diff --git a/Documentation/admin-guide/perf/ampere_cspmu.rst b/Documentation/admin-guide/perf/ampere_cspmu.rst new file mode 100644 index 0000000..94f93f5 --- /dev/null +++ b/Documentation/admin-guide/perf/ampere_cspmu.rst @@ -0,0 +1,29 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================================ +Ampere SoC Performance Monitoring Unit (PMU) +============================================ + +Ampere SoC PMU is a generic PMU IP that follows Arm CoreSight PMU architecture. +Therefore, the driver is implemented as a submodule of arm_cspmu driver. At the +first phase it's used for counting MCU events on AmpereOne. + + +MCU PMU events +-------------- + +The PMU driver supports setting filters for "rank", "bank", and "threshold". +Note, that the filters are per PMU instance rather than per event. + + +Example for perf tool use:: + + / # perf list ampere + + ampere_mcu_pmu_0/act_sent/ [Kernel PMU event] + <...> + ampere_mcu_pmu_1/rd_sent/ [Kernel PMU event] + <...> + + / # perf stat -a -e ampere_mcu_pmu_0/act_sent,bank=5,rank=3,threshold=2/,ampere_mcu_pmu_1/rd_sent/ \ + sleep 1 diff --git a/Documentation/admin-guide/perf/index.rst b/Documentation/admin-guide/perf/index.rst index f60be04..a2e6f2c 100644 --- a/Documentation/admin-guide/perf/index.rst +++ b/Documentation/admin-guide/perf/index.rst @@ -22,3 +22,4 @@ Performance monitor support nvidia-pmu meson-ddr-pmu cxl + ampere_cspmu diff --git a/Documentation/arch/arm64/cpu-feature-registers.rst b/Documentation/arch/arm64/cpu-feature-registers.rst index de6d8a4..44f9bd7 100644 --- a/Documentation/arch/arm64/cpu-feature-registers.rst +++ b/Documentation/arch/arm64/cpu-feature-registers.rst @@ -268,6 +268,8 @@ infrastructure: +------------------------------+---------+---------+ | SHA3 | [35-32] | y | +------------------------------+---------+---------+ + | B16B16 | [27-24] | y | + +------------------------------+---------+---------+ | BF16 | [23-20] | y | +------------------------------+---------+---------+ | BitPerm | [19-16] | y | diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 76ff9d7..4b8399a 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -308,6 +308,15 @@ HWCAP2_MOPS HWCAP2_HBC Functionality implied by ID_AA64ISAR2_EL1.BC == 0b0001. +HWCAP2_SVE_B16B16 + Functionality implied by ID_AA64ZFR0_EL1.B16B16 == 0b0001. + +HWCAP2_LRCPC3 + Functionality implied by ID_AA64ISAR1_EL1.LRCPC == 0b0011. + +HWCAP2_LSE128 + Functionality implied by ID_AA64ISAR0_EL1.Atomic == 0b0011. + 4. Unused AT_HWCAP bits ----------------------- diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index c392e18..9afdc4c 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -164,9 +164,6 @@ static int xen_starting_cpu(unsigned int cpu) BUG_ON(err); per_cpu(xen_vcpu, cpu) = vcpup; - if (!xen_kernel_unmapped_at_usr()) - xen_setup_runstate_info(cpu); - after_register_vcpu_info: enable_percpu_irq(xen_events_irq, 0); return 0; @@ -523,9 +520,6 @@ static int __init xen_guest_init(void) return -EINVAL; } - if (!xen_kernel_unmapped_at_usr()) - xen_time_setup_guest(); - if (xen_initial_domain()) pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); @@ -535,7 +529,13 @@ static int __init xen_guest_init(void) } early_initcall(xen_guest_init); -static int __init xen_pm_init(void) +static int xen_starting_runstate_cpu(unsigned int cpu) +{ + xen_setup_runstate_info(cpu); + return 0; +} + +static int __init xen_late_init(void) { if (!xen_domain()) return -ENODEV; @@ -548,9 +548,16 @@ static int __init xen_pm_init(void) do_settimeofday64(&ts); } - return 0; + if (xen_kernel_unmapped_at_usr()) + return 0; + + xen_time_setup_guest(); + + return cpuhp_setup_state(CPUHP_AP_ARM_XEN_RUNSTATE_STARTING, + "arm/xen_runstate:starting", + xen_starting_runstate_cpu, NULL); } -late_initcall(xen_pm_init); +late_initcall(xen_late_init); /* empty stubs */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 78f20e6..6062a52 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1368,6 +1368,8 @@ choice config CPU_BIG_ENDIAN bool "Build big-endian kernel" depends on !LD_IS_LLD || LLD_VERSION >= 130000 + # https://github.com/llvm/llvm-project/commit/1379b150991f70a5782e9a143c2ba5308da1161c + depends on AS_IS_GNU || AS_VERSION >= 150000 help Say Y if you plan on running a kernel with a big-endian userspace. diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 5c8ee5a..4b6d2d5 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -6,5 +6,5 @@ generic-y += qspinlock.h generic-y += parport.h generic-y += user.h -generated-y += cpucaps.h +generated-y += cpucap-defs.h generated-y += sysreg-defs.h diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 94b4861..210bb43 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -226,8 +226,8 @@ alternative_endif static __always_inline bool alternative_has_cap_likely(const unsigned long cpucap) { - compiletime_assert(cpucap < ARM64_NCAPS, - "cpucap must be < ARM64_NCAPS"); + if (!cpucap_is_possible(cpucap)) + return false; asm_volatile_goto( ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops) @@ -244,8 +244,8 @@ l_no: static __always_inline bool alternative_has_cap_unlikely(const unsigned long cpucap) { - compiletime_assert(cpucap < ARM64_NCAPS, - "cpucap must be < ARM64_NCAPS"); + if (!cpucap_is_possible(cpucap)) + return false; asm_volatile_goto( ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap]) diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 01281a5..5f17261 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -79,6 +79,14 @@ static inline u64 gic_read_iar_cavium_thunderx(void) return 0x3ff; } +static u64 __maybe_unused gic_read_iar(void) +{ + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_CAVIUM_23154)) + return gic_read_iar_cavium_thunderx(); + else + return gic_read_iar_common(); +} + static inline void gic_write_ctlr(u32 val) { write_sysreg_s(val, SYS_ICC_CTLR_EL1); diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h index b0abc64..ecdb3cf 100644 --- a/arch/arm64/include/asm/archrandom.h +++ b/arch/arm64/include/asm/archrandom.h @@ -63,7 +63,7 @@ static __always_inline bool __cpu_has_rng(void) { if (unlikely(!system_capabilities_finalized() && !preemptible())) return this_cpu_has_cap(ARM64_HAS_RNG); - return cpus_have_const_cap(ARM64_HAS_RNG); + return alternative_has_cap_unlikely(ARM64_HAS_RNG); } static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index d115451..fefac75 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -132,7 +132,7 @@ void flush_dcache_folio(struct folio *); static __always_inline void icache_inval_all_pou(void) { - if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) + if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC)) return; asm("ic ialluis"); diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index e749838..f303409 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -63,12 +63,6 @@ struct cpuinfo_arm64 { u64 reg_id_aa64smfr0; struct cpuinfo_32bit aarch32; - - /* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */ - u64 reg_zcr; - - /* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */ - u64 reg_smcr; }; DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data); diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h new file mode 100644 index 0000000..270680e --- /dev/null +++ b/arch/arm64/include/asm/cpucaps.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_CPUCAPS_H +#define __ASM_CPUCAPS_H + +#include + +#ifndef __ASSEMBLY__ +#include +/* + * Check whether a cpucap is possible at compiletime. + */ +static __always_inline bool +cpucap_is_possible(const unsigned int cap) +{ + compiletime_assert(__builtin_constant_p(cap), + "cap must be a constant"); + compiletime_assert(cap < ARM64_NCAPS, + "cap must be < ARM64_NCAPS"); + + switch (cap) { + case ARM64_HAS_PAN: + return IS_ENABLED(CONFIG_ARM64_PAN); + case ARM64_HAS_EPAN: + return IS_ENABLED(CONFIG_ARM64_EPAN); + case ARM64_SVE: + return IS_ENABLED(CONFIG_ARM64_SVE); + case ARM64_SME: + case ARM64_SME2: + case ARM64_SME_FA64: + return IS_ENABLED(CONFIG_ARM64_SME); + case ARM64_HAS_CNP: + return IS_ENABLED(CONFIG_ARM64_CNP); + case ARM64_HAS_ADDRESS_AUTH: + case ARM64_HAS_GENERIC_AUTH: + return IS_ENABLED(CONFIG_ARM64_PTR_AUTH); + case ARM64_HAS_GIC_PRIO_MASKING: + return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI); + case ARM64_MTE: + return IS_ENABLED(CONFIG_ARM64_MTE); + case ARM64_BTI: + return IS_ENABLED(CONFIG_ARM64_BTI); + case ARM64_HAS_TLB_RANGE: + return IS_ENABLED(CONFIG_ARM64_TLB_RANGE); + case ARM64_UNMAP_KERNEL_AT_EL0: + return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0); + case ARM64_WORKAROUND_843419: + return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419); + case ARM64_WORKAROUND_1742098: + return IS_ENABLED(CONFIG_ARM64_ERRATUM_1742098); + case ARM64_WORKAROUND_2645198: + return IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198); + case ARM64_WORKAROUND_2658417: + return IS_ENABLED(CONFIG_ARM64_ERRATUM_2658417); + case ARM64_WORKAROUND_CAVIUM_23154: + return IS_ENABLED(CONFIG_CAVIUM_ERRATUM_23154); + case ARM64_WORKAROUND_NVIDIA_CARMEL_CNP: + return IS_ENABLED(CONFIG_NVIDIA_CARMEL_CNP_ERRATUM); + case ARM64_WORKAROUND_REPEAT_TLBI: + return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI); + } + + return true; +} +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 5bba393..f6d416f 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -23,6 +23,7 @@ #include #include #include +#include /* * CPU feature register tracking @@ -380,6 +381,7 @@ struct arm64_cpu_capabilities { * method is robust against being called multiple times. */ const struct arm64_cpu_capabilities *match_list; + const struct cpumask *cpus; }; static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) @@ -438,6 +440,11 @@ unsigned long cpu_get_elf_hwcap2(void); #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name)) #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name)) +static __always_inline bool boot_capabilities_finalized(void) +{ + return alternative_has_cap_likely(ARM64_ALWAYS_BOOT); +} + static __always_inline bool system_capabilities_finalized(void) { return alternative_has_cap_likely(ARM64_ALWAYS_SYSTEM); @@ -450,6 +457,8 @@ static __always_inline bool system_capabilities_finalized(void) */ static __always_inline bool cpus_have_cap(unsigned int num) { + if (__builtin_constant_p(num) && !cpucap_is_possible(num)) + return false; if (num >= ARM64_NCAPS) return false; return arch_test_bit(num, system_cpucaps); @@ -458,55 +467,37 @@ static __always_inline bool cpus_have_cap(unsigned int num) /* * Test for a capability without a runtime check. * - * Before capabilities are finalized, this returns false. - * After capabilities are finalized, this is patched to avoid a runtime check. + * Before boot capabilities are finalized, this will BUG(). + * After boot capabilities are finalized, this is patched to avoid a runtime + * check. * * @num must be a compile-time constant. */ -static __always_inline bool __cpus_have_const_cap(int num) +static __always_inline bool cpus_have_final_boot_cap(int num) { - if (num >= ARM64_NCAPS) - return false; - return alternative_has_cap_unlikely(num); + if (boot_capabilities_finalized()) + return alternative_has_cap_unlikely(num); + else + BUG(); } /* * Test for a capability without a