diff options
Diffstat (limited to 'arch/arm64/include/asm')
28 files changed, 679 insertions, 191 deletions
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index ab8b396428..bc0b0d75ac 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -50,16 +50,12 @@ msr daif, \flags .endm - .macro enable_dbg - msr daifclr, #8 - .endm - .macro disable_step_tsk, flgs, tmp tbz \flgs, #TIF_SINGLESTEP, 9990f mrs \tmp, mdscr_el1 bic \tmp, \tmp, #DBG_MDSCR_SS msr mdscr_el1, \tmp - isb // Synchronise with enable_dbg + isb // Take effect before a subsequent clear of DAIF.D 9990: .endm @@ -480,9 +476,10 @@ alternative_endif */ .macro reset_pmuserenr_el0, tmpreg mrs \tmpreg, id_aa64dfr0_el1 - sbfx \tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4 - cmp \tmpreg, #1 // Skip if no PMU present - b.lt 9000f + ubfx \tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4 + cmp \tmpreg, #ID_AA64DFR0_EL1_PMUVer_NI + ccmp \tmpreg, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne + b.eq 9000f // Skip if no PMU present or IMP_DEF msr pmuserenr_el0, xzr // Disable PMU access from EL0 9000: .endm diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index cf2987464c..1ca947d5c9 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -40,6 +40,10 @@ */ #define dgh() asm volatile("hint #6" : : : "memory") +#define spec_bar() asm volatile(ALTERNATIVE("dsb nsh\nisb\n", \ + SB_BARRIER_INSN"nop\n", \ + ARM64_HAS_SB)) + #ifdef CONFIG_ARM64_PSEUDO_NMI #define pmr_sync() \ do { \ diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 270680e2b5..7529c02639 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -58,6 +58,8 @@ cpucap_is_possible(const unsigned int cap) return IS_ENABLED(CONFIG_NVIDIA_CARMEL_CNP_ERRATUM); case ARM64_WORKAROUND_REPEAT_TLBI: return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI); + case ARM64_WORKAROUND_SPECULATIVE_SSBS: + return IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS); } return true; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 52f076afeb..7b32b99023 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,9 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -159,6 +162,9 @@ #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_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #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) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index b7afaa0268..fd87c4b8f9 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -59,13 +59,14 @@ .macro __init_el2_debug mrs x1, id_aa64dfr0_el1 - sbfx x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4 - cmp x0, #1 - b.lt .Lskip_pmu_\@ // Skip if no PMU present + ubfx x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4 + cmp x0, #ID_AA64DFR0_EL1_PMUVer_NI + ccmp x0, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne + b.eq .Lskip_pmu_\@ // Skip if no PMU present or IMP_DEF mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to .Lskip_pmu_\@: - csel x2, xzr, x0, lt // all PMU counters from EL1 + csel x2, xzr, x0, eq // all PMU counters from EL1 /* Statistical profiling */ ubfx x0, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4 @@ -145,7 +146,7 @@ /* Coprocessor traps */ .macro __init_el2_cptr __check_hvhe .LnVHE_\@, x1 - mov x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN) + mov x0, #CPACR_ELx_FPEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ .LnVHE_\@: @@ -276,7 +277,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SVE traps - orr x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN) + orr x0, x0, #CPACR_ELx_ZEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ @@ -297,7 +298,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SME traps - orr x0, x0, #(CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN) + orr x0, x0, #CPACR_ELx_SMEN msr cpacr_el1, x0 b .Lskip_set_cptr_sme_\@ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 81606bf7d5..7abf09df70 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -404,6 +404,18 @@ static inline bool esr_fsc_is_access_flag_fault(unsigned long esr) return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS; } +/* Indicate whether ESR.EC==0x1A is for an ERETAx instruction */ +static inline bool esr_iss_is_eretax(unsigned long esr) +{ + return esr & ESR_ELx_ERET_ISS_ERET; +} + +/* Indicate which key is used for ERETAx (false: A-Key, true: B-Key) */ +static inline bool esr_iss_is_eretab(unsigned long esr) +{ + return esr & ESR_ELx_ERET_ISS_ERETA; +} + const char *esr_get_class_string(unsigned long esr); #endif /* __ASSEMBLY */ diff --git a/arch/arm64/include/asm/fb.h b/arch/arm64/include/asm/fb.h deleted file mode 100644 index 1a495d8fb2..0000000000 --- a/arch/arm64/include/asm/fb.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 ARM Ltd. - */ -#ifndef __ASM_FB_H_ -#define __ASM_FB_H_ - -#include <asm-generic/fb.h> - -#endif /* __ASM_FB_H_ */ diff --git a/arch/arm64/include/asm/fpu.h b/arch/arm64/include/asm/fpu.h new file mode 100644 index 0000000000..2ae50bdce5 --- /dev/null +++ b/arch/arm64/include/asm/fpu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef __ASM_FPU_H +#define __ASM_FPU_H + +#include <asm/neon.h> + +#define kernel_fpu_available() cpu_has_neon() +#define kernel_fpu_begin() kernel_neon_begin() +#define kernel_fpu_end() kernel_neon_end() + +#endif /* ! __ASM_FPU_H */ diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 2ddc33d93b..3954cbd2ff 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -18,11 +18,11 @@ extern bool arch_hugetlb_migration_supported(struct hstate *h); #endif -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index db1aeacd4c..8c0a36f72d 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -135,6 +135,12 @@ enum aarch64_insn_special_register { AARCH64_INSN_SPCLREG_SP_EL2 = 0xF210 }; +enum aarch64_insn_system_register { + AARCH64_INSN_SYSREG_TPIDR_EL1 = 0x4684, + AARCH64_INSN_SYSREG_TPIDR_EL2 = 0x6682, + AARCH64_INSN_SYSREG_SP_EL0 = 0x4208, +}; + enum aarch64_insn_variant { AARCH64_INSN_VARIANT_32BIT, AARCH64_INSN_VARIANT_64BIT @@ -686,6 +692,8 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, } #endif u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type); +u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, + enum aarch64_insn_system_register sysreg); 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 8d825522c5..41fd90895d 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -140,6 +140,134 @@ extern void __memset_io(volatile void __iomem *, int, size_t); #define memcpy_toio(c,a,l) __memcpy_toio((c),(a),(l)) /* + * The ARM64 iowrite implementation is intended to support drivers that want to + * use write combining. For instance PCI drivers using write combining with a 64 + * byte __iowrite64_copy() expect to get a 64 byte MemWr TLP on the PCIe bus. + * + * Newer ARM core have sensitive write combining buffers, it is important that + * the stores be contiguous blocks of store instructions. Normal memcpy + * approaches have a very low chance to generate write combining. + * + * Since this is the only API on ARM64 that should be used with write combining + * it also integrates the DGH hint which is supposed to lower the latency to + * emit the large TLP from the CPU. + */ + +static __always_inline void +__const_memcpy_toio_aligned32(volatile u32 __iomem *to, const u32 *from, + size_t count) +{ + switch (count) { + case 8: + asm volatile("str %w0, [%8, #4 * 0]\n" + "str %w1, [%8, #4 * 1]\n" + "str %w2, [%8, #4 * 2]\n" + "str %w3, [%8, #4 * 3]\n" + "str %w4, [%8, #4 * 4]\n" + "str %w5, [%8, #4 * 5]\n" + "str %w6, [%8, #4 * 6]\n" + "str %w7, [%8, #4 * 7]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "rZ"(from[4]), "rZ"(from[5]), + "rZ"(from[6]), "rZ"(from[7]), "r"(to)); + break; + case 4: + asm volatile("str %w0, [%4, #4 * 0]\n" + "str %w1, [%4, #4 * 1]\n" + "str %w2, [%4, #4 * 2]\n" + "str %w3, [%4, #4 * 3]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "r"(to)); + break; + case 2: + asm volatile("str %w0, [%2, #4 * 0]\n" + "str %w1, [%2, #4 * 1]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "r"(to)); + break; + case 1: + __raw_writel(*from, to); + break; + default: + BUILD_BUG(); + } +} + +void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count); + +static __always_inline void +__iowrite32_copy(void __iomem *to, const void *from, size_t count) +{ + if (__builtin_constant_p(count) && + (count == 8 || count == 4 || count == 2 || count == 1)) { + __const_memcpy_toio_aligned32(to, from, count); + dgh(); + } else { + __iowrite32_copy_full(to, from, count); + } +} +#define __iowrite32_copy __iowrite32_copy + +static __always_inline void +__const_memcpy_toio_aligned64(volatile u64 __iomem *to, const u64 *from, + size_t count) +{ + switch (count) { + case 8: + asm volatile("str %x0, [%8, #8 * 0]\n" + "str %x1, [%8, #8 * 1]\n" + "str %x2, [%8, #8 * 2]\n" + "str %x3, [%8, #8 * 3]\n" + "str %x4, [%8, #8 * 4]\n" + "str %x5, [%8, #8 * 5]\n" + "str %x6, [%8, #8 * 6]\n" + "str %x7, [%8, #8 * 7]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "rZ"(from[4]), "rZ"(from[5]), + "rZ"(from[6]), "rZ"(from[7]), "r"(to)); + break; + case 4: + asm volatile("str %x0, [%4, #8 * 0]\n" + "str %x1, [%4, #8 * 1]\n" + "str %x2, [%4, #8 * 2]\n" + "str %x3, [%4, #8 * 3]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "r"(to)); + break; + case 2: + asm volatile("str %x0, [%2, #8 * 0]\n" + "str %x1, [%2, #8 * 1]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "r"(to)); + break; + case 1: + __raw_writeq(*from, to); + break; + default: + BUILD_BUG(); + } +} + +void __iowrite64_copy_full(void __iomem *to, const void *from, size_t count); + +static __always_inline void +__iowrite64_copy(void __iomem *to, const void *from, size_t count) +{ + if (__builtin_constant_p(count) && + (count == 8 || count == 4 || count == 2 || count == 1)) { + __const_memcpy_toio_aligned64(to, from, count); + dgh(); + } else { + __iowrite64_copy_full(to, from, count); + } +} +#define __iowrite64_copy __iowrite64_copy + +/* * I/O memory mapping functions. */ diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 6aafbb7899..4e753908b8 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -15,17 +15,23 @@ #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE +#define JUMP_TABLE_ENTRY(key, label) \ + ".pushsection __jump_table, \"aw\"\n\t" \ + ".align 3\n\t" \ + ".long 1b - ., %l["#label"] - .\n\t" \ + ".quad %c0 - .