZ_8M) -#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) -#define FIXADDR_TOP (VMEMMAP_START - SZ_32M) +#define VMEMMAP_START (VMEMMAP_END - VMEMMAP_SIZE) +#define VMEMMAP_END (-UL(SZ_1G)) +#define PCI_IO_START (VMEMMAP_END + SZ_8M) +#define PCI_IO_END (PCI_IO_START + PCI_IO_SIZE) +#define FIXADDR_TOP (-UL(SZ_8M)) #if VA_BITS > 48 +#ifdef CONFIG_ARM64_16K_PAGES +#define VA_BITS_MIN (47) +#else #define VA_BITS_MIN (48) +#endif #else #define VA_BITS_MIN (VA_BITS) #endif @@ -173,6 +177,7 @@ * Memory types for Stage-2 translation */ #define MT_S2_NORMAL 0xf +#define MT_S2_NORMAL_NC 0x5 #define MT_S2_DEVICE_nGnRE 0x1 /* @@ -180,6 +185,7 @@ * Stage-2 enforces Normal-WB and Device-nGnRE */ #define MT_S2_FWB_NORMAL 6 +#define MT_S2_FWB_NORMAL_NC 5 #define MT_S2_FWB_DEVICE_nGnRE 1 #ifdef CONFIG_ARM64_4K_PAGES @@ -209,9 +215,20 @@ #include <asm/boot.h> #include <asm/bug.h> #include <asm/sections.h> +#include <asm/sysreg.h> + +static inline u64 __pure read_tcr(void) +{ + u64 tcr; + + // read_sysreg() uses asm volatile, so avoid it here + asm("mrs %0, tcr_el1" : "=r"(tcr)); + return tcr; +} #if VA_BITS > 48 -extern u64 vabits_actual; +// For reasons of #include hell, we can't use TCR_T1SZ_OFFSET/TCR_T1SZ_MASK here +#define vabits_actual (64 - ((read_tcr() >> 16) & 63)) #else #define vabits_actual ((u64)VA_BITS) #endif diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 2fcf51231d6e..65977c7783c5 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -71,10 +71,46 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, pgprot_t prot, bool page_mappings_only); extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); -extern bool kaslr_requires_kpti(void); + +/* + * This check is triggered during the early boot before the cpufeature + * is initialised. Checking the status on the local CPU allows the boot + * CPU to detect the need for non-global mappings and thus avoiding a + * pagetable re-write after all the CPUs are booted. This check will be + * anyway run on individual CPUs, allowing us to get the consistent + * state once the SMP CPUs are up and thus make the switch to non-global + * mappings if required. + */ +static inline bool kaslr_requires_kpti(void) +{ + /* + * E0PD does a similar job to KPTI so can be used instead + * where available. + */ + if (IS_ENABLED(CONFIG_ARM64_E0PD)) { + u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + if (cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_EL1_E0PD_SHIFT)) + return false; + } + + /* + * Systems affected by Cavium erratum 24756 are incompatible + * with KPTI. + */ + if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { + extern const struct midr_range cavium_erratum_27456_cpus[]; + + if (is_midr_in_range_list(read_cpuid_id(), + cavium_erratum_27456_cpus)) + return false; + } + + return true; +} #define INIT_MM_CONTEXT(name) \ - .pgd = init_pg_dir, + .pgd = swapper_pg_dir, #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 9ce4200508b1..c768d16b81a4 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -61,11 +61,9 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) } /* - * TCR.T0SZ value to use when the ID map is active. Usually equals - * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in - * physical memory, in which case it will be smaller. + * TCR.T0SZ value to use when the ID map is active. */ -extern int idmap_t0sz; +#define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS) /* * Ensure TCR.T0SZ is set to the provided value. @@ -110,18 +108,13 @@ static inline void cpu_uninstall_idmap(void) cpu_switch_mm(mm->pgd, mm); } -static inline void __cpu_install_idmap(pgd_t *idmap) +static inline void cpu_install_idmap(void) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); - cpu_switch_mm(lm_alias(idmap), &init_mm); -} - -static inline void cpu_install_idmap(void) -{ - __cpu_install_idmap(idmap_pg_dir); + cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* @@ -148,51 +141,21 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) isb(); } -/* - * 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 __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp) -{ - typedef void (ttbr_replace_func)(phys_addr_t); - extern ttbr_replace_func idmap_cpu_replace_ttbr1; - ttbr_replace_func *replace_phys; - unsigned long daif; - - /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */ - phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp)); - - if (cnp) - ttbr1 |= TTBR_CNP_BIT; - - replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); - - __cpu_install_idmap(idmap); - - /* - * We really don't want to take *any* exceptions while TTBR1 is - * in the process of being replaced so mask everything. - */ - daif = local_daif_save(); - replace_phys(ttbr1); - local_daif_restore(daif); - - cpu_uninstall_idmap(); -} +void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp); static inline void cpu_enable_swapper_cnp(void) { - __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir, true); + __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true); } -static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) +static inline void cpu_replace_ttbr1(pgd_t *pgdp) { /* * Only for early TTBR1 replacement before