runtime check. * - * Before capabilities are finalized, this will BUG(). - * After capabilities are finalized, this is patched to avoid a runtime check. + * Before system capabilities are finalized, this will BUG(). + * After system capabilities are finalized, this is patched to avoid a runtime + * check. * * @num must be a compile-time constant. */ static __always_inline bool cpus_have_final_cap(int num) { if (system_capabilities_finalized()) - return __cpus_have_const_cap(num); + return alternative_has_cap_unlikely(num); else BUG(); } -/* - * Test for a capability, possibly with a runtime check for non-hyp code. - * - * For hyp code, this behaves the same as cpus_have_final_cap(). - * - * For non-hyp code: - * Before capabilities are finalized, this behaves as cpus_have_cap(). - * After capabilities are finalized, this is patched to avoid a runtime check. - * - * @num must be a compile-time constant. - */ -static __always_inline bool cpus_have_const_cap(int num) -{ - if (is_hyp_code()) - return cpus_have_final_cap(num); - else if (system_capabilities_finalized()) - return __cpus_have_const_cap(num); - else - return cpus_have_cap(num); -} - static inline int __attribute_const__ cpuid_feature_extract_signed_field_width(u64 features, int field, int width) { @@ -626,7 +617,9 @@ static inline bool id_aa64pfr1_mte(u64 pfr1) return val >= ID_AA64PFR1_EL1_MTE_MTE2; } -void __init setup_cpu_features(void); +void __init setup_system_features(void); +void __init setup_user_features(void); + void check_local_cpu_capabilities(void); u64 read_sanitised_ftr_reg(u32 id); @@ -735,13 +728,12 @@ static inline bool system_supports_mixed_endian(void) static __always_inline bool system_supports_fpsimd(void) { - return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); + return alternative_has_cap_likely(ARM64_HAS_FPSIMD); } static inline bool system_uses_hw_pan(void) { - return IS_ENABLED(CONFIG_ARM64_PAN) && - cpus_have_const_cap(ARM64_HAS_PAN); + return alternative_has_cap_unlikely(ARM64_HAS_PAN); } static inline bool system_uses_ttbr0_pan(void) @@ -752,26 +744,22 @@ static inline bool system_uses_ttbr0_pan(void) static __always_inline bool system_supports_sve(void) { - return IS_ENABLED(CONFIG_ARM64_SVE) && - cpus_have_const_cap(ARM64_SVE); + return alternative_has_cap_unlikely(ARM64_SVE); } static __always_inline bool system_supports_sme(void) { - return IS_ENABLED(CONFIG_ARM64_SME) && - cpus_have_const_cap(ARM64_SME); + return alternative_has_cap_unlikely(ARM64_SME); } static __always_inline bool system_supports_sme2(void) { - return IS_ENABLED(CONFIG_ARM64_SME) && - cpus_have_const_cap(ARM64_SME2); + return alternative_has_cap_unlikely(ARM64_SME2); } static __always_inline bool system_supports_fa64(void) { - return IS_ENABLED(CONFIG_ARM64_SME) && - cpus_have_const_cap(ARM64_SME_FA64); + return alternative_has_cap_unlikely(ARM64_SME_FA64); } static __always_inline bool system_supports_tpidr2(void) @@ -781,20 +769,17 @@ static __always_inline bool system_supports_tpidr2(void) static __always_inline bool system_supports_cnp(void) { - return IS_ENABLED(CONFIG_ARM64_CNP) && - cpus_have_const_cap(ARM64_HAS_CNP); + return alternative_has_cap_unlikely(ARM64_HAS_CNP); } static inline bool system_supports_address_auth(void) { - return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) && - cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH); + return cpus_have_final_boot_cap(ARM64_HAS_ADDRESS_AUTH); } static inline bool system_supports_generic_auth(void) { - return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) && - cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH); + return alternative_has_cap_unlikely(ARM64_HAS_GENERIC_AUTH); } static inline bool system_has_full_ptr_auth(void) @@ -804,14 +789,12 @@ static inline bool system_has_full_ptr_auth(void) static __always_inline bool system_uses_irq_prio_masking(void) { - return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && - cpus_have_const_cap(ARM64_HAS_GIC_PRIO_MASKING); + return alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING); } static inline bool system_supports_mte(void) { - return IS_ENABLED(CONFIG_ARM64_MTE) && - cpus_have_const_cap(ARM64_MTE); + return alternative_has_cap_unlikely(ARM64_MTE); } static inline bool system_has_prio_mask_debugging(void) @@ -822,13 +805,18 @@ static inline bool system_has_prio_mask_debugging(void) static inline bool system_supports_bti(void) { - return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI); + return cpus_have_final_cap(ARM64_BTI); +} + +static inline bool system_supports_bti_kernel(void) +{ + return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && + cpus_have_final_boot_cap(ARM64_BTI); } static inline bool system_supports_tlb_range(void) { - return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) && - cpus_have_const_cap(ARM64_HAS_TLB_RANGE); + return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE); } int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 74d00fe..7c7493c 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,7 +86,8 @@ #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B -#define APM_CPU_PART_POTENZA 0x000 +#define APM_CPU_PART_XGENE 0x000 +#define APM_CPU_VAR_POTENZA 0x00 #define CAVIUM_CPU_PART_THUNDERX 0x0A1 #define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 8df46f1..50e5f25 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -32,6 +32,32 @@ #define VFP_STATE_SIZE ((32 * 8) + 4) #endif +static inline unsigned long cpacr_save_enable_kernel_sve(void) +{ + unsigned long old = read_sysreg(cpacr_el1); + unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN; + + write_sysreg(old | set, cpacr_el1); + isb(); + return old; +} + +static inline unsigned long cpacr_save_enable_kernel_sme(void) +{ + unsigned long old = read_sysreg(cpacr_el1); + unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_SMEN_EL1EN; + + write_sysreg(old | set, cpacr_el1); + isb(); + return old; +} + +static inline void cpacr_restore(unsigned long cpacr) +{ + write_sysreg(cpacr, cpacr_el1); + isb(); +} + /* * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future @@ -123,12 +149,12 @@ extern void sme_save_state(void *state, int zt); extern void sme_load_state(void const *state, int zt); struct arm64_cpu_capabilities; -extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); -extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused); -extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused); -extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); -extern u64 read_zcr_features(void); extern u64 read_smcr_features(void); /* diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 5212674..cd71e09 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -139,6 +139,9 @@ #define KERNEL_HWCAP_SME_F16F16 __khwcap2_feature(SME_F16F16) #define KERNEL_HWCAP_MOPS __khwcap2_feature(MOPS) #define KERNEL_HWCAP_HBC __khwcap2_feature(HBC) +#define KERNEL_HWCAP_SVE_B16B16 __khwcap2_feature(SVE_B16B16) +#define KERNEL_HWCAP_LRCPC3 __khwcap2_feature(LRCPC3) +#define KERNEL_HWCAP_LSE128 __khwcap2_feature(LSE128) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index fac08e1..50ce8b6 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -6,6 +6,9 @@ #include +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace + struct pt_regs; int set_handle_irq(void (*handle_irq)(struct pt_regs *)); diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 1f31ec1..0a7186a 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -21,12 +21,6 @@ * exceptions should be unmasked. */ -static __always_inline bool __irqflags_uses_pmr(void) -{ - return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && - alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING); -} - static __always_inline void __daif_local_irq_enable(void) { barrier(); @@ -49,7 +43,7 @@ static __always_inline void __pmr_local_irq_enable(void) static inline void arch_local_irq_enable(void) { - if (__irqflags_uses_pmr()) { + if (system_uses_irq_prio_masking()) { __pmr_local_irq_enable(); } else { __daif_local_irq_enable(); @@ -77,7 +71,7 @@ static __always_inline void __pmr_local_irq_disable(void) static inline void arch_local_irq_disable(void) { - if (__irqflags_uses_pmr()) { + if (system_uses_irq_prio_masking()) { __pmr_local_irq_disable(); } else { __daif_local_irq_disable(); @@ -99,7 +93,7 @@ static __always_inline unsigned long __pmr_local_save_flags(void) */ static inline unsigned long arch_local_save_flags(void) { - if (__irqflags_uses_pmr()) { + if (system_uses_irq_prio_masking()) { return __pmr_local_save_flags(); } else { return __daif_local_save_flags(); @@ -118,7 +112,7 @@ static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags) static inline bool arch_irqs_disabled_flags(unsigned long flags) { - if (__irqflags_uses_pmr()) { + if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled_flags(flags); } else { return __daif_irqs_disabled_flags(flags); @@ -137,7 +131,7 @@ static __always_inline bool __pmr_irqs_disabled(void) static inline bool arch_irqs_disabled(void) { - if (__irqflags_uses_pmr()) { + if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled(); } else { return __daif_irqs_disabled(); @@ -169,7 +163,7 @@ static __always_inline unsigned long __pmr_local_irq_save(void) static inline unsigned long arch_local_irq_save(void) { - if (__irqflags_uses_pmr()) { + if (system_uses_irq_prio_masking()) { return __pmr_local_irq_save(); } else { return __daif_local_irq_save(); @@ -196,7 +190,7 @@ static __always_inline void __pmr_local_irq_restore(unsigned long flags) */ static inline void arch_local_irq_restore(unsigned long flags) { - if (__irqflags_uses_pmr()) { + if (system_uses_irq_prio_masking()) { __pmr_local_irq_restore(flags); } else { __daif_local_irq_restore(flags); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 3d6725f..cbd2f16 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -71,14 +71,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; if (has_vhe() || has_hvhe()) vcpu->arch.hcr_el2 |= HCR_E2H; - if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) { + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) { /* route synchronous external abort exceptions to EL2 */ vcpu->arch.hcr_el2 |= HCR_TEA; /* trap error record accesses */ vcpu->arch.hcr_el2 |= HCR_TERR; } - if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) { + if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) { vcpu->arch.hcr_el2 |= HCR_FWB; } else { /* diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index af06ccb..e64d64e 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1052,7 +1052,7 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) static inline bool kvm_system_needs_idmapped_vectors(void) { - return cpus_have_const_cap(ARM64_SPECTRE_V3A); + return cpus_have_final_cap(ARM64_SPECTRE_V3A); } static inline void kvm_arch_sync_events(struct kvm *kvm) {} diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 96a80e8..2781066 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -218,7 +218,7 @@ static inline void __clean_dcache_guest_page(void *va, size_t size) * faulting in pages. Furthermore, FWB implies IDC, so cleaning to * PoU is not required either in this case. */ - if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) + if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) return; kvm_flush_dcache_to_poc(va, size); diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index cbbcdc3..3129a58 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -16,14 +16,9 @@ #include #include -static __always_inline bool system_uses_lse_atomics(void) -{ - return alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS); -} - #define __lse_ll_sc_body(op, ...) \ ({ \ - system_uses_lse_atomics() ? \ + alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS) ? \ __lse_##op(__VA_ARGS__) : \ __ll_sc_##op(__VA_ARGS__); \ }) @@ -34,8 +29,6 @@ static __always_inline bool system_uses_lse_atomics(void) #else /* CONFIG_ARM64_LSE_ATOMICS */ -static inline bool system_uses_lse_atomics(void) { return false; } - #define __lse_ll_sc_body(op, ...) __ll_sc_##op(__VA_ARGS__) #define ARM64_LSE_ATOMIC_INSN(llsc, lse) llsc diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 94b6885..2fcf512 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -57,7 +57,7 @@ typedef struct { static inline bool arm64_kernel_unmapped_at_el0(void) { - return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0); + return alternative_has_cap_unlikely(ARM64_UNMAP_KERNEL_AT_EL0); } extern void arm64_memblock_init(void); diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index a6fb325..9ce4200 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -152,7 +152,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) +static inline void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; @@ -162,17 +162,8 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */ phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp)); - if (system_supports_cnp() && !WARN_ON(pgdp != lm_alias(swapper_pg_dir))) { - /* - * cpu_replace_ttbr1() is used when there's a boot CPU - * up (i.e. cpufeature framework is not up yet) and - * latter only when we enable CNP via cpufeature's - * enable() callback. - * Also we rely on the system_cpucaps bit being set before - * calling the enable() function. - */ + if (cnp) ttbr1 |= TTBR_CNP_BIT; - } replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); @@ -189,6 +180,21 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) cpu_uninstall_idmap(); } +static inline void cpu_enable_swapper_cnp(void) +{ + __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir, true); +} + +static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) +{ + /* + * Only for early TTBR1 replacement before cpucaps are finalized and + * before we've decided whether to use CNP. + */ + WARN_ON(system_capabilities_finalized()); + __cpu_replace_ttbr1(pgdp, idmap, false); +} + /* * It would be nice to return ASIDs back to the allocator, but unfortunately * that introduces a race with a generation rollover where we could erroneously diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index bfa6638..79550b2 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -44,8 +44,7 @@ struct plt_entry { static inline bool is_forbidden_offset_for_adrp(void *place) { - return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) && - cpus_have_const_cap(ARM64_WORKAROUND_843419) && + return cpus_have_final_cap(ARM64_WORKAROUND_843419) && ((u64)place & 0xfff) >= 0xff8; } diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 4cedbaa..91fbd5c 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -90,7 +90,7 @@ static inline bool try_page_mte_tagging(struct page *page) } void mte_zero_clear_page_tags(void *addr); -void mte_sync_tags(pte_t pte); +void mte_sync_tags(pte_t pte, unsigned int nr_pages); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); @@ -122,7 +122,7 @@ static inline bool try_page_mte_tagging(struct page *page) static inline void mte_zero_clear_page_tags(void *addr) { } -static inline void mte_sync_tags(pte_t pte) +static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages) { } static inline void mte_copy_page_tags(void *kto, const void *kfrom) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index eed814b..e9624f6 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -75,11 +75,7 @@ extern bool arm64_use_ng_mappings; * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. */ -#ifdef CONFIG_ARM64_BTI_KERNEL -#define PTE_MAYBE_GP (system_supports_bti() ? PTE_GP : 0) -#else -#define PTE_MAYBE_GP 0 -#endif +#define PTE_MAYBE_GP (system_supports_bti_kernel() ? PTE_GP : 0) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(_PAGE_KERNEL_RO) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7f7d9b1..b19a8ae 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -325,8 +325,7 @@ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, __func__, pte_val(old_pte), pte_val(pte)); } -static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) +static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) { if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte); @@ -339,24 +338,22 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, */ if (system_supports_mte() && pte_access_permitted(pte, false) && !pte_special(pte) && pte_tagged(pte)) - mte_sync_tags(pte); - - __check_safe_pte_update(mm, ptep, pte); - - set_pte(ptep, pte); + mte_sync_tags(pte, nr_pages); } -static inline void set_ptes(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned int nr) +static inline void set_ptes(struct mm_struct *mm, + unsigned long __always_unused addr, + pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); + __sync_cache_and_tags(pte, nr); for (;;) { - __set_pte_at(mm, addr, ptep, pte); + __check_safe_pte_update(mm, ptep, pte); + set_pte(ptep, pte); if (--nr == 0) break; ptep++; - addr += PAGE_SIZE; pte_val(pte) += PAGE_SIZE; } } @@ -531,18 +528,29 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) +static inline void __set_pte_at(struct mm_struct *mm, + unsigned long __always_unused addr, + pte_t *ptep, pte_t pte, unsigned int nr) +{ + __sync_cache_and_tags(pte, nr); + __check_safe_pte_update(mm, ptep, pte); + set_pte(ptep, pte); +} + static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, pmdp, pmd); - return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); + return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd), + PMD_SIZE >> PAGE_SHIFT); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, pudp, pud); - return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); + return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud), + PUD_SIZE >> PAGE_SHIFT); } #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 9b31e6d..efb1311 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -89,9 +89,9 @@ extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); #ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL -extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask); +extern void arch_send_wakeup_ipi(unsigned int cpu); #else -static inline void arch_send_wakeup_ipi_mask(const struct cpumask *mask) +static inline void arch_send_wakeup_ipi(unsigned int cpu) { BUILD_BUG(); } diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index 9cc5014..06c357d 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -73,7 +73,7 @@ static __always_inline void arm64_apply_bp_hardening(void) { struct bp_hardening_data *d; - if (!cpus_have_const_cap(ARM64_SPECTRE_V2)) + if (!alternative_has_cap_unlikely(ARM64_SPECTRE_V2)) return; d = this_cpu_ptr(&bp_hardening_data); diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index b149cf9..7aa476a 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -105,7 +105,7 @@ static inline unsigned long get_trans_granule(void) #define __tlbi_level(op, addr, level) do { \ u64 arg = addr; \ \ - if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) && \ + if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) && \ level) { \ u64 ttl = level & 3; \ ttl |= get_trans_granule() << 2; \ @@ -284,16 +284,15 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) { -#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI /* * TLB flush deferral is not required on systems which are affected by * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation * will have two consecutive TLBI instructions with a dsb(ish) in between * defeating the purpose (i.e save overall 'dsb ish' cost). */ - if (unlikely(cpus_have_const_cap(ARM64_WORKAROUND_REPEAT_TLBI))) + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI)) return false; -#endif + return true; } diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h index bc9a214..b815d8f 100644 --- a/arch/arm64/include/asm/vectors.h +++ b/arch/arm64/include/asm/vectors.h @@ -62,7 +62,7 @@ DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector); static inline const char * arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot) { - if (arm64_kernel_unmapped_at_el0()) + if (cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0)) return (char *)(TRAMP_VALIAS + SZ_2K * slot); WARN_ON_ONCE(slot == EL1_VECTOR_KPTI); diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 53026f4..5023599 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -104,5 +104,8 @@ #define HWCAP2_SME_F16F16 (1UL << 42) #define HWCAP2_MOPS (1UL << 43) #define HWCAP2_HBC (1UL << 44) +#define HWCAP2_SVE_B16B16 (1UL << 45) +#define HWCAP2_LRCPC3 (1UL << 46) +#define HWCAP2_LSE128 (1UL << 47) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c index b1990e3..e1be29e 100644 --- a/arch/arm64/kernel/acpi_parking_protocol.c +++ b/arch/arm64/kernel/acpi_parking_protocol.c @@ -103,7 +103,7 @@ static int acpi_parking_protocol_cpu_boot(unsigned int cpu) &mailbox->entry_point); writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id); - arch_send_wakeup_ipi_mask(cpumask_of(cpu)); + arch_send_wakeup_ipi(cpu); return 0; } diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5706e74..e29e0fe 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -121,22 +121,6 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0); } -static DEFINE_RAW_SPINLOCK(reg_user_mask_modification); -static void __maybe_unused -cpu_clear_bf16_from_user_emulation(const struct arm64_cpu_capabilities *__unused) -{ - struct arm64_ftr_reg *regp; - - regp = get_arm64_ftr_reg(SYS_ID_AA64ISAR1_EL1); - if (!regp) - return; - - raw_spin_lock(®_user_mask_modification); - if (regp->user_mask & ID_AA64ISAR1_EL1_BF16_MASK) - regp->user_mask &= ~ID_AA64ISAR1_EL1_BF16_MASK; - raw_spin_unlock(®_user_mask_modification); -} - #define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \ .matches = is_affected_midr_range, \ .midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max) @@ -727,7 +711,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A510 r0p0 - r1p1 */ ERRATA_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1), MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)), - .cpu_enable = cpu_clear_bf16_from_user_emulation, }, #endif #ifdef CONFIG_ARM64_ERRATUM_2966298 diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 444a73c..f6b2e29 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -279,6 +279,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SHA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_B16B16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, 0), @@ -611,18 +613,6 @@ static const struct arm64_ftr_bits ftr_id_dfr1[] = { ARM64_FTR_END, }; -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_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, -}; - /* * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of @@ -735,10 +725,6 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2), ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3), - /* 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), @@ -1040,22 +1026,26 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) if (IS_ENABLED(CONFIG_ARM64_SVE) && id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) { - info->reg_zcr = read_zcr_features(); - init_cpu_ftr_reg(SYS_ZCR_EL1, info->reg_zcr); + unsigned long cpacr = cpacr_save_enable_kernel_sve(); + vec_init_vq_map(ARM64_VEC_SVE); + + cpacr_restore(cpacr); } if (IS_ENABLED(CONFIG_ARM64_SME) && id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { - info->reg_smcr = read_smcr_features(); + unsigned long cpacr = cpacr_save_enable_kernel_sme(); + /* * We mask out SMPS since even if the hardware * supports priorities the kernel does not at present * and we block access to them. */ info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; - init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr); vec_init_vq_map(ARM64_VEC_SME); + + cpacr_restore(cpacr); } if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) @@ -1289,32 +1279,34 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); + /* Probe vector lengths */ if (IS_ENABLED(CONFIG_ARM64_SVE) && id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) { - info->reg_zcr = read_zcr_features(); - taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu, - info->reg_zcr, boot->reg_zcr); + if (!system_capabilities_finalized()) { + unsigned long cpacr = cpacr_save_enable_kernel_sve(); - /* Probe vector lengths */ - if (!system_capabilities_finalized()) vec_update_vq_map(ARM64_VEC_SVE); + + cpacr_restore(cpacr); + } } if (IS_ENABLED(CONFIG_ARM64_SME) && id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { - info->reg_smcr = read_smcr_features(); + unsigned long cpacr = cpacr_save_enable_kernel_sme(); + /* * We mask out SMPS since even if the hardware * supports priorities the kernel does not at present * and we block access to them. */ info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; - taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu, - info->reg_smcr, boot->reg_smcr); /* Probe vector lengths */ if (!system_capabilities_finalized()) vec_update_vq_map(ARM64_VEC_SME); + + cpacr_restore(cpacr); } /* @@ -1564,14 +1556,6 @@ static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int _ MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK)); } -static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unused) -{ - u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); - - return cpuid_feature_extract_signed_field(pfr0, - ID_AA64PFR0_EL1_FP_SHIFT) < 0; -} - static bool has_cache_idc(const struct arm64_cpu_capabilities *entry, int scope) { @@ -1621,7 +1605,7 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) if (is_kdump_kernel()) return false; - if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP)) + if (cpus_have_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP)) return false; return has_cpuid_feature(entry, scope); @@ -1754,16 +1738,15 @@ void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags); -static phys_addr_t kpti_ng_temp_alloc; +static phys_addr_t __initdata kpti_ng_temp_alloc; -static phys_addr_t kpti_ng_pgd_alloc(int shift) +static phys_addr_t __init kpti_ng_pgd_alloc(int shift) { kpti_ng_temp_alloc -= PAGE_SIZE; return kpti_ng_temp_alloc; } -static void -kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) +static int __init __kpti_install_ng_mappings(void *__unused) { typedef void (kpti_remap_fn)(int, int, phys_addr_t, unsigned long); extern kpti_remap_fn idmap_kpti_install_ng_mappings; @@ -1776,20 +1759,6 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) pgd_t *kpti_ng_temp_pgd; u64 alloc = 0; - if (__this_cpu_read(this_cpu_vector) == vectors) { - const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI); - - __this_cpu_write(this_cpu_vector, v); - } - - /* - * We don't need to rewrite the page-tables if either we've done - * it already or we have KASLR enabled and therefore have not - * created any global mappings at all. - */ - if (arm64_use_ng_mappings) - return; - remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); if (!cpu) { @@ -1826,14 +1795,39 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) free_pages(alloc, order); arm64_use_ng_mappings = true; } + + return 0; +} + +static void __init kpti_install_ng_mappings(void) +{ + /* + * We don't need to rewrite the page-tables if either we've done + * it already or we have KASLR enabled and therefore have not + * created any global mappings at all. + */ + if (arm64_use_ng_mappings) + return; + + stop_machine(__kpti_install_ng_mappings, NULL, cpu_online_mask); } + #else -static void -kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) +static inline void kpti_install_ng_mappings(void) { } #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ +static void cpu_enable_kpti(struct arm64_cpu_capabilities const *cap) +{ + if (__this_cpu_read(this_cpu_vector) == vectors) { + const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI); + + __this_cpu_write(this_cpu_vector, v); + } + +} + static int __init parse_kpti(char *str) { bool enabled; @@ -1848,6 +1842,8 @@ static int __init parse_kpti(char *str) early_param("kpti", parse_kpti); #ifdef CONFIG_ARM64_HW_AFDBM +static struct cpumask dbm_cpus __read_mostly; + static inline void __cpu_enable_hw_dbm(void) { u64 tcr = read_sysreg(tcr_el1) | TCR_HD; @@ -1883,35 +1879,22 @@ static bool cpu_can_use_dbm(const struct arm64_cpu_capabilities *cap) static void cpu_enable_hw_dbm(struct arm64_cpu_capabilities const *cap) { - if (cpu_can_use_dbm(cap)) + if (cpu_can_use_dbm(cap)) { __cpu_enable_hw_dbm(); + cpumask_set_cpu(smp_processor_id(), &dbm_cpus); + } } static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap, int __unused) { - static bool detected = false; /* * DBM is a non-conflicting feature. i.e, the kernel can safely * run a mix of CPUs with and without the feature. So, we * unconditionally enable the capability to allow any late CPU * to use the feature. We only enable the control bits on the - * CPU, if it actually supports. - * - * We have to make sure we print the "feature" detection only - * when at least one CPU actually uses it. So check if this CPU - * can actually use it and print the message exactly once. - * - * This is safe as all CPUs (including secondary CPUs - due to the - * LOCAL_CPU scope - and the hotplugged CPUs - via verification) - * goes through the "matches" check exactly once. Also if a CPU - * matches the criteria, it is guaranteed that the CPU will turn - * the DBM on, as the capability is unconditionally enabled. + * CPU, if it is supported. */ - if (!detected && cpu_can_use_dbm(cap)) { - detected = true; - pr_info("detected: Hardware dirty bit management\n"); - } return true; } @@ -1944,8 +1927,6 @@ int get_cpu_with_amu_feat(void) static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) { if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) { - pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n", - smp_processor_id()); cpumask_set_cpu(smp_processor_id(), &amu_cpus); /* 0 reference values signal broken/disabled counters */ @@ -2190,12 +2171,23 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_MTE */ +static void user_feature_fixup(void) +{ + if (cpus_have_cap(ARM64_WORKAROUND_2658417)) { + struct arm64_ftr_reg *regp; + + regp = get_arm64_ftr_reg(SYS_ID_AA64ISAR1_EL1); + if (regp) + regp->user_mask &= ~ID_AA64ISAR1_EL1_BF16_MASK; + } +} + static void elf_hwcap_fixup(void) { -#ifdef CONFIG_ARM64_ERRATUM_1742098 - if (cpus_have_const_cap(ARM64_WORKAROUND_1742098)) +#ifdef CONFIG_COMPAT + if (cpus_have_cap(ARM64_WORKAROUND_1742098)) compat_elf_hwcap2 &= ~COMPAT_HWCAP2_AES; -#endif /* ARM64_ERRATUM_1742098 */ +#endif /* CONFIG_COMPAT */ } #ifdef CONFIG_KVM @@ -2351,7 +2343,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Kernel page table isolation (KPTI)", .capability = ARM64_UNMAP_KERNEL_AT_EL0, .type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE, - .cpu_enable = kpti_install_ng_mappings, + .cpu_enable = cpu_enable_kpti, .matches = unmap_kernel_at_el0, /* * The ID feature fields below are used to indicate that @@ -2361,11 +2353,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = { ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, CSV3, IMP) }, { - /* FP/SIMD is not implemented */ - .capability = ARM64_HAS_NO_FPSIMD, - .type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE, - .min_field_value = 0, - .matches = has_no_fpsimd, + .capability = ARM64_HAS_FPSIMD, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_fpsimd, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, FP, IMP) }, #ifdef CONFIG_ARM64_PMEM { @@ -2388,7 +2380,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Scalable Vector Extension", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SVE, - .cpu_enable = sve_kernel_enable, + .cpu_enable = cpu_enable_sve, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, SVE, IMP) }, @@ -2405,16 +2397,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { #endif /* CONFIG_ARM64_RAS_EXTN */ #ifdef CONFIG_ARM64_AMU_EXTN { - /* - * The feature is enabled by default if CONFIG_ARM64_AMU_EXTN=y. - * Therefore, don't provide .desc as we don't want the detection - * message to be shown until at least one CPU is detected to - * support the feature. - */ + .desc = "Activity Monitors Unit (AMU)", .capability = ARM64_HAS_AMU_EXTN, .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .matches = has_amu, .cpu_enable = cpu_amu_enable, + .cpus = &amu_cpus, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, AMU, IMP) }, #endif /* CONFIG_ARM64_AMU_EXTN */ @@ -2454,18 +2442,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { }, #ifdef CONFIG_ARM64_HW_AFDBM { - /* - * Since we turn this on always, we don't want the user to - * think that the feature is available when it may not be. - * So hide the description. - * - * .desc = "Hardware pagetable Dirty Bit Management", - * - */ + .desc = "Hardware dirty bit management", .