diff options
| author | Linus Torvalds | 2024-09-16 06:55:07 +0200 |
|---|---|---|
| committer | Linus Torvalds | 2024-09-16 06:55:07 +0200 |
| commit | 114143a595895c03fbefccfd8346fc51fb4908ed (patch) | |
| tree | 161f753ad69a2aabe7cd7ac7cc493c3678dbd760 /arch | |
| parent | 8617d7d6298f54dfef4038281863270b5864fe83 (diff) | |
| parent | 75078ba2b38a38d94017bd334f71aaed205e30a4 (diff) | |
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Will Deacon:
"The highlights are support for Arm's "Permission Overlay Extension"
using memory protection keys, support for running as a protected guest
on Android as well as perf support for a bunch of new interconnect
PMUs.
Summary:
ACPI:
- Enable PMCG erratum workaround for HiSilicon HIP10 and 11
platforms.
- Ensure arm64-specific IORT header is covered by MAINTAINERS.
CPU Errata:
- Enable workaround for hardware access/dirty issue on Ampere-1A
cores.
Memory management:
- Define PHYSMEM_END to fix a crash in the amdgpu driver.
- Avoid tripping over invalid kernel mappings on the kexec() path.
- Userspace support for the Permission Overlay Extension (POE) using
protection keys.
Perf and PMUs:
- Add support for the "fixed instruction counter" extension in the
CPU PMU architecture.
- Extend and fix the event encodings for Apple's M1 CPU PMU.
- Allow LSM hooks to decide on SPE permissions for physical
profiling.
- Add support for the CMN S3 and NI-700 PMUs.
Confidential Computing:
- Add support for booting an arm64 kernel as a protected guest under
Android's "Protected KVM" (pKVM) hypervisor.
Selftests:
- Fix vector length issues in the SVE/SME sigreturn tests
- Fix build warning in the ptrace tests.
Timers:
- Add support for PR_{G,S}ET_TSC so that 'rr' can deal with
non-determinism arising from the architected counter.
Miscellaneous:
- Rework our IPI-based CPU stopping code to try NMIs if regular IPIs
don't succeed.
- Minor fixes and cleanups"
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (94 commits)
perf: arm-ni: Fix an NULL vs IS_ERR() bug
arm64: hibernate: Fix warning for cast from restricted gfp_t
arm64: esr: Define ESR_ELx_EC_* constants as UL
arm64: pkeys: remove redundant WARN
perf: arm_pmuv3: Use BR_RETIRED for HW branch event if enabled
MAINTAINERS: List Arm interconnect PMUs as supported
perf: Add driver for Arm NI-700 interconnect PMU
dt-bindings/perf: Add Arm NI-700 PMU
perf/arm-cmn: Improve format attr printing
perf/arm-cmn: Clean up unnecessary NUMA_NO_NODE check
arm64/mm: use lm_alias() with addresses passed to memblock_free()
mm: arm64: document why pte is not advanced in contpte_ptep_set_access_flags()
arm64: Expose the end of the linear map in PHYSMEM_END
arm64: trans_pgd: mark PTEs entries as valid to avoid dead kexec()
arm64/mm: Delete __init region from memblock.reserved
perf/arm-cmn: Support CMN S3
dt-bindings: perf: arm-cmn: Add CMN S3
perf/arm-cmn: Refactor DTC PMU register access
perf/arm-cmn: Make cycle counts less surprising
perf/arm-cmn: Improve build-time assertion
...
Diffstat (limited to 'arch')
61 files changed, 1153 insertions, 258 deletions
diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index a41b503b7dcd..f63ba8986b24 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -127,6 +127,12 @@ static inline u32 read_pmuver(void) return (dfr0 >> 24) & 0xf; } +static inline bool pmuv3_has_icntr(void) +{ + /* FEAT_PMUv3_ICNTR not accessible for 32-bit */ + return false; +} + static inline void write_pmcr(u32 val) { write_sysreg(val, PMCR); @@ -152,6 +158,13 @@ static inline u64 read_pmccntr(void) return read_sysreg(PMCCNTR); } +static inline void write_pmicntr(u64 val) {} + +static inline u64 read_pmicntr(void) +{ + return 0; +} + static inline void write_pmcntenset(u32 val) { write_sysreg(val, PMCNTENSET); @@ -177,6 +190,13 @@ static inline void write_pmccfiltr(u32 val) write_sysreg(val, PMCCFILTR); } +static inline void write_pmicfiltr(u64 val) {} + +static inline u64 read_pmicfiltr(void) +{ + return 0; +} + static inline void write_pmovsclr(u32 val) { write_sysreg(val, PMOVSR); diff --git a/arch/arm/include/asm/hypervisor.h b/arch/arm/include/asm/hypervisor.h index bd61502b9715..8a648e506540 100644 --- a/arch/arm/include/asm/hypervisor.h +++ b/arch/arm/include/asm/hypervisor.h @@ -7,4 +7,6 @@ void kvm_init_hyp_services(void); bool kvm_arm_hyp_service_available(u32 func_id); +static inline void kvm_arch_init_hyp_services(void) { }; + #endif diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2f8ff354ca6..ed15b876fa74 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -34,6 +34,7 @@ config ARM64 select ARCH_HAS_KERNEL_FPU_SUPPORT if KERNEL_MODE_NEON select ARCH_HAS_KEEPINITRD select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_DEVMAP @@ -423,7 +424,7 @@ config AMPERE_ERRATUM_AC03_CPU_38 default y help This option adds an alternative code sequence to work around Ampere - erratum AC03_CPU_38 on AmpereOne. + errata AC03_CPU_38 and AC04_CPU_10 on AmpereOne. The affected design reports FEAT_HAFDBS as not implemented in ID_AA64MMFR1_EL1.HAFDBS, but (V)TCR_ELx.{HA,HD} are not RES0 @@ -2137,6 +2138,29 @@ config ARM64_EPAN if the cpu does not implement the feature. endmenu # "ARMv8.7 architectural features" +menu "ARMv8.9 architectural features" + +config ARM64_POE + prompt "Permission Overlay Extension" + def_bool y + select ARCH_USES_HIGH_VMA_FLAGS + select ARCH_HAS_PKEYS + help + The Permission Overlay Extension is used to implement Memory + Protection Keys. Memory Protection Keys provides a mechanism for + enforcing page-based protections, but without requiring modification + of the page tables when an application changes protection domains. + + For details, see Documentation/core-api/protection-keys.rst + + If unsure, say y. + +config ARCH_PKEY_BITS + int + default 3 + +endmenu # "ARMv8.9 architectural features" + config ARM64_SVE bool "ARM Scalable Vector Extension support" default y diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index a4697a0b6835..468a049bc63b 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -33,6 +33,14 @@ static inline void write_pmevtypern(int n, unsigned long val) PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } +#define RETURN_READ_PMEVTYPERN(n) \ + return read_sysreg(pmevtyper##n##_el0) +static inline unsigned long read_pmevtypern(int n) +{ + PMEVN_SWITCH(n, RETURN_READ_PMEVTYPERN); + return 0; +} + static inline unsigned long read_pmmir(void) { return read_cpuid(PMMIR_EL1); @@ -46,6 +54,14 @@ static inline u32 read_pmuver(void) ID_AA64DFR0_EL1_PMUVer_SHIFT); } +static inline bool pmuv3_has_icntr(void) +{ + u64 dfr1 = read_sysreg(id_aa64dfr1_el1); + + return !!cpuid_feature_extract_unsigned_field(dfr1, + ID_AA64DFR1_EL1_PMICNTR_SHIFT); +} + static inline void write_pmcr(u64 val) { write_sysreg(val, pmcr_el0); @@ -71,22 +87,32 @@ static inline u64 read_pmccntr(void) return read_sysreg(pmccntr_el0); } -static inline void write_pmcntenset(u32 val) +static inline void write_pmicntr(u64 val) +{ + write_sysreg_s(val, SYS_PMICNTR_EL0); +} + +static inline u64 read_pmicntr(void) +{ + return read_sysreg_s(SYS_PMICNTR_EL0); +} + +static inline void write_pmcntenset(u64 val) { write_sysreg(val, pmcntenset_el0); } -static inline void write_pmcntenclr(u32 val) +static inline void write_pmcntenclr(u64 val) { write_sysreg(val, pmcntenclr_el0); } -static inline void write_pmintenset(u32 val) +static inline void write_pmintenset(u64 val) { write_sysreg(val, pmintenset_el1); } -static inline void write_pmintenclr(u32 val) +static inline void write_pmintenclr(u64 val) { write_sysreg(val, pmintenclr_el1); } @@ -96,12 +122,27 @@ static inline void write_pmccfiltr(u64 val) write_sysreg(val, pmccfiltr_el0); } -static inline void write_pmovsclr(u32 val) +static inline u64 read_pmccfiltr(void) +{ + return read_sysreg(pmccfiltr_el0); +} + +static inline void write_pmicfiltr(u64 val) +{ + write_sysreg_s(val, SYS_PMICFILTR_EL0); +} + +static inline u64 read_pmicfiltr(void) +{ + return read_sysreg_s(SYS_PMICFILTR_EL0); +} + +static inline void write_pmovsclr(u64 val) { write_sysreg(val, pmovsclr_el0); } -static inline u32 read_pmovsclr(void) +static inline u64 read_pmovsclr(void) { return read_sysreg(pmovsclr_el0); } diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 558434267271..3d261cc123c1 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -832,6 +832,12 @@ static inline bool system_supports_lpa2(void) return cpus_have_final_cap(ARM64_HAS_LPA2); } +static inline bool system_supports_poe(void) +{ + return IS_ENABLED(CONFIG_ARM64_POE) && + alternative_has_cap_unlikely(ARM64_HAS_S1POE); +} + int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); bool try_emulate_mrs(struct pt_regs *regs, u32 isn); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 5fd7caea4419..5a7dfeb8e8eb 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -143,6 +143,7 @@ #define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define AMPERE_CPU_PART_AMPERE1A 0xAC4 #define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ @@ -212,6 +213,7 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_AMPERE1A MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1A) #define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index fd87c4b8f984..e0ffdf13a18b 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -165,42 +165,53 @@ mrs x1, id_aa64dfr0_el1 ubfx x1, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4 cmp x1, #3 - b.lt .Lset_debug_fgt_\@ + b.lt .Lskip_spe_fgt_\@ /* Disable PMSNEVFR_EL1 read and write traps */ orr x0, x0, #(1 << 62) -.Lset_debug_fgt_\@: +.Lskip_spe_fgt_\@: msr_s SYS_HDFGRTR_EL2, x0 msr_s SYS_HDFGWTR_EL2, x0 mov x0, xzr mrs x1, id_aa64pfr1_el1 ubfx x1, x1, #ID_AA64PFR1_EL1_SME_SHIFT, #4 - cbz x1, .Lset_pie_fgt_\@ + cbz x1, .Lskip_debug_fgt_\@ /* Disable nVHE traps of TPIDR2 and SMPRI */ orr x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK orr x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK -.Lset_pie_fgt_\@: +.Lskip_debug_fgt_\@: mrs_s x1, SYS_ID_AA64MMFR3_EL1 ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4 - cbz x1, .Lset_fgt_\@ + cbz x1, .Lskip_pie_fgt_\@ /* Disable