diff options
Diffstat (limited to 'arch/arm64/kernel')
38 files changed, 1338 insertions, 815 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 467cb71172..763824963e 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -33,8 +33,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ - syscall.o proton-pack.o idreg-override.o idle.o \ - patching.o + syscall.o proton-pack.o idle.o patching.o pi/ obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o @@ -57,7 +56,7 @@ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o obj-$(CONFIG_PARAVIRT) += paravirt.o -obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o pi/ +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_ELF_CORE) += elfcore.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \ @@ -66,20 +65,12 @@ obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o -obj-$(CONFIG_CRASH_CORE) += crash_core.o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o -obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o - -# We need to prevent the SCS patching code from patching itself. Using -# -mbranch-protection=none here to avoid the patchable PAC opcodes from being -# generated triggers an issue with full LTO on Clang, which stops emitting PAC -# instructions altogether. So disable LTO as well for the compilation unit. -CFLAGS_patch-scs.o += -mbranch-protection=none -CFLAGS_REMOVE_patch-scs.o += $(CC_FLAGS_LTO) # Force dependency (vdso*-wrap.S includes vdso.so through incbin) $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 5a7dbbe0ce..81496083c0 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,8 +75,8 @@ int main(void) DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); - DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); DEFINE(S_PC, offsetof(struct pt_regs, pc)); + DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 8d1a634a40..56583677c1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -140,12 +140,42 @@ void dump_cpu_features(void) pr_emerg("0x%*pb\n", ARM64_NCAPS, &system_cpucaps); } +#define __ARM64_MAX_POSITIVE(reg, field) \ + ((reg##_##field##_SIGNED ? \ + BIT(reg##_##field##_WIDTH - 1) : \ + BIT(reg##_##field##_WIDTH)) - 1) + +#define __ARM64_MIN_NEGATIVE(reg, field) BIT(reg##_##field##_WIDTH - 1) + +#define __ARM64_CPUID_FIELDS(reg, field, min_value, max_value) \ + .sys_reg = SYS_##reg, \ + .field_pos = reg##_##field##_SHIFT, \ + .field_width = reg##_##field##_WIDTH, \ + .sign = reg##_##field##_SIGNED, \ + .min_field_value = min_value, \ + .max_field_value = max_value, + +/* + * ARM64_CPUID_FIELDS() encodes a field with a range from min_value to + * an implicit maximum that depends on the sign-ess of the field. + * + * An unsigned field will be capped at all ones, while a signed field + * will be limited to the positive half only. + */ #define ARM64_CPUID_FIELDS(reg, field, min_value) \ - .sys_reg = SYS_##reg, \ - .field_pos = reg##_##field##_SHIFT, \ - .field_width = reg##_##field##_WIDTH, \ - .sign = reg##_##field##_SIGNED, \ - .min_field_value = reg##_##field##_##min_value, + __ARM64_CPUID_FIELDS(reg, field, \ + SYS_FIELD_VALUE(reg, field, min_value), \ + __ARM64_MAX_POSITIVE(reg, field)) + +/* + * ARM64_CPUID_FIELDS_NEG() encodes a field with a range from an + * implicit minimal value to max_value. This should be used when + * matching a non-implemented property. + */ +#define ARM64_CPUID_FIELDS_NEG(reg, field, max_value) \ + __ARM64_CPUID_FIELDS(reg, field, \ + __ARM64_MIN_NEGATIVE(reg, field), \ + SYS_FIELD_VALUE(reg, field, max_value)) #define __ARM64_FTR_BITS(SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ { \ @@ -220,6 +250,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_LUT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0), @@ -234,6 +265,11 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64isar3[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV2_SHIFT, 4, 0), @@ -267,6 +303,11 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64pfr2[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR2_EL1_FPMR_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, 0), @@ -295,6 +336,8 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_LUTv2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0), @@ -307,6 +350,10 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F16_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0), @@ -316,6 +363,22 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8FMA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8CVT_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, }; @@ -407,6 +470,11 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64mmfr4[] = { + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR4_EL1_E2H0_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_EL0_DIC_SHIFT, 1, 1), @@ -655,13 +723,15 @@ static const struct arm64_ftr_bits ftr_raz[] = { #define ARM64_FTR_REG(id, table) \ __ARM64_FTR_REG_OVERRIDE(#id, id, table, &no_override) -struct arm64_ftr_override __ro_after_init id_aa64mmfr1_override; -struct arm64_ftr_override __ro_after_init id_aa64pfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64pfr1_override; -struct arm64_ftr_override __ro_after_init id_aa64zfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64smfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64isar1_override; -struct arm64_ftr_override __ro_after_init id_aa64isar2_override; +struct arm64_ftr_override id_aa64mmfr0_override; +struct arm64_ftr_override id_aa64mmfr1_override; +struct arm64_ftr_override id_aa64mmfr2_override; +struct arm64_ftr_override id_aa64pfr0_override; +struct arm64_ftr_override id_aa64pfr1_override; +struct arm64_ftr_override id_aa64zfr0_override; +struct arm64_ftr_override id_aa64smfr0_override; +struct arm64_ftr_override id_aa64isar1_override; +struct arm64_ftr_override id_aa64isar2_override; struct arm64_ftr_override arm64_sw_feature_override; @@ -702,10 +772,12 @@ static const struct __ftr_reg_entry { &id_aa64pfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1, &id_aa64pfr1_override), + ARM64_FTR_REG(SYS_ID_AA64PFR2_EL1, ftr_id_aa64pfr2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0, &id_aa64zfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0, &id_aa64smfr0_override), + ARM64_FTR_REG(SYS_ID_AA64FPFR0_EL1, ftr_id_aa64fpfr0), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -717,13 +789,17 @@ static const struct __ftr_reg_entry { &id_aa64isar1_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), + ARM64_FTR_REG(SYS_ID_AA64ISAR3_EL1, ftr_id_aa64isar3), /* Op1 = 0, CRn = 0, CRm = 7 */ - ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0), + ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0, + &id_aa64mmfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1, &id_aa64mmfr1_override), - ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2), + ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2, + &id_aa64mmfr2_override), ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3), + ARM64_FTR_REG(SYS_ID_AA64MMFR4_EL1, ftr_id_aa64mmfr4), /* Op1 = 1, CRn = 0, CRm = 0 */ ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid), @@ -919,7 +995,8 @@ static void init_cpu_ftr_reg(u32 sys_reg, u64 new) pr_warn("%s[%d:%d]: %s to %llx\n", reg->name, ftrp->shift + ftrp->width - 1, - ftrp->shift, str, tmp); + ftrp->shift, str, + tmp & (BIT(ftrp->width) - 1)); } else if ((ftr_mask & reg->override->val) == ftr_mask) { reg->override->val &= ~ftr_mask; pr_warn("%s[%d:%d]: impossible override, ignored\n", @@ -1043,14 +1120,18 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0); init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1); init_cpu_ftr_reg(SYS_ID_AA64ISAR2_EL1, info->reg_id_aa64isar2); + init_cpu_ftr_reg(SYS_ID_AA64ISAR3_EL1, info->reg_id_aa64isar3); init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0); init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1); init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2); init_cpu_ftr_reg(SYS_ID_AA64MMFR3_EL1, info->reg_id_aa64mmfr3); + init_cpu_ftr_reg(SYS_ID_AA64MMFR4_EL1, info->reg_id_aa64mmfr4); init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); + init_cpu_ftr_reg(SYS_ID_AA64PFR2_EL1, info->reg_id_aa64pfr2); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0); + init_cpu_ftr_reg(SYS_ID_AA64FPFR0_EL1, info->reg_id_aa64fpfr0); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) init_32bit_cpu_features(&info->aarch32); @@ -1272,6 +1353,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64isar1, boot->reg_id_aa64isar1); taint |= check_update_ftr_reg(SYS_ID_AA64ISAR2_EL1, cpu, info->reg_id_aa64isar2, boot->reg_id_aa64isar2); + taint |= check_update_ftr_reg(SYS_ID_AA64ISAR3_EL1, cpu, + info->reg_id_aa64isar3, boot->reg_id_aa64isar3); /* * Differing PARange support is fine as long as all peripherals and @@ -1291,6 +1374,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1); + taint |= check_update_ftr_reg(SYS_ID_AA64PFR2_EL1, cpu, + info->reg_id_aa64pfr2, boot->reg_id_aa64pfr2); taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu, info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0); @@ -1298,6 +1383,9 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64FPFR0_EL1, cpu, + info->reg_id_aa64fpfr0, boot->reg_id_aa64fpfr0); + /* Probe vector lengths */ if (IS_ENABLED(CONFIG_ARM64_SVE) && id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) { @@ -1410,17 +1498,21 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64PFR0_EL1); read_sysreg_case(SYS_ID_AA64PFR1_EL1); + read_sysreg_case(SYS_ID_AA64PFR2_EL1); read_sysreg_case(SYS_ID_AA64ZFR0_EL1); read_sysreg_case(SYS_ID_AA64SMFR0_EL1); + read_sysreg_case(SYS_ID_AA64FPFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR0_EL1); read_sysreg_case(SYS_ID_AA64MMFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR2_EL1); read_sysreg_case(SYS_ID_AA64MMFR3_EL1); + read_sysreg_case(SYS_ID_AA64MMFR4_EL1); read_sysreg_case(SYS_ID_AA64ISAR0_EL1); read_sysreg_case(SYS_ID_AA64ISAR1_EL1); read_sysreg_case(SYS_ID_AA64ISAR2_EL1); + read_sysreg_case(SYS_ID_AA64ISAR3_EL1); read_sysreg_case(SYS_CNTFRQ_EL0); read_sysreg_case(SYS_CTR_EL0); @@ -1451,11 +1543,28 @@ has_always(const struct arm64_cpu_capabilities *entry, int scope) static bool feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) { - int val = cpuid_feature_extract_field_width(reg, entry->field_pos, - entry->field_width, - entry->sign); + int val, min, max; + u64 tmp; + + val = cpuid_feature_extract_field_width(reg, entry->field_pos, + entry->field_width, + entry->sign); + + tmp = entry->min_field_value; + tmp <<= entry->field_pos; + + min = cpuid_feature_extract_field_width(tmp, entry->field_pos, + entry->field_width, + entry->sign); - return val >= entry->min_field_value; + tmp = entry->max_field_value; + tmp <<= entry->field_pos; + + max = cpuid_feature_extract_field_width(tmp, entry->field_pos, + entry->field_width, + entry->sign); + + return val >= min && val <= max; } static u64 @@ -1620,46 +1729,6 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) return has_cpuid_feature(entry, scope); } -/* - * This check is triggered during the early boot before the cpufeature - * is initialised. Checking the status on the local CPU allows the boot - * CPU to detect the need for non-global mappings and thus avoiding a - * pagetable re-write after all the CPUs are booted. This check will be - * anyway run on individual CPUs, allowing us to get the consistent - * state once the SMP CPUs are up and thus make the switch to non-global - * mappings if required. - */ -bool kaslr_requires_kpti(void) -{ - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return false; - - /* - * E0PD does a similar job to KPTI so can be used instead - * where available. - */ - if (IS_ENABLED(CONFIG_ARM64_E0PD)) { - u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); - if (cpuid_feature_extract_unsigned_field(mmfr2, - ID_AA64MMFR2_EL1_E0PD_SHIFT)) - return false; - } - - /* - * Systems affected by Cavium erratum 24756 are incompatible - * with KPTI. - */ - if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { - extern const struct midr_range cavium_erratum_27456_cpus[]; - - if (is_midr_in_range_list(read_cpuid_id(), - cavium_erratum_27456_cpus)) - return false; - } - - return kaslr_enabled(); -} - static bool __meltdown_safe = true; static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ @@ -1712,7 +1781,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, } /* Useful for KASLR robustness */ - if (kaslr_requires_kpti()) { + if (kaslr_enabled() && kaslr_requires_kpti()) { if (!