The base floating point, SVE and SME all have enable controls for EL0 and EL1 in CPACR_EL1 which have a similar layout and function. Currently the basic floating point enable FPEN is defined differently to the SVE control, specified as a single define in kvm_arm.h rather than in sysreg.h. Move the define to sysreg.h and provide separate EL0 and EL1 control bits so code managing the different floating point enables can look consistent.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_arm.h | 1 - arch/arm64/include/asm/sysreg.h | 4 ++++ 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 01d47c5886dc..eec790842fe2 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -355,7 +355,6 @@ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)

-#define CPACR_EL1_FPEN (3 << 20) #define CPACR_EL1_TTA (1 << 28) #define CPACR_EL1_DEFAULT (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 898bee0004ae..1da4c43d597d 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -1097,6 +1097,10 @@ #define ZCR_ELx_LEN_SIZE 9 #define ZCR_ELx_LEN_MASK 0x1ff

+#define CPACR_EL1_FPEN_EL1EN (BIT(20)) /* enable EL1 access */ +#define CPACR_EL1_FPEN_EL0EN (BIT(21)) /* enable EL0 access, if EL1EN set */ +#define CPACR_EL1_FPEN (CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN) + #define CPACR_EL1_ZEN_EL1EN (BIT(16)) /* enable EL1 access */ #define CPACR_EL1_ZEN_EL0EN (BIT(17)) /* enable EL0 access, if EL1EN set */ #define CPACR_EL1_ZEN (CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)

CPACR_EL1 has several bitfields for controlling traps for floating point features to EL1, each of which has a separate bits for EL0 and EL1. Marc Zyngier noted that we are not consistent in our use of defines to manipulate these, sometimes using a define covering the whole field and sometimes using defines for the individual bits. Make this consistent by expanding the whole field defines where they are used (currently only in the KVM code) and deleting them so that no further uses can be introduced.

Suggested-by: Marc Zyngier maz@kernel.org Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_arm.h | 3 ++- arch/arm64/include/asm/sysreg.h | 2 -- arch/arm64/kvm/hyp/include/hyp/switch.h | 4 ++-- arch/arm64/kvm/hyp/vhe/switch.c | 6 +++--- 4 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index eec790842fe2..1767ded83888 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -356,6 +356,7 @@ ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)

#define CPACR_EL1_TTA (1 << 28) -#define CPACR_EL1_DEFAULT (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN) +#define CPACR_EL1_DEFAULT (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |\ + CPACR_EL1_ZEN_EL1EN)

#endif /* __ARM64_KVM_ARM_H__ */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 1da4c43d597d..e66dd9ebc337 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -1099,11 +1099,9 @@

#define CPACR_EL1_FPEN_EL1EN (BIT(20)) /* enable EL1 access */ #define CPACR_EL1_FPEN_EL0EN (BIT(21)) /* enable EL0 access, if EL1EN set */ -#define CPACR_EL1_FPEN (CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN)

#define CPACR_EL1_ZEN_EL1EN (BIT(16)) /* enable EL1 access */ #define CPACR_EL1_ZEN_EL0EN (BIT(17)) /* enable EL0 access, if EL1EN set */ -#define CPACR_EL1_ZEN (CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)

/* TCR EL1 Bit Definitions */ #define SYS_TCR_EL1_TCMA1 (BIT(58)) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 701cfb964905..6379a1e3e6e5 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -174,9 +174,9 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)

/* Valid trap. Switch the context: */ if (has_vhe()) { - reg = CPACR_EL1_FPEN; + reg = CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN; if (sve_guest) - reg |= CPACR_EL1_ZEN; + reg |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;

sysreg_clear_set(cpacr_el1, 0, reg); } else { diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 11d053fdd604..619353b06e38 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -38,7 +38,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)

val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; - val &= ~CPACR_EL1_ZEN; + val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);

/* * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to @@ -53,9 +53,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)

if (update_fp_enabled(vcpu)) { if (vcpu_has_sve(vcpu)) - val |= CPACR_EL1_ZEN; + val |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN; } else { - val &= ~CPACR_EL1_FPEN; + val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN); __activate_traps_fpsimd32(vcpu); }

Since all the fields in the main ID registers are 4 bits wide we have up until now not bothered specifying the width in the code. Since we now wish to use this mechanism to enumerate features from the floating point feature registers which do not follow this pattern add a width to the table. This means updating all the existing table entries but makes it less likely that we run into issues in future due to implicitly assuming a 4 bit width.

Signed-off-by: Mark Brown broonie@kernel.org Cc: Suzuki K Poulose suzuki.poulose@arm.com --- arch/arm64/include/asm/cpufeature.h | 1 + arch/arm64/kernel/cpufeature.c | 167 +++++++++++++++++----------- 2 files changed, 102 insertions(+), 66 deletions(-)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index ef6be92b1921..2728abd9cae4 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -356,6 +356,7 @@ struct arm64_cpu_capabilities { struct { /* Feature register checking */ u32 sys_reg; u8 field_pos; + u8 field_width; u8 min_field_value; u8 hwcap_type; bool sign; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index e5f23dab1c8d..64a748c2b351 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1307,7 +1307,9 @@ u64 __read_sysreg_by_encoding(u32 sys_id) static bool feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) { - int val = cpuid_feature_extract_field(reg, entry->field_pos, entry->sign); + int val = cpuid_feature_extract_field_width(reg, entry->field_pos, + entry->field_width, + entry->sign);

return val >= entry->min_field_value; } @@ -1955,6 +1957,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR0_EL1, .field_pos = ID_AA64MMFR0_ECV_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, }, @@ -1966,6 +1969,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR1_EL1, .field_pos = ID_AA64MMFR1_PAN_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, .cpu_enable = cpu_enable_pan, @@ -1979,6 +1983,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR1_EL1, .field_pos = ID_AA64MMFR1_PAN_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 3, }, @@ -1991,6 +1996,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, .field_pos = ID_AA64ISAR0_ATOMICS_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 2, }, @@ -2015,6 +2021,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64PFR0_EL0_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT, }, #ifdef CONFIG_KVM @@ -2026,6 +2033,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64PFR0_EL1_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT, }, { @@ -2046,6 +2054,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { */ .sys_reg = SYS_ID_AA64PFR0_EL1, .field_pos = ID_AA64PFR0_CSV3_SHIFT, + .field_width = 4, .min_field_value = 1, .matches = unmap_kernel_at_el0, .cpu_enable = kpti_install_ng_mappings, @@ -2065,6 +2074,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR1_EL1, .field_pos = ID_AA64ISAR1_DPB_SHIFT, + .field_width = 4, .min_field_value = 1, }, { @@ -2075,6 +2085,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_DPB_SHIFT, + .field_width = 4, .min_field_value = 2, }, #endif @@ -2086,6 +2097,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64PFR0_SVE_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR0_SVE, .matches = has_cpuid_feature, .cpu_enable = sve_kernel_enable, @@ -2100,6 +2112,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64PFR0_RAS_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR0_RAS_V1, .cpu_enable = cpu_clear_disr, }, @@ -2118,6 +2131,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64PFR0_AMU_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR0_AMU, .cpu_enable = cpu_amu_enable, }, @@ -2142,6 +2156,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64MMFR2_FWB_SHIFT, + .field_width = 4, .min_field_value = 1, .matches = has_cpuid_feature, .cpu_enable = cpu_has_fwb, @@ -2153,6 +2168,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64MMFR2_TTL_SHIFT, + .field_width = 4, .min_field_value = 1, .matches = has_cpuid_feature, }, @@ -2163,6 +2179,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, .field_pos = ID_AA64ISAR0_TLB_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = ID_AA64ISAR0_TLB_RANGE, }, @@ -2181,6 +2198,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64MMFR1_HADBS_SHIFT, + .field_width = 4, .min_field_value = 2, .matches = has_hw_dbm, .cpu_enable = cpu_enable_hw_dbm, @@ -2193,6 +2211,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, .field_pos = ID_AA64ISAR0_CRC32_SHIFT, + .field_width = 4, .min_field_value = 1, }, { @@ -2202,6 +2221,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR1_EL1, .field_pos = ID_AA64PFR1_SSBS_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY, }, @@ -2214,6 +2234,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64MMFR2_CNP_SHIFT, + .field_width = 4, .min_field_value = 1, .cpu_enable = cpu_enable_cnp, }, @@ -2225,6 +2246,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR1_EL1, .field_pos = ID_AA64ISAR1_SB_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, }, @@ -2236,6 +2258,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_APA_SHIFT, + .field_width = 4, .min_field_value = ID_AA64ISAR1_APA_ARCHITECTED, .matches = has_address_auth_cpucap, }, @@ -2246,6 +2269,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_API_SHIFT, + .field_width = 4, .min_field_value = ID_AA64ISAR1_API_IMP_DEF, .matches = has_address_auth_cpucap, }, @@ -2261,6 +2285,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_GPA_SHIFT, + .field_width = 4, .min_field_value = ID_AA64ISAR1_GPA_ARCHITECTED, .matches = has_cpuid_feature, }, @@ -2271,6 +2296,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_GPI_SHIFT, + .field_width = 4, .min_field_value = ID_AA64ISAR1_GPI_IMP_DEF, .matches = has_cpuid_feature, }, @@ -2291,6 +2317,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = can_use_gic_priorities, .sys_reg = SYS_ID_AA64PFR0_EL1, .field_pos = ID_AA64PFR0_GIC_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, }, @@ -2302,6 +2329,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, + .field_width = 4, .field_pos = ID_AA64MMFR2_E0PD_SHIFT, .matches = has_cpuid_feature, .min_field_value = 1, @@ -2316,6 +2344,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, .field_pos = ID_AA64ISAR0_RNDR_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, }, @@ -2333,6 +2362,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = bti_enable, .sys_reg = SYS_ID_AA64PFR1_EL1, .field_pos = ID_AA64PFR1_BT_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR1_BT_BTI, .sign = FTR_UNSIGNED, }, @@ -2345,6 +2375,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR1_EL1, .field_pos = ID_AA64PFR1_MTE_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR1_MTE, .sign = FTR_UNSIGNED, .cpu_enable = cpu_enable_mte, @@ -2356,6 +2387,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR1_EL1, .field_pos = ID_AA64PFR1_MTE_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR1_MTE_ASYMM, .sign = FTR_UNSIGNED, }, @@ -2367,16 +2399,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_LRCPC_SHIFT, + .field_width = 4, .matches = has_cpuid_feature, .min_field_value = 1, }, {}, };

-#define HWCAP_CPUID_MATCH(reg, field, s, min_value) \ +#define HWCAP_CPUID_MATCH(reg, field, width, s, min_value) \ .matches = has_cpuid_feature, \ .sys_reg = reg, \ .field_pos = field, \ + .field_width = width, \ .sign = s, \ .min_field_value = min_value,

@@ -2386,10 +2420,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .hwcap_type = cap_type, \ .hwcap = cap, \

-#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap) \ +#define HWCAP_CAP(reg, field, width, s, min_value, cap_type, cap) \ { \ __HWCAP_CAP(#cap, cap_type, cap) \ - HWCAP_CPUID_MATCH(reg, field, s, min_value) \ + HWCAP_CPUID_MATCH(reg, field, width, s, min_value) \ }

#define HWCAP_MULTI_CAP(list, cap_type, cap) \ @@ -2409,11 +2443,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_APA_SHIFT, - FTR_UNSIGNED, ID_AA64ISAR1_APA_ARCHITECTED) + 4, FTR_UNSIGNED, + ID_AA64ISAR1_APA_ARCHITECTED) }, { HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_API_SHIFT, - FTR_UNSIGNED, ID_AA64ISAR1_API_IMP_DEF) + 4, FTR_UNSIGNED, ID_AA64ISAR1_API_IMP_DEF) }, {}, }; @@ -2421,77 +2456,77 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { { HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_GPA_SHIFT, - FTR_UNSIGNED, ID_AA64ISAR1_GPA_ARCHITECTED) + 4, FTR_UNSIGNED, ID_AA64ISAR1_GPA_ARCHITECTED) }, { HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_GPI_SHIFT, - FTR_UNSIGNED, ID_AA64ISAR1_GPI_IMP_DEF) + 4, FTR_UNSIGNED, ID_AA64ISAR1_GPI_IMP_DEF) }, {}, }; #endif

static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RNDR_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_BF16_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DGH_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_I8MM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM), - HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_BF16_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DGH_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_I8MM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM), + HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SVEVER_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SVEVER_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BF16_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BF16, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_I8MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_I8MM, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F32MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F32MM, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), - HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SVEVER_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_SVEVER_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BF16_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_BF16, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_I8MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_I8MM, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F32MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_F32MM, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), #ifdef CONFIG_ARM64_BTI - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_BT_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_BT_BTI, CAP_HWCAP, KERNEL_HWCAP_BTI), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_BT_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_BT_BTI, CAP_HWCAP, KERNEL_HWCAP_BTI), #endif #ifdef CONFIG_ARM64_PTR_AUTH HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA), HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG), #endif #ifdef CONFIG_ARM64_MTE - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_MTE, CAP_HWCAP, KERNEL_HWCAP_MTE), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_MTE, CAP_HWCAP, KERNEL_HWCAP_MTE), #endif /* CONFIG_ARM64_MTE */ - HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), - HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), - HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES), + HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), + HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), + HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES), {}, };

@@ -2520,15 +2555,15 @@ static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope) static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = { #ifdef CONFIG_COMPAT HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON), - HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4), + HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4), /* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */ - HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP), - HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3), - HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), - HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), - HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1), - HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2), - HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32), + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP), + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32), #endif {}, };

Some features may invalidate some tests, for example by supporting an operation which would trap otherwise. Allow tests to list features that they are incompatible with so we can cover the case where a signal will be generated without disruption on systems where that won't happen.

Signed-off-by: Mark Brown broonie@kernel.org --- .../selftests/arm64/signal/test_signals.h | 1 + .../arm64/signal/test_signals_utils.c | 34 ++++++++++++++----- .../arm64/signal/test_signals_utils.h | 2 ++ 3 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index ebe8694dbef0..f909b70d9e98 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -53,6 +53,7 @@ struct tdescr { char *name; char *descr; unsigned long feats_required; + unsigned long feats_incompatible; /* bitmask of effectively supported feats: populated at run-time */ unsigned long feats_supported; bool initialized; diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 2f8c23af3b5e..5743897984b0 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -36,6 +36,8 @@ static inline char *feats_to_string(unsigned long feats) { size_t flen = MAX_FEATS_SZ - 1;

+ feats_string[0] = '\0'; + for (int i = 0; i < FMAX_END; i++) { if (feats & (1UL << i)) { size_t tlen = strlen(feats_names[i]); @@ -256,7 +258,7 @@ int test_init(struct tdescr *td) td->minsigstksz = MINSIGSTKSZ; fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz);

- if (td->feats_required) { + if (td->feats_required || td->feats_incompatible) { td->feats_supported = 0; /* * Checking for CPU required features using both the @@ -267,15 +269,29 @@ int test_init(struct tdescr *td) if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; if (feats_ok(td)) { - fprintf(stderr, - "Required Features: [%s] supported\n", - feats_to_string(td->feats_required & - td->feats_supported)); + if (td->feats_required & td->feats_supported) + fprintf(stderr, + "Required Features: [%s] supported\n", + feats_to_string(td->feats_required & + td->feats_supported)); + if (!(td->feats_incompatible & td->feats_supported)) + fprintf(stderr, + "Incompatible Features: [%s] absent\n", + feats_to_string(td->feats_incompatible)); } else { - fprintf(stderr, - "Required Features: [%s] NOT supported\n", - feats_to_string(td->feats_required & - ~td->feats_supported)); + if ((td->feats_required & td->feats_supported) != + td->feats_supported) + fprintf(stderr, + "Required Features: [%s] NOT supported\n", + feats_to_string(td->feats_required & + ~td->feats_supported)); + if (td->feats_incompatible & td->feats_supported) + fprintf(stderr, + "Incompatible Features: [%s] supported\n", + feats_to_string(td->feats_incompatible & + ~td->feats_supported)); + + td->result = KSFT_SKIP; return 0; } diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h index 6772b5c8d274..f3aa99ba67bb 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.h +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h @@ -18,6 +18,8 @@ void test_result(struct tdescr *td);

static inline bool feats_ok(struct tdescr *td) { + if (td->feats_incompatible & td->feats_supported) + return false; return (td->feats_required & td->feats_supported) == td->feats_required; }

Provide ABI documentation for SME similar to that for SVE. Due to the very large overlap around streaming SVE mode in both implementation and interfaces documentation for streaming mode SVE is added to the SVE document rather than the SME one.

Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/arm64/index.rst | 1 + Documentation/arm64/sme.rst | 432 ++++++++++++++++++++++++++++++++++ Documentation/arm64/sve.rst | 70 +++++- 3 files changed, 493 insertions(+), 10 deletions(-) create mode 100644 Documentation/arm64/sme.rst

diff --git a/Documentation/arm64/index.rst b/Documentation/arm64/index.rst index 4f840bac083e..ae21f8118830 100644 --- a/Documentation/arm64/index.rst +++ b/Documentation/arm64/index.rst @@ -21,6 +21,7 @@ ARM64 Architecture perf pointer-authentication silicon-errata + sme sve tagged-address-abi tagged-pointers diff --git a/Documentation/arm64/sme.rst b/Documentation/arm64/sme.rst new file mode 100644 index 000000000000..15df3157c592 --- /dev/null +++ b/Documentation/arm64/sme.rst @@ -0,0 +1,432 @@ +=================================================== +Scalable Matrix Extension support for AArch64 Linux +=================================================== + +This document outlines briefly the interface provided to userspace by Linux in +order to support use of the ARM Scalable Matrix Extension (SME). + +This is an outline of the most important features and issues only and not +intended to be exhaustive. It should be read in conjunction with the SVE +documentation in sve.rst which provides details on the Streaming SVE mode +included in SME. + +This document does not aim to describe the SME architecture or programmer's +model. To aid understanding, a minimal description of relevant programmer's +model features for SME is included in Appendix A. + + +1. General +----------- + +* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA + register state and TPIDR2_EL0 are tracked per thread. + +* The presence of SME is reported to userspace via HWCAP2_SME in the aux vector + AT_HWCAP2 entry. Presence of this flag implies the presence of the SME + instructions and registers, and the Linux-specific system interfaces + described in this document. SME is reported in /proc/cpuinfo as "sme". + +* Support for the execution of SME instructions in userspace can also be + detected by reading the CPU ID register ID_AA64PFR1_EL1 using an MRS + instruction, and checking that the value of the SME field is nonzero. [3] + + It does not guarantee the presence of the system interfaces described in the + following sections: software that needs to verify that those interfaces are + present must check for HWCAP2_SME instead. + +* There are a number of optional SME features, presence of these is reported + through AT_HWCAP2 through: + + HWCAP2_SME_I16I64 + HWCAP2_SME_F64F64 + HWCAP2_SME_I8I32 + HWCAP2_SME_F16F32 + HWCAP2_SME_B16F32 + HWCAP2_SME_F32F32 + HWCAP2_SME_FA64 + + This list may be extended over time as the SME architecture evolves. + + These extensions are also reported via the CPU ID register ID_AA64SMFR0_EL1, + which userspace can read using an MRS instruction. See elf_hwcaps.txt and + cpu-feature-registers.txt for details. + +* Debuggers should restrict themselves to interacting with the target via the + NT_ARM_SVE, NT_ARM_SSVE and NT_ARM_ZA regsets. The recommended way + of detecting support for these regsets is to connect to a target process + first and then attempt a + + ptrace(PTRACE_GETREGSET, pid, NT_ARM_<regset>, &iov). + +* Whenever ZA register values are exchanged in memory between userspace and + the kernel, the register value is encoded in memory as a series of horizontal + vectors from 0 to VL/8-1 stored in the same endianness invariant format as is + used for SVE vectors. + +* On thread creation TPIDR2_EL0 is preserved unless CLONE_SETTLS is specified, + in which case it is set to 0. + +2. Vector lengths +------------------ + +SME defines a second vector length similar to the SVE vector length which is +controls the size of the streaming mode SVE vectors and the ZA matrix array. +The ZA matrix is square with each side having as many bytes as a SVE vector. + + +3. Sharing of streaming and non-streaming mode SVE state +--------------------------------------------------------- + +It is implementation defined which if any parts of the SVE state are shared +between streaming and non-streaming modes. When switching between modes +via software interfaces such as ptrace if no register content is provided as +part of switching no state will be assumed to be shared and everything will +be zeroed. + + +4. System call behaviour +------------------------- + +* On syscall PSTATE.ZA is preserved, if PSTATE.ZA==1 then the contents of the + ZA matrix are preserved. + +* On syscall PSTATE.SM will be cleared and the SVE registers will be handled + as normal. + +* Neither the SVE registers nor ZA are used to pass arguments to or receive + results from any syscall. + +* On creation fork() or clone() the newly created process will have PSTATE.SM + and PSTATE.ZA cleared. + +* All other SME state of a thread, including the currently configured vector + length, the state of the PR_SME_VL_INHERIT flag, and the deferred vector + length (if any), is preserved across all syscalls, subject to the specific + exceptions for execve() described in section 6. + + +5. Signal handling +------------------- + +* Signal handlers are invoked with streaming mode and ZA disabled. + +* A new signal frame record za_context encodes the ZA register contents on + signal delivery. [1] + +* The signal frame record for ZA always contains basic metadata, in particular + the thread's vector length (in za_context.vl). + +* The ZA matrix may or may not be included in the record, depending on + the value of PSTATE.ZA. The registers are present if and only if: + za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + in which case PSTATE.ZA == 1. + +* If matrix data is present, the remainder of the record has a vl-dependent + size and layout. Macros ZA_SIG_* are defined [1] to facilitate access to + them. + +* The matrix is stored as a series of horizontal vectors in the same format as + is used for SVE vectors. + +* If the ZA context is too big to fit in sigcontext.__reserved[], then extra + space is allocated on the stack, an extra_context record is written in + __reserved[] referencing this space. za_context is then written in the + extra space. Refer to [1] for further details about this mechanism. + + +5. Signal return +----------------- + +When returning from a signal handler: + +* If there is no za_context record in the signal frame, or if the record is + present but contains no register data as desribed in the previous section, + then ZA is disabled. + +* If za_context is present in the signal frame and contains matrix data then + PSTATE.ZA is set to 1 and ZA is populated with the specified data. + +* The vector length cannot be changed via signal return. If za_context.vl in + the signal frame does not match the current vector length, the signal return + attempt is treated as illegal, resulting in a forced SIGSEGV. + + +6. prctl extensions +-------------------- + +Some new prctl() calls are added to allow programs to manage the SME vector +length: + +prctl(PR_SME_SET_VL, unsigned long arg) + + Sets the vector length of the calling thread and related flags, where + arg == vl | flags. Other threads of the calling process are unaffected. + + vl is the desired vector length, where sve_vl_valid(vl) must be true. + + flags: + + PR_SME_VL_INHERIT + + Inherit the current vector length across execve(). Otherwise, the + vector length is reset to the system default at execve(). (See + Section 9.) + + PR_SME_SET_VL_ONEXEC + + Defer the requested vector length change until the next execve() + performed by this thread. + + The effect is equivalent to implicit exceution of the following + call immediately after the next execve() (if any) by the thread: + + prctl(PR_SME_SET_VL, arg & ~PR_SME_SET_VL_ONEXEC) + + This allows launching of a new program with a different vector + length, while avoiding runtime side effects in the caller. + + Without PR_SME_SET_VL_ONEXEC, the requested change takes effect + immediately. + + + Return value: a nonnegative on success, or a negative value on error: + EINVAL: SME not supported, invalid vector length requested, or + invalid flags. + + + On success: + + * Either the calling thread's vector length or the deferred vector length + to be applied at the next execve() by the thread (dependent on whether + PR_SME_SET_VL_ONEXEC is present in arg), is set to the largest value + supported by the system that is less than or equal to vl. If vl == + SVE_VL_MAX, the value set will be the largest value supported by the + system. + + * Any previously outstanding deferred vector length change in the calling + thread is cancelled. + + * The returned value describes the resulting configuration, encoded as for + PR_SME_GET_VL. The vector length reported in this value is the new + current vector length for this thread if PR_SME_SET_VL_ONEXEC was not + present in arg; otherwise, the reported vector length is the deferred + vector length that will be applied at the next execve() by the calling + thread. + + * Changing the vector length causes all of ZA, P0..P15, FFR and all bits of + Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become + unspecified, including both streaming and non-streaming SVE state. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + +prctl(PR_SME_GET_VL) + + Gets the vector length of the calling thread. + + The following flag may be OR-ed into the result: + + PR_SME_VL_INHERIT + + Vector length will be inherited across execve(). + + There is no way to determine whether there is an outstanding deferred + vector length change (which would only normally be the case between a + fork() or vfork() and the corresponding execve() in typical use). + + To extract the vector length from the result, bitwise and it with + PR_SME_VL_LEN_MASK. + + Return value: a nonnegative value on success, or a negative value on error: + EINVAL: SME not supported. + + +7. ptrace extensions +--------------------- + +* A new regset NT_ARM_SSVE is defined for access to streaming mode SVE + state via PTRACE_GETREGSET and PTRACE_SETREGSET, this is documented in + sve.rst. + +* A new regset NT_ARM_ZA is defined for ZA state for access to ZA state via + PTRACE_GETREGSET and PTRACE_SETREGSET. + + Refer to [2] for definitions. + +The regset data starts with struct user_za_header, containing: + + size + + Size of the complete regset, in bytes. + This depends on vl and possibly on other things in the future. + + If a call to PTRACE_GETREGSET requests less data than the value of + size, the caller can allocate a larger buffer and retry in order to + read the complete regset. + + max_size + + Maximum size in bytes that the regset can grow to for the target + thread. The regset won't grow bigger than this even if the target + thread changes its vector length etc. + + vl + + Target thread's current streaming vector length, in bytes. + + max_vl + + Maximum possible streaming vector length for the target thread. + + flags + + Zero or more of the following flags, which have the same + meaning and behaviour as the corresponding PR_SET_VL_* flags: + + SME_PT_VL_INHERIT + + SME_PT_VL_ONEXEC (SETREGSET only). + +* The effects of changing the vector length and/or flags are equivalent to + those documented for PR_SME_SET_VL. + + The caller must make a further GETREGSET call if it needs to know what VL is + actually set by SETREGSET, unless is it known in advance that the requested + VL is supported. + +* The size and layout of the payload depends on the header fields. The + SME_PT_ZA_*() macros are provided to facilitate access to the data. + +* In either case, for SETREGSET it is permissible to omit the payload, in which + case the vector length and flags are changed and PSTATE.ZA is set to 0 + (along with any consequences of those changes). If a payload is provided + then PSTATE.ZA will be set to 1. + +* For SETREGSET, if the requested VL is not supported, the effect will be the + same as if the payload were omitted, except that an EIO error is reported. + No attempt is made to translate the payload data to the correct layout + for the vector length actually set. It is up to the caller to translate the + payload layout for the actual VL and retry. + +* The effect of writing a partial, incomplete payload is unspecified. + + +8. ELF coredump extensions +--------------------------- + +* NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated. + +* A NT_ARM_ZA note will be added to each coredump for each thread of the + dumped process. The contents will be equivalent to the data that would have + been read if a PTRACE_GETREGSET of NT_ARM_ZA were executed for each thread + when the coredump was generated. + + +9. System runtime configuration +-------------------------------- + +* To mitigate the ABI impact of expansion of the signal frame, a policy + mechanism is provided for administrators, distro maintainers and developers + to set the default vector length for userspace processes: + +/proc/sys/abi/sme_default_vector_length + + Writing the text representation of an integer to this file sets the system + default vector length to the specified value, unless the value is greater + than the maximum vector length supported by the system in which case the + default vector length is set to that maximum. + + The result can be determined by reopening the file and reading its + contents. + + At boot, the default vector length is initially set to 32 or the maximum + supported vector length, whichever is smaller and supported. This + determines the initial vector length of the init process (PID 1). + + Reading this file returns the current system default vector length. + +* At every execve() call, the new vector length of the new process is set to + the system default vector length, unless + + * PR_SME_VL_INHERIT (or equivalently SME_PT_VL_INHERIT) is set for the + calling thread, or + + * a deferred vector length change is pending, established via the + PR_SME_SET_VL_ONEXEC flag (or SME_PT_VL_ONEXEC). + +* Modifying the system default vector length does not affect the vector length + of any existing process or thread that does not make an execve() call. + + +Appendix A. SME programmer's model (informative) +================================================= + +This section provides a minimal description of the additions made by SVE to the +ARMv8-A programmer's model that are relevant to this document. + +Note: This section is for information only and not intended to be complete or +to replace any architectural specification. + +A.1. Registers +--------------- + +In A64 state, SME adds the following: + +* A new mode, streaming mode, in which a subset of the normal FPSIMD and SVE + features are available. When supported EL0 software may enter and leave + streaming mode at any time. + + For best system performance it is strongly encouraged for software to enable + streaming mode only when it is actively being used. + +* A new vector length controlling the size of ZA and the Z registers when in + streaming mode, separately to the vector length used for SVE when not in + streaming mode. There is no requirement that either the currently selected + vector length or the set of vector lengths supported for the two modes in + a given system have any relationship. The streaming mode vector length + is referred to as SVL. + +* A new ZA matrix register. This is a square matrix of SVLxSVL bits. Most + operations on ZA require that streaming mode be enabled but ZA can be + enabled without streaming mode in order to load, save and retain data. + + For best system performance it is strongly encouraged for software to enable + ZA only when it is actively being used. + +* Two new 1 bit fields in PSTATE which may be controlled via the SMSTART and + SMSTOP instructions or by access to the SVCR system register: + + * PSTATE.ZA, if this is 1 then the ZA matrix is accessible and has valid + data while if it is 0 then ZA can not be accessed. When PSTATE.ZA is + changed from 0 to 1 all bits in ZA are cleared. + + * PSTATE.SM, if this is 1 then the PE is in streaming mode. When the value + of PSTATE.SM is changed then it is implementation defined if the subset + of the floating point register bits valid in both modes may be retained. + Any other bits will be cleared. + + +References +========== + +[1] arch/arm64/include/uapi/asm/sigcontext.h + AArch64 Linux signal ABI definitions + +[2] arch/arm64/include/uapi/asm/ptrace.h + AArch64 Linux ptrace ABI definitions + +[3] Documentation/arm64/cpu-feature-registers.rst + +[4] ARM IHI0055C + http://infocenter.arm.com/help/topic/com.arm.doc.ihi0055c/IHI0055C_beta_aapc... + http://infocenter.arm.com/help/topic/com.arm.doc.subset.swdev.abi/index.html + Procedure Call Standard for the ARM 64-bit Architecture (AArch64) diff --git a/Documentation/arm64/sve.rst b/Documentation/arm64/sve.rst index 9d9a4de5bc34..93c2c2990584 100644 --- a/Documentation/arm64/sve.rst +++ b/Documentation/arm64/sve.rst @@ -7,7 +7,9 @@ Author: Dave Martin Dave.Martin@arm.com Date: 4 August 2017

This document outlines briefly the interface provided to userspace by Linux in -order to support use of the ARM Scalable Vector Extension (SVE). +order to support use of the ARM Scalable Vector Extension (SVE), including +interactions with Streaming SVE mode added by the Scalable Matrix Extension +(SME).

This is an outline of the most important features and issues only and not intended to be exhaustive. @@ -23,6 +25,10 @@ model features for SVE is included in Appendix A. * SVE registers Z0..Z31, P0..P15 and FFR and the current vector length VL, are tracked per-thread.

+* In streaming mode FFR is not accessible unless HWCAP2_SME_FA64 is present + in the system, when it is not supported and these interfaces are used to + access streaming mode FFR is read and written as zero. + * The presence of SVE is reported to userspace via HWCAP_SVE in the aux vector AT_HWCAP entry. Presence of this flag implies the presence of the SVE instructions and registers, and the Linux-specific system interfaces @@ -53,10 +59,19 @@ model features for SVE is included in Appendix A. which userspace can read using an MRS instruction. See elf_hwcaps.txt and cpu-feature-registers.txt for details.

+* On hardware that supports the SME extensions, HWCAP2_SME will also be + reported in the AT_HWCAP2 aux vector entry. Among other things SME adds + streaming mode which provides a subset of the SVE feature set using a + separate SME vector length and the same Z/V registers. See sme.rst + for more details. + * Debuggers should restrict themselves to interacting with the target via the NT_ARM_SVE regset. The recommended way of detecting support for this regset is to connect to a target process first and then attempt a - ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). + ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). Note that when SME is + present and streaming SVE mode is in use the FPSIMD subset of registers + will be read via NT_ARM_SVE and NT_ARM_SVE writes will exit streaming mode + in the target.

* Whenever SVE scalable register values (Zn, Pn, FFR) are exchanged in memory between userspace and the kernel, the register value is encoded in memory in @@ -126,6 +141,11 @@ the SVE instruction set architecture. are only present in fpsimd_context. For convenience, the content of V0..V31 is duplicated between sve_context and fpsimd_context.

+* The record contains a flag field which includes a flag SVE_SIG_FLAG_SM which + if set indicates that the thread is in streaming mode and the vector length + and register data (if present) describe the streaming SVE data and vector + length. + * The signal frame record for SVE always contains basic metadata, in particular the thread's vector length (in sve_context.vl).

@@ -170,6 +190,11 @@ When returning from a signal handler: the signal frame does not match the current vector length, the signal return attempt is treated as illegal, resulting in a forced SIGSEGV.

+* It is permitted to enter or leave streaming mode by setting or clearing + the SVE_SIG_FLAG_SM flag but applications should take care to ensure that + when doing so sve_context.vl and any register data are appropriate for the + vector length in the new mode. +

6. prctl extensions -------------------- @@ -265,8 +290,14 @@ prctl(PR_SVE_GET_VL) 7. ptrace extensions ---------------------

-* A new regset NT_ARM_SVE is defined for use with PTRACE_GETREGSET and - PTRACE_SETREGSET. +* New regsets NT_ARM_SVE and NT_ARM_SSVE are defined for use with + PTRACE_GETREGSET and PTRACE_SETREGSET. NT_ARM_SSVE describes the + streaming mode SVE registers and NT_ARM_SVE describes the + non-streaming mode SVE registers. + + In this description a register set is referred to as being "live" when + the target is in the appropriate streaming or non-streaming mode and is + using data beyond the subset shared with the FPSIMD Vn registers.

Refer to [2] for definitions.

@@ -297,7 +328,7 @@ The regset data starts with struct user_sve_header, containing:

flags

- either + at most one of

SVE_PT_REGS_FPSIMD

@@ -331,6 +362,10 @@ The regset data starts with struct user_sve_header, containing:

SVE_PT_VL_ONEXEC (SETREGSET only).

+ If neither FPSIMD nor SVE flags are provided then no register + payload is available, this is only possible when SME is implemented. + + * The effects of changing the vector length and/or flags are equivalent to those documented for PR_SVE_SET_VL.

@@ -346,6 +381,13 @@ The regset data starts with struct user_sve_header, containing: case only the vector length and flags are changed (along with any consequences of those changes).

+* In systems supporting SME when in streaming mode a GETREGSET for + NT_REG_SVE will return only the user_sve_header with no register data, + similarly a GETREGSET for NT_REG_SSVE will not return any register data + when not in streaming mode. + +* A GETREGSET for NT_ARM_SSVE will never return SVE_PT_REGS_FPSIMD. + * For SETREGSET, if an SVE_PT_REGS_SVE payload is present and the requested VL is not supported, the effect will be the same as if the payload were omitted, except that an EIO error is reported. No @@ -355,17 +397,25 @@ The regset data starts with struct user_sve_header, containing: unspecified. It is up to the caller to translate the payload layout for the actual VL and retry.

+* Where SME is implemented it is not possible to GETREGSET the register + state for normal SVE when in streaming mode, nor the streaming mode + register state when in normal mode, regardless of the implementation defined + behaviour of the hardware for sharing data between the two modes. + +* Any SETREGSET of NT_ARM_SVE will exit streaming mode if the target was in + streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode + if the target was not in streaming mode. + * The effect of writing a partial, incomplete payload is unspecified.

8. ELF coredump extensions ---------------------------

-* A NT_ARM_SVE note will be added to each coredump for each thread of the - dumped process. The contents will be equivalent to the data that would have - been read if a PTRACE_GETREGSET of NT_ARM_SVE were executed for each thread - when the coredump was generated. - +* NT_ARM_SVE and NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated.

9. System runtime configuration --------------------------------

As for SVE provide a sysctl which allows the default SME vector length to be configured.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kernel/fpsimd.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 3fb2167f8af7..841b9609342f 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -483,6 +483,30 @@ static int __init sve_sysctl_init(void) static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */

+#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) +static struct ctl_table sme_default_vl_table[] = { + { + .procname = "sme_default_vector_length", + .mode = 0644, + .proc_handler = vec_proc_do_default_vl, + .extra1 = &vl_info[ARM64_VEC_SME], + }, + { } +}; + +static int __init sme_sysctl_init(void) +{ + if (system_supports_sme()) + if (!register_sysctl("abi", sme_default_vl_table)) + return -EINVAL; + + return 0; +} + +#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ +static int __init sme_sysctl_init(void) { return 0; } +#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ + #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))

@@ -1681,6 +1705,9 @@ static int __init fpsimd_init(void) if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE)) pr_notice("SME is implemented but not SVE\n");

- return sve_sysctl_init(); + sve_sysctl_init(); + sme_sysctl_init(); + + return 0; } core_initcall(fpsimd_init);

As for SVE provide a prctl() interface which allows processes to configure their SME vector length.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/fpsimd.h | 4 ++++ arch/arm64/include/asm/processor.h | 4 +++- arch/arm64/include/asm/thread_info.h | 1 + arch/arm64/kernel/fpsimd.c | 32 ++++++++++++++++++++++++++++ include/uapi/linux/prctl.h | 9 ++++++++ kernel/sys.c | 12 +++++++++++ 6 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 8cb99b6fe565..babf944e7c0c 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -288,6 +288,8 @@ static inline int sme_max_virtualisable_vl(void) }

extern unsigned int sme_get_vl(void); +extern int sme_set_current_vl(unsigned long arg); +extern int sme_get_current_vl(void);

#else

@@ -299,6 +301,8 @@ static inline void sme_setup(void) { } static inline unsigned int sme_get_vl(void) { return 0; } static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } +static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } +static inline int sme_get_current_vl(void) { return -EINVAL; }

#endif /* ! CONFIG_ARM64_SME */

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index df68f0fb0ded..f2c2ebd440e2 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -354,9 +354,11 @@ extern void __init minsigstksz_setup(void); */ #include <asm/fpsimd.h>

-/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ +/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() +#define SME_SET_VL(arg) sme_set_current_vl(arg) +#define SME_GET_VL() sme_get_current_vl()

/* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index e1317b7c4525..4e6b58dcd6f9 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -82,6 +82,7 @@ int arch_dup_task_struct(struct task_struct *dst, #define TIF_SVE_VL_INHERIT 24 /* Inherit SVE vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ +#define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */

#define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 841b9609342f..1edb3996f9cf 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -149,6 +149,8 @@ static unsigned int vec_vl_inherit_flag(enum vec_type type) switch (type) { case ARM64_VEC_SVE: return TIF_SVE_VL_INHERIT; + case ARM64_VEC_SME: + return TIF_SME_VL_INHERIT; default: WARN_ON_ONCE(1); return 0; @@ -801,6 +803,36 @@ int sve_get_current_vl(void) return vec_prctl_status(ARM64_VEC_SVE, 0); }

+#ifdef CONFIG_ARM64_SME +/* PR_SME_SET_VL */ +int sme_set_current_vl(unsigned long arg) +{ + unsigned long vl, flags; + int ret; + + vl = arg & PR_SME_VL_LEN_MASK; + flags = arg & ~vl; + + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags); + if (ret) + return ret; + + return vec_prctl_status(ARM64_VEC_SME, flags); +} + +/* PR_SME_GET_VL */ +int sme_get_current_vl(void) +{ + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + return vec_prctl_status(ARM64_VEC_SME, 0); +} +#endif /* CONFIG_ARM64_SME */ + static void vec_probe_vqs(struct vl_info *info, DECLARE_BITMAP(map, SVE_VQ_MAX)) { diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..a5e06dcbba13 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,6 +272,15 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2

+/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0

diff --git a/kernel/sys.c b/kernel/sys.c index ecc4cf019242..5cd4fffc7cd0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -116,6 +116,12 @@ #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif +#ifndef SME_SET_VL +# define SME_SET_VL(a) (-EINVAL) +#endif +#ifndef SME_GET_VL +# define SME_GET_VL() (-EINVAL) +#endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif @@ -2523,6 +2529,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SVE_GET_VL: error = SVE_GET_VL(); break; + case PR_SME_SET_VL: + error = SME_SET_VL(arg2); + break; + case PR_SME_GET_VL: + error = SME_GET_VL(); + break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL;

The Scalable Matrix Extension introduces support for a new thread specific data register TPIDR2 intended for use by libc. The kernel must save the value of TPIDR2 on context switch and should ensure that all new threads start off with a default value of 0. Add a field to the thread_struct to store TPIDR2 and context switch it with the other thread specific data.

In case there are future extensions which also use TPIDR2 we introduce system_supports_tpidr2() and use that rather than system_supports_sme() for TPIDR2 handling.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/cpufeature.h | 5 +++++ arch/arm64/include/asm/processor.h | 1 + arch/arm64/kernel/fpsimd.c | 4 ++++ arch/arm64/kernel/process.c | 14 ++++++++++++-- 4 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 9d36035acce3..12252352d2ee 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -747,6 +747,11 @@ static __always_inline bool system_supports_fa64(void) cpus_have_const_cap(ARM64_SME_FA64); }

+static __always_inline bool system_supports_tpidr2(void) +{ + return system_supports_sme(); +} + static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index f2c2ebd440e2..008a1767ebff 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -168,6 +168,7 @@ struct thread_struct { u64 mte_ctrl; #endif u64 sctlr_user; + u64 tpidr2_el0; };

static inline unsigned int thread_get_vl(struct thread_struct *thread, diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 1edb3996f9cf..40ef89120774 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1092,6 +1092,10 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) /* Allow SME in kernel */ write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); isb(); + + /* Allow EL0 to access TPIDR2 */ + write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); + isb(); }

/* diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 5369e649fa79..e69a3dcdb0d9 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -250,6 +250,8 @@ void show_regs(struct pt_regs *regs) static void tls_thread_flush(void) { write_sysreg(0, tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(0, SYS_TPIDR2_EL0);

if (is_compat_task()) { current->thread.uw.tp_value = 0; @@ -343,6 +345,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, * out-of-sync with the saved value. */ *task_user_tls(p) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2()) + p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);

if (stack_start) { if (is_compat_thread(task_thread_info(p))) @@ -353,10 +357,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,

/* * If a TLS pointer was passed to clone, use it for the new - * thread. + * thread. We also reset TPIDR2 if it's in use. */ - if (clone_flags & CLONE_SETTLS) + if (clone_flags & CLONE_SETTLS) { p->thread.uw.tp_value = tls; + p->thread.tpidr2_el0 = 0; + } } else { /* * A kthread has no context to ERET to, so ensure any buggy @@ -387,6 +393,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, void tls_preserve_current_state(void) { *task_user_tls(current) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2() && !is_compat_task()) + current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); }

static void tls_thread_switch(struct task_struct *next) @@ -399,6 +407,8 @@ static void tls_thread_switch(struct task_struct *next) write_sysreg(0, tpidrro_el0);

write_sysreg(*task_user_tls(next), tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0); }

/*

In SME the use of both streaming SVE mode and ZA are tracked through PSTATE.SM and PSTATE.ZA, visible through the system register SVCR. In order to context switch the floating point state for SME we need to context switch the contents of this register as part of context switching the floating point state.

Since changing the vector length exits streaming SVE mode and disables ZA we also make sure we update SVCR appropriately when setting vector length, and similarly ensure that new threads have streaming SVE mode and ZA disabled.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/fpsimd.h | 3 ++- arch/arm64/include/asm/processor.h | 1 + arch/arm64/include/asm/thread_info.h | 1 + arch/arm64/kernel/fpsimd.c | 18 +++++++++++++++++- arch/arm64/kernel/process.c | 2 ++ arch/arm64/kvm/fpsimd.c | 4 ++++ 6 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index babf944e7c0c..d1bae65d3dba 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -46,7 +46,8 @@ extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);

extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, - void *sve_state, unsigned int sve_vl); + void *sve_state, unsigned int sve_vl, + u64 *svcr);

extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 008a1767ebff..7e08a4d48c24 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -168,6 +168,7 @@ struct thread_struct { u64 mte_ctrl; #endif u64 sctlr_user; + u64 svcr; u64 tpidr2_el0; };

diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 4e6b58dcd6f9..848739c15de8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -82,6 +82,7 @@ int arch_dup_task_struct(struct task_struct *dst, #define TIF_SVE_VL_INHERIT 24 /* Inherit SVE vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ +#define TIF_SME 27 /* SME in use */ #define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */

#define _TIF_SIGPENDING (1 << TIF_SIGPENDING) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 40ef89120774..a1918b71d335 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -121,6 +121,7 @@ struct fpsimd_last_state_struct { struct user_fpsimd_state *st; void *sve_state; + u64 *svcr; unsigned int sve_vl; };

@@ -359,6 +360,9 @@ static void task_fpsimd_load(void) WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context());

+ if (IS_ENABLED(CONFIG_ARM64_SME) && test_thread_flag(TIF_SME)) + write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0); + if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); sve_load_state(sve_pffr(&current->thread), @@ -384,6 +388,12 @@ static void fpsimd_save(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return;

+ if (IS_ENABLED(CONFIG_ARM64_SME) && + test_thread_flag(TIF_SME)) { + u64 *svcr = last->svcr; + *svcr = read_sysreg_s(SYS_SVCR_EL0); + } + if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { if (WARN_ON(sve_get_vl() != last->sve_vl)) { @@ -735,6 +745,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) sve_to_fpsimd(task);

+ if (system_supports_sme() && type == ARM64_VEC_SME) + task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK | + SYS_SVCR_EL0_ZA_MASK); + if (task == current) put_cpu_fpsimd_context();

@@ -1398,6 +1412,7 @@ static void fpsimd_bind_task_to_cpu(void) last->st = &current->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; last->sve_vl = task_get_sve_vl(current); + last->svcr = &current->thread.svcr; current->thread.fpsimd_cpu = smp_processor_id();

if (system_supports_sve()) { @@ -1412,7 +1427,7 @@ static void fpsimd_bind_task_to_cpu(void) }

void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, - unsigned int sve_vl) + unsigned int sve_vl, u64 *svcr) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); @@ -1421,6 +1436,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, WARN_ON(!in_softirq() && !irqs_disabled());

last->st = st; + last->svcr = svcr; last->sve_state = sve_state; last->sve_vl = sve_vl; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index e69a3dcdb0d9..f2d32a29641c 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -310,6 +310,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) dst->thread.sve_state = NULL; clear_tsk_thread_flag(dst, TIF_SVE);

+ dst->thread.svcr = 0; + /* clear any pending asynchronous tag fault raised by the parent */ clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);

diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 2f48fd362a8c..04698c4bcd30 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -103,6 +103,10 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!irqs_disabled());

if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { + /* + * Currently we do not support SME guests so SVCR is + * always 0 and we just need a variable to point to. + */ fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, vcpu->arch.sve_state, vcpu->arch.sve_max_vl);

When in streaming mode we need to save and restore the streaming mode SVE register state rather than the regular SVE register state. This uses the streaming mode vector length and omits FFR but is otherwise identical, if TIF_SVE is enabled when we are in streaming mode then streaming mode takes precedence.

This does not handle use of streaming SVE state with KVM, ptrace or signals. This will be updated in further patches.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/fpsimd.h | 22 +++++- arch/arm64/include/asm/fpsimdmacros.h | 11 +++ arch/arm64/include/asm/processor.h | 10 +++ arch/arm64/kernel/entry-fpsimd.S | 5 ++ arch/arm64/kernel/fpsimd.c | 109 +++++++++++++++++++++----- arch/arm64/kvm/fpsimd.c | 3 +- 6 files changed, 137 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index d1bae65d3dba..650ec642159c 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -47,11 +47,21 @@ extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);

extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, void *sve_state, unsigned int sve_vl, - u64 *svcr); + unsigned int sme_vl, u64 *svcr);

extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void);

+static inline bool thread_sm_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK); +} + +static inline bool thread_za_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK); +} + /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100

@@ -63,7 +73,14 @@ static inline size_t sve_ffr_offset(int vl)

static inline void *sve_pffr(struct thread_struct *thread) { - return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread)); + unsigned int vl; + + if (system_supports_sme() && thread_sm_enabled(thread)) + vl = thread_get_sme_vl(thread); + else + vl = thread_get_sve_vl(thread); + + return (char *)thread->sve_state + sve_ffr_offset(vl); }

extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); @@ -72,6 +89,7 @@ extern void sve_load_state(void const *state, u32 const *pfpsr, extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); +extern void sme_set_vq(unsigned long vq_minus_1);

struct arm64_cpu_capabilities; extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 11c426ddd62c..a50fa1eab730 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -261,6 +261,17 @@ 921: .endm

+/* Update SMCR_EL1.LEN with the new VQ */ +.macro sme_load_vq xvqminus1, xtmp, xtmp2 + mrs_s \xtmp, SYS_SMCR_EL1 + bic \xtmp2, \xtmp, SMCR_ELx_LEN_MASK + orr \xtmp2, \xtmp2, \xvqminus1 + cmp \xtmp2, \xtmp + b.eq 921f + msr_s SYS_SMCR_EL1, \xtmp2 //self-synchronising +921: +.endm + /* Preserve the first 128-bits of Znz and zero the rest. */ .macro _sve_flush_z nz _sve_check_zreg \nz diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 7e08a4d48c24..6e2af9de153c 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -183,6 +183,11 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) return thread_get_vl(thread, ARM64_VEC_SVE); }

+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) +{ + return thread_get_vl(thread, ARM64_VEC_SME); +} + unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); @@ -196,6 +201,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task) return task_get_vl(task, ARM64_VEC_SVE); }

+static inline unsigned int task_get_sme_vl(const struct task_struct *task) +{ + return task_get_vl(task, ARM64_VEC_SME); +} + static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index deee5f01462e..6f88c0f86d50 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -94,4 +94,9 @@ SYM_FUNC_START(sme_get_vl) ret SYM_FUNC_END(sme_get_vl)

+SYM_FUNC_START(sme_set_vq) + sme_load_vq x0, x1, x2 + ret +SYM_FUNC_END(sme_set_vq) + #endif /* CONFIG_ARM64_SME */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index a1918b71d335..12fef62cf07a 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -123,6 +123,7 @@ struct fpsimd_last_state_struct { void *sve_state; u64 *svcr; unsigned int sve_vl; + unsigned int sme_vl; };

static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); @@ -301,17 +302,28 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, task->thread.vl_onexec[type] = vl; }

+/* + * TIF_SME controls whether a task can use SME without trapping while + * in userspace, when TIF_SME is set then we must have storage + * alocated in sve_state and za_state to store the contents of both ZA + * and the SVE registers for both streaming and non-streaming modes. + * + * If both SVCR.ZA and SVCR.SM are disabled then at any point we + * may disable TIF_SME and reenable traps. + */ + + /* * TIF_SVE controls whether a task can use SVE without trapping while - * in userspace, and also the way a task's FPSIMD/SVE state is stored - * in thread_struct. + * in userspace, and also (together with TIF_SME) the way a task's + * FPSIMD/SVE state is stored in thread_struct. * * The kernel uses this flag to track whether a user task is actively * using SVE, and therefore whether full SVE register state needs to * be tracked. If not, the cheaper FPSIMD context handling code can * be used instead of the more costly SVE equivalents. * - * * TIF_SVE set: + * * TIF_SVE or SVCR.SM set: * * The task can execute SVE instructions while in userspace without * trapping to the kernel. @@ -319,7 +331,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the * corresponding Zn), P0-P15 and FFR are encoded in in * task->thread.sve_state, formatted appropriately for vector - * length task->thread.sve_vl. + * length task->thread.sve_vl or, if SVCR.SM is set, + * task->thread.sme_vl. * * task->thread.sve_state must point to a valid buffer at least * sve_state_size(task) bytes in size. @@ -357,19 +370,40 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, */ static void task_fpsimd_load(void) { + bool restore_sve_regs = false; + bool restore_ffr; + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context());

- if (IS_ENABLED(CONFIG_ARM64_SME) && test_thread_flag(TIF_SME)) - write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0); - + /* Check if we should restore SVE first */ if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); + restore_sve_regs = true; + restore_ffr = true; + } + + /* Restore SME, override SVE register configuration if needed */ + if (system_supports_sme()) { + unsigned long sme_vl = task_get_sme_vl(current); + + if (test_thread_flag(TIF_SME)) + sme_set_vq(sve_vq_from_vl(sme_vl) - 1); + + write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0); + + if (thread_sm_enabled(&current->thread)) { + restore_sve_regs = true; + restore_ffr = system_supports_fa64(); + } + } + + if (restore_sve_regs) sve_load_state(sve_pffr(&current->thread), - &current->thread.uw.fpsimd_state.fpsr, true); - } else { + &current->thread.uw.fpsimd_state.fpsr, + restore_ffr); + else fpsimd_load_state(&current->thread.uw.fpsimd_state); - } }

/* @@ -381,6 +415,9 @@ static void fpsimd_save(void) struct fpsimd_last_state_struct const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ + bool save_sve_regs = false; + bool save_ffr; + unsigned int vl;

WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); @@ -388,15 +425,33 @@ static void fpsimd_save(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return;

- if (IS_ENABLED(CONFIG_ARM64_SME) && - test_thread_flag(TIF_SME)) { + if (test_thread_flag(TIF_SVE)) { + save_sve_regs = true; + save_ffr = true; + vl = last->sve_vl; + } + + if (system_supports_sme()) { u64 *svcr = last->svcr; *svcr = read_sysreg_s(SYS_SVCR_EL0); + + if (thread_za_enabled(&current->thread)) { + /* ZA state managment is not implemented yet */ + force_signal_inject(SIGKILL, SI_KERNEL, 0, 0); + return; + } + + /* If we are in streaming mode override regular SVE. */ + if (*svcr & SYS_SVCR_EL0_SM_MASK) { + save_sve_regs = true; + save_ffr = system_supports_fa64(); + vl = last->sme_vl; + } }

- if (IS_ENABLED(CONFIG_ARM64_SVE) && - test_thread_flag(TIF_SVE)) { - if (WARN_ON(sve_get_vl() != last->sve_vl)) { + if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) { + /* Get the configured VL from RDVL, will account for SM */ + if (WARN_ON(sve_get_vl() != vl)) { /* * Can't save the user regs, so current would * re-enter user with corrupt state. @@ -407,8 +462,8 @@ static void fpsimd_save(void) }

sve_save_state((char *)last->sve_state + - sve_ffr_offset(last->sve_vl), - &last->st->fpsr, true); + sve_ffr_offset(vl), + &last->st->fpsr, save_ffr); } else { fpsimd_save_state(last->st); } @@ -613,7 +668,14 @@ static void sve_to_fpsimd(struct task_struct *task) */ static size_t sve_state_size(struct task_struct const *task) { - return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task))); + unsigned int vl = 0; + + if (system_supports_sve()) + vl = task_get_sve_vl(task); + if (system_supports_sme()) + vl = max(vl, task_get_sme_vl(task)); + + return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)); }

/* @@ -742,7 +804,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, }

fpsimd_flush_task_state(task); - if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) + if (test_and_clear_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task);

if (system_supports_sme() && type == ARM64_VEC_SME) @@ -1369,6 +1432,9 @@ void fpsimd_flush_thread(void) fpsimd_flush_thread_vl(ARM64_VEC_SVE); }

+ if (system_supports_sme()) + fpsimd_flush_thread_vl(ARM64_VEC_SME); + put_cpu_fpsimd_context(); }

@@ -1412,6 +1478,7 @@ static void fpsimd_bind_task_to_cpu(void) last->st = &current->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; last->sve_vl = task_get_sve_vl(current); + last->sme_vl = task_get_sme_vl(current); last->svcr = &current->thread.svcr; current->thread.fpsimd_cpu = smp_processor_id();

@@ -1427,7 +1494,8 @@ static void fpsimd_bind_task_to_cpu(void) }

void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, - unsigned int sve_vl, u64 *svcr) + unsigned int sve_vl, unsigned int sme_vl, + u64 *svcr) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); @@ -1439,6 +1507,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, last->svcr = svcr; last->sve_state = sve_state; last->sve_vl = sve_vl; + last->sme_vl = sme_vl; }

/* diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 04698c4bcd30..902c598b7ed2 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -109,7 +109,8 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) */ fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, vcpu->arch.sve_state, - vcpu->arch.sve_max_vl); + vcpu->arch.sve_max_vl, + 0);

clear_thread_flag(TIF_FOREIGN_FPSTATE); update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));

The ABI requires that streaming mode and ZA are disabled when invoking signal handlers, do this in setup_return() when we prepare the task state for the signal handler.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kernel/signal.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index d8aaf4b6f432..cda04fd73333 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -758,6 +758,13 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, /* TCO (Tag Check Override) always cleared for signal handlers */ regs->pstate &= ~PSR_TCO_BIT;

+ /* Signal handlers are invoked with ZA and streaming mode disabled */ + if (system_supports_sme()) { + current->thread.svcr &= ~(SYS_SVCR_EL0_ZA_MASK | + SYS_SVCR_EL0_SM_MASK); + sme_smstop(); + } + if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else

When in streaming mode we have the same set of SVE registers as we do in regular SVE mode with the exception of FFR and the use of the SME vector length. Provide signal handling for these registers by taking one of the reserved words in the SVE signal context as a flags field and defining a flag with a flag which is set for streaming mode. When the flag is set the vector length is set to the streaming mode vector length and we save and restore streaming mode data. We support entering or leaving streaming mode based on the value of the flag but do not support changing the vector length, this is not currently supported SVE signal handling.

We could instead allocate a separate record in the signal frame for the streaming mode SVE context but this inflates the size of the maximal signal frame required and adds complication when validating signal frames from userspace, especially given the current structure of the code.

Any implementation of support for streaming mode vectors in signals will have some potential for causing issues for applications that attempt to handle SVE vectors in signals, use streaming mode but do not understand streaming mode in their signal handling code, it is hard to identify a case that is clearly better than any other - they all have cases where they could cause unexpected register corruption or faults.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/uapi/asm/sigcontext.h | 16 ++++++-- arch/arm64/kernel/signal.c | 48 ++++++++++++++++++------ 2 files changed, 50 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 0c796c795dbe..3a3366d4fbc2 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -134,9 +134,12 @@ struct extra_context { struct sve_context { struct _aarch64_ctx head; __u16 vl; - __u16 __reserved[3]; + __u16 flags; + __u16 __reserved[2]; };

+#define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */ + #endif /* !__ASSEMBLY__ */

#include <asm/sve_context.h> @@ -186,9 +189,16 @@ struct sve_context { * sve_context.vl must equal the thread's current vector length when * doing a sigreturn. * + * On systems with support for SME the SVE register state may reflect either + * streaming or non-streaming mode. In streaming mode the streaming mode + * vector length will be used and the flag SVE_SIG_FLAG_SM will be set in + * the flags field. It is permitted to enter or leave streaming mode in + * a signal return, applications should take care to ensure that any difference + * in vector length between the two modes is handled, including any resixing + * and movement of context blocks. * - * Note: for all these macros, the "vq" argument denotes the SVE - * vector length in quadwords (i.e., units of 128 bits). + * Note: for all these macros, the "vq" argument denotes the vector length + * in quadwords (i.e., units of 128 bits). * * The correct way to obtain vq is to use sve_vq_from_vl(vl). The * result is valid if and only if sve_vl_valid(vl) is true. This is diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index cda04fd73333..5e6ec6ed8a1c 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -227,11 +227,17 @@ static int preserve_sve_context(struct sve_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + u16 flags = 0; unsigned int vl = task_get_sve_vl(current); unsigned int vq = 0;

- if (test_thread_flag(TIF_SVE)) + if (thread_sm_enabled(&current->thread)) { + vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); + flags |= SVE_SIG_FLAG_SM; + } else if (test_thread_flag(TIF_SVE)) { + vq = sve_vq_from_vl(vl); + }

memset(reserved, 0, sizeof(reserved));

@@ -239,6 +245,7 @@ static int preserve_sve_context(struct sve_context __user *ctx) __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); + __put_user_error(flags, &ctx->flags, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));

@@ -259,18 +266,28 @@ static int preserve_sve_context(struct sve_context __user *ctx) static int restore_sve_fpsimd_context(struct user_ctxs *user) { int err; - unsigned int vq; + unsigned int vl, vq; struct user_fpsimd_state fpsimd; struct sve_context sve;

if (__copy_from_user(&sve, user->sve, sizeof(sve))) return -EFAULT;

- if (sve.vl != task_get_sve_vl(current)) + if (sve.flags & SVE_SIG_FLAG_SM) { + if (!system_supports_sme()) + return -EINVAL; + + vl = task_get_sme_vl(current); + } else { + vl = task_get_sve_vl(current); + } + + if (sve.vl != vl) return -EINVAL;

if (sve.head.size <= sizeof(*user->sve)) { clear_thread_flag(TIF_SVE); + current->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK; goto fpsimd_only; }

@@ -302,7 +319,10 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (err) return -EFAULT;

- set_thread_flag(TIF_SVE); + if (sve.flags & SVE_SIG_FLAG_SM) + current->thread.svcr |= SYS_SVCR_EL0_SM_MASK; + else + set_thread_flag(TIF_SVE);

fpsimd_only: /* copy the FP and status/control registers */ @@ -394,7 +414,7 @@ static int parse_user_sigframe(struct user_ctxs *user, break;

case SVE_MAGIC: - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) goto invalid;

if (user->sve) @@ -593,11 +613,16 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, if (system_supports_sve()) { unsigned int vq = 0;

- if (add_all || test_thread_flag(TIF_SVE)) { - int vl = sve_max_vl(); + if (add_all || test_thread_flag(TIF_SVE) || + thread_sm_enabled(&current->thread)) { + int vl = max(sve_max_vl(), sme_max_vl());

- if (!add_all) - vl = task_get_sve_vl(current); + if (!add_all) { + if (thread_sm_enabled(&current->thread)) + vl = task_get_sme_vl(current); + else + vl = task_get_sve_vl(current); + }

vq = sve_vq_from_vl(vl); } @@ -648,8 +673,9 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); }

- /* Scalable Vector Extension state, if present */ - if (system_supports_sve() && err == 0 && user->sve_offset) { + /* Scalable Vector Extension state (including streaming), if present */ + if ((system_supports_sve() || system_supports_sme()) && + err == 0 && user->sve_offset) { struct sve_context __user *sve_ctx = apply_user_offset(user, user->sve_offset); err |= preserve_sve_context(sve_ctx);

Implement support for ZA in signal handling in a very similar way to how we implement support for SVE registers, using a signal context structure with optional register state after it. Where present this register state stores the ZA matrix as a series of horizontal vectors numbered from 0 to VL/8 in the endinanness independent format used for vectors.

As with SVE we do not allow changes in the vector length during signal return but we do allow ZA to be enabled or disabled.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/uapi/asm/sigcontext.h | 41 +++++++ arch/arm64/kernel/fpsimd.c | 3 - arch/arm64/kernel/signal.c | 139 +++++++++++++++++++++++ 3 files changed, 180 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 3a3366d4fbc2..d45bdf2c8b26 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -140,6 +140,14 @@ struct sve_context {

#define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */

+#define ZA_MAGIC 0x54366345 + +struct za_context { + struct _aarch64_ctx head; + __u16 vl; + __u16 __reserved[3]; +}; + #endif /* !__ASSEMBLY__ */

#include <asm/sve_context.h> @@ -259,4 +267,37 @@ struct sve_context { #define SVE_SIG_CONTEXT_SIZE(vq) \ (SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq))

+/* + * If the ZA register is enabled for the thread at signal delivery then, + * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * and the register data may be accessed using the ZA_SIG_*() macros. + * + * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * then ZA was not enabled and no register data was included in which case + * ZA register was not enabled for the thread and no register data + * the ZA_SIG_*() macros should not be used except for this check. + * + * The same convention applies when returning from a signal: a caller + * will need to remove or resize the za_context block if it wants to + * enable the ZA register when it was previously non-live or vice-versa. + * This may require the caller to allocate fresh memory and/or move other + * context blocks in the signal frame. + * + * Changing the vector length during signal return is not permitted: + * za_context.vl must equal the thread's current SME vector length when + * doing a sigreturn. + */ + +#define ZA_SIG_REGS_OFFSET \ + ((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_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ + (SVE_SIG_ZREG_SIZE(vq) * n)) + +#define ZA_SIG_CONTEXT_SIZE(vq) \ + (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) + #endif /* _UAPI__ASM_SIGCONTEXT_H */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 33f80512753d..2242c14a5a05 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1190,9 +1190,6 @@ void fpsimd_release_task(struct task_struct *dead_task)

#ifdef CONFIG_ARM64_SME

-/* This will move to uapi/asm/sigcontext.h when signals are implemented */ -#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) - /* * Ensure that task->thread.za_state is allocated and sufficiently large. * diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 5e6ec6ed8a1c..8efa78765cad 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -57,6 +57,7 @@ struct rt_sigframe_user_layout { unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; + unsigned long za_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -219,6 +220,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) struct user_ctxs { struct fpsimd_context __user *fpsimd; struct sve_context __user *sve; + struct za_context __user *za; };

#ifdef CONFIG_ARM64_SVE @@ -347,6 +349,101 @@ extern int restore_sve_fpsimd_context(struct user_ctxs *user);

#endif /* ! CONFIG_ARM64_SVE */

+#ifdef CONFIG_ARM64_SME + +static int preserve_za_context(struct za_context __user *ctx) +{ + int err = 0; + u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + unsigned int vl = task_get_sme_vl(current); + unsigned int vq; + + if (thread_za_enabled(&current->thread)) + vq = sve_vq_from_vl(vl); + else + vq = 0; + + memset(reserved, 0, sizeof(reserved)); + + __put_user_error(ZA_MAGIC, &ctx->head.magic, err); + __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16), + &ctx->head.size, err); + __put_user_error(vl, &ctx->vl, err); + BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); + err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); + + if (vq) { + /* + * This assumes that the ZA state has already been saved to + * the task struct by calling the function + * fpsimd_signal_preserve_current_state(). + */ + err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, + current->thread.za_state, + ZA_SIG_REGS_SIZE(vq)); + } + + return err ? -EFAULT : 0; +} + +static int restore_za_context(struct user_ctxs __user *user) +{ + int err; + unsigned int vq; + struct za_context za; + + if (__copy_from_user(&za, user->za, sizeof(za))) + return -EFAULT; + + if (za.vl != task_get_sme_vl(current)) + return -EINVAL; + + if (za.head.size <= sizeof(*user->za)) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + return 0; + } + + vq = sve_vq_from_vl(za.vl); + + if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq)) + return -EINVAL; + + /* + * Careful: we are about __copy_from_user() directly into + * thread.za_state with preemption enabled, so protection is + * needed to prevent a racing context switch from writing stale + * registers back over the new data. + */ + + fpsimd_flush_task_state(current); + /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ + + sme_alloc(current); + if (!current->thread.za_state) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + clear_thread_flag(TIF_SME); + return -ENOMEM; + } + + err = __copy_from_user(current->thread.za_state, + (char __user const *)user->za + + ZA_SIG_REGS_OFFSET, + ZA_SIG_REGS_SIZE(vq)); + if (err) + return -EFAULT; + + set_thread_flag(TIF_SME); + current->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + + return 0; +} +#else /* ! CONFIG_ARM64_SME */ + +/* Turn any non-optimised out attempts to use these into a link error: */ +extern int preserve_za_context(void __user *ctx); +extern int restore_za_context(struct user_ctxs *user); + +#endif /* ! CONFIG_ARM64_SME */

static int parse_user_sigframe(struct user_ctxs *user, struct rt_sigframe __user *sf) @@ -361,6 +458,7 @@ static int parse_user_sigframe(struct user_ctxs *user,

user->fpsimd = NULL; user->sve = NULL; + user->za = NULL;

if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -426,6 +524,19 @@ static int parse_user_sigframe(struct user_ctxs *user, user->sve = (struct sve_context __user *)head; break;

+ case ZA_MAGIC: + if (!system_supports_sme()) + goto invalid; + + if (user->za) + goto invalid; + + if (size < sizeof(*user->za)) + goto invalid; + + user->za = (struct za_context __user *)head; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -549,6 +660,9 @@ static int restore_sigframe(struct pt_regs *regs, } }

+ if (err == 0 && system_supports_sme() && user.za) + err = restore_za_context(&user); + return err; }

@@ -633,6 +747,24 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; }

+ if (system_supports_sme()) { + unsigned int vl; + unsigned int vq = 0; + + if (add_all) + vl = sme_max_vl(); + else + vl = task_get_sme_vl(current); + + if (thread_za_enabled(&current->thread)) + vq = sve_vq_from_vl(vl); + + err = sigframe_alloc(user, &user->za_offset, + ZA_SIG_CONTEXT_SIZE(vq)); + if (err) + return err; + } + return sigframe_alloc_end(user); }

@@ -681,6 +813,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_sve_context(sve_ctx); }

+ /* ZA state if present */ + if (system_supports_sme() && err == 0 && user->za_offset) { + struct za_context __user *za_ctx = + apply_user_offset(user, user->za_offset); + err |= preserve_za_context(za_ctx); + } + if (err == 0 && user->extra_offset) { char __user *sfp = (char __user *)user->sigframe; char __user *userp =

The streaming mode SVE registers are represented using the same data structures as for SVE but since the vector lengths supported and in use may not be the same as SVE we represent them with a new type NT_ARM_SSVE. Unfortunately we only have a single 16 bit reserved field available in the header so there is no space to fit the current and maximum vector length for both standard and streaming SVE mode without redefining the structure in a way the creates a complicatd and fragile ABI. Since FFR is not present in streaming mode it is read and written as zero.

Setting NT_ARM_SSVE registers will put the task into streaming mode, similarly setting NT_ARM_SVE registers will exit it. Reads that do not correspond to the current mode of the task will return the header with no register data. For compatibility reasons on write setting no flag for the register type will be interpreted as setting SVE registers, though users can provide no register data as an alternative mechanism for doing so.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/uapi/asm/ptrace.h | 13 +- arch/arm64/kernel/fpsimd.c | 21 ++- arch/arm64/kernel/ptrace.c | 212 +++++++++++++++++++++------ include/uapi/linux/elf.h | 1 + 4 files changed, 190 insertions(+), 57 deletions(-)

diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 758ae984ff97..522b925a78c1 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -109,7 +109,7 @@ struct user_hwdebug_state { } dbg_regs[16]; };

-/* SVE/FP/SIMD state (NT_ARM_SVE) */ +/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */

struct user_sve_header { __u32 size; /* total meaningful regset content in bytes */ @@ -220,6 +220,7 @@ struct user_sve_header { (SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \ SVE_PT_SVE_PREGS_OFFSET(vq))

+/* For streaming mode SVE (SSVE) FFR must be read and written as zero */ #define SVE_PT_SVE_FFR_OFFSET(vq) \ (SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq))

@@ -240,10 +241,12 @@ struct user_sve_header { - SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1)) \ / __SVE_VQ_BYTES * __SVE_VQ_BYTES)

-#define SVE_PT_SIZE(vq, flags) \ - (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ - SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ - : SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags)) +#define SVE_PT_SIZE(vq, flags) \ + (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ + SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ + : ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ? \ + SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \ + : SVE_PT_REGS_OFFSET)))

/* pointer authentication masks (NT_ARM_PAC_MASK) */

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 2242c14a5a05..8b111b7f2006 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -645,14 +645,19 @@ static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst, */ static void fpsimd_to_sve(struct task_struct *task) { - unsigned int vq; + unsigned int vq, vl; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;

if (!system_supports_sve()) return;

- vq = sve_vq_from_vl(task_get_sve_vl(task)); + if (thread_sm_enabled(&task->thread)) + vl = task_get_sme_vl(task); + else + vl = task_get_sve_vl(task); + + vq = sve_vq_from_vl(vl); __fpsimd_to_sve(sst, fst, vq); }

@@ -669,7 +674,7 @@ static void fpsimd_to_sve(struct task_struct *task) */ static void sve_to_fpsimd(struct task_struct *task) { - unsigned int vq; + unsigned int vq, vl; void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; @@ -678,7 +683,12 @@ static void sve_to_fpsimd(struct task_struct *task) if (!system_supports_sve()) return;

- vq = sve_vq_from_vl(task_get_sve_vl(task)); + if (thread_sm_enabled(&task->thread)) + vl = task_get_sme_vl(task); + else + vl = task_get_sve_vl(task); + + vq = sve_vq_from_vl(vl); for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); @@ -819,8 +829,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, /* * To ensure the FPSIMD bits of the SVE vector registers are preserved, * write any live register state back to task_struct, and convert to a - * regular FPSIMD thread. Since the vector length can only be changed - * with a syscall we can't be in streaming mode while reconfiguring. + * regular FPSIMD thread. */ if (task == current) { get_cpu_fpsimd_context(); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 39dbdfdc38d3..0b8324fa1abc 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -714,21 +714,51 @@ static int system_call_set(struct task_struct *target, #ifdef CONFIG_ARM64_SVE

static void sve_init_header_from_task(struct user_sve_header *header, - struct task_struct *target) + struct task_struct *target, + enum vec_type type) { unsigned int vq; + bool active; + bool fpsimd_only; + enum vec_type task_type;

memset(header, 0, sizeof(*header));

- header->flags = test_tsk_thread_flag(target, TIF_SVE) ? - SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD; - if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) - header->flags |= SVE_PT_VL_INHERIT; + /* Check if the requested registers are active for the task */ + if (thread_sm_enabled(&target->thread)) + task_type = ARM64_VEC_SME; + else + task_type = ARM64_VEC_SVE; + active = (task_type == type); + + switch (type) { + case ARM64_VEC_SVE: + if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); + break; + case ARM64_VEC_SME: + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = false; + break; + default: + WARN_ON_ONCE(1); + return; + }

- header->vl = task_get_sve_vl(target); + if (active) { + if (fpsimd_only) { + header->flags |= SVE_PT_REGS_FPSIMD; + } else { + header->flags |= SVE_PT_REGS_SVE; + } + } + + header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl);

- header->max_vl = sve_max_vl(); + header->max_vl = vec_max_vl(type); header->size = SVE_PT_SIZE(vq, header->flags); header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), SVE_PT_REGS_SVE); @@ -739,19 +769,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header) return ALIGN(header->size, SVE_VQ_BYTES); }

-static int sve_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) +static int sve_get_common(struct task_struct *target, + const struct user_regset *regset, + struct membuf to, + enum vec_type type) { struct user_sve_header header; unsigned int vq; unsigned long start, end;

- if (!system_supports_sve()) - return -EINVAL; - /* Header */ - sve_init_header_from_task(&header, target); + sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl);

membuf_write(&to, &header, sizeof(header)); @@ -759,49 +787,61 @@ static int sve_get(struct task_struct *target, if (target == current) fpsimd_preserve_current_state();

- /* Registers: FPSIMD-only case */ - BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); - if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + + switch ((header.flags & SVE_PT_REGS_MASK)) { + case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to);

- /* Otherwise: full SVE case */ + case SVE_PT_REGS_SVE: + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + membuf_write(&to, target->thread.sve_state, end - start);

- BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); - start = SVE_PT_SVE_OFFSET; - end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); - membuf_write(&to, target->thread.sve_state, end - start); + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + membuf_zero(&to, end - start);

- start = end; - end = SVE_PT_SVE_FPSR_OFFSET(vq); - membuf_zero(&to, end - start); + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, + end - start);

- /* - * Copy fpsr, and fpcr which must follow contiguously in - * struct fpsimd_state: - */ - start = end; - end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; - membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); + start = end; + end = sve_size_from_header(&header); + return membuf_zero(&to, end - start);

- start = end; - end = sve_size_from_header(&header); - return membuf_zero(&to, end - start); + default: + return 0; + } }

-static int sve_set(struct task_struct *target, +static int sve_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + struct membuf to) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SVE); +} + +static int sve_set_common(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + enum vec_type type) { int ret; struct user_sve_header header; unsigned int vq; unsigned long start, end;

- if (!system_supports_sve()) - return -EINVAL; - /* Header */ if (count < sizeof(header)) return -EINVAL; @@ -814,13 +854,37 @@ static int sve_set(struct task_struct *target, * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for us: */ - ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl, + ret = vec_set_vector_length(target, type, header.vl, ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); if (ret) goto out;

/* Actual VL set may be less than the user asked for: */ - vq = sve_vq_from_vl(task_get_sve_vl(target)); + vq = sve_vq_from_vl(task_get_vl(target, type)); + + /* Enter/exit streaming mode */ + if (system_supports_sme()) { + u64 old_svcr = target->thread.svcr; + + switch (type) { + case ARM64_VEC_SVE: + target->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK; + break; + case ARM64_VEC_SME: + target->thread.svcr |= SYS_SVCR_EL0_SM_MASK; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + /* + * If we switched then invalidate any existing SVE + * state and ensure there's storage. + */ + if (target->thread.svcr != old_svcr) + sve_alloc(target); + }

/* Registers: FPSIMD-only case */

@@ -832,7 +896,10 @@ static int sve_set(struct task_struct *target, goto out; }

- /* Otherwise: full SVE case */ + /* + * Otherwise: no registers or full SVE case. For backwards + * compatibility reasons we treat empty flags as SVE registers. + */

/* * If setting a different VL from the requested VL and there is @@ -853,8 +920,9 @@ static int sve_set(struct task_struct *target,

/* * Ensure target->thread.sve_state is up to date with target's - * FPSIMD regs, so that a short copyin leaves trailing registers - * unmodified. + * FPSIMD regs, so that a short copyin leaves trailing + * registers unmodified. Always enable SVE even if going into + * streaming mode. */ fpsimd_sync_to_sve(target); set_tsk_thread_flag(target, TIF_SVE); @@ -890,8 +958,46 @@ static int sve_set(struct task_struct *target, return ret; }

+static int sve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SVE); +} + #endif /* CONFIG_ARM64_SVE */

+#ifdef CONFIG_ARM64_SME + +static int ssve_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SME); +} + +static int ssve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SME); +} + +#endif /* CONFIG_ARM64_SME */ + #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, @@ -1109,6 +1215,9 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif +#ifdef CONFIG_ARM64_SVE + REGSET_SSVE, +#endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, @@ -1189,6 +1298,17 @@ static const struct user_regset aarch64_regsets[] = { .set = sve_set, }, #endif +#ifdef CONFIG_ARM64_SME + [REGSET_SSVE] = { /* Streaming mode SVE */ + .core_note_type = NT_ARM_SSVE, + .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = ssve_get, + .set = ssve_set, + }, +#endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { .core_note_type = NT_ARM_PAC_MASK, diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 61bf4774b8f2..61502388683f 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -427,6 +427,7 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */

The ZA array can be read and written with the NT_ARM_ZA. Similarly to our interface for the SVE vector registers the regset consists of a header with information on the current vector length followed by an optional register data payload, represented as for signals as a series of horizontal vectors from 0 to VL/8 in the endianness independent format used for vectors.

On get if ZA is enabled then register data will be provided, otherwise it will be omitted. On set if register data is provided then ZA is enabled and initialized using the provided data, otherwise it is disabled.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/uapi/asm/ptrace.h | 56 +++++++++++ arch/arm64/kernel/ptrace.c | 144 +++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 3 files changed, 201 insertions(+)

diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 522b925a78c1..7fa2f7036aa7 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -268,6 +268,62 @@ struct user_pac_generic_keys { __uint128_t apgakey; };

+/* ZA state (NT_ARM_ZA) */ + +struct user_za_header { + __u32 size; /* total meaningful regset content in bytes */ + __u32 max_size; /* maxmium possible size for this thread */ + __u16 vl; /* current vector length */ + __u16 max_vl; /* maximum possible vector length */ + __u16 flags; + __u16 __reserved; +}; + +/* + * Common ZA_PT_* flags: + * These must be kept in sync with prctl interface in <linux/prctl.h> + */ +#define ZA_PT_VL_INHERIT ((1 << 17) /* PR_SME_VL_INHERIT */ >> 16) +#define ZA_PT_VL_ONEXEC ((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16) + + +/* + * The remainder of the ZA state follows struct user_za_header. The + * total size of the ZA state (including header) depends on the + * metadata in the header: ZA_PT_SIZE(vq, flags) gives the total size + * of the state in bytes, including the header. + * + * Refer to <asm/sigcontext.h> for details of how to pass the correct + * "vq" argument to these macros. + */ + +/* Offset from the start of struct user_za_header to the register data */ +#define ZA_PT_ZA_OFFSET \ + ((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +/* + * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size + * ZA_PT_ZA_SIZE(vq, flags). + * + * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8 + * bytes each, starting from vector 0. + * + * Additional data might be appended in the future. + * + * The ZA matrix is represented in memory in an endianness-invariant layout + * which differs from the layout used for the FPSIMD V-registers on big-endian + * systems: see sigcontext.h for more explanation. + */ + +#define ZA_PT_ZAV_OFFSET(vq, n) \ + (ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n)) + +#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_PT_SIZE(vq) \ + (ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq)) + #endif /* __ASSEMBLY__ */

#endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 0b8324fa1abc..d6f27d3bf6e7 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -996,6 +996,141 @@ static int ssve_set(struct task_struct *target, ARM64_VEC_SME); }

+static int za_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + memset(&header, 0, sizeof(header)); + + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header.flags |= ZA_PT_VL_INHERIT; + + header.vl = task_get_sme_vl(target); + vq = sve_vq_from_vl(header.vl); + header.max_vl = sme_max_vl(); + header.max_size = ZA_PT_SIZE(vq); + + /* If ZA is not active there is only the header */ + if (thread_za_enabled(&target->thread)) + header.size = ZA_PT_SIZE(vq); + else + header.size = ZA_PT_ZA_OFFSET; + + membuf_write(&to, &header, sizeof(header)); + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + end = ZA_PT_ZA_OFFSET; +; + if (target == current) + fpsimd_preserve_current_state(); + + /* Any register data to include? */ + if (thread_za_enabled(&target->thread)) { + start = end; + end = ZA_PT_SIZE(vq); + membuf_write(&to, target->thread.za_state, end - start); + } + + /* Zero any trailing padding */ + start = end; + end = ALIGN(header.size, SVE_VQ_BYTES); + return membuf_zero(&to, end - start); +} + +static int za_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; + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + if (count < sizeof(header)) + return -EINVAL; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + goto out; + + /* + * All current ZA_PT_* flags are consumed by + * vec_set_vector_length(), which will also validate them for + * us: + */ + ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, + ((unsigned long)header.flags) << 16); + if (ret) + goto out; + + /* Actual VL set may be less than the user asked for: */ + vq = sve_vq_from_vl(task_get_sme_vl(target)); + + /* Ensure there is some SVE storage for streaming mode */ + if (!target->thread.sve_state) { + sve_alloc(target); + if (!target->thread.sve_state) { + clear_thread_flag(TIF_SME); + ret = -ENOMEM; + goto out; + } + } + + /* Allocate/reinit ZA storage */ + sme_alloc(target); + if (!target->thread.za_state) { + ret = -ENOMEM; + clear_tsk_thread_flag(target, TIF_SME); + goto out; + } + + /* If there is no data then disable ZA */ + if (!count) { + target->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + goto out; + } + + /* + * If setting a different VL from the requested VL and there is + * register data, the data layout will be wrong: don't even + * try to set the registers in this case. + */ + if (vq != sve_vq_from_vl(header.vl)) { + ret = -EIO; + goto out; + } + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + start = ZA_PT_ZA_OFFSET; + end = ZA_PT_SIZE(vq); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.za_state, + start, end); + if (ret) + goto out; + + /* Mark ZA as active and let userspace use it */ + set_tsk_thread_flag(target, TIF_SME); + target->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + +out: + fpsimd_flush_task_state(target); + return ret; +} + #endif /* CONFIG_ARM64_SME */

#ifdef CONFIG_ARM64_PTR_AUTH @@ -1217,6 +1352,7 @@ enum aarch64_regset { #endif #ifdef CONFIG_ARM64_SVE REGSET_SSVE, + REGSET_ZA, #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, @@ -1308,6 +1444,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = ssve_get, .set = ssve_set, }, + [REGSET_ZA] = { /* SME ZA */ + .core_note_type = NT_ARM_ZA, + .n = DIV_ROUND_UP(ZA_PT_ZA_SIZE(SVE_VQ_MAX), SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = za_get, + .set = za_set, + }, #endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 61502388683f..7ef574f3256a 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -428,6 +428,7 @@ typedef struct elf64_shdr { #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */

Both streaming mode and ZA may increase power consumption when they are enabled and streaming mode makes many FPSIMD and SVE instructions undefined which will cause problems for any kernel mode floating point so disable both when we flush the CPU state. This covers both kernel_neon_begin() and idle and after flushing the state a reload is always required anyway.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kernel/fpsimd.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8b111b7f2006..e00d3a9e919c 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1762,6 +1762,15 @@ static void fpsimd_flush_cpu_state(void) { WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); + + /* + * Leaving streaming mode enabled will cause issues for any kernel + * NEON and leaving streaming mode or ZA enabled may increase power + * consumption. + */ + if (system_supports_sme()) + sme_smstop(); + set_thread_flag(TIF_FOREIGN_FPSTATE); }

When saving and restoring the floating point state over an EFI runtime call ensure that we handle streaming mode, only handling FFR if we are not in streaming mode and ensuring that we are in normal mode over the call into runtime services.

We currently assume that ZA will not be modified by runtime services, the specification is not yet finalised so this may need updating if that changes.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kernel/fpsimd.c | 47 +++++++++++++++++++++++++++++++++----- 1 file changed, 41 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index e00d3a9e919c..a7077a5d1ed2 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1059,21 +1059,25 @@ int vec_verify_vq_map(enum vec_type type)

static void __init sve_efi_setup(void) { - struct vl_info *info = &vl_info[ARM64_VEC_SVE]; + int max_vl = 0; + int i;

if (!IS_ENABLED(CONFIG_EFI)) return;

+ for (i = 0; i < ARRAY_SIZE(vl_info); i++) + max_vl = max(vl_info[i].max_vl, max_vl); + /* * alloc_percpu() warns and prints a backtrace if this goes wrong. * This is evidence of a crippled system and we are returning void, * so no attempt is made to handle this situation here. */ - if (!sve_vl_valid(info->max_vl)) + if (!sve_vl_valid(max_vl)) goto fail;

efi_sve_state = __alloc_percpu( - SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES); + SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES); if (!efi_sve_state) goto fail;

@@ -1848,6 +1852,7 @@ EXPORT_SYMBOL(kernel_neon_end); static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state); static DEFINE_PER_CPU(bool, efi_fpsimd_state_used); static DEFINE_PER_CPU(bool, efi_sve_state_used); +static DEFINE_PER_CPU(bool, efi_sm_state);

/* * EFI runtime services support functions @@ -1882,12 +1887,28 @@ void __efi_fpsimd_begin(void) */ if (system_supports_sve() && likely(efi_sve_state)) { char *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + u64 svcr;

__this_cpu_write(efi_sve_state_used, true);

+ /* If we are in streaming mode don't touch FFR */ + if (system_supports_sme()) { + svcr = read_sysreg_s(SYS_SVCR_EL0); + + ffr = svcr & SYS_SVCR_EL0_SM_MASK; + + __this_cpu_write(efi_sm_state, ffr); + } + sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr); + + if (system_supports_sme()) + sysreg_clear_set_s(SYS_SVCR_EL0, + SYS_SVCR_EL0_SM_MASK, 0); + } else { fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state)); } @@ -1910,11 +1931,25 @@ void __efi_fpsimd_end(void) if (system_supports_sve() && likely(__this_cpu_read(efi_sve_state_used))) { char const *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + + /* + * Restore streaming mode; EFI calls are + * normal function calls so should not return in + * streaming mode. + */ + if (system_supports_sme()) { + if (__this_cpu_read(efi_sm_state)) { + sysreg_clear_set_s(SYS_SVCR_EL0, + 0, + SYS_SVCR_EL0_SM_MASK); + ffr = false; + } + }

- sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1); sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr);

__this_cpu_write(efi_sve_state_used, false); } else {

For the time being we do not support use of SME by KVM guests, support for this will be enabled in future. In order to prevent any side effects or side channels via the new system registers, including the EL0 read/write register TPIDR2, explicitly undefine all the system registers added by SME and mask out the SME bitfield in SYS_ID_AA64PFR1.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kvm/sys_regs.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 4dc2fba316ff..43516eda9143 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1089,6 +1089,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, case SYS_ID_AA64PFR1_EL1: if (!kvm_has_mte(vcpu->kvm)) val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE); + + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_SME); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) @@ -1508,7 +1510,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), ID_SANITISED(ID_AA64ZFR0_EL1), - ID_UNALLOCATED(4,5), + ID_HIDDEN(ID_AA64SMFR0_EL1), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7),

@@ -1551,6 +1553,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {

{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TRFCR_EL1), undef_access }, + { SYS_DESC(SYS_SMPRI_EL1), undef_access }, + { SYS_DESC(SYS_SMCR_EL1), undef_access }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 }, { SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 }, @@ -1633,8 +1637,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {

{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, { SYS_DESC(SYS_CLIDR_EL1), access_clidr }, + { SYS_DESC(SYS_SMIDR_EL1), undef_access }, { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, + { SYS_DESC(SYS_SVCR_EL0), undef_access },

{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr, .reg = PMCR_EL0 }, @@ -1674,6 +1680,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {

{ 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 },

{ SYS_DESC(SYS_SCXTNUM_EL0), undef_access },

SME defines two new traps which need to be enabled for guests to ensure that they can't use SME, one for the main SME operations which mirrors the traps for SVE and another for access to TPIDR2 in SCTLR_EL2.

For VHE manage SMEN along with ZEN in activate_traps() and the FP state management callbacks, along with SCTLR_EL2.EnTPIDR2. There is no existing dynamic management of SCTLR_EL2.

For nVHE manage TSM in activate_traps() along with the fine grained traps for TPIDR2 and SMPRI. There is no existing dynamic management of fine grained traps.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kvm/hyp/nvhe/switch.c | 30 ++++++++++++++++++++++++++++++ arch/arm64/kvm/hyp/vhe/switch.c | 11 ++++++++++- 2 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6410d21d8695..caace61ea459 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -47,10 +47,24 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val |= CPTR_EL2_TFP | CPTR_EL2_TZ; __activate_traps_fpsimd32(vcpu); } + if (cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM;

write_sysreg(val, cptr_el2); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);

+ if (cpus_have_final_cap(ARM64_SME)) { + val = read_sysreg_s(SYS_HFGRTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;

@@ -94,9 +108,25 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)

write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);

+ if (cpus_have_final_cap(ARM64_SME)) { + u64 val; + + val = read_sysreg_s(SYS_HFGRTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + cptr = CPTR_EL2_DEFAULT; if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)) cptr |= CPTR_EL2_TZ; + if (cpus_have_final_cap(ARM64_SME)) + cptr &= ~CPTR_EL2_TSM;

write_sysreg(cptr, cptr_el2); write_sysreg(__kvm_hyp_host_vector, vbar_el2); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 619353b06e38..a4d2fb5c9710 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -38,7 +38,8 @@ static void __activate_traps(struct kvm_vcpu *vcpu)

val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; - val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN); + val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | + CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);

/* * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to @@ -59,6 +60,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); }

+ if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(val, cpacr_el1);

write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); @@ -80,6 +85,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));

+ if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); write_sysreg(vectors, vbar_el1); }

While we don't currently support SME in guests we do currently support it for the host system so we need to take care of SME's impact, including the floating point register state, when running guests. Simiarly to SVE we need to manage the traps in CPACR_RL1, what is new is the handling of streaming mode and ZA.

Normally we defer any handling of the floating point register state until the guest first uses it however if the system is in streaming mode FPSIMD and SVE operations may generate SME traps which we would need to distinguish from actual attempts by the guest to use SME. Rather than do this for the time being if we are in streaming mode when entering the guest we force the floating point state to be saved immediately and exit streaming mode, meaning that the guest won't generate SME traps for supported operations.

We could handle ZA in the access trap similarly to the FPSIMD/SVE state without the disruption caused by streaming mode but for simplicity handle it the same way as streaming mode for now.

This will be revisited when we support SME for guests (hopefully before SME hardware becomes available), for now it will only incur additional cost on systems with SME and even there only if streaming mode or ZA are enabled.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 1 + arch/arm64/kvm/fpsimd.c | 36 +++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7dc85d5a6552..404b7358ba96 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -438,6 +438,7 @@ struct kvm_vcpu_arch { #define KVM_ARM64_DEBUG_STATE_SAVE_SPE (1 << 12) /* Save SPE context if active */ #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ #define KVM_ARM64_FP_FOREIGN_FPSTATE (1 << 14) +#define KVM_ARM64_HOST_SME_ENABLED (1 << 15) /* SME enabled for EL0 */

#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 338733ac63f8..1c585553d74f 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -82,6 +82,26 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)

if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; + + /* + * We don't currently support SME guests but if we leave + * things in streaming mode then when the guest starts running + * FPSIMD or SVE code it may generate SME traps so as a + * special case if we are in streaming mode we force the host + * state to be saved now and exit streaming mode so that we + * don't have to handle any SME traps for valid guest + * operations. Do this for ZA as well for now for simplicity. + */ + if (system_supports_sme()) { + if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) + vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED; + + if (read_sysreg_s(SYS_SVCR_EL0) & + (SYS_SVCR_EL0_SM_MASK | SYS_SVCR_EL0_ZA_MASK)) { + vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; + fpsimd_save_and_flush_cpu_state(); + } + } }

void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu) @@ -129,6 +149,22 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)

local_irq_save(flags);

+ /* + * If we have VHE then the Hyp code will reset CPACR_EL1 to + * CPACR_EL1_DEFAULT and we need to reenable SME. + */ + if (has_vhe() && system_supports_sme()) { + /* Also restore EL0 state seen on entry */ + if (vcpu->arch.flags & KVM_ARM64_HOST_SME_ENABLED) + sysreg_clear_set(CPACR_EL1, 0, + CPACR_EL1_SMEN_EL0EN | + CPACR_EL1_SMEN_EL1EN); + else + sysreg_clear_set(CPACR_EL1, + CPACR_EL1_SMEN_EL0EN, + CPACR_EL1_SMEN_EL1EN); + } + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { if (vcpu_has_sve(vcpu)) { __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);

Now that basline support for the Scalable Matrix Extension (SME) is present introduce the Kconfig option allowing it to be built. While the feature registers don't impose a strong requirement for a system with SME to support SVE at runtime the support for streaming mode SVE is mostly shared with normal SVE so depend on SVE.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/Kconfig | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index cbcd42decb2a..4fd7574866cc 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1924,6 +1924,17 @@ config ARM64_SVE booting the kernel. If unsure and you are not observing these symptoms, you should assume that it is safe to say Y.

+config ARM64_SME + bool "ARM Scalable Matrix Extension support" + default y + depends on ARM64_SVE + help + The Scalable Matrix Extension (SME) is an extension to the AArch64 + execution state which utilises a substantial subset of the SVE + instruction set, together with the addition of new architectural + register state capable of holding two dimensional matrix tiles to + enable various matrix operations. + config ARM64_MODULE_PLTS bool "Use PLTs to allow module memory to spill over into vmalloc area" depends on MODULES

As for the kernel so that we don't have ambitious toolchain requirements to build the tests manually encode some of the SVE instructions.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/fp/sme-inst.h | 51 +++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 tools/testing/selftests/arm64/fp/sme-inst.h

diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h new file mode 100644 index 000000000000..7191e53ca1c0 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/sme-inst.h @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021-2 ARM Limited. +// Original author: Mark Brown broonie@kernel.org + +#ifndef SME_INST_H +#define SME_INST_H + +/* + * RDSVL X\nx, #\imm + */ +.macro rdsvl nx, imm + .inst 0x4bf5800 \ + | (\imm << 5) \ + | (\nx) +.endm + +.macro smstop + msr S0_3_C4_C6_3, xzr +.endm + +.macro smstart_za + msr S0_3_C4_C5_3, xzr +.endm + +.macro smstart_sm + msr S0_3_C4_C3_3, xzr +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _ldr_za nw, nxbase, offset=0 + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _str_za nw, nxbase, offset=0 + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +#endif

One of the features of SME is the addition of streaming mode, in which we have access to a set of streaming mode SVE registers at the SME vector length. Since these are accessed using the SVE instructions let's reuse the existing SVE stress test for testing with a compile time option for controlling the few small differences needed:

- Enter streaming mode immediately on starting the program. - In streaming mode FFR is removed so skip reading and writing FFR.

In order to avoid requiring a cutting edge toolchain with SME support use the op/CR form for specifying SVCR.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/fp/.gitignore | 1 + tools/testing/selftests/arm64/fp/Makefile | 3 + tools/testing/selftests/arm64/fp/ssve-stress | 59 ++++++++++++++++++++ tools/testing/selftests/arm64/fp/sve-test.S | 20 +++++++ 4 files changed, 83 insertions(+) create mode 100644 tools/testing/selftests/arm64/fp/ssve-stress

diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index 6e9a610c5e5d..5729a5b1adfc 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -5,5 +5,6 @@ rdvl-sve sve-probe-vls sve-ptrace sve-test +ssve-test vec-syscfg vlset diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index a224fff8082b..e6643c9b0474 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -5,6 +5,7 @@ TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \ rdvl-sme rdvl-sve \ sve-test sve-stress \ + ssve-test ssve-stress \ vlset

all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) @@ -19,6 +20,8 @@ sve-ptrace: sve-ptrace.o sve-probe-vls: sve-probe-vls.o rdvl.o sve-test: sve-test.o asm-utils.o $(CC) -nostdlib $^ -o $@ +ssve-test: sve-test.S asm-utils.o + $(CC) -DSSVE -nostdlib $^ -o $@ vec-syscfg: vec-syscfg.o rdvl.o vlset: vlset.o

diff --git a/tools/testing/selftests/arm64/fp/ssve-stress b/tools/testing/selftests/arm64/fp/ssve-stress new file mode 100644 index 000000000000..e2bd2cc184ad --- /dev/null +++ b/tools/testing/selftests/arm64/fp/ssve-stress @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2015-2019 ARM Limited. +# Original author: Dave Martin Dave.Martin@arm.com + +set -ue + +NR_CPUS=`nproc` + +pids= +logs= + +cleanup () { + trap - INT TERM CHLD + set +e + + if [ -n "$pids" ]; then + kill $pids + wait $pids + pids= + fi + + if [ -n "$logs" ]; then + cat $logs + rm $logs + logs= + fi +} + +interrupt () { + cleanup + exit 0 +} + +child_died () { + cleanup + exit 1 +} + +trap interrupt INT TERM EXIT + +for x in `seq 0 $((NR_CPUS * 4))`; do + log=`mktemp` + logs=$logs\ $log + ./ssve-test >$log & + pids=$pids\ $! +done + +# Wait for all child processes to be created: +sleep 10 + +while :; do + kill -USR1 $pids +done & +pids=$pids\ $! + +wait + +exit 1 diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index f5b1b48ffff2..589264231a2d 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -13,6 +13,7 @@ #include <asm/unistd.h> #include "assembler.h" #include "asm-offsets.h" +#include "sme-inst.h"

#define NZR 32 #define NPR 16 @@ -156,6 +157,7 @@ endfunction // We fill the upper lanes of FFR with zeros. // Beware: corrupts P0. function setup_ffr +#ifndef SSVE mov x4, x30

and w0, w0, #0x3 @@ -178,6 +180,9 @@ function setup_ffr wrffr p0.b

ret x4 +#else + ret +#endif endfunction

// Trivial memory compare: compare x2 bytes starting at address x0 with @@ -260,6 +265,7 @@ endfunction // Beware -- corrupts P0. // Clobbers x0-x5. function check_ffr +#ifndef SSVE mov x3, x30

ldr x4, =scratch @@ -280,6 +286,9 @@ function check_ffr mov x2, x5 mov x30, x3 b memcmp +#else + ret +#endif endfunction

// Any SVE register modified here can cause corruption in the main @@ -295,10 +304,12 @@ function irritator_handler movi v0.8b, #1 movi v9.16b, #2 movi v31.8b, #3 +#ifndef SSVE // And P0 rdffr p0.b // And FFR wrffr p15.b +#endif

ret endfunction @@ -359,6 +370,11 @@ endfunction .globl _start function _start _start: +#ifdef SSVE + puts "Streaming mode " + smstart_sm +#endif + // Sanity-check and report the vector length

rdvl x19, #8 @@ -407,6 +423,10 @@ _start: orr w2, w2, #SA_NODEFER bl setsignal

+#ifdef SSVE + smstart_sm // syscalls will have exited streaming mode +#endif + mov x22, #0 // generation number, increments per iteration .Ltest_loop: rdvl x0, #8

As part of the generic code for signal handling test cases we parse all signal frames to make sure they have at least the basic form we expect and that there are no unexpected frames present in the signal context. Add coverage of the ZA signal frame to this code.

Signed-off-by: Mark Brown broonie@kernel.org --- .../arm64/signal/testcases/testcases.c | 36 +++++++++++++++++++ .../arm64/signal/testcases/testcases.h | 3 +- 2 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c index 8c2a57fc2f9c..84c36bee4d82 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.c +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -75,6 +75,31 @@ bool validate_sve_context(struct sve_context *sve, char **err) return true; }

+bool validate_za_context(struct za_context *za, char **err) +{ + /* Size will be rounded up to a multiple of 16 bytes */ + size_t regs_size + = ((ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za->vl)) + 15) / 16) * 16; + + if (!za || !err) + return false; + + /* Either a bare za_context or a za_context followed by regs data */ + if ((za->head.size != sizeof(struct za_context)) && + (za->head.size != regs_size)) { + *err = "bad size for ZA context"; + return false; + } + + if (!sve_vl_valid(za->vl)) { + *err = "SME VL in ZA context invalid"; + + return false; + } + + return true; +} + bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) { bool terminated = false; @@ -82,6 +107,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) int flags = 0; struct extra_context *extra = NULL; struct sve_context *sve = NULL; + struct za_context *za = NULL; struct _aarch64_ctx *head = (struct _aarch64_ctx *)uc->uc_mcontext.__reserved;

@@ -120,6 +146,13 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) sve = (struct sve_context *)head; flags |= SVE_CTX; break; + case ZA_MAGIC: + if (flags & ZA_CTX) + *err = "Multiple ZA_MAGIC"; + /* Size is validated in validate_za_context() */ + za = (struct za_context *)head; + flags |= ZA_CTX; + break; case EXTRA_MAGIC: if (flags & EXTRA_CTX) *err = "Multiple EXTRA_MAGIC"; @@ -165,6 +198,9 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) if (flags & SVE_CTX) if (!validate_sve_context(sve, err)) return false; + if (flags & ZA_CTX) + if (!validate_za_context(za, err)) + return false;

head = GET_RESV_NEXT_HEAD(head); } diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h index ad884c135314..49f1d5de7b5b 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.h +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h @@ -16,7 +16,8 @@

#define FPSIMD_CTX (1 << 0) #define SVE_CTX (1 << 1) -#define EXTRA_CTX (1 << 2) +#define ZA_CTX (1 << 2) +#define EXTRA_CTX (1 << 3)

#define KSFT_BAD_MAGIC 0xdeadbeef

Add a stress test for context switching of the ZA register state based on the similar tests Dave Martin wrote for FPSIMD and SVE registers. The test loops indefinitely writing a data pattern to ZA then reading it back and verifying that it's what was expected.

Unlike the other tests we manually assemble the SME instructions since at present no released toolchain has SME support integrated.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/arm64/fp/.gitignore | 1 + tools/testing/selftests/arm64/fp/Makefile | 3 + tools/testing/selftests/arm64/fp/za-stress | 59 +++ tools/testing/selftests/arm64/fp/za-test.S | 388 ++++++++++++++++++++ 4 files changed, 451 insertions(+) create mode 100644 tools/testing/selftests/arm64/fp/za-stress create mode 100644 tools/testing/selftests/arm64/fp/za-test.S

diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index 5729a5b1adfc..ead3197e720b 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -8,3 +8,4 @@ sve-test ssve-test vec-syscfg vlset +za-test diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index e6643c9b0474..38d2d0d5a0eb 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -6,6 +6,7 @@ TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \ rdvl-sme rdvl-sve \ sve-test sve-stress \ ssve-test ssve-stress \ + za-test za-stress \ vlset

all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) @@ -24,5 +25,7 @@ ssve-test: sve-test.S asm-utils.o $(CC) -DSSVE -nostdlib $^ -o $@ vec-syscfg: vec-syscfg.o rdvl.o vlset: vlset.o +za-test: za-test.o asm-utils.o + $(CC) -nostdlib $^ -o $@

include ../../lib.mk diff --git a/tools/testing/selftests/arm64/fp/za-stress b/tools/testing/selftests/arm64/fp/za-stress new file mode 100644 index 000000000000..5ac386b55b95 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-stress @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2015-2019 ARM Limited. +# Original author: Dave Martin Dave.Martin@arm.com + +set -ue + +NR_CPUS=`nproc` + +pids= +logs= + +cleanup () { + trap - INT TERM CHLD + set +e + + if [ -n "$pids" ]; then + kill $pids + wait $pids + pids= + fi + + if [ -n "$logs" ]; then + cat $logs + rm $logs + logs= + fi +} + +interrupt () { + cleanup + exit 0 +} + +child_died () { + cleanup + exit 1 +} + +trap interrupt INT TERM EXIT + +for x in `seq 0 $((NR_CPUS * 4))`; do + log=`mktemp` + logs=$logs\ $log + ./za-test >$log & + pids=$pids\ $! +done + +# Wait for all child processes to be created: +sleep 10 + +while :; do + kill -USR1 $pids +done & +pids=$pids\ $! + +wait + +exit 1 diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S new file mode 100644 index 000000000000..9ab6f9cd9623 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/za-test.S @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021 ARM Limited. +// Original author: Mark Brown broonie@kernel.org +// +// Scalable Matrix Extension ZA context switch test +// Repeatedly writes unique test patterns into each ZA tile +// and reads them back to verify integrity. +// +// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done +// (leave it running for as long as you want...) +// kill $pids + +#include <asm/unistd.h> +#include "assembler.h" +#include "asm-offsets.h" +#include "sme-inst.h" + +.arch_extension sve + +#define MAXVL 2048 +#define MAXVL_B (MAXVL / 8) + +// Declare some storage space to shadow ZA register contents and a +// scratch buffer for a vector. +.pushsection .text +.data +.align 4 +zaref: + .space MAXVL_B * MAXVL_B +scratch: + .space MAXVL_B +.popsection + +// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. +// Clobbers x0-x3 +function memcpy + cmp x2, #0 + b.eq 1f +0: ldrb w3, [x1], #1 + strb w3, [x0], #1 + subs x2, x2, #1 + b.ne 0b +1: ret +endfunction + +// Generate a test pattern for storage in ZA +// x0: pid +// x1: row in ZA +// x2: generation + +// These values are used to constuct a 32-bit pattern that is repeated in the +// scratch buffer as many times as will fit: +// bits 31:28 generation number (increments once per test_loop) +// bits 27:16 pid +// bits 15: 8 row number +// bits 7: 0 32-bit lane index + +function pattern + mov w3, wzr + bfi w3, w0, #16, #12 // PID + bfi w3, w1, #8, #8 // Row + bfi w3, w2, #28, #4 // Generation + + ldr x0, =scratch + mov w1, #MAXVL_B / 4 + +0: str w3, [x0], #4 + add w3, w3, #1 // Lane + subs w1, w1, #1 + b.ne 0b + + ret +endfunction + +// Get the address of shadow data for ZA horizontal vector xn +.macro _adrza xd, xn, nrtmp + ldr \xd, =zaref + rdsvl \nrtmp, 1 + madd \xd, x\nrtmp, \xn, \xd +.endm + +// Set up test pattern in a ZA horizontal vector +// x0: pid +// x1: row number +// x2: generation +function setup_za + mov x4, x30 + mov x12, x1 // Use x12 for vector select + + bl pattern // Get pattern in scratch buffer + _adrza x0, x12, 2 // Shadow buffer pointer to x0 and x5 + mov x5, x0 + ldr x1, =scratch + bl memcpy // length set up in x2 by _adrza + + _ldr_za 12, 5 // load vector w12 from pointer x5 + + ret x4 +endfunction + +// Trivial memory compare: compare x2 bytes starting at address x0 with +// bytes starting at address x1. +// Returns only if all bytes match; otherwise, the program is aborted. +// Clobbers x0-x5. +function memcmp + cbz x2, 2f + + stp x0, x1, [sp, #-0x20]! + str x2, [sp, #0x10] + + mov x5, #0 +0: ldrb w3, [x0, x5] + ldrb w4, [x1, x5] + add x5, x5, #1 + cmp w3, w4 + b.ne 1f + subs x2, x2, #1 + b.ne 0b + +1: ldr x2, [sp, #0x10] + ldp x0, x1, [sp], #0x20 + b.ne barf + +2: ret +endfunction + +// Verify that a ZA vector matches its shadow in memory, else abort +// x0: row number +// Clobbers x0-x7 and x12. +function check_za + mov x3, x30 + + mov x12, x0 + _adrza x5, x0, 6 // pointer to expected value in x5 + mov x4, x0 + ldr x7, =scratch // x7 is scratch + + mov x0, x7 // Poison scratch + mov x1, x6 + bl memfill_ae + + _str_za 12, 7 // save vector w12 to pointer x7 + + mov x0, x5 + mov x1, x7 + mov x2, x6 + mov x30, x3 + b memcmp +endfunction + +// Any SME register modified here can cause corruption in the main +// thread -- but *only* the locations modified here. +function irritator_handler + // Increment the irritation signal count (x23): + ldr x0, [x2, #ucontext_regs + 8 * 23] + add x0, x0, #1 + str x0, [x2, #ucontext_regs + 8 * 23] + + // Corrupt some random ZA data +#if 0 + adr x0, .text + (irritator_handler - .text) / 16 * 16 + movi v0.8b, #1 + movi v9.16b, #2 + movi v31.8b, #3 +#endif + + ret +endfunction + +function terminate_handler + mov w21, w0 + mov x20, x2 + + puts "Terminated by signal " + mov w0, w21 + bl putdec + puts ", no error, iterations=" + ldr x0, [x20, #ucontext_regs + 8 * 22] + bl putdec + puts ", signals=" + ldr x0, [x20, #ucontext_regs + 8 * 23] + bl putdecn + + mov x0, #0 + mov x8, #__NR_exit + svc #0 +endfunction + +// w0: signal number +// x1: sa_action +// w2: sa_flags +// Clobbers x0-x6,x8 +function setsignal + str x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]! + + mov w4, w0 + mov x5, x1 + mov w6, w2 + + add x0, sp, #16 + mov x1, #sa_sz + bl memclr + + mov w0, w4 + add x1, sp, #16 + str w6, [x1, #sa_flags] + str x5, [x1, #sa_handler] + mov x2, #0 + mov x3, #sa_mask_sz + mov x8, #__NR_rt_sigaction + svc #0 + + cbz w0, 1f + + puts "sigaction failure\n" + b .Labort + +1: ldr x30, [sp], #((sa_sz + 15) / 16 * 16 + 16) + ret +endfunction + +// Main program entry point +.globl _start +function _start +_start: + puts "Streaming mode " + smstart_za + + // Sanity-check and report the vector length + + rdsvl 19, 8 + cmp x19, #128 + b.lo 1f + cmp x19, #2048 + b.hi 1f + tst x19, #(8 - 1) + b.eq 2f + +1: puts "bad vector length: " + mov x0, x19 + bl putdecn + b .Labort + +2: puts "vector length:\t" + mov x0, x19 + bl putdec + puts " bits\n" + + // Obtain our PID, to ensure test pattern uniqueness between processes + mov x8, #__NR_getpid + svc #0 + mov x20, x0 + + puts "PID:\t" + mov x0, x20 + bl putdecn + + mov x23, #0 // Irritation signal count + + mov w0, #SIGINT + adr x1, terminate_handler + mov w2, #SA_SIGINFO + bl setsignal + + mov w0, #SIGTERM + adr x1, terminate_handler + mov w2, #SA_SIGINFO + bl setsignal + + mov w0, #SIGUSR1 + adr x1, irritator_handler + mov w2, #SA_SIGINFO + orr w2, w2, #SA_NODEFER + bl setsignal + + mov x22, #0 // generation number, increments per iteration +.Ltest_loop: + rdsvl 0, 8 + cmp x0, x19 + b.ne vl_barf + + rdsvl 21, 1 // Set up ZA & shadow with test pattern +0: mov x0, x20 + sub x1, x21, #1 + mov x2, x22 + bl setup_za + subs x21, x21, #1 + b.ne 0b + + and x8, x22, #127 // Every 128 interations... + cbz x8, 0f + mov x8, #__NR_getpid // (otherwise minimal syscall) + b 1f +0: + mov x8, #__NR_sched_yield // ...encourage preemption +1: + svc #0 + + mrs x0, S3_3_C4_C2_2 // SVCR should have ZA=1,SM=0 + and x1, x0, #3 + cmp x1, #2 + b.ne svcr_barf + + rdsvl 21, 1 // Verify that the data made it through + rdsvl 24, 1 // Verify that the data made it through +0: sub x0, x24, x21 + bl check_za + subs x21, x21, #1 + bne 0b + + add x22, x22, #1 // Everything still working + b .Ltest_loop + +.Labort: + mov x0, #0 + mov x1, #SIGABRT + mov x8, #__NR_kill + svc #0 +endfunction + +function barf +// fpsimd.c acitivty log dump hack +// ldr w0, =0xdeadc0de +// mov w8, #__NR_exit +// svc #0 +// end hack + smstop + mov x10, x0 // expected data + mov x11, x1 // actual data + mov x12, x2 // data size + + puts "Mismatch: PID=" + mov x0, x20 + bl putdec + puts ", iteration=" + mov x0, x22 + bl putdec + puts ", row=" + mov x0, x21 + bl putdecn + puts "\tExpected [" + mov x0, x10 + mov x1, x12 + bl dumphex + puts "]\n\tGot [" + mov x0, x11 + mov x1, x12 + bl dumphex + puts "]\n" + + mov x8, #__NR_getpid + svc #0 +// fpsimd.c acitivty log dump hack +// ldr w0, =0xdeadc0de +// mov w8, #__NR_exit +// svc #0 +// ^ end of hack + mov x1, #SIGABRT + mov x8, #__NR_kill + svc #0 +// mov x8, #__NR_exit +// mov x1, #1 +// svc #0 +endfunction + +function vl_barf + mov x10, x0 + + puts "Bad active VL: " + mov x0, x10 + bl putdecn + + mov x8, #__NR_exit + mov x1, #1 + svc #0 +endfunction + +function svcr_barf + mov x10, x0 + + puts "Bad SVCR: " + mov x0, x10 + bl putdecn + + mov x8, #__NR_exit + mov x1, #1 + svc #0 +endfunction

Add test cases for the SME signal handing ABI patterned off the SVE tests. Due to the small size of the tests and the differences in ABI (especially around needing to account for both streaming SVE and ZA) there is some code duplication here.

We currently cover: - Reporting of the vector length. - Lack of support for changing vector length. - Presence and size of register state for streaming SVE and ZA.

As with the SVE tests we do not yet have any validation of register contents.

Signed-off-by: Mark Brown broonie@kernel.org --- .../testing/selftests/arm64/signal/.gitignore | 2 + .../selftests/arm64/signal/test_signals.h | 4 + .../arm64/signal/test_signals_utils.c | 6 + .../testcases/fake_sigreturn_sme_change_vl.c | 92 +++++++++++++ .../arm64/signal/testcases/sme_trap_no_sm.c | 38 ++++++ .../signal/testcases/sme_trap_non_streaming.c | 45 ++++++ .../arm64/signal/testcases/sme_trap_za.c | 36 +++++ .../selftests/arm64/signal/testcases/sme_vl.c | 68 +++++++++ .../arm64/signal/testcases/ssve_regs.c | 129 ++++++++++++++++++ 9 files changed, 420 insertions(+) create mode 100644 tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c create mode 100644 tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c create mode 100644 tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c create mode 100644 tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c create mode 100644 tools/testing/selftests/arm64/signal/testcases/sme_vl.c create mode 100644 tools/testing/selftests/arm64/signal/testcases/ssve_regs.c

diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index c1742755abb9..4de8eb26d4de 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* +sme_* +ssve_* sve_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index f909b70d9e98..c70fdec7d7c4 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -34,11 +34,15 @@ enum { FSSBS_BIT, FSVE_BIT, + FSME_BIT, + FSME_FA64_BIT, FMAX_END };

#define FEAT_SSBS (1UL << FSSBS_BIT) #define FEAT_SVE (1UL << FSVE_BIT) +#define FEAT_SME (1UL << FSME_BIT) +#define FEAT_SME_FA64 (1UL << FSME_FA64_BIT)

/* * A descriptor used to describe and configure a test case. diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 5743897984b0..b588d10afd5b 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -27,6 +27,8 @@ static int sig_copyctx = SIGTRAP; static char const *const feats_names[FMAX_END] = { " SSBS ", " SVE ", + " SME ", + " FA64 ", };

#define MAX_FEATS_SZ 128 @@ -268,6 +270,10 @@ int test_init(struct tdescr *td) td->feats_supported |= FEAT_SSBS; if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; + if (getauxval(AT_HWCAP2) & HWCAP2_SME) + td->feats_supported |= FEAT_SME; + if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64) + td->feats_supported |= FEAT_SME_FA64; if (feats_ok(td)) { if (td->feats_required & td->feats_supported) fprintf(stderr, diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c new file mode 100644 index 000000000000..7ed762b7202f --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Attempt to change the streaming SVE vector length in a signal + * handler, this is not supported and is expected to segfault. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sme_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SVE_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SME_VL_LEN_MASK; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least two VLs */ + if (nvls < 2) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static int fake_sigreturn_ssve_change_vl(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *sve; + + /* Get a signal context with a SME ZA frame in it */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + if (head->size != sizeof(struct sve_context)) { + fprintf(stderr, "Register data present, aborting\n"); + return 1; + } + + sve = (struct sve_context *)head; + + /* No changes are supported; init left us at minimum VL so go to max */ + fprintf(stderr, "Attempting to change VL from %d to %d\n", + sve->vl, vls[0]); + sve->vl = vls[0]; + + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_SSVE_CHANGE", + .descr = "Attempt to change Streaming SVE VL", + .feats_required = FEAT_SME, + .sig_ok = SIGSEGV, + .timeout = 3, + .init = sme_get_vls, + .run = fake_sigreturn_ssve_change_vl, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c new file mode 100644 index 000000000000..f9d76ae32bba --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that using a streaming mode instruction without enabling it + * generates a SIGILL. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_no_sm_trigger(struct tdescr *td) +{ + /* SMSTART ZA ; ADDHA ZA0.S, P0/M, P0/M, Z0.S */ + asm volatile(".inst 0xd503457f ; .inst 0xc0900000"); + + return 0; +} + +int sme_trap_no_sm_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME trap without SM", + .descr = "Check that we get a SIGILL if we use streaming mode without enabling it", + .timeout = 3, + .feats_required = FEAT_SME, /* We need a SMSTART ZA */ + .sanity_disabled = true, + .trigger = sme_trap_no_sm_trigger, + .run = sme_trap_no_sm_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c new file mode 100644 index 000000000000..e469ae5348e3 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that using an instruction not supported in streaming mode + * traps when in streaming mode. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_non_streaming_trigger(struct tdescr *td) +{ + /* + * The framework will handle SIGILL so we need to exit SM to + * stop any other code triggering a further SIGILL down the + * line from using a streaming-illegal instruction. + */ + asm volatile(".inst 0xd503437f; /* SMSTART ZA */ \ + cnt v0.16b, v0.16b; \ + .inst 0xd503447f /* SMSTOP ZA */"); + + return 0; +} + +int sme_trap_non_streaming_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME SM trap unsupported instruction", + .descr = "Check that we get a SIGILL if we use an unsupported instruction in streaming mode", + .feats_required = FEAT_SME, + .feats_incompatible = FEAT_SME_FA64, + .timeout = 3, + .sanity_disabled = true, + .trigger = sme_trap_non_streaming_trigger, + .run = sme_trap_non_streaming_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c new file mode 100644 index 000000000000..3a7747af4715 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that accessing ZA without enabling it generates a SIGILL. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +int sme_trap_za_trigger(struct tdescr *td) +{ + /* ZERO ZA */ + asm volatile(".inst 0xc00800ff"); + + return 0; +} + +int sme_trap_za_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + return 1; +} + +struct tdescr tde = { + .name = "SME ZA trap", + .descr = "Check that we get a SIGILL if we access ZA without enabling", + .timeout = 3, + .sanity_disabled = true, + .trigger = sme_trap_za_trigger, + .run = sme_trap_za_run, + .sig_ok = SIGILL, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_vl.c b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c new file mode 100644 index 000000000000..13ff3b35cbaf --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Check that the SME vector length reported in signal contexts is the + * expected one. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +unsigned int vl; + +static bool get_sme_vl(struct tdescr *td) +{ + int ret = prctl(PR_SME_GET_VL); + if (ret == -1) + return false; + + vl = ret; + + return true; +} + +static int sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct za_context *za; + + /* Get a signal context which should have a ZA frame in it */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, ZA_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No ZA context\n"); + return 1; + } + za = (struct za_context *)head; + + if (za->vl != vl) { + fprintf(stderr, "ZA sigframe VL %u, expected %u\n", + za->vl, vl); + return 1; + } else { + fprintf(stderr, "got expected VL %u\n", vl); + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "SME VL", + .descr = "Check that we get the right SME VL reported", + .feats_required = FEAT_SME, + .timeout = 3, + .init = get_sme_vl, + .run = sme_vl, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c new file mode 100644 index 000000000000..6150862a9cde --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that the streaming SVE register context in signal frames is + * set up as expected. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sme_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SVE_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SME_VL_LEN_MASK; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least one VL */ + if (nvls < 1) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static void setup_ssve_regs(void) +{ + /* SMSTART SM */ + asm volatile(".inst 0x7f4303d5"); + + /* RDVL x16, #1 so we should have SVE regs; real data is TODO */ + asm volatile(".inst 0x04bf5030" : : : "x16" ); +} + +static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, + unsigned int vl) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + struct sve_context *ssve; + + fprintf(stderr, "Testing VL %d\n", vl); + + if (prctl(PR_SME_SET_VL, vl) == -1) { + fprintf(stderr, "Failed to set VL\n"); + return 1; + } + + /* + * Get a signal context which should have a SVE frame and registers + * in it. + */ + setup_ssve_regs(); + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, SVE_MAGIC, resv_sz, &offset); + if (!head) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + ssve = (struct sve_context *)head; + if (ssve->vl != vl) { + fprintf(stderr, "Got VL %d, expected %d\n", ssve->vl, vl); + return 1; + } + + /* The actual size validation is done in get_current_context() */ + fprintf(stderr, "Got expected size %u and VL %d\n", + head->size, ssve->vl); + + return 0; +} + +static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + int i; + + for (i = 0; i < nvls; i++) { + /* + * TODO: the signal test helpers can't currently cope + * with signal frames bigger than struct sigcontext, + * skip VLs that will trigger that. + */ + if (vls[i] > 64) + continue; + + if (do_one_sme_vl(td, si, uc, vls[i])) + return 1; + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "Streaming SVE registers", + .descr = "Check that we get the right Streaming SVE registers reported", + .feats_required = FEAT_SME, + .timeout = 3, + .init = sme_get_vls, + .run = sme_regs, +};