trapping of PIR_EL1 / PIRE0_EL1 */ orr x0, x0, #HFGxTR_EL2_nPIR_EL1 orr x0, x0, #HFGxTR_EL2_nPIRE0_EL1 -.Lset_fgt_\@: +.Lskip_pie_fgt_\@: + mrs_s x1, SYS_ID_AA64MMFR3_EL1 + ubfx x1, x1, #ID_AA64MMFR3_EL1_S1POE_SHIFT, #4 + cbz x1, .Lskip_poe_fgt_\@ + + /* Disable trapping of POR_EL0 */ + orr x0, x0, #HFGxTR_EL2_nPOR_EL0 + +.Lskip_poe_fgt_\@: msr_s SYS_HFGRTR_EL2, x0 msr_s SYS_HFGWTR_EL2, x0 msr_s SYS_HFGITR_EL2, xzr mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU ubfx x1, x1, #ID_AA64PFR0_EL1_AMU_SHIFT, #4 - cbz x1, .Lskip_fgt_\@ + cbz x1, .Lskip_amu_fgt_\@ msr_s SYS_HAFGRTR_EL2, xzr + +.Lskip_amu_fgt_\@: + .Lskip_fgt_\@: .endm diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 56c148890daf..2f3d56857a97 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -10,63 +10,63 @@ #include <asm/memory.h> #include <asm/sysreg.h> -#define ESR_ELx_EC_UNKNOWN (0x00) -#define ESR_ELx_EC_WFx (0x01) +#define ESR_ELx_EC_UNKNOWN UL(0x00) +#define ESR_ELx_EC_WFx UL(0x01) /* Unallocated EC: 0x02 */ -#define ESR_ELx_EC_CP15_32 (0x03) -#define ESR_ELx_EC_CP15_64 (0x04) -#define ESR_ELx_EC_CP14_MR (0x05) -#define ESR_ELx_EC_CP14_LS (0x06) -#define ESR_ELx_EC_FP_ASIMD (0x07) -#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ -#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +#define ESR_ELx_EC_CP15_32 UL(0x03) +#define ESR_ELx_EC_CP15_64 UL(0x04) +#define ESR_ELx_EC_CP14_MR UL(0x05) +#define ESR_ELx_EC_CP14_LS UL(0x06) +#define ESR_ELx_EC_FP_ASIMD UL(0x07) +#define ESR_ELx_EC_CP10_ID UL(0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC UL(0x09) /* EL2 and above */ /* Unallocated EC: 0x0A - 0x0B */ -#define ESR_ELx_EC_CP14_64 (0x0C) -#define ESR_ELx_EC_BTI (0x0D) -#define ESR_ELx_EC_ILL (0x0E) +#define ESR_ELx_EC_CP14_64 UL(0x0C) +#define ESR_ELx_EC_BTI UL(0x0D) +#define ESR_ELx_EC_ILL UL(0x0E) /* Unallocated EC: 0x0F - 0x10 */ -#define ESR_ELx_EC_SVC32 (0x11) -#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ -#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ +#define ESR_ELx_EC_SVC32 UL(0x11) +#define ESR_ELx_EC_HVC32 UL(0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 UL(0x13) /* EL2 and above */ /* Unallocated EC: 0x14 */ -#define ESR_ELx_EC_SVC64 (0x15) -#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ -#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ -#define ESR_ELx_EC_SYS64 (0x18) -#define ESR_ELx_EC_SVE (0x19) -#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +#define ESR_ELx_EC_SVC64 UL(0x15) +#define ESR_ELx_EC_HVC64 UL(0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 UL(0x17) /* EL2 and above */ +#define ESR_ELx_EC_SYS64 UL(0x18) +#define ESR_ELx_EC_SVE UL(0x19) +#define ESR_ELx_EC_ERET UL(0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ -#define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ -#define ESR_ELx_EC_SME (0x1D) +#define ESR_ELx_EC_FPAC UL(0x1C) /* EL1 and above */ +#define ESR_ELx_EC_SME UL(0x1D) /* Unallocated EC: 0x1E */ -#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ -#define ESR_ELx_EC_IABT_LOW (0x20) -#define ESR_ELx_EC_IABT_CUR (0x21) -#define ESR_ELx_EC_PC_ALIGN (0x22) +#define ESR_ELx_EC_IMP_DEF UL(0x1f) /* EL3 only */ +#define ESR_ELx_EC_IABT_LOW UL(0x20) +#define ESR_ELx_EC_IABT_CUR UL(0x21) +#define ESR_ELx_EC_PC_ALIGN UL(0x22) /* Unallocated EC: 0x23 */ -#define ESR_ELx_EC_DABT_LOW (0x24) -#define ESR_ELx_EC_DABT_CUR (0x25) -#define ESR_ELx_EC_SP_ALIGN (0x26) -#define ESR_ELx_EC_MOPS (0x27) -#define ESR_ELx_EC_FP_EXC32 (0x28) +#define ESR_ELx_EC_DABT_LOW UL(0x24) +#define ESR_ELx_EC_DABT_CUR UL(0x25) +#define ESR_ELx_EC_SP_ALIGN UL(0x26) +#define ESR_ELx_EC_MOPS UL(0x27) +#define ESR_ELx_EC_FP_EXC32 UL(0x28) /* Unallocated EC: 0x29 - 0x2B */ -#define ESR_ELx_EC_FP_EXC64 (0x2C) +#define ESR_ELx_EC_FP_EXC64 UL(0x2C) /* Unallocated EC: 0x2D - 0x2E */ -#define ESR_ELx_EC_SERROR (0x2F) -#define ESR_ELx_EC_BREAKPT_LOW (0x30) -#define ESR_ELx_EC_BREAKPT_CUR (0x31) -#define ESR_ELx_EC_SOFTSTP_LOW (0x32) -#define ESR_ELx_EC_SOFTSTP_CUR (0x33) -#define ESR_ELx_EC_WATCHPT_LOW (0x34) -#define ESR_ELx_EC_WATCHPT_CUR (0x35) +#define ESR_ELx_EC_SERROR UL(0x2F) +#define ESR_ELx_EC_BREAKPT_LOW UL(0x30) +#define ESR_ELx_EC_BREAKPT_CUR UL(0x31) +#define ESR_ELx_EC_SOFTSTP_LOW UL(0x32) +#define ESR_ELx_EC_SOFTSTP_CUR UL(0x33) +#define ESR_ELx_EC_WATCHPT_LOW UL(0x34) +#define ESR_ELx_EC_WATCHPT_CUR UL(0x35) /* Unallocated EC: 0x36 - 0x37 */ -#define ESR_ELx_EC_BKPT32 (0x38) +#define ESR_ELx_EC_BKPT32 UL(0x38) /* Unallocated EC: 0x39 */ -#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ +#define ESR_ELx_EC_VECTOR32 UL(0x3A) /* EL2 only */ /* Unallocated EC: 0x3B */ -#define ESR_ELx_EC_BRK64 (0x3C) +#define ESR_ELx_EC_BRK64 UL(0x3C) /* Unallocated EC: 0x3D - 0x3F */ -#define ESR_ELx_EC_MAX (0x3F) +#define ESR_ELx_EC_MAX UL(0x3F) #define ESR_ELx_EC_SHIFT (26) #define ESR_ELx_EC_WIDTH (6) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index bc69ac368d73..f2a84efc3618 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -155,8 +155,6 @@ 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); - /* * Helpers to translate bit indices in sve_vq_map to VQ values (and * vice versa). This allows find_next_bit() to be used to find the diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 4edd3b61df11..a775adddecf2 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -157,6 +157,7 @@ #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) +#define KERNEL_HWCAP_POE __khwcap2_feature(POE) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/hypervisor.h b/arch/arm64/include/asm/hypervisor.h index 0ae427f352c8..409e239834d1 100644 --- a/arch/arm64/include/asm/hypervisor.h +++ b/arch/arm64/include/asm/hypervisor.h @@ -7,4 +7,15 @@ void kvm_init_hyp_services(void); bool kvm_arm_hyp_service_available(u32 func_id); +#ifdef CONFIG_ARM_PKVM_GUEST +void pkvm_init_hyp_services(void); +#else +static inline void pkvm_init_hyp_services(void) { }; +#endif + +static inline void kvm_arch_init_hyp_services(void) +{ + pkvm_init_hyp_services(); +}; + #endif diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 41fd90895dfc..1ada23a6ec19 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -271,6 +271,10 @@ __iowrite64_copy(void __iomem *to, const void *from, size_t count) * I/O memory mapping functions. */ +typedef int (*ioremap_prot_hook_t)(phys_addr_t phys_addr, size_t size, + pgprot_t *prot); +int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook); + #define ioremap_prot ioremap_prot #define _PAGE_IOREMAP PROT_DEVICE_nGnRE diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 2181a11b9d92..25f49f5fc4a6 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -10,6 +10,7 @@ #include <asm/hyp_image.h> #include <asm/insn.h> #include <asm/virt.h> +#include <asm/sysreg.h> #define ARM_EXIT_WITH_SERROR_BIT 31 #define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT)) @@ -259,7 +260,7 @@ extern u64 __kvm_get_mdcr_el2(void); asm volatile( \ " mrs %1, spsr_el2\n" \ " mrs %2, elr_el2\n" \ - "1: at "at_op", %3\n" \ + "1: " __msr_s(at_op, "%3") "\n" \ " isb\n" \ " b 9f\n" \ "2: msr spsr_el2, %1\n" \ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index a33f5996ca9f..d5857452a1ec 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -446,6 +446,8 @@ enum vcpu_sysreg { GCR_EL1, /* Tag Control Register */ TFSRE0_EL1, /* Tag Fault Status Register (EL0) */ + POR_EL0, /* Permission Overlay Register 0 (EL0) */ + /* 32bit specific registers. */ DACR32_EL2, /* Domain Access Control Register */ IFSR32_EL2, /* Instruction Fault Status Register */ @@ -517,6 +519,8 @@ enum vcpu_sysreg { VNCR(PIR_EL1), /* Permission Indirection Register 1 (EL1) */ VNCR(PIRE0_EL1), /* Permission Indirection Register 0 (EL1) */ + VNCR(POR_EL1), /* Permission Overlay Register 1 (EL1) */ + VNCR(HFGRTR_EL2), VNCR(HFGWTR_EL2), VNCR(HFGITR_EL2), @@ -1330,12 +1334,12 @@ void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM -void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr); -void kvm_clr_pmu_events(u32 clr); +void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr); +void kvm_clr_pmu_events(u64 clr); bool kvm_set_pmuserenr(u64 val); #else -static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} -static inline void kvm_clr_pmu_events(u32 clr) {} +static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {} +static inline void kvm_clr_pmu_events(u64 clr) {} static inline bool kvm_set_pmuserenr(u64 val) { return false; diff --git a/arch/arm64/include/asm/mem_encrypt.h b/arch/arm64/include/asm/mem_encrypt.h new file mode 100644 index 000000000000..b0c9a86b13a4 --- /dev/null +++ b/arch/arm64/include/asm/mem_encrypt.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_MEM_ENCRYPT_H +#define __ASM_MEM_ENCRYPT_H + +struct arm64_mem_crypt_ops { + int (*encrypt)(unsigned long addr, int numpages); + int (*decrypt)(unsigned long addr, int numpages); +}; + +int arm64_mem_crypt_ops_register(const struct arm64_mem_crypt_ops *ops); + +int set_memory_encrypted(unsigned long addr, int numpages); +int set_memory_decrypted(unsigned long addr, int numpages); + +#endif /* __ASM_MEM_ENCRYPT_H */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 54fb014eba05..0480c61dbb4f 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -110,6 +110,8 @@ #define PAGE_END (_PAGE_END(VA_BITS_MIN)) #endif /* CONFIG_KASAN */ +#define PHYSMEM_END __pa(PAGE_END - 1) + #define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) /* diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index 5966ee4a6154..52791715f6e6 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -7,7 +7,7 @@ #include <uapi/asm/mman.h> static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, - unsigned long pkey __always_unused) + unsigned long pkey) { unsigned long ret = 0; @@ -17,6 +17,14 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, if (system_supports_mte() && (prot & PROT_MTE)) ret |= VM_MTE; +#ifdef CONFIG_ARCH_HAS_PKEYS + if (system_supports_poe()) { + ret |= pkey & BIT(0) ? VM_PKEY_BIT0 : 0; + ret |= pkey & BIT(1) ? VM_PKEY_BIT1 : 0; + ret |= pkey & BIT(2) ? VM_PKEY_BIT2 : 0; + } +#endif + return ret; } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 65977c7783c5..2ec96d91acc6 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -25,6 +25,7 @@ typedef struct { refcount_t pinned; void *vdso; unsigned long flags; + u8 pkey_allocation_map; } mm_context_t; /* @@ -63,7 +64,6 @@ static inline bool arm64_kernel_unmapped_at_el0(void) extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); -extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index bd19f4c758b7..7c09d47e09cb 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -15,12 +15,12 @@ #include <linux/sched/hotplug.h> #include <linux/mm_types.h> #include <linux/pgtable.h> +#include <linux/pkeys.