\n\t" \ + ".popsection\n\t" \ + : : "i"(key) : : label + static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { + char *k = &((char *)key)[branch]; + asm goto( "1: nop \n\t" - " .pushsection __jump_table, \"aw\" \n\t" - " .align 3 \n\t" - " .long 1b - ., %l[l_yes] - . \n\t" - " .quad %c0 - . \n\t" - " .popsection \n\t" - : : "i"(&((char *)key)[branch]) : : l_yes); + JUMP_TABLE_ENTRY(k, l_yes) + ); return false; l_yes: @@ -35,15 +41,11 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { + char *k = &((char *)key)[branch]; asm goto( "1: b %l[l_yes] \n\t" - " .pushsection __jump_table, \"aw\" \n\t" - " .align 3 \n\t" - " .long 1b - ., %l[l_yes] - . \n\t" - " .quad %c0 - . \n\t" - " .popsection \n\t" - : : "i"(&((char *)key)[branch]) : : l_yes); - + JUMP_TABLE_ENTRY(k, l_yes) + ); return false; l_yes: return true; diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index e01bb5ca13..b2adc2c6c8 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -305,6 +305,12 @@ GENMASK(19, 14) | \ BIT(11)) +#define CPTR_VHE_EL2_RES0 (GENMASK(63, 32) | \ + GENMASK(27, 26) | \ + GENMASK(23, 22) | \ + GENMASK(19, 18) | \ + GENMASK(15, 0)) + /* Hyp Debug Configuration Register bits */ #define MDCR_EL2_E2TB_MASK (UL(0x3)) #define MDCR_EL2_E2TB_SHIFT (UL(24)) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 24b5e6b234..a6330460d9 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -73,10 +73,8 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range, __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context, __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff, - __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr, - __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr, - __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs, - __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs, + __KVM_HOST_SMCCC_FUNC___vgic_v3_save_vmcr_aprs, + __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs, __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps, __KVM_HOST_SMCCC_FUNC___pkvm_init_vm, __KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu, @@ -241,8 +239,6 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu); extern u64 __vgic_v3_get_gic_config(void); -extern u64 __vgic_v3_read_vmcr(void); -extern void __vgic_v3_write_vmcr(u32 vmcr); extern void __vgic_v3_init_lrs(void); extern u64 __kvm_get_mdcr_el2(void); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 975af30af3..21650e7924 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -125,16 +125,6 @@ static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_TWI; } -static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK); -} - -static inline void vcpu_ptrauth_disable(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK); -} - static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu) { return vcpu->arch.vsesr_el2; @@ -567,6 +557,68 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) vcpu_set_flag((v), e); \ } while (0) +#define __build_check_all_or_none(r, bits) \ + BUILD_BUG_ON(((r) & (bits)) && ((r) & (bits)) != (bits)) + +#define __cpacr_to_cptr_clr(clr, set) \ + ({ \ + u64 cptr = 0; \ + \ + if ((set) & CPACR_ELx_FPEN) \ + cptr |= CPTR_EL2_TFP; \ + if ((set) & CPACR_ELx_ZEN) \ + cptr |= CPTR_EL2_TZ; \ + if ((set) & CPACR_ELx_SMEN) \ + cptr |= CPTR_EL2_TSM; \ + if ((clr) & CPACR_ELx_TTA) \ + cptr |= CPTR_EL2_TTA; \ + if ((clr) & CPTR_EL2_TAM) \ + cptr |= CPTR_EL2_TAM; \ + if ((clr) & CPTR_EL2_TCPAC) \ + cptr |= CPTR_EL2_TCPAC; \ + \ + cptr; \ + }) + +#define __cpacr_to_cptr_set(clr, set) \ + ({ \ + u64 cptr = 0; \ + \ + if ((clr) & CPACR_ELx_FPEN) \ + cptr |= CPTR_EL2_TFP; \ + if ((clr) & CPACR_ELx_ZEN) \ + cptr |= CPTR_EL2_TZ; \ + if ((clr) & CPACR_ELx_SMEN) \ + cptr |= CPTR_EL2_TSM; \ + if ((set) & CPACR_ELx_TTA) \ + cptr |= CPTR_EL2_TTA; \ + if ((set) & CPTR_EL2_TAM) \ + cptr |= CPTR_EL2_TAM; \ + if ((set) & CPTR_EL2_TCPAC) \ + cptr |= CPTR_EL2_TCPAC; \ + \ + cptr; \ + }) + +#define cpacr_clear_set(clr, set) \ + do { \ + BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0); \ + BUILD_BUG_ON((clr) & CPACR_ELx_E0POE); \ + __build_check_all_or_none((clr), CPACR_ELx_FPEN); \ + __build_check_all_or_none((set), CPACR_ELx_FPEN); \ + __build_check_all_or_none((clr), CPACR_ELx_ZEN); \ + __build_check_all_or_none((set), CPACR_ELx_ZEN); \ + __build_check_all_or_none((clr), CPACR_ELx_SMEN); \ + __build_check_all_or_none((set), CPACR_ELx_SMEN); \ + \ + if (has_vhe() || has_hvhe()) \ + sysreg_clear_set(cpacr_el1, clr, set); \ + else \ + sysreg_clear_set(cptr_el2, \ + __cpacr_to_cptr_clr(clr, set), \ + __cpacr_to_cptr_set(clr, set));\ + } while (0) + static __always_inline void kvm_write_cptr_el2(u64 val) { if (has_vhe() || has_hvhe()) @@ -580,23 +632,20 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) u64 val; if (has_vhe()) { - val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN | - CPACR_EL1_ZEN_EL1EN); + val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN); if (cpus_have_final_cap(ARM64_SME)) val |= CPACR_EL1_SMEN_EL1EN; } else if (has_hvhe()) { - val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN); + val = CPACR_ELx_FPEN; - if (!vcpu_has_sve(vcpu) || - (vcpu->arch.fp_state != FP_STATE_GUEST_OWNED)) - val |= CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN; + if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs()) + val |= CPACR_ELx_ZEN; if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN; + val |= CPACR_ELx_SMEN; } else { val = CPTR_NVHE_EL2_RES1; - if (vcpu_has_sve(vcpu) && - (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)) + if (vcpu_has_sve(vcpu) && guest_owns_fp_regs()) val |= CPTR_EL2_TZ; if (cpus_have_final_cap(ARM64_SME)) val &= ~CPTR_EL2_TSM; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 9e8a496fb2..36b8e97bf4 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -76,6 +76,7 @@ static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); extern unsigned int __ro_after_init kvm_sve_max_vl; +extern unsigned int __ro_after_init kvm_host_sve_max_vl; int __init kvm_arm_init_sve(void); u32 __attribute_const__ kvm_target_cpu(void); @@ -211,6 +212,7 @@ typedef unsigned int pkvm_handle_t; struct kvm_protected_vm { pkvm_handle_t handle; struct kvm_hyp_memcache teardown_mc; + bool enabled; }; struct kvm_mpidr_data { @@ -220,20 +222,10 @@ struct kvm_mpidr_data { static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr) { - unsigned long mask = data->mpidr_mask; - u64 aff = mpidr & MPIDR_HWID_BITMASK; - int nbits, bit, bit_idx = 0; - u16 index = 0; + unsigned long index = 0, mask = data->mpidr_mask; + unsigned long aff = mpidr & MPIDR_HWID_BITMASK; - /* - * If this looks like RISC-V's BEXT or x86's PEXT - * instructions, it isn't by accident. - */ - nbits = fls(mask); - for_each_set_bit(bit, &mask, nbits) { - index |= (aff & BIT(bit)) >> (bit - bit_idx); - bit_idx++; - } + bitmap_gather(&index, &aff, &mask, fls(mask)); return index; } @@ -530,8 +522,64 @@ struct kvm_cpu_context { u64 *vncr_array; }; +struct cpu_sve_state { + __u64 zcr_el1; + + /* + * Ordering is important since __sve_save_state/__sve_restore_state + * relies on it. + */ + __u32 fpsr; + __u32 fpcr; + + /* Must be SVE_VQ_BYTES (128 bit) aligned. */ + __u8 sve_regs[]; +}; + +/* + * This structure is instantiated on a per-CPU basis, and contains + * data that is: + * + * - tied to a single physical CPU, and + * - either have a lifetime that does not extend past vcpu_put() + * - or is an invariant for the lifetime of the system + * + * Use host_data_ptr(field) as a way to access a pointer to such a + * field. + */ struct kvm_host_data { struct kvm_cpu_context host_ctxt; + + /* + * All pointers in this union are hyp VA. + * sve_state is only used in pKVM and if system_supports_sve(). + */ + union { + struct user_fpsimd_state *fpsimd_state; + struct cpu_sve_state *sve_state; + }; + + /* Ownership of the FP regs */ + enum { + FP_STATE_FREE, + FP_STATE_HOST_OWNED, + FP_STATE_GUEST_OWNED, + } fp_owner; + + /* + * host_debug_state contains the host registers which are + * saved and restored during world switches. + */ + struct { + /* {Break,watch}point registers */ + struct kvm_guest_debug_arch regs; + /* Statistical profiling extension */ + u64 pmscr_el1; + /* Self-hosted trace */ + u64 trfcr_el1; + /* Values of trap registers for the host before guest entry. */ + u64 mdcr_el2; + } host_debug_state; }; struct kvm_host_psci_config { @@ -592,19 +640,9 @@ struct kvm_vcpu_arch { u64 mdcr_el2; u64 cptr_el2; - /* Values of trap registers for the host before guest entry. */ - u64 mdcr_el2_host; - /* Exception Information */ struct kvm_vcpu_fault_info fault; - /* Ownership of the FP regs */ - enum { - FP_STATE_FREE, - FP_STATE_HOST_OWNED, - FP_STATE_GUEST_OWNED, - } fp_state; - /* Configuration flags, set once and for all before the vcpu can run */ u8 cflags; @@ -627,11 +665,10 @@ struct kvm_vcpu_arch { * We maintain more than a single set of debug registers to support * debugging the guest from the host and to maintain separate host and * guest state during world switches. vcpu_debug_state are the debug - * registers of the vcpu as the guest sees them. host_debug_state are - * the host registers which are saved and restored during - * world switches. external_debug_state contains the debug - * values we want to debug the guest. This is set via the - * KVM_SET_GUEST_DEBUG ioctl. + * registers of the vcpu as the guest sees them. + * + * external_debug_state contains the debug values we want to debug the + * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl. * * debug_ptr points to the set of debug registers that should be loaded * onto the hardware when running the guest. @@ -640,18 +677,6 @@ struct kvm_vcpu_arch { struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; - struct user_fpsimd_state *host_fpsimd_state; /* hyp VA */ - struct task_struct *parent_task; - - struct { - /* {Break,watch}point registers */ - struct kvm_guest_debug_arch regs; - /* Statistical profiling extension */ - u64 pmscr_el1; - /* Self-hosted trace */ - u64 trfcr_el1; - } host_debug_state; - /* VGIC state */ struct vgic_cpu vgic_cpu; struct arch_timer_cpu timer_cpu; @@ -817,8 +842,6 @@ struct kvm_vcpu_arch { #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)) -/* vcpu running in HYP context */ -#define VCPU_HYP_CONTEXT __vcpu_single_flag(iflags, BIT(7)) /* SVE enabled for host EL0 */ #define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) @@ -896,7 +919,7 @@ struct kvm_vcpu_arch { * Don't bother with VNCR-based accesses in the nVHE code, it has no * business dealing with NV. */ -static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) +static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) { #if !defined (__KVM_NVHE_HYPERVISOR__) if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && @@ -906,6 +929,13 @@ static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) return (u64 *)&ctxt->sys_regs[r]; } +#define __ctxt_sys_reg(c,r) \ + ({ \ + BUILD_BUG_ON(__builtin_constant_p(r) && \ + (r) >= NR_SYS_REGS); \ + ___ctxt_sys_reg(c, r); \ + }) + #define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r)) u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg); @@ -1168,6 +1198,44 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data); +/* + * How we access per-CPU host data depends on the where we access it from, + * and the mode we're in: + * + * - VHE and nVHE hypervisor bits use their locally defined instance + * + * - the rest of the kernel use either the VHE or nVHE one, depending on + * the mode we're running in. + * + * Unless we're in protected mode, fully deprivileged, and the nVHE + * per-CPU stuff is exclusively accessible to the protected EL2 code. + * In this case, the EL1 code uses the *VHE* data as its private state + * (which makes sense in a way as there shouldn't be any shared state + * between the host and the hypervisor). + * + * Yes, this is all totally trivial. Shoot me now. + */ +#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) +#define host_data_ptr(f) (&this_cpu_ptr(&kvm_host_data)->f) +#else +#define host_data_ptr(f) \ + (static_branch_unlikely(&kvm_protected_mode_initialized) ? \ + &this_cpu_ptr(&kvm_host_data)->f : \ + &this_cpu_ptr_hyp_sym(kvm_host_data)->f) +#endif + +/* Check whether the FP regs are owned by the guest */ +static inline bool guest_owns_fp_regs(void) +{ + return *host_data_ptr(fp_owner) == FP_STATE_GUEST_OWNED; +} + +/* Check whether the FP regs are owned by the host */ +static inline bool host_owns_fp_regs(void) +{ + return *host_data_ptr(fp_owner) == FP_STATE_HOST_OWNED; +} + static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ @@ -1211,7 +1279,6 @@ 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) { @@ -1247,10 +1314,9 @@ struct kvm *kvm_arch_alloc_vm(void); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE -static inline bool kvm_vm_is_protected(struct kvm *kvm) -{ - return false; -} +#define kvm_vm_is_protected(kvm) (is_protected_kvm_enabled() && (kvm)->arch.pkvm.enabled) + +#define vcpu_is_protected(vcpu) kvm_vm_is_protected((vcpu)->kvm) int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature); bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); @@ -1275,6 +1341,8 @@ static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature) #define vcpu_has_feature(v, f) __vcpu_has_feature(&(v)->kvm->arch, (f)) +#define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED) + int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM extern phys_addr_t hyp_mem_base; @@ -1331,4 +1399,19 @@ bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \ get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max)) +/* Check for a given level of PAuth support */ +#define kvm_has_pauth(k, l) \ + ({ \ + bool pa, pi, pa3; \ + \ + pa = kvm_has_feat((k), ID_AA64ISAR1_EL1, APA, l); \ + pa &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPA, IMP); \ + pi = kvm_has_feat((k), ID_AA64ISAR1_EL1, API, l); \ + pi &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPI, IMP); \ + pa3 = kvm_has_feat((k), ID_AA64ISAR2_EL1, APA3, l); \ + pa3 &= kvm_has_feat((k), ID_AA64ISAR2_EL1, GPA3, IMP); \ + \ + (pa + pi + pa3) == 1; \ + }) + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 3e2a1ac0c9..b05bceca33 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -80,8 +80,8 @@ void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if); void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if); void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if); void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if); -void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if); -void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if); +void __vgic_v3_save_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if); +void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if); int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu); #ifdef __KVM_NVHE_HYPERVISOR__ @@ -111,7 +111,8 @@ 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_restore_state(void *sve_pffr, u32 *fpsr); +void __sve_save_state(void *sve_pffr, u32 *fpsr, int save_ffr); +void __sve_restore_state(void *sve_pffr, u32 *fpsr, int restore_ffr); u64 __guest_enter(struct kvm_vcpu *vcpu); @@ -142,5 +143,6 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val); extern unsigned long kvm_nvhe_sym(__icache_flags); extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits); +extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl); #endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index c77d795556..5e0ab05962 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -60,7 +60,20 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0) return ttbr0 & ~GENMASK_ULL(63, 48); } +extern bool forward_smc_trap(struct kvm_vcpu *vcpu); int kvm_init_nv_sysregs(struct kvm *kvm); +#ifdef CONFIG_ARM64_PTR_AUTH +bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr); +#else +static inline bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr) +{ + /* We really should never execute this... */ + WARN_ON_ONCE(1); + *elr = 0xbad9acc0debadbad; + return false; +} +#endif + #endif /* __ARM64_KVM_NESTED_H */ diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h index ad9cfb5c1f..cd56acd9a8 100644 --- a/arch/arm64/include/asm/kvm_pkvm.h +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -128,4 +128,13 @@ static inline unsigned long hyp_ffa_proxy_pages(void) return (2 * KVM_FFA_MBOX_NR_PAGES) + DIV_ROUND_UP(desc_max, PAGE_SIZE); } +static inline size_t pkvm_host_sve_state_size(void) +{ + if (!system_supports_sve()) + return 0; + + return size_add(sizeof(struct cpu_sve_state), + SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl))); +} + #endif /* __ARM64_KVM_PKVM_H__ */ diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h index 0cd0965255..d81bac256a 100644 --- a/arch/arm64/include/asm/kvm_ptrauth.h +++ b/arch/arm64/include/asm/kvm_ptrauth.h @@ -99,5 +99,26 @@ alternative_else_nop_endif .macro ptrauth_switch_to_hyp g_ctxt, h_ctxt, reg1, reg2, reg3 .endm #endif /* CONFIG_ARM64_PTR_AUTH */ + +#else /* !__ASSEMBLY */ + +#define __ptrauth_save_key(ctxt, key) \ + do { \ + u64 __val; \ + __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ + ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \ + __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ + ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val; \ + } while(0) + +#define ptrauth_save_keys(ctxt) \ + do { \ + __ptrauth_save_key(ctxt, APIA); \ + __ptrauth_save_key(ctxt, APIB); \ + __ptrauth_save_key(ctxt, APDA); \ + __ptrauth_save_key(ctxt, APDB); \ + __ptrauth_save_key(ctxt, APGA); \ + } while(0) + #endif /* __ASSEMBLY__ */ #endif /* __ASM_KVM_PTRAUTH_H */ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index ef207a0d4f..1f60aa1bc7 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -170,6 +170,7 @@ #define PTE_CONT (_AT(pteval_t, 1) << 52) /* Contiguous range */ #define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */ #define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */ +#define PTE_SWBITS_MASK _AT(pteval_t, (BIT(63) | GENMASK(58, 55))) #define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (50 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) #ifdef CONFIG_ARM64_PA_BITS_52 @@ -297,6 +298,7 @@ #define TCR_TBI1 (UL(1) << 38) #define TCR_HA (UL(1) << 39) #define TCR_HD (UL(1) << 40) +#define TCR_TBID0 (UL(1) << 51) #define TCR_TBID1 (UL(1) << 52) #define TCR_NFD0 (UL(1) << 53) #define TCR_NFD1 (UL(1) << 54) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index dd9ee67d1d..b11cfb9fdd 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -18,14 +18,21 @@ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define PTE_DEVMAP (_AT(pteval_t, 1) << 57) -#define PTE_PROT_NONE (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */ /* - * This bit indicates that the entry is present i.e. pmd_page() - * still points to a valid huge page in memory even if the pmd - * has been invalidated. + * PTE_PRESENT_INVALID=1 & PTE_VALID=0 indicates that the pte's fields should be + * interpreted according to the HW layout by SW but any attempted HW access to + * the address will result in a fault. pte_present() returns true. */ -#define PMD_PRESENT_INVALID (_AT(pteval_t, 1) << 59) /* only when !PMD_SECT_VALID */ +#define PTE_PRESENT_INVALID (PTE_NG) /* only when !PTE_VALID */ + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +#define PTE_UFFD_WP (_AT(pteval_t, 1) << 58) /* uffd-wp tracking */ +#define PTE_SWP_UFFD_WP (_AT(pteval_t, 1) << 3) /* only for swp ptes */ +#else +#define PTE_UFFD_WP (_AT(pteval_t, 0)) +#define PTE_SWP_UFFD_WP (_AT(pteval_t, 0)) +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) @@ -103,7 +110,7 @@ static inline bool __pure lpa2_is_enabled(void) __val; \ }) -#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) +#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PRESENT_INVALID | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) /* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ #define PAGE_SHARED __pgprot(_PAGE_SHARED) #define PAGE_SHARED_EXEC __pgprot(_PAGE_SHARED_EXEC) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index afdd56d26a..7a4f5604be 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -49,12 +49,6 @@ __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 @@ -105,7 +99,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) /* * The following only work if pte_present(). Undefined behaviour otherwise. */ -#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))) +#define pte_present(pte) (pte_valid(pte) || pte_present_invalid(pte)) #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)) @@ -132,6 +126,8 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) +#define pte_present_invalid(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID) /* * Execute-only user mappings do not have the PTE_USER bit set. All valid * kernel mappings have the PTE_UXN bit set. @@ -261,6 +257,13 @@ static inline pte_t pte_mkpresent(pte_t pte) return set_pte_bit(pte, __pgprot(PTE_VALID)); } +static inline pte_t pte_mkinvalid(pte_t pte) +{ + pte = set_pte_bit(pte, __pgprot(PTE_PRESENT_INVALID)); + pte = clear_pte_bit(pte, __pgprot(PTE_VALID)); + return pte; +} + static inline pmd_t pmd_mkcont(pmd_t pmd) { return __pmd(pmd_val(pmd) | PMD_SECT_CONT); @@ -271,9 +274,31 @@ 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) +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline int pte_uffd_wp(pte_t pte) +{ + return !!(pte_val(pte) & PTE_UFFD_WP); +} + +static inline pte_t pte_mkuffd_wp(pte_t pte) +{ + return pte_wrprotect(set_pte_bit(pte, __pgprot(PTE_UFFD_WP))); +} + +static inline pte_t pte_clear_uffd_wp(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_UFFD_WP)); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +static inline void __set_pte_nosync(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); +} + +static inline void __set_pte(pte_t *ptep, pte_t pte) +{ + __set_pte_nosync(ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance @@ -463,13 +488,39 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline pte_t pte_swp_mkuffd_wp(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); +} + +static inline int pte_swp_uffd_wp(pte_t pte) +{ + return !!(pte_val(pte) & PTE_SWP_UFFD_WP); +} + +static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { - return (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) == PTE_PROT_NONE; + /* + * pte_present_invalid() tells us that the pte is invalid from HW + * perspective but present from SW perspective, so the fields are to be + * interpretted as per the HW layout. The second 2 checks are the unique + * encoding that we use for PROT_NONE. It is insufficient to only use + * the first check because we share the same encoding scheme with pmds + * which support pmd_mkinvalid(), so can be present-invalid without + * being PROT_NONE. + */ + return pte_present_invalid(pte) && !pte_user(pte) && !pte_user_exec(pte); } static inline int pmd_protnone(pmd_t pmd) @@ -478,12 +529,7 @@ static inline int pmd_protnone(pmd_t pmd) } #endif -#define pmd_present_invalid(pmd) (!!