cpucaps are finalized and * before we've decided whether to use CNP. */ WARN_ON(system_capabilities_finalized()); - __cpu_replace_ttbr1(pgdp, idmap, false); + __cpu_replace_ttbr1(pgdp, false); } /* diff --git a/arch/arm64/include/asm/mshyperv.h b/arch/arm64/include/asm/mshyperv.h index 20070a847304..a975e1a689dd 100644 --- a/arch/arm64/include/asm/mshyperv.h +++ b/arch/arm64/include/asm/mshyperv.h @@ -31,12 +31,12 @@ void hv_set_vpreg(u32 reg, u64 value); u64 hv_get_vpreg(u32 reg); void hv_get_vpreg_128(u32 reg, struct hv_get_vp_registers_output *result); -static inline void hv_set_register(unsigned int reg, u64 value) +static inline void hv_set_msr(unsigned int reg, u64 value) { hv_set_vpreg(reg, value); } -static inline u64 hv_get_register(unsigned int reg) +static inline u64 hv_get_msr(unsigned int reg) { return hv_get_vpreg(reg); } diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 237224484d0f..8ff5f2a2579e 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -14,6 +14,7 @@ #include <asm/tlbflush.h> #define __HAVE_ARCH_PGD_FREE +#define __HAVE_ARCH_PUD_FREE #include <asm-generic/pgalloc.h> #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) @@ -43,7 +44,8 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { - set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); + if (pgtable_l4_enabled()) + set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); } static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp) @@ -53,6 +55,13 @@ static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp) p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN; __p4d_populate(p4dp, __pa(pudp), p4dval); } + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (!pgtable_l4_enabled()) + return; + __pud_free(mm, pud); +} #else static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { @@ -60,6 +69,47 @@ static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#if CONFIG_PGTABLE_LEVELS > 4 + +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) +{ + if (pgtable_l5_enabled()) + set_pgd(pgdp, __pgd(__phys_to_pgd_val(p4dp) | prot)); +} + +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp) +{ + pgdval_t pgdval = PGD_TYPE_TABLE; + + pgdval |= (mm == &init_mm) ? PGD_TABLE_UXN : PGD_TABLE_PXN; + __pgd_populate(pgdp, __pa(p4dp), pgdval); +} + +static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + gfp_t gfp = GFP_PGTABLE_USER; + + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + return (p4d_t *)get_zeroed_page(gfp); +} + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); + free_page((unsigned long)p4d); +} + +#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) +#else +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) +{ + BUILD_BUG(); +} +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index e4944d517c99..ef207a0d4f0d 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -26,10 +26,10 @@ #define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3)) /* - * Size mapped by an entry at level n ( 0 <= n <= 3) + * Size mapped by an entry at level n ( -1 <= n <= 3) * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits * in the final page. The maximum number of translation levels supported by - * the architecture is 4. Hence, starting at level n, we have further + * the architecture is 5. Hence, starting at level n, we have further * ((4 - n) - 1) levels of translation excluding the offset within the page. * So, the total number of bits mapped by an entry at level n is : * @@ -62,9 +62,16 @@ #define PTRS_PER_PUD (1 << (PAGE_SHIFT - 3)) #endif +#if CONFIG_PGTABLE_LEVELS > 4 +#define P4D_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(0) +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE-1)) +#define PTRS_PER_P4D (1 << (PAGE_SHIFT - 3)) +#endif + /* * PGDIR_SHIFT determines the size a top-level page table entry can map - * (depending on the configuration, this level can be 0, 1 or 2). + * (depending on the configuration, this level can be -1, 0, 1 or 2). */ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) @@ -87,6 +94,15 @@ /* * Hardware page table definitions. * + * Level -1 descriptor (PGD). + */ +#define PGD_TYPE_TABLE (_AT(pgdval_t, 3) << 0) +#define PGD_TABLE_BIT (_AT(pgdval_t, 1) << 1) +#define PGD_TYPE_MASK (_AT(pgdval_t, 3) << 0) +#define PGD_TABLE_PXN (_AT(pgdval_t, 1) << 59) +#define PGD_TABLE_UXN (_AT(pgdval_t, 1) << 60) + +/* * Level 0 descriptor (P4D). */ #define P4D_TYPE_TABLE (_AT(p4dval_t, 3) << 0) @@ -155,13 +171,17 @@ #define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */ #define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */ -#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) +#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (50 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) #ifdef CONFIG_ARM64_PA_BITS_52 +#ifdef CONFIG_ARM64_64K_PAGES #define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12) -#define PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH) #define PTE_ADDR_HIGH_SHIFT 36 +#define PHYS_TO_PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH) #else -#define PTE_ADDR_MASK PTE_ADDR_LOW +#define PTE_ADDR_HIGH (_AT(pteval_t, 0x3) << 8) +#define PTE_ADDR_HIGH_SHIFT 42 +#define