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/proc-fns.h> -#include <asm-generic/mm_hooks.h> #include <asm/cputype.h> #include <asm/sysreg.h> #include <asm/tlbflush.h> @@ -175,9 +175,36 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) { atomic64_set(&mm->context.id, 0); refcount_set(&mm->context.pinned, 0); + + /* pkey 0 is the default, so always reserve it. */ + mm->context.pkey_allocation_map = BIT(0); + + return 0; +} + +static inline void arch_dup_pkeys(struct mm_struct *oldmm, + struct mm_struct *mm) +{ + /* Duplicate the oldmm pkey state in mm: */ + mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; +} + +static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) +{ + arch_dup_pkeys(oldmm, mm); + return 0; } +static inline void arch_exit_mmap(struct mm_struct *mm) +{ +} + +static inline void arch_unmap(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) @@ -267,6 +294,23 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm) return -1UL >> 8; } +/* + * Only enforce protection keys on the current process, because there is no + * user context to access POR_EL0 for another address space. + */ +static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, + bool write, bool execute, bool foreign) +{ + if (!system_supports_poe()) + return true; + + /* allow access if the VMA is not one from this process */ + if (foreign || vma_is_foreign(vma)) + return true; + + return por_el0_allows_pkey(vma_pkey(vma), write, execute); +} + #include <asm-generic/mmu_context.h> #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 1f60aa1bc750..0b54fc121aa0 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -135,7 +135,6 @@ /* * Section */ -#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) #define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */ #define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) @@ -200,6 +199,16 @@ #define PTE_PI_IDX_3 54 /* UXN */ /* + * POIndex[2:0] encoding (Permission Overlay Extension) + */ +#define PTE_PO_IDX_0 (_AT(pteval_t, 1) << 60) +#define PTE_PO_IDX_1 (_AT(pteval_t, 1) << 61) +#define PTE_PO_IDX_2 (_AT(pteval_t, 1) << 62) + +#define PTE_PO_IDX_MASK GENMASK_ULL(62, 60) + + +/* * Memory Attribute override for Stage-2 (MemAttr[3:0]) */ #define PTE_S2_MEMATTR(t) (_AT(pteval_t, (t)) << 2) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index b11cfb9fdd37..2a11d0c10760 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -154,10 +154,10 @@ static inline bool __pure lpa2_is_enabled(void) #define PIE_E0 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_X_O) | \ - PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX) | \ - PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RWX) | \ - PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R) | \ - PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW)) + PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O) | \ + PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RWX_O) | \ + PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R_O) | \ + PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW_O)) #define PIE_E1 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_NONE_O) | \ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7a4f5604be3f..96c2b0b07c4c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,6 +34,7 @@ #include <asm/cmpxchg.h> #include <asm/fixmap.h> +#include <asm/por.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> @@ -149,6 +150,24 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_accessible(mm, pte) \ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) +static inline bool por_el0_allows_pkey(u8 pkey, bool write, bool execute) +{ + u64 por; + + if (!system_supports_poe()) + return true; + + por = read_sysreg_s(SYS_POR_EL0); + + if (write) + return por_elx_allows_write(por, pkey); + + if (execute) + return por_elx_allows_exec(por, pkey); + + return por_elx_allows_read(por, pkey); +} + /* * p??_access_permitted() is true for valid user mappings (PTE_USER * bit set, subject to the write permission check). For execute-only @@ -156,8 +175,11 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) * not set) must return false. PROT_NONE mappings do not have the * PTE_VALID bit set. */ -#define pte_access_permitted(pte, write) \ +#define pte_access_permitted_no_overlay(pte, write) \ (((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte))) +#define pte_access_permitted(pte, write) \ + (pte_access_permitted_no_overlay(pte, write) && \ + por_el0_allows_pkey(FIELD_GET(PTE_PO_IDX_MASK, pte_val(pte)), write, false)) #define pmd_access_permitted(pmd, write) \ (pte_access_permitted(pmd_pte(pmd), (write))) #define pud_access_permitted(pud, write) \ @@ -373,10 +395,11 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) /* * If the PTE would provide user space access to the tags associated * with it then ensure that the MTE tags are synchronised. Although - * pte_access_permitted() returns false for exec only mappings, they - * don't expose tags (instruction fetches don't check tags). + * pte_access_permitted_no_overlay() returns false for exec only + * mappings, they don't expose tags (instruction fetches don't check + * tags). */ - if (system_supports_mte() && pte_access_permitted(pte, false) && + if (system_supports_mte() && pte_access_permitted_no_overlay(pte, false) && !pte_special(pte) && pte_tagged(pte)) mte_sync_tags(pte, nr_pages); } @@ -1103,7 +1126,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | - PTE_GP | PTE_ATTRINDX_MASK; + PTE_GP | PTE_ATTRINDX_MASK | PTE_PO_IDX_MASK; + /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); diff --git a/arch/arm64/include/asm/pkeys.h b/arch/arm64/include/asm/pkeys.h new file mode 100644 index 000000000000..0ca5f83ce148 --- /dev/null +++ b/arch/arm64/include/asm/pkeys.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Arm Ltd. + * + * Based on arch/x86/include/asm/pkeys.h + */ + +#ifndef _ASM_ARM64_PKEYS_H +#define _ASM_ARM64_PKEYS_H + +#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2) + +#define arch_max_pkey() 8 + +int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); + +static inline bool arch_pkeys_enabled(void) +{ + return system_supports_poe(); +} + +static inline int vma_pkey(struct vm_area_struct *vma) +{ + return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT; +} + +static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, + int prot, int pkey) +{ + if (pkey != -1) + return pkey; + + return vma_pkey(vma); +} + +static inline int execute_only_pkey(struct mm_struct *mm) +{ + // Execute-only mappings are handled by EPAN/FEAT_PAN3. + return -1; +} + +#define mm_pkey_allocation_map(mm) (mm)->context.pkey_allocation_map +#define mm_set_pkey_allocated(mm, pkey) do { \ + mm_pkey_allocation_map(mm) |= (1U << pkey); \ +} while (0) +#define mm_set_pkey_free(mm, pkey) do { \ + mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ +} while (0) + +static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) +{ + /* + * "Allocated" pkeys are those that have been returned + * from pkey_alloc() or pkey 0 which is allocated + * implicitly when the mm is created. + */ + if (pkey < 0 || pkey >= arch_max_pkey()) + return false; + + return mm_pkey_allocation_map(mm) & (1U << pkey); +} + +/* + * Returns a positive, 3-bit key on success, or -1 on failure. + */ +static inline int mm_pkey_alloc(struct mm_struct *mm) +{ + /* + * Note: this is the one and only place we make sure + * that the pkey is valid as far as the hardware is + * concerned. The rest of the kernel trusts that + * only good, valid pkeys come out of here. + */ + u8 all_pkeys_mask = GENMASK(arch_max_pkey() - 1, 0); + int ret; + + if (!arch_pkeys_enabled()) + return -1; + + /* + * Are we out of pkeys? We must handle this specially + * because ffz() behavior is undefined if there are no + * zeros. + */ + if (mm_pkey_allocation_map(mm) == all_pkeys_mask) + return -1; + + ret = ffz(mm_pkey_allocation_map(mm)); + + mm_set_pkey_allocated(mm, ret); + + return ret; +} + +static inline int mm_pkey_free(struct mm_struct *mm, int pkey) +{ + if (!mm_pkey_is_allocated(mm, pkey)) + return -EINVAL; + + mm_set_pkey_free(mm, pkey); + + return 0; +} + +#endif /* _ASM_ARM64_PKEYS_H */ diff --git a/arch/arm64/include/asm/por.h b/arch/arm64/include/asm/por.h new file mode 100644 index 000000000000..e06e9f473675 --- /dev/null +++ b/arch/arm64/include/asm/por.