__kpti_forced) { str = "KASLR"; __kpti_forced = 1; @@ -1739,6 +1808,28 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, return !meltdown_safe; } +static bool has_nv1(const struct arm64_cpu_capabilities *entry, int scope) +{ + /* + * Although the Apple M2 family appears to support NV1, the + * PTW barfs on the nVHE EL2 S1 page table format. Pretend + * that it doesn't support NV1 at all. + */ + static const struct midr_range nv1_ni_list[] = { + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), + {} + }; + + return (__system_matches_cap(ARM64_HAS_NESTED_VIRT) && + !(has_cpuid_feature(entry, scope) || + is_midr_in_range_list(read_cpuid_id(), nv1_ni_list))); +} + #if defined(ID_AA64MMFR0_EL1_TGRAN_LPA2) && defined(ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2) static bool has_lpa2_at_stage1(u64 mmfr0) { @@ -1801,6 +1892,11 @@ static int __init __kpti_install_ng_mappings(void *__unused) pgd_t *kpti_ng_temp_pgd; u64 alloc = 0; + if (levels == 5 && !pgtable_l5_enabled()) + levels = 4; + else if (levels == 4 && !pgtable_l4_enabled()) + levels = 3; + remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); if (!cpu) { @@ -1814,9 +1910,9 @@ static int __init __kpti_install_ng_mappings(void *__unused) // // The physical pages are laid out as follows: // - // +--------+-/-------+-/------ +-\\--------+ - // : PTE[] : | PMD[] : | PUD[] : || PGD[] : - // +--------+-\-------+-\------ +-//--------+ + // +--------+-/-------+-/------ +-/------ +-\\\--------+ + // : PTE[] : | PMD[] : | PUD[] : | P4D[] : ||| PGD[] : + // +--------+-\-------+-\------ +-\------ +-///--------+ // ^ // The first page is mapped into this hierarchy at a PMD_SHIFT // aligned virtual address, so that we can manipulate the PTE @@ -2042,14 +2138,7 @@ static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap, static bool hvhe_possible(const struct arm64_cpu_capabilities *entry, int __unused) { - u64 val; - - val = read_sysreg(id_aa64mmfr1_el1); - if (!cpuid_feature_extract_unsigned_field(val, ID_AA64MMFR1_EL1_VH_SHIFT)) - return false; - - val = arm64_sw_feature_override.val & arm64_sw_feature_override.mask; - return cpuid_feature_extract_unsigned_field(val, ARM64_SW_FEATURE_OVERRIDE_HVHE); + return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_HVHE); } #ifdef CONFIG_ARM64_PAN @@ -2739,6 +2828,39 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_lpa2, }, + { + .desc = "FPMR", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_HAS_FPMR, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_fpmr, + ARM64_CPUID_FIELDS(ID_AA64PFR2_EL1, FPMR, IMP) + }, +#ifdef CONFIG_ARM64_VA_BITS_52 + { + .capability = ARM64_HAS_VA52, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .matches = has_cpuid_feature, +#ifdef CONFIG_ARM64_64K_PAGES + .desc = "52-bit Virtual Addressing (LVA)", + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, VARange, 52) +#else + .desc = "52-bit Virtual Addressing (LPA2)", +#ifdef CONFIG_ARM64_4K_PAGES + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN4, 52_BIT) +#else + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN16, 52_BIT) +#endif +#endif + }, +#endif + { + .desc = "NV1", + .capability = ARM64_HAS_HCR_NV1, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_nv1, + ARM64_CPUID_FIELDS_NEG(ID_AA64MMFR4_EL1, E2H0, NI_NV1) + }, {}, }; @@ -2822,6 +2944,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, FP16, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), HWCAP_CAP(ID_AA64PFR0_EL1, DIT, IMP, CAP_HWCAP, KERNEL_HWCAP_DIT), + HWCAP_CAP(ID_AA64PFR2_EL1, FPMR, IMP, CAP_HWCAP, KERNEL_HWCAP_FPMR), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, IMP, CAP_HWCAP, KERNEL_HWCAP_DCPOP), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, DPB2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), HWCAP_CAP(ID_AA64ISAR1_EL1, JSCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_JSCVT), @@ -2835,6 +2958,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_EBF16), HWCAP_CAP(ID_AA64ISAR1_EL1, DGH, IMP, CAP_HWCAP, KERNEL_HWCAP_DGH), HWCAP_CAP(ID_AA64ISAR1_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_I8MM), + HWCAP_CAP(ID_AA64ISAR2_EL1, LUT, IMP, CAP_HWCAP, KERNEL_HWCAP_LUT), + HWCAP_CAP(ID_AA64ISAR3_EL1, FAMINMAX, IMP, CAP_HWCAP, KERNEL_HWCAP_FAMINMAX), HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), @@ -2875,6 +3000,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), @@ -2882,12 +3008,23 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), + HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), + HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), #endif /* CONFIG_ARM64_SME */ + HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), {}, }; @@ -3052,13 +3189,9 @@ static void __init enable_cpu_capabilities(u16 scope_mask) boot_scope = !!(scope_mask & SCOPE_BOOT_CPU); for (i = 0; i < ARM64_NCAPS; i++) { - unsigned int num; - caps = cpucap_ptrs[i]; - if (!caps || !(caps->type & scope_mask)) - continue; - num = caps->capability; - if (!cpus_have_cap(num)) + if (!caps || !(caps->type & scope_mask) || + !cpus_have_cap(caps->capability)) continue; if (boot_scope && caps->cpu_enable) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 47043c0d95..09eeaa24d4 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -128,6 +128,21 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SVE_B16B16] = "sveb16b16", [KERNEL_HWCAP_LRCPC3] = "lrcpc3", [KERNEL_HWCAP_LSE128] = "lse128", + [KERNEL_HWCAP_FPMR] = "fpmr", + [KERNEL_HWCAP_LUT] = "lut", + [KERNEL_HWCAP_FAMINMAX] = "faminmax", + [KERNEL_HWCAP_F8CVT] = "f8cvt", + [KERNEL_HWCAP_F8FMA] = "f8fma", + [KERNEL_HWCAP_F8DP4] = "f8dp4", + [KERNEL_HWCAP_F8DP2] = "f8dp2", + [KERNEL_HWCAP_F8E4M3] = "f8e4m3", + [KERNEL_HWCAP_F8E5M2] = "f8e5m2", + [KERNEL_HWCAP_SME_LUTV2] = "smelutv2", + [KERNEL_HWCAP_SME_F8F16] = "smef8f16", + [KERNEL_HWCAP_SME_F8F32] = "smef8f32", + [KERNEL_HWCAP_SME_SF8FMA] = "smesf8fma", + [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", + [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", }; #ifdef CONFIG_COMPAT @@ -443,14 +458,18 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64isar0 = read_cpuid(ID_AA64ISAR0_EL1); info->reg_id_aa64isar1 = read_cpuid(ID_AA64ISAR1_EL1); info->reg_id_aa64isar2 = read_cpuid(ID_AA64ISAR2_EL1); + info->reg_id_aa64isar3 = read_cpuid(ID_AA64ISAR3_EL1); info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1); info->reg_id_aa64mmfr3 = read_cpuid(ID_AA64MMFR3_EL1); + info->reg_id_aa64mmfr4 = read_cpuid(ID_AA64MMFR4_EL1); info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); + info->reg_id_aa64pfr2 = read_cpuid(ID_AA64PFR2_EL1); info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1); info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); + info->reg_id_aa64fpfr0 = read_cpuid(ID_AA64FPFR0_EL1); if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) info->reg_gmid = read_cpuid(GMID_EL1); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 0228001347..9afcc690fe 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -103,7 +103,7 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { struct set_perm_data *spd = data; const efi_memory_desc_t *md = spd->md; - pte_t pte = READ_ONCE(*ptep); + pte_t pte = __ptep_get(ptep); if (md->attribute & EFI_MEMORY_RO) pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); @@ -111,7 +111,7 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) pte = set_pte_bit(pte, __pgprot(PTE_PXN)); else if (system_supports_bti_kernel() && spd->has_bti) pte = set_pte_bit(pte, __pgprot(PTE_GP)); - set_pte(ptep, pte); + __set_pte(ptep, pte); return 0; } diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 0fc94207e6..b77a15955f 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -10,6 +10,7 @@ #include <linux/linkage.h> #include <linux/lockdep.h> #include <linux/ptrace.h> +#include <linux/resume_user_mode.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/thread_info.h> @@ -126,16 +127,49 @@ static __always_inline void __exit_to_user_mode(void) lockdep_hardirqs_on(CALLER_ADDR0); } +static void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) +{ + do { + local_irq_enable(); + + if (thread_flags & _TIF_NEED_RESCHED) + schedule(); + + if (thread_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + + if (thread_flags & _TIF_MTE_ASYNC_FAULT) { + clear_thread_flag(TIF_MTE_ASYNC_FAULT); + send_sig_fault(SIGSEGV, SEGV_MTEAERR, + (void __user *)NULL, current); + } + + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + do_signal(regs); + + if (thread_flags & _TIF_NOTIFY_RESUME) + resume_user_mode_work(regs); + + if (thread_flags & _TIF_FOREIGN_FPSTATE) + fpsimd_restore_current_state(); + + local_irq_disable(); + thread_flags = read_thread_flags(); + } while (thread_flags & _TIF_WORK_MASK); +} + static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) { unsigned long flags; - local_daif_mask(); + local_irq_disable(); flags = read_thread_flags(); if (unlikely(flags & _TIF_WORK_MASK)) do_notify_resume(regs, flags); + local_daif_mask(); + lockdep_sys_exit(); } diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 5e7b0eb468..82e8a60173 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -359,6 +359,9 @@ static void task_fpsimd_load(void) WARN_ON(preemptible()); WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); + if (system_supports_fpmr()) + write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR); + if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: @@ -446,6 +449,9 @@ static void fpsimd_save_user_state(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; + if (system_supports_fpmr()) + *(last->fpmr) = read_sysreg_s(SYS_FPMR); + /* * If a task is in a syscall the ABI allows us to only * preserve the state shared with FPSIMD so don't bother @@ -688,6 +694,12 @@ static void sve_to_fpsimd(struct task_struct *task) } } +void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p) +{ + write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK, + SYS_SCTLR_EL1); +} + #ifdef CONFIG_ARM64_SVE /* * Call __sve_free() directly only if you know task can't be scheduled @@ -1134,6 +1146,8 @@ void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1); isb(); + + write_sysreg_s(0, SYS_ZCR_EL1); } void __init sve_setup(void) @@ -1245,6 +1259,9 @@ void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p) write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); isb(); + /* Ensure all bits in SMCR are set to known values */ + write_sysreg_s(0, SYS_SMCR_EL1); + /* Allow EL0 to access TPIDR2 */ write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); isb(); @@ -1717,6 +1734,7 @@ static void fpsimd_bind_task_to_cpu(void) last->sve_vl = task_get_sve_vl(current); last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; + last->fpmr = ¤t->thread.uw.fpmr; last->fp_type = ¤t->thread.fp_type; last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id(); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index a92905e6d4..cb68adcabe 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -80,28 +80,42 @@ * x19 primary_entry() .. start_kernel() whether we entered with the MMU on * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 - * x22 create_idmap() .. start_kernel() ID map VA of the DT blob - * x23 primary_entry() .. start_kernel() physical misalignment/KASLR offset - * x24 __primary_switch() linear map KASLR seed - * x25 primary_entry() .. start_kernel() supported VA size - * x28 create_idmap() callee preserved temp register */ SYM_CODE_START(primary_entry) bl record_mmu_state bl preserve_boot_args - bl create_idmap + + adrp x1, early_init_stack + mov sp, x1 + mov x29, xzr + adrp x0, init_idmap_pg_dir + mov x1, xzr + bl __pi_create_init_idmap + + /* + * If the page tables have been populated with non-cacheable + * accesses (MMU disabled), invalidate those tables again to + * remove any speculatively loaded cache lines. + */ + cbnz x19, 0f + dmb sy + mov x1, x0 // end of used region + adrp x0, init_idmap_pg_dir + adr_l x2, dcache_inval_poc + blr x2 + b 1f /* * If we entered with the MMU and caches on, clean the ID mapped part * of the primary boot code to the PoC so we can safely execute it with * the MMU off. */ - cbz x19, 0f - adrp x0, __idmap_text_start +0: adrp x0, __idmap_text_start adr_l x1, __idmap_text_end adr_l x2, dcache_clean_poc blr x2 -0: mov x0, x19 + +1: mov x0, x19 bl init_kernel_el // w0=cpu_boot_mode mov x20, x0 @@ -111,14 +125,6 @@ SYM_CODE_START(primary_entry) * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ -#if VA_BITS > 48 - mrs_s x0, SYS_ID_AA64MMFR2_EL1 - tst x0, ID_AA64MMFR2_EL1_VARange_MASK - mov x0, #VA_BITS - mov x25, #VA_BITS_MIN - csel x25, x25, x0, eq - mov x0, x25 -#endif bl __cpu_setup // initialise processor b __primary_switch SYM_CODE_END(primary_entry) @@ -177,267 +183,6 @@ SYM_CODE_START_LOCAL(preserve_boot_args) ret SYM_CODE_END(preserve_boot_args) -SYM_FUNC_START_LOCAL(clear_page_tables) - /* - * Clear the init page tables. - */ - adrp x0, init_pg_dir - adrp x1, init_pg_end - sub x2, x1, x0 - mov x1, xzr - b __pi_memset // tail call -SYM_FUNC_END(clear_page_tables) - -/* - * Macro to populate page table entries, these entries can be pointers to the next level - * or last level entries pointing to physical memory. - * - * tbl: page table address - * rtbl: pointer to page table or physical memory - * index: start index to write - * eindex: end index to write - [index, eindex] written to - * flags: flags for pagetable entry to or in - * inc: increment to rtbl between each entry - * tmp1: temporary variable - * - * Preserves: tbl, eindex, flags, inc - * Corrupts: index, tmp1 - * Returns: rtbl - */ - .macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1 -.Lpe\@: phys_to_pte \tmp1, \rtbl - orr \tmp1, \tmp1, \flags // tmp1 = table entry - str \tmp1, [\tbl, \index, lsl #3] - add \rtbl, \rtbl, \inc // rtbl = pa next level - add \index, \index, #1 - cmp \index, \eindex - b.ls .Lpe\@ - .endm - -/* - * Compute indices of table entries from virtual address range. If multiple entries - * were needed in the previous page table level then the next page table level is assumed - * to be composed of multiple pages. (This effectively scales the end index). - * - * vstart: virtual address of start of range - * vend: virtual address of end of range - we map [vstart, vend] - * shift: shift used to transform virtual address into index - * order: #imm 2log(number of entries in page table) - * istart: index in table corresponding to vstart - * iend: index in table corresponding to vend - * count: On entry: how many extra entries were required in previous level, scales - * our end index. - * On exit: returns how many extra entries required for next page table level - * - * Preserves: vstart, vend - * Returns: istart, iend, count - */ - .macro compute_indices, vstart, vend, shift, order, istart, iend, count - ubfx \istart, \vstart, \shift, \order - ubfx \iend, \vend, \shift, \order - add \iend, \iend, \count, lsl \order - sub \count, \iend, \istart - .endm - -/* - * Map memory for specified virtual address range. Each level of page table needed supports - * multiple entries. If a level requires n entries the next page table level is assumed to be - * formed from n pages. - * - * tbl: location of page table - * rtbl: address to be used for first level page table entry (typically tbl + PAGE_SIZE) - * vstart: virtual address of start of range - * vend: virtual address of end of range - we map [vstart, vend - 1] - * flags: flags to use to map last level entries - * phys: physical address corresponding to vstart - physical memory is contiguous - * order: #imm 2log(number of entries in PGD table) - * - * If extra_shift is set, an extra level will be populated if the end address does - * not fit in 'extra_shift' bits. This assumes vend is in the TTBR0 range. - * - * Temporaries: istart, iend, tmp, count, sv - these need to be different registers - * Preserves: vstart, flags - * Corrupts: tbl, rtbl, vend, istart, iend, tmp, count, sv - */ - .macro map_memory, tbl, rtbl, vstart, vend, flags, phys, order, istart, iend, tmp, count, sv, extra_shift - sub \vend, \vend, #1 - add \rtbl, \tbl, #PAGE_SIZE - mov \count, #0 - - .ifnb \extra_shift - tst \vend, #~((1 << (\extra_shift)) - 1) - b.eq .L_\@ - compute_indices \vstart, \vend, #\extra_shift, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv - .endif -.L_\@: - compute_indices \vstart, \vend, #PGDIR_SHIFT, #\order, \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv - -#if SWAPPER_PGTABLE_LEVELS > 3 - compute_indices \vstart, \vend, #PUD_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv -#endif - -#if SWAPPER_PGTABLE_LEVELS > 2 - compute_indices \vstart, \vend, #SWAPPER_TABLE_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv -#endif - - compute_indices \vstart, \vend, #SWAPPER_BLOCK_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - bic \rtbl, \phys, #SWAPPER_BLOCK_SIZE - 1 - populate_entries \tbl, \rtbl, \istart, \iend, \flags, #SWAPPER_BLOCK_SIZE, \tmp - .endm - -/* - * Remap a subregion created with the map_memory macro with modified attributes - * or output address. The entire remapped region must have been covered in the - * invocation of map_memory. - * - * x0: last level table address (returned in first argument to map_memory) - * x1: start VA of the existing mapping - * x2: start VA of the region to update - * x3: end VA of the region to update (exclusive) - * x4: start PA associated with the region to update - * x5: attributes to set on the updated region - * x6: order of the last level mappings - */ -SYM_FUNC_START_LOCAL(remap_region) - sub x3, x3, #1 // make end inclusive - - // Get the index offset for the start of the last level table - lsr x1, x1, x6 - bfi x1, xzr, #0, #PAGE_SHIFT - 3 - - // Derive the start and end indexes into the last level table - // associated with the provided region - lsr x2, x2, x6 - lsr x3, x3, x6 - sub x2, x2, x1 - sub x3, x3, x1 - - mov x1, #1 - lsl x6, x1, x6 // block size at this level - - populate_entries x0, x4, x2, x3, x5, x6, x7 - ret -SYM_FUNC_END(remap_region) - -SYM_FUNC_START_LOCAL(create_idmap) - mov x28, lr - /* - * The ID map carries a 1:1 mapping of the physical address range - * covered by the loaded image, which could be anywhere in DRAM. This - * means that the required size of the VA (== PA) space is decided at - * boot time, and could be more than the configured size of the VA - * space for ordinary kernel and user space mappings. - * - * There are three cases to consider here: - * - 39 <= VA_BITS < 48, and the ID map needs up to 48 VA bits to cover - * the placement of the image. In this case, we configure one extra - * level of translation on the fly for the ID map only. (This case - * also covers 42-bit VA/52-bit PA on 64k pages). - * - * - VA_BITS == 48, and the ID map needs more than 48 VA bits. This can - * only happen when using 64k pages, in which case we need to extend - * the root level table rather than add a level. Note that we can - * treat this case as 'always extended' as long as we take care not - * to program an unsupported T0SZ value into the TCR register. - * - * - Combinations that would require two additional levels of - * translation are not supported, e.g., VA_BITS==36 on 16k pages, or - * VA_BITS==39/4k pages with 5-level paging, where the input address - * requires more than 47 or 48 bits, respectively. - */ -#if (VA_BITS < 48) -#define IDMAP_PGD_ORDER (VA_BITS - PGDIR_SHIFT) -#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) - - /* - * If VA_BITS < 48, we have to configure an additional table level. - * First, we have to verify our assumption that the current value of - * VA_BITS was chosen such that all translation levels are fully - * utilised, and that lowering T0SZ will always result in an additional - * translation level to be configured. - */ -#if VA_BITS != EXTRA_SHIFT -#error "Mismatch between VA_BITS and page size/number of translation levels" -#endif -#else -#define IDMAP_PGD_ORDER (PHYS_MASK_SHIFT - PGDIR_SHIFT) -#define EXTRA_SHIFT - /* - * If VA_BITS == 48, we don't have to configure an additional - * translation level, but the top-level table has more entries. - */ -#endif - adrp x0, init_idmap_pg_dir - adrp x3, _text - adrp x6, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE - mov_q x7, SWAPPER_RX_MMUFLAGS - - map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14, EXTRA_SHIFT - - /* Remap the kernel page tables r/w in the ID map */ - adrp x1, _text - adrp x2, init_pg_dir - adrp x3, init_pg_end - bic x4, x2, #SWAPPER_BLOCK_SIZE - 1 - mov_q x5, SWAPPER_RW_MMUFLAGS - mov x6, #SWAPPER_BLOCK_SHIFT - bl remap_region - - /* Remap the FDT after the kernel image */ - adrp x1, _text - adrp x22, _end + SWAPPER_BLOCK_SIZE - bic x2, x22, #SWAPPER_BLOCK_SIZE - 1 - bfi x22, x21, #0, #SWAPPER_BLOCK_SHIFT // remapped FDT address - add x3, x2, #MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE - bic x4, x21, #SWAPPER_BLOCK_SIZE - 1 - mov_q x5, SWAPPER_RW_MMUFLAGS - mov x6, #SWAPPER_BLOCK_SHIFT - bl remap_region - - /* - * Since the page tables have been populated with non-cacheable - * accesses (MMU disabled), invalidate those tables again to - * remove any speculatively loaded cache lines. - */ - cbnz x19, 0f // skip cache invalidation if MMU is on - dmb sy - - adrp x0, init_idmap_pg_dir - adrp x1, init_idmap_pg_end - bl dcache_inval_poc -0: ret x28 -SYM_FUNC_END(create_idmap) - -SYM_FUNC_START_LOCAL(create_kernel_mapping) - adrp x0, init_pg_dir - mov_q x5, KIMAGE_VADDR // compile time __va(_text) -#ifdef CONFIG_RELOCATABLE - add x5, x5, x23 // add KASLR displacement -#endif - adrp x6, _end // runtime __pa(_end) - adrp x3, _text // runtime __pa(_text) - sub x6, x6, x3 // _end - _text - add x6, x6, x5 // runtime __va(_end) - mov_q x7, SWAPPER_RW_MMUFLAGS - - map_memory x0, x1, x5, x6, x7, x3, (VA_BITS - PGDIR_SHIFT), x10, x11, x12, x13, x14 - - dsb ishst // sync with page table walker - ret -SYM_FUNC_END(create_kernel_mapping) - /* * Initialize CPU registers with task-specific and cpu-specific context. * @@ -489,34 +234,9 @@ SYM_FUNC_START_LOCAL(__primary_switched) mov x0, x20 bl set_cpu_boot_mode_flag - // Clear BSS - adr_l x0, __bss_start - mov x1, xzr - adr_l x2, __bss_stop - sub x2, x2, x0 - bl __pi_memset - dsb ishst // Make zero page visible to PTW - -#if VA_BITS > 48 - adr_l x8, vabits_actual // Set this early so KASAN early init - str x25, [x8] // ... observes the correct value - dc civac, x8 // Make visible to booting secondaries -#endif - -#ifdef CONFIG_RANDOMIZE_BASE - adrp x5, memstart_offset_seed // Save KASLR linear map seed - strh w24, [x5, :lo12:memstart_offset_seed] -#endif #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init #endif - mov x0, x21 // pass FDT address in x0 - bl early_fdt_map // Try mapping the FDT early - mov x0, x20 // pass the full boot status - bl init_feature_override // Parse cpu feature overrides -#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS - bl scs_patch_vmlinux -#endif mov x0, x20 bl finalise_el2 // Prefer VHE if possible ldp x29, x30, [sp], #16 @@ -576,6 +296,21 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) isb 0: mov_q x0, HCR_HOST_NVHE_FLAGS + + /* + * Compliant CPUs advertise their VHE-onlyness with + * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be + * RES1 in that case. Publish the E2H bit early so that + * it can be picked up by the init_el2_state macro. + * + * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but + * don't advertise it (they predate this relaxation). + */ + mrs_s x1, SYS_ID_AA64MMFR4_EL1 + tbz x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f + + orr x0, x0, #HCR_E2H +1: msr hcr_el2, x0 isb @@ -588,26 +323,19 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) mov_q x1, INIT_SCTLR_EL1_MMU_OFF - /* - * Fruity CPUs seem to have HCR_EL2.E2H set to RES1, - * making it impossible to start in nVHE mode. Is that - * compliant with the architecture? Absolutely not! - */ mrs x0, hcr_el2 and x0, x0, #HCR_E2H - cbz x0, 1f + cbz x0, 2f /* Set a sane SCTLR_EL1, the VHE way */ - pre_disable_mmu_workaround msr_s SYS_SCTLR_EL12, x1 mov x2, #BOOT_CPU_FLAG_E2H - b 2f + b 3f -1: - pre_disable_mmu_workaround +2: msr sctlr_el1, x1 mov x2, xzr -2: +3: __init_el2_nvhe_prepare_eret mov w0, #BOOT_CPU_MODE_EL2 @@ -648,10 +376,13 @@ SYM_FUNC_START_LOCAL(secondary_startup) * Common entry point for secondary CPUs. */ mov x20, x0 // preserve boot mode + +#ifdef CONFIG_ARM64_VA_BITS_52 +alternative_if ARM64_HAS_VA52 bl __cpu_secondary_check52bitva -#if VA_BITS > 48 - ldr_l x0, vabits_actual +alternative_else_nop_endif #endif + bl __cpu_setup // initialise processor adrp x1, swapper_pg_dir adrp x2, idmap_pg_dir @@ -754,15 +485,18 @@ SYM_FUNC_START(__enable_mmu) ret SYM_FUNC_END(__enable_mmu) +#ifdef CONFIG_ARM64_VA_BITS_52 SYM_FUNC_START(__cpu_secondary_check52bitva) -#if VA_BITS > 48 - ldr_l x0, vabits_actual - cmp x0, #52 - b.ne 2f - +#ifndef CONFIG_ARM64_LPA2 mrs_s x0, SYS_ID_AA64MMFR2_EL1 and x0, x0, ID_AA64MMFR2_EL1_VARange_MASK cbnz x0, 2f +#else + mrs x0, id_aa64mmfr0_el1 + sbfx x0, x0, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4 + cmp x0, #ID_AA64MMFR0_EL1_TGRAN_LPA2 + b.ge 2f +#endif update_early_cpu_boot_status \ CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_52_BIT_VA, x0, x1 @@ -770,9 +504,9 @@ SYM_FUNC_START(__cpu_secondary_check52bitva) wfi b 1b -#endif 2: ret SYM_FUNC_END(__cpu_secondary_check52bitva) +#endif SYM_FUNC_START_LOCAL(__no_granule_support) /* Indicate that this CPU can't boot and is stuck in the kernel */ @@ -784,123 +518,18 @@ SYM_FUNC_START_LOCAL(__no_granule_support) b 1b SYM_FUNC_END(__no_granule_support) -#ifdef CONFIG_RELOCATABLE -SYM_FUNC_START_LOCAL(__relocate_kernel) - /* - * Iterate over each entry in the relocation table, and apply the - * relocations in place. - */ - adr_l x9, __rela_start - adr_l x10, __rela_end - mov_q x11, KIMAGE_VADDR // default virtual offset - add x11, x11, x23 // actual virtual offset - -0: cmp x9, x10 - b.hs 1f - ldp x12, x13, [x9], #24 - ldr x14, [x9, #-8] - cmp w13, #R_AARCH64_RELATIVE - b.ne 0b - add x14, x14, x23 // relocate - str x14, [x12, x23] - b 0b - -1: -#ifdef CONFIG_RELR - /* - * Apply RELR relocations. - * - * RELR is a compressed format for storing relative relocations. The - * encoded sequence of entries looks like: - * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ] - * - * i.e. start with an address, followed by any number of bitmaps. The - * address entry encodes 1 relocation. The subsequent bitmap entries - * encode up to 63 relocations each, at subsequent offsets following - * the last address entry. - * - * The bitmap entries must have 1 in the least significant bit. The - * assumption here is that an address cannot have 1 in lsb. Odd - * addresses are not supported. Any odd addresses are stored in the RELA - * section, which is handled above. - * - * Excluding the least significant bit in the bitmap, each non-zero - * bit in the bitmap represents a relocation to be applied to - * a corresponding machine word that follows the base address - * word. The second least significant bit represents the machine - * word immediately following the initial address, and each bit - * that follows represents the next word, in linear order. As such, - * a single bitmap can encode up to 63 relocations in a 64-bit object. - * - * In this implementation we store the address of the next RELR table - * entry in x9, the address being relocated by the current address or - * bitmap entry in x13 and the address being relocated by the current - * bit in x14. - */ - adr_l x9, __relr_start - adr_l x10, __relr_end - -2: cmp x9, x10 - b.hs 7f - ldr x11, [x9], #8 - tbnz x11, #0, 3f // branch to handle bitmaps - add x13, x11, x23 - ldr x12, [x13] // relocate address entry - add x12, x12, x23 - str x12, [x13], #8 // adjust to start of bitmap - b 2b - -3: mov x14, x13 -4: lsr x11, x11, #1 - cbz x11, 6f - tbz x11, #0, 5f // skip bit if not set - ldr x12, [x14] // relocate bit - add x12, x12, x23 - str x12, [x14] - -5: add x14, x14, #8 // move to next bit's address - b 4b - -6: /* - * Move to the next bitmap's address. 8 is the word size, and 63 is the - * number of significant bits in a bitmap entry. - */ - add x13, x13, #(8 * 63) - b 2b - -7: -#endif - ret - -SYM_FUNC_END(__relocate_kernel) -#endif - SYM_FUNC_START_LOCAL(__primary_switch) adrp x1, reserved_pg_dir adrp x2, init_idmap_pg_dir bl __enable_mmu -#ifdef CONFIG_RELOCATABLE - adrp x23, KERNEL_START - and x23, x23, MIN_KIMG_ALIGN - 1 -#ifdef CONFIG_RANDOMIZE_BASE - mov x0, x22 - adrp x1, init_pg_end + + adrp x1, early_init_stack mov sp, x1 mov x29, xzr - bl __pi_kaslr_early_init - and x24, x0, #SZ_2M - 1 // capture memstart offset seed - bic x0, x0, #SZ_2M - 1 - orr x23, x23, x0 // record kernel offset -#endif -#endif - bl clear_page_tables - bl create_kernel_mapping + mov x0, x20 // pass the full boot status + mov x1, x21 // pass the FDT + bl __pi_early_map_kernel // Map and relocate the kernel - adrp x1, init_pg_dir - load_ttbr1 x1, x1, x2 -#ifdef CONFIG_RELOCATABLE - bl __relocate_kernel -#endif ldr x8, =__primary_switched adrp x0, KERNEL_START // __pa(KERNEL_START) br x8 diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 35225632d7..2f5755192c 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -21,6 +21,7 @@ #include <asm/current.h> #include <asm/debug-monitors.h> +#include <asm/esr.h> #include <asm/hw_breakpoint.h> #include <asm/traps.h> #include <asm/cputype.h> @@ -779,7 +780,7 @@ static int watchpoint_handler(unsigned long addr, unsigned long esr, * Check that the access type matches. * 0 => load, otherwise => store */ - access = (esr & AARCH64_ESR_ACCESS_MASK) ? HW_BREAKPOINT_W : + access = (esr & ESR_ELx_WNR) ? HW_BREAKPOINT_W : HW_BREAKPOINT_R; if (!(access & hw_breakpoint_type(wp))) continue; diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 5e4dc72ab1..ba4f8f7d6a 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -36,6 +36,41 @@ PROVIDE(__pi___memcpy = __pi_memcpy); PROVIDE(__pi___memmove = __pi_memmove); PROVIDE(__pi___memset = __pi_memset); +PROVIDE(__pi_id_aa64isar1_override = id_aa64isar1_override); +PROVIDE(__pi_id_aa64isar2_override = id_aa64isar2_override); +PROVIDE(__pi_id_aa64mmfr0_override = id_aa64mmfr0_override); +PROVIDE(__pi_id_aa64mmfr1_override = id_aa64mmfr1_override); +PROVIDE(__pi_id_aa64mmfr2_override = id_aa64mmfr2_override); +PROVIDE(__pi_id_aa64pfr0_override = id_aa64pfr0_override); +PROVIDE(__pi_id_aa64pfr1_override = id_aa64pfr1_override); +PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override); +PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override); +PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override); +PROVIDE(__pi_arm64_use_ng_mappings = arm64_use_ng_mappings); +#ifdef CONFIG_CAVIUM_ERRATUM_27456 +PROVIDE(__pi_cavium_erratum_27456_cpus = cavium_erratum_27456_cpus); +#endif +PROVIDE(__pi__ctype = _ctype); +PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed); + +PROVIDE(__pi_init_idmap_pg_dir = init_idmap_pg_dir); +PROVIDE(__pi_init_idmap_pg_end = init_idmap_pg_end); +PROVIDE(__pi_init_pg_dir = init_pg_dir); +PROVIDE(__pi_init_pg_end = init_pg_end); +PROVIDE(__pi_swapper_pg_dir = swapper_pg_dir); + +PROVIDE(__pi__text = _text); +PROVIDE(__pi__stext = _stext); +PROVIDE(__pi__etext = _etext); +PROVIDE(__pi___start_rodata = __start_rodata); +PROVIDE(__pi___inittext_begin = __inittext_begin); +PROVIDE(__pi___inittext_end = __inittext_end); +PROVIDE(__pi___initdata_begin = __initdata_begin); +PROVIDE(__pi___initdata_end = __initdata_end); +PROVIDE(__pi__data = _data); +PROVIDE(__pi___bss_start = __bss_start); +PROVIDE(__pi__end = _end); + #ifdef CONFIG_KVM /* diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 12c7f3c8ba..1da3e25f9d 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -16,9 +16,7 @@ bool __ro_after_init __kaslr_is_enabled = false; void __init kaslr_init(void) { - if (cpuid_feature_extract_unsigned_field(arm64_sw_feature_override.val & - arm64_sw_feature_override.mask, - ARM64_SW_FEATURE_OVERRIDE_NOKASLR)) { + if (kaslr_disabled_cmdline()) { pr_info("KASLR disabled on command line\n"); return; } diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index b38aae5b48..82e2203d86 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -255,7 +255,7 @@ void machine_crash_shutdown(struct pt_regs *regs) pr_info("Starting crashdump kernel...\n"); } -#ifdef CONFIG_HIBERNATION +#if defined(CONFIG_CRASH_DUMP) && defined(CONFIG_HIBERNATION) /* * To preserve the crash dump kernel image, the relevant memory segments * should be mapped again around the hibernation. diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 0e017358f4..af1ca875c5 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -39,6 +39,7 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) return kexec_image_post_load_cleanup_default(image); } +#ifdef CONFIG_CRASH_DUMP static int prepare_elf_headers(void **addr, unsigned long *sz) { struct crash_mem *cmem; @@ -80,6 +81,7 @@ out: kfree(cmem); return ret; } +#endif /* * Tries to add the initrd and DTB to the image. If it is not possible to find @@ -93,8 +95,8 @@ int load_other_segments(struct kimage *image, char *cmdline) { struct kexec_buf kbuf; - void *headers, *dtb = NULL; - unsigned long headers_sz, initrd_load_addr = 0, dtb_len, + void *dtb = NULL; + unsigned long initrd_load_addr = 0, dtb_len, orig_segments = image->nr_segments; int ret = 0; @@ -102,7 +104,10 @@ int load_other_segments(struct kimage *image, /* not allocate anything below the kernel */ kbuf.buf_min = kernel_load_addr + kernel_size; +#ifdef CONFIG_CRASH_DUMP /* load elf core header */ + void *headers; + unsigned long headers_sz; if (image->type == KEXEC_TYPE_CRASH) { ret = prepare_elf_headers(&headers, &headers_sz); if (ret) { @@ -130,6 +135,7 @@ int load_other_segments(struct kimage *image, kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); } +#endif /* load initrd */ if (initrd) { diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index dd85129759..47e0be610b 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -595,7 +595,7 @@ int module_finalize(const Elf_Ehdr *hdr, if (scs_is_dynamic()) { s = find_section(hdr, sechdrs, ".init.eh_frame"); if (s) - scs_patch((void *)s->sh_addr, s->sh_size); + __pi_scs_patch((void *)s->sh_addr, s->sh_size); } return module_init_ftrace_plt(hdr, sechdrs, me); diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index a41ef3213e..dcdcccd408 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -67,7 +67,7 @@ int memcmp_pages(struct page *page1, struct page *page2) /* * If the page content is identical but at least one of the pages is * tagged, return non-zero to avoid KSM merging. If only one of the - * pages is tagged, set_pte_at() may zero or change the tags of the + * pages is tagged, __set_ptes() may zero or change the tags of the * other page via mte_sync_tags(). */ if (page_mte_tagged(page1) || page_mte_tagged(page2)) diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index b4835f6d59..2555349303 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -105,6 +105,81 @@ noinstr int aarch64_insn_write_literal_u64(void *addr, u64 val) return ret; } +typedef void text_poke_f(void *dst, void *src, size_t patched, size_t len); + +static void *__text_poke(text_poke_f func, void *addr, void *src, size_t len) +{ + unsigned long flags; + size_t patched = 0; + size_t size; + void *waddr; + void *ptr; + + raw_spin_lock_irqsave(&patch_lock, flags); + + while (patched < len) { + ptr = addr + patched; + size = min_t(size_t, PAGE_SIZE - offset_in_page(ptr), + len - patched); + + waddr = patch_map(ptr, FIX_TEXT_POKE0); + func(waddr, src, patched, size); + patch_unmap(FIX_TEXT_POKE0); + + patched += size; + } + raw_spin_unlock_irqrestore(&patch_lock, flags); + + flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len); + + return addr; +} + +static void text_poke_memcpy(void *dst, void *src, size_t patched, size_t len) +{ + copy_to_kernel_nofault(dst, src + patched, len); +} + +static void text_poke_memset(void *dst, void *src, size_t patched, size_t len) +{ + u32 c = *(u32 *)src; + + memset32(dst, c, len / 4); +} + +/** + * aarch64_insn_copy - Copy instructions into (an unused part of) RX memory + * @dst: address to modify + * @src: source of the copy + * @len: length to copy + * + * Useful for JITs to dump new code blocks into unused regions of RX memory. + */ +noinstr void *aarch64_insn_copy(void *dst, void *src, size_t len) +{ + /* A64 instructions must be word aligned */ + if ((uintptr_t)dst & 0x3) + return NULL; + + return __text_poke(text_poke_memcpy, dst, src, len); +} + +/** + * aarch64_insn_set - memset for RX memory regions. + * @dst: address to modify + * @insn: value to set + * @len: length of memory region. + * + * Useful for JITs to fill regions of RX memory with illegal instructions. + */ +noinstr void *aarch64_insn_set(void *dst, u32 insn, size_t len) +{ + if ((uintptr_t)dst & 0x3) + return NULL; + + return __text_poke(text_poke_memset, dst, &insn, len); +} + int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn) { u32 *tp = addr; diff --git a/arch/arm64/kernel/pi/.gitignore b/arch/arm64/kernel/pi/.gitignore new file mode 100644 index 0000000000..efb29b663e --- /dev/null +++ b/arch/arm64/kernel/pi/.gitignore @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +relacheck diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index c844a0546d..4393b41f0b 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -11,6 +11,9 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ -fno-asynchronous-unwind-tables -fno-unwind-tables \ $(call cc-option,-fno-addrsig) +# this code may run with the MMU off so disable unaligned accesses +CFLAGS_map_range.o += -mstrict-align + # remove SCS flags from all objects in this directory KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS)) # disable LTO @@ -22,14 +25,26 @@ KCSAN_SANITIZE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +hostprogs := relacheck + +quiet_cmd_piobjcopy = $(quiet_cmd_objcopy) + cmd_piobjcopy = $(cmd_objcopy) && $(obj)/relacheck $(@) $(<) + $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ - --remove-section=.note.gnu.property \ - --prefix-alloc-sections=.init -$(obj)/%.pi.o: $(obj)/%.o FORCE - $(call if_changed,objcopy) + --remove-section=.note.gnu.property +$(obj)/%.pi.o: $(obj)/%.o $(obj)/relacheck FORCE + $(call if_changed,piobjcopy) + +# ensure that all the lib- code ends up as __init code and data +$(obj)/lib-%.pi.o: OBJCOPYFLAGS += --prefix-alloc-sections=.init $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) -obj-y := kaslr_early.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o -extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) +obj-y := idreg-override.pi.o \ + map_kernel.pi.o map_range.pi.o \ + lib-fdt.pi.o lib-fdt_ro.pi.o +obj-$(CONFIG_RELOCATABLE) += relocate.pi.o +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o +obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.pi.o +extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index e30fd9e32e..aad399796e 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -14,6 +14,8 @@ #include <asm/cpufeature.h> #include <asm/setup.h> +#include "pi.h" + #define FTR_DESC_NAME_LEN 20 #define FTR_DESC_FIELD_LEN 10 #define FTR_ALIAS_NAME_LEN 30 @@ -21,15 +23,6 @@ static u64 __boot_status __initdata; -// temporary __prel64 related definitions -// to be removed when this code is moved under pi/ - -#define __prel64_initconst __initconst - -#define PREL64(type, name) union { type *name; } - -#define prel64_pointer(__d) (__d) - typedef bool filter_t(u64 val); struct ftr_set_desc { @@ -66,6 +59,35 @@ static const struct ftr_set_desc mmfr1 __prel64_initconst = { }, }; + +static bool __init mmfr2_varange_filter(u64 val) +{ + int __maybe_unused feat; + + if (val) + return false; + +#ifdef CONFIG_ARM64_LPA2 + feat = cpuid_feature_extract_signed_field(read_sysreg(id_aa64mmfr0_el1), + ID_AA64MMFR0_EL1_TGRAN_SHIFT); + if (feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2) { + id_aa64mmfr0_override.val |= + (ID_AA64MMFR0_EL1_TGRAN_LPA2 - 1) << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + } +#endif + return true; +} + +static const struct ftr_set_desc mmfr2 __prel64_initconst = { + .name = "id_aa64mmfr2", + .override = &id_aa64mmfr2_override, + .fields = { + FIELD("varange", ID_AA64MMFR2_EL1_VARange_SHIFT, mmfr2_varange_filter), + {} + }, +}; + static bool __init pfr0_sve_filter(u64 val) { /* @@ -166,6 +188,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = { .fields = { FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL), FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter), + FIELD("rodataoff", ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF, NULL), {} }, }; @@ -173,6 +196,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = { static const PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = { { &mmfr1 }, + { &mmfr2 }, { &pfr0 }, { &pfr1 }, { &isar1 }, @@ -197,6 +221,8 @@ static const struct { { "arm64.nomops", "id_aa64isar2.mops=0" }, { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "arm64_sw.nokaslr=1" }, + { "rodata=off", "arm64_sw.rodataoff=1" }, + { "arm64.nolva", "id_aa64mmfr2.varange=0" }, }; static int __init parse_hexdigit(const char *p, u64 *v) @@ -313,42 +339,35 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) } while (1); } -static __init const u8 *get_bootargs_cmdline(void) +static __init const u8 *get_bootargs_cmdline(const void *fdt, int node) { + static char const bootargs[] __initconst = "bootargs"; const u8 *prop; - void *fdt; - int node; - fdt = get_early_fdt_ptr(); - if (!fdt) - return NULL; - - node = fdt_path_offset(fdt, "/chosen"); if (node < 0) return NULL; - prop = fdt_getprop(fdt, node, "bootargs", NULL); + prop = fdt_getprop(fdt, node, bootargs, NULL); if (!prop) return NULL; return strlen(prop) ? prop : NULL; } -static __init void parse_cmdline(void) +static __init void parse_cmdline(const void *fdt, int chosen) { - const u8 *prop = get_bootargs_cmdline(); + static char const cmdline[] __initconst = CONFIG_CMDLINE; + const u8 *prop = get_bootargs_cmdline(fdt, chosen); if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop) - __parse_cmdline(CONFIG_CMDLINE, true); + __parse_cmdline(cmdline, true); if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop) __parse_cmdline(prop, true); } -/* Keep checkers quiet */ -void init_feature_override(u64 boot_status); - -asmlinkage void __init init_feature_override(u64 boot_status) +void __init init_feature_override(u64 boot_status, const void *fdt, + int chosen) { struct arm64_ftr_override *override; const struct ftr_set_desc *reg; @@ -364,7 +383,7 @@ asmlinkage void __init init_feature_override(u64 boot_status) __boot_status = boot_status; - parse_cmdline(); + parse_cmdline(fdt, chosen); for (i = 0; i < ARRAY_SIZE(regs); i++) { reg = prel64_pointer(regs[i].reg); @@ -373,3 +392,10 @@ asmlinkage void __init init_feature_override(u64 boot_status) (unsigned long)(override + 1)); } } + +char * __init skip_spaces(const char *str) +{ + while (isspace(*str)) + ++str; + return (char *)str; +} diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index 17bff6e399..0257b43819 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -14,69 +14,23 @@ #include <asm/archrandom.h> #include <asm/memory.h> +#include <asm/pgtable.h> -/* taken from lib/string.c */ -static char *__strstr(const char *s1, const char *s2) -{ - size_t l1, l2; - - l2 = strlen(s2); - if (!l2) - return (char *)s1; - l1 = strlen(s1); - while (l1 >= l2) { - l1--; - if (!memcmp(s1, s2, l2)) - return (char *)s1; - s1++; - } - return NULL; -} -static bool cmdline_contains_nokaslr(const u8 *cmdline) -{ - const u8 *str; - - str = __strstr(cmdline, "nokaslr"); - return str == cmdline || (str > cmdline && *(str - 1) == ' '); -} - -static bool is_kaslr_disabled_cmdline(void *fdt) -{ - if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { - int node; - const u8 *prop; - - node = fdt_path_offset(fdt, "/chosen"); - if (node < 0) - goto out; - - prop = fdt_getprop(fdt, node, "bootargs", NULL); - if (!prop) - goto out; - - if (cmdline_contains_nokaslr(prop)) - return true; +#include "pi.h" - if (IS_ENABLED(CONFIG_CMDLINE_EXTEND)) - goto out; +extern u16 memstart_offset_seed; - return false; - } -out: - return cmdline_contains_nokaslr(CONFIG_CMDLINE); -} - -static u64 get_kaslr_seed(void *fdt) +static u64 __init get_kaslr_seed(void *fdt, int node) { - int node, len; + static char const seed_str[] __initconst = "kaslr-seed"; fdt64_t *prop; u64 ret; + int len; - node = fdt_path_offset(fdt, "/chosen"); if (node < 0) return 0; - prop = fdt_getprop_w(fdt, node, "kaslr-seed", &len); + prop = fdt_getprop_w(fdt, node, seed_str, &len); if (!prop || len != sizeof(u64)) return 0; @@ -85,26 +39,28 @@ static u64 get_kaslr_seed(void *fdt) return ret; } -asmlinkage u64 kaslr_early_init(void *fdt) +u64 __init kaslr_early_init(void *fdt, int chosen) { - u64 seed; + u64 seed, range; - if (is_kaslr_disabled_cmdline(fdt)) + if (kaslr_disabled_cmdline()) return 0; - seed = get_kaslr_seed(fdt); + seed = get_kaslr_seed(fdt, chosen); if (!seed) { if (!__early_cpu_has_rndr() || !__arm64_rndr((unsigned long *)&seed)) return 0; } + memstart_offset_seed = seed & U16_MAX; + /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable * kernel image offset from the seed. Let's place the kernel in the - * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of - * the lower and upper quarters to avoid colliding with other - * allocations. + * 'middle' half of the VMALLOC area, and stay clear of the lower and + * upper quarters to avoid colliding with other allocations. */ - return BIT(VA_BITS_MIN - 3) + (seed & GENMASK(VA_BITS_MIN - 3, 0)); + range = (VMALLOC_END - KIMAGE_VADDR) / 2; + return range / 2 + (((__uint128_t)range * seed) >> 64); } diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c new file mode 100644 index 0000000000..5fa08e13e1 --- /dev/null +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -0,0 +1,253 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel <ardb@google.com> + +#include <linux/init.h> +#include <linux/libfdt.h> +#include <linux/linkage.h> +#include <linux/types.h> +#include <linux/sizes.h> +#include <linux/string.h> + +#include <asm/memory.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/tlbflush.h> + +#include "pi.h" + +extern const u8 __eh_frame_start[], __eh_frame_end[]; + +extern void idmap_cpu_replace_ttbr1(void *pgdir); + +static void __init map_segment(pgd_t *pg_dir, u64 *pgd, u64 va_offset, + void *start, void *end, pgprot_t prot, + bool may_use_cont, int root_level) +{ + map_range(pgd, ((u64)start + va_offset) & ~PAGE_OFFSET, + ((u64)end + va_offset) & ~PAGE_OFFSET, (u64)start, + prot, root_level, (pte_t *)pg_dir, may_use_cont, 0); +} + +static void __init unmap_segment(pgd_t *pg_dir, u64 va_offset, void *start, + void *end, int root_level) +{ + map_segment(pg_dir, NULL, va_offset, start, end, __pgprot(0), + false, root_level); +} + +static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) +{ + bool enable_scs = IS_ENABLED(CONFIG_UNWIND_PATCH_PAC_INTO_SCS); + bool twopass = IS_ENABLED(CONFIG_RELOCATABLE); + u64 pgdp = (u64)init_pg_dir + PAGE_SIZE; + pgprot_t text_prot = PAGE_KERNEL_ROX; + pgprot_t data_prot = PAGE_KERNEL; + pgprot_t prot; + + /* + * External debuggers may need to write directly to the text mapping to + * install SW breakpoints. Allow this (only) when explicitly requested + * with rodata=off. + */ + if (arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF)) + text_prot = PAGE_KERNEL_EXEC; + + /* + * We only enable the shadow call stack dynamically if we are running + * on a system that does not implement PAC or BTI. PAC and SCS provide + * roughly the same level of protection, and BTI relies on the PACIASP + * instructions serving as landing pads, preventing us from patching + * those instructions into something else. + */ + if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && cpu_has_pac()) + enable_scs = false; + + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && cpu_has_bti()) { + enable_scs = false; + + /* + * If we have a CPU that supports BTI and a kernel built for + * BTI then mark the kernel executable text as guarded pages + * now so we don't have to rewrite the page tables later. + */ + text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP); + } + + /* Map all code read-write on the first pass if needed */ + twopass |= enable_scs; + prot = twopass ? data_prot : text_prot; + + map_segment(init_pg_dir, &pgdp, va_offset, _stext, _etext, prot, + !twopass, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __start_rodata, + __inittext_begin, data_prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __inittext_begin, + __inittext_end, prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __initdata_begin, + __initdata_end, data_prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, _data, _end, data_prot, + true, root_level); + dsb(ishst); + + idmap_cpu_replace_ttbr1(init_pg_dir); + + if (twopass) { + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate_kernel(kaslr_offset); + + if (enable_scs) { + scs_patch(__eh_frame_start + va_offset, + __eh_frame_end - __eh_frame_start); + asm("ic ialluis"); + + dynamic_scs_is_enabled = true; + } + + /* + * Unmap the text region before remapping it, to avoid + * potential TLB conflicts when creating the contiguous + * descriptors. + */ + unmap_segment(init_pg_dir, va_offset, _stext, _etext, + root_level); + dsb(ishst); + isb(); + __tlbi(vmalle1); + isb(); + + /* + * Remap these segments with different permissions + * No new page table allocations should be needed + */ + map_segment(init_pg_dir, NULL, va_offset, _stext, _etext, + text_prot, true, root_level); + map_segment(init_pg_dir, NULL, va_offset, __inittext_begin, + __inittext_end, text_prot, false, root_level); + } + + /* Copy the root page table to its final location */ + memcpy((void *)swapper_pg_dir + va_offset, init_pg_dir, PAGE_SIZE); + dsb(ishst); + idmap_cpu_replace_ttbr1(swapper_pg_dir); +} + +static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr) +{ + u64 sctlr = read_sysreg(sctlr_el1); + u64 tcr = read_sysreg(tcr_el1) | TCR_DS; + + asm(" msr sctlr_el1, %0 ;" + " isb ;" + " msr ttbr0_el1, %1 ;" + " msr tcr_el1, %2 ;" + " isb ;" + " tlbi vmalle1 ;" + " dsb nsh ;" + " isb ;" + " msr sctlr_el1, %3 ;" + " isb ;" + :: "r"(sctlr & ~SCTLR_ELx_M), "r"(ttbr), "r"(tcr), "r"(sctlr)); +} + +static void __init remap_idmap_for_lpa2(void) +{ + /* clear the bits that change meaning once LPA2 is turned on */ + pteval_t mask = PTE_SHARED; + + /* + * We have to clear bits [9:8] in all block or page descriptors in the + * initial ID map, as otherwise they will be (mis)interpreted as + * physical address bits once we flick the LPA2 switch (TCR.DS). Since + * we cannot manipulate live descriptors in that way without creating + * potential TLB conflicts, let's create another temporary ID map in a + * LPA2 compatible fashion, and update the initial ID map while running + * from that. + */ + create_init_idmap(init_pg_dir, mask); + dsb(ishst); + set_ttbr0_for_lpa2((u64)init_pg_dir); + + /* + * Recreate the initial ID map with the same granularity as before. + * Don't bother with the FDT, we no longer need it after this. + */ + memset(init_idmap_pg_dir, 0, + (u64)init_idmap_pg_dir - (u64)init_idmap_pg_end); + + create_init_idmap(init_idmap_pg_dir, mask); + dsb(ishst); + + /* switch back to the updated initial ID map */ + set_ttbr0_for_lpa2((u64)init_idmap_pg_dir); + + /* wipe the temporary ID map from memory */ + memset(init_pg_dir, 0, (u64)init_pg_end - (u64)init_pg_dir); +} + +static void __init map_fdt(u64 fdt) +{ + static u8 ptes[INIT_IDMAP_FDT_SIZE] __initdata __aligned(PAGE_SIZE); + u64 efdt = fdt + MAX_FDT_SIZE; + u64 ptep = (u64)ptes; + + /* + * Map up to MAX_FDT_SIZE bytes, but avoid overlap with + * the kernel image. + */ + map_range(&ptep, fdt, (u64)_text > fdt ? min((u64)_text, efdt) : efdt, + fdt, PAGE_KERNEL, IDMAP_ROOT_LEVEL, + (pte_t *)init_idmap_pg_dir, false, 0); + dsb(ishst); +} + +asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) +{ + static char const chosen_str[] __initconst = "/chosen"; + u64 va_base, pa_base = (u64)&_text; + u64 kaslr_offset = pa_base % MIN_KIMG_ALIGN; + int root_level = 4 - CONFIG_PGTABLE_LEVELS; + int va_bits = VA_BITS; + int chosen; + + map_fdt((u64)fdt); + + /* Clear BSS and the initial page tables */ + memset(__bss_start, 0, (u64)init_pg_end - (u64)__bss_start); + + /* Parse the command line for CPU feature overrides */ + chosen = fdt_path_offset(fdt, chosen_str); + init_feature_override(boot_status, fdt, chosen); + + if (IS_ENABLED(CONFIG_ARM64_64K_PAGES) && !cpu_has_lva()) { + va_bits = VA_BITS_MIN; + } else if (IS_ENABLED(CONFIG_ARM64_LPA2) && !cpu_has_lpa2()) { + va_bits = VA_BITS_MIN; + root_level++; + } + + if (va_bits > VA_BITS_MIN) + sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(va_bits)); + + /* + * The virtual KASLR displacement modulo 2MiB is decided by the + * physical placement of the image, as otherwise, we might not be able + * to create the early kernel mapping using 2 MiB block descriptors. So + * take the low bits of the KASLR offset from the physical address, and + * fill in the high bits from the seed. + */ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + u64 kaslr_seed = kaslr_early_init(fdt, chosen); + + if (kaslr_seed && kaslr_requires_kpti()) + arm64_use_ng_mappings = true; + + kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1); + } + + if (IS_ENABLED(CONFIG_ARM64_LPA2) && va_bits > VA_BITS_MIN) + remap_idmap_for_lpa2(); + + va_base = KIMAGE_VADDR + kaslr_offset; + map_kernel(kaslr_offset, va_base - pa_base, root_level); +} diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c new file mode 100644 index 0000000000..5410b2cac5 --- /dev/null +++ b/arch/arm64/kernel/pi/map_range.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel <ardb@google.com> + +#include <linux/types.h> +#include <linux/sizes.h> + +#include <asm/memory.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> + +#include "pi.h" + +/** + * map_range - Map a contiguous range of physical pages into virtual memory + * + * @pte: Address of physical pointer to array of pages to + * allocate page tables from + * @start: Virtual address of the start of the range + * @end: Virtual address of the end of the range (exclusive) + * @pa: Physical address of the start of the range + * @prot: Access permissions of the range + * @level: Translation level for the mapping + * @tbl: The level @level page table to create the mappings in + * @may_use_cont: Whether the use of the contiguous attribute is allowed + * @va_offset: Offset between a physical page and its current mapping + * in the VA space + */ +void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset) +{ + u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX; + u64 protval = pgprot_val(prot) & ~PTE_TYPE_MASK; + int lshift = (3 - level) * (PAGE_SHIFT - 3); + u64 lmask = (PAGE_SIZE << lshift) - 1; + + start &= PAGE_MASK; + pa &= PAGE_MASK; + + /* Advance tbl to the entry that covers start */ + tbl += (start >> (lshift + PAGE_SHIFT)) % PTRS_PER_PTE; + + /* + * Set the right block/page bits for this level unless we are + * clearing the mapping + */ + if (protval) + protval |= (level < 3) ? PMD_TYPE_SECT : PTE_TYPE_PAGE; + + while (start < end) { + u64 next = min((start | lmask) + 1, PAGE_ALIGN(end)); + + if (level < 3 && (start | next | pa) & lmask) { + /* + * This chunk needs a finer grained mapping. Create a + * table mapping if necessary and recurse. + */ + if (pte_none(*tbl)) { + *tbl = __pte(__phys_to_pte_val(*pte) | + PMD_TYPE_TABLE | PMD_TABLE_UXN); + *pte += PTRS_PER_PTE * sizeof(pte_t); + } + map_range(pte, start, next, pa, prot, level + 1, + (pte_t *)(__pte_to_phys(*tbl) + va_offset), + may_use_cont, va_offset); + } else { + /* + * Start a contiguous range if start and pa are + * suitably aligned + */ + if (((start | pa) & cmask) == 0 && may_use_cont) + protval |= PTE_CONT; + + /* + * Clear the contiguous attribute if the remaining + * range does not cover a contiguous block + */ + if ((end & ~cmask) <= start) + protval &= ~PTE_CONT; + + /* Put down a block or page mapping */ + *tbl = __pte(__phys_to_pte_val(pa) | protval); + } + pa += next - start; + start = next; + tbl++; + } +} + +asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir, pteval_t clrmask) +{ + u64 ptep = (u64)pg_dir + PAGE_SIZE; + pgprot_t text_prot = PAGE_KERNEL_ROX; + pgprot_t data_prot = PAGE_KERNEL; + + pgprot_val(text_prot) &= ~clrmask; + pgprot_val(data_prot) &= ~clrmask; + + map_range(&ptep, (u64)_stext, (u64)__initdata_begin, (u64)_stext, + text_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + map_range(&ptep, (u64)__initdata_begin, (u64)_end, (u64)__initdata_begin, + data_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + + return ptep; +} diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c index a1fe4b4ff5..49d8b40e61 100644 --- a/arch/arm64/kernel/patch-scs.c +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -4,16 +4,17 @@ * Author: Ard Biesheuvel <ardb@google.com> */ -#include <linux/bug.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/linkage.h> -#include <linux/printk.h> #include <linux/types.h> -#include <asm/cacheflush.h> #include <asm/scs.h> +#include "pi.h" + +bool dynamic_scs_is_enabled; + // // This minimal DWARF CFI parser is partially based on the code in // arch/arc/kernel/unwind.c, and on the document below: @@ -49,8 +50,6 @@ #define DW_CFA_GNU_negative_offset_extended 0x2f #define DW_CFA_hi_user 0x3f -extern const u8 __eh_frame_start[], __eh_frame_end[]; - enum { PACIASP = 0xd503233f, AUTIASP = 0xd50323bf, @@ -81,7 +80,11 @@ static void __always_inline scs_patch_loc(u64 loc) */ return; } - dcache_clean_pou(loc, loc + sizeof(u32)); + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_CLEAN_CACHE)) + asm("dc civac, %0" :: "r"(loc)); + else + asm(ALTERNATIVE("dc cvau, %0", "nop", ARM64_HAS_CACHE_IDC) + :: "r"(loc)); } /* @@ -128,10 +131,10 @@ struct eh_frame { }; }; -static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, - bool fde_has_augmentation_data, - int code_alignment_factor, - bool dry_run) +static int scs_handle_fde_frame(const struct eh_frame *frame, + bool fde_has_augmentation_data, + int code_alignment_factor, + bool dry_run) { int size = frame->size - offsetof(struct eh_frame, opcodes) + 4; u64 loc = (u64)offset_to_ptr(&frame->initial_loc); @@ -198,14 +201,13 @@ static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, break; default: - pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame); return -ENOEXEC; } } return 0; } -int noinstr scs_patch(const u8 eh_frame[], int size) +int scs_patch(const u8 eh_frame[], int size) { const u8 *p = eh_frame; @@ -250,13 +252,3 @@ int noinstr scs_patch(const u8 eh_frame[], int size) } return 0; } - -asmlinkage void __init scs_patch_vmlinux(void) -{ - if (!should_patch_pac_into_scs()) - return; - - WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start)); - icache_inval_all_pou(); - isb(); -} diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h new file mode 100644 index 0000000000..c91e5e965c --- /dev/null +++ b/arch/arm64/kernel/pi/pi.h @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel <ardb@google.com> + +#include <linux/types.h> + +#define __prel64_initconst __section(".init.rodata.prel64") + +#define PREL64(type, name) union { type *name; prel64_t name ## _prel; } + +#define prel64_pointer(__d) (typeof(__d))prel64_to_pointer(&__d##_prel) + +typedef volatile signed long prel64_t; + +static inline void *prel64_to_pointer(const prel64_t *offset) +{ + if (!*offset) + return NULL; + return (void *)offset + *offset; +} + +extern bool dynamic_scs_is_enabled; + +extern pgd_t init_idmap_pg_dir[], init_idmap_pg_end[]; + +void init_feature_override(u64 boot_status, const void *fdt, int chosen); +u64 kaslr_early_init(void *fdt, int chosen); +void relocate_kernel(u64 offset); +int scs_patch(const u8 eh_frame[], int size); + +void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset); + +asmlinkage void early_map_kernel(u64 boot_status, void *fdt); + +asmlinkage u64 create_init_idmap(pgd_t *pgd, pteval_t clrmask); diff --git a/arch/arm64/kernel/pi/relacheck.c b/arch/arm64/kernel/pi/relacheck.c new file mode 100644 index 0000000000..b0cd4d0d27 --- /dev/null +++ b/arch/arm64/kernel/pi/relacheck.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 - Google LLC + * Author: Ard Biesheuvel <ardb@google.com> + */ + +#include <elf.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define HOST_ORDER ELFDATA2LSB +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#define HOST_ORDER ELFDATA2MSB +#endif + +static Elf64_Ehdr *ehdr; +static Elf64_Shdr *shdr; +static const char *strtab; +static bool swap; + +static uint64_t swab_elfxword(uint64_t val) +{ + return swap ? __builtin_bswap64(val) : val; +} + +static uint32_t swab_elfword(uint32_t val) +{ + return swap ? __builtin_bswap32(val) : val; +} + +static uint16_t swab_elfhword(uint16_t val) +{ + return swap ? __builtin_bswap16(val) : val; +} + +int main(int argc, char *argv[]) +{ + struct stat stat; + int fd, ret; + + if (argc < 3) { + fprintf(stderr, "file arguments missing\n"); + exit(EXIT_FAILURE); + } + + fd = open(argv[1], O_RDWR); + if (fd < 0) { + fprintf(stderr, "failed to open %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + ret = fstat(fd, &stat); + if (ret < 0) { + fprintf(stderr, "failed to stat() %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + ehdr = mmap(0, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (ehdr == MAP_FAILED) { + fprintf(stderr, "failed to mmap() %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + swap = ehdr->e_ident[EI_DATA] != HOST_ORDER; + shdr = (void *)ehdr + swab_elfxword(ehdr->e_shoff); + strtab = (void *)ehdr + + swab_elfxword(shdr[swab_elfhword(ehdr->e_shstrndx)].sh_offset); + + for (int i = 0; i < swab_elfhword(ehdr->e_shnum); i++) { + unsigned long info, flags; + bool prel64 = false; + Elf64_Rela *rela; + int numrela; + + if (swab_elfword(shdr[i].sh_type) != SHT_RELA) + continue; + + /* only consider RELA sections operating on data */ + info = swab_elfword(shdr[i].sh_info); + flags = swab_elfxword(shdr[info].sh_flags); + if ((flags & (SHF_ALLOC | SHF_EXECINSTR)) != SHF_ALLOC) + continue; + + /* + * We generally don't permit ABS64 relocations in the code that + * runs before relocation processing occurs. If statically + * initialized absolute symbol references are unavoidable, they + * may be emitted into a *.rodata.prel64 section and they will + * be converted to place-relative 64-bit references. This + * requires special handling in the referring code. + */ + if (strstr(strtab + swab_elfword(shdr[info].sh_name), + ".rodata.prel64")) { + prel64 = true; + } + + rela = (void *)ehdr + swab_elfxword(shdr[i].sh_offset); + numrela = swab_elfxword(shdr[i].sh_size) / sizeof(*rela); + + for (int j = 0; j < numrela; j++) { + uint64_t info = swab_elfxword(rela[j].r_info); + + if (ELF64_R_TYPE(info) != R_AARCH64_ABS64) + continue; + + if (prel64) { + /* convert ABS64 into PREL64 */ + info ^= R_AARCH64_ABS64 ^ R_AARCH64_PREL64; + rela[j].r_info = swab_elfxword(info); + } else { + fprintf(stderr, + "Unexpected absolute relocations detected in %s\n", + argv[2]); + close(fd); + unlink(argv[1]); + exit(EXIT_FAILURE); + } + } + } + close(fd); + return 0; +} diff --git a/arch/arm64/kernel/pi/relocate.c b/arch/arm64/kernel/pi/relocate.c new file mode 100644 index 0000000000..2407d26963 --- /dev/null +++ b/arch/arm64/kernel/pi/relocate.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Authors: Ard Biesheuvel <ardb@google.com> +// Peter Collingbourne <pcc@google.com> + +#include <linux/elf.h> +#include <linux/init.h> +#include <linux/types.h> + +#include "pi.h" + +extern const Elf64_Rela rela_start[], rela_end[]; +extern const u64 relr_start[], relr_end[]; + +void __init relocate_kernel(u64 offset) +{ + u64 *place = NULL; + + for (const Elf64_Rela *rela = rela_start; rela < rela_end; rela++) { + if (ELF64_R_TYPE(rela->r_info) != R_AARCH64_RELATIVE) + continue; + *(u64 *)(rela->r_offset + offset) = rela->r_addend + offset; + } + + if (!IS_ENABLED(CONFIG_RELR) || !offset) + return; + + /* + * Apply RELR relocations. + * + * RELR is a compressed format for storing relative relocations. The + * encoded sequence of entries looks like: + * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ] + * + * i.e. start with an address, followed by any number of bitmaps. The + * address entry encodes 1 relocation. The subsequent bitmap entries + * encode up to 63 relocations each, at subsequent offsets following + * the last address entry. + * + * The bitmap entries must have 1 in the least significant bit. The + * assumption here is that an address cannot have 1 in lsb. Odd + * addresses are not supported. Any odd addresses are stored in the + * RELA section, which is handled above. + * + * With the exception of the least significant bit, each bit in the + * bitmap corresponds with a machine word that follows the base address + * word, and the bit value indicates whether or not a relocation needs + * to be applied to it. The second least significant bit represents the + * machine word immediately following the initial address, and each bit + * that follows represents the next word, in linear order. As such, a + * single bitmap can encode up to 63 relocations in a 64-bit object. + */ + for (const u64 *relr = relr_start; relr < relr_end; relr++) { + if ((*relr & 1) == 0) { + place = (u64 *)(*relr + offset); + *place++ += offset; + } else { + for (u64 *p = place, r = *relr >> 1; r; p++, r >>= 1) + if (r & 1) + *p += offset; + place += 63; + } + } +} diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 70b91a8c6b..327855a11d 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -371,6 +371,21 @@ static struct break_hook kprobes_break_ss_hook = { .fn = kprobe_breakpoint_ss_handler, }; +static int __kprobes +kretprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr) +{ + if (regs->pc != (unsigned long)__kretprobe_trampoline) + return DBG_HOOK_ERROR; + + regs->pc = kretprobe_trampoline_handler(regs, (void *)regs->regs[29]); + return DBG_HOOK_HANDLED; +} + +static struct break_hook kretprobes_break_hook = { + .imm = KRETPROBES_BRK_IMM, + .fn = kretprobe_breakpoint_handler, +}; + /* * Provide a blacklist of symbols identifying ranges which cannot be kprobed. * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). @@ -396,11 +411,6 @@ int __init arch_populate_kprobe_blacklist(void) return ret; } -void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) -{ - return (void *)kretprobe_trampoline_handler(regs, (void *)regs->regs[29]); -} - void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -420,6 +430,7 @@ int __init arch_init_kprobes(void) { register_kernel_break_hook(&kprobes_break_hook); register_kernel_break_hook(&kprobes_break_ss_hook); + register_kernel_break_hook(&kretprobes_break_hook); return 0; } diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 9a6499bed5..a362f3dbb3 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -4,83 +4,17 @@ */ #include <linux/linkage.h> -#include <asm/asm-offsets.h> +#include <asm/asm-bug.h> #include <asm/assembler.h> .text - .macro save_all_base_regs - stp x0, x1, [sp, #S_X0] - stp x2, x3, [sp, #S_X2] - stp x4, x5, [sp, #S_X4] - stp x6, x7, [sp, #S_X6] - stp x8, x9, [sp, #S_X8] - stp x10, x11, [sp, #S_X10] - stp x12, x13, [sp, #S_X12] - stp x14, x15, [sp, #S_X14] - stp x16, x17, [sp, #S_X16] - stp x18, x19, [sp, #S_X18] - stp x20, x21, [sp, #S_X20] - stp x22, x23, [sp, #S_X22] - stp x24, x25, [sp, #S_X24] - stp x26, x27, [sp, #S_X26] - stp x28, x29, [sp, #S_X28] - add x0, sp, #PT_REGS_SIZE - stp lr, x0, [sp, #S_LR] - /* - * Construct a useful saved PSTATE - */ - mrs x0, nzcv - mrs x1, daif - orr x0, x0, x1 - mrs x1, CurrentEL - orr x0, x0, x1 - mrs x1, SPSel - orr x0, x0, x1 - stp xzr, x0, [sp, #S_PC] - .endm - - .macro restore_all_base_regs - ldr x0, [sp, #S_PSTATE] - and x0, x0, #(PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT) - msr nzcv, x0 - ldp x0, x1, [sp, #S_X0] - ldp x2, x3, [sp, #S_X2] - ldp x4, x5, [sp, #S_X4] - ldp x6, x7, [sp, #S_X6] - ldp x8, x9, [sp, #S_X8] - ldp x10, x11, [sp, #S_X10] - ldp x12, x13, [sp, #S_X12] - ldp x14, x15, [sp, #S_X14] - ldp x16, x17, [sp, #S_X16] - ldp x18, x19, [sp, #S_X18] - ldp x20, x21, [sp, #S_X20] - ldp x22, x23, [sp, #S_X22] - ldp x24, x25, [sp, #S_X24] - ldp x26, x27, [sp, #S_X26] - ldp x28, x29, [sp, #S_X28] - .endm - SYM_CODE_START(__kretprobe_trampoline) - sub sp, sp, #PT_REGS_SIZE - - save_all_base_regs - - /* Setup a frame pointer. */ - add x29, sp, #S_FP - - mov x0, sp - bl trampoline_probe_handler /* - * Replace trampoline address in lr with actual orig_ret_addr return - * address. + * Trigger a breakpoint exception. The PC will be adjusted by + * kretprobe_breakpoint_handler(), and no subsequent instructions will + * be executed from the trampoline. */ - mov lr, x0 - - /* The frame pointer (x29) is restored with other registers. */ - restore_all_base_regs - - add sp, sp, #PT_REGS_SIZE - ret - + brk #KRETPROBES_BRK_IMM + ASM_BUG() SYM_CODE_END(__kretprobe_trampoline) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 7387b68c74..4ae31b7af6 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -290,9 +290,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) fpsimd_preserve_current_state(); *dst = *src; - /* We rely on the above assignment to initialize dst's thread_flags: */ - BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK)); - /* * Detach src's sve_state (if any) from dst so that it does not * get erroneously used or freed prematurely. dst's copies diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 964d0446da..0d022599eb 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -174,7 +174,6 @@ static void ptrace_hbptriggered(struct perf_event *bp, struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); const char *desc = "Hardware breakpoint trap (ptrace)"; -#ifdef CONFIG_COMPAT if (is_compat_task()) { int si_errno = 0; int i; @@ -196,7 +195,7 @@ static void ptrace_hbptriggered(struct perf_event *bp, desc); return; } -#endif + arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc); } @@ -698,6 +697,39 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, return ret; } +static int fpmr_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_fpmr()) + return -EINVAL; + + if (target == current) + fpsimd_preserve_current_state(); + + return membuf_store(&to, target->thread.uw.fpmr); +} + +static int fpmr_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; + unsigned long fpmr; + + if (!system_supports_fpmr()) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count); + if (ret) + return ret; + + target->thread.uw.fpmr = fpmr; + + fpsimd_flush_task_state(target); + + return 0; +} + static int system_call_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) @@ -1416,6 +1448,7 @@ enum aarch64_regset { REGSET_HW_BREAK, REGSET_HW_WATCH, #endif + REGSET_FPMR, REGSET_SYSTEM_CALL, #ifdef CONFIG_ARM64_SVE REGSET_SVE, @@ -1494,6 +1527,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = system_call_get, .set = system_call_set, }, + [REGSET_FPMR] = { + .core_note_type = NT_ARM_FPMR, + .n = 1, + .size = sizeof(u64), + .align = sizeof(u64), + .regset_get = fpmr_get, + .set = fpmr_set, + }, #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, @@ -1594,7 +1635,6 @@ static const struct user_regset_view user_aarch64_view = { .regsets = aarch64_regsets, .n = ARRAY_SIZE(aarch64_regsets) }; -#ifdef CONFIG_COMPAT enum compat_regset { REGSET_COMPAT_GPR, REGSET_COMPAT_VFP, @@ -1851,6 +1891,7 @@ static const struct user_regset_view user_aarch32_ptrace_view = { .regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets) }; +#ifdef CONFIG_COMPAT static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t __user *ret) { @@ -2112,7 +2153,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, const struct user_regset_view *task_user_regset_view(struct task_struct *task) { -#ifdef CONFIG_COMPAT /* * Core dumping of 32-bit tasks or compat ptrace requests must use the * user_aarch32_view compatible with arm32. Native ptrace requests on @@ -2123,7 +2163,7 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) return &user_aarch32_view; else if (is_compat_thread(task_thread_info(task))) return &user_aarch32_ptrace_view; -#endif + return &user_aarch64_view; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 42c690bb2d..65a052bf74 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -166,21 +166,6 @@ static void __init smp_build_mpidr_hash(void) pr_warn("Large number of MPIDR hash buckets detected\n"); } -static void *early_fdt_ptr __initdata; - -void __init *get_early_fdt_ptr(void) -{ - return early_fdt_ptr; -} - -asmlinkage void __init early_fdt_map(u64 dt_phys) -{ - int fdt_size; - - early_fixmap_init(); - early_fdt_ptr = fixmap_remap_fdt(dt_phys, &fdt_size, PAGE_KERNEL); -} - static void __init setup_machine_fdt(phys_addr_t dt_phys) { int size; @@ -298,13 +283,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) kaslr_init(); - /* - * If know now we are going to need KPTI then use non-global - * mappings from the start, avoiding the cost of rewriting - * everything later. - */ - arm64_use_ng_mappings = kaslr_requires_kpti(); - early_fixmap_init(); early_ioremap_init(); @@ -320,9 +298,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) dynamic_scs_init(); /* - * Unmask asynchronous aborts and fiq after bringing up possible - * earlycon. (Report possible System Errors once we can report this - * occurred). + * Unmask SError as soon as possible after initializing earlycon so + * that we can report any SErrors immediately. */ local_daif_restore(DAIF_PROCCTX_NOIRQ); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 425b1bc17a..4a77f4976e 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -16,8 +16,8 @@ #include <linux/uaccess.h> #include <linux/sizes.h> #include <linux/string.h> -#include <linux/resume_user_mode.h> #include <linux/ratelimit.h> +#include <linux/rseq.h> #include <linux/syscalls.h> #include <asm/daifflags.h> @@ -60,6 +60,7 @@ struct rt_sigframe_user_layout { unsigned long tpidr2_offset; unsigned long za_offset; unsigned long zt_offset; + unsigned long fpmr_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -182,6 +183,8 @@ struct user_ctxs { u32 za_size; struct zt_context __user *zt; u32 zt_size; + struct fpmr_context __user *fpmr; + u32 fpmr_size; }; static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) @@ -227,6 +230,33 @@ static int restore_fpsimd_context(struct user_ctxs *user) return err ? -EFAULT : 0; } +static int preserve_fpmr_context(struct fpmr_context __user *ctx) +{ + int err = 0; + + current->thread.uw.fpmr = read_sysreg_s(SYS_FPMR); + + __put_user_error(FPMR_MAGIC, &ctx->head.magic, err); + __put_user_error(sizeof(*ctx), &ctx->head.size, err); + __put_user_error(current->thread.uw.fpmr, &ctx->fpmr, err); + + return err; +} + +static int restore_fpmr_context(struct user_ctxs *user) +{ + u64 fpmr; + int err = 0; + + if (user->fpmr_size != sizeof(*user->fpmr)) + return -EINVAL; + + __get_user_error(fpmr, &user->fpmr->fpmr, err); + if (!err) + write_sysreg_s(fpmr, SYS_FPMR); + + return err; +} #ifdef CONFIG_ARM64_SVE @@ -590,6 +620,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->tpidr2 = NULL; user->za = NULL; user->zt = NULL; + user->fpmr = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -684,6 +715,17 @@ static int parse_user_sigframe(struct user_ctxs *user, user->zt_size = size; break; + case FPMR_MAGIC: + if (!system_supports_fpmr()) + goto invalid; + + if (user->fpmr) + goto invalid; + + user->fpmr = (struct fpmr_context __user *)head; + user->fpmr_size = size; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -806,6 +848,9 @@ static int restore_sigframe(struct pt_regs *regs, if (err == 0 && system_supports_tpidr2() && user.tpidr2) err = restore_tpidr2_context(&user); + if (err == 0 && system_supports_fpmr() && user.fpmr) + err = restore_fpmr_context(&user); + if (err == 0 && system_supports_sme() && user.za) err = restore_za_context(&user); @@ -928,6 +973,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, } } + if (system_supports_fpmr()) { + err = sigframe_alloc(user, &user->fpmr_offset, + sizeof(struct fpmr_context)); + if (err) + return err; + } + return sigframe_alloc_end(user); } @@ -983,6 +1035,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_tpidr2_context(tpidr2_ctx); } + /* FPMR if supported */ + if (system_supports_fpmr() && err == 0) { + struct fpmr_context __user *fpmr_ctx = + apply_user_offset(user, user->fpmr_offset); + err |= preserve_fpmr_context(fpmr_ctx); + } + /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = @@ -1207,7 +1266,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) * the kernel can handle, and then we build all the user-level signal handling * stack-frames in one go after that. */ -static void do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { unsigned long continue_addr = 0, restart_addr = 0; int retval = 0; @@ -1278,41 +1337,6 @@ static void do_signal(struct pt_regs *regs) restore_saved_sigmask(); } -void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) -{ - do { - if (thread_flags & _TIF_NEED_RESCHED) { - /* Unmask Debug and SError for the next task */ - local_daif_restore(DAIF_PROCCTX_NOIRQ); - - schedule(); - } else { - local_daif_restore(DAIF_PROCCTX); - - if (thread_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - - if (thread_flags & _TIF_MTE_ASYNC_FAULT) { - clear_thread_flag(TIF_MTE_ASYNC_FAULT); - send_sig_fault(SIGSEGV, SEGV_MTEAERR, - (void __user *)NULL, current); - } - - if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) - do_signal(regs); - - if (thread_flags & _TIF_NOTIFY_RESUME) - resume_user_mode_work(regs); - - if (thread_flags & _TIF_FOREIGN_FPSTATE) - fpsimd_restore_current_state(); - } - - local_daif_mask(); - thread_flags = read_thread_flags(); - } while (thread_flags & _TIF_WORK_MASK); -} - unsigned long __ro_after_init signal_minsigstksz; /* diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 2aa5129d82..f093cdf71b 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -102,9 +102,6 @@ SYM_CODE_START(cpu_resume) mov x0, xzr bl init_kernel_el mov x19, x0 // preserve boot mode -#if VA_BITS > 48 - ldr_l x0, vabits_actual -#endif bl __cpu_setup /* enable the MMU early - so we can access sleep_save_stash by va */ adrp x1, swapper_pg_dir diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index b2a60e0bcf..684c265116 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/efi.h> #include <linux/export.h> +#include <linux/filter.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/sched.h> @@ -266,6 +267,31 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, kunwind_stack_walk(arch_kunwind_consume_entry, &data, task, regs); } +struct bpf_unwind_consume_entry_data { + bool (*consume_entry)(void *cookie, u64 ip, u64 sp, u64 fp); + void *cookie; +}; + +static bool +arch_bpf_unwind_consume_entry(const struct kunwind_state *state, void *cookie) +{ + struct bpf_unwind_consume_entry_data *data = cookie; + + return data->consume_entry(data->cookie, state->common.pc, 0, + state->common.fp); +} + +noinline noinstr void arch_bpf_stack_walk(bool (*consume_entry)(void *cookie, u64 ip, u64 sp, + u64 fp), void *cookie) +{ + struct bpf_unwind_consume_entry_data data = { + .consume_entry = consume_entry, + .cookie = cookie, + }; + + kunwind_stack_walk(arch_bpf_unwind_consume_entry, &data, current, NULL); +} + static bool dump_backtrace_entry(void *arg, unsigned long where) { char *loglvl = arg; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 9a70d9746b..ad198262b9 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -20,14 +20,11 @@ long sys_ni_syscall(void); static long do_ni_syscall(struct pt_regs *regs, int scno) { -#ifdef CONFIG_COMPAT - long ret; if (is_compat_task()) { - ret = compat_arm_syscall(regs, scno); + long ret = compat_arm_syscall(regs, scno); if (ret != -ENOSYS) return ret; } -#endif return sys_ni_syscall(); } diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 5562daf38a..89b6e78400 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -69,10 +69,7 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = { /* * The vDSO data page. */ -static union { - struct vdso_data data[CS_BASES]; - u8 page[PAGE_SIZE]; -} vdso_data_store __page_aligned_data; +static union vdso_data_store vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = vdso_data_store.data; static int vdso_mremap(const struct vm_special_mapping *sm, diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/vmcore_info.c index 66cde752cd..b19d5d6cb8 100644 --- a/arch/arm64/kernel/crash_core.c +++ b/arch/arm64/kernel/vmcore_info.c @@ -4,7 +4,7 @@ * Copyright (C) Huawei Futurewei Technologies. */ -#include <linux/crash_core.h> +#include <linux/vmcore_info.h> #include <asm/cpufeature.h> #include <asm/memory.h> #include <asm/pgtable-hwdef.h> @@ -23,7 +23,6 @@ void arch_crash_save_vmcoreinfo(void) /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); - vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 3cd7e76cc5..755a22d4f8 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -126,9 +126,9 @@ jiffies = jiffies_64; #ifdef CONFIG_UNWIND_TABLES #define UNWIND_DATA_SECTIONS \ .eh_frame : { \ - __eh_frame_start = .; \ + __pi___eh_frame_start = .; \ *(.eh_frame) \ - __eh_frame_end = .; \ + __pi___eh_frame_end = .; \ } #else #define UNWIND_DATA_SECTIONS @@ -270,15 +270,15 @@ SECTIONS HYPERVISOR_RELOC_SECTION .rela.dyn : ALIGN(8) { - __rela_start = .; + __pi_rela_start = .; *(.rela .rela*) - __rela_end = .; + __pi_rela_end = .; } .relr.dyn : ALIGN(8) { - __relr_start = .; + __pi_relr_start = .; *(.relr.dyn) - __relr_end = .; + __pi_relr_end = .; } . = ALIGN(SEGMENT_ALIGN); @@ -311,12 +311,17 @@ SECTIONS __pecoff_data_rawsize = ABSOLUTE(. - __initdata_begin); _edata = .; + /* start of zero-init region */ BSS_SECTION(SBSS_ALIGN, 0, 0) . = ALIGN(PAGE_SIZE); init_pg_dir = .; . += INIT_DIR_SIZE; init_pg_end = .; + /* end of zero-init region */ + + . += SZ_4K; /* stack for the early C runtime */ + early_init_stack = .; . = ALIGN(SEGMENT_ALIGN); __pecoff_data_size = ABSOLUTE(. - __initdata_begin); |