PHYS_TO_PTE_ADDR_MASK GENMASK_ULL(49, 8) +#endif #endif /* @@ -284,6 +304,7 @@ #define TCR_E0PD1 (UL(1) << 56) #define TCR_TCMA0 (UL(1) << 57) #define TCR_TCMA1 (UL(1) << 58) +#define TCR_DS (UL(1) << 59) /* * TTBR. diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 483dbfa39c4c..dd9ee67d1d87 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -30,8 +30,8 @@ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) -#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) +#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_MAYBE_NG | PTE_MAYBE_SHARED | PTE_AF) +#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_MAYBE_NG | PMD_MAYBE_SHARED | PMD_SECT_AF) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) @@ -57,10 +57,6 @@ #define _PAGE_READONLY_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define _PAGE_EXECONLY (_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) -#ifdef __ASSEMBLY__ -#define PTE_MAYBE_NG 0 -#endif - #ifndef __ASSEMBLY__ #include <asm/cpufeature.h> @@ -71,7 +67,19 @@ extern bool arm64_use_ng_mappings; #define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) #define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) +#ifndef CONFIG_ARM64_LPA2 #define lpa2_is_enabled() false +#define PTE_MAYBE_SHARED PTE_SHARED +#define PMD_MAYBE_SHARED PMD_SECT_S +#else +static inline bool __pure lpa2_is_enabled(void) +{ + return read_tcr() & TCR_DS; +} + +#define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) +#define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) +#endif /* * If we have userspace only BTI we don't want to mark kernel pages diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h index b8f158ae2527..6d6d4065b0cb 100644 --- a/arch/arm64/include/asm/pgtable-types.h +++ b/arch/arm64/include/asm/pgtable-types.h @@ -36,6 +36,12 @@ typedef struct { pudval_t pud; } pud_t; #define __pud(x) ((pud_t) { (x) } ) #endif +#if CONFIG_PGTABLE_LEVELS > 4 +typedef struct { p4dval_t p4d; } p4d_t; +#define p4d_val(x) ((x).p4d) +#define __p4d(x) ((p4d_t) { (x) } ) +#endif + typedef struct { pgdval_t pgd; } pgd_t; #define pgd_val(x) ((x).pgd) #define __pgd(x) ((pgd_t) { (x) } ) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 79ce70fbb751..afdd56d26ad7 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -18,11 +18,15 @@ * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space - * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space - * and fixed mappings + * VMALLOC_END: extends to the available space below vmemmap */ #define VMALLOC_START (MODULES_END) -#define VMALLOC_END (VMEMMAP_START - SZ_256M) +#if VA_BITS == VA_BITS_MIN +#define VMALLOC_END (VMEMMAP_START - SZ_8M) +#else +#define VMEMMAP_UNUSED_NPAGES ((_PAGE_OFFSET(vabits_actual) - PAGE_OFFSET) >> PAGE_SHIFT) +#define VMALLOC_END (VMEMMAP_START + VMEMMAP_UNUSED_NPAGES * sizeof(struct page) - SZ_8M) +#endif #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) @@ -76,15 +80,16 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { + pte_val(pte) &= ~PTE_MAYBE_SHARED; return (pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { - return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PTE_ADDR_MASK; + return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else -#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_MASK) +#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) #define __phys_to_pte_val(phys) (phys) #endif @@ -93,7 +98,8 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) __pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pte_none(pte) (!pte_val(pte)) -#define pte_clear(mm,addr,ptep) set_pte(ptep, __pte(0)) +#define __pte_clear(mm, addr, ptep) \ + __set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) /* @@ -133,11 +139,15 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) /* + * Returns true if the pte is valid and has the contiguous bit set. + */ +#define pte_valid_cont(pte) (pte_valid(pte) && pte_cont(pte)) +/* * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. * Note that we can't make any assumptions based on the state of the access - * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * flag, since __ptep_clear_flush_young() elides a DSB when invalidating the * TLB. */ #define pte_accessible(mm, pte) \ @@ -261,7 +271,7 @@ static inline pte_t pte_mkdevmap(pte_t pte) return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); } -static inline void set_pte(pte_t *ptep, pte_t pte) +static inline void __set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); @@ -275,6 +285,11 @@ static inline void set_pte(pte_t *ptep, pte_t pte) } } +static inline pte_t __ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} + extern void __sync_icache_dcache(pte_t pteval); bool pgattr_change_is_safe(u64 old, u64 new); @@ -302,7 +317,7 @@ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; - old_pte = READ_ONCE(*ptep); + old_pte = __ptep_get(ptep); if (!pte_valid(old_pte) || !pte_valid(pte)) return; @@ -311,7 +326,7 @@ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, /* * Check for potential race with hardware updates of the pte - * (ptep_set_access_flags safely changes valid ptes without going + * (__ptep_set_access_flags safely