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Arm Ltd. + */ + +#ifndef _ASM_ARM64_POR_H +#define _ASM_ARM64_POR_H + +#define POR_BITS_PER_PKEY 4 +#define POR_ELx_IDX(por_elx, idx) (((por_elx) >> ((idx) * POR_BITS_PER_PKEY)) & 0xf) + +static inline bool por_elx_allows_read(u64 por, u8 pkey) +{ + u8 perm = POR_ELx_IDX(por, pkey); + + return perm & POE_R; +} + +static inline bool por_elx_allows_write(u64 por, u8 pkey) +{ + u8 perm = POR_ELx_IDX(por, pkey); + + return perm & POE_W; +} + +static inline bool por_elx_allows_exec(u64 por, u8 pkey) +{ + u8 perm = POR_ELx_IDX(por, pkey); + + return perm & POE_X; +} + +#endif /* _ASM_ARM64_POR_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index f77371232d8c..1438424f0064 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -184,6 +184,7 @@ struct thread_struct { u64 sctlr_user; u64 svcr; u64 tpidr2_el0; + u64 por_el0; }; static inline unsigned int thread_get_vl(struct thread_struct *thread, @@ -402,5 +403,10 @@ long get_tagged_addr_ctrl(struct task_struct *task); #define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current) #endif +int get_tsc_mode(unsigned long adr); +int set_tsc_mode(unsigned int val); +#define GET_TSC_CTL(adr) get_tsc_mode((adr)) +#define SET_TSC_CTL(val) set_tsc_mode((val)) + #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/set_memory.h b/arch/arm64/include/asm/set_memory.h index 0f740b781187..917761feeffd 100644 --- a/arch/arm64/include/asm/set_memory.h +++ b/arch/arm64/include/asm/set_memory.h @@ -3,6 +3,7 @@ #ifndef _ASM_ARM64_SET_MEMORY_H #define _ASM_ARM64_SET_MEMORY_H +#include <asm/mem_encrypt.h> #include <asm-generic/set_memory.h> bool can_set_direct_map(void); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 4a9ea103817e..95b605e0dfaf 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -403,7 +403,6 @@ #define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2) #define SYS_PMOVSCLR_EL0 sys_reg(3, 3, 9, 12, 3) #define SYS_PMSWINC_EL0 sys_reg(3, 3, 9, 12, 4) -#define SYS_PMSELR_EL0 sys_reg(3, 3, 9, 12, 5) #define SYS_PMCEID0_EL0 sys_reg(3, 3, 9, 12, 6) #define SYS_PMCEID1_EL0 sys_reg(3, 3, 9, 12, 7) #define SYS_PMCCNTR_EL0 sys_reg(3, 3, 9, 13, 0) @@ -1077,6 +1076,9 @@ #define POE_RXW UL(0x7) #define POE_MASK UL(0xf) +/* Initial value for Permission Overlay Extension for EL0 */ +#define POR_EL0_INIT POE_RXW + #define ARM64_FEATURE_FIELD_BITS 4 /* Defined for compatibility only, do not add new users. */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index e72a3bf9e563..1114c1c3300a 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -81,6 +81,7 @@ void arch_setup_new_exec(void); #define TIF_SME 27 /* SME in use */ #define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */ #define TIF_KERNEL_FPSTATE 29 /* Task is in a kernel mode FPSIMD section */ +#define TIF_TSC_SIGSEGV 30 /* SIGSEGV on counter-timer access */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) @@ -97,6 +98,7 @@ void arch_setup_new_exec(void); #define _TIF_SVE (1 << TIF_SVE) #define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) +#define _TIF_TSC_SIGSEGV (1 << TIF_TSC_SIGSEGV) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index eefe766d6161..d780d1bd2eac 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -25,6 +25,7 @@ try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn) void force_signal_inject(int signal, int code, unsigned long address, unsigned long err); void arm64_notify_segfault(unsigned long addr); void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str); +void arm64_force_sig_fault_pkey(unsigned long far, const char *str, int pkey); void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str); void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str); diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h index df2c47c55972..06f8ec0906a6 100644 --- a/arch/arm64/include/asm/vncr_mapping.h +++ b/arch/arm64/include/asm/vncr_mapping.h @@ -52,6 +52,7 @@ #define VNCR_PIRE0_EL1 0x290 #define VNCR_PIRE0_EL2 0x298 #define VNCR_PIR_EL1 0x2A0 +#define VNCR_POR_EL1 0x2A8 #define VNCR_ICH_LR0_EL2 0x400 #define VNCR_ICH_LR1_EL2 0x408 #define VNCR_ICH_LR2_EL2 0x410 diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 285610e626f5..055381b2c615 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -122,5 +122,6 @@ #define HWCAP2_SME_SF8FMA (1UL << 60) #define HWCAP2_SME_SF8DP4 (1UL << 61) #define HWCAP2_SME_SF8DP2 (1UL << 62) +#define HWCAP2_POE (1UL << 63) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h index 1e6482a838e1..e7e0c8216243 100644 --- a/arch/arm64/include/uapi/asm/mman.h +++ b/arch/arm64/include/uapi/asm/mman.h @@ -7,4 +7,13 @@ #define PROT_BTI 0x10 /* BTI guarded page */ #define PROT_MTE 0x20 /* Normal Tagged mapping */ +/* Override any generic PKEY permission defines */ +#define PKEY_DISABLE_EXECUTE 0x4 +#define PKEY_DISABLE_READ 0x8 +#undef PKEY_ACCESS_MASK +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE |\ + PKEY_DISABLE_READ |\ + PKEY_DISABLE_EXECUTE) + #endif /* ! _UAPI__ASM_MMAN_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 8a45b7a411e0..bb7af77a30a7 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -98,6 +98,13 @@ struct esr_context { __u64 esr; }; +#define POE_MAGIC 0x504f4530 + +struct poe_context { + struct _aarch64_ctx head; + __u64 por_el0; +}; + /* * extra_context: describes extra space in the signal frame for * additional structures that don't fit in sigcontext.__reserved[]. @@ -320,10 +327,10 @@ struct zt_context { ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \ / __SVE_VQ_BYTES * __SVE_VQ_BYTES) -#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) +#define ZA_SIG_REGS_SIZE(vq) (((vq) * __SVE_VQ_BYTES) * ((vq) * __SVE_VQ_BYTES)) #define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ - (SVE_SIG_ZREG_SIZE(vq) * n)) + (SVE_SIG_ZREG_SIZE(vq) * (n))) #define ZA_SIG_CONTEXT_SIZE(vq) \ (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) @@ -334,7 +341,7 @@ struct zt_context { #define ZT_SIG_REGS_OFFSET sizeof(struct zt_context) -#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n) +#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * (n)) #define ZT_SIG_CONTEXT_SIZE(n) \ (sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n)) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index f6b6b4507357..dfefbdf4073a 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -456,6 +456,14 @@ static const struct midr_range erratum_spec_ssbs_list[] = { }; #endif +#ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38 +static const struct midr_range erratum_ac03_cpu_38_list[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1), + MIDR_ALL_VERSIONS(MIDR_AMPERE1A), + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -772,7 +780,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "AmpereOne erratum AC03_CPU_38", .capability = ARM64_WORKAROUND_AMPERE_AC03_CPU_38, - ERRATA_MIDR_ALL_VERSIONS(MIDR_AMPERE1), + ERRATA_MIDR_RANGE_LIST(erratum_ac03_cpu_38_list), }, #endif { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 646ecd3069fd..718728a85430 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -466,6 +466,8 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_POE), + FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_S1POE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_S1PIE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_TCRX_SHIFT, 4, 0), ARM64_FTR_END, @@ -2348,6 +2350,14 @@ static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused) sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_MSCEn); } +#ifdef CONFIG_ARM64_POE +static void cpu_enable_poe(const struct arm64_cpu_capabilities *__unused) +{ + sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1x_E0POE); + sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_E0POE); +} +#endif + /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) @@ -2870,6 +2880,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_nv1, ARM64_CPUID_FIELDS_NEG(ID_AA64MMFR4_EL1, E2H0, NI_NV1) }, +#ifdef CONFIG_ARM64_POE + { + .desc = "Stage-1 Permission Overlay Extension (S1POE)", + .capability = ARM64_HAS_S1POE, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_poe, + ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, S1POE, IMP) + }, +#endif {}, }; @@ -3034,6 +3054,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), +#ifdef CONFIG_ARM64_POE + HWCAP_CAP(ID_AA64MMFR3_EL1, S1POE, IMP, CAP_HWCAP, KERNEL_HWCAP_POE), +#endif {}, }; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 09eeaa24d456..44718d0482b3 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -143,6 +143,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_SF8FMA] = "smesf8fma", [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", + [KERNEL_HWCAP_POE] = "poe", }; #ifdef CONFIG_COMPAT @@ -280,7 +281,7 @@ const struct seq_operations cpuinfo_op = { }; -static struct kobj_type cpuregs_kobj_type = { +static const struct kobj_type cpuregs_kobj_type = { .sysfs_ops = &kobj_sysfs_ops, }; diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 02870beb271e..7b11d84f533c 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -407,7 +407,7 @@ int swsusp_arch_resume(void) void *, phys_addr_t, phys_addr_t); struct trans_pgd_info trans_info = { .trans_alloc_page = hibernate_page_alloc, - .trans_alloc_arg = (void *)GFP_ATOMIC, + .trans_alloc_arg = (__force void *)GFP_ATOMIC, }; /* diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4ae31b7af6c3..0540653fbf38 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -43,6 +43,7 @@ #include <linux/stacktrace.h> #include <asm/alternative.h> +#include <asm/arch_timer.h> #include <asm/compat.h> #include <asm/cpufeature.h> #include <asm/cacheflush.h> @@ -271,12 +272,21 @@ static void flush_tagged_addr_state(void) clear_thread_flag(TIF_TAGGED_ADDR); } +static void flush_poe(void) +{ + if (!system_supports_poe()) + return; + + write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0); +} + void flush_thread(void) { fpsimd_flush_thread(); tls_thread_flush(); flush_ptrace_hw_breakpoint(current); flush_tagged_addr_state(); + flush_poe(); } void arch_release_task_struct(struct task_struct *tsk) @@ -371,6 +381,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (system_supports_tpidr2()) p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); + if (system_supports_poe()) + p->thread.por_el0 = read_sysreg_s(SYS_POR_EL0); + if (stack_start) { if (is_compat_thread(task_thread_info(p))) childregs->compat_sp = stack_start; @@ -472,27 +485,63 @@ static void entry_task_switch(struct task_struct *next) } /* - * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. - * Ensure access is disabled when switching to a 32bit task, ensure - * access is enabled when switching to a 64bit task. + * Handle sysreg updates for ARM erratum 1418040 which affects the 32bit view of + * CNTVCT, various other errata which require trapping all CNTVCT{,_EL0} + * accesses and prctl(PR_SET_TSC). Ensure access is disabled iff a workaround is + * required or PR_TSC_SIGSEGV is set. */ -static void erratum_1418040_thread_switch(struct task_struct *next) +static void update_cntkctl_el1(struct task_struct *next) { - if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) || - !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) - return; + struct thread_info *ti = task_thread_info(next); - if (is_compat_thread(task_thread_info(next))) + if (test_ti_thread_flag(ti, TIF_TSC_SIGSEGV) || + has_erratum_handler(read_cntvct_el0) || + (IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && + this_cpu_has_cap(ARM64_WORKAROUND_1418040) && + is_compat_thread(ti))) sysreg_clear_set(cntkctl_el1, ARCH_TIMER_USR_VCT_ACCESS_EN, 0); else sysreg_clear_set(cntkctl_el1, 0, ARCH_TIMER_USR_VCT_ACCESS_EN); } -static void erratum_1418040_new_exec(void) +static void cntkctl_thread_switch(struct task_struct *prev, + struct task_struct *next) +{ + if ((read_ti_thread_flags(task_thread_info(prev)) & + (_TIF_32BIT | _TIF_TSC_SIGSEGV)) != + (read_ti_thread_flags(task_thread_info(next)) & + (_TIF_32BIT | _TIF_TSC_SIGSEGV))) + update_cntkctl_el1(next); +} + +static int do_set_tsc_mode(unsigned int val) { + bool tsc_sigsegv; + + if (val == PR_TSC_SIGSEGV) + tsc_sigsegv = true; + else if (val == PR_TSC_ENABLE) + tsc_sigsegv = false; + else + return -EINVAL; + preempt_disable(); - erratum_1418040_thread_switch(current); + update_thread_flag(TIF_TSC_SIGSEGV, tsc_sigsegv); + update_cntkctl_el1(current); preempt_enable(); + + return 0; +} + +static void permission_overlay_switch(struct task_struct *next) +{ + if (!system_supports_poe()) + return; + + current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0); + if (current->thread.por_el0 != next->thread.por_el0) { + write_sysreg_s(next->thread.por_el0, SYS_POR_EL0); + } } /* @@ -528,8 +577,9 @@ struct task_struct *__switch_to(struct task_struct *prev, contextidr_thread_switch(next); entry_task_switch(next); ssbs_thread_switch(next); - erratum_1418040_thread_switch(next); + cntkctl_thread_switch(prev, next); ptrauth_thread_switch_user(next); + permission_overlay_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case @@ -645,7 +695,7 @@ void arch_setup_new_exec(void) current->mm->context.flags = mmflags; ptrauth_thread_init_user(); mte_thread_init_user(); - erratum_1418040_new_exec(); + do_set_tsc_mode(PR_TSC_ENABLE); if (task_spec_ssb_noexec(current)) { arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS, @@ -754,3 +804,26 @@ int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state, return prot; } #endif + +int get_tsc_mode(unsigned long adr) +{ + unsigned int val; + + if (is_compat_task()) + return -EINVAL; + + if (test_thread_flag(TIF_TSC_SIGSEGV)) + val = PR_TSC_SIGSEGV; + else + val = PR_TSC_ENABLE; + + return put_user(val, (unsigned int __user *)adr); +} + +int set_tsc_mode(unsigned int val) +{ + if (is_compat_task()) + return -EINVAL; + + return do_set_tsc_mode(val); +} diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 0d022599eb61..b756578aeaee 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1440,6 +1440,39 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct } #endif +#ifdef CONFIG_ARM64_POE +static int poe_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_poe()) + return -EINVAL; + + return membuf_write(&to, &target->thread.por_el0, + sizeof(target->thread.por_el0)); +} + +static int poe_set(struct task_struct *target, const struct + user_regset *regset, unsigned int pos, + unsigned int count, const void *kbuf, const + void __user *ubuf) +{ + int ret; + long ctrl; + + if (!system_supports_poe()) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); + if (ret) + return ret; + + target->thread.por_el0 = ctrl; + + return 0; +} +#endif + enum aarch64_regset { REGSET_GPR, REGSET_FPR, @@ -1469,6 +1502,9 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI REGSET_TAGGED_ADDR_CTRL, #endif +#ifdef CONFIG_ARM64_POE + REGSET_POE +#endif }; static const struct user_regset aarch64_regsets[] = { @@ -1628,6 +1664,16 @@ static const struct user_regset aarch64_regsets[] = { .set = tagged_addr_ctrl_set, }, #endif +#ifdef CONFIG_ARM64_POE + [REGSET_POE] = { + .core_note_type = NT_ARM_POE, + .n = 1, + .size = sizeof(long), + .align = sizeof(long), + .regset_get = poe_get, + .set = poe_set, + }, +#endif }; static const struct user_regset_view user_aarch64_view = { diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 4a77f4976e11..561986947530 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -61,6 +61,7 @@ struct rt_sigframe_user_layout { unsigned long za_offset; unsigned long zt_offset; unsigned long fpmr_offset; + unsigned long poe_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -185,6 +186,8 @@ struct user_ctxs { u32 zt_size; struct fpmr_context __user *fpmr; u32 fpmr_size; + struct poe_context __user *poe; + u32 poe_size; }; static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) @@ -258,6 +261,32 @@ static int restore_fpmr_context(struct user_ctxs *user) return err; } +static int preserve_poe_context(struct poe_context __user *ctx) +{ + int err = 0; + + __put_user_error(POE_MAGIC, &ctx->head.magic, err); + __put_user_error(sizeof(*ctx), &ctx->head.size, err); + __put_user_error(read_sysreg_s(SYS_POR_EL0), &ctx->por_el0, err); + + return err; +} + +static int restore_poe_context(struct user_ctxs *user) +{ + u64 por_el0; + int err = 0; + + if (user->poe_size != sizeof(*user->poe)) + return -EINVAL; + + __get_user_error(por_el0, &(user->poe->por_el0), err); + if (!err) + write_sysreg_s(por_el0, SYS_POR_EL0); + + return err; +} + #ifdef CONFIG_ARM64_SVE static int preserve_sve_context(struct sve_context __user *ctx) @@ -621,6 +650,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->za = NULL; user->zt = NULL; user->fpmr = NULL; + user->poe = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -671,6 +701,17 @@ static int parse_user_sigframe(struct user_ctxs *user, /* ignore */ break; + case POE_MAGIC: + if (!system_supports_poe()) + goto invalid; + + if (user->poe) + goto invalid; + + user->poe = (struct poe_context __user *)head; + user->poe_size = size; + break; + case SVE_MAGIC: if (!system_supports_sve() && !system_supports_sme()) goto invalid; @@ -857,6 +898,9 @@ static int restore_sigframe(struct pt_regs *regs, if (err == 0 && system_supports_sme2() && user.zt) err = restore_zt_context(&user); + if (err == 0 && system_supports_poe() && user.poe) + err = restore_poe_context(&user); + return err; } @@ -980,6 +1024,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } + if (system_supports_poe()) { + err = sigframe_alloc(user, &user->poe_offset, + sizeof(struct poe_context)); + if (err) + return err; + } + return sigframe_alloc_end(user); } @@ -1042,6 +1093,14 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_fpmr_context(fpmr_ctx); } + if (system_supports_poe() && err == 0 && user->poe_offset) { + struct poe_context __user *poe_ctx = + apply_user_offset(user, user->poe_offset); + + err |= preserve_poe_context(poe_ctx); + } + + /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = @@ -1178,6 +1237,9 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, sme_smstop(); } + if (system_supports_poe()) + write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0); + if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f01f0fd7b7fe..3b3f6b56e733 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -68,7 +68,7 @@ enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, - IPI_CPU_CRASH_STOP, + IPI_CPU_STOP_NMI, IPI_TIMER, IPI_IRQ_WORK, NR_IPI, @@ -85,6 +85,8 @@ static int ipi_irq_base __ro_after_init; static int nr_ipi __ro_after_init = NR_IPI; static struct irq_desc *ipi_desc[MAX_IPI] __ro_after_init; +static bool crash_stop; + static void ipi_setup(int cpu); #ifdef CONFIG_HOTPLUG_CPU @@ -823,7 +825,7 @@ static const char *ipi_types[MAX_IPI] __tracepoint_string = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNC] = "Function call interrupts", [IPI_CPU_STOP] = "CPU stop interrupts", - [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", + [IPI_CPU_STOP_NMI] = "CPU stop NMIs", [IPI_TIMER] = "Timer broadcast interrupts", [IPI_IRQ_WORK] = "IRQ work interrupts", [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts", @@ -867,9 +869,9 @@ void arch_irq_work_raise(void) } #endif -static void __noreturn local_cpu_stop(void) +static void __noreturn local_cpu_stop(unsigned int cpu) { - set_cpu_online(smp_processor_id(), false); + set_cpu_online(cpu, false); local_daif_mask(); sdei_mask_local_cpu(); @@ -883,21 +885,26 @@ static void __noreturn local_cpu_stop(void) */ void __noreturn panic_smp_self_stop(void) { - local_cpu_stop(); + local_cpu_stop(smp_processor_id()); } -#ifdef CONFIG_KEXEC_CORE -static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); -#endif - static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) { #ifdef CONFIG_KEXEC_CORE + /* + * Use local_daif_mask() instead of local_irq_disable() to make sure + * that pseudo-NMIs are disabled. The "crash stop" code starts with + * an IRQ and falls back to NMI (which might be pseudo). If the IRQ + * finally goes through right as we're timing out then the NMI could + * interrupt us. It's better to prevent the NMI and let the IRQ + * finish since the pt_regs will be better. + */ + local_daif_mask(); + crash_save_cpu(regs, cpu); - atomic_dec(&waiting_for_crash_ipi); + set_cpu_online(cpu, false); - local_irq_disable(); sdei_mask_local_cpu(); if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) @@ -962,14 +969,12 @@ static void do_handle_IPI(int ipinr) break; case IPI_CPU_STOP: - local_cpu_stop(); - break; - - case IPI_CPU_CRASH_STOP: - if (IS_ENABLED(CONFIG_KEXEC_CORE)) { + case IPI_CPU_STOP_NMI: + if (IS_ENABLED(CONFIG_KEXEC_CORE) && crash_stop) { ipi_cpu_crash_stop(cpu, get_irq_regs()); - unreachable(); + } else { + local_cpu_stop(cpu); } break; @@ -1024,8 +1029,7 @@ static bool ipi_should_be_nmi(enum ipi_msg_type ipi) return false; switch (ipi) { - case IPI_CPU_STOP: - case IPI_CPU_CRASH_STOP: + case IPI_CPU_STOP_NMI: case IPI_CPU_BACKTRACE: case IPI_KGDB_ROUNDUP: return true; @@ -1138,79 +1142,109 @@ static inline unsigned int num_other_online_cpus(void) void smp_send_stop(void) { + static unsigned long stop_in_progress; + cpumask_t mask; unsigned long timeout; - if (num_other_online_cpus()) { - cpumask_t mask; + /* + * If this cpu is the only one alive at this point in time, online or + * not, there are no stop messages to be sent around, so just back out. + */ + if (num_other_online_cpus() == 0) + goto skip_ipi; - cpumask_copy(&mask, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), &mask); + /* Only proceed if this is the first CPU to reach this code */ + if (test_and_set_bit(0, &stop_in_progress)) + return; - if (system_state <= SYSTEM_RUNNING) - pr_crit("SMP: stopping secondary CPUs\n"); - smp_cross_call(&mask, IPI_CPU_STOP); - } + /* + * Send an IPI to all currently online CPUs except the CPU running + * this code. + * + * NOTE: we don't do anything here to prevent other CPUs from coming + * online after we snapshot `cpu_online_mask`. Ideally, the calling code + * should do something to prevent other CPUs from coming up. This code + * can be called in the panic path and thus it doesn't seem wise to + * grab the CPU hotplug mutex ourselves. Worst case: + * - If a CPU comes online as we're running, we'll likely notice it + * during the 1 second wait below and then we'll catch it when we try + * with an NMI (assuming NMIs are enabled) since we re-snapshot the + * mask before sending an NMI. + * - If we leave the function and see that CPUs are still online we'll + * at least print a warning. Especially without NMIs this function + * isn't foolproof anyway so calling code will just have to accept + * the fact that there could be cases where a CPU can't be stopped. + */ + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); - /* Wait up to one second for other CPUs to stop */ + if (system_state <= SYSTEM_RUNNING) + pr_crit("SMP: stopping secondary CPUs\n"); + + /* + * Start with a normal IPI and wait up to one second for other CPUs to + * stop. We do this first because it gives other processors a chance + * to exit critical sections / drop locks and makes the rest of the + * stop process (especially console flush) more robust. + */ + smp_cross_call(&mask, IPI_CPU_STOP); timeout = USEC_PER_SEC; while (num_other_online_cpus() && timeout--) udelay(1); - if (num_other_online_cpus()) + /* + * If CPUs are still online, try an NMI. There's no excuse for this to + * be slow, so we only give them an extra 10 ms to respond. + */ + if (num_other_online_cpus() && ipi_should_be_nmi(IPI_CPU_STOP_NMI)) { + smp_rmb(); + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + pr_info("SMP: retry stop with NMI for CPUs %*pbl\n", + cpumask_pr_args(&mask)); + + smp_cross_call(&mask, IPI_CPU_STOP_NMI); + timeout = USEC_PER_MSEC * 10; + while (num_other_online_cpus() && timeout--) + udelay(1); + } + + if (num_other_online_cpus()) { + smp_rmb(); + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", - cpumask_pr_args(cpu_online_mask)); + cpumask_pr_args(&mask)); + } +skip_ipi: sdei_mask_local_cpu(); } #ifdef CONFIG_KEXEC_CORE void crash_smp_send_stop(void) { - static int cpus_stopped; - cpumask_t mask; - unsigned long timeout; - /* * This function can be called twice in panic path, but obviously * we execute this only once. + * + * We use this same boolean to tell whether the IPI we send was a + * stop or a "crash stop". */ - if (cpus_stopped) + if (crash_stop) return; + crash_stop = 1; - cpus_stopped = 1; + smp_send_stop(); - /* - * If this cpu is the only one alive at this point in time, online or - * not, there are no stop messages to be sent around, so just back out. - */ - if (num_other_online_cpus() == 0) - goto skip_ipi; - - cpumask_copy(&mask, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), &mask); - - atomic_set(&waiting_for_crash_ipi, num_other_online_cpus()); - - pr_crit("SMP: stopping secondary CPUs\n"); - smp_cross_call(&mask, IPI_CPU_CRASH_STOP); - - /* Wait up to one second for other CPUs to stop */ - timeout = USEC_PER_SEC; - while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) - udelay(1); - - if (atomic_read(&waiting_for_crash_ipi) > 0) - pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", - cpumask_pr_args(&mask)); - -skip_ipi: - sdei_mask_local_cpu(); sdei_handler_abort(); } bool smp_crash_stop_failed(void) { - return (atomic_read(&waiting_for_crash_ipi) > 0); + return num_other_online_cpus() != 0; } #endif diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 9e22683aa921..563cbce11126 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -273,6 +273,12 @@ void arm64_force_sig_fault(int signo, int code, unsigned long far, force_sig_fault(signo, code, (void __user *)far); } +void arm64_force_sig_fault_pkey(unsigned long far, const char *str, int pkey) +{ + arm64_show_signal(SIGSEGV, str); + force_sig_pkuerr((void __user *)far, pkey); +} + void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str) { @@ -601,18 +607,26 @@ static void ctr_read_handler(unsigned long esr, struct pt_regs *regs) static void cntvct_read_handler(unsigned long esr, struct pt_regs *regs) { - int rt = ESR_ELx_SYS64_ISS_RT(esr); + if (test_thread_flag(TIF_TSC_SIGSEGV)) { + force_sig(SIGSEGV); + } else { + int rt = ESR_ELx_SYS64_ISS_RT(esr); - pt_regs_write_reg(regs, rt, arch_timer_read_counter()); - arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); + pt_regs_write_reg(regs, rt, arch_timer_read_counter()); + arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); + } } static void cntfrq_read_handler(unsigned long esr, struct pt_regs *regs) { - int rt = ESR_ELx_SYS64_ISS_RT(esr); + if (test_thread_flag(TIF_TSC_SIGSEGV)) { + force_sig(SIGSEGV); + } else { + int rt = ESR_ELx_SYS64_ISS_RT(esr); - pt_regs_write_reg(regs, rt, arch_timer_get_rate()); - arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); + pt_regs_write_reg(regs, rt, arch_timer_get_rate()); + arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); + } } static void mrs_handler(unsigned long esr, struct pt_regs *regs) diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h index 9e13c1bc2ad5..17df94570f03 100644 --- a/arch/arm64/kvm/hyp/include/hyp/fault.h +++ b/arch/arm64/kvm/hyp/include/hyp/fault.h @@ -14,6 +14,7 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) { + int ret; u64 par, tmp; /* @@ -27,7 +28,9 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) * saved the guest context yet, and we may return early... */ par = read_sysreg_par(); - if (!__kvm_at("s1e1r", far)) + ret = system_supports_poe() ? __kvm_at(OP_AT_S1E1A, far) : + __kvm_at(OP_AT_S1E1R, far); + if (!ret) tmp = read_sysreg_par(); else tmp = SYS_PAR_EL1_F; /* back to the guest */ diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index 4c0fdabaf8ae..1579a3c08a36 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -16,9 +16,15 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> +static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt); + static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { ctxt_sys_reg(ctxt, MDSCR_EL1) = read_sysreg(mdscr_el1); + + // POR_EL0 can affect uaccess, so must be saved/restored early. + if (ctxt_has_s1poe(ctxt)) + ctxt_sys_reg(ctxt, POR_EL0) = read_sysreg_s(SYS_POR_EL0); } static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt) @@ -66,6 +72,17 @@ static inline bool ctxt_has_tcrx(struct kvm_cpu_context *ctxt) return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, TCRX, IMP); } +static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu; + + if (!system_supports_poe()) + return false; + + vcpu = ctxt_to_vcpu(ctxt); + return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, S1POE, IMP); +} + static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) { ctxt_sys_reg(ctxt, SCTLR_EL1) = read_sysreg_el1(SYS_SCTLR); @@ -80,6 +97,9 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) ctxt_sys_reg(ctxt, PIR_EL1) = read_sysreg_el1(SYS_PIR); ctxt_sys_reg(ctxt, PIRE0_EL1) = read_sysreg_el1(SYS_PIRE0); } + + if (ctxt_has_s1poe(ctxt)) + ctxt_sys_reg(ctxt, POR_EL1) = read_sysreg_el1(SYS_POR); } ctxt_sys_reg(ctxt, ESR_EL1) = read_sysreg_el1(SYS_ESR); ctxt_sys_reg(ctxt, AFSR0_EL1) = read_sysreg_el1(SYS_AFSR0); @@ -120,6 +140,10 @@ static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1), mdscr_el1); + + // POR_EL0 can affect uaccess, so must be saved/restored early. + if (ctxt_has_s1poe(ctxt)) + write_sysreg_s(ctxt_sys_reg(ctxt, POR_EL0), SYS_POR_EL0); } static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) @@ -158,6 +182,9 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1), SYS_PIR); write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1), SYS_PIRE0); } + + if (ctxt_has_s1poe(ctxt)) + write_sysreg_el1(ctxt_sys_reg(ctxt, POR_EL1), SYS_POR); } write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1), SYS_ESR); write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1), SYS_AFSR0); diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 82a2a003259c..ac36c438b8c1 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -233,7 +233,7 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) int i; struct kvm_pmu *pmu = &vcpu->arch.pmu; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) pmu->pmc[i].idx = i; } @@ -260,7 +260,7 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) { int i; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i)); irq_work_sync(&vcpu->arch.pmu.overflow_work); } @@ -291,7 +291,7 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) return; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc; if (!(val & BIT(i))) @@ -323,7 +323,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) if (!kvm_vcpu_has_pmu(vcpu) || !val) return; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc; if (!(val & BIT(i))) @@ -910,10 +910,10 @@ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; /* - * The arm_pmu->num_events considers the cycle counter as well. - * Ignore that and return only the general-purpose counters. + * The arm_pmu->cntr_mask considers the fixed counter(s) as well. + * Ignore those and return only the general-purpose counters. */ - return arm_pmu->num_events - 1; + return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS); } static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu) diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 329819806096..0b3adf3e17b4 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -5,6 +5,8 @@ */ #include <linux/kvm_host.h> #include <linux/perf_event.h> +#include <linux/perf/arm_pmu.h> +#include <linux/perf/arm_pmuv3.h> static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events); @@ -35,7 +37,7 @@ struct kvm_pmu_events *kvm_get_pmu_events(void) * Add events to track that we may want to switch at guest entry/exit * time. */ -void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) +void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); @@ -51,7 +53,7 @@ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) /* * Stop tracking events */ -void kvm_clr_pmu_events(u32 clr) +void kvm_clr_pmu_events(u64 clr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); @@ -62,79 +64,32 @@ void kvm_clr_pmu_events(u32 clr) pmu->events_guest &= ~clr; } -#define PMEVTYPER_READ_CASE(idx) \ - case idx: \ - return read_sysreg(pmevtyper##idx##_el0) - -#define PMEVTYPER_WRITE_CASE(idx) \ - case idx: \ - write_sysreg(val, pmevtyper##idx##_el0); \ - break - -#define PMEVTYPER_CASES(readwrite) \ - PMEVTYPER_##readwrite##_CASE(0); \ - PMEVTYPER_##readwrite##_CASE(1); \ - PMEVTYPER_##readwrite##_CASE(2); \ - PMEVTYPER_##readwrite##_CASE(3); \ - PMEVTYPER_##readwrite##_CASE(4); \ - PMEVTYPER_##readwrite##_CASE(5); \ - PMEVTYPER_##readwrite##_CASE(6); \ - PMEVTYPER_##readwrite##_CASE(7); \ - PMEVTYPER_##readwrite##_CASE(8); \ - PMEVTYPER_##readwrite##_CASE(9); \ - PMEVTYPER_##readwrite##_CASE(10); \ - PMEVTYPER_##readwrite##_CASE(11); \ - PMEVTYPER_##readwrite##_CASE(12); \ - PMEVTYPER_##readwrite##_CASE(13); \ - PMEVTYPER_##readwrite##_CASE(14); \ - PMEVTYPER_##readwrite##_CASE(15); \ - PMEVTYPER_##readwrite##_CASE(16); \ - PMEVTYPER_##readwrite##_CASE(17); \ - PMEVTYPER_##readwrite##_CASE(18); \ - PMEVTYPER_##readwrite##_CASE(19); \ - PMEVTYPER_##readwrite##_CASE(20); \ - PMEVTYPER_##readwrite##_CASE(21); \ - PMEVTYPER_##readwrite##_CASE(22); \ - PMEVTYPER_##readwrite##_CASE(23); \ - PMEVTYPER_##readwrite##_CASE(24); \ - PMEVTYPER_##readwrite##_CASE(25); \ - PMEVTYPER_##readwrite##_CASE(26); \ - PMEVTYPER_##readwrite##_CASE(27); \ - PMEVTYPER_##readwrite##_CASE(28); \ - PMEVTYPER_##readwrite##_CASE(29); \ - PMEVTYPER_##readwrite##_CASE(30) - /* * Read a value direct from PMEVTYPER<idx> where idx is 0-30 - * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31). + * or PMxCFILTR_EL0 where idx is 31-32. */ static u64 kvm_vcpu_pmu_read_evtype_direct(int idx) { - switch (idx) { - PMEVTYPER_CASES(READ); - case ARMV8_PMU_CYCLE_IDX: - return read_sysreg(pmccfiltr_el0); - default: - WARN_ON(1); - } + if (idx == ARMV8_PMU_CYCLE_IDX) + return read_pmccfiltr(); + else if (idx == ARMV8_PMU_INSTR_IDX) + return read_pmicfiltr(); - return 0; + return read_pmevtypern(idx); } /* * Write a value direct to PMEVTYPER<idx> where idx is 0-30 - * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31). + * or PMxCFILTR_EL0 where idx is 31-32. */ static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val) { - switch (idx) { - PMEVTYPER_CASES(WRITE); - case ARMV8_PMU_CYCLE_IDX: - write_sysreg(val, pmccfiltr_el0); - break; - default: - WARN_ON(1); - } + if (idx == ARMV8_PMU_CYCLE_IDX) + write_pmccfiltr(val); + else if (idx == ARMV8_PMU_INSTR_IDX) + write_pmicfiltr(val); + else + write_pmevtypern(idx, val); } /* @@ -145,7 +100,7 @@ static void kvm_vcpu_pmu_enable_el0(unsigned long events) u64 typer; u32 counter; - for_each_set_bit(counter, &events, 32) { + for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer &= ~ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); @@ -160,7 +115,7 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events) u64 typer; u32 counter; - for_each_set_bit(counter, &events, 32) { + for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer |= ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); @@ -176,7 +131,7 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events) void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; - u32 events_guest, events_host; + u64 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; @@ -197,7 +152,7 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; - u32 events_guest, events_host; + u64 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 31e49da867ff..3e22ce1c4770 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -18,6 +18,7 @@ #include <linux/printk.h> #include <linux/uaccess.h> +#include <asm/arm_pmuv3.h> #include <asm/cacheflush.h> #include <asm/cputype.h> #include <asm/debug-monitors.h> @@ -893,7 +894,7 @@ static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { reset_unknown(vcpu, r); - __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_COUNTER_MASK; + __vcpu_sys_reg(vcpu, r->reg) &= PMSELR_EL0_SEL_MASK; return __vcpu_sys_reg(vcpu, r->reg); } @@ -985,7 +986,7 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, else /* return PMSELR.SEL field */ p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0) - & ARMV8_PMU_COUNTER_MASK; + & PMSELR_EL0_SEL_MASK; return true; } @@ -1053,8 +1054,8 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, if (pmu_access_event_counter_el0_disabled(vcpu)) return false; - idx = __vcpu_sys_reg(vcpu, PMSELR_EL0) - & ARMV8_PMU_COUNTER_MASK; + idx = SYS_FIELD_GET(PMSELR_EL0, SEL, + __vcpu_sys_reg(vcpu, PMSELR_EL0)); } else if (r->Op2 == 0) { /* PMCCNTR_EL0 */ if (pmu_access_cycle_counter_el0_disabled(vcpu)) @@ -1104,7 +1105,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) { /* PMXEVTYPER_EL0 */ - idx = __vcpu_sys_reg(vcpu, PMSELR_EL0) & ARMV8_PMU_COUNTER_MASK; + idx = SYS_FIELD_GET(PMSELR_EL0, SEL, __vcpu_sys_reg(vcpu, PMSELR_EL0)); reg = PMEVTYPER0_EL0 + idx; } else if (r->CRn == 14 && (r->CRm & 12) == 12) { idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); @@ -1562,6 +1563,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, case SYS_ID_AA64MMFR2_EL1: val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; break; + case SYS_ID_AA64MMFR3_EL1: + val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE; + break; case SYS_ID_MMFR4_EL1: val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX); break; @@ -2261,6 +2265,15 @@ static bool access_zcr_el2(struct kvm_vcpu *vcpu, return true; } +static unsigned int s1poe_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S1POE, IMP)) + return 0; + + return REG_HIDDEN; +} + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -2424,7 +2437,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64MMFR2_EL1_IDS | ID_AA64MMFR2_EL1_NV | ID_AA64MMFR2_EL1_CCIDX)), - ID_SANITISED(ID_AA64MMFR3_EL1), + ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX | + ID_AA64MMFR3_EL1_S1POE)), ID_SANITISED(ID_AA64MMFR4_EL1), ID_UNALLOCATED(7,5), ID_UNALLOCATED(7,6), @@ -2498,6 +2512,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1 }, { SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1 }, + { SYS_DESC(SYS_POR_EL1), NULL, reset_unknown, POR_EL1, + .visibility = s1poe_visibility }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, { SYS_DESC(SYS_LORSA_EL1), trap_loregion }, @@ -2584,6 +2600,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { .access = access_pmovs, .reg = PMOVSSET_EL0, .get_user = get_pmreg, .set_user = set_pmreg }, + { SYS_DESC(SYS_POR_EL0), NULL, reset_unknown, POR_EL0, + .visibility = s1poe_visibility }, { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, { SYS_DESC(SYS_TPIDR2_EL0), undef_access }, @@ -4574,8 +4592,6 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu) kvm->arch.fgu[HFGxTR_GROUP] = (HFGxTR_EL2_nAMAIR2_EL1 | HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nS2POR_EL1 | - HFGxTR_EL2_nPOR_EL1 | - HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nACCDATA_EL1 | HFGxTR_EL2_nSMPRI_EL1_MASK | HFGxTR_EL2_nTPIDR2_EL0_MASK); @@ -4610,6 +4626,10 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu) kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPIRE0_EL1 | HFGxTR_EL2_nPIR_EL1); + if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1POE, IMP)) + kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPOR_EL1 | + HFGxTR_EL2_nPOR_EL0); + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP)) kvm->arch.fgu[HAFGRTR_GROUP] |= ~(HAFGRTR_EL2_RES0 | HAFGRTR_EL2_RES1); diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 60454256945b..2fc8c6dd0407 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-y := dma-mapping.o extable.o fault.o init.o \ cache.o copypage.o flush.o \ - ioremap.o mmap.o pgd.o mmu.o \ + ioremap.o mmap.o pgd.o mem_encrypt.o mmu.o \ context.o proc.o pageattr.o fixmap.o obj-$(CONFIG_ARM64_CONTPTE) += contpte.