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .capability = ARM64_HW_DBM, .matches = has_hw_dbm, .cpu_enable = cpu_enable_hw_dbm, + .cpus = &dbm_cpus, ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, DBM) }, #endif @@ -2641,7 +2623,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME, .matches = has_cpuid_feature, - .cpu_enable = sme_kernel_enable, + .cpu_enable = cpu_enable_sme, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SME, IMP) }, /* FA64 should be sorted after the base SME capability */ @@ -2650,7 +2632,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME_FA64, .matches = has_cpuid_feature, - .cpu_enable = fa64_kernel_enable, + .cpu_enable = cpu_enable_fa64, ARM64_CPUID_FIELDS(ID_AA64SMFR0_EL1, FA64, IMP) }, { @@ -2658,7 +2640,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME2, .matches = has_cpuid_feature, - .cpu_enable = sme2_kernel_enable, + .cpu_enable = cpu_enable_sme2, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SME, SME2) }, #endif /* CONFIG_ARM64_SME */ @@ -2787,6 +2769,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, SHA2, SHA512, CAP_HWCAP, KERNEL_HWCAP_SHA512), HWCAP_CAP(ID_AA64ISAR0_EL1, CRC32, IMP, CAP_HWCAP, KERNEL_HWCAP_CRC32), HWCAP_CAP(ID_AA64ISAR0_EL1, ATOMIC, IMP, CAP_HWCAP, KERNEL_HWCAP_ATOMICS), + HWCAP_CAP(ID_AA64ISAR0_EL1, ATOMIC, FEAT_LSE128, CAP_HWCAP, KERNEL_HWCAP_LSE128), HWCAP_CAP(ID_AA64ISAR0_EL1, RDM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM), HWCAP_CAP(ID_AA64ISAR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SHA3), HWCAP_CAP(ID_AA64ISAR0_EL1, SM3, IMP, CAP_HWCAP, KERNEL_HWCAP_SM3), @@ -2807,6 +2790,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR1_EL1, FCMA, IMP, CAP_HWCAP, KERNEL_HWCAP_FCMA), HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, IMP, CAP_HWCAP, KERNEL_HWCAP_LRCPC), HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, LRCPC2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), + HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, LRCPC3, CAP_HWCAP, KERNEL_HWCAP_LRCPC3), HWCAP_CAP(ID_AA64ISAR1_EL1, FRINTTS, IMP, CAP_HWCAP, KERNEL_HWCAP_FRINT), HWCAP_CAP(ID_AA64ISAR1_EL1, SB, IMP, CAP_HWCAP, KERNEL_HWCAP_SB), HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_BF16), @@ -2821,6 +2805,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP(ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), @@ -2981,7 +2966,7 @@ static void update_cpu_capabilities(u16 scope_mask) !caps->matches(caps, cpucap_default_scope(caps))) continue; - if (caps->desc) + if (caps->desc && !caps->cpus) pr_info("detected: %s\n", caps->desc); __set_bit(caps->capability, system_cpucaps); @@ -3153,36 +3138,28 @@ static void verify_local_elf_hwcaps(void) static void verify_sve_features(void) { - u64 safe_zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1); - u64 zcr = read_zcr_features(); + unsigned long cpacr = cpacr_save_enable_kernel_sve(); - unsigned int safe_len = safe_zcr & ZCR_ELx_LEN_MASK; - unsigned int len = zcr & ZCR_ELx_LEN_MASK; - - if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SVE)) { + if (vec_verify_vq_map(ARM64_VEC_SVE)) { pr_crit("CPU%d: SVE: vector length support mismatch\n", smp_processor_id()); cpu_die_early(); } - /* Add checks on other ZCR bits here if necessary */ + cpacr_restore(cpacr); } 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; + unsigned long cpacr = cpacr_save_enable_kernel_sme(); - if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) { + if (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 */ + cpacr_restore(cpacr); } static void verify_hyp_capabilities(void) @@ -3289,7 +3266,6 @@ EXPORT_SYMBOL_GPL(this_cpu_has_cap); * This helper function is used in a narrow window when, * - The system wide safe registers are set with all the SMP CPUs and, * - The SYSTEM_FEATURE system_cpucaps may not have been set. - * In all other cases cpus_have_{const_}cap() should be used. */ static bool __maybe_unused __system_matches_cap(unsigned int n) { @@ -3328,23 +3304,50 @@ unsigned long cpu_get_elf_hwcap2(void) return elf_hwcap[1]; } -static void __init setup_system_capabilities(void) +void __init setup_system_features(void) { + int i; /* - * We have finalised the system-wide safe feature - * registers, finalise the capabilities that depend - * on it. Also enable all the available capabilities, - * that are not enabled already. + * The system-wide safe feature feature register values have been + * finalized. Finalize and log the available system capabilities. */ update_cpu_capabilities(SCOPE_SYSTEM); + if (IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) && + !cpus_have_cap(ARM64_HAS_PAN)) + pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); + + /* + * Enable all the available capabilities which have not been enabled + * already. + */ enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU); + + kpti_install_ng_mappings(); + + sve_setup(); + sme_setup(); + + /* + * Check for sane CTR_EL0.CWG value. + */ + if (!cache_type_cwg()) + pr_warn("No Cache Writeback Granule information, assuming %d\n", + ARCH_DMA_MINALIGN); + + for (i = 0; i < ARM64_NCAPS; i++) { + const struct arm64_cpu_capabilities *caps = cpucap_ptrs[i]; + + if (caps && caps->cpus && caps->desc && + cpumask_any(caps->cpus) < nr_cpu_ids) + pr_info("detected: %s on CPU%*pbl\n", + caps->desc, cpumask_pr_args(caps->cpus)); + } } -void __init setup_cpu_features(void) +void __init setup_user_features(void) { - u32 cwg; + user_feature_fixup(); - setup_system_capabilities(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) { @@ -3352,20 +3355,7 @@ void __init setup_cpu_features(void) elf_hwcap_fixup(); } - if (system_uses_ttbr0_pan()) - pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); - - sve_setup(); - sme_setup(); minsigstksz_setup(); - - /* - * Check for sane CTR_EL0.CWG value. - */ - cwg = cache_type_cwg(); - if (!cwg) - pr_warn("No Cache Writeback Granule information, assuming %d\n", - ARCH_DMA_MINALIGN); } static int enable_mismatched_32bit_el0(unsigned int cpu) @@ -3422,7 +3412,7 @@ subsys_initcall_sync(init_32bit_el0_mask); static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap) { - cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir); + cpu_enable_swapper_cnp(); } /* diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 98fda85..a257da7 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -127,6 +127,9 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_F16F16] = "smef16f16", [KERNEL_HWCAP_MOPS] = "mops", [KERNEL_HWCAP_HBC] = "hbc", + [KERNEL_HWCAP_SVE_B16B16] = "sveb16b16", + [KERNEL_HWCAP_LRCPC3] = "lrcpc3", + [KERNEL_HWCAP_LSE128] = "lse128", }; #ifdef CONFIG_COMPAT diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 2b478ca..3f8c9c1 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -113,8 +113,7 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); if (md->attribute & EFI_MEMORY_XP) pte = set_pte_bit(pte, __pgprot(PTE_PXN)); - else if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && - system_supports_bti() && spd->has_bti) + else if (system_supports_bti_kernel() && spd->has_bti) pte = set_pte_bit(pte, __pgprot(PTE_GP)); set_pte(ptep, pte); return 0; diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 91e44ac..5ddc246 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1160,44 +1160,20 @@ fail: panic("Cannot allocate percpu memory for EFI SVE save/restore"); } -/* - * Enable SVE for EL1. - * Intended for use by the cpufeatures code during CPU boot. - */ -void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1); isb(); } -/* - * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE - * vector length. - * - * Use only if SVE is present. - * This function clobbers the SVE vector length. - */ -u64 read_zcr_features(void) -{ - /* - * Set the maximum possible VL, and write zeroes to all other - * bits to see if they stick. - */ - sve_kernel_enable(NULL); - write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1); - - /* Return LEN value that would be written to get the maximum VL */ - return sve_vq_from_vl(sve_get_vl()) - 1; -} - void __init sve_setup(void) { struct vl_info *info = &vl_info[ARM64_VEC_SVE]; - u64 zcr; DECLARE_BITMAP(tmp_map, SVE_VQ_MAX); unsigned long b; + int max_bit; - if (!system_supports_sve()) + if (!cpus_have_cap(ARM64_SVE)) return; /* @@ -1208,17 +1184,8 @@ void __init sve_setup(void) if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map))) set_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map); - zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1); - info->max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1); - - /* - * Sanity-check that the max VL we determined through CPU features - * corresponds properly to sve_vq_map. If not, do our best: - */ - if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SVE, - info->max_vl))) - info->max_vl = find_supported_vector_length(ARM64_VEC_SVE, - info->max_vl); + max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX); + info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit)); /* * For the default VL, pick the maximum supported value <= 64. @@ -1296,7 +1263,7 @@ static void sme_free(struct task_struct *task) task->thread.sme_state = NULL; } -void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +void cpu_enable_sme(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, @@ -1311,80 +1278,48 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) isb(); } -/* - * This must be called after sme_kernel_enable(), we rely on the - * feature table being sorted to ensure this. - */ -void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +void cpu_enable_sme2(const struct arm64_cpu_capabilities *__always_unused p) { + /* This must be enabled after SME */ + BUILD_BUG_ON(ARM64_SME2 <= ARM64_SME); + /* Allow use of ZT0 */ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK, SYS_SMCR_EL1); } -/* - * 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) +void cpu_enable_fa64(const struct arm64_cpu_capabilities *__always_unused p) { + /* This must be enabled after SME */ + BUILD_BUG_ON(ARM64_SME_FA64 <= ARM64_SME); + /* 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) -{ - sme_kernel_enable(NULL); - - /* - * Set the maximum possible VL. - */ - write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK, - SYS_SMCR_EL1); - - /* Return LEN value that would be written to get the maximum VL */ - return sve_vq_from_vl(sme_get_vl()) - 1; -} - void __init sme_setup(void) { struct vl_info *info = &vl_info[ARM64_VEC_SME]; - u64 smcr; - int min_bit; + int min_bit, max_bit; - if (!system_supports_sme()) + if (!cpus_have_cap(ARM64_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. + * let's double check here. The bitmap is SVE_VQ_MAP sized for + * sharing with SVE. */ 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); + max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX); + info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit)); WARN_ON(info->min_vl > info->max_vl); @@ -1529,8 +1464,17 @@ void do_sme_acc(unsigned long 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); + /* Even if we chose not to use FPSIMD, the hardware could still trap: */ + if (!system_supports_fpsimd()) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); + return; + } + + /* + * When FPSIMD is enabled, we should never take a trap unless something + * has gone very wrong. + */ + BUG(); } /* @@ -1771,13 +1715,23 @@ void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state) void fpsimd_restore_current_state(void) { /* - * For the tasks that were created before we detected the absence of - * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(), - * e.g, init. This could be then inherited by the children processes. - * If we later detect that the system doesn't support FP/SIMD, - * we must clear the flag for all the tasks to indicate that the - * FPSTATE is clean (as we can't have one) to avoid looping for ever in - * do_notify_resume(). + * TIF_FOREIGN_FPSTATE is set on the init task and copied by + * arch_dup_task_struct() regardless of whether FP/SIMD is detected. + * Thus user threads can have this set even when FP/SIMD hasn't been + * detected. + * + * When FP/SIMD is detected, begin_new_exec() will set + * TIF_FOREIGN_FPSTATE via flush_thread() -> fpsimd_flush_thread(), + * and fpsimd_thread_switch() will set TIF_FOREIGN_FPSTATE when + * switching tasks. We detect FP/SIMD before we exec the first user + * process, ensuring this has TIF_FOREIGN_FPSTATE set and + * do_notify_resume() will call fpsimd_restore_current_state() to + * install the user FP/SIMD context. + * + * When FP/SIMD is not detected, nothing else will clear or set + * TIF_FOREIGN_FPSTATE prior to the first return to userspace, and + * we must clear TIF_FOREIGN_FPSTATE to avoid do_notify_resume() + * looping forever calling fpsimd_restore_current_state(). */ if (!system_supports_fpsimd()) { clear_thread_flag(TIF_FOREIGN_FPSTATE); @@ -2110,6 +2064,13 @@ static inline void fpsimd_hotplug_init(void) static inline void fpsimd_hotplug_init(void) { } #endif +void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__always_unused p) +{ + unsigned long enable = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN; + write_sysreg(read_sysreg(CPACR_EL1) | enable, CPACR_EL1); + isb(); +} + /* * FP/SIMD support code initialisation. */ diff --git a/arch/arm64/kernel/idle.c b/arch/arm64/kernel/idle.c index c112575..05cfb34 100644 --- a/arch/arm64/kernel/idle.c +++ b/arch/arm64/kernel/idle.c @@ -20,7 +20,7 @@ * ensure that interrupts are not masked at the PMR (because the core will * not wake up if we block the wake up signal in the interrupt controller). */ -void noinstr cpu_do_idle(void) +void __cpuidle cpu_do_idle(void) { struct arm_cpuidle_irq_context context; @@ -35,7 +35,7 @@ void noinstr cpu_do_idle(void) /* * This is our default idle handler. */ -void noinstr arch_cpu_idle(void) +void __cpuidle arch_cpu_idle(void) { /* * This should do all the clock switching and wait for interrupt diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index bd69a4e..bde3297 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -167,9 +167,6 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, switch (ELF64_R_TYPE(rela[i].r_info)) { case R_AARCH64_JUMP26: case R_AARCH64_CALL26: - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - break; - /* * We only have to consider branch targets that resolve * to symbols that are defined in a different section. @@ -203,8 +200,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, break; case R_AARCH64_ADR_PREL_PG_HI21_NC: case R_AARCH64_ADR_PREL_PG_HI21: - if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) || - !cpus_have_const_cap(ARM64_WORKAROUND_843419)) + if (!cpus_have_final_cap(ARM64_WORKAROUND_843419)) break; /* @@ -239,13 +235,13 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, } } - if (IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) && - cpus_have_const_cap(ARM64_WORKAROUND_843419)) + if (cpus_have_final_cap(ARM64_WORKAROUND_843419)) { /* * Add some slack so we can skip PLT slots that may trigger * the erratum due to the placement of the ADRP instruction. */ ret += DIV_ROUND_UP(ret, (SZ_4K / sizeof(struct plt_entry))); + } return ret; } @@ -269,9 +265,6 @@ static int partition_branch_plt_relas(Elf64_Sym *syms, Elf64_Rela *rela, { int i = 0, j = numrels - 1; - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return 0; - while (i < j) { if (branch_rela_needs_plt(syms, &rela[i], dstidx)) i++; diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 4edecaa..2fb5e7a 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -35,10 +35,10 @@ DEFINE_STATIC_KEY_FALSE(mte_async_or_asymm_mode); EXPORT_SYMBOL_GPL(mte_async_or_asymm_mode); #endif -void mte_sync_tags(pte_t pte) +void mte_sync_tags(pte_t pte, unsigned int nr_pages) { struct page *page = pte_page(pte); - long i, nr_pages = compound_nr(page); + unsigned int i; /* if PG_mte_tagged is set, tags have already been initialised */ for (i = 0; i < nr_pages; i++, page++) { diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 0fcc4eb..657ea27 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -454,7 +454,7 @@ static void ssbs_thread_switch(struct task_struct *next) * If all CPUs implement the SSBS extension, then we just need to * context-switch the PSTATE field. */ - if (cpus_have_const_cap(ARM64_SSBS)) + if (alternative_has_cap_unlikely(ARM64_SSBS)) return; spectre_v4_enable_task_mitigation(next); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 05f40c4..6268a13 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -972,7 +972,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) * When KPTI is in use, the vectors are switched when exiting to * user-space. */ - if (arm64_kernel_unmapped_at_el0()) + if (cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0)) return; write_sysreg(v, vbar_el1); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 196533c..be95b52 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -32,7 +32,9 @@ #include #include #include +#include #include +#include #include #include @@ -72,13 +74,19 @@ enum ipi_msg_type { IPI_CPU_CRASH_STOP, IPI_TIMER, IPI_IRQ_WORK, - IPI_WAKEUP, - NR_IPI + NR_IPI, + /* + * Any enum >= NR_IPI and < MAX_IPI is special and not tracable + * with trace_ipi_* + */ + IPI_CPU_BACKTRACE = NR_IPI, + IPI_KGDB_ROUNDUP, + MAX_IPI }; -static int ipi_irq_base __read_mostly; -static int nr_ipi __read_mostly = NR_IPI; -static struct irq_desc *ipi_desc[NR_IPI] __read_mostly; +static int ipi_irq_base __ro_after_init; +static int nr_ipi __ro_after_init = NR_IPI; +static struct irq_desc *ipi_desc[MAX_IPI] __ro_after_init; static void ipi_setup(int cpu); @@ -431,9 +439,10 @@ static void __init hyp_mode_check(void) void __init smp_cpus_done(unsigned int max_cpus) { pr_info("SMP: Total of %d processors activated.\n", num_online_cpus()); - setup_cpu_features(); + setup_system_features(); hyp_mode_check(); apply_alternatives_all(); + setup_user_features(); mark_linear_text_alias_ro(); } @@ -520,7 +529,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) { u64 hwid = processor->arm_mpidr; - if (!(processor->flags & ACPI_MADT_ENABLED)) { + if (!acpi_gicc_is_usable(processor)) { pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid); return; } @@ -764,7 +773,6 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", [IPI_TIMER] = "Timer broadcast interrupts", [IPI_IRQ_WORK] = "IRQ work interrupts", - [IPI_WAKEUP] = "CPU wake-up interrupts", }; static void smp_cross_call(const struct cpumask *target, unsigned int ipinr); @@ -797,13 +805,6 @@ void arch_send_call_function_single_ipi(int cpu) smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC); } -#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL -void arch_send_wakeup_ipi_mask(const struct cpumask *mask) -{ - smp_cross_call(mask, IPI_WAKEUP); -} -#endif - #ifdef CONFIG_IRQ_WORK void arch_irq_work_raise(void) { @@ -854,6 +855,38 @@ static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs #endif } +static void arm64_backtrace_ipi(cpumask_t *mask) +{ + __ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask); +} + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu) +{ + /* + * NOTE: though nmi_trigger_cpumask_backtrace() has "nmi_" in the name, + * nothing about it truly needs to be implemented using an NMI, it's + * just that it's _allowed_ to work with NMIs. If ipi_should_be_nmi() + * returned false our backtrace attempt will just use a regular IPI. + */ + nmi_trigger_cpumask_backtrace(mask, exclude_cpu, arm64_backtrace_ipi); +} + +#ifdef CONFIG_KGDB +void kgdb_roundup_cpus(void) +{ + int this_cpu = raw_smp_processor_id(); + int cpu; + + for_each_online_cpu(cpu) { + /* No need to roundup ourselves */ + if (cpu == this_cpu) + continue; + + __ipi_send_single(ipi_desc[IPI_KGDB_ROUNDUP], cpu); + } +} +#endif + /* * Main handler for inter-processor interrupts */ @@ -897,13 +930,17 @@ static void do_handle_IPI(int ipinr) break; #endif -#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL - case IPI_WAKEUP: - WARN_ONCE(!acpi_parking_protocol_valid(cpu), - "CPU%u: Wake-up IPI outside the ACPI parking protocol\n", - cpu); + case IPI_CPU_BACKTRACE: + /* + * NOTE: in some cases this _won't_ be NMI context. See the + * comment in arch_trigger_cpumask_backtrace(). + */ + nmi_cpu_backtrace(get_irq_regs()); + break; + + case IPI_KGDB_ROUNDUP: + kgdb_nmicallback(cpu, get_irq_regs()); break; -#endif default: pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); @@ -926,6 +963,25 @@ static void smp_cross_call(const struct cpumask *target, unsigned int ipinr) __ipi_send_mask(ipi_desc[ipinr], target); } +static bool ipi_should_be_nmi(enum ipi_msg_type ipi) +{ + DECLARE_STATIC_KEY_FALSE(supports_pseudo_nmis); + + if (!system_uses_irq_prio_masking() || + !static_branch_likely(&supports_pseudo_nmis)) + return false; + + switch (ipi) { + case IPI_CPU_STOP: + case IPI_CPU_CRASH_STOP: + case IPI_CPU_BACKTRACE: + case IPI_KGDB_ROUNDUP: + return true; + default: + return false; + } +} + static void ipi_setup(int cpu) { int i; @@ -933,8 +989,14 @@ static void ipi_setup(int cpu) if (WARN_ON_ONCE(!ipi_irq_base)) return; - for (i = 0; i < nr_ipi; i++) - enable_percpu_irq(ipi_irq_base + i, 0); + for (i = 0; i < nr_ipi; i++) { + if (ipi_should_be_nmi(i)) { + prepare_percpu_nmi(ipi_irq_base + i); + enable_percpu_nmi(ipi_irq_base + i, 0); + } else { + enable_percpu_irq(ipi_irq_base + i, 0); + } + } } #ifdef CONFIG_HOTPLUG_CPU @@ -945,8 +1007,14 @@ static void ipi_teardown(int cpu) if (WARN_ON_ONCE(!ipi_irq_base)) return; - for (i = 0; i < nr_ipi; i++) - disable_percpu_irq(ipi_irq_base + i); + for (i = 0; i < nr_ipi; i++) { + if (ipi_should_be_nmi(i)) { + disable_percpu_nmi(ipi_irq_base + i); + teardown_percpu_nmi(ipi_irq_base + i); + } else { + disable_percpu_irq(ipi_irq_base + i); + } + } } #endif @@ -954,15 +1022,23 @@ void __init set_smp_ipi_range(int ipi_base, int n) { int i; - WARN_ON(n < NR_IPI); - nr_ipi = min(n, NR_IPI); + WARN_ON(n < MAX_IPI); + nr_ipi = min(n, MAX_IPI); for (i = 0; i < nr_ipi; i++) { int err; - err = request_percpu_irq(ipi_base + i, ipi_handler, - "IPI", &cpu_number); - WARN_ON(err); + if (ipi_should_be_nmi(i)) { + err = request_percpu_nmi(ipi_base + i, ipi_handler, + "IPI", &cpu_number); + WARN(err, "Could not request IPI %d as NMI, err=%d\n", + i, err); + } else { + err = request_percpu_irq(ipi_base + i, ipi_handler, + "IPI", &cpu_number); + WARN(err, "Could not request IPI %d as IRQ, err=%d\n", + i, err); + } ipi_desc[i] = irq_to_desc(ipi_base + i); irq_set_status_flags(ipi_base + i, IRQ_HIDDEN); @@ -979,6 +1055,17 @@ void arch_smp_send_reschedule(int cpu) smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); } +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL +void arch_send_wakeup_ipi(unsigned int cpu) +{ + /* + * We use a scheduler IPI to wake the CPU as this avoids the need for a + * dedicated IPI and we can safely handle spurious scheduler IPIs. + */ + smp_send_reschedule(cpu); +} +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST void tick_broadcast(const struct cpumask *mask) { diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 0fbdf5f..eca4d04 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -55,13 +55,13 @@ void notrace __cpu_suspend_exit(void) /* Restore CnP bit in TTBR1_EL1 */ if (system_supports_cnp()) - cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir); + cpu_enable_swapper_cnp(); /* * PSTATE was not saved over suspend/resume, re-enable any detected * features that might not have been set correctly. */ - if (cpus_have_const_cap(ARM64_HAS_DIT)) + if (alternative_has_cap_unlikely(ARM64_HAS_DIT)) set_pstate_dit(1); __uaccess_enable_hw_pan(); @@ -98,6 +98,15 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) struct sleep_stack_data state; struct arm_cpuidle_irq_context context; + /* + * Some portions of CPU state (e.g. PSTATE.