changes valid ptes without going * through an invalid entry). */ VM_WARN_ONCE(!pte_young(pte), @@ -341,23 +356,38 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) mte_sync_tags(pte, nr_pages); } -static inline void set_ptes(struct mm_struct *mm, - unsigned long __always_unused addr, - pte_t *ptep, pte_t pte, unsigned int nr) +/* + * 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)); +} + +#define pte_advance_pfn pte_advance_pfn +static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) +{ + return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte)); +} + +static inline void __set_ptes(struct mm_struct *mm, + unsigned long __always_unused addr, + pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); __sync_cache_and_tags(pte, nr); for (;;) { __check_safe_pte_update(mm, ptep, pte); - set_pte(ptep, pte); + __set_pte(ptep, pte); if (--nr == 0) break; ptep++; - pte_val(pte) += PAGE_SIZE; + pte = pte_advance_pfn(pte, 1); } } -#define set_ptes set_ptes /* * Huge pte definitions. @@ -433,16 +463,6 @@ 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 @@ -534,7 +554,7 @@ static inline void __set_pte_at(struct mm_struct *mm, { __sync_cache_and_tags(pte, nr); __check_safe_pte_update(mm, ptep, pte); - set_pte(ptep, pte); + __set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, @@ -616,12 +636,12 @@ static inline bool pud_table(pud_t pud) { return true; } PUD_TYPE_TABLE) #endif -extern pgd_t init_pg_dir[PTRS_PER_PGD]; +extern pgd_t init_pg_dir[]; extern pgd_t init_pg_end[]; -extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; -extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; -extern pgd_t tramp_pg_dir[PTRS_PER_PGD]; -extern pgd_t reserved_pg_dir[PTRS_PER_PGD]; +extern pgd_t swapper_pg_dir[]; +extern pgd_t idmap_pg_dir[]; +extern pgd_t tramp_pg_dir[]; +extern pgd_t reserved_pg_dir[]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); @@ -694,14 +714,14 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) +static inline bool pgtable_l4_enabled(void); + static inline void set_pud(pud_t *pudp, pud_t pud) { -#ifdef __PAGETABLE_PUD_FOLDED - if (in_swapper_pgdir(pudp)) { + if (!pgtable_l4_enabled() && in_swapper_pgdir(pudp)) { set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud))); return; } -#endif /* __PAGETABLE_PUD_FOLDED */ WRITE_ONCE(*pudp, pud); @@ -754,12 +774,27 @@ static inline pmd_t *pud_pgtable(pud_t pud) #if CONFIG_PGTABLE_LEVELS > 3 +static __always_inline bool pgtable_l4_enabled(void) +{ + if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2)) + return true; + if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) + return vabits_actual == VA_BITS; + return alternative_has_cap_unlikely(ARM64_HAS_VA52); +} + +static inline bool mm_pud_folded(const struct mm_struct *mm) +{ + return !pgtable_l4_enabled(); +} +#define mm_pud_folded mm_pud_folded + #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) -#define p4d_none(p4d) (!p4d_val(p4d)) -#define p4d_bad(p4d) (!(p4d_val(p4d) & 2)) -#define p4d_present(p4d) (p4d_val(p4d)) +#define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) +#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) +#define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { @@ -775,7 +810,8 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) static inline void p4d_clear(p4d_t *p4dp) { - set_p4d(p4dp, __p4d(0)); + if (pgtable_l4_enabled()) + set_p4d(p4dp, __p4d(0)); } static inline phys_addr_t p4d_page_paddr(p4d_t p4d) @@ -783,27 +819,75 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d) return __p4d_to_phys(p4d); } +#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) +{ + return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); +} + static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_page_paddr(p4d)); } -/* Find an entry in the first-level page table. */ -#define pud_offset_phys(dir, addr) (p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) +static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) +{ + BUG_ON(!pgtable_l4_enabled()); -#define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) -#define pud_set_fixmap_offset(p4d, addr) pud_set_fixmap(pud_offset_phys(p4d, addr)) -#define pud_clear_fixmap() clear_fixmap(FIX_PUD) + return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); +} -#define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) +static inline +pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr); +} +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) +{ + return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); +} +#define pud_offset pud_offset + +static inline pud_t *pud_set_fixmap(unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return NULL; + return (pud_t *)set_fixmap_offset(FIX_PUD, addr); +} + +static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return pud_set_fixmap(pud_offset_phys(p4dp, addr)); +} + +static inline void pud_clear_fixmap(void) +{ + if (pgtable_l4_enabled()) + clear_fixmap(FIX_PUD); +} /* use ONLY for statically allocated translation tables */ -#define pud_offset_kimg(dir,addr) ((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr)))) +static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr)); +} + +#define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) #else +static inline bool pgtable_l4_enabled(void) { return false; } + #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) -#define pgd_page_paddr(pgd) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */ #define pud_set_fixmap(addr) NULL @@ -814,6 +898,122 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#if CONFIG_PGTABLE_LEVELS > 4 + +static __always_inline bool pgtable_l5_enabled(void) +{ + if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) + return vabits_actual == VA_BITS; + return alternative_has_cap_unlikely(ARM64_HAS_VA52); +} + +static inline bool mm_p4d_folded(const struct mm_struct *mm) +{ + return !pgtable_l5_enabled(); +} +#define mm_p4d_folded mm_p4d_folded + +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) + +#define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) +#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) +#define pgd_present(pgd) (!pgd_none(pgd)) + +static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (in_swapper_pgdir(pgdp)) { + set_swapper_pgd(pgdp, __pgd(pgd_val(pgd))); + return; + } + + WRITE_ONCE(*pgdp, pgd); + dsb(ishst); + isb(); +} + +static inline void pgd_clear(pgd_t *pgdp) +{ + if (pgtable_l5_enabled()) + set_pgd(pgdp, __pgd(0)); +} + +static inline phys_addr_t pgd_page_paddr(pgd_t pgd) +{ + return __pgd_to_phys(pgd); +} + +#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + +static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) +{ + return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); +} + +static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) +{ + BUG_ON(!pgtable_l5_enabled()); + + return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); +} + +static inline +p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr); +} +#define p4d_offset_lockless p4d_offset_lockless + +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) +{ + return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); +} + +static inline p4d_t *p4d_set_fixmap(unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return NULL; + return (p4d_t *)set_fixmap_offset(FIX_P4D, addr); +} + +static inline p4d_t *p4d_set_fixmap_offset(pgd_t *pgdp, unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return p4d_set_fixmap(p4d_offset_phys(pgdp, addr)); +} + +static inline void p4d_clear_fixmap(void) +{ + if (pgtable_l5_enabled()) + clear_fixmap(FIX_P4D); +} + +/* use ONLY for statically allocated translation tables */ +static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return (p4d_t *)__phys_to_kimg(p4d_offset_phys(pgdp, addr)); +} + +#define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) + +#else + +static inline bool pgtable_l5_enabled(void) { return false; } + +/* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */ +#define p4d_set_fixmap(addr) NULL +#define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) +#define p4d_clear_fixmap() + +#define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) + +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e)) @@ -848,8 +1048,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); } -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -extern int ptep_set_access_flags(struct vm_area_struct *vma, +extern int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); @@ -859,7 +1058,8 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { - return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); + return __ptep_set_access_flags(vma, address, (pte_t *)pmdp, + pmd_pte(entry), dirty); } static inline int pud_devmap(pud_t pud) @@ -893,12 +1093,13 @@ static inline bool pud_user_accessible_page(pud_t pud) /* * Atomic pte/pmd modifications. */ -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int __ptep_test_and_clear_young(pte_t *ptep) +static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) { pte_t old_pte, pte; - pte = READ_ONCE(*ptep); + pte = __ptep_get(ptep); do { old_pte = pte; pte = pte_mkold(pte); @@ -909,18 +1110,10 @@ static inline int __ptep_test_and_clear_young(pte_t *ptep) return pte_young(pte); } -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pte_t *ptep) -{ - return __ptep_test_and_clear_young(ptep); -} - -#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -static inline int ptep_clear_flush_young(struct vm_area_struct *vma, +static inline int __ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young = ptep_test_and_clear_young(vma, address, ptep); + int young = __ptep_test_and_clear_young(vma, address, ptep); if (young) { /* @@ -943,12 +1136,11 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); + return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, +static inline pte_t __ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); @@ -958,6 +1150,37 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, return pte; } +static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr, int full) +{ + for (;;) { + __ptep_get_and_clear(mm, addr, ptep); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} + +static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + unsigned int nr, int full) +{ + pte_t pte, tmp_pte; + + pte = __ptep_get_and_clear(mm, addr, ptep); + while (--nr) { + ptep++; + addr += PAGE_SIZE; + tmp_pte = __ptep_get_and_clear(mm, addr, ptep); + if (pte_dirty(tmp_pte)) + pte = pte_mkdirty(pte); + if (pte_young(tmp_pte)) + pte = pte_mkyoung(pte); + } + return pte; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, @@ -971,16 +1194,12 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -/* - * ptep_set_wrprotect - mark read-only while trasferring potential hardware - * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. - */ -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) +static inline void ___ptep_set_wrprotect(struct mm_struct *mm, + unsigned long address, pte_t *ptep, + pte_t pte) { - pte_t old_pte, pte; + pte_t old_pte; - pte = READ_ONCE(*ptep); do { old_pte = pte; pte = pte_wrprotect(pte); @@ -989,12 +1208,31 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres } while (pte_val(pte) != pte_val(old_pte)); } +/* + * __ptep_set_wrprotect - mark read-only while trasferring potential hardware + * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. + */ +static inline void __ptep_set_wrprotect(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + ___ptep_set_wrprotect(mm, address, ptep, __ptep_get(ptep)); +} + +static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, + pte_t *ptep, unsigned int nr) +{ + unsigned int i; + + for (i = 0; i < nr; i++, address += PAGE_SIZE, ptep++) + __ptep_set_wrprotect(mm, address, ptep); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - ptep_set_wrprotect(mm, address, (pte_t *)pmdp); + __ptep_set_wrprotect(mm, address, (pte_t *)pmdp); } #define pmdp_establish pmdp_establish @@ -1072,7 +1310,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif /* CONFIG_ARM64_MTE */ /* - * On AArch64, the cache coherency is handled via the set_pte_at() function. + * On AArch64, the cache coherency is handled via the __set_ptes() function. */ static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, @@ -1124,6 +1362,282 @@ extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, extern void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t new_pte); + +#ifdef CONFIG_ARM64_CONTPTE + +/* + * The contpte APIs are used to transparently manage the contiguous bit in ptes + * where it is possible and makes sense to do so. The PTE_CONT bit is considered + * a private implementation detail of the public ptep API (see below). + */ +extern void __contpte_try_fold(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte); +extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep); +extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned int nr); +extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr, int full); +extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + unsigned int nr, int full); +extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr); +extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t entry, int dirty); + +static __always_inline void contpte_try_fold(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, pte_t pte) +{ + /* + * Only bother trying if both the virtual and physical addresses are + * aligned and correspond to the last entry in a contig range. The core + * code mostly modifies ranges from low to high, so this is the likely + * the last modification in the contig range, so a good time to fold. + * We can't fold special mappings, because there is no associated folio. + */ + + const unsigned long contmask = CONT_PTES - 1; + bool valign = ((addr >> PAGE_SHIFT) & contmask) == contmask; + + if (unlikely(valign)) { + bool palign = (pte_pfn(pte) & contmask) == contmask; + + if (unlikely(palign && + pte_valid(pte) && !pte_cont(pte) && !pte_special(pte))) + __contpte_try_fold(mm, addr, ptep, pte); + } +} + +static __always_inline void contpte_try_unfold(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, pte_t pte) +{ + if (unlikely(pte_valid_cont(pte))) + __contpte_try_unfold(mm, addr, ptep, pte); +} + +#define pte_batch_hint pte_batch_hint +static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) +{ + if (!pte_valid_cont(pte)) + return 1; + + return CONT_PTES - (((unsigned long)ptep >> 3) & (CONT_PTES - 1)); +} + +/* + * The below functions constitute the public API that arm64 presents to the + * core-mm to manipulate PTE entries within their page tables (or at least this + * is the subset of the API that arm64 needs to implement). These public + * versions will automatically and transparently apply the contiguous bit where + * it makes sense to do so. Therefore any users that are contig-aware (e.g. + * hugetlb, kernel mapper) should NOT use these APIs, but instead use the + * private versions, which are prefixed with double underscore. All of these + * APIs except for ptep_get_lockless() are expected to be called with the PTL + * held. Although the contiguous bit is considered private to the + * implementation, it is deliberately allowed to leak through the getters (e.g. + * ptep_get()), back to core code. This is required so that pte_leaf_size() can + * provide an accurate size for perf_get_pgtable_size(). But this leakage means + * its possible a pte will be passed to a setter with the contiguous bit set, so + * we explicitly