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index a3edced29ac1..55107d27d3f8 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -421,6 +421,12 @@ int contpte_ptep_set_access_flags(struct vm_area_struct *vma, ptep = contpte_align_down(ptep); start_addr = addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); + /* + * We are not advancing entry because __ptep_set_access_flags() + * only consumes access flags from entry. And since we have checked + * for the whole contpte block and returned early, pte_same() + * within __ptep_set_access_flags() is likely false. + */ for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) __ptep_set_access_flags(vma, addr, ptep, entry, 0); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 451ba7cbd5ad..8b281cf308b3 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -23,6 +23,7 @@ #include <linux/sched/debug.h> #include <linux/highmem.h> #include <linux/perf_event.h> +#include <linux/pkeys.h> #include <linux/preempt.h> #include <linux/hugetlb.h> @@ -486,6 +487,23 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } +static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma, + unsigned int mm_flags) +{ + unsigned long iss2 = ESR_ELx_ISS2(esr); + + if (!system_supports_poe()) + return false; + + if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay)) + return true; + + return !arch_vma_access_permitted(vma, + mm_flags & FAULT_FLAG_WRITE, + mm_flags & FAULT_FLAG_INSTRUCTION, + false); +} + static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; @@ -511,6 +529,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; int si_code; + int pkey = -1; if (kprobe_page_fault(regs, esr)) return 0; @@ -575,6 +594,16 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } + + if (fault_from_pkey(esr, vma, mm_flags)) { + pkey = vma_pkey(vma); + vma_end_read(vma); + fault = 0; + si_code = SEGV_PKUERR; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto bad_area; + } + fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); @@ -610,7 +639,16 @@ retry: goto bad_area; } + if (fault_from_pkey(esr, vma, mm_flags)) { + pkey = vma_pkey(vma); + mmap_read_unlock(mm); + fault = 0; + si_code = SEGV_PKUERR; + goto bad_area; + } + fault = handle_mm_fault(vma, addr, mm_flags, regs); + /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) @@ -669,8 +707,23 @@ bad_area: arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { + /* + * The pkey value that we return to userspace can be different + * from the pkey that caused the fault. + * + * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); + * 2. T1 : set POR_EL0 to deny access to pkey=4, touches, page + * 3. T1 : faults... + * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); + * 5. T1 : enters fault handler, takes mmap_lock, etc... + * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really + * faulted on a pte with its pkey=4. + */ /* Something tried to access memory that out of memory map */ - arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); + if (si_code == SEGV_PKUERR) + arm64_force_sig_fault_pkey(far, inf->name, pkey); + else + arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9b5ab6818f7f..a0400b9aa814 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -414,8 +414,16 @@ void __init mem_init(void) void free_initmem(void) { - free_reserved_area(lm_alias(__init_begin), - lm_alias(__init_end), + void *lm_init_begin = lm_alias(__init_begin); + void *lm_init_end = lm_alias(__init_end); + + WARN_ON(!IS_ALIGNED((unsigned long)lm_init_begin, PAGE_SIZE)); + WARN_ON(!IS_ALIGNED((unsigned long)lm_init_end, PAGE_SIZE)); + + /* Delete __init region from memblock.reserved. */ + memblock_free(lm_init_begin, lm_init_end - lm_init_begin); + + free_reserved_area(lm_init_begin, lm_init_end, POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index 269f2f63ab7d..6cc0b7e7eb03 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -3,10 +3,22 @@ #include <linux/mm.h> #include <linux/io.h> +static ioremap_prot_hook_t ioremap_prot_hook; + +int arm64_ioremap_prot_hook_register(ioremap_prot_hook_t hook) +{ + if (WARN_ON(ioremap_prot_hook)) + return -EBUSY; + + ioremap_prot_hook = hook; + return 0; +} + void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, unsigned long prot) { unsigned long last_addr = phys_addr + size - 1; + pgprot_t pgprot = __pgprot(prot); /* Don't allow outside PHYS_MASK */ if (last_addr & ~PHYS_MASK) @@ -16,7 +28,16 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, if (WARN_ON(pfn_is_map_memory(__phys_to_pfn(phys_addr)))) return NULL; - return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); + /* + * If a hook is registered (e.g. for confidential computing + * purposes), call that now and barf if it fails. + */ + if (unlikely(ioremap_prot_hook) && + WARN_ON(ioremap_prot_hook(phys_addr, size, &pgprot))) { + return NULL; + } + + return generic_ioremap_prot(phys_addr, size, pgprot); } EXPORT_SYMBOL(ioremap_prot); diff --git a/arch/arm64/mm/mem_encrypt.c b/arch/arm64/mm/mem_encrypt.c new file mode 100644 index 000000000000..ee3c0ab04384 --- /dev/null +++ b/arch/arm64/mm/mem_encrypt.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Implementation of the memory encryption/decryption API. + * + * Since the low-level details of the operation depend on the + * Confidential Computing environment (e.g. pKVM, CCA, ...), this just + * acts as a top-level dispatcher to whatever hooks may have been + * registered. + * + * Author: Will Deacon <will@kernel.org> + * Copyright (C) 2024 Google LLC + * + * "Hello, boils and ghouls!" + */ + +#include <linux/bug.h> +#include <linux/compiler.h> +#include <linux/err.h> +#include <linux/mm.h> + +#include <asm/mem_encrypt.h> + +static const struct arm64_mem_crypt_ops *crypt_ops; + +int arm64_mem_crypt_ops_register(const struct arm64_mem_crypt_ops *ops) +{ + if (WARN_ON(crypt_ops)) + return -EBUSY; + + crypt_ops = ops; + return 0; +} + +int set_memory_encrypted(unsigned long addr, int numpages) +{ + if (likely(!crypt_ops) || WARN_ON(!PAGE_ALIGNED(addr))) + return 0; + + return crypt_ops->encrypt(addr, numpages); +} +EXPORT_SYMBOL_GPL(set_memory_encrypted); + +int set_memory_decrypted(unsigned long addr, int numpages) +{ + if (likely(!crypt_ops) || WARN_ON(!PAGE_ALIGNED(addr))) + return 0; + + return crypt_ops->decrypt(addr, numpages); +} +EXPORT_SYMBOL_GPL(set_memory_decrypted); diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 642bdf908b22..7e3ad97e27d8 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -102,6 +102,17 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags) if (vm_flags & VM_MTE) prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED); +#ifdef CONFIG_ARCH_HAS_PKEYS + if (system_supports_poe()) { + if (vm_flags & VM_PKEY_BIT0) + prot |= PTE_PO_IDX_0; + if (vm_flags & VM_PKEY_BIT1) + prot |= PTE_PO_IDX_1; + if (vm_flags & VM_PKEY_BIT2) + prot |= PTE_PO_IDX_2; + } +#endif + return __pgprot(prot); } EXPORT_SYMBOL(vm_get_page_prot); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 353ea5dc32b8..e55b02fbddc8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -25,6 +25,7 @@ #include <linux/vmalloc.h> #include <linux/set_memory.h> #include <linux/kfence.h> +#include <linux/pkeys.h> #include <asm/barrier.h> #include <asm/cputype.h> @@ -1549,3 +1550,47 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp) cpu_uninstall_idmap(); } + +#ifdef CONFIG_ARCH_HAS_PKEYS +int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) +{ + u64 new_por = POE_RXW; + u64 old_por; + u64 pkey_shift; + + if (!system_supports_poe()) + return -ENOSPC; + + /* + * This code should only be called with valid 'pkey' + * values originating from in-kernel users. Complain + * if a bad value is observed. + */ + if (WARN_ON_ONCE(pkey >= arch_max_pkey())) + return -EINVAL; + + /* Set the bits we need in POR: */ + new_por = POE_RXW; + if (init_val & PKEY_DISABLE_WRITE) + new_por &= ~POE_W; + if (init_val & PKEY_DISABLE_ACCESS) + new_por &= ~POE_RW; + if (init_val & PKEY_DISABLE_READ) + new_por &= ~POE_R; + if (init_val & PKEY_DISABLE_EXECUTE) + new_por &= ~POE_X; + + /* Shift the bits in to the correct place in POR for pkey: */ + pkey_shift = pkey * POR_BITS_PER_PKEY; + new_por <<= pkey_shift; + + /* Get old POR and mask off any old bits in place: */ + old_por = read_sysreg_s(SYS_POR_EL0); + old_por &= ~(POE_MASK << pkey_shift); + + /* Write old part along with new part: */ + write_sysreg_s(old_por | new_por, SYS_POR_EL0); + + return 0; +} +#endif diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index f4bc6c5bac06..8abdc7fed321 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -36,8 +36,6 @@ #define TCR_KASLR_FLAGS 0 #endif -#define TCR_SMP_FLAGS TCR_SHARED - /* PTWs cacheable, inner/outer WBWA */ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA @@ -469,7 +467,7 @@ SYM_FUNC_START(__cpu_setup) tcr .req x16 mov_q mair, MAIR_EL1_SET mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS_MIN) | TCR_CACHE_FLAGS | \ - TCR_SMP_FLAGS | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ + TCR_SHARED | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS tcr_clear_errata_bits tcr, x9, x5 diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 5139a28130c0..0f7b484cb2ff 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -42,14 +42,16 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) * the temporary mappings we use during restore. */ __set_pte(dst_ptep, pte_mkwrite_novma(pte)); - } else if ((debug_pagealloc_enabled() || - is_kfence_address((void *)addr)) && !pte_none(pte)) { + } else if (!pte_none(pte)) { /* * debug_pagealloc will removed the PTE_VALID bit if * the page isn't in use by the resume kernel. It may have * been in use by the original kernel, in which case we need * to put it back in our copy to do the restore. * + * Other cases include kfence / vmalloc / memfd_secret which + * may call `set_direct_map_invalid_noflush()`. + * * Before marking this entry valid, check the pfn should * be mapped. */ diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index ac3429d892b9..eedb5acc21ed 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -45,6 +45,7 @@ HAS_MOPS HAS_NESTED_VIRT HAS_PAN HAS_S1PIE +HAS_S1POE HAS_RAS_EXTN HAS_RNG HAS_SB diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 7ceaa1e0b4bc..8d637ac4b7c6 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2029,6 +2029,31 @@ Sysreg FAR_EL1 3 0 6 0 0 Field 63:0 ADDR EndSysreg +Sysreg PMICNTR_EL0 3 3 9 4 0 +Field 63:0 ICNT +EndSysreg + +Sysreg PMICFILTR_EL0 3 3 9 6 0 +Res0 63:59 +Field 58 SYNC +Field 57:56 VS +Res0 55:32 +Field 31 P +Field 30 U +Field 29 NSK +Field 28 NSU +Field 27 NSH +Field 26 M +Res0 25 +Field 24 SH +Field 23 T +Field 22 RLK +Field 21 RLU +Field 20 RLH +Res0 19:16 +Field 15:0 evtCount +EndSysreg + Sysreg PMSCR_EL1 3 0 9 9 0 Res0 63:8 Field 7:6 PCT @@ -2153,6 +2178,11 @@ Field 4 P Field 3:0 ALIGN EndSysreg +Sysreg PMSELR_EL0 3 3 9 12 5 +Res0 63:5 +Field 4:0 SEL +EndSysreg + SysregFields CONTEXTIDR_ELx Res0 63:32 Field 31:0 PROCID diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d7b09b064a8a..8a4ee57cd4ef 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -1026,6 +1026,10 @@ config PPC_MEM_KEYS If unsure, say y. +config ARCH_PKEY_BITS + int + default 5 + config PPC_SECURE_BOOT prompt "Enable secure boot support" bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 475bc538615e..6f1c31f4b9ab 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1889,6 +1889,10 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +config ARCH_PKEY_BITS + int + default 4 + choice prompt "TSX enable mode" depends on CPU_SUP_INTEL |