(pmd_val(pmd) & PMD_PRESENT_INVALID)) - -static inline int pmd_present(pmd_t pmd) -{ - return pte_present(pmd_pte(pmd)) || pmd_present_invalid(pmd); -} +#define pmd_present(pmd) pte_present(pmd_pte(pmd)) /* * THP definitions. @@ -508,16 +554,16 @@ static inline int pmd_trans_huge(pmd_t pmd) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) - -static inline pmd_t pmd_mkinvalid(pmd_t pmd) -{ - pmd = set_pmd_bit(pmd, __pgprot(PMD_PRESENT_INVALID)); - pmd = clear_pmd_bit(pmd, __pgprot(PMD_SECT_VALID)); - - return pmd; -} - -#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) +#define pmd_mkinvalid(pmd) pte_pmd(pte_mkinvalid(pmd_pte(pmd))) +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +#define pmd_uffd_wp(pmd) pte_uffd_wp(pmd_pte(pmd)) +#define pmd_mkuffd_wp(pmd) pte_pmd(pte_mkuffd_wp(pmd_pte(pmd))) +#define pmd_clear_uffd_wp(pmd) pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd))) +#define pmd_swp_uffd_wp(pmd) pte_swp_uffd_wp(pmd_pte(pmd)) +#define pmd_swp_mkuffd_wp(pmd) pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd))) +#define pmd_swp_clear_uffd_wp(pmd) \ + pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd))) +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define pmd_write(pmd) pte_write(pmd_pte(pmd)) @@ -709,7 +755,11 @@ 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)) +#ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) +#else +#define pud_leaf(pud) false +#endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) @@ -760,6 +810,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) #else +#define pud_valid(pud) false #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) #define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ @@ -1005,6 +1056,8 @@ static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) static inline bool pgtable_l5_enabled(void) { return false; } +#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + /* 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) @@ -1012,6 +1065,28 @@ static inline bool pgtable_l5_enabled(void) { return false; } #define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) +static inline +p4d_t *p4d_offset_lockless_folded(pgd_t *pgdp, pgd_t pgd, unsigned long addr) +{ + /* + * With runtime folding of the pud, pud_offset_lockless() passes + * the 'pgd_t *' we return here to p4d_to_folded_pud(), which + * will offset the pointer assuming that it points into + * a page-table page. However, the fast GUP path passes us a + * pgd_t allocated on the stack and so we must use the original + * pointer in 'pgdp' to construct the p4d pointer instead of + * using the generic p4d_offset_lockless() implementation. + * + * Note: reusing the original pointer means that we may + * dereference the same (live) page-table entry multiple times. + * This is safe because it is still only loaded once in the + * context of each level and the CPU guarantees same-address + * read-after-read ordering. + */ + return p4d_offset(pgdp, addr); +} +#define p4d_offset_lockless p4d_offset_lockless_folded + #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #define pgd_ERROR(e) \ @@ -1027,8 +1102,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK. */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP | - PTE_ATTRINDX_MASK; + PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | + PTE_GP | PTE_ATTRINDX_MASK; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); @@ -1076,17 +1151,17 @@ static inline int pgd_devmap(pgd_t pgd) #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)); + return pte_valid(pte) && (pte_user(pte) || pte_user_exec(pte)); } static inline bool pmd_user_accessible_page(pmd_t pmd) { - return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); + return pmd_valid(pmd) && !pmd_table(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { - return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud)); + return pud_valid(pud) && !pud_table(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif @@ -1227,6 +1302,46 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, __ptep_set_wrprotect(mm, address, ptep); } +static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, cydp_t flags) +{ + pte_t old_pte; + + do { + old_pte = pte; + + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + + pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), + pte_val(old_pte), pte_val(pte)); + } while (pte_val(pte) != pte_val(old_pte)); +} + +static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + pte = __ptep_get(ptep); + + if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) + __set_pte(ptep, pte_mkclean(pte_mkold(pte))); + else + __clear_young_dirty_pte(vma, addr, ptep, pte, flags); + + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, @@ -1248,15 +1363,16 @@ 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: remember PG_anon_exclusive - * bits 3-7: swap type - * bits 8-57: swap offset - * bit 58: PTE_PROT_NONE (must be zero) + * bit 3: remember uffd-wp state + * bits 6-10: swap type + * bit 11: PTE_PRESENT_INVALID (must be zero) + * bits 12-61: swap offset */ -#define __SWP_TYPE_SHIFT 3 +#define __SWP_TYPE_SHIFT 6 #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) +#define __SWP_OFFSET_SHIFT 12 +#define __SWP_OFFSET_BITS 50 #define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) @@ -1280,12 +1396,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) -{ - if (system_supports_mte()) - return mte_save_tags(page); - return 0; -} +extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) @@ -1301,11 +1412,7 @@ 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 folio *folio) -{ - if (system_supports_mte()) - mte_restore_tags(entry, &folio->page); -} +extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ @@ -1392,6 +1499,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); +extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) @@ -1616,6 +1726,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } +#define clear_young_dirty_ptes clear_young_dirty_ptes +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); + else + contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); +} + #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get @@ -1635,6 +1756,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags +#define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index a75de2665d..95fbc8c056 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -142,17 +142,24 @@ static inline unsigned long get_trans_granule(void) * EL1, Inner Shareable". * */ -#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl) \ - ({ \ - unsigned long __ta = (baddr); \ - unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0; \ - __ta &= GENMASK_ULL(36, 0); \ - __ta |= __ttl << 37; \ - __ta |= (unsigned long)(num) << 39; \ - __ta |= (unsigned long)(scale) << 44; \ - __ta |= get_trans_granule() << 46; \ - __ta |= (unsigned long)(asid) << 48; \ - __ta; \ +#define TLBIR_ASID_MASK GENMASK_ULL(63, 48) +#define TLBIR_TG_MASK GENMASK_ULL(47, 46) +#define TLBIR_SCALE_MASK GENMASK_ULL(45, 44) +#define TLBIR_NUM_MASK GENMASK_ULL(43, 39) +#define TLBIR_TTL_MASK GENMASK_ULL(38, 37) +#define TLBIR_BADDR_MASK GENMASK_ULL(36, 0) + +#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl) \ + ({ \ + unsigned long __ta = 0; \ + unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0; \ + __ta |= FIELD_PREP(TLBIR_BADDR_MASK, baddr); \ + __ta |= FIELD_PREP(TLBIR_TTL_MASK, __ttl); \ + __ta |= FIELD_PREP(TLBIR_NUM_MASK, num); \ + __ta |= FIELD_PREP(TLBIR_SCALE_MASK, scale); \ + __ta |= FIELD_PREP(TLBIR_TG_MASK, get_trans_granule()); \ + __ta |= FIELD_PREP(TLBIR_ASID_MASK, asid); \ + __ta; \ }) /* These macros are used by the TLBI RANGE feature. */ @@ -439,11 +446,11 @@ static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma, * When not uses TLB range ops, we can handle up to * (MAX_DVM_OPS - 1) pages; * When uses TLB range ops, we can handle up to - * (MAX_TLBI_RANGE_PAGES - 1) pages. + * MAX_TLBI_RANGE_PAGES pages. */ if ((!system_supports_tlb_range() && (end - start) >= (MAX_DVM_OPS * stride)) || - pages >= MAX_TLBI_RANGE_PAGES) { + pages > MAX_TLBI_RANGE_PAGES) { flush_tlb_mm(vma->vm_mm); return; } diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index a323b109b9..0f6ef432fb 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -35,9 +35,9 @@ void update_freq_counters_refs(void); /* Enable topology flag updates */ #define arch_update_cpu_topology topology_update_cpu_topology -/* Replace task scheduler's default thermal pressure API */ -#define arch_scale_thermal_pressure topology_get_thermal_pressure -#define arch_update_thermal_pressure topology_update_thermal_pressure +/* Replace task scheduler's default HW pressure API */ +#define arch_scale_hw_pressure topology_get_hw_pressure +#define arch_update_hw_pressure topology_update_hw_pressure #include <asm-generic/topology.h> diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 491b2b9bd5..1346579f80 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -39,7 +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 462 +#define __NR_compat_syscalls 463 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 9ee1ffded2..1386e8e751 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -929,6 +929,8 @@ __SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr) __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) #define __NR_lsm_list_modules 461 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 261d6e9df2..ebf4a9f943 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -82,6 +82,12 @@ bool is_kvm_arm_initialised(void); DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); +static inline bool is_pkvm_initialized(void) +{ + return IS_ENABLED(CONFIG_KVM) && + static_branch_likely(&kvm_protected_mode_initialized); +} + /* Reports the availability of HYP mode */ static inline bool is_hyp_mode_available(void) { @@ -89,8 +95,7 @@ static inline bool is_hyp_mode_available(void) * If KVM protected mode is initialized, all CPUs must have been booted * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. */ - if (IS_ENABLED(CONFIG_KVM) && - static_branch_likely(&kvm_protected_mode_initialized)) + if (is_pkvm_initialized()) return true; return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 && @@ -104,8 +109,7 @@ static inline bool is_hyp_mode_mismatched(void) * If KVM protected mode is initialized, all CPUs must have been booted * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. */ - if (IS_ENABLED(CONFIG_KVM) && - static_branch_likely(&kvm_protected_mode_initialized)) + if (is_pkvm_initialized()) return false; return __boot_cpu_mode[0] != __boot_cpu_mode[1]; |