clear the contiguous bit in those cases to prevent accidentally + * setting it in the pgtable. + */ + +#define ptep_get ptep_get +static inline pte_t ptep_get(pte_t *ptep) +{ + pte_t pte = __ptep_get(ptep); + + if (likely(!pte_valid_cont(pte))) + return pte; + + return contpte_ptep_get(ptep, pte); +} + +#define ptep_get_lockless ptep_get_lockless +static inline pte_t ptep_get_lockless(pte_t *ptep) +{ + pte_t pte = __ptep_get(ptep); + + if (likely(!pte_valid_cont(pte))) + return pte; + + return contpte_ptep_get_lockless(ptep); +} + +static inline void set_pte(pte_t *ptep, pte_t pte) +{ + /* + * We don't have the mm or vaddr so cannot unfold contig entries (since + * it requires tlb maintenance). set_pte() is not used in core code, so + * this should never even be called. Regardless do our best to service + * any call and emit a warning if there is any attempt to set a pte on + * top of an existing contig range. + */ + pte_t orig_pte = __ptep_get(ptep); + + WARN_ON_ONCE(pte_valid_cont(orig_pte)); + __set_pte(ptep, pte_mknoncont(pte)); +} + +#define set_ptes set_ptes +static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned int nr) +{ + pte = pte_mknoncont(pte); + + if (likely(nr == 1)) { + contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); + __set_ptes(mm, addr, ptep, pte, 1); + contpte_try_fold(mm, addr, ptep, pte); + } else { + contpte_set_ptes(mm, addr, ptep, pte, nr); + } +} + +static inline void pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); + __pte_clear(mm, addr, ptep); +} + +#define clear_full_ptes clear_full_ptes +static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr, int full) +{ + if (likely(nr == 1)) { + contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); + __clear_full_ptes(mm, addr, ptep, nr, full); + } else { + contpte_clear_full_ptes(mm, addr, ptep, nr, full); + } +} + +#define get_and_clear_full_ptes get_and_clear_full_ptes +static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + unsigned int nr, int full) +{ + pte_t pte; + + if (likely(nr == 1)) { + contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); + pte = __get_and_clear_full_ptes(mm, addr, ptep, nr, full); + } else { + pte = contpte_get_and_clear_full_ptes(mm, addr, ptep, nr, full); + } + + return pte; +} + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); + return __ptep_get_and_clear(mm, addr, ptep); +} + +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + pte_t orig_pte = __ptep_get(ptep); + + if (likely(!pte_valid_cont(orig_pte))) + return __ptep_test_and_clear_young(vma, addr, ptep); + + return contpte_ptep_test_and_clear_young(vma, addr, ptep); +} + +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +static inline int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + pte_t orig_pte = __ptep_get(ptep); + + if (likely(!pte_valid_cont(orig_pte))) + return __ptep_clear_flush_young(vma, addr, ptep); + + return contpte_ptep_clear_flush_young(vma, addr, ptep); +} + +#define wrprotect_ptes wrprotect_ptes +static __always_inline void wrprotect_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, unsigned int nr) +{ + if (likely(nr == 1)) { + /* + * Optimization: wrprotect_ptes() can only be called for present + * ptes so we only need to check contig bit as condition for + * unfold, and we can remove the contig bit from the pte we read + * to avoid re-reading. This speeds up fork() which is sensitive + * for order-0 folios. Equivalent to contpte_try_unfold(). + */ + pte_t orig_pte = __ptep_get(ptep); + + if (unlikely(pte_cont(orig_pte))) { + __contpte_try_unfold(mm, addr, ptep, orig_pte); + orig_pte = pte_mknoncont(orig_pte); + } + ___ptep_set_wrprotect(mm, addr, ptep, orig_pte); + } else { + contpte_wrprotect_ptes(mm, addr, ptep, nr); + } +} + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + wrprotect_ptes(mm, addr, ptep, 1); +} + +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +static inline int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t entry, int dirty) +{ + pte_t orig_pte = __ptep_get(ptep); + + entry = pte_mknoncont(entry); + + if (likely(!pte_valid_cont(orig_pte))) + return __ptep_set_access_flags(vma, addr, ptep, entry, dirty); + + return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); +} + +#else /* CONFIG_ARM64_CONTPTE */ + +#define ptep_get __ptep_get +#define set_pte __set_pte +#define set_ptes __set_ptes +#define pte_clear __pte_clear +#define clear_full_ptes __clear_full_ptes +#define get_and_clear_full_ptes __get_and_clear_full_ptes +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define ptep_get_and_clear __ptep_get_and_clear +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +#define ptep_test_and_clear_young __ptep_test_and_clear_young +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define ptep_clear_flush_young __ptep_clear_flush_young +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +#define ptep_set_wrprotect __ptep_set_wrprotect +#define wrprotect_ptes __wrprotect_ptes +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +#define ptep_set_access_flags __ptep_set_access_flags + +#endif /* CONFIG_ARM64_CONTPTE */ + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5b0a04810b23..f77371232d8c 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -155,6 +155,8 @@ struct thread_struct { struct { unsigned long tp_value; /* TLS register */ unsigned long tp2_value; + u64 fpmr; + unsigned long pad; struct user_fpsimd_state fpsimd_state; } uw; @@ -253,6 +255,8 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != sizeof_field(struct thread_struct, uw.tp_value) + sizeof_field(struct thread_struct, uw.tp2_value) + + sizeof_field(struct thread_struct, uw.fpmr) + + sizeof_field(struct thread_struct, uw.pad) + sizeof_field(struct thread_struct, uw.fpsimd_state)); *offset = offsetof(struct thread_struct, uw); diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h index 581caac525b0..5b1701c76d1c 100644 --- a/arch/arm64/include/asm/ptdump.h +++ b/arch/arm64/include/asm/ptdump.h @@ -29,13 +29,6 @@ void __init ptdump_debugfs_register(struct ptdump_info *info, const char *name); static inline void ptdump_debugfs_register(struct ptdump_info *info, const char *name) { } #endif -void ptdump_check_wx(void); #endif /* CONFIG_PTDUMP_CORE */ -#ifdef CONFIG_DEBUG_WX -#define debug_checkwx() ptdump_check_wx() -#else -#define debug_checkwx() do { } while (0) -#endif - #endif /* __ASM_PTDUMP_H */ diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index 3fdae5fe3142..2e010ea76be2 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -33,37 +33,11 @@ #include <asm/cpufeature.h> #ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS -static inline bool should_patch_pac_into_scs(void) -{ - u64 reg; - - /* - * We only enable the shadow call stack dynamically if we are running - * on a system that does not implement PAC or BTI. PAC and SCS provide - * roughly the same level of protection, and BTI relies on the PACIASP - * instructions serving as landing pads, preventing us from patching - * those instructions into something else. - */ - reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1); - if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) | - SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg)) - return false; - - reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); - if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg)) - return false; - - if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) { - reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1); - if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT)) - return false; - } - return true; -} - static inline void dynamic_scs_init(void) { - if (should_patch_pac_into_scs()) { + extern bool __pi_dynamic_scs_is_enabled; + + if (__pi_dynamic_scs_is_enabled) { pr_info("Enabling dynamic shadow call stack\n"); static_branch_enable(&dynamic_scs_enabled); } @@ -72,8 +46,8 @@ static inline void dynamic_scs_init(void) static inline void dynamic_scs_init(void) {} #endif -int scs_patch(const u8 eh_frame[], int size); -asmlinkage void scs_patch_vmlinux(void); +int __pi_scs_patch(const u8 eh_frame[], int size); +asmlinkage void __pi_scs_patch_vmlinux(void); #endif /* __ASSEMBLY __ */ diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h index 2e4d7da74fb8..ba269a7a3201 100644 --- a/arch/arm64/include/asm/setup.h +++ b/arch/arm64/include/asm/setup.h @@ -7,9 +7,6 @@ #include <uapi/asm/setup.h> -void *get_early_fdt_ptr(void); -void early_fdt_map(u64 dt_phys); - /* * These two variables are used in the head.S file. */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index c3b19b376c86..9e8999592f3a 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -1181,6 +1181,8 @@ par; \ }) +#define SYS_FIELD_VALUE(reg, field, val) reg##_##field##_##val + #define SYS_FIELD_GET(reg, field, val) \ FIELD_GET(reg##_##field##_MASK, val) @@ -1188,7 +1190,8 @@ FIELD_PREP(reg##_##field##_MASK, val) #define SYS_FIELD_PREP_ENUM(reg, field, val) \ - FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val) + FIELD_PREP(reg##_##field##_MASK, \ + SYS_FIELD_VALUE(reg, field, val)) #endif diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 0150deb332af..a947c6e784ed 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -103,6 +103,9 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, { struct ptdesc *ptdesc = virt_to_ptdesc(pudp); + if (!pgtable_l4_enabled()) + return; + pagetable_pud_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 1deb5d789c2e..3b0e8248e1a4 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -422,7 +422,7 @@ do { \ #define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \ __flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled()); -static inline void __flush_tlb_range(struct vm_area_struct *vma, +static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long stride, bool last_level, int tlb_level) @@ -456,10 +456,19 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, __flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true, lpa2_is_enabled()); - dsb(ish); mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); } +static inline void __flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long stride, bool last_level, + int tlb_level) +{ + __flush_tlb_range_nosync(vma, start, end, stride, + last_level, tlb_level); + dsb(ish); +} + static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { |