diff options
29 files changed, 622 insertions, 201 deletions
diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst index 3278fb4bf219..cad6fdc96b98 100644 --- a/Documentation/arch/arm64/booting.rst +++ b/Documentation/arch/arm64/booting.rst @@ -449,6 +449,18 @@ Before jumping into the kernel, the following conditions must be met: - HFGWTR_EL2.nGCS_EL0 (bit 52) must be initialised to 0b1. + - For CPUs with debug architecture i.e FEAT_Debugv8pN (all versions): + + - If EL3 is present: + + - MDCR_EL3.TDA (bit 9) must be initialized to 0b0 + + - For CPUs with FEAT_PMUv3: + + - If EL3 is present: + + - MDCR_EL3.TPM (bit 6) must be initialized to 0b0 + The requirements described above for CPU mode, caches, MMUs, architected timers, coherency and system registers apply to all CPUs. All CPUs must enter the kernel in the same exception level. Where the values documented diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 2ff922a406ad..69d7afe56853 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -174,26 +174,82 @@ HWCAP_GCS Functionality implied by ID_AA64PFR1_EL1.GCS == 0b1, as described by Documentation/arch/arm64/gcs.rst. +HWCAP_CMPBR + Functionality implied by ID_AA64ISAR2_EL1.CSSC == 0b0010. + +HWCAP_FPRCVT + Functionality implied by ID_AA64ISAR3_EL1.FPRCVT == 0b0001. + +HWCAP_F8MM8 + Functionality implied by ID_AA64FPFR0_EL1.F8MM8 == 0b0001. + +HWCAP_F8MM4 + Functionality implied by ID_AA64FPFR0_EL1.F8MM4 == 0b0001. + +HWCAP_SVE_F16MM + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.F16MM == 0b0001. + +HWCAP_SVE_ELTPERM + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.ELTPERM == 0b0001. + +HWCAP_SVE_AES2 + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.AES == 0b0011. + +HWCAP_SVE_BFSCALE + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.B16B16 == 0b0010. + +HWCAP_SVE2P2 + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SVEver == 0b0011. + +HWCAP_SME2P2 + Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0011. + +HWCAP_SME_SBITPERM + Functionality implied by ID_AA64SMFR0_EL1.SBitPerm == 0b1. + +HWCAP_SME_AES + Functionality implied by ID_AA64SMFR0_EL1.AES == 0b1. + +HWCAP_SME_SFEXPA + Functionality implied by ID_AA64SMFR0_EL1.SFEXPA == 0b1. + +HWCAP_SME_STMOP + Functionality implied by ID_AA64SMFR0_EL1.STMOP == 0b1. + +HWCAP_SME_SMOP4 + Functionality implied by ID_AA64SMFR0_EL1.SMOP4 == 0b1. + HWCAP2_DCPODP Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010. HWCAP2_SVE2 - Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SVEver == 0b0001. HWCAP2_SVEAES - Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.AES == 0b0001. HWCAP2_SVEPMULL - Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.AES == 0b0010. HWCAP2_SVEBITPERM - Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.BitPerm == 0b0001. HWCAP2_SVESHA3 - Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SHA3 == 0b0001. HWCAP2_SVESM4 - Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SM4 == 0b0001. HWCAP2_FLAGM2 Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010. @@ -202,16 +258,20 @@ HWCAP2_FRINT Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001. HWCAP2_SVEI8MM - Functionality implied by ID_AA64ZFR0_EL1.I8MM == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.I8MM == 0b0001. HWCAP2_SVEF32MM - Functionality implied by ID_AA64ZFR0_EL1.F32MM == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.F32MM == 0b0001. HWCAP2_SVEF64MM - Functionality implied by ID_AA64ZFR0_EL1.F64MM == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.F64MM == 0b0001. HWCAP2_SVEBF16 - Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.BF16 == 0b0001. HWCAP2_I8MM Functionality implied by ID_AA64ISAR1_EL1.I8MM == 0b0001. @@ -277,7 +337,8 @@ HWCAP2_EBF16 Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0010. HWCAP2_SVE_EBF16 - Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0010. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.BF16 == 0b0010. HWCAP2_CSSC Functionality implied by ID_AA64ISAR2_EL1.CSSC == 0b0001. @@ -286,7 +347,8 @@ HWCAP2_RPRFM Functionality implied by ID_AA64ISAR2_EL1.RPRFM == 0b0001. HWCAP2_SVE2P1 - Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0010. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SVEver == 0b0010. HWCAP2_SME2 Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0001. @@ -313,7 +375,8 @@ HWCAP2_HBC Functionality implied by ID_AA64ISAR2_EL1.BC == 0b0001. HWCAP2_SVE_B16B16 - Functionality implied by ID_AA64ZFR0_EL1.B16B16 == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.B16B16 == 0b0001. HWCAP2_LRCPC3 Functionality implied by ID_AA64ISAR1_EL1.LRCPC == 0b0011. diff --git a/Documentation/arch/arm64/memory.rst b/Documentation/arch/arm64/memory.rst index 8a658984b8bb..678fbb418c3a 100644 --- a/Documentation/arch/arm64/memory.rst +++ b/Documentation/arch/arm64/memory.rst @@ -23,71 +23,6 @@ swapper_pg_dir contains only kernel (global) mappings while the user pgd contains only user (non-global) mappings. The swapper_pg_dir address is written to TTBR1 and never written to TTBR0. - -AArch64 Linux memory layout with 4KB pages + 4 levels (48-bit):: - - Start End Size Use - ----------------------------------------------------------------------- - 0000000000000000 0000ffffffffffff 256TB user - ffff000000000000 ffff7fffffffffff 128TB kernel logical memory map - [ffff600000000000 ffff7fffffffffff] 32TB [kasan shadow region] - ffff800000000000 ffff80007fffffff 2GB modules - ffff800080000000 fffffbffefffffff 124TB vmalloc - fffffbfff0000000 fffffbfffdffffff 224MB fixed mappings (top down) - fffffbfffe000000 fffffbfffe7fffff 8MB [guard region] - fffffbfffe800000 fffffbffff7fffff 16MB PCI I/O space - fffffbffff800000 fffffbffffffffff 8MB [guard region] - fffffc0000000000 fffffdffffffffff 2TB vmemmap - fffffe0000000000 ffffffffffffffff 2TB [guard region] - - -AArch64 Linux memory layout with 64KB pages + 3 levels (52-bit with HW support):: - - Start End Size Use - ----------------------------------------------------------------------- - 0000000000000000 000fffffffffffff 4PB user - fff0000000000000 ffff7fffffffffff ~4PB kernel logical memory map - [fffd800000000000 ffff7fffffffffff] 512TB [kasan shadow region] - ffff800000000000 ffff80007fffffff 2GB modules - ffff800080000000 fffffbffefffffff 124TB vmalloc - fffffbfff0000000 fffffbfffdffffff 224MB fixed mappings (top down) - fffffbfffe000000 fffffbfffe7fffff 8MB [guard region] - fffffbfffe800000 fffffbffff7fffff 16MB PCI I/O space - fffffbffff800000 fffffbffffffffff 8MB [guard region] - fffffc0000000000 ffffffdfffffffff ~4TB vmemmap - ffffffe000000000 ffffffffffffffff 128GB [guard region] - - -Translation table lookup with 4KB pages:: - - +--------+--------+--------+--------+--------+--------+--------+--------+ - |63 56|55 48|47 40|39 32|31 24|23 16|15 8|7 0| - +--------+--------+--------+--------+--------+--------+--------+--------+ - | | | | | | - | | | | | v - | | | | | [11:0] in-page offset - | | | | +-> [20:12] L3 index - | | | +-----------> [29:21] L2 index - | | +---------------------> [38:30] L1 index - | +-------------------------------> [47:39] L0 index - +----------------------------------------> [55] TTBR0/1 - - -Translation table lookup with 64KB pages:: - - +--------+--------+--------+--------+--------+--------+--------+--------+ - |63 56|55 48|47 40|39 32|31 24|23 16|15 8|7 0| - +--------+--------+--------+--------+--------+--------+--------+--------+ - | | | | | - | | | | v - | | | | [15:0] in-page offset - | | | +----------> [28:16] L3 index - | | +--------------------------> [41:29] L2 index - | +-------------------------------> [47:42] L1 index (48-bit) - | [51:42] L1 index (52-bit) - +----------------------------------------> [55] TTBR0/1 - - When using KVM without the Virtualization Host Extensions, the hypervisor maps kernel pages in EL2 at a fixed (and potentially random) offset from the linear mapping. See the kern_hyp_va macro and diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index cbbf70e0f204..0b5ca6e0eb09 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -46,6 +46,8 @@ cpucap_is_possible(const unsigned int cap) return IS_ENABLED(CONFIG_ARM64_POE); case ARM64_HAS_GCS: return IS_ENABLED(CONFIG_ARM64_GCS); + case ARM64_HAFT: + return IS_ENABLED(CONFIG_ARM64_HAFT); case ARM64_UNMAP_KERNEL_AT_EL0: return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0); case ARM64_WORKAROUND_843419: diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 8b4e5a3cd24c..a4d0b77a68d9 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -852,8 +852,7 @@ static inline bool system_supports_gcs(void) static inline bool system_supports_haft(void) { - return IS_ENABLED(CONFIG_ARM64_HAFT) && - cpus_have_final_cap(ARM64_HAFT); + return cpus_have_final_cap(ARM64_HAFT); } static __always_inline bool system_supports_mpam(void) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 85ef966c08cd..cc39c57df787 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -154,7 +154,7 @@ /* Coprocessor traps */ .macro __init_el2_cptr __check_hvhe .LnVHE_\@, x1 - mov x0, #CPACR_ELx_FPEN + mov x0, #CPACR_EL1_FPEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ .LnVHE_\@: @@ -332,7 +332,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SVE traps - orr x0, x0, #CPACR_ELx_ZEN + orr x0, x0, #CPACR_EL1_ZEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ @@ -353,7 +353,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SME traps - orr x0, x0, #CPACR_ELx_SMEN + orr x0, x0, #CPACR_EL1_SMEN msr cpacr_el1, x0 b .Lskip_set_cptr_sme_\@ diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 2b6c61c608e2..1c3f9617d54f 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -93,6 +93,21 @@ #define KERNEL_HWCAP_PACA __khwcap_feature(PACA) #define KERNEL_HWCAP_PACG __khwcap_feature(PACG) #define KERNEL_HWCAP_GCS __khwcap_feature(GCS) +#define KERNEL_HWCAP_CMPBR __khwcap_feature(CMPBR) +#define KERNEL_HWCAP_FPRCVT __khwcap_feature(FPRCVT) +#define KERNEL_HWCAP_F8MM8 __khwcap_feature(F8MM8) +#define KERNEL_HWCAP_F8MM4 __khwcap_feature(F8MM4) +#define KERNEL_HWCAP_SVE_F16MM __khwcap_feature(SVE_F16MM) +#define KERNEL_HWCAP_SVE_ELTPERM __khwcap_feature(SVE_ELTPERM) +#define KERNEL_HWCAP_SVE_AES2 __khwcap_feature(SVE_AES2) +#define KERNEL_HWCAP_SVE_BFSCALE __khwcap_feature(SVE_BFSCALE) +#define KERNEL_HWCAP_SVE2P2 __khwcap_feature(SVE2P2) +#define KERNEL_HWCAP_SME2P2 __khwcap_feature(SME2P2) +#define KERNEL_HWCAP_SME_SBITPERM __khwcap_feature(SME_SBITPERM) +#define KERNEL_HWCAP_SME_AES __khwcap_feature(SME_AES) +#define KERNEL_HWCAP_SME_SFEXPA __khwcap_feature(SME_SFEXPA) +#define KERNEL_HWCAP_SME_STMOP __khwcap_feature(SME_STMOP) +#define KERNEL_HWCAP_SME_SMOP4 __khwcap_feature(SME_SMOP4) #define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 64) #define KERNEL_HWCAP_DCPODP __khwcap2_feature(DCPODP) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 3e0f0de1d2da..43e365fbff0b 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -391,8 +391,6 @@ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ ECN(BKPT32), ECN(VECTOR32), ECN(BRK64), ECN(ERET) -#define CPACR_EL1_TTA (1 << 28) - #define kvm_mode_names \ { PSR_MODE_EL0t, "EL0t" }, \ { PSR_MODE_EL1t, "EL1t" }, \ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index cf811009a33c..4f1d99725f6b 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -556,13 +556,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) ({ \ u64 cptr = 0; \ \ - if ((set) & CPACR_ELx_FPEN) \ + if ((set) & CPACR_EL1_FPEN) \ cptr |= CPTR_EL2_TFP; \ - if ((set) & CPACR_ELx_ZEN) \ + if ((set) & CPACR_EL1_ZEN) \ cptr |= CPTR_EL2_TZ; \ - if ((set) & CPACR_ELx_SMEN) \ + if ((set) & CPACR_EL1_SMEN) \ cptr |= CPTR_EL2_TSM; \ - if ((clr) & CPACR_ELx_TTA) \ + if ((clr) & CPACR_EL1_TTA) \ cptr |= CPTR_EL2_TTA; \ if ((clr) & CPTR_EL2_TAM) \ cptr |= CPTR_EL2_TAM; \ @@ -576,13 +576,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) ({ \ u64 cptr = 0; \ \ - if ((clr) & CPACR_ELx_FPEN) \ + if ((clr) & CPACR_EL1_FPEN) \ cptr |= CPTR_EL2_TFP; \ - if ((clr) & CPACR_ELx_ZEN) \ + if ((clr) & CPACR_EL1_ZEN) \ cptr |= CPTR_EL2_TZ; \ - if ((clr) & CPACR_ELx_SMEN) \ + if ((clr) & CPACR_EL1_SMEN) \ cptr |= CPTR_EL2_TSM; \ - if ((set) & CPACR_ELx_TTA) \ + if ((set) & CPACR_EL1_TTA) \ cptr |= CPTR_EL2_TTA; \ if ((set) & CPTR_EL2_TAM) \ cptr |= CPTR_EL2_TAM; \ @@ -595,13 +595,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) #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); \ + BUILD_BUG_ON((clr) & CPACR_EL1_E0POE); \ + __build_check_all_or_none((clr), CPACR_EL1_FPEN); \ + __build_check_all_or_none((set), CPACR_EL1_FPEN); \ + __build_check_all_or_none((clr), CPACR_EL1_ZEN); \ + __build_check_all_or_none((set), CPACR_EL1_ZEN); \ + __build_check_all_or_none((clr), CPACR_EL1_SMEN); \ + __build_check_all_or_none((set), CPACR_EL1_SMEN); \ \ if (has_vhe() || has_hvhe()) \ sysreg_clear_set(cpacr_el1, clr, set); \ @@ -624,16 +624,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) u64 val; if (has_vhe()) { - val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN); + val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN); if (cpus_have_final_cap(ARM64_SME)) val |= CPACR_EL1_SMEN_EL1EN; } else if (has_hvhe()) { - val = CPACR_ELx_FPEN; + val = CPACR_EL1_FPEN; if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs()) - val |= CPACR_ELx_ZEN; + val |= CPACR_EL1_ZEN; if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_ELx_SMEN; + val |= CPACR_EL1_SMEN; } else { val = CPTR_NVHE_EL2_RES1; @@ -685,7 +685,7 @@ static inline bool ____cptr_xen_trap_enabled(const struct kvm_vcpu *vcpu, #define __guest_hyp_cptr_xen_trap_enabled(vcpu, xen) \ (!vcpu_has_nv(vcpu) ? false : \ ____cptr_xen_trap_enabled(vcpu, \ - SYS_FIELD_GET(CPACR_ELx, xen, \ + SYS_FIELD_GET(CPACR_EL1, xen, \ vcpu_sanitised_cptr_el2(vcpu)))) static inline bool guest_hyp_fpsimd_traps_enabled(const struct kvm_vcpu *vcpu) diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 233e65522716..6cd08198bf19 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -33,14 +33,14 @@ static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr) static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2) { - u64 cpacr_el1 = CPACR_ELx_RES1; + u64 cpacr_el1 = CPACR_EL1_RES1; if (cptr_el2 & CPTR_EL2_TTA) - cpacr_el1 |= CPACR_ELx_TTA; + cpacr_el1 |= CPACR_EL1_TTA; if (!(cptr_el2 & CPTR_EL2_TFP)) - cpacr_el1 |= CPACR_ELx_FPEN; + cpacr_el1 |= CPACR_EL1_FPEN; if (!(cptr_el2 & CPTR_EL2_TZ)) - cpacr_el1 |= CPACR_ELx_ZEN; + cpacr_el1 |= CPACR_EL1_ZEN; cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM); diff --git a/arch/arm64/include/asm/rsi.h b/arch/arm64/include/asm/rsi.h index 188cbb9b23f5..b42aeac05340 100644 --- a/arch/arm64/include/asm/rsi.h +++ b/arch/arm64/include/asm/rsi.h @@ -10,6 +10,8 @@ #include <linux/jump_label.h> #include <asm/rsi_cmds.h> +#define RSI_PDEV_NAME "arm-cca-dev" + DECLARE_STATIC_KEY_FALSE(rsi_present); void __init arm64_rsi_init(void); diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 48d46b768eae..705a7afa8e58 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -56,6 +56,21 @@ #define HWCAP_PACA (1 << 30) #define HWCAP_PACG (1UL << 31) #define HWCAP_GCS (1UL << 32) +#define HWCAP_CMPBR (1UL << 33) +#define HWCAP_FPRCVT (1UL << 34) +#define HWCAP_F8MM8 (1UL << 35) +#define HWCAP_F8MM4 (1UL << 36) +#define HWCAP_SVE_F16MM (1UL << 37) +#define HWCAP_SVE_ELTPERM (1UL << 38) +#define HWCAP_SVE_AES2 (1UL << 39) +#define HWCAP_SVE_BFSCALE (1UL << 40) +#define HWCAP_SVE2P2 (1UL << 41) +#define HWCAP_SME2P2 (1UL << 42) +#define HWCAP_SME_SBITPERM (1UL << 43) +#define HWCAP_SME_AES (1UL << 44) +#define HWCAP_SME_SFEXPA (1UL << 45) +#define HWCAP_SME_STMOP (1UL << 46) +#define HWCAP_SME_SMOP4 (1UL << 47) /* * HWCAP2 flags - for AT_HWCAP2 diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6ce71f444ed8..540ec508a12f 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -268,6 +268,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar3[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FPRCVT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -318,6 +319,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F16MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SM4_SHIFT, 4, 0), @@ -330,6 +333,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_EltPerm_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, 0), @@ -373,6 +378,16 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SBitPerm_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_AES_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SFEXPA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_STMOP_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMOP4_SHIFT, 1, 0), ARM64_FTR_END, }; @@ -381,6 +396,8 @@ static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM8_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, @@ -1004,17 +1021,16 @@ static void init_cpu_ftr_reg(u32 sys_reg, u64 new) /* Override was valid */ ftr_new = tmp; str = "forced"; - } else if (ftr_ovr == tmp) { + } else { /* Override was the safe value */ str = "already set"; } - if (str) - pr_warn("%s[%d:%d]: %s to %llx\n", - reg->name, - ftrp->shift + ftrp->width - 1, - ftrp->shift, str, - tmp & (BIT(ftrp->width) - 1)); + pr_warn("%s[%d:%d]: %s to %llx\n", + reg->name, + ftrp->shift + ftrp->width - 1, + ftrp->shift, str, + tmp & (BIT(ftrp->width) - 1)); } else if ((ftr_mask & reg->override->val) == ftr_mask) { reg->override->val &= ~ftr_mask; pr_warn("%s[%d:%d]: impossible override, ignored\n", @@ -1167,12 +1183,6 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); - /* - * We mask out SMPS since even if the hardware - * supports priorities the kernel does not at present - * and we block access to them. - */ - info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; vec_init_vq_map(ARM64_VEC_SME); cpacr_restore(cpacr); @@ -1423,13 +1433,6 @@ void update_cpu_features(int cpu, id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); - /* - * We mask out SMPS since even if the hardware - * supports priorities the kernel does not at present - * and we block access to them. - */ - info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; - /* Probe vector lengths */ if (!system_capabilities_finalized()) vec_update_vq_map(ARM64_VEC_SME); @@ -2376,8 +2379,8 @@ static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused) #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); + sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1_E0POE); + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_E0POE); } #endif @@ -3022,6 +3025,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = match, \ } +#define HWCAP_CAP_MATCH_ID(match, reg, field, min_value, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + HWCAP_CPUID_MATCH(reg, field, min_value) \ + .matches = match, \ + } + #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { @@ -3050,6 +3060,13 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { }; #endif +#ifdef CONFIG_ARM64_SVE +static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope) +{ + return system_supports_sve() && has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -3092,19 +3109,24 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), - HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), - HWCAP_CAP(ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), - HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), - HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p2, CAP_HWCAP, KERNEL_HWCAP_SVE2P2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, AES2, CAP_HWCAP, KERNEL_HWCAP_SVE_AES2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, BFSCALE, CAP_HWCAP, KERNEL_HWCAP_SVE_BFSCALE), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F16MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_F16MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, EltPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_ELTPERM), #endif #ifdef CONFIG_ARM64_GCS HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS), @@ -3124,6 +3146,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR0_EL1, ECV, IMP, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(ID_AA64MMFR1_EL1, AFP, IMP, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC), + HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, CMPBR, CAP_HWCAP, KERNEL_HWCAP_CMPBR), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), @@ -3133,6 +3156,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), + HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), @@ -3150,6 +3174,13 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4), + HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), + HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), + HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), + HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP), + HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4), #endif /* CONFIG_ARM64_SME */ HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index d79e88fccdfc..285d7d538342 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -145,6 +145,21 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", [KERNEL_HWCAP_POE] = "poe", + [KERNEL_HWCAP_CMPBR] = "cmpbr", + [KERNEL_HWCAP_FPRCVT] = "fprcvt", + [KERNEL_HWCAP_F8MM8] = "f8mm8", + [KERNEL_HWCAP_F8MM4] = "f8mm4", + [KERNEL_HWCAP_SVE_F16MM] = "svef16mm", + [KERNEL_HWCAP_SVE_ELTPERM] = "sveeltperm", + [KERNEL_HWCAP_SVE_AES2] = "sveaes2", + [KERNEL_HWCAP_SVE_BFSCALE] = "svebfscale", + [KERNEL_HWCAP_SVE2P2] = "sve2p2", + [KERNEL_HWCAP_SME2P2] = "sme2p2", + [KERNEL_HWCAP_SME_SBITPERM] = "smesbitperm", + [KERNEL_HWCAP_SME_AES] = "smeaes", + [KERNEL_HWCAP_SME_SFEXPA] = "smesfexpa", + [KERNEL_HWCAP_SME_STMOP] = "smestmop", + [KERNEL_HWCAP_SME_SMOP4] = "smesmop4", }; #ifdef CONFIG_COMPAT @@ -482,6 +497,16 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0)) info->reg_mpamidr = read_cpuid(MPAMIDR_EL1); + if (IS_ENABLED(CONFIG_ARM64_SME) && + id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + /* + * We mask out SMPS since even if the hardware + * supports priorities the kernel does not at present + * and we block access to them. + */ + info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; + } + cpuinfo_detect_icache_policy(info); } diff --git a/arch/arm64/kernel/rsi.c b/arch/arm64/kernel/rsi.c index 3031f25c32ef..ce4778141ec7 100644 --- a/arch/arm64/kernel/rsi.c +++ b/arch/arm64/kernel/rsi.c @@ -8,6 +8,7 @@ #include <linux/psci.h> #include <linux/swiotlb.h> #include <linux/cc_platform.h> +#include <linux/platform_device.h> #include <asm/io.h> #include <asm/mem_encrypt.h> @@ -140,3 +141,17 @@ void __init arm64_rsi_init(void) static_branch_enable(&rsi_present); } +static struct platform_device rsi_dev = { + .name = RSI_PDEV_NAME, + .id = PLATFORM_DEVID_NONE +}; + +static int __init arm64_create_dummy_rsi_dev(void) +{ + if (is_realm_world() && + platform_device_register(&rsi_dev)) + pr_err("failed to register rsi platform device\n"); + return 0; +} + +arch_initcall(arm64_create_dummy_rsi_dev) diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 8c5d7990e5b3..0905b8778a9b 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -111,7 +111,7 @@ static bool s1pie_enabled(struct kvm_vcpu *vcpu, enum trans_regime regime) return vcpu_read_sys_reg(vcpu, TCR2_EL2) & TCR2_EL2_PIE; case TR_EL10: return (__vcpu_sys_reg(vcpu, HCRX_EL2) & HCRX_EL2_TCR2En) && - (__vcpu_sys_reg(vcpu, TCR2_EL1) & TCR2_EL1x_PIE); + (__vcpu_sys_reg(vcpu, TCR2_EL1) & TCR2_EL1_PIE); default: BUG(); } @@ -140,8 +140,8 @@ static void compute_s1poe(struct kvm_vcpu *vcpu, struct s1_walk_info *wi) } val = __vcpu_sys_reg(vcpu, TCR2_EL1); - wi->poe = val & TCR2_EL1x_POE; - wi->e0poe = val & TCR2_EL1x_E0POE; + wi->poe = val & TCR2_EL1_POE; + wi->e0poe = val & TCR2_EL1_E0POE; } } diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 1ffbfd1c3cf2..f1b7287e1f3c 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -494,7 +494,7 @@ static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu) if (!vcpu_el2_e2h_is_set(vcpu)) val = translate_cptr_el2_to_cpacr_el1(val); - if (val & CPACR_ELx_TTA) + if (val & CPACR_EL1_TTA) return BEHAVE_FORWARD_RW; return BEHAVE_HANDLE_LOCALLY; diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index ea5484ce1f3b..98718bd65bf1 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -169,7 +169,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) if (has_vhe() && system_supports_sme()) { /* Also restore EL0 state seen on entry */ if (vcpu_get_flag(vcpu, HOST_SME_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN); + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN); else sysreg_clear_set(CPACR_EL1, CPACR_EL1_SMEN_EL0EN, diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 34f53707892d..abfa6ad92e91 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -419,9 +419,9 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) /* First disable enough traps to allow us to update the registers */ if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve())) - cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN); else - cpacr_clear_set(0, CPACR_ELx_FPEN); + cpacr_clear_set(0, CPACR_EL1_FPEN); isb(); /* Write out the host state if it's in the registers */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 6aa0b13d86e5..6c90ef6736d6 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -68,7 +68,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (!guest_owns_fp_regs()) return; - cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN); isb(); if (vcpu_has_sve(vcpu)) @@ -481,7 +481,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) handle_host_smc(host_ctxt); break; case ESR_ELx_EC_SVE: - cpacr_clear_set(0, CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_ZEN); isb(); sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 01616c39a810..a6638c4ecd32 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -68,7 +68,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu) /* Trap SVE */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) { if (has_hvhe()) - cptr_clear |= CPACR_ELx_ZEN; + cptr_clear |= CPACR_EL1_ZEN; else cptr_set |= CPTR_EL2_TZ; } diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index cc69106734ca..0f6b01b3da5c 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -48,14 +48,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA; if (cpus_have_final_cap(ARM64_SME)) { if (has_hvhe()) - val &= ~CPACR_ELx_SMEN; + val &= ~CPACR_EL1_SMEN; else val |= CPTR_EL2_TSM; } if (!guest_owns_fp_regs()) { if (has_hvhe()) - val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN); + val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN); else val |= CPTR_EL2_TFP | CPTR_EL2_TZ; @@ -192,7 +192,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) /* Re-enable SVE traps if not supported for the guest vcpu. */ if (!vcpu_has_sve(vcpu)) - cpacr_clear_set(CPACR_ELx_ZEN, 0); + cpacr_clear_set(CPACR_EL1_ZEN, 0); } else { __fpsimd_save_state(*host_data_ptr(fpsimd_state)); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 80581b1c3995..59d992455793 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -77,12 +77,12 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM * shift value for trapping the AMU accesses. */ - u64 val = CPACR_ELx_TTA | CPTR_EL2_TAM; + u64 val = CPACR_EL1_TTA | CPTR_EL2_TAM; if (guest_owns_fp_regs()) { - val |= CPACR_ELx_FPEN; + val |= CPACR_EL1_FPEN; if (vcpu_has_sve(vcpu)) - val |= CPACR_ELx_ZEN; + val |= CPACR_EL1_ZEN; } else { __activate_traps_fpsimd32(vcpu); } @@ -122,13 +122,13 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) * hypervisor has traps enabled to dispel any illusion of something more * complicated taking place. */ - if (!(SYS_FIELD_GET(CPACR_ELx, FPEN, cptr) & BIT(0))) - val &= ~CPACR_ELx_FPEN; - if (!(SYS_FIELD_GET(CPACR_ELx, ZEN, cptr) & BIT(0))) - val &= ~CPACR_ELx_ZEN; + if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_FPEN; + if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_ZEN; if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP)) - val |= cptr & CPACR_ELx_E0POE; + val |= cptr & CPACR_EL1_E0POE; val |= cptr & CPTR_EL2_TCPAC; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 83c6b4a07ef5..6efbe3f4a579 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1604,6 +1604,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, if (!cpus_have_final_cap(ARM64_HAS_WFXT)) val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT); break; + case SYS_ID_AA64ISAR3_EL1: + val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_FAMINMAX; + break; case SYS_ID_AA64MMFR2_EL1: val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; break; @@ -2608,7 +2611,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_WRITABLE(ID_AA64ISAR2_EL1, ~(ID_AA64ISAR2_EL1_RES0 | ID_AA64ISAR2_EL1_APA3 | ID_AA64ISAR2_EL1_GPA3)), - ID_UNALLOCATED(6,3), + ID_WRITABLE(ID_AA64ISAR3_EL1, (ID_AA64ISAR3_EL1_FPRCVT | + ID_AA64ISAR3_EL1_FAMINMAX)), ID_UNALLOCATED(6,4), ID_UNALLOCATED(6,5), ID_UNALLOCATED(6,6), diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index b8edc5765441..fb30c8804f87 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -501,7 +501,7 @@ alternative_else_nop_endif #ifdef CONFIG_ARM64_HAFT cmp x9, ID_AA64MMFR1_EL1_HAFDBS_HAFT b.lt 1f - orr tcr2, tcr2, TCR2_EL1x_HAFT + orr tcr2, tcr2, TCR2_EL1_HAFT #endif /* CONFIG_ARM64_HAFT */ 1: #endif /* CONFIG_ARM64_HW_AFDBM */ @@ -532,7 +532,8 @@ alternative_else_nop_endif #undef PTE_MAYBE_NG #undef PTE_MAYBE_SHARED - orr tcr2, tcr2, TCR2_EL1x_PIE + orr tcr2, tcr2, TCR2_EL1_PIE + msr REG_TCR2_EL1, x0 .Lskip_indirection: diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk index d1254a056114..1a2afc9fdd42 100755 --- a/arch/arm64/tools/gen-sysreg.awk +++ b/arch/arm64/tools/gen-sysreg.awk @@ -206,7 +206,7 @@ END { # Currently this is effectivey a comment, in future we may want to emit # defines for the fields. -/^Fields/ && block_current() == "Sysreg" { +(/^Fields/ || /^Mapping/) && block_current() == "Sysreg" { expect_fields(2) if (next_bit != 63) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index b081b54d6d22..94ca9cdb0b16 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -24,8 +24,16 @@ # ... # EndEnum -# Alternatively if multiple registers share the same layout then -# a SysregFields block can be used to describe the shared layout +# For VHE aliases (*_EL12, *_EL02) of system registers, a Mapping +# entry describes the register the alias actually accesses: + +# Sysreg <name_EL12> <op0> <op1> <crn> <crm> <op2> +# Mapping <name_EL1> +# EndSysreg + +# Where multiple system regsiters are not VHE aliases but share a +# common layout, a SysregFields block can be used to describe the +# shared layout: # SysregFields <fieldsname> # <field> @@ -1010,7 +1018,12 @@ UnsignedEnum 35:32 FPMR 0b0000 NI 0b0001 IMP EndEnum -Res0 31:12 +Res0 31:20 +UnsignedEnum 19:16 UINJ + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 15:12 UnsignedEnum 11:8 MTEFAR 0b0000 NI 0b0001 IMP @@ -1035,7 +1048,10 @@ UnsignedEnum 55:52 F32MM 0b0000 NI 0b0001 IMP EndEnum -Res0 51:48 +UnsignedEnum 51:48 F16MM + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 47:44 I8MM 0b0000 NI 0b0001 IMP @@ -1053,6 +1069,7 @@ Res0 31:28 UnsignedEnum 27:24 B16B16 0b0000 NI 0b0001 IMP + 0b0010 BFSCALE EndEnum UnsignedEnum 23:20 BF16 0b0000 NI @@ -1063,16 +1080,22 @@ UnsignedEnum 19:16 BitPerm 0b0000 NI 0b0001 IMP EndEnum -Res0 15:8 +UnsignedEnum 15:12 EltPerm + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 11:8 UnsignedEnum 7:4 AES 0b0000 NI 0b0001 IMP 0b0010 PMULL128 + 0b0011 AES2 EndEnum UnsignedEnum 3:0 SVEver 0b0000 IMP 0b0001 SVE2 0b0010 SVE2p1 + 0b0011 SVE2p2 EndEnum EndSysreg @@ -1090,7 +1113,7 @@ UnsignedEnum 59:56 SMEver 0b0000 SME 0b0001 SME2 0b0010 SME2p1 - 0b0000 IMP + 0b0011 SME2p2 EndEnum UnsignedEnum 55:52 I16I64 0b0000 NI @@ -1154,7 +1177,29 @@ UnsignedEnum 28 SF8DP2 0b0 NI 0b1 IMP EndEnum -Res0 27:0 +Res0 27:26 +UnsignedEnum 25 SBitPerm + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 24 AES + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 23 SFEXPA + 0b0 NI + 0b1 IMP +EndEnum +Res0 22:17 +UnsignedEnum 16 STMOP + 0b0 NI + 0b1 IMP +EndEnum +Res0 15:1 +UnsignedEnum 0 SMOP4 + 0b0 NI + 0b1 IMP +EndEnum EndSysreg Sysreg ID_AA64FPFR0_EL1 3 0 0 4 7 @@ -1175,7 +1220,15 @@ UnsignedEnum 28 F8DP2 0b0 NI 0b1 IMP EndEnum -Res0 27:2 +UnsignedEnum 27 F8MM8 + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 26 F8MM4 + 0b0 NI + 0b1 IMP +EndEnum +Res0 25:2 UnsignedEnum 1 F8E4M3 0b0 NI 0b1 IMP @@ -1503,12 +1556,16 @@ EndEnum UnsignedEnum 55:52 CSSC 0b0000 NI 0b0001 IMP + 0b0010 CMPBR EndEnum UnsignedEnum 51:48 RPRFM 0b0000 NI 0b0001 IMP EndEnum -Res0 47:44 +UnsignedEnum 47:44 PCDPHINT + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 43:40 PRFMSLC 0b0000 NI 0b0001 IMP @@ -1561,7 +1618,23 @@ EndEnum EndSysreg Sysreg ID_AA64ISAR3_EL1 3 0 0 6 3 -Res0 63:16 +Res0 63:32 +UnsignedEnum 31:28 FPRCVT + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 27:24 LSUI + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 23:20 OCCMO + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 19:16 LSFE + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 15:12 PACM 0b0000 NI 0b0001 TRIVIAL_IMP @@ -1978,7 +2051,7 @@ Field 1 A Field 0 M EndSysreg -SysregFields CPACR_ELx +Sysreg CPACR_EL1 3 0 1 0 2 Res0 63:30 Field 29 E0POE Field 28 TTA @@ -1989,10 +2062,6 @@ Field 21:20 FPEN Res0 19:18 Field 17:16 ZEN Res0 15:0 -EndSysregFields - -Sysreg CPACR_EL1 3 0 1 0 2 -Fields CPACR_ELx EndSysreg Sysreg SMPRI_EL1 3 0 1 2 4 @@ -2947,23 +3016,23 @@ Field 63:0 PhysicalOffset EndSysreg Sysreg CPACR_EL12 3 5 1 0 2 -Fields CPACR_ELx +Mapping CPACR_EL1 EndSysreg Sysreg ZCR_EL12 3 5 1 2 0 -Fields ZCR_ELx +Mapping ZCR_EL1 EndSysreg Sysreg SMCR_EL12 3 5 1 2 6 -Fields SMCR_ELx +Mapping SMCR_EL1 EndSysreg Sysreg GCSCR_EL12 3 5 2 5 0 -Fields GCSCR_ELx +Mapping GCSCR_EL1 EndSysreg Sysreg GCSPR_EL12 3 5 2 5 1 -Fields GCSPR_ELx +Mapping GCSPR_EL1 EndSysreg Sysreg FAR_EL12 3 5 6 0 0 @@ -2975,7 +3044,7 @@ Fields MPAM1_ELx EndSysreg Sysreg CONTEXTIDR_EL12 3 5 13 0 1 -Fields CONTEXTIDR_ELx +Mapping CONTEXTIDR_EL1 EndSysreg SysregFields TTBRx_EL1 @@ -2992,7 +3061,7 @@ Sysreg TTBR1_EL1 3 0 2 0 1 Fields TTBRx_EL1 EndSysreg -SysregFields TCR2_EL1x +Sysreg TCR2_EL1 3 0 2 0 3 Res0 63:16 Field 15 DisCH1 Field 14 DisCH0 @@ -3006,14 +3075,10 @@ Field 3 POE Field 2 E0POE Field 1 PIE Field 0 PnCH -EndSysregFields - -Sysreg TCR2_EL1 3 0 2 0 3 -Fields TCR2_EL1x EndSysreg Sysreg TCR2_EL12 3 5 2 0 3 -Fields TCR2_EL1x +Mapping TCR2_EL1 EndSysreg Sysreg TCR2_EL2 3 4 2 0 3 @@ -3084,7 +3149,7 @@ Fields PIRx_ELx EndSysreg Sysreg PIRE0_EL12 3 5 10 2 2 -Fields PIRx_ELx +Mapping PIRE0_EL1 EndSysreg Sysreg PIRE0_EL2 3 4 10 2 2 @@ -3096,7 +3161,7 @@ Fields PIRx_ELx EndSysreg Sysreg PIR_EL12 3 5 10 2 3 -Fields PIRx_ELx +Mapping PIR_EL1 EndSysreg Sysreg PIR_EL2 3 4 10 2 3 @@ -3116,7 +3181,7 @@ Fields PIRx_ELx EndSysreg Sysreg POR_EL12 3 5 10 2 4 -Fields PIRx_ELx +Mapping POR_EL1 EndSysreg Sysreg S2POR_EL1 3 0 10 2 5 diff --git a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c index 488153879ec9..87f162736b2e 100644 --- a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c +++ b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c @@ -6,6 +6,7 @@ #include <linux/arm-smccc.h> #include <linux/cc_platform.h> #include <linux/kernel.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/smp.h> #include <linux/tsm.h> @@ -219,6 +220,13 @@ static void __exit arm_cca_guest_exit(void) } module_exit(arm_cca_guest_exit); +/* modalias, so userspace can autoload this module when RSI is available */ +static const struct platform_device_id arm_cca_match[] __maybe_unused = { + { RSI_PDEV_NAME, 0}, + { } +}; + +MODULE_DEVICE_TABLE(platform, arm_cca_match); MODULE_AUTHOR("Sami Mujawar <sami.mujawar@arm.com>"); MODULE_DESCRIPTION("Arm CCA Guest TSM Driver"); MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 0029ed9c5c9a..35f521e5f41c 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -46,6 +46,12 @@ static void atomics_sigill(void) asm volatile(".inst 0xb82003ff" : : : ); } +static void cmpbr_sigill(void) +{ + /* Not implemented, too complicated and unreliable anyway */ +} + + static void crc32_sigill(void) { /* CRC32W W0, W0, W1 */ @@ -82,6 +88,18 @@ static void f8fma_sigill(void) asm volatile(".inst 0xec0fc00"); } +static void f8mm4_sigill(void) +{ + /* FMMLA V0.4SH, V0.16B, V0.16B */ + asm volatile(".inst 0x6e00ec00"); +} + +static void f8mm8_sigill(void) +{ + /* FMMLA V0.4S, V0.16B, V0.16B */ + asm volatile(".inst 0x6e80ec00"); +} + static void faminmax_sigill(void) { /* FAMIN V0.4H, V0.4H, V0.4H */ @@ -98,6 +116,12 @@ static void fpmr_sigill(void) asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0"); } +static void fprcvt_sigill(void) +{ + /* FCVTAS S0, H0 */ + asm volatile(".inst 0x1efa0000"); +} + static void gcs_sigill(void) { unsigned long *gcspr; @@ -226,6 +250,42 @@ static void sme2p1_sigill(void) asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); } +static void sme2p2_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* UXTB Z0.D, P0/Z, Z0.D */ + asm volatile(".inst 0x4c1a000" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void sme_aes_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* AESD z0.b, z0.b, z0.b */ + asm volatile(".inst 0x4522e400" : : : "z0"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void sme_sbitperm_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* BDEP Z0.B, Z0.B, Z0.B */ + asm volatile(".inst 0x4500b400" : : : "z0"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + static void smei16i32_sigill(void) { /* SMSTART */ @@ -339,8 +399,44 @@ static void smesf8fma_sigill(void) /* SMSTART */ asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); - /* FMLALB V0.8H, V0.16B, V0.16B */ - asm volatile(".inst 0xec0fc00"); + /* FMLALB Z0.8H, Z0.B, Z0.B */ + asm volatile(".inst 0x64205000"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesfexpa_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FEXPA Z0.D, Z0.D */ + asm volatile(".inst 0x04e0b800"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesmop4_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* SMOP4A ZA0.S, Z0.B, { Z0.B - Z1.B } */ + asm volatile(".inst 0x80108000"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smestmop_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* STMOPA ZA0.S, { Z0.H - Z1.H }, Z0.H, Z20[0] */ + asm volatile(".inst 0x80408008"); /* SMSTOP */ asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); @@ -364,18 +460,42 @@ static void sve2p1_sigill(void) asm volatile(".inst 0x65000000" : : : "z0"); } +static void sve2p2_sigill(void) +{ + /* NOT Z0.D, P0/Z, Z0.D */ + asm volatile(".inst 0x4cea000" : : : "z0"); +} + static void sveaes_sigill(void) { /* AESD z0.b, z0.b, z0.b */ asm volatile(".inst 0x4522e400" : : : "z0"); } +static void sveaes2_sigill(void) +{ + /* AESD {Z0.B - Z1.B }, { Z0.B - Z1.B }, Z0.Q */ + asm volatile(".inst 0x4522ec00" : : : "z0"); +} + static void sveb16b16_sigill(void) { /* BFADD Z0.H, Z0.H, Z0.H */ asm volatile(".inst 0x65000000" : : : ); } +static void svebfscale_sigill(void) +{ + /* BFSCALE Z0.H, P0/M, Z0.H, Z0.H */ + asm volatile(".inst 0x65098000" : : : "z0"); +} + +static void svef16mm_sigill(void) +{ + /* FMMLA Z0.S, Z0.H, Z0.H */ + asm volatile(".inst 0x6420e400"); +} + static void svepmull_sigill(void) { /* PMULLB Z0.Q, Z0.D, Z0.D */ @@ -394,6 +514,12 @@ static void svesha3_sigill(void) asm volatile(".inst 0x4203800" : : : "z0"); } +static void sveeltperm_sigill(void) +{ + /* COMPACT Z0.B, P0, Z0.B */ + asm volatile(".inst 0x5218000" : : : "x0"); +} + static void svesm4_sigill(void) { /* SM4E Z0.S, Z0.S, Z0.S */ @@ -470,6 +596,13 @@ static const struct hwcap_data { .sigill_fn = aes_sigill, }, { + .name = "CMPBR", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_CMPBR, + .cpuinfo = "cmpbr", + .sigill_fn = cmpbr_sigill, + }, + { .name = "CRC32", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_CRC32, @@ -524,6 +657,20 @@ static const struct hwcap_data { .sigill_fn = f8fma_sigill, }, { + .name = "F8MM8", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_F8MM8, + .cpuinfo = "f8mm8", + .sigill_fn = f8mm8_sigill, + }, + { + .name = "F8MM4", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_F8MM4, + .cpuinfo = "f8mm4", + .sigill_fn = f8mm4_sigill, + }, + { .name = "FAMINMAX", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_FAMINMAX, @@ -546,6 +693,13 @@ static const struct hwcap_data { .sigill_reliable = true, }, { + .name = "FPRCVT", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_FPRCVT, + .cpuinfo = "fprcvt", + .sigill_fn = fprcvt_sigill, + }, + { .name = "GCS", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_GCS, @@ -692,6 +846,20 @@ static const struct hwcap_data { .sigill_fn = sme2p1_sigill, }, { + .name = "SME 2.2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME2P2, + .cpuinfo = "sme2p2", + .sigill_fn = sme2p2_sigill, + }, + { + .name = "SME AES", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_AES, + .cpuinfo = "smeaes", + .sigill_fn = sme_aes_sigill, + }, + { .name = "SME I16I32", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SME_I16I32, @@ -741,6 +909,13 @@ static const struct hwcap_data { .sigill_fn = smelutv2_sigill, }, { + .name = "SME SBITPERM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SBITPERM, + .cpuinfo = "smesbitperm", + .sigill_fn = sme_sbitperm_sigill, + }, + { .name = "SME SF8FMA", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SME_SF8FMA, @@ -762,6 +937,27 @@ static const struct hwcap_data { .sigill_fn = smesf8dp4_sigill, }, { + .name = "SME SFEXPA", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SFEXPA, + .cpuinfo = "smesfexpa", + .sigill_fn = smesfexpa_sigill, + }, + { + .name = "SME SMOP4", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SMOP4, + .cpuinfo = "smesmop4", + .sigill_fn = smesmop4_sigill, + }, + { + .name = "SME STMOP", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_STMOP, + .cpuinfo = "smestmop", + .sigill_fn = smestmop_sigill, + }, + { .name = "SVE", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_SVE, @@ -784,6 +980,13 @@ static const struct hwcap_data { .sigill_fn = sve2p1_sigill, }, { + .name = "SVE 2.2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE2P2, + .cpuinfo = "sve2p2", + .sigill_fn = sve2p2_sigill, + }, + { .name = "SVE AES", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SVEAES, @@ -791,6 +994,34 @@ static const struct hwcap_data { .sigill_fn = sveaes_sigill, }, { + .name = "SVE AES2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_AES2, + .cpuinfo = "sveaes2", + .sigill_fn = sveaes2_sigill, + }, + { + .name = "SVE BFSCALE", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_BFSCALE, + .cpuinfo = "svebfscale", + .sigill_fn = svebfscale_sigill, + }, + { + .name = "SVE ELTPERM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_ELTPERM, + .cpuinfo = "sveeltperm", + .sigill_fn = sveeltperm_sigill, + }, + { + .name = "SVE F16MM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_F16MM, + .cpuinfo = "svef16mm", + .sigill_fn = svef16mm_sigill, + }, + { .name = "SVE2 B16B16", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SVE_B16B16, |