summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/kernel')
-rw-r--r--arch/arm64/kernel/Makefile4
-rw-r--r--arch/arm64/kernel/alternative.c6
-rw-r--r--arch/arm64/kernel/cpu_errata.c4
-rw-r--r--arch/arm64/kernel/cpufeature.c182
-rw-r--r--arch/arm64/kernel/cpuinfo.c13
-rw-r--r--arch/arm64/kernel/debug-monitors.c12
-rw-r--r--arch/arm64/kernel/elfcore.c49
-rw-r--r--arch/arm64/kernel/entry-common.c25
-rw-r--r--arch/arm64/kernel/entry-fpsimd.S36
-rw-r--r--arch/arm64/kernel/entry-ftrace.S17
-rw-r--r--arch/arm64/kernel/entry.S2
-rw-r--r--arch/arm64/kernel/fpsimd.c655
-rw-r--r--arch/arm64/kernel/ftrace.c17
-rw-r--r--arch/arm64/kernel/hw_breakpoint.c6
-rw-r--r--arch/arm64/kernel/kgdb.c6
-rw-r--r--arch/arm64/kernel/machine_kexec.c9
-rw-r--r--arch/arm64/kernel/machine_kexec_file.c12
-rw-r--r--arch/arm64/kernel/module-plts.c2
-rw-r--r--arch/arm64/kernel/mte.c48
-rw-r--r--arch/arm64/kernel/paravirt.c29
-rw-r--r--arch/arm64/kernel/patching.c4
-rw-r--r--arch/arm64/kernel/probes/kprobes.c4
-rw-r--r--arch/arm64/kernel/probes/uprobes.c4
-rw-r--r--arch/arm64/kernel/process.c44
-rw-r--r--arch/arm64/kernel/proton-pack.c1
-rw-r--r--arch/arm64/kernel/ptrace.c366
-rw-r--r--arch/arm64/kernel/relocate_kernel.S22
-rw-r--r--arch/arm64/kernel/setup.c17
-rw-r--r--arch/arm64/kernel/signal.c189
-rw-r--r--arch/arm64/kernel/signal32.c1
-rw-r--r--arch/arm64/kernel/smp.c3
-rw-r--r--arch/arm64/kernel/stacktrace.c124
-rw-r--r--arch/arm64/kernel/suspend.c2
-rw-r--r--arch/arm64/kernel/sys_compat.c2
-rw-r--r--arch/arm64/kernel/syscall.c29
-rw-r--r--arch/arm64/kernel/traps.c67
-rw-r--r--arch/arm64/kernel/vdso/Makefile6
-rw-r--r--arch/arm64/kernel/vdso32/Makefile3
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S21
39 files changed, 1656 insertions, 387 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 986837d7ec82..fa7981d0d917 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -75,6 +75,10 @@ obj-$(CONFIG_ARM64_MTE) += mte.o
obj-y += vdso-wrap.o
obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o
+# Force dependency (vdso*-wrap.S includes vdso.so through incbin)
+$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
+$(obj)/vdso32-wrap.o: $(obj)/vdso32/vdso.so
+
obj-y += probes/
head-y := head.o
extra-y += $(head-y) vmlinux.lds
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 3fb79b76e9d9..7bbf5104b7b7 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature)
/*
* Check if the target PC is within an alternative block.
*/
-static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
+static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
{
unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
return !(pc >= replptr && pc <= (replptr + alt->alt_len));
@@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
#define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
-static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr)
+static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr)
{
u32 insn;
@@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp
return insn;
}
-static void patch_alternative(struct alt_instr *alt,
+static noinstr void patch_alternative(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
__le32 *replptr;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 4c9b5b4b7a0b..c05cc3b6162e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
#ifdef CONFIG_ARM64_ERRATUM_1286807
{
ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+ /* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */
+ ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe),
},
#endif
{},
@@ -215,7 +217,7 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
#endif
#ifdef CONFIG_CAVIUM_ERRATUM_23154
-const struct midr_range cavium_erratum_23154_cpus[] = {
+static const struct midr_range cavium_erratum_23154_cpus[] = {
MIDR_ALL_VERSIONS(MIDR_THUNDERX),
MIDR_ALL_VERSIONS(MIDR_THUNDERX_81XX),
MIDR_ALL_VERSIONS(MIDR_THUNDERX_83XX),
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d72c4b4d389c..4ccddf382e5b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -191,20 +191,20 @@ static bool __system_matches_cap(unsigned int n);
* sync with the documentation of the CPU feature register ABI.
*/
static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RNDR_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TLB_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TS_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA3_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA1_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_AES_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_TLB_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_TS_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_FHM_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_DP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SM4_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SM3_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA3_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_RDM_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_ATOMIC_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_CRC32_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA1_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_AES_SHIFT, 4, 0),
ARM64_FTR_END,
};
@@ -261,6 +261,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SME_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE),
@@ -293,6 +295,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
ARM64_FTR_END,
};
+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_FA64_SHIFT, 1, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I16I64_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F64F64_SHIFT, 1, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I8I32_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F16F32_SHIFT, 1, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_B16F32_SHIFT, 1, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F32F32_SHIFT, 1, 0),
+ ARM64_FTR_END,
+};
+
static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0),
@@ -557,7 +577,13 @@ static const struct arm64_ftr_bits ftr_id_dfr1[] = {
static const struct arm64_ftr_bits ftr_zcr[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
- ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_SIZE, 0), /* LEN */
+ ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_WIDTH, 0), /* LEN */
+ ARM64_FTR_END,
+};
+
+static const struct arm64_ftr_bits ftr_smcr[] = {
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
+ SMCR_ELx_LEN_SHIFT, SMCR_ELx_LEN_WIDTH, 0), /* LEN */
ARM64_FTR_END,
};
@@ -645,6 +671,7 @@ static const struct __ftr_reg_entry {
ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1,
&id_aa64pfr1_override),
ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
+ ARM64_FTR_REG(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0),
/* Op1 = 0, CRn = 0, CRm = 5 */
ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -654,7 +681,6 @@ static const struct __ftr_reg_entry {
ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0),
ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1,
&id_aa64isar1_override),
- ARM64_FTR_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2),
ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2,
&id_aa64isar2_override),
@@ -666,6 +692,7 @@ static const struct __ftr_reg_entry {
/* Op1 = 0, CRn = 1, CRm = 2 */
ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
+ ARM64_FTR_REG(SYS_SMCR_EL1, ftr_smcr),
/* Op1 = 1, CRn = 0, CRm = 0 */
ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid),
@@ -810,7 +837,7 @@ static void __init sort_ftr_regs(void)
* to sys_id for subsequent binary search in get_arm64_ftr_reg()
* to work correctly.
*/
- BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id);
+ BUG_ON(arm64_ftr_regs[i].sys_id <= arm64_ftr_regs[i - 1].sys_id);
}
}
@@ -960,6 +987,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
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_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
+ init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0);
if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
init_32bit_cpu_features(&info->aarch32);
@@ -969,6 +997,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
vec_init_vq_map(ARM64_VEC_SVE);
}
+ if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) {
+ init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr);
+ if (IS_ENABLED(CONFIG_ARM64_SME))
+ vec_init_vq_map(ARM64_VEC_SME);
+ }
+
if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
@@ -1195,6 +1229,9 @@ void update_cpu_features(int cpu,
taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu,
info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0);
+ taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu,
+ info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0);
+
if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
info->reg_zcr, boot->reg_zcr);
@@ -1205,6 +1242,16 @@ void update_cpu_features(int cpu,
vec_update_vq_map(ARM64_VEC_SVE);
}
+ if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) {
+ taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu,
+ info->reg_smcr, boot->reg_smcr);
+
+ /* Probe vector lengths, unless we already gave up on SME */
+ if (id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1)) &&
+ !system_capabilities_finalized())
+ vec_update_vq_map(ARM64_VEC_SME);
+ }
+
/*
* The kernel uses the LDGM/STGM instructions and the number of tags
* they read/write depends on the GMID_EL1.BS field. Check that the
@@ -1288,6 +1335,7 @@ 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_AA64ZFR0_EL1);
+ read_sysreg_case(SYS_ID_AA64SMFR0_EL1);
read_sysreg_case(SYS_ID_AA64DFR0_EL1);
read_sysreg_case(SYS_ID_AA64DFR1_EL1);
read_sysreg_case(SYS_ID_AA64MMFR0_EL1);
@@ -2013,7 +2061,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cpuid_feature,
.sys_reg = SYS_ID_AA64ISAR0_EL1,
- .field_pos = ID_AA64ISAR0_ATOMICS_SHIFT,
+ .field_pos = ID_AA64ISAR0_EL1_ATOMIC_SHIFT,
.field_width = 4,
.sign = FTR_UNSIGNED,
.min_field_value = 2,
@@ -2195,10 +2243,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cpuid_feature,
.sys_reg = SYS_ID_AA64ISAR0_EL1,
- .field_pos = ID_AA64ISAR0_TLB_SHIFT,
+ .field_pos = ID_AA64ISAR0_EL1_TLB_SHIFT,
.field_width = 4,
.sign = FTR_UNSIGNED,
- .min_field_value = ID_AA64ISAR0_TLB_RANGE,
+ .min_field_value = ID_AA64ISAR0_EL1_TLB_RANGE,
},
#ifdef CONFIG_ARM64_HW_AFDBM
{
@@ -2227,7 +2275,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cpuid_feature,
.sys_reg = SYS_ID_AA64ISAR0_EL1,
- .field_pos = ID_AA64ISAR0_CRC32_SHIFT,
+ .field_pos = ID_AA64ISAR0_EL1_CRC32_SHIFT,
.field_width = 4,
.min_field_value = 1,
},
@@ -2382,7 +2430,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cpuid_feature,
.sys_reg = SYS_ID_AA64ISAR0_EL1,
- .field_pos = ID_AA64ISAR0_RNDR_SHIFT,
+ .field_pos = ID_AA64ISAR0_EL1_RNDR_SHIFT,
.field_width = 4,
.sign = FTR_UNSIGNED,
.min_field_value = 1,
@@ -2442,6 +2490,33 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = has_cpuid_feature,
.min_field_value = 1,
},
+#ifdef CONFIG_ARM64_SME
+ {
+ .desc = "Scalable Matrix Extension",
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_SME,
+ .sys_reg = SYS_ID_AA64PFR1_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64PFR1_SME_SHIFT,
+ .field_width = 4,
+ .min_field_value = ID_AA64PFR1_SME,
+ .matches = has_cpuid_feature,
+ .cpu_enable = sme_kernel_enable,
+ },
+ /* FA64 should be sorted after the base SME capability */
+ {
+ .desc = "FA64",
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_SME_FA64,
+ .sys_reg = SYS_ID_AA64SMFR0_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64SMFR0_FA64_SHIFT,
+ .field_width = 1,
+ .min_field_value = ID_AA64SMFR0_FA64,
+ .matches = has_cpuid_feature,
+ .cpu_enable = fa64_kernel_enable,
+ },
+#endif /* CONFIG_ARM64_SME */
{},
};
@@ -2514,22 +2589,22 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = {
#endif
static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_ATOMIC_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RDM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SHA3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM3_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_SM4_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
@@ -2575,6 +2650,16 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
+#ifdef CONFIG_ARM64_SME
+ HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_FA64, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I16I64, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F64F64, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I8I32, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F16F32, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_B16F32, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F32F32, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+#endif /* CONFIG_ARM64_SME */
{},
};
@@ -2872,6 +2957,23 @@ static void verify_sve_features(void)
/* Add checks on other ZCR bits here if necessary */
}
+static void verify_sme_features(void)
+{
+ u64 safe_smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
+ u64 smcr = read_smcr_features();
+
+ unsigned int safe_len = safe_smcr & SMCR_ELx_LEN_MASK;
+ unsigned int len = smcr & SMCR_ELx_LEN_MASK;
+
+ if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) {
+ pr_crit("CPU%d: SME: vector length support mismatch\n",
+ smp_processor_id());
+ cpu_die_early();
+ }
+
+ /* Add checks on other SMCR bits here if necessary */
+}
+
static void verify_hyp_capabilities(void)
{
u64 safe_mmfr1, mmfr0, mmfr1;
@@ -2924,6 +3026,9 @@ static void verify_local_cpu_capabilities(void)
if (system_supports_sve())
verify_sve_features();
+ if (system_supports_sme())
+ verify_sme_features();
+
if (is_hyp_mode_available())
verify_hyp_capabilities();
}
@@ -3041,6 +3146,7 @@ void __init setup_cpu_features(void)
pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
sve_setup();
+ sme_setup();
minsigstksz_setup();
/* Advertise that we have computed the system capabilities */
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 330b92ea863a..8a8136a096ac 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -98,6 +98,14 @@ static const char *const hwcap_str[] = {
[KERNEL_HWCAP_AFP] = "afp",
[KERNEL_HWCAP_RPRES] = "rpres",
[KERNEL_HWCAP_MTE3] = "mte3",
+ [KERNEL_HWCAP_SME] = "sme",
+ [KERNEL_HWCAP_SME_I16I64] = "smei16i64",
+ [KERNEL_HWCAP_SME_F64F64] = "smef64f64",
+ [KERNEL_HWCAP_SME_I8I32] = "smei8i32",
+ [KERNEL_HWCAP_SME_F16F32] = "smef16f32",
+ [KERNEL_HWCAP_SME_B16F32] = "smeb16f32",
+ [KERNEL_HWCAP_SME_F32F32] = "smef32f32",
+ [KERNEL_HWCAP_SME_FA64] = "smefa64",
};
#ifdef CONFIG_COMPAT
@@ -401,6 +409,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
+ info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1);
if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
info->reg_gmid = read_cpuid(GMID_EL1);
@@ -412,6 +421,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
id_aa64pfr0_sve(info->reg_id_aa64pfr0))
info->reg_zcr = read_zcr_features();
+ if (IS_ENABLED(CONFIG_ARM64_SME) &&
+ id_aa64pfr1_sme(info->reg_id_aa64pfr1))
+ info->reg_smcr = read_smcr_features();
+
cpuinfo_detect_icache_policy(info);
}
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 4f3661eeb7ec..bf9fe71589bc 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -202,7 +202,7 @@ void unregister_kernel_step_hook(struct step_hook *hook)
* So we call all the registered handlers, until the right handler is
* found which returns zero.
*/
-static int call_step_hook(struct pt_regs *regs, unsigned int esr)
+static int call_step_hook(struct pt_regs *regs, unsigned long esr)
{
struct step_hook *hook;
struct list_head *list;
@@ -238,7 +238,7 @@ static void send_user_sigtrap(int si_code)
"User debug trap");
}
-static int single_step_handler(unsigned long unused, unsigned int esr,
+static int single_step_handler(unsigned long unused, unsigned long esr,
struct pt_regs *regs)
{
bool handler_found = false;
@@ -299,11 +299,11 @@ void unregister_kernel_break_hook(struct break_hook *hook)
unregister_debug_hook(&hook->node);
}
-static int call_break_hook(struct pt_regs *regs, unsigned int esr)
+static int call_break_hook(struct pt_regs *regs, unsigned long esr)
{
struct break_hook *hook;
struct list_head *list;
- int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
+ int (*fn)(struct pt_regs *regs, unsigned long esr) = NULL;
list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
@@ -312,7 +312,7 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
* entirely not preemptible, and we can use rcu list safely here.
*/
list_for_each_entry_rcu(hook, list, node) {
- unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+ unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
if ((comment & ~hook->mask) == hook->imm)
fn = hook->fn;
@@ -322,7 +322,7 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
}
NOKPROBE_SYMBOL(call_break_hook);
-static int brk_handler(unsigned long unused, unsigned int esr,
+static int brk_handler(unsigned long unused, unsigned long esr,
struct pt_regs *regs)
{
if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index 3ed39c61a510..98d67444a5b6 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -8,16 +8,9 @@
#include <asm/cpufeature.h>
#include <asm/mte.h>
-#ifndef VMA_ITERATOR
-#define VMA_ITERATOR(name, mm, addr) \
- struct mm_struct *name = mm
-#define for_each_vma(vmi, vma) \
- for (vma = vmi->mmap; vma; vma = vma->vm_next)
-#endif
-
-#define for_each_mte_vma(vmi, vma) \
+#define for_each_mte_vma(tsk, vma) \
if (system_supports_mte()) \
- for_each_vma(vmi, vma) \
+ for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \
if (vma->vm_flags & VM_MTE)
static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
@@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
static int mte_dump_tag_range(struct coredump_params *cprm,
unsigned long start, unsigned long end)
{
+ int ret = 1;
unsigned long addr;
+ void *tags = NULL;
for (addr = start; addr < end; addr += PAGE_SIZE) {
- char tags[MTE_PAGE_TAG_STORAGE];
struct page *page = get_dump_page(addr);
/*
@@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
continue;
}
+ if (!tags) {
+ tags = mte_allocate_tag_storage();
+ if (!tags) {
+ put_page(page);
+ ret = 0;
+ break;
+ }
+ }
+
mte_save_page_tags(page_address(page), tags);
put_page(page);
- if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE))
- return 0;
+ if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) {
+ mte_free_tag_storage(tags);
+ ret = 0;
+ break;
+ }
}
- return 1;
+ if (tags)
+ mte_free_tag_storage(tags);
+
+ return ret;
}
Elf_Half elf_core_extra_phdrs(void)
{
struct vm_area_struct *vma;
int vma_count = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
+ for_each_mte_vma(current, vma)
vma_count++;
return vma_count;
@@ -83,12 +91,11 @@ Elf_Half elf_core_extra_phdrs(void)
int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
{
struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma) {
+ for_each_mte_vma(current, vma) {
struct elf_phdr phdr;
- phdr.p_type = PT_ARM_MEMTAG_MTE;
+ phdr.p_type = PT_AARCH64_MEMTAG_MTE;
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
@@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void)
{
struct vm_area_struct *vma;
size_t data_size = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
+ for_each_mte_vma(current, vma)
data_size += mte_vma_tag_dump_size(vma);
return data_size;
@@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void)
int elf_core_write_extra_data(struct coredump_params *cprm)
{
struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma) {
+ for_each_mte_vma(current, vma) {
if (vma->vm_flags & VM_DONTDUMP)
continue;
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 878c65aa7206..56cefd33eb8e 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -75,7 +75,7 @@ static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs)
if (interrupts_enabled(regs)) {
if (regs->exit_rcu) {
trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ lockdep_hardirqs_on_prepare();
rcu_irq_exit();
lockdep_hardirqs_on(CALLER_ADDR0);
return;
@@ -121,7 +121,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
static __always_inline void __exit_to_user_mode(void)
{
trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ lockdep_hardirqs_on_prepare();
user_enter_irqoff();
lockdep_hardirqs_on(CALLER_ADDR0);
}
@@ -179,7 +179,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs)
ftrace_nmi_exit();
if (restore) {
trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ lockdep_hardirqs_on_prepare();
}
rcu_nmi_exit();
@@ -215,7 +215,7 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
if (restore) {
trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ lockdep_hardirqs_on_prepare();
}
rcu_nmi_exit();
@@ -282,13 +282,13 @@ extern void (*handle_arch_irq)(struct pt_regs *);
extern void (*handle_arch_fiq)(struct pt_regs *);
static void noinstr __panic_unhandled(struct pt_regs *regs, const char *vector,
- unsigned int esr)
+ unsigned long esr)
{
arm64_enter_nmi(regs);
console_verbose();
- pr_crit("Unhandled %s exception on CPU%d, ESR 0x%08x -- %s\n",
+ pr_crit("Unhandled %s exception on CPU%d, ESR 0x%016lx -- %s\n",
vector, smp_processor_id(), esr,
esr_get_class_string(esr));
@@ -537,6 +537,14 @@ static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr)
exit_to_user_mode(regs);
}
+static void noinstr el0_sme_acc(struct pt_regs *regs, unsigned long esr)
+{
+ enter_from_user_mode(regs);
+ local_daif_restore(DAIF_PROCCTX);
+ do_sme_acc(esr, regs);
+ exit_to_user_mode(regs);
+}
+
static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
{
enter_from_user_mode(regs);
@@ -645,6 +653,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs)
case ESR_ELx_EC_SVE:
el0_sve_acc(regs, esr);
break;
+ case ESR_ELx_EC_SME:
+ el0_sme_acc(regs, esr);
+ break;
case ESR_ELx_EC_FP_EXC64:
el0_fpsimd_exc(regs, esr);
break;
@@ -818,7 +829,7 @@ UNHANDLED(el0t, 32, error)
#ifdef CONFIG_VMAP_STACK
asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs)
{
- unsigned int esr = read_sysreg(esr_el1);
+ unsigned long esr = read_sysreg(esr_el1);
unsigned long far = read_sysreg(far_el1);
arm64_enter_nmi(regs);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index dc242e269f9a..229436f33df5 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -86,3 +86,39 @@ SYM_FUNC_START(sve_flush_live)
SYM_FUNC_END(sve_flush_live)
#endif /* CONFIG_ARM64_SVE */
+
+#ifdef CONFIG_ARM64_SME
+
+SYM_FUNC_START(sme_get_vl)
+ _sme_rdsvl 0, 1
+ ret
+SYM_FUNC_END(sme_get_vl)
+
+SYM_FUNC_START(sme_set_vq)
+ sme_load_vq x0, x1, x2
+ ret
+SYM_FUNC_END(sme_set_vq)
+
+/*
+ * Save the SME state
+ *
+ * x0 - pointer to buffer for state
+ */
+SYM_FUNC_START(za_save_state)
+ _sme_rdsvl 1, 1 // x1 = VL/8
+ sme_save_za 0, x1, 12
+ ret
+SYM_FUNC_END(za_save_state)
+
+/*
+ * Load the SME state
+ *
+ * x0 - pointer to buffer for state
+ */
+SYM_FUNC_START(za_load_state)
+ _sme_rdsvl 1, 1 // x1 = VL/8
+ sme_load_za 0, x1, 12
+ ret
+SYM_FUNC_END(za_load_state)
+
+#endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index e535480a4069..d42a205ef625 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -97,12 +97,6 @@ SYM_CODE_START(ftrace_common)
SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
bl ftrace_stub
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
- nop // If enabled, this will be replaced
- // "b ftrace_graph_caller"
-#endif
-
/*
* At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
* x19-x29 per the AAPCS, and we created frame records upon entry, so we need
@@ -127,17 +121,6 @@ ftrace_common_return:
ret x9
SYM_CODE_END(ftrace_common)
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_CODE_START(ftrace_graph_caller)
- ldr x0, [sp, #S_PC]
- sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
- add x1, sp, #S_LR // parent_ip (callsite's LR)
- ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP)
- bl prepare_ftrace_return
- b ftrace_common_return
-SYM_CODE_END(ftrace_graph_caller)
-#endif
-
#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
/*
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index ede028dee81b..5b82b9292400 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -596,7 +596,7 @@ SYM_CODE_START_LOCAL(ret_to_user)
ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step
enable_step_tsk x19, x2
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
- bl stackleak_erase
+ bl stackleak_erase_on_task_stack
#endif
kernel_exit 0
SYM_CODE_END(ret_to_user)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 47af76e53221..819979398127 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -121,7 +121,10 @@
struct fpsimd_last_state_struct {
struct user_fpsimd_state *st;
void *sve_state;
+ void *za_state;
+ u64 *svcr;
unsigned int sve_vl;
+ unsigned int sme_vl;
};
static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -136,6 +139,12 @@ __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
.max_virtualisable_vl = SVE_VL_MIN,
},
#endif
+#ifdef CONFIG_ARM64_SME
+ [ARM64_VEC_SME] = {
+ .type = ARM64_VEC_SME,
+ .name = "SME",
+ },
+#endif
};
static unsigned int vec_vl_inherit_flag(enum vec_type type)
@@ -143,6 +152,8 @@ static unsigned int vec_vl_inherit_flag(enum vec_type type)
switch (type) {
case ARM64_VEC_SVE:
return TIF_SVE_VL_INHERIT;
+ case ARM64_VEC_SME:
+ return TIF_SME_VL_INHERIT;
default:
WARN_ON_ONCE(1);
return 0;
@@ -186,6 +197,26 @@ extern void __percpu *efi_sve_state;
#endif /* ! CONFIG_ARM64_SVE */
+#ifdef CONFIG_ARM64_SME
+
+static int get_sme_default_vl(void)
+{
+ return get_default_vl(ARM64_VEC_SME);
+}
+
+static void set_sme_default_vl(int val)
+{
+ set_default_vl(ARM64_VEC_SME, val);
+}
+
+static void sme_free(struct task_struct *);
+
+#else
+
+static inline void sme_free(struct task_struct *t) { }
+
+#endif
+
DEFINE_PER_CPU(bool, fpsimd_context_busy);
EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
@@ -206,10 +237,19 @@ static void __get_cpu_fpsimd_context(void)
*
* The double-underscore version must only be called if you know the task
* can't be preempted.
+ *
+ * On RT kernels local_bh_disable() is not sufficient because it only
+ * serializes soft interrupt related sections via a local lock, but stays
+ * preemptible. Disabling preemption is the right choice here as bottom
+ * half processing is always in thread context on RT kernels so it
+ * implicitly prevents bottom half processing as well.
*/
static void get_cpu_fpsimd_context(void)
{
- local_bh_disable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_bh_disable();
+ else
+ preempt_disable();
__get_cpu_fpsimd_context();
}
@@ -230,7 +270,10 @@ static void __put_cpu_fpsimd_context(void)
static void put_cpu_fpsimd_context(void)
{
__put_cpu_fpsimd_context();
- local_bh_enable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_bh_enable();
+ else
+ preempt_enable();
}
static bool have_cpu_fpsimd_context(void)
@@ -238,23 +281,6 @@ static bool have_cpu_fpsimd_context(void)
return !preemptible() && __this_cpu_read(fpsimd_context_busy);
}
-/*
- * Call __sve_free() directly only if you know task can't be scheduled
- * or preempted.
- */
-static void __sve_free(struct task_struct *task)
-{
- kfree(task->thread.sve_state);
- task->thread.sve_state = NULL;
-}
-
-static void sve_free(struct task_struct *task)
-{
- WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
-
- __sve_free(task);
-}
-
unsigned int task_get_vl(const struct task_struct *task, enum vec_type type)
{
return task->thread.vl[type];
@@ -279,16 +305,27 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
}
/*
+ * TIF_SME controls whether a task can use SME without trapping while
+ * in userspace, when TIF_SME is set then we must have storage
+ * alocated in sve_state and za_state to store the contents of both ZA
+ * and the SVE registers for both streaming and non-streaming modes.
+ *
+ * If both SVCR.ZA and SVCR.SM are disabled then at any point we
+ * may disable TIF_SME and reenable traps.
+ */
+
+
+/*
* TIF_SVE controls whether a task can use SVE without trapping while
- * in userspace, and also the way a task's FPSIMD/SVE state is stored
- * in thread_struct.
+ * in userspace, and also (together with TIF_SME) the way a task's
+ * FPSIMD/SVE state is stored in thread_struct.
*
* The kernel uses this flag to track whether a user task is actively
* using SVE, and therefore whether full SVE register state needs to
* be tracked. If not, the cheaper FPSIMD context handling code can
* be used instead of the more costly SVE equivalents.
*
- * * TIF_SVE set:
+ * * TIF_SVE or SVCR.SM set:
*
* The task can execute SVE instructions while in userspace without
* trapping to the kernel.
@@ -296,7 +333,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
* When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
* corresponding Zn), P0-P15 and FFR are encoded in in
* task->thread.sve_state, formatted appropriately for vector
- * length task->thread.sve_vl.
+ * length task->thread.sve_vl or, if SVCR.SM is set,
+ * task->thread.sme_vl.
*
* task->thread.sve_state must point to a valid buffer at least
* sve_state_size(task) bytes in size.
@@ -334,16 +372,44 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
*/
static void task_fpsimd_load(void)
{
+ bool restore_sve_regs = false;
+ bool restore_ffr;
+
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
+ /* Check if we should restore SVE first */
if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
+ restore_sve_regs = true;
+ restore_ffr = true;
+ }
+
+ /* Restore SME, override SVE register configuration if needed */
+ if (system_supports_sme()) {
+ unsigned long sme_vl = task_get_sme_vl(current);
+
+ /* Ensure VL is set up for restoring data */
+ if (test_thread_flag(TIF_SME))
+ sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
+
+ write_sysreg_s(current->thread.svcr, SYS_SVCR);
+
+ if (thread_za_enabled(&current->thread))
+ za_load_state(current->thread.za_state);
+
+ if (thread_sm_enabled(&current->thread)) {
+ restore_sve_regs = true;
+ restore_ffr = system_supports_fa64();
+ }
+ }
+
+ if (restore_sve_regs)
sve_load_state(sve_pffr(&current->thread),
- &current->thread.uw.fpsimd_state.fpsr, true);
- } else {
+ &current->thread.uw.fpsimd_state.fpsr,
+ restore_ffr);
+ else
fpsimd_load_state(&current->thread.uw.fpsimd_state);
- }
}
/*
@@ -361,6 +427,9 @@ static void fpsimd_save(void)
struct fpsimd_last_state_struct const *last =
this_cpu_ptr(&fpsimd_last_state);
/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
+ bool save_sve_regs = false;
+ bool save_ffr;
+ unsigned int vl;
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
@@ -368,9 +437,32 @@ static void fpsimd_save(void)
if (test_thread_flag(TIF_FOREIGN_FPSTATE))
return;
- if (IS_ENABLED(CONFIG_ARM64_SVE) &&
- test_thread_flag(TIF_SVE)) {
- if (WARN_ON(sve_get_vl() != last->sve_vl)) {
+ if (test_thread_flag(TIF_SVE)) {
+ save_sve_regs = true;
+ save_ffr = true;
+ vl = last->sve_vl;
+ }
+
+ if (system_supports_sme()) {
+ u64 *svcr = last->svcr;
+ *svcr = read_sysreg_s(SYS_SVCR);
+
+ *svcr = read_sysreg_s(SYS_SVCR);
+
+ if (*svcr & SVCR_ZA_MASK)
+ za_save_state(last->za_state);
+
+ /* If we are in streaming mode override regular SVE. */
+ if (*svcr & SVCR_SM_MASK) {
+ save_sve_regs = true;
+ save_ffr = system_supports_fa64();
+ vl = last->sme_vl;
+ }
+ }
+
+ if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) {
+ /* Get the configured VL from RDVL, will account for SM */
+ if (WARN_ON(sve_get_vl() != vl)) {
/*
* Can't save the user regs, so current would
* re-enter user with corrupt state.
@@ -381,8 +473,8 @@ static void fpsimd_save(void)
}
sve_save_state((char *)last->sve_state +
- sve_ffr_offset(last->sve_vl),
- &last->st->fpsr, true);
+ sve_ffr_offset(vl),
+ &last->st->fpsr, save_ffr);
} else {
fpsimd_save_state(last->st);
}
@@ -409,6 +501,8 @@ static unsigned int find_supported_vector_length(enum vec_type type,
if (vl > max_vl)
vl = max_vl;
+ if (vl < info->min_vl)
+ vl = info->min_vl;
bit = find_next_bit(info->vq_map, SVE_VQ_MAX,
__vq_to_bit(sve_vq_from_vl(vl)));
@@ -467,6 +561,30 @@ static int __init sve_sysctl_init(void)
static int __init sve_sysctl_init(void) { return 0; }
#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
+#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL)
+static struct ctl_table sme_default_vl_table[] = {
+ {
+ .procname = "sme_default_vector_length",
+ .mode = 0644,
+ .proc_handler = vec_proc_do_default_vl,
+ .extra1 = &vl_info[ARM64_VEC_SME],
+ },
+ { }
+};
+
+static int __init sme_sysctl_init(void)
+{
+ if (system_supports_sme())
+ if (!register_sysctl("abi", sme_default_vl_table))
+ return -EINVAL;
+
+ return 0;
+}
+
+#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
+static int __init sme_sysctl_init(void) { return 0; }
+#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
+
#define ZREG(sve_state, vq, n) ((char *)(sve_state) + \
(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
@@ -520,7 +638,7 @@ static void fpsimd_to_sve(struct task_struct *task)
if (!system_supports_sve())
return;
- vq = sve_vq_from_vl(task_get_sve_vl(task));
+ vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
__fpsimd_to_sve(sst, fst, vq);
}
@@ -537,7 +655,7 @@ static void fpsimd_to_sve(struct task_struct *task)
*/
static void sve_to_fpsimd(struct task_struct *task)
{
- unsigned int vq;
+ unsigned int vq, vl;
void const *sst = task->thread.sve_state;
struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
unsigned int i;
@@ -546,7 +664,8 @@ static void sve_to_fpsimd(struct task_struct *task)
if (!system_supports_sve())
return;
- vq = sve_vq_from_vl(task_get_sve_vl(task));
+ vl = thread_get_cur_vl(&task->thread);
+ vq = sve_vq_from_vl(vl);
for (i = 0; i < SVE_NUM_ZREGS; ++i) {
p = (__uint128_t const *)ZREG(sst, vq, i);
fst->vregs[i] = arm64_le128_to_cpu(*p);
@@ -554,14 +673,37 @@ static void sve_to_fpsimd(struct task_struct *task)
}
#ifdef CONFIG_ARM64_SVE
+/*
+ * Call __sve_free() directly only if you know task can't be scheduled
+ * or preempted.
+ */
+static void __sve_free(struct task_struct *task)
+{
+ kfree(task->thread.sve_state);
+ task->thread.sve_state = NULL;
+}
+
+static void sve_free(struct task_struct *task)
+{
+ WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
+
+ __sve_free(task);
+}
/*
* Return how many bytes of memory are required to store the full SVE
* state for task, given task's currently configured vector length.
*/
-static size_t sve_state_size(struct task_struct const *task)
+size_t sve_state_size(struct task_struct const *task)
{
- return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task)));
+ unsigned int vl = 0;
+
+ if (system_supports_sve())
+ vl = task_get_sve_vl(task);
+ if (system_supports_sme())
+ vl = max(vl, task_get_sme_vl(task));
+
+ return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
}
/*
@@ -588,6 +730,19 @@ void sve_alloc(struct task_struct *task)
/*
+ * Force the FPSIMD state shared with SVE to be updated in the SVE state
+ * even if the SVE state is the current active state.
+ *
+ * This should only be called by ptrace. task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void fpsimd_force_sync_to_sve(struct task_struct *task)
+{
+ fpsimd_to_sve(task);
+}
+
+/*
* Ensure that task->thread.sve_state is up to date with respect to
* the user task, irrespective of when SVE is in use or not.
*
@@ -597,7 +752,8 @@ void sve_alloc(struct task_struct *task)
*/
void fpsimd_sync_to_sve(struct task_struct *task)
{
- if (!test_tsk_thread_flag(task, TIF_SVE))
+ if (!test_tsk_thread_flag(task, TIF_SVE) &&
+ !thread_sm_enabled(&task->thread))
fpsimd_to_sve(task);
}
@@ -611,7 +767,8 @@ void fpsimd_sync_to_sve(struct task_struct *task)
*/
void sve_sync_to_fpsimd(struct task_struct *task)
{
- if (test_tsk_thread_flag(task, TIF_SVE))
+ if (test_tsk_thread_flag(task, TIF_SVE) ||
+ thread_sm_enabled(&task->thread))
sve_to_fpsimd(task);
}
@@ -636,7 +793,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
if (!test_tsk_thread_flag(task, TIF_SVE))
return;
- vq = sve_vq_from_vl(task_get_sve_vl(task));
+ vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
__fpsimd_to_sve(sst, fst, vq);
@@ -680,8 +837,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
/*
* To ensure the FPSIMD bits of the SVE vector registers are preserved,
* write any live register state back to task_struct, and convert to a
- * regular FPSIMD thread. Since the vector length can only be changed
- * with a syscall we can't be in streaming mode while reconfiguring.
+ * regular FPSIMD thread.
*/
if (task == current) {
get_cpu_fpsimd_context();
@@ -690,17 +846,26 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
}
fpsimd_flush_task_state(task);
- if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+ if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
+ thread_sm_enabled(&task->thread))
sve_to_fpsimd(task);
+ if (system_supports_sme() && type == ARM64_VEC_SME) {
+ task->thread.svcr &= ~(SVCR_SM_MASK |
+ SVCR_ZA_MASK);
+ clear_thread_flag(TIF_SME);
+ }
+
if (task == current)
put_cpu_fpsimd_context();
/*
- * Force reallocation of task SVE state to the correct size
- * on next use:
+ * Force reallocation of task SVE and SME state to the correct
+ * size on next use:
*/
sve_free(task);
+ if (system_supports_sme() && type == ARM64_VEC_SME)
+ sme_free(task);
task_set_vl(task, type, vl);
@@ -761,6 +926,36 @@ int sve_get_current_vl(void)
return vec_prctl_status(ARM64_VEC_SVE, 0);
}
+#ifdef CONFIG_ARM64_SME
+/* PR_SME_SET_VL */
+int sme_set_current_vl(unsigned long arg)
+{
+ unsigned long vl, flags;
+ int ret;
+
+ vl = arg & PR_SME_VL_LEN_MASK;
+ flags = arg & ~vl;
+
+ if (!system_supports_sme() || is_compat_task())
+ return -EINVAL;
+
+ ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags);
+ if (ret)
+ return ret;
+
+ return vec_prctl_status(ARM64_VEC_SME, flags);
+}
+
+/* PR_SME_GET_VL */
+int sme_get_current_vl(void)
+{
+ if (!system_supports_sme() || is_compat_task())
+ return -EINVAL;
+
+ return vec_prctl_status(ARM64_VEC_SME, 0);
+}
+#endif /* CONFIG_ARM64_SME */
+
static void vec_probe_vqs(struct vl_info *info,
DECLARE_BITMAP(map, SVE_VQ_MAX))
{
@@ -770,7 +965,23 @@ static void vec_probe_vqs(struct vl_info *info,
for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) {
write_vl(info->type, vq - 1); /* self-syncing */
- vl = sve_get_vl();
+
+ switch (info->type) {
+ case ARM64_VEC_SVE:
+ vl = sve_get_vl();
+ break;
+ case ARM64_VEC_SME:
+ vl = sme_get_vl();
+ break;
+ default:
+ vl = 0;
+ break;
+ }
+
+ /* Minimum VL identified? */
+ if (sve_vq_from_vl(vl) > vq)
+ break;
+
vq = sve_vq_from_vl(vl); /* skip intervening lengths */
set_bit(__vq_to_bit(vq), map);
}
@@ -856,21 +1067,25 @@ int vec_verify_vq_map(enum vec_type type)
static void __init sve_efi_setup(void)
{
- struct vl_info *info = &vl_info[ARM64_VEC_SVE];
+ int max_vl = 0;
+ int i;
if (!IS_ENABLED(CONFIG_EFI))
return;
+ for (i = 0; i < ARRAY_SIZE(vl_info); i++)
+ max_vl = max(vl_info[i].max_vl, max_vl);
+
/*
* alloc_percpu() warns and prints a backtrace if this goes wrong.
* This is evidence of a crippled system and we are returning void,
* so no attempt is made to handle this situation here.
*/
- if (!sve_vl_valid(info->max_vl))
+ if (!sve_vl_valid(max_vl))
goto fail;
efi_sve_state = __alloc_percpu(
- SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES);
+ SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES);
if (!efi_sve_state)
goto fail;
@@ -989,10 +1204,172 @@ void __init sve_setup(void)
void fpsimd_release_task(struct task_struct *dead_task)
{
__sve_free(dead_task);
+ sme_free(dead_task);
}
#endif /* CONFIG_ARM64_SVE */
+#ifdef CONFIG_ARM64_SME
+
+/*
+ * Ensure that task->thread.za_state is allocated and sufficiently large.
+ *
+ * This function should be used only in preparation for replacing
+ * task->thread.za_state with new data. The memory is always zeroed
+ * here to prevent stale data from showing through: this is done in
+ * the interest of testability and predictability, the architecture
+ * guarantees that when ZA is enabled it will be zeroed.
+ */
+void sme_alloc(struct task_struct *task)
+{
+ if (task->thread.za_state) {
+ memset(task->thread.za_state, 0, za_state_size(task));
+ return;
+ }
+
+ /* This could potentially be up to 64K. */
+ task->thread.za_state =
+ kzalloc(za_state_size(task), GFP_KERNEL);
+}
+
+static void sme_free(struct task_struct *task)
+{
+ kfree(task->thread.za_state);
+ task->thread.za_state = NULL;
+}
+
+void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+ /* Set priority for all PEs to architecturally defined minimum */
+ write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK,
+ SYS_SMPRI_EL1);
+
+ /* Allow SME in kernel */
+ write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1);
+ isb();
+
+ /* Allow EL0 to access TPIDR2 */
+ write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1);
+ isb();
+}
+
+/*
+ * This must be called after sme_kernel_enable(), we rely on the
+ * feature table being sorted to ensure this.
+ */
+void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+ /* Allow use of FA64 */
+ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK,
+ SYS_SMCR_EL1);
+}
+
+/*
+ * Read the pseudo-SMCR used by cpufeatures to identify the supported
+ * vector length.
+ *
+ * Use only if SME is present.
+ * This function clobbers the SME vector length.
+ */
+u64 read_smcr_features(void)
+{
+ u64 smcr;
+ unsigned int vq_max;
+
+ sme_kernel_enable(NULL);
+ sme_smstart_sm();
+
+ /*
+ * Set the maximum possible VL.
+ */
+ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK,
+ SYS_SMCR_EL1);
+
+ smcr = read_sysreg_s(SYS_SMCR_EL1);
+ smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
+ vq_max = sve_vq_from_vl(sve_get_vl());
+ smcr |= vq_max - 1; /* set LEN field to maximum effective value */
+
+ sme_smstop_sm();
+
+ return smcr;
+}
+
+void __init sme_setup(void)
+{
+ struct vl_info *info = &vl_info[ARM64_VEC_SME];
+ u64 smcr;
+ int min_bit;
+
+ if (!system_supports_sme())
+ return;
+
+ /*
+ * SME doesn't require any particular vector length be
+ * supported but it does require at least one. We should have
+ * disabled the feature entirely while bringing up CPUs but
+ * let's double check here.
+ */
+ WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX));
+
+ min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX);
+ info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit));
+
+ smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
+ info->max_vl = sve_vl_from_vq((smcr & SMCR_ELx_LEN_MASK) + 1);
+
+ /*
+ * Sanity-check that the max VL we determined through CPU features
+ * corresponds properly to sme_vq_map. If not, do our best:
+ */
+ if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SME,
+ info->max_vl)))
+ info->max_vl = find_supported_vector_length(ARM64_VEC_SME,
+ info->max_vl);
+
+ WARN_ON(info->min_vl > info->max_vl);
+
+ /*
+ * For the default VL, pick the maximum supported value <= 32
+ * (256 bits) if there is one since this is guaranteed not to
+ * grow the signal frame when in streaming mode, otherwise the
+ * minimum available VL will be used.
+ */
+ set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32));
+
+ pr_info("SME: minimum available vector length %u bytes per vector\n",
+ info->min_vl);
+ pr_info("SME: maximum available vector length %u bytes per vector\n",
+ info->max_vl);
+ pr_info("SME: default vector length %u bytes per vector\n",
+ get_sme_default_vl());
+}
+
+#endif /* CONFIG_ARM64_SME */
+
+static void sve_init_regs(void)
+{
+ /*
+ * Convert the FPSIMD state to SVE, zeroing all the state that
+ * is not shared with FPSIMD. If (as is likely) the current
+ * state is live in the registers then do this there and
+ * update our metadata for the current task including
+ * disabling the trap, otherwise update our in-memory copy.
+ * We are guaranteed to not be in streaming mode, we can only
+ * take a SVE trap when not in streaming mode and we can't be
+ * in streaming mode when taking a SME trap.
+ */
+ if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
+ unsigned long vq_minus_one =
+ sve_vq_from_vl(task_get_sve_vl(current)) - 1;
+ sve_set_vq(vq_minus_one);
+ sve_flush_live(true, vq_minus_one);
+ fpsimd_bind_task_to_cpu();
+ } else {
+ fpsimd_to_sve(current);
+ }
+}
+
/*
* Trapped SVE access
*
@@ -1004,7 +1381,7 @@ void fpsimd_release_task(struct task_struct *dead_task)
* would have disabled the SVE access trap for userspace during
* ret_to_user, making an SVE access trap impossible in that case.
*/
-void do_sve_acc(unsigned int esr, struct pt_regs *regs)
+void do_sve_acc(unsigned long esr, struct pt_regs *regs)
{
/* Even if we chose not to use SVE, the hardware could still trap: */
if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
@@ -1024,29 +1401,84 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs)
WARN_ON(1); /* SVE access shouldn't have trapped */
/*
- * Convert the FPSIMD state to SVE, zeroing all the state that
- * is not shared with FPSIMD. If (as is likely) the current
- * state is live in the registers then do this there and
- * update our metadata for the current task including
- * disabling the trap, otherwise update our in-memory copy.
+ * Even if the task can have used streaming mode we can only
+ * generate SVE access traps in normal SVE mode and
+ * transitioning out of streaming mode may discard any
+ * streaming mode state. Always clear the high bits to avoid
+ * any potential errors tracking what is properly initialised.
+ */
+ sve_init_regs();
+
+ put_cpu_fpsimd_context();
+}
+
+/*
+ * Trapped SME access
+ *
+ * Storage is allocated for the full SVE and SME state, the current
+ * FPSIMD register contents are migrated to SVE if SVE is not already
+ * active, and the access trap is disabled.
+ *
+ * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state()
+ * would have disabled the SME access trap for userspace during
+ * ret_to_user, making an SVE access trap impossible in that case.
+ */
+void do_sme_acc(unsigned long esr, struct pt_regs *regs)
+{
+ /* Even if we chose not to use SME, the hardware could still trap: */
+ if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) {
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+ return;
+ }
+
+ /*
+ * If this not a trap due to SME being disabled then something
+ * is being used in the wrong mode, report as SIGILL.
*/
+ if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) {
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+ return;
+ }
+
+ sve_alloc(current);
+ sme_alloc(current);
+ if (!current->thread.sve_state || !current->thread.za_state) {
+ force_sig(SIGKILL);
+ return;
+ }
+
+ get_cpu_fpsimd_context();
+
+ /* With TIF_SME userspace shouldn't generate any traps */
+ if (test_and_set_thread_flag(TIF_SME))
+ WARN_ON(1);
+
if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
unsigned long vq_minus_one =
- sve_vq_from_vl(task_get_sve_vl(current)) - 1;
- sve_set_vq(vq_minus_one);
- sve_flush_live(true, vq_minus_one);
+ sve_vq_from_vl(task_get_sme_vl(current)) - 1;
+ sme_set_vq(vq_minus_one);
+
fpsimd_bind_task_to_cpu();
- } else {
- fpsimd_to_sve(current);
}
+ /*
+ * If SVE was not already active initialise the SVE registers,
+ * any non-shared state between the streaming and regular SVE
+ * registers is architecturally guaranteed to be zeroed when
+ * we enter streaming mode. We do not need to initialize ZA
+ * since ZA must be disabled at this point and enabling ZA is
+ * architecturally defined to zero ZA.
+ */
+ if (system_supports_sve() && !test_thread_flag(TIF_SVE))
+ sve_init_regs();
+
put_cpu_fpsimd_context();
}
/*
* Trapped FP/ASIMD access.
*/
-void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs)
{
/* TODO: implement lazy context saving/restoring */
WARN_ON(1);
@@ -1055,7 +1487,7 @@ void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
/*
* Raise a SIGFPE for the current process.
*/
-void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs)
{
unsigned int si_code = FPE_FLTUNK;
@@ -1141,6 +1573,9 @@ static void fpsimd_flush_thread_vl(enum vec_type type)
void fpsimd_flush_thread(void)
{
+ void *sve_state = NULL;
+ void *za_state = NULL;
+
if (!system_supports_fpsimd())
return;
@@ -1152,11 +1587,28 @@ void fpsimd_flush_thread(void)
if (system_supports_sve()) {
clear_thread_flag(TIF_SVE);
- sve_free(current);
+
+ /* Defer kfree() while in atomic context */
+ sve_state = current->thread.sve_state;
+ current->thread.sve_state = NULL;
+
fpsimd_flush_thread_vl(ARM64_VEC_SVE);
}
+ if (system_supports_sme()) {
+ clear_thread_flag(TIF_SME);
+
+ /* Defer kfree() while in atomic context */
+ za_state = current->thread.za_state;
+ current->thread.za_state = NULL;
+
+ fpsimd_flush_thread_vl(ARM64_VEC_SME);
+ current->thread.svcr = 0;
+ }
+
put_cpu_fpsimd_context();
+ kfree(sve_state);
+ kfree(za_state);
}
/*
@@ -1198,22 +1650,34 @@ static void fpsimd_bind_task_to_cpu(void)
WARN_ON(!system_supports_fpsimd());
last->st = &current->thread.uw.fpsimd_state;
last->sve_state = current->thread.sve_state;
+ last->za_state = current->thread.za_state;
last->sve_vl = task_get_sve_vl(current);
+ last->sme_vl = task_get_sme_vl(current);
+ last->svcr = &current->thread.svcr;
current->thread.fpsimd_cpu = smp_processor_id();
+ /*
+ * Toggle SVE and SME trapping for userspace if needed, these
+ * are serialsied by ret_to_user().
+ */
+ if (system_supports_sme()) {
+ if (test_thread_flag(TIF_SME))
+ sme_user_enable();
+ else
+ sme_user_disable();
+ }
+
if (system_supports_sve()) {
- /* Toggle SVE trapping for userspace if needed */
if (test_thread_flag(TIF_SVE))
sve_user_enable();
else
sve_user_disable();
-
- /* Serialised by exception return to user */
}
}
void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
- unsigned int sve_vl)
+ unsigned int sve_vl, void *za_state,
+ unsigned int sme_vl, u64 *svcr)
{
struct fpsimd_last_state_struct *last =
this_cpu_ptr(&fpsimd_last_state);
@@ -1222,8 +1686,11 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
WARN_ON(!in_softirq() && !irqs_disabled());
last->st = st;
+ last->svcr = svcr;
last->sve_state = sve_state;
+ last->za_state = za_state;
last->sve_vl = sve_vl;
+ last->sme_vl = sme_vl;
}
/*
@@ -1320,6 +1787,15 @@ static void fpsimd_flush_cpu_state(void)
{
WARN_ON(!system_supports_fpsimd());
__this_cpu_write(fpsimd_last_state.st, NULL);
+
+ /*
+ * Leaving streaming mode enabled will cause issues for any kernel
+ * NEON and leaving streaming mode or ZA enabled may increase power
+ * consumption.
+ */
+ if (system_supports_sme())
+ sme_smstop();
+
set_thread_flag(TIF_FOREIGN_FPSTATE);
}
@@ -1397,6 +1873,7 @@ EXPORT_SYMBOL(kernel_neon_end);
static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state);
static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
static DEFINE_PER_CPU(bool, efi_sve_state_used);
+static DEFINE_PER_CPU(bool, efi_sm_state);
/*
* EFI runtime services support functions
@@ -1431,12 +1908,28 @@ void __efi_fpsimd_begin(void)
*/
if (system_supports_sve() && likely(efi_sve_state)) {
char *sve_state = this_cpu_ptr(efi_sve_state);
+ bool ffr = true;
+ u64 svcr;
__this_cpu_write(efi_sve_state_used, true);
+ if (system_supports_sme()) {
+ svcr = read_sysreg_s(SYS_SVCR);
+
+ if (!system_supports_fa64())
+ ffr = svcr & SVCR_SM_MASK;
+
+ __this_cpu_write(efi_sm_state, ffr);
+ }
+
sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()),
&this_cpu_ptr(&efi_fpsimd_state)->fpsr,
- true);
+ ffr);
+
+ if (system_supports_sme())
+ sysreg_clear_set_s(SYS_SVCR,
+ SVCR_SM_MASK, 0);
+
} else {
fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
}
@@ -1459,11 +1952,26 @@ void __efi_fpsimd_end(void)
if (system_supports_sve() &&
likely(__this_cpu_read(efi_sve_state_used))) {
char const *sve_state = this_cpu_ptr(efi_sve_state);
+ bool ffr = true;
+
+ /*
+ * Restore streaming mode; EFI calls are
+ * normal function calls so should not return in
+ * streaming mode.
+ */
+ if (system_supports_sme()) {
+ if (__this_cpu_read(efi_sm_state)) {
+ sysreg_clear_set_s(SYS_SVCR,
+ 0,
+ SVCR_SM_MASK);
+ if (!system_supports_fa64())
+ ffr = efi_sm_state;
+ }
+ }
- sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1);
sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()),
&this_cpu_ptr(&efi_fpsimd_state)->fpsr,
- true);
+ ffr);
__this_cpu_write(efi_sve_state_used, false);
} else {
@@ -1538,6 +2046,13 @@ static int __init fpsimd_init(void)
if (!cpu_have_named_feature(ASIMD))
pr_notice("Advanced SIMD is not implemented\n");
- return sve_sysctl_init();
+
+ if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE))
+ pr_notice("SME is implemented but not SVE\n");
+
+ sve_sysctl_init();
+ sme_sysctl_init();
+
+ return 0;
}
core_initcall(fpsimd_init);
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 4506c4a90ac1..f447c4a36f69 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -268,6 +268,22 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
}
#ifdef CONFIG_DYNAMIC_FTRACE
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+ /*
+ * When DYNAMIC_FTRACE_WITH_REGS is selected, `fregs` can never be NULL
+ * and arch_ftrace_get_regs(fregs) will always give a non-NULL pt_regs
+ * in which we can safely modify the LR.
+ */
+ struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+ unsigned long *parent = (unsigned long *)&procedure_link_pointer(regs);
+
+ prepare_ftrace_return(ip, parent, frame_pointer(regs));
+}
+#else
/*
* Turn on/off the call to ftrace_graph_caller() in ftrace_caller()
* depending on @enable.
@@ -297,5 +313,6 @@ int ftrace_disable_ftrace_graph_caller(void)
{
return ftrace_modify_graph_caller(false);
}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 712e97c03e54..b29a311bb055 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -617,7 +617,7 @@ NOKPROBE_SYMBOL(toggle_bp_registers);
/*
* Debug exception handlers.
*/
-static int breakpoint_handler(unsigned long unused, unsigned int esr,
+static int breakpoint_handler(unsigned long unused, unsigned long esr,
struct pt_regs *regs)
{
int i, step = 0, *kernel_step;
@@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler);
* addresses. There is no straight-forward way, short of disassembling the
* offending instruction, to map that address back to the watchpoint. This
* function computes the distance of the memory access from the watchpoint as a
- * heuristic for the likelyhood that a given access triggered the watchpoint.
+ * heuristic for the likelihood that a given access triggered the watchpoint.
*
* See Section D2.10.5 "Determining the memory location that caused a Watchpoint
* exception" of ARMv8 Architecture Reference Manual for details.
@@ -751,7 +751,7 @@ static int watchpoint_report(struct perf_event *wp, unsigned long addr,
return step;
}
-static int watchpoint_handler(unsigned long addr, unsigned int esr,
+static int watchpoint_handler(unsigned long addr, unsigned long esr,
struct pt_regs *regs)
{
int i, step = 0, *kernel_step, access, closest_match = 0;
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 2aede780fb80..cda9c1e9864f 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -232,14 +232,14 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
return err;
}
-static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
+static int kgdb_brk_fn(struct pt_regs *regs, unsigned long esr)
{
kgdb_handle_exception(1, SIGTRAP, 0, regs);
return DBG_HOOK_HANDLED;
}
NOKPROBE_SYMBOL(kgdb_brk_fn)
-static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
+static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned long esr)
{
compiled_break = 1;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
@@ -248,7 +248,7 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
}
NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
-static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
+static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned long esr)
{
if (!kgdb_single_step)
return DBG_HOOK_ERROR;
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index e16b248699d5..19c2d487cb08 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -329,8 +329,13 @@ bool crash_is_nosave(unsigned long pfn)
/* in reserved memory? */
addr = __pfn_to_phys(pfn);
- if ((addr < crashk_res.start) || (crashk_res.end < addr))
- return false;
+ if ((addr < crashk_res.start) || (crashk_res.end < addr)) {
+ if (!crashk_low_res.end)
+ return false;
+
+ if ((addr < crashk_low_res.start) || (crashk_low_res.end < addr))
+ return false;
+ }
if (!kexec_crash_image)
return true;
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 59c648d51848..889951291cc0 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -65,10 +65,18 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
/* Exclude crashkernel region */
ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
+ if (ret)
+ goto out;
+
+ if (crashk_low_res.end) {
+ ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+ if (ret)
+ goto out;
+ }
- if (!ret)
- ret = crash_prepare_elf64_headers(cmem, true, addr, sz);
+ ret = crash_prepare_elf64_headers(cmem, true, addr, sz);
+out:
kfree(cmem);
return ret;
}
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index e53493d8b208..a3d0494f25a9 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
* increasing the section's alignment so that the
* resulting address of this instruction is guaranteed
* to equal the offset in that particular bit (as well
- * as all less signficant bits). This ensures that the
+ * as all less significant bits). This ensures that the
* address modulo 4 KB != 0xfff8 or 0xfffc (which would
* have all ones in bits [11:3])
*/
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 78b3e0f8e997..57b30bcf9f21 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -15,6 +15,7 @@
#include <linux/swapops.h>
#include <linux/thread_info.h>
#include <linux/types.h>
+#include <linux/uaccess.h>
#include <linux/uio.h>
#include <asm/barrier.h>
@@ -76,6 +77,9 @@ void mte_sync_tags(pte_t old_pte, pte_t pte)
mte_sync_page_tags(page, old_pte, check_swap,
pte_is_tagged);
}
+
+ /* ensure the tags are visible before the PTE is set */
+ smp_wmb();
}
int memcmp_pages(struct page *page1, struct page *page2)
@@ -106,7 +110,8 @@ int memcmp_pages(struct page *page1, struct page *page2)
static inline void __mte_enable_kernel(const char *mode, unsigned long tcf)
{
/* Enable MTE Sync Mode for EL1. */
- sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, tcf);
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK,
+ SYS_FIELD_PREP(SCTLR_EL1, TCF, tcf));
isb();
pr_info_once("MTE: enabled in %s mode at EL1\n", mode);
@@ -122,12 +127,12 @@ void mte_enable_kernel_sync(void)
WARN_ONCE(system_uses_mte_async_or_asymm_mode(),
"MTE async mode enabled system wide!");
- __mte_enable_kernel("synchronous", SCTLR_ELx_TCF_SYNC);
+ __mte_enable_kernel("synchronous", SCTLR_EL1_TCF_SYNC);
}
void mte_enable_kernel_async(void)
{
- __mte_enable_kernel("asynchronous", SCTLR_ELx_TCF_ASYNC);
+ __mte_enable_kernel("asynchronous", SCTLR_EL1_TCF_ASYNC);
/*
* MTE async mode is set system wide by the first PE that
@@ -144,7 +149,7 @@ void mte_enable_kernel_async(void)
void mte_enable_kernel_asymm(void)
{
if (cpus_have_cap(ARM64_MTE_ASYMM)) {
- __mte_enable_kernel("asymmetric", SCTLR_ELx_TCF_ASYMM);
+ __mte_enable_kernel("asymmetric", SCTLR_EL1_TCF_ASYMM);
/*
* MTE asymm mode behaves as async mode for store
@@ -216,11 +221,11 @@ static void mte_update_sctlr_user(struct task_struct *task)
* default order.
*/
if (resolved_mte_tcf & MTE_CTRL_TCF_ASYMM)
- sctlr |= SCTLR_EL1_TCF0_ASYMM;
+ sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, ASYMM);
else if (resolved_mte_tcf & MTE_CTRL_TCF_ASYNC)
- sctlr |= SCTLR_EL1_TCF0_ASYNC;
+ sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, ASYNC);
else if (resolved_mte_tcf & MTE_CTRL_TCF_SYNC)
- sctlr |= SCTLR_EL1_TCF0_SYNC;
+ sctlr |= SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF0, SYNC);
task->thread.sctlr_user = sctlr;
}
@@ -543,3 +548,32 @@ static int register_mte_tcf_preferred_sysctl(void)
return 0;
}
subsys_initcall(register_mte_tcf_preferred_sysctl);
+
+/*
+ * Return 0 on success, the number of bytes not probed otherwise.
+ */
+size_t mte_probe_user_range(const char __user *uaddr, size_t size)
+{
+ const char __user *end = uaddr + size;
+ int err = 0;
+ char val;
+
+ __raw_get_user(val, uaddr, err);
+ if (err)
+ return size;
+
+ uaddr = PTR_ALIGN(uaddr, MTE_GRANULE_SIZE);
+ while (uaddr < end) {
+ /*
+ * A read is sufficient for mte, the caller should have probed
+ * for the pte write permission if required.
+ */
+ __raw_get_user(val, uaddr, err);
+ if (err)
+ return end - uaddr;
+ uaddr += MTE_GRANULE_SIZE;
+ }
+ (void)val;
+
+ return 0;
+}
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 75fed4460407..57c7c211f8c7 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -35,7 +35,7 @@ static u64 native_steal_clock(int cpu)
DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
struct pv_time_stolen_time_region {
- struct pvclock_vcpu_stolen_time *kaddr;
+ struct pvclock_vcpu_stolen_time __rcu *kaddr;
};
static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region);
@@ -52,7 +52,9 @@ early_param("no-steal-acc", parse_no_stealacc);
/* return stolen time in ns by asking the hypervisor */
static u64 para_steal_clock(int cpu)
{
+ struct pvclock_vcpu_stolen_time *kaddr = NULL;
struct pv_time_stolen_time_region *reg;
+ u64 ret = 0;
reg = per_cpu_ptr(&stolen_time_region, cpu);
@@ -61,28 +63,37 @@ static u64 para_steal_clock(int cpu)
* online notification callback runs. Until the callback
* has run we just return zero.
*/
- if (!reg->kaddr)
+ rcu_read_lock();
+ kaddr = rcu_dereference(reg->kaddr);
+ if (!kaddr) {
+ rcu_read_unlock();
return 0;
+ }
- return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
+ ret = le64_to_cpu(READ_ONCE(kaddr->stolen_time));
+ rcu_read_unlock();
+ return ret;
}
static int stolen_time_cpu_down_prepare(unsigned int cpu)
{
+ struct pvclock_vcpu_stolen_time *kaddr = NULL;
struct pv_time_stolen_time_region *reg;
reg = this_cpu_ptr(&stolen_time_region);
if (!reg->kaddr)
return 0;
- memunmap(reg->kaddr);
- memset(reg, 0, sizeof(*reg));
+ kaddr = rcu_replace_pointer(reg->kaddr, NULL, true);
+ synchronize_rcu();
+ memunmap(kaddr);
return 0;
}
static int stolen_time_cpu_online(unsigned int cpu)
{
+ struct pvclock_vcpu_stolen_time *kaddr = NULL;
struct pv_time_stolen_time_region *reg;
struct arm_smccc_res res;
@@ -93,17 +104,19 @@ static int stolen_time_cpu_online(unsigned int cpu)
if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
return -EINVAL;
- reg->kaddr = memremap(res.a0,
+ kaddr = memremap(res.a0,
sizeof(struct pvclock_vcpu_stolen_time),
MEMREMAP_WB);
+ rcu_assign_pointer(reg->kaddr, kaddr);
+
if (!reg->kaddr) {
pr_warn("Failed to map stolen time data structure\n");
return -ENOMEM;
}
- if (le32_to_cpu(reg->kaddr->revision) != 0 ||
- le32_to_cpu(reg->kaddr->attributes) != 0) {
+ if (le32_to_cpu(kaddr->revision) != 0 ||
+ le32_to_cpu(kaddr->attributes) != 0) {
pr_warn_once("Unexpected revision or attributes in stolen time data\n");
return -ENXIO;
}
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
index 771f543464e0..33e0fabc0b79 100644
--- a/arch/arm64/kernel/patching.c
+++ b/arch/arm64/kernel/patching.c
@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
int i, ret = 0;
struct aarch64_insn_patch *pp = arg;
- /* The first CPU becomes master */
- if (atomic_inc_return(&pp->cpu_count) == 1) {
+ /* The last CPU becomes master */
+ if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) {
for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
pp->new_insns[i]);
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d9dfa82c1f18..d1d182320245 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -335,7 +335,7 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
}
static int __kprobes
-kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr)
+kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned long esr)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long addr = instruction_pointer(regs);
@@ -359,7 +359,7 @@ static struct break_hook kprobes_break_ss_hook = {
};
static int __kprobes
-kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
+kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr)
{
kprobe_handler(regs);
return DBG_HOOK_HANDLED;
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 9be668f3f034..d49aef2657cd 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -166,7 +166,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self,
}
static int uprobe_breakpoint_handler(struct pt_regs *regs,
- unsigned int esr)
+ unsigned long esr)
{
if (uprobe_pre_sstep_notifier(regs))
return DBG_HOOK_HANDLED;
@@ -175,7 +175,7 @@ static int uprobe_breakpoint_handler(struct pt_regs *regs,
}
static int uprobe_single_step_handler(struct pt_regs *regs,
- unsigned int esr)
+ unsigned long esr)
{
struct uprobe_task *utask = current->utask;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7fa97df55e3a..9734c9fb1a32 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -250,6 +250,8 @@ void show_regs(struct pt_regs *regs)
static void tls_thread_flush(void)
{
write_sysreg(0, tpidr_el0);
+ if (system_supports_tpidr2())
+ write_sysreg_s(0, SYS_TPIDR2_EL0);
if (is_compat_task()) {
current->thread.uw.tp_value = 0;
@@ -298,16 +300,42 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
/*
* Detach src's sve_state (if any) from dst so that it does not
- * get erroneously used or freed prematurely. dst's sve_state
+ * get erroneously used or freed prematurely. dst's copies
* will be allocated on demand later on if dst uses SVE.
* For consistency, also clear TIF_SVE here: this could be done
* later in copy_process(), but to avoid tripping up future
- * maintainers it is best not to leave TIF_SVE and sve_state in
+ * maintainers it is best not to leave TIF flags and buffers in
* an inconsistent state, even temporarily.
*/
dst->thread.sve_state = NULL;
clear_tsk_thread_flag(dst, TIF_SVE);
+ /*
+ * In the unlikely event that we create a new thread with ZA
+ * enabled we should retain the ZA state so duplicate it here.
+ * This may be shortly freed if we exec() or if CLONE_SETTLS
+ * but it's simpler to do it here. To avoid confusing the rest
+ * of the code ensure that we have a sve_state allocated
+ * whenever za_state is allocated.
+ */
+ if (thread_za_enabled(&src->thread)) {
+ dst->thread.sve_state = kzalloc(sve_state_size(src),
+ GFP_KERNEL);
+ if (!dst->thread.sve_state)
+ return -ENOMEM;
+ dst->thread.za_state = kmemdup(src->thread.za_state,
+ za_state_size(src),
+ GFP_KERNEL);
+ if (!dst->thread.za_state) {
+ kfree(dst->thread.sve_state);
+ dst->thread.sve_state = NULL;
+ return -ENOMEM;
+ }
+ } else {
+ dst->thread.za_state = NULL;
+ clear_tsk_thread_flag(dst, TIF_SME);
+ }
+
/* clear any pending asynchronous tag fault raised by the parent */
clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
@@ -343,6 +371,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
* out-of-sync with the saved value.
*/
*task_user_tls(p) = read_sysreg(tpidr_el0);
+ if (system_supports_tpidr2())
+ p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
if (stack_start) {
if (is_compat_thread(task_thread_info(p)))
@@ -353,10 +383,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
/*
* If a TLS pointer was passed to clone, use it for the new
- * thread.
+ * thread. We also reset TPIDR2 if it's in use.
*/
- if (clone_flags & CLONE_SETTLS)
+ if (clone_flags & CLONE_SETTLS) {
p->thread.uw.tp_value = tls;
+ p->thread.tpidr2_el0 = 0;
+ }
} else {
/*
* A kthread has no context to ERET to, so ensure any buggy
@@ -387,6 +419,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
void tls_preserve_current_state(void)
{
*task_user_tls(current) = read_sysreg(tpidr_el0);
+ if (system_supports_tpidr2() && !is_compat_task())
+ current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
}
static void tls_thread_switch(struct task_struct *next)
@@ -399,6 +433,8 @@ static void tls_thread_switch(struct task_struct *next)
write_sysreg(0, tpidrro_el0);
write_sysreg(*task_user_tls(next), tpidr_el0);
+ if (system_supports_tpidr2())
+ write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0);
}
/*
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index 5777929d35bf..40be3a7c2c53 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope)
if (scope == SCOPE_LOCAL_CPU) {
static const struct midr_range spectre_bhb_k32_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 230a47b9189e..21da83187a60 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -713,21 +713,51 @@ static int system_call_set(struct task_struct *target,
#ifdef CONFIG_ARM64_SVE
static void sve_init_header_from_task(struct user_sve_header *header,
- struct task_struct *target)
+ struct task_struct *target,
+ enum vec_type type)
{
unsigned int vq;
+ bool active;
+ bool fpsimd_only;
+ enum vec_type task_type;
memset(header, 0, sizeof(*header));
- header->flags = test_tsk_thread_flag(target, TIF_SVE) ?
- SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD;
- if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
- header->flags |= SVE_PT_VL_INHERIT;
+ /* Check if the requested registers are active for the task */
+ if (thread_sm_enabled(&target->thread))
+ task_type = ARM64_VEC_SME;
+ else
+ task_type = ARM64_VEC_SVE;
+ active = (task_type == type);
+
+ switch (type) {
+ case ARM64_VEC_SVE:
+ if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
+ header->flags |= SVE_PT_VL_INHERIT;
+ fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE);
+ break;
+ case ARM64_VEC_SME:
+ if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
+ header->flags |= SVE_PT_VL_INHERIT;
+ fpsimd_only = false;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return;
+ }
- header->vl = task_get_sve_vl(target);
+ if (active) {
+ if (fpsimd_only) {
+ header->flags |= SVE_PT_REGS_FPSIMD;
+ } else {
+ header->flags |= SVE_PT_REGS_SVE;
+ }
+ }
+
+ header->vl = task_get_vl(target, type);
vq = sve_vq_from_vl(header->vl);
- header->max_vl = sve_max_vl();
+ header->max_vl = vec_max_vl(type);
header->size = SVE_PT_SIZE(vq, header->flags);
header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),
SVE_PT_REGS_SVE);
@@ -738,19 +768,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header)
return ALIGN(header->size, SVE_VQ_BYTES);
}
-static int sve_get(struct task_struct *target,
- const struct user_regset *regset,
- struct membuf to)
+static int sve_get_common(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to,
+ enum vec_type type)
{
struct user_sve_header header;
unsigned int vq;
unsigned long start, end;
- if (!system_supports_sve())
- return -EINVAL;
-
/* Header */
- sve_init_header_from_task(&header, target);
+ sve_init_header_from_task(&header, target, type);
vq = sve_vq_from_vl(header.vl);
membuf_write(&to, &header, sizeof(header));
@@ -758,49 +786,61 @@ static int sve_get(struct task_struct *target,
if (target == current)
fpsimd_preserve_current_state();
- /* Registers: FPSIMD-only case */
-
BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
- if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD)
+ BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+
+ switch ((header.flags & SVE_PT_REGS_MASK)) {
+ case SVE_PT_REGS_FPSIMD:
return __fpr_get(target, regset, to);
- /* Otherwise: full SVE case */
+ case SVE_PT_REGS_SVE:
+ start = SVE_PT_SVE_OFFSET;
+ end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+ membuf_write(&to, target->thread.sve_state, end - start);
- BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
- start = SVE_PT_SVE_OFFSET;
- end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
- membuf_write(&to, target->thread.sve_state, end - start);
+ start = end;
+ end = SVE_PT_SVE_FPSR_OFFSET(vq);
+ membuf_zero(&to, end - start);
- start = end;
- end = SVE_PT_SVE_FPSR_OFFSET(vq);
- membuf_zero(&to, end - start);
+ /*
+ * Copy fpsr, and fpcr which must follow contiguously in
+ * struct fpsimd_state:
+ */
+ start = end;
+ end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+ membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr,
+ end - start);
- /*
- * Copy fpsr, and fpcr which must follow contiguously in
- * struct fpsimd_state:
- */
- start = end;
- end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
- membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start);
+ start = end;
+ end = sve_size_from_header(&header);
+ return membuf_zero(&to, end - start);
- start = end;
- end = sve_size_from_header(&header);
- return membuf_zero(&to, end - start);
+ default:
+ return 0;
+ }
}
-static int sve_set(struct task_struct *target,
+static int sve_get(struct task_struct *target,
const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
+ struct membuf to)
+{
+ if (!system_supports_sve())
+ return -EINVAL;
+
+ return sve_get_common(target, regset, to, ARM64_VEC_SVE);
+}
+
+static int sve_set_common(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf,
+ enum vec_type type)
{
int ret;
struct user_sve_header header;
unsigned int vq;
unsigned long start, end;
- if (!system_supports_sve())
- return -EINVAL;
-
/* Header */
if (count < sizeof(header))
return -EINVAL;
@@ -813,13 +853,37 @@ static int sve_set(struct task_struct *target,
* Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
* vec_set_vector_length(), which will also validate them for us:
*/
- ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl,
+ ret = vec_set_vector_length(target, type, header.vl,
((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
if (ret)
goto out;
/* Actual VL set may be less than the user asked for: */
- vq = sve_vq_from_vl(task_get_sve_vl(target));
+ vq = sve_vq_from_vl(task_get_vl(target, type));
+
+ /* Enter/exit streaming mode */
+ if (system_supports_sme()) {
+ u64 old_svcr = target->thread.svcr;
+
+ switch (type) {
+ case ARM64_VEC_SVE:
+ target->thread.svcr &= ~SVCR_SM_MASK;
+ break;
+ case ARM64_VEC_SME:
+ target->thread.svcr |= SVCR_SM_MASK;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
+
+ /*
+ * If we switched then invalidate any existing SVE
+ * state and ensure there's storage.
+ */
+ if (target->thread.svcr != old_svcr)
+ sve_alloc(target);
+ }
/* Registers: FPSIMD-only case */
@@ -828,10 +892,15 @@ static int sve_set(struct task_struct *target,
ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
SVE_PT_FPSIMD_OFFSET);
clear_tsk_thread_flag(target, TIF_SVE);
+ if (type == ARM64_VEC_SME)
+ fpsimd_force_sync_to_sve(target);
goto out;
}
- /* Otherwise: full SVE case */
+ /*
+ * Otherwise: no registers or full SVE case. For backwards
+ * compatibility reasons we treat empty flags as SVE registers.
+ */
/*
* If setting a different VL from the requested VL and there is
@@ -852,8 +921,9 @@ static int sve_set(struct task_struct *target,
/*
* Ensure target->thread.sve_state is up to date with target's
- * FPSIMD regs, so that a short copyin leaves trailing registers
- * unmodified.
+ * FPSIMD regs, so that a short copyin leaves trailing
+ * registers unmodified. Always enable SVE even if going into
+ * streaming mode.
*/
fpsimd_sync_to_sve(target);
set_tsk_thread_flag(target, TIF_SVE);
@@ -889,8 +959,181 @@ out:
return ret;
}
+static int sve_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ if (!system_supports_sve())
+ return -EINVAL;
+
+ return sve_set_common(target, regset, pos, count, kbuf, ubuf,
+ ARM64_VEC_SVE);
+}
+
#endif /* CONFIG_ARM64_SVE */
+#ifdef CONFIG_ARM64_SME
+
+static int ssve_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!system_supports_sme())
+ return -EINVAL;
+
+ return sve_get_common(target, regset, to, ARM64_VEC_SME);
+}
+
+static int ssve_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ if (!system_supports_sme())
+ return -EINVAL;
+
+ return sve_set_common(target, regset, pos, count, kbuf, ubuf,
+ ARM64_VEC_SME);
+}
+
+static int za_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to)
+{
+ struct user_za_header header;
+ unsigned int vq;
+ unsigned long start, end;
+
+ if (!system_supports_sme())
+ return -EINVAL;
+
+ /* Header */
+ memset(&header, 0, sizeof(header));
+
+ if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
+ header.flags |= ZA_PT_VL_INHERIT;
+
+ header.vl = task_get_sme_vl(target);
+ vq = sve_vq_from_vl(header.vl);
+ header.max_vl = sme_max_vl();
+ header.max_size = ZA_PT_SIZE(vq);
+
+ /* If ZA is not active there is only the header */
+ if (thread_za_enabled(&target->thread))
+ header.size = ZA_PT_SIZE(vq);
+ else
+ header.size = ZA_PT_ZA_OFFSET;
+
+ membuf_write(&to, &header, sizeof(header));
+
+ BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header));
+ end = ZA_PT_ZA_OFFSET;
+
+ if (target == current)
+ fpsimd_preserve_current_state();
+
+ /* Any register data to include? */
+ if (thread_za_enabled(&target->thread)) {
+ start = end;
+ end = ZA_PT_SIZE(vq);
+ membuf_write(&to, target->thread.za_state, end - start);
+ }
+
+ /* Zero any trailing padding */
+ start = end;
+ end = ALIGN(header.size, SVE_VQ_BYTES);
+ return membuf_zero(&to, end - start);
+}
+
+static int za_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+ struct user_za_header header;
+ unsigned int vq;
+ unsigned long start, end;
+
+ if (!system_supports_sme())
+ return -EINVAL;
+
+ /* Header */
+ if (count < sizeof(header))
+ return -EINVAL;
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header,
+ 0, sizeof(header));
+ if (ret)
+ goto out;
+
+ /*
+ * All current ZA_PT_* flags are consumed by
+ * vec_set_vector_length(), which will also validate them for
+ * us:
+ */
+ ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl,
+ ((unsigned long)header.flags) << 16);
+ if (ret)
+ goto out;
+
+ /* Actual VL set may be less than the user asked for: */
+ vq = sve_vq_from_vl(task_get_sme_vl(target));
+
+ /* Ensure there is some SVE storage for streaming mode */
+ if (!target->thread.sve_state) {
+ sve_alloc(target);
+ if (!target->thread.sve_state) {
+ clear_thread_flag(TIF_SME);
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+
+ /* Allocate/reinit ZA storage */
+ sme_alloc(target);
+ if (!target->thread.za_state) {
+ ret = -ENOMEM;
+ clear_tsk_thread_flag(target, TIF_SME);
+ goto out;
+ }
+
+ /* If there is no data then disable ZA */
+ if (!count) {
+ target->thread.svcr &= ~SVCR_ZA_MASK;
+ goto out;
+ }
+
+ /*
+ * If setting a different VL from the requested VL and there is
+ * register data, the data layout will be wrong: don't even
+ * try to set the registers in this case.
+ */
+ if (vq != sve_vq_from_vl(header.vl)) {
+ ret = -EIO;
+ goto out;
+ }
+
+ BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header));
+ start = ZA_PT_ZA_OFFSET;
+ end = ZA_PT_SIZE(vq);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ target->thread.za_state,
+ start, end);
+ if (ret)
+ goto out;
+
+ /* Mark ZA as active and let userspace use it */
+ set_tsk_thread_flag(target, TIF_SME);
+ target->thread.svcr |= SVCR_ZA_MASK;
+
+out:
+ fpsimd_flush_task_state(target);
+ return ret;
+}
+
+#endif /* CONFIG_ARM64_SME */
+
#ifdef CONFIG_ARM64_PTR_AUTH
static int pac_mask_get(struct task_struct *target,
const struct user_regset *regset,
@@ -1108,6 +1351,10 @@ enum aarch64_regset {
#ifdef CONFIG_ARM64_SVE
REGSET_SVE,
#endif
+#ifdef CONFIG_ARM64_SVE
+ REGSET_SSVE,
+ REGSET_ZA,
+#endif
#ifdef CONFIG_ARM64_PTR_AUTH
REGSET_PAC_MASK,
REGSET_PAC_ENABLED_KEYS,
@@ -1188,6 +1435,33 @@ static const struct user_regset aarch64_regsets[] = {
.set = sve_set,
},
#endif
+#ifdef CONFIG_ARM64_SME
+ [REGSET_SSVE] = { /* Streaming mode SVE */
+ .core_note_type = NT_ARM_SSVE,
+ .n = DIV_ROUND_UP(SVE_PT_SIZE(SME_VQ_MAX, SVE_PT_REGS_SVE),
+ SVE_VQ_BYTES),
+ .size = SVE_VQ_BYTES,
+ .align = SVE_VQ_BYTES,
+ .regset_get = ssve_get,
+ .set = ssve_set,
+ },
+ [REGSET_ZA] = { /* SME ZA */
+ .core_note_type = NT_ARM_ZA,
+ /*
+ * ZA is a single register but it's variably sized and
+ * the ptrace core requires that the size of any data
+ * be an exact multiple of the configured register
+ * size so report as though we had SVE_VQ_BYTES
+ * registers. These values aren't exposed to
+ * userspace.
+ */
+ .n = DIV_ROUND_UP(ZA_PT_SIZE(SME_VQ_MAX), SVE_VQ_BYTES),
+ .size = SVE_VQ_BYTES,
+ .align = SVE_VQ_BYTES,
+ .regset_get = za_get,
+ .set = za_set,
+ },
+#endif
#ifdef CONFIG_ARM64_PTR_AUTH
[REGSET_PAC_MASK] = {
.core_note_type = NT_ARM_PAC_MASK,
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index f0a3df9e18a3..413f899e4ac6 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -37,6 +37,15 @@
* safe memory that has been set up to be preserved during the copy operation.
*/
SYM_CODE_START(arm64_relocate_new_kernel)
+ /*
+ * The kimage structure isn't allocated specially and may be clobbered
+ * during relocation. We must load any values we need from it prior to
+ * any relocation occurring.
+ */
+ ldr x28, [x0, #KIMAGE_START]
+ ldr x27, [x0, #KIMAGE_ARCH_EL2_VECTORS]
+ ldr x26, [x0, #KIMAGE_ARCH_DTB_MEM]
+
/* Setup the list loop variables. */
ldr x18, [x0, #KIMAGE_ARCH_ZERO_PAGE] /* x18 = zero page for BBM */
ldr x17, [x0, #KIMAGE_ARCH_TTBR1] /* x17 = linear map copy */
@@ -72,21 +81,20 @@ SYM_CODE_START(arm64_relocate_new_kernel)
ic iallu
dsb nsh
isb
- ldr x4, [x0, #KIMAGE_START] /* relocation start */
- ldr x1, [x0, #KIMAGE_ARCH_EL2_VECTORS] /* relocation start */
- ldr x0, [x0, #KIMAGE_ARCH_DTB_MEM] /* dtb address */
turn_off_mmu x12, x13
/* Start new image. */
- cbz x1, .Lel1
- mov x1, x4 /* relocation start */
- mov x2, x0 /* dtb address */
+ cbz x27, .Lel1
+ mov x1, x28 /* kernel entry point */
+ mov x2, x26 /* dtb address */
mov x3, xzr
mov x4, xzr
mov x0, #HVC_SOFT_RESTART
hvc #0 /* Jumps from el2 */
.Lel1:
+ mov x0, x26 /* dtb address */
+ mov x1, xzr
mov x2, xzr
mov x3, xzr
- br x4 /* Jumps from el1 */
+ br x28 /* Jumps from el1 */
SYM_CODE_END(arm64_relocate_new_kernel)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 3505789cf4bd..fea3223704b6 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -225,6 +225,8 @@ static void __init request_standard_resources(void)
kernel_code.end = __pa_symbol(__init_begin - 1);
kernel_data.start = __pa_symbol(_sdata);
kernel_data.end = __pa_symbol(_end - 1);
+ insert_resource(&iomem_resource, &kernel_code);
+ insert_resource(&iomem_resource, &kernel_data);
num_standard_resources = memblock.memory.cnt;
res_size = num_standard_resources * sizeof(*standard_resources);
@@ -246,20 +248,7 @@ static void __init request_standard_resources(void)
res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
}
- request_resource(&iomem_resource, res);
-
- if (kernel_code.start >= res->start &&
- kernel_code.end <= res->end)
- request_resource(res, &kernel_code);
- if (kernel_data.start >= res->start &&
- kernel_data.end <= res->end)
- request_resource(res, &kernel_data);
-#ifdef CONFIG_KEXEC_CORE
- /* Userspace will find "Crash kernel" region in /proc/iomem. */
- if (crashk_res.end && crashk_res.start >= res->start &&
- crashk_res.end <= res->end)
- request_resource(res, &crashk_res);
-#endif
+ insert_resource(&iomem_resource, res);
}
}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 4a4122ef6f39..edb2d9206a78 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -56,6 +56,7 @@ struct rt_sigframe_user_layout {
unsigned long fpsimd_offset;
unsigned long esr_offset;
unsigned long sve_offset;
+ unsigned long za_offset;
unsigned long extra_offset;
unsigned long end_offset;
};
@@ -218,6 +219,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
struct user_ctxs {
struct fpsimd_context __user *fpsimd;
struct sve_context __user *sve;
+ struct za_context __user *za;
};
#ifdef CONFIG_ARM64_SVE
@@ -226,11 +228,17 @@ static int preserve_sve_context(struct sve_context __user *ctx)
{
int err = 0;
u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+ u16 flags = 0;
unsigned int vl = task_get_sve_vl(current);
unsigned int vq = 0;
- if (test_thread_flag(TIF_SVE))
+ if (thread_sm_enabled(&current->thread)) {
+ vl = task_get_sme_vl(current);
vq = sve_vq_from_vl(vl);
+ flags |= SVE_SIG_FLAG_SM;
+ } else if (test_thread_flag(TIF_SVE)) {
+ vq = sve_vq_from_vl(vl);
+ }
memset(reserved, 0, sizeof(reserved));
@@ -238,6 +246,7 @@ static int preserve_sve_context(struct sve_context __user *ctx)
__put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16),
&ctx->head.size, err);
__put_user_error(vl, &ctx->vl, err);
+ __put_user_error(flags, &ctx->flags, err);
BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
@@ -258,18 +267,28 @@ static int preserve_sve_context(struct sve_context __user *ctx)
static int restore_sve_fpsimd_context(struct user_ctxs *user)
{
int err;
- unsigned int vq;
+ unsigned int vl, vq;
struct user_fpsimd_state fpsimd;
struct sve_context sve;
if (__copy_from_user(&sve, user->sve, sizeof(sve)))
return -EFAULT;
- if (sve.vl != task_get_sve_vl(current))
+ if (sve.flags & SVE_SIG_FLAG_SM) {
+ if (!system_supports_sme())
+ return -EINVAL;
+
+ vl = task_get_sme_vl(current);
+ } else {
+ vl = task_get_sve_vl(current);
+ }
+
+ if (sve.vl != vl)
return -EINVAL;
if (sve.head.size <= sizeof(*user->sve)) {
clear_thread_flag(TIF_SVE);
+ current->thread.svcr &= ~SVCR_SM_MASK;
goto fpsimd_only;
}
@@ -301,7 +320,10 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
if (err)
return -EFAULT;
- set_thread_flag(TIF_SVE);
+ if (sve.flags & SVE_SIG_FLAG_SM)
+ current->thread.svcr |= SVCR_SM_MASK;
+ else
+ set_thread_flag(TIF_SVE);
fpsimd_only:
/* copy the FP and status/control registers */
@@ -326,6 +348,101 @@ extern int restore_sve_fpsimd_context(struct user_ctxs *user);
#endif /* ! CONFIG_ARM64_SVE */
+#ifdef CONFIG_ARM64_SME
+
+static int preserve_za_context(struct za_context __user *ctx)
+{
+ int err = 0;
+ u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+ unsigned int vl = task_get_sme_vl(current);
+ unsigned int vq;
+
+ if (thread_za_enabled(&current->thread))
+ vq = sve_vq_from_vl(vl);
+ else
+ vq = 0;
+
+ memset(reserved, 0, sizeof(reserved));
+
+ __put_user_error(ZA_MAGIC, &ctx->head.magic, err);
+ __put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16),
+ &ctx->head.size, err);
+ __put_user_error(vl, &ctx->vl, err);
+ BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+ err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+ if (vq) {
+ /*
+ * This assumes that the ZA state has already been saved to
+ * the task struct by calling the function
+ * fpsimd_signal_preserve_current_state().
+ */
+ err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
+ current->thread.za_state,
+ ZA_SIG_REGS_SIZE(vq));
+ }
+
+ return err ? -EFAULT : 0;
+}
+
+static int restore_za_context(struct user_ctxs __user *user)
+{
+ int err;
+ unsigned int vq;
+ struct za_context za;
+
+ if (__copy_from_user(&za, user->za, sizeof(za)))
+ return -EFAULT;
+
+ if (za.vl != task_get_sme_vl(current))
+ return -EINVAL;
+
+ if (za.head.size <= sizeof(*user->za)) {
+ current->thread.svcr &= ~SVCR_ZA_MASK;
+ return 0;
+ }
+
+ vq = sve_vq_from_vl(za.vl);
+
+ if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq))
+ return -EINVAL;
+
+ /*
+ * Careful: we are about __copy_from_user() directly into
+ * thread.za_state with preemption enabled, so protection is
+ * needed to prevent a racing context switch from writing stale
+ * registers back over the new data.
+ */
+
+ fpsimd_flush_task_state(current);
+ /* From now, fpsimd_thread_switch() won't touch thread.sve_state */
+
+ sme_alloc(current);
+ if (!current->thread.za_state) {
+ current->thread.svcr &= ~SVCR_ZA_MASK;
+ clear_thread_flag(TIF_SME);
+ return -ENOMEM;
+ }
+
+ err = __copy_from_user(current->thread.za_state,
+ (char __user const *)user->za +
+ ZA_SIG_REGS_OFFSET,
+ ZA_SIG_REGS_SIZE(vq));
+ if (err)
+ return -EFAULT;
+
+ set_thread_flag(TIF_SME);
+ current->thread.svcr |= SVCR_ZA_MASK;
+
+ return 0;
+}
+#else /* ! CONFIG_ARM64_SME */
+
+/* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_za_context(void __user *ctx);
+extern int restore_za_context(struct user_ctxs *user);
+
+#endif /* ! CONFIG_ARM64_SME */
static int parse_user_sigframe(struct user_ctxs *user,
struct rt_sigframe __user *sf)
@@ -340,6 +457,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
user->fpsimd = NULL;
user->sve = NULL;
+ user->za = NULL;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
@@ -393,7 +511,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
break;
case SVE_MAGIC:
- if (!system_supports_sve())
+ if (!system_supports_sve() && !system_supports_sme())
goto invalid;
if (user->sve)
@@ -405,6 +523,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
user->sve = (struct sve_context __user *)head;
break;
+ case ZA_MAGIC:
+ if (!system_supports_sme())
+ goto invalid;
+
+ if (user->za)
+ goto invalid;
+
+ if (size < sizeof(*user->za))
+ goto invalid;
+
+ user->za = (struct za_context __user *)head;
+ break;
+
case EXTRA_MAGIC:
if (have_extra_context)
goto invalid;
@@ -528,6 +659,9 @@ static int restore_sigframe(struct pt_regs *regs,
}
}
+ if (err == 0 && system_supports_sme() && user.za)
+ err = restore_za_context(&user);
+
return err;
}
@@ -594,11 +728,12 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
if (system_supports_sve()) {
unsigned int vq = 0;
- if (add_all || test_thread_flag(TIF_SVE)) {
- int vl = sve_max_vl();
+ if (add_all || test_thread_flag(TIF_SVE) ||
+ thread_sm_enabled(&current->thread)) {
+ int vl = max(sve_max_vl(), sme_max_vl());
if (!add_all)
- vl = task_get_sve_vl(current);
+ vl = thread_get_cur_vl(&current->thread);
vq = sve_vq_from_vl(vl);
}
@@ -609,6 +744,24 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
return err;
}
+ if (system_supports_sme()) {
+ unsigned int vl;
+ unsigned int vq = 0;
+
+ if (add_all)
+ vl = sme_max_vl();
+ else
+ vl = task_get_sme_vl(current);
+
+ if (thread_za_enabled(&current->thread))
+ vq = sve_vq_from_vl(vl);
+
+ err = sigframe_alloc(user, &user->za_offset,
+ ZA_SIG_CONTEXT_SIZE(vq));
+ if (err)
+ return err;
+ }
+
return sigframe_alloc_end(user);
}
@@ -649,13 +802,21 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
}
- /* Scalable Vector Extension state, if present */
- if (system_supports_sve() && err == 0 && user->sve_offset) {
+ /* Scalable Vector Extension state (including streaming), if present */
+ if ((system_supports_sve() || system_supports_sme()) &&
+ err == 0 && user->sve_offset) {
struct sve_context __user *sve_ctx =
apply_user_offset(user, user->sve_offset);
err |= preserve_sve_context(sve_ctx);
}
+ /* ZA state if present */
+ if (system_supports_sme() && err == 0 && user->za_offset) {
+ struct za_context __user *za_ctx =
+ apply_user_offset(user, user->za_offset);
+ err |= preserve_za_context(za_ctx);
+ }
+
if (err == 0 && user->extra_offset) {
char __user *sfp = (char __user *)user->sigframe;
char __user *userp =
@@ -759,6 +920,13 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
/* TCO (Tag Check Override) always cleared for signal handlers */
regs->pstate &= ~PSR_TCO_BIT;
+ /* Signal handlers are invoked with ZA and streaming mode disabled */
+ if (system_supports_sme()) {
+ current->thread.svcr &= ~(SVCR_ZA_MASK |
+ SVCR_SM_MASK);
+ sme_smstop();
+ }
+
if (ka->sa.sa_flags & SA_RESTORER)
sigtramp = ka->sa.sa_restorer;
else
@@ -1011,6 +1179,7 @@ static_assert(offsetof(siginfo_t, si_upper) == 0x28);
static_assert(offsetof(siginfo_t, si_pkey) == 0x20);
static_assert(offsetof(siginfo_t, si_perf_data) == 0x18);
static_assert(offsetof(siginfo_t, si_perf_type) == 0x20);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24);
static_assert(offsetof(siginfo_t, si_band) == 0x10);
static_assert(offsetof(siginfo_t, si_fd) == 0x18);
static_assert(offsetof(siginfo_t, si_call_addr) == 0x10);
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index d984282b979f..4700f8522d27 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -487,6 +487,7 @@ static_assert(offsetof(compat_siginfo_t, si_upper) == 0x18);
static_assert(offsetof(compat_siginfo_t, si_pkey) == 0x14);
static_assert(offsetof(compat_siginfo_t, si_perf_data) == 0x10);
static_assert(offsetof(compat_siginfo_t, si_perf_type) == 0x14);
+static_assert(offsetof(compat_siginfo_t, si_perf_flags) == 0x18);
static_assert(offsetof(compat_siginfo_t, si_band) == 0x0c);
static_assert(offsetof(compat_siginfo_t, si_fd) == 0x10);
static_assert(offsetof(compat_siginfo_t, si_call_addr) == 0x0c);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 27df5c1e6baa..62ed361a4376 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void)
* Log the CPU info before it is marked online and might get read.
*/
cpuinfo_store_cpu();
+ store_cpu_topology(cpu);
/*
* Enable GIC and timers.
@@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void)
ipi_setup(cpu);
- store_cpu_topology(cpu);
numa_add_cpu(cpu);
/*
@@ -512,6 +512,7 @@ struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
{
return &cpu_madt_gicc[cpu];
}
+EXPORT_SYMBOL_GPL(acpi_cpu_get_madt_gicc);
/*
* acpi_map_gic_cpu_interface - parse processor MADT entry
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index e4103e085681..0467cb79f080 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -19,43 +19,60 @@
#include <asm/stacktrace.h>
/*
- * AArch64 PCS assigns the frame pointer to x29.
+ * A snapshot of a frame record or fp/lr register values, along with some
+ * accounting information necessary for robust unwinding.
*
- * A simple function prologue looks like this:
- * sub sp, sp, #0x10
- * stp x29, x30, [sp]
- * mov x29, sp
+ * @fp: The fp value in the frame record (or the real fp)
+ * @pc: The lr value in the frame record (or the real lr)
*
- * A simple function epilogue looks like this:
- * mov sp, x29
- * ldp x29, x30, [sp]
- * add sp, sp, #0x10
+ * @stacks_done: Stacks which have been entirely unwound, for which it is no
+ * longer valid to unwind to.
+ *
+ * @prev_fp: The fp that pointed to this frame record, or a synthetic value
+ * of 0. This is used to ensure that within a stack, each
+ * subsequent frame record is at an increasing address.
+ * @prev_type: The type of stack this frame record was on, or a synthetic
+ * value of STACK_TYPE_UNKNOWN. This is used to detect a
+ * transition from one stack to another.
+ *
+ * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance
+ * associated with the most recently encountered replacement lr
+ * value.
*/
+struct unwind_state {
+ unsigned long fp;
+ unsigned long pc;
+ DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES);
+ unsigned long prev_fp;
+ enum stack_type prev_type;
+#ifdef CONFIG_KRETPROBES
+ struct llist_node *kr_cur;
+#endif
+};
-
-static notrace void start_backtrace(struct stackframe *frame, unsigned long fp,
- unsigned long pc)
+static notrace void unwind_init(struct unwind_state *state, unsigned long fp,
+ unsigned long pc)
{
- frame->fp = fp;
- frame->pc = pc;
+ state->fp = fp;
+ state->pc = pc;
#ifdef CONFIG_KRETPROBES
- frame->kr_cur = NULL;
+ state->kr_cur = NULL;
#endif
/*
* Prime the first unwind.
*
- * In unwind_frame() we'll check that the FP points to a valid stack,
+ * In unwind_next() we'll check that the FP points to a valid stack,
* which can't be STACK_TYPE_UNKNOWN, and the first unwind will be
* treated as a transition to whichever stack that happens to be. The
* prev_fp value won't be used, but we set it to 0 such that it is
* definitely not an accessible stack address.
*/
- bitmap_zero(frame->stacks_done, __NR_STACK_TYPES);
- frame->prev_fp = 0;
- frame->prev_type = STACK_TYPE_UNKNOWN;
+ bitmap_zero(state->stacks_done, __NR_STACK_TYPES);
+ state->prev_fp = 0;
+ state->prev_type = STACK_TYPE_UNKNOWN;
}
-NOKPROBE_SYMBOL(start_backtrace);
+NOKPROBE_SYMBOL(unwind_init);
/*
* Unwind from one frame record (A) to the next frame record (B).
@@ -64,15 +81,12 @@ NOKPROBE_SYMBOL(start_backtrace);
* records (e.g. a cycle), determined based on the location and fp value of A
* and the location (but not the fp value) of B.
*/
-static int notrace unwind_frame(struct task_struct *tsk,
- struct stackframe *frame)
+static int notrace unwind_next(struct task_struct *tsk,
+ struct unwind_state *state)
{
- unsigned long fp = frame->fp;
+ unsigned long fp = state->fp;
struct stack_info info;
- if (!tsk)
- tsk = current;
-
/* Final frame; nothing to unwind */
if (fp == (unsigned long)task_pt_regs(tsk)->stackframe)
return -ENOENT;
@@ -83,7 +97,7 @@ static int notrace unwind_frame(struct task_struct *tsk,
if (!on_accessible_stack(tsk, fp, 16, &info))
return -EINVAL;
- if (test_bit(info.type, frame->stacks_done))
+ if (test_bit(info.type, state->stacks_done))
return -EINVAL;
/*
@@ -99,27 +113,27 @@ static int notrace unwind_frame(struct task_struct *tsk,
* stack to another, it's never valid to unwind back to that first
* stack.
*/
- if (info.type == frame->prev_type) {
- if (fp <= frame->prev_fp)
+ if (info.type == state->prev_type) {
+ if (fp <= state->prev_fp)
return -EINVAL;
} else {
- set_bit(frame->prev_type, frame->stacks_done);
+ set_bit(state->prev_type, state->stacks_done);
}
/*
* Record this frame record's values and location. The prev_fp and
- * prev_type are only meaningful to the next unwind_frame() invocation.
+ * prev_type are only meaningful to the next unwind_next() invocation.
*/
- frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
- frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
- frame->prev_fp = fp;
- frame->prev_type = info.type;
+ state->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
+ state->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
+ state->prev_fp = fp;
+ state->prev_type = info.type;
- frame->pc = ptrauth_strip_insn_pac(frame->pc);
+ state->pc = ptrauth_strip_insn_pac(state->pc);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
if (tsk->ret_stack &&
- (frame->pc == (unsigned long)return_to_handler)) {
+ (state->pc == (unsigned long)return_to_handler)) {
unsigned long orig_pc;
/*
* This is a case where function graph tracer has
@@ -127,37 +141,37 @@ static int notrace unwind_frame(struct task_struct *tsk,
* to hook a function return.
* So replace it to an original value.
*/
- orig_pc = ftrace_graph_ret_addr(tsk, NULL, frame->pc,
- (void *)frame->fp);
- if (WARN_ON_ONCE(frame->pc == orig_pc))
+ orig_pc = ftrace_graph_ret_addr(tsk, NULL, state->pc,
+ (void *)state->fp);
+ if (WARN_ON_ONCE(state->pc == orig_pc))
return -EINVAL;
- frame->pc = orig_pc;
+ state->pc = orig_pc;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#ifdef CONFIG_KRETPROBES
- if (is_kretprobe_trampoline(frame->pc))
- frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur);
+ if (is_kretprobe_trampoline(state->pc))
+ state->pc = kretprobe_find_ret_addr(tsk, (void *)state->fp, &state->kr_cur);
#endif
return 0;
}
-NOKPROBE_SYMBOL(unwind_frame);
+NOKPROBE_SYMBOL(unwind_next);
-static void notrace walk_stackframe(struct task_struct *tsk,
- struct stackframe *frame,
- bool (*fn)(void *, unsigned long), void *data)
+static void notrace unwind(struct task_struct *tsk,
+ struct unwind_state *state,
+ stack_trace_consume_fn consume_entry, void *cookie)
{
while (1) {
int ret;
- if (!fn(data, frame->pc))
+ if (!consume_entry(cookie, state->pc))
break;
- ret = unwind_frame(tsk, frame);
+ ret = unwind_next(tsk, state);
if (ret < 0)
break;
}
}
-NOKPROBE_SYMBOL(walk_stackframe);
+NOKPROBE_SYMBOL(unwind);
static bool dump_backtrace_entry(void *arg, unsigned long where)
{
@@ -196,17 +210,17 @@ noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task,
struct pt_regs *regs)
{
- struct stackframe frame;
+ struct unwind_state state;
if (regs)
- start_backtrace(&frame, regs->regs[29], regs->pc);
+ unwind_init(&state, regs->regs[29], regs->pc);
else if (task == current)
- start_backtrace(&frame,
+ unwind_init(&state,
(unsigned long)__builtin_frame_address(1),
(unsigned long)__builtin_return_address(0));
else
- start_backtrace(&frame, thread_saved_fp(task),
+ unwind_init(&state, thread_saved_fp(task),
thread_saved_pc(task));
- walk_stackframe(task, &frame, consume_entry, cookie);
+ unwind(task, &state, consume_entry, cookie);
}
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 19ee7c33769d..2b0887e58a7c 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
/*
* Restore pstate flags. OS lock and mdscr have been already
* restored, so from this point onwards, debugging is fully
- * renabled if it was enabled when core started shutdown.
+ * reenabled if it was enabled when core started shutdown.
*/
local_daif_restore(flags);
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 12c6864e51e1..df14336c3a29 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -113,6 +113,6 @@ long compat_arm_syscall(struct pt_regs *regs, int scno)
addr = instruction_pointer(regs) - (compat_thumb_mode(regs) ? 2 : 4);
arm64_notify_die("Oops - bad compat syscall(2)", regs,
- SIGILL, ILL_ILLTRP, addr, scno);
+ SIGILL, ILL_ILLTRP, addr, 0);
return 0;
}
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index c938603b3ba0..733451fe7e41 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -158,11 +158,36 @@ trace_exit:
syscall_trace_exit(regs);
}
-static inline void sve_user_discard(void)
+/*
+ * As per the ABI exit SME streaming mode and clear the SVE state not
+ * shared with FPSIMD on syscall entry.
+ */
+static inline void fp_user_discard(void)
{
+ /*
+ * If SME is active then exit streaming mode. If ZA is active
+ * then flush the SVE registers but leave userspace access to
+ * both SVE and SME enabled, otherwise disable SME for the
+ * task and fall through to disabling SVE too. This means
+ * that after a syscall we never have any streaming mode
+ * register state to track, if this changes the KVM code will
+ * need updating.
+ */
+ if (system_supports_sme() && test_thread_flag(TIF_SME)) {
+ u64 svcr = read_sysreg_s(SYS_SVCR);
+
+ if (svcr & SVCR_SM_MASK)
+ sme_smstop_sm();
+ }
+
if (!system_supports_sve())
return;
+ /*
+ * If SME is not active then disable SVE, the registers will
+ * be cleared when userspace next attempts to access them and
+ * we do not need to track the SVE register state until then.
+ */
clear_thread_flag(TIF_SVE);
/*
@@ -177,7 +202,7 @@ static inline void sve_user_discard(void)
void do_el0_svc(struct pt_regs *regs)
{
- sve_user_discard();
+ fp_user_discard();
el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 0529fd57567e..9ac7a81b79be 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -242,7 +242,7 @@ static void arm64_show_signal(int signo, const char *str)
static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
struct task_struct *tsk = current;
- unsigned int esr = tsk->thread.fault_code;
+ unsigned long esr = tsk->thread.fault_code;
struct pt_regs *regs = task_pt_regs(tsk);
/* Leave if the signal won't be shown */
@@ -253,7 +253,7 @@ static void arm64_show_signal(int signo, const char *str)
pr_info("%s[%d]: unhandled exception: ", tsk->comm, task_pid_nr(tsk));
if (esr)
- pr_cont("%s, ESR 0x%08x, ", esr_get_class_string(esr), esr);
+ pr_cont("%s, ESR 0x%016lx, ", esr_get_class_string(esr), esr);
pr_cont("%s", str);
print_vma_addr(KERN_CONT " in ", regs->pc);
@@ -287,7 +287,7 @@ void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far,
void arm64_notify_die(const char *str, struct pt_regs *regs,
int signo, int sicode, unsigned long far,
- int err)
+ unsigned long err)
{
if (user_mode(regs)) {
WARN_ON(regs != current_pt_regs());
@@ -439,7 +439,7 @@ exit:
return fn ? fn(regs, instr) : 1;
}
-void force_signal_inject(int signal, int code, unsigned long address, unsigned int err)
+void force_signal_inject(int signal, int code, unsigned long address, unsigned long err)
{
const char *desc;
struct pt_regs *regs = current_pt_regs();
@@ -506,7 +506,7 @@ void do_bti(struct pt_regs *regs)
}
NOKPROBE_SYMBOL(do_bti);
-void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr)
+void do_ptrauth_fault(struct pt_regs *regs, unsigned long esr)
{
/*
* Unexpected FPAC exception or pointer authentication failure in
@@ -532,7 +532,7 @@ NOKPROBE_SYMBOL(do_ptrauth_fault);
uaccess_ttbr0_disable(); \
}
-static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
+static void user_cache_maint_handler(unsigned long esr, struct pt_regs *regs)
{
unsigned long tagged_address, address;
int rt = ESR_ELx_SYS64_ISS_RT(esr);
@@ -572,7 +572,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
-static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
+static void ctr_read_handler(unsigned long esr, struct pt_regs *regs)
{
int rt = ESR_ELx_SYS64_ISS_RT(esr);
unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
@@ -591,7 +591,7 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
-static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+static void cntvct_read_handler(unsigned long esr, struct pt_regs *regs)
{
int rt = ESR_ELx_SYS64_ISS_RT(esr);
@@ -599,7 +599,7 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
-static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
+static void cntfrq_read_handler(unsigned long esr, struct pt_regs *regs)
{
int rt = ESR_ELx_SYS64_ISS_RT(esr);
@@ -607,7 +607,7 @@ static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
-static void mrs_handler(unsigned int esr, struct pt_regs *regs)
+static void mrs_handler(unsigned long esr, struct pt_regs *regs)
{
u32 sysreg, rt;
@@ -618,15 +618,15 @@ static void mrs_handler(unsigned int esr, struct pt_regs *regs)
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
}
-static void wfi_handler(unsigned int esr, struct pt_regs *regs)
+static void wfi_handler(unsigned long esr, struct pt_regs *regs)
{
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
struct sys64_hook {
- unsigned int esr_mask;
- unsigned int esr_val;
- void (*handler)(unsigned int esr, struct pt_regs *regs);
+ unsigned long esr_mask;
+ unsigned long esr_val;
+ void (*handler)(unsigned long esr, struct pt_regs *regs);
};
static const struct sys64_hook sys64_hooks[] = {
@@ -675,7 +675,7 @@ static const struct sys64_hook sys64_hooks[] = {
};
#ifdef CONFIG_COMPAT
-static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
+static bool cp15_cond_valid(unsigned long esr, struct pt_regs *regs)
{
int cond;
@@ -695,7 +695,7 @@ static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
return aarch32_opcode_cond_checks[cond](regs->pstate);
}
-static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
+static void compat_cntfrq_read_handler(unsigned long esr, struct pt_regs *regs)
{
int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT;
@@ -712,7 +712,7 @@ static const struct sys64_hook cp15_32_hooks[] = {
{},
};
-static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+static void compat_cntvct_read_handler(unsigned long esr, struct pt_regs *regs)
{
int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT;
int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT;
@@ -737,7 +737,7 @@ static const struct sys64_hook cp15_64_hooks[] = {
{},
};
-void do_cp15instr(unsigned int esr, struct pt_regs *regs)
+void do_cp15instr(unsigned long esr, struct pt_regs *regs)
{
const struct sys64_hook *hook, *hook_base;
@@ -778,7 +778,7 @@ void do_cp15instr(unsigned int esr, struct pt_regs *regs)
NOKPROBE_SYMBOL(do_cp15instr);
#endif
-void do_sysinstr(unsigned int esr, struct pt_regs *regs)
+void do_sysinstr(unsigned long esr, struct pt_regs *regs)
{
const struct sys64_hook *hook;
@@ -821,6 +821,7 @@ static const char *esr_class_str[] = {
[ESR_ELx_EC_SVE] = "SVE",
[ESR_ELx_EC_ERET] = "ERET/ERETAA/ERETAB",
[ESR_ELx_EC_FPAC] = "FPAC",
+ [ESR_ELx_EC_SME] = "SME",
[ESR_ELx_EC_IMP_DEF] = "EL3 IMP DEF",
[ESR_ELx_EC_IABT_LOW] = "IABT (lower EL)",
[ESR_ELx_EC_IABT_CUR] = "IABT (current EL)",
@@ -842,7 +843,7 @@ static const char *esr_class_str[] = {
[ESR_ELx_EC_BRK64] = "BRK (AArch64)",
};
-const char *esr_get_class_string(u32 esr)
+const char *esr_get_class_string(unsigned long esr)
{
return esr_class_str[ESR_ELx_EC(esr)];
}
@@ -851,7 +852,7 @@ const char *esr_get_class_string(u32 esr)
* bad_el0_sync handles unexpected, but potentially recoverable synchronous
* exceptions taken from EL0.
*/
-void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr)
{
unsigned long pc = instruction_pointer(regs);
@@ -867,7 +868,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)
__aligned(16);
-void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far)
+void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far)
{
unsigned long tsk_stk = (unsigned long)current->stack;
unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
@@ -876,7 +877,7 @@ void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far)
console_verbose();
pr_emerg("Insufficient stack space to handle exception!");
- pr_emerg("ESR: 0x%08x -- %s\n", esr, esr_get_class_string(esr));
+ pr_emerg("ESR: 0x%016lx -- %s\n", esr, esr_get_class_string(esr));
pr_emerg("FAR: 0x%016lx\n", far);
pr_emerg("Task stack: [0x%016lx..0x%016lx]\n",
@@ -897,11 +898,11 @@ void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far)
}
#endif
-void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr)
+void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr)
{
console_verbose();
- pr_crit("SError Interrupt on CPU%d, code 0x%08x -- %s\n",
+ pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n",
smp_processor_id(), esr, esr_get_class_string(esr));
if (regs)
__show_regs(regs);
@@ -912,9 +913,9 @@ void __noreturn arm64_serror_panic(struct pt_regs *regs, u32 esr)
unreachable();
}
-bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
+bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr)
{
- u32 aet = arm64_ras_serror_get_severity(esr);
+ unsigned long aet = arm64_ras_serror_get_severity(esr);
switch (aet) {
case ESR_ELx_AET_CE: /* corrected error */
@@ -944,7 +945,7 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
}
}
-void do_serror(struct pt_regs *regs, unsigned int esr)
+void do_serror(struct pt_regs *regs, unsigned long esr)
{
/* non-RAS errors are not containable */
if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
@@ -965,7 +966,7 @@ int is_valid_bugaddr(unsigned long addr)
return 1;
}
-static int bug_handler(struct pt_regs *regs, unsigned int esr)
+static int bug_handler(struct pt_regs *regs, unsigned long esr)
{
switch (report_bug(regs->pc, regs)) {
case BUG_TRAP_TYPE_BUG:
@@ -990,7 +991,7 @@ static struct break_hook bug_break_hook = {
.imm = BUG_BRK_IMM,
};
-static int reserved_fault_handler(struct pt_regs *regs, unsigned int esr)
+static int reserved_fault_handler(struct pt_regs *regs, unsigned long esr)
{
pr_err("%s generated an invalid instruction at %pS!\n",
"Kernel text patching",
@@ -1012,7 +1013,7 @@ static struct break_hook fault_break_hook = {
#define KASAN_ESR_SIZE_MASK 0x0f
#define KASAN_ESR_SIZE(esr) (1 << ((esr) & KASAN_ESR_SIZE_MASK))
-static int kasan_handler(struct pt_regs *regs, unsigned int esr)
+static int kasan_handler(struct pt_regs *regs, unsigned long esr)
{
bool recover = esr & KASAN_ESR_RECOVER;
bool write = esr & KASAN_ESR_WRITE;
@@ -1055,11 +1056,11 @@ static struct break_hook kasan_break_hook = {
* Initial handler for AArch64 BRK exceptions
* This handler only used until debug_traps_init().
*/
-int __init early_brk64(unsigned long addr, unsigned int esr,
+int __init early_brk64(unsigned long addr, unsigned long esr,
struct pt_regs *regs)
{
#ifdef CONFIG_KASAN_SW_TAGS
- unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+ unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 172452f79e46..f6e25d7c346a 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -32,7 +32,8 @@ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
# -Wmissing-prototypes and -Wmissing-declarations are removed from
# the CFLAGS of vgettimeofday.c to make possible to build the
# kernel with CONFIG_WERROR enabled.
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) \
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) \
+ $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) \
$(CC_FLAGS_LTO) -Wmissing-prototypes -Wmissing-declarations
KASAN_SANITIZE := n
KCSAN_SANITIZE := n
@@ -52,9 +53,6 @@ GCOV_PROFILE := n
targets += vdso.lds
CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
-# Force dependency (incbin is bad)
-$(obj)/vdso.o : $(obj)/vdso.so
-
# Link rule for the .so file, .lds has to be first
$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
$(call if_changed,vdsold_and_vdso_check)
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index ed181bedbffc..05ba1aae1b6f 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -131,9 +131,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
targets += vdso.lds
CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
-# Force dependency (vdso.s includes vdso.so through incbin)
-$(obj)/vdso.o: $(obj)/vdso.so
-
include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE
$(call if_changed,vdsosym)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index edaf0faf766f..2d4a8f995175 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -93,7 +93,6 @@ jiffies = jiffies_64;
#ifdef CONFIG_HIBERNATION
#define HIBERNATE_TEXT \
- . = ALIGN(SZ_4K); \
__hibernate_exit_text_start = .; \
*(.hibernate_exit.text) \
__hibernate_exit_text_end = .;
@@ -103,7 +102,6 @@ jiffies = jiffies_64;
#ifdef CONFIG_KEXEC_CORE
#define KEXEC_TEXT \
- . = ALIGN(SZ_4K); \
__relocate_new_kernel_start = .; \
*(.kexec_relocate.text) \
__relocate_new_kernel_end = .;
@@ -170,9 +168,6 @@ SECTIONS
KPROBES_TEXT
HYPERVISOR_TEXT
IDMAP_TEXT
- HIBERNATE_TEXT
- KEXEC_TEXT
- TRAMP_TEXT
*(.gnu.warning)
. = ALIGN(16);
*(.got) /* Global offset table */
@@ -194,6 +189,14 @@ SECTIONS
HYPERVISOR_DATA_SECTIONS
+ /* code sections that are never executed via the kernel mapping */
+ .rodata.text : {
+ TRAMP_TEXT
+ HIBERNATE_TEXT
+ KEXEC_TEXT
+ . = ALIGN(PAGE_SIZE);
+ }
+
idmap_pg_dir = .;
. += IDMAP_DIR_SIZE;
idmap_pg_end = .;
@@ -337,8 +340,8 @@ ASSERT(__hyp_idmap_text_end - __hyp_idmap_text_start <= PAGE_SIZE,
ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
"ID map text too big or misaligned")
#ifdef CONFIG_HIBERNATION
-ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
- <= SZ_4K, "Hibernate exit text too big or misaligned")
+ASSERT(__hibernate_exit_text_end - __hibernate_exit_text_start <= SZ_4K,
+ "Hibernate exit text is bigger than 4 KiB")
#endif
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE,
@@ -362,7 +365,7 @@ ASSERT(swapper_pg_dir - tramp_pg_dir == TRAMP_SWAPPER_OFFSET,
#ifdef CONFIG_KEXEC_CORE
/* kexec relocation code should fit into one KEXEC_CONTROL_PAGE_SIZE */
-ASSERT(__relocate_new_kernel_end - (__relocate_new_kernel_start & ~(SZ_4K - 1))
- <= SZ_4K, "kexec relocation code is too big or misaligned")
+ASSERT(__relocate_new_kernel_end - __relocate_new_kernel_start <= SZ_4K,
+ "kexec relocation code is bigger than 4 KiB")
ASSERT(KEXEC_CONTROL_PAGE_SIZE >= SZ_4K, "KEXEC_CONTROL_PAGE_SIZE is broken")
#endif