{PAN,DIT}) are initialized + * before alternatives are patched, but are only restored by + * __cpu_suspend_exit() after alternatives are patched. To avoid + * accidentally losing these bits we must not attempt to suspend until + * after alternatives have been patched. + */ + WARN_ON(!system_capabilities_finalized()); + /* Report any MTE async fault before going to suspend */ mte_suspend_enter(); diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index df14336..4a609e9 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -31,7 +31,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end) if (fatal_signal_pending(current)) return 0; - if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_1542419)) { /* * The workaround requires an inner-shareable tlbi. * We pick the reserved-ASID to minimise the impact. diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 8b70759..9eba6cd 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -631,7 +631,7 @@ 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); - if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_1542419)) { /* Hide DIC so that we can trap the unnecessary maintenance...*/ val &= ~BIT(CTR_EL0_DIC_SHIFT); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index d9e1355..5562daf 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -212,7 +212,7 @@ static int __setup_additional_pages(enum vdso_abi abi, if (IS_ERR(ret)) goto up_fail; - if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti()) + if (system_supports_bti_kernel()) gp_flags = VM_ARM64_BTI; vdso_base += VVAR_NR_PAGES * PAGE_SIZE; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 4866b3f..4ea6c22 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -284,7 +284,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_arm_pvtime_supported(); break; case KVM_CAP_ARM_EL1_32BIT: - r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1); + r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1); break; case KVM_CAP_GUEST_DEBUG_HW_BPS: r = get_num_brps(); @@ -296,7 +296,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_arm_support_pmu_v3(); break; case KVM_CAP_ARM_INJECT_SERROR_ESR: - r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN); + r = cpus_have_final_cap(ARM64_HAS_RAS_EXTN); break; case KVM_CAP_ARM_VM_IPA_SIZE: r = get_kvm_ipa_limit(); @@ -1207,7 +1207,7 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu, if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features)) return 0; - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) + if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1)) return -EINVAL; /* MTE is incompatible with AArch32 */ @@ -1777,7 +1777,7 @@ static void hyp_install_host_vector(void) * Call initialization code, and switch to the full blown HYP code. * If the cpucaps haven't been finalized yet, something has gone very * wrong, and hyp will crash and burn when it uses any - * cpus_have_const_cap() wrapper. + * cpus_have_*_cap() wrapper. */ BUG_ON(!system_capabilities_finalized()); params = this_cpu_ptr_nvhe_sym(kvm_init_params); @@ -2310,7 +2310,7 @@ static int __init init_hyp_mode(void) if (is_protected_kvm_enabled()) { if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && - cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH)) + cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH)) pkvm_hyp_init_ptrauth(); init_cpu_logical_map(); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 95f6945..aaf1d49 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -815,7 +815,7 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { events->exception.serror_pending = !!(vcpu->arch.hcr_el2 & HCR_VSE); - events->exception.serror_has_esr = cpus_have_const_cap(ARM64_HAS_RAS_EXTN); + events->exception.serror_has_esr = cpus_have_final_cap(ARM64_HAS_RAS_EXTN); if (events->exception.serror_pending && events->exception.serror_has_esr) events->exception.serror_esr = vcpu_get_vsesr(vcpu); @@ -837,7 +837,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, bool ext_dabt_pending = events->exception.ext_dabt_pending; if (serror_pending && has_esr) { - if (!cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) + if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) return -EINVAL; if (!((events->exception.serror_esr) & ~ESR_ELx_ISS_MASK)) @@ -874,7 +874,7 @@ u32 __attribute_const__ kvm_target_cpu(void) break; case ARM_CPU_IMP_APM: switch (part_number) { - case APM_CPU_PART_POTENZA: + case APM_CPU_PART_XGENE: return KVM_ARM_TARGET_XGENE_POTENZA; } break; diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index f155b8c..77fb330 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -401,7 +401,7 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) if (device) return -EINVAL; - if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti()) + if (system_supports_bti_kernel()) attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP; } else { attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN; @@ -664,7 +664,7 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) static bool stage2_has_fwb(struct kvm_pgtable *pgt) { - if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) + if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) return false; return !(pgt->flags & KVM_PGTABLE_S2_NOFWB); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 482280f..e6061fd 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1578,7 +1578,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (device) prot |= KVM_PGTABLE_PROT_DEVICE; - else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) + else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC)) prot |= KVM_PGTABLE_PROT_X; /* diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 0afd613..b78017e 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -207,7 +207,7 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, * CPU left in the system, and certainly not from non-secure * software). */ - if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) + if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) kvm_set_way_flush(vcpu); return true; diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 3dfc8b8..9465d37 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -684,7 +684,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info) if (kvm_vgic_global_state.vcpu_base == 0) kvm_info("disabling GICv2 emulation\n"); - if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_30115)) { + if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_30115)) { group0_trap = true; group1_trap = true; } diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c index 5b78901..cb2062e 100644 --- a/arch/arm64/lib/delay.c +++ b/arch/arm64/lib/delay.c @@ -27,7 +27,7 @@ void __delay(unsigned long cycles) { cycles_t start = get_cycles(); - if (cpus_have_const_cap(ARM64_HAS_WFXT)) { + if (alternative_has_cap_unlikely(ARM64_HAS_WFXT)) { u64 end = start + cycles; /* diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 2e5d1e2..460d799 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -571,7 +571,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, /* Write implies read */ vm_flags |= VM_WRITE; /* If EPAN is absent then exec implies read */ - if (!cpus_have_const_cap(ARM64_HAS_EPAN)) + if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 13fd592..f5aae34 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -544,8 +544,7 @@ bool __init arch_hugetlb_valid_size(unsigned long size) pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && - cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8a0f860..8deec68 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -493,8 +494,16 @@ void __init mem_init(void) { bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit); - if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC)) + if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) { + /* + * If no bouncing needed for ZONE_DMA, reduce the swiotlb + * buffer for kmalloc() bouncing to 1MB per 1GB of RAM. + */ + unsigned long size = + DIV_ROUND_UP(memblock_phys_mem_size(), 1024); + swiotlb_adjust_size(min(swiotlb_size_or_default(), size)); swiotlb = true; + } swiotlb_init(swiotlb, SWIOTLB_VERBOSE); diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 8f5b7ce..645fe60 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -68,7 +68,7 @@ static int __init adjust_protection_map(void) * With Enhanced PAN we can honour the execute-only permissions as * there is no PAN override with such mappings. */ - if (cpus_have_const_cap(ARM64_HAS_EPAN)) { + if (cpus_have_cap(ARM64_HAS_EPAN)) { protection_map[VM_EXEC] = PAGE_EXECONLY; protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 47781be..15f6347 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1469,8 +1469,7 @@ early_initcall(prevent_bootmem_remove_init); pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && - cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 14fdf64..f66c37a 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -405,8 +405,7 @@ SYM_FUNC_START(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh - mov x1, #3 << 20 - msr cpacr_el1, x1 // Enable FP/ASIMD + msr cpacr_el1, xzr // Reset cpacr_el1 mov x1, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x1 // access to the DCC from EL0 isb // Unmask debug exceptions now, diff --git a/arch/arm64/tools/Makefile b/arch/arm64/tools/Makefile index 07a93ab..fa2251d 100644 --- a/arch/arm64/tools/Makefile +++ b/arch/arm64/tools/Makefile @@ -3,7 +3,7 @@ gen := arch/$(ARCH)/include/generated kapi := $(gen)/asm -kapi-hdrs-y := $(kapi)/cpucaps.h $(kapi)/sysreg-defs.h +kapi-hdrs-y := $(kapi)/cpucap-defs.h $(kapi)/sysreg-defs.h targets += $(addprefix ../../../, $(kapi-hdrs-y)) @@ -17,7 +17,7 @@ quiet_cmd_gen_cpucaps = GEN $@ quiet_cmd_gen_sysreg = GEN $@ cmd_gen_sysreg = mkdir -p $(dir $@); $(AWK) -f $(real-prereqs) > $@ -$(kapi)/cpucaps.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE +$(kapi)/cpucap-defs.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE $(call if_changed,gen_cpucaps) $(kapi)/sysreg-defs.h: $(src)/gen-sysreg.awk $(src)/sysreg FORCE diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index dea3dc8..b98c382 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -27,6 +27,7 @@ HAS_ECV_CNTPOFF HAS_EPAN HAS_EVT HAS_FGT +HAS_FPSIMD HAS_GENERIC_AUTH HAS_GENERIC_AUTH_ARCH_QARMA3 HAS_GENERIC_AUTH_ARCH_QARMA5 @@ -39,7 +40,6 @@ HAS_LDAPR HAS_LSE_ATOMICS HAS_MOPS HAS_NESTED_VIRT -HAS_NO_FPSIMD HAS_NO_HW_PREFETCH HAS_PAN HAS_S1PIE diff --git a/arch/arm64/tools/gen-cpucaps.awk b/arch/arm64/tools/gen-cpucaps.awk index 8525980..2f4f61a 100755 --- a/arch/arm64/tools/gen-cpucaps.awk +++ b/arch/arm64/tools/gen-cpucaps.awk @@ -15,8 +15,8 @@ function fatal(msg) { /^#/ { next } BEGIN { - print "#ifndef __ASM_CPUCAPS_H" - print "#define __ASM_CPUCAPS_H" + print "#ifndef __ASM_CPUCAP_DEFS_H" + print "#define __ASM_CPUCAP_DEFS_H" print "" print "/* Generated file - do not edit */" cap_num = 0 @@ -31,7 +31,7 @@ BEGIN { END { printf("#define ARM64_NCAPS\t\t\t\t\t%d\n", cap_num) print "" - print "#endif /* __ASM_CPUCAPS_H */" + print "#endif /* __ASM_CPUCAP_DEFS_H */" } # Any lines not handled by previous rules are unexpected diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 76ce150..96cbeea 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1026,7 +1026,11 @@ UnsignedEnum 35:32 SHA3 0b0000 NI 0b0001 IMP EndEnum -Res0 31:24 +Res0 31:28 +UnsignedEnum 27:24 B16B16 + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 23:20 BF16 0b0000 NI 0b0001 IMP @@ -1235,6 +1239,7 @@ EndEnum UnsignedEnum 23:20 ATOMIC 0b0000 NI 0b0010 IMP + 0b0011 FEAT_LSE128 EndEnum UnsignedEnum 19:16 CRC32 0b0000 NI @@ -1305,6 +1310,7 @@ UnsignedEnum 23:20 LRCPC 0b0000 NI 0b0001 IMP 0b0010 LRCPC2 + 0b0011 LRCPC3 EndEnum UnsignedEnum 19:16 FCMA 0b0000 NI diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 7dd6dba..b203cfe 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -90,7 +90,7 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry, struct acpi_madt_generic_interrupt *gicc = container_of(entry, struct acpi_madt_generic_interrupt, header); - if (!(gicc->flags & ACPI_MADT_ENABLED)) + if (!acpi_gicc_is_usable(gicc)) return -ENODEV; /* device_declaration means Device object in DSDT, in the diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 7dd2c61..e054de9 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -836,8 +836,9 @@ static u64 __arch_timer_check_delta(void) * Note that TVAL is signed, thus has only 31 of its * 32 bits to express magnitude. */ - MIDR_ALL_VERSIONS(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, - APM_CPU_PART_POTENZA)), + MIDR_REV_RANGE(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, + APM_CPU_PART_XGENE), + APM_CPU_VAR_POTENZA, 0x0, 0xf), {}, }; @@ -917,7 +918,7 @@ static void arch_timer_evtstrm_enable(unsigned int divider) #ifdef CONFIG_ARM64 /* ECV is likely to require a large divider. Use the EVNTIS flag. */ - if (cpus_have_const_cap(ARM64_HAS_ECV) && divider > 15) { + if (cpus_have_final_cap(ARM64_HAS_ECV) && divider > 15) { cntkctl |= ARCH_TIMER_EVT_INTERVAL_SCALE; divider -= 8; } @@ -955,6 +956,30 @@ static void arch_timer_configure_evtstream(void) arch_timer_evtstrm_enable(max(0, lsb)); } +static int arch_timer_evtstrm_starting_cpu(unsigned int cpu) +{ + arch_timer_configure_evtstream(); + return 0; +} + +static int arch_timer_evtstrm_dying_cpu(unsigned int cpu) +{ + cpumask_clear_cpu(smp_processor_id(), &evtstrm_available); + return 0; +} + +static int __init arch_timer_evtstrm_register(void) +{ + if (!arch_timer_evt || !evtstrm_enable) + return 0; + + return cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_EVTSTRM_STARTING, + "clockevents/arm/arch_timer_evtstrm:starting", + arch_timer_evtstrm_starting_cpu, + arch_timer_evtstrm_dying_cpu); +} +core_initcall(arch_timer_evtstrm_register); + static void arch_counter_set_user_access(void) { u32 cntkctl = arch_timer_get_cntkctl(); @@ -1016,8 +1041,6 @@ static int arch_timer_starting_cpu(unsigned int cpu) } arch_counter_set_user_access(); - if (evtstrm_enable) - arch_timer_configure_evtstream(); return 0; } @@ -1164,8 +1187,6 @@ static int arch_timer_dying_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); - cpumask_clear_cpu(smp_processor_id(), &evtstrm_available); - arch_timer_stop(clk); return 0; } @@ -1279,6 +1300,7 @@ out_unreg_notify: out_free: free_percpu(arch_timer_evt); + arch_timer_evt = NULL; out: return err; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index f59ac95..68d11cc 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -79,6 +79,13 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); #define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer) /* + * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs + * are potentially stolen by the secure side. Some code, especially code dealing + * with hwirq IDs, is simplified by accounting for all 16. + */ +#define SGI_NR 16 + +/* * The behaviours of RPR and PMR registers differ depending on the value of * SCR_EL3.FIQ, and the behaviour of non-secure priority registers of the * distributor and redistributors depends on whether security is enabled in the @@ -99,7 +106,7 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); * - Figure 4-7 Secure read of the priority field for a Non-secure Group 1 * interrupt. */ -static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); +DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities); EXPORT_SYMBOL(gic_nonsecure_priorities); @@ -125,8 +132,8 @@ EXPORT_SYMBOL(gic_nonsecure_priorities); __priority; \ }) -/* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */ -static refcount_t *ppi_nmi_refs; +/* rdist_nmi_refs[n] == number of cpus having the rdist interrupt n set as NMI */ +static refcount_t *rdist_nmi_refs; static struct gic_kvm_info gic_v3_kvm_info __initdata; static DEFINE_PER_CPU(bool, has_rss); @@ -270,17 +277,6 @@ static void gic_redist_wait_for_rwp(void) gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } -#ifdef CONFIG_ARM64 - -static u64 __maybe_unused gic_read_iar(void) -{ - if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_23154)) - return gic_read_iar_cavium_thunderx(); - else - return gic_read_iar_common(); -} -#endif - static void gic_enable_redist(bool enable) { void __iomem *rbase; @@ -519,9 +515,22 @@ static u32 __gic_get_ppi_index(irq_hw_number_t hwirq) } } -static u32 gic_get_ppi_index(struct irq_data *d) +static u32 __gic_get_rdist_index(irq_hw_number_t hwirq) +{ + switch (__get_intid_range(hwirq)) { + case SGI_RANGE: + case PPI_RANGE: + return hwirq; + case EPPI_RANGE: + return hwirq - EPPI_BASE_INTID + 32; + default: + unreachable(); + } +} + +static u32 gic_get_rdist_index(struct irq_data *d) { - return __gic_get_ppi_index(d->hwirq); + return __gic_get_rdist_index(d->hwirq); } static int gic_irq_nmi_setup(struct irq_data *d) @@ -545,11 +554,14 @@ static int gic_irq_nmi_setup(struct irq_data *d) /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { - u32 idx = gic_get_ppi_index(d); + u32 idx = gic_get_rdist_index(d); - /* Setting up PPI as NMI, only switch handler for first NMI */ - if (!refcount_inc_not_zero(&ppi_nmi_refs[idx])) { - refcount_set(&ppi_nmi_refs[idx], 1); + /* + * Setting up a percpu interrupt as NMI, only switch handler + * for first NMI + */ + if (!refcount_inc_not_zero(&rdist_nmi_refs[idx])) { + refcount_set(&rdist_nmi_refs[idx], 1); desc->handle_irq = handle_percpu_devid_fasteoi_nmi; } } else { @@ -582,10 +594,10 @@ static void gic_irq_nmi_teardown(struct irq_data *d) /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { - u32 idx = gic_get_ppi_index(d); + u32 idx = gic_get_rdist_index(d); /* Tearing down NMI, only switch handler for last NMI */ - if (refcount_dec_and_test(&ppi_nmi_refs[idx])) + if (refcount_dec_and_test(&rdist_nmi_refs[idx])) desc->handle_irq = handle_percpu_devid_irq; } else { desc->handle_irq = handle_fasteoi_irq; @@ -1279,10 +1291,10 @@ static void gic_cpu_init(void) rbase = gic_data_rdist_sgi_base(); /* Configure SGIs/PPIs as non-secure Group-1 */ - for (i = 0; i < gic_data.ppi_nr + 16; i += 32) + for (i = 0; i < gic_data.ppi_nr + SGI_NR; i += 32) writel_relaxed(~0, rbase + GICR_IGROUPR0 + i / 8); - gic_cpu_config(rbase, gic_data.ppi_nr + 16, gic_redist_wait_for_rwp); + gic_cpu_config(rbase, gic_data.ppi_nr + SGI_NR, gic_redist_wait_for_rwp); /* initialise system registers */ gic_cpu_sys_reg_init(); @@ -1952,12 +1964,13 @@ static void gic_enable_nmi_support(void) return; } - ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL); - if (!ppi_nmi_refs) + rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR, + sizeof(*rdist_nmi_refs), GFP_KERNEL); + if (!rdist_nmi_refs) return; - for (i = 0; i < gic_data.ppi_nr; i++) - refcount_set(&ppi_nmi_refs[i], 0); + for (i = 0; i < gic_data.ppi_nr + SGI_NR; i++) + refcount_set(&rdist_nmi_refs[i], 0); pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n", gic_has_relaxed_pmr_sync() ? "relaxed" : "forced"); @@ -2074,6 +2087,7 @@ static int __init gic_init_bases(phys_addr_t dist_phys_base, gic_dist_init(); gic_cpu_init(); + gic_enable_nmi_support(); gic_smp_init(); gic_cpu_pm_init(); @@ -2086,8 +2100,6 @@ static int __init gic_init_bases(phys_addr_t dist_phys_base, gicv2m_init(handle, gic_data.domain); } - gic_enable_nmi_support(); - return 0; out_free: @@ -2380,8 +2392,7 @@ gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2; void __iomem *redist_base; - /* GICC entry which has !ACPI_MADT_ENABLED is not unusable so skip */ - if (!(gicc->flags & ACPI_MADT_ENABLED)) + if (!acpi_gicc_is_usable(gicc)) return 0; redist_base = ioremap(gicc->gicr_base_address, size); @@ -2431,7 +2442,7 @@ static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header, * If GICC is enabled and has valid gicr base address, then it means * GICR base is presented via GICC */ - if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) { + if (acpi_gicc_is_usable(gicc) && gicc->gicr_base_address) { acpi_data.enabled_rdists++; return 0; } @@ -2440,7 +2451,7 @@ static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header, * It's perfectly valid firmware can pass disabled GICC entry, driver * should not treat as errors, skip the entry instead of probe fail. */ - if (!(gicc->flags & ACPI_MADT_ENABLED)) + if (!acpi_gicc_is_usable(gicc)) return 0; return -ENODEV; @@ -2499,8 +2510,7 @@ static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *hea int maint_irq_mode; static int first_madt = true; - /* Skip unusable CPUs */ - if (!(gicc->flags & ACPI_MADT_ENABLED)) + if (!acpi_gicc_is_usable(gicc)) return 0; maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ? diff --git a/drivers/perf/amlogic/meson_g12_ddr_pmu.c b/drivers/perf/amlogic/meson_g12_ddr_pmu.c index 8b64388..15d52ab 100644 --- a/drivers/perf/amlogic/meson_g12_ddr_pmu.c +++ b/drivers/perf/amlogic/meson_g12_ddr_pmu.c @@ -377,6 +377,7 @@ static const struct of_device_id meson_ddr_pmu_dt_match[] = { }, {} }; +MODULE_DEVICE_TABLE(of, meson_ddr_pmu_dt_match); static struct platform_driver g12_ddr_pmu_driver = { .probe = g12_ddr_pmu_probe, diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 6b50bc5..014010d 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -112,7 +112,9 @@ #define CMN_DTM_PMEVCNTSR 0x240 -#define CMN_DTM_UNIT_INFO 0x0910 +#define CMN650_DTM_UNIT_INFO 0x0910 +#define CMN_DTM_UNIT_INFO 0x0960 +#define CMN_DTM_UNIT_INFO_DTC_DOMAIN GENMASK_ULL(1, 0) #define CMN_DTM_NUM_COUNTERS 4 /* Want more local counters? Why not replicate the whole DTM! Ugh... */ @@ -279,16 +281,13 @@ struct arm_cmn_node { u16 id, logid; enum cmn_node_type type; - int dtm; - union { - /* DN/HN-F/CXHA */ - struct { - u8 val : 4; - u8 count : 4; - } occupid[SEL_MAX]; - /* XP */ - u8 dtc; - }; + u8 dtm; + s8 dtc; + /* DN/HN-F/CXHA */ + struct { + u8 val : 4; + u8 count : 4; + } occupid[SEL_MAX]; union { u8 event[4]; __le32 event_sel; @@ -538,12 +537,12 @@ static int arm_cmn_map_show(struct seq_file *s, void *data) seq_puts(s, "\n |"); for (x = 0; x < cmn->mesh_x; x++) { - u8 dtc = cmn->xps[xp_base + x].dtc; + s8 dtc = cmn->xps[xp_base + x].dtc; - if (dtc & (dtc - 1)) + if (dtc < 0) seq_puts(s, " DTC ?? |"); else - seq_printf(s, " DTC %ld |", __ffs(dtc)); + seq_printf(s, " DTC %d |", dtc); } seq_puts(s, "\n |"); for (x = 0; x < cmn->mesh_x; x++) @@ -587,8 +586,7 @@ static void arm_cmn_debugfs_init(struct arm_cmn *cmn, int id) {} struct arm_cmn_hw_event { struct arm_cmn_node *dn; u64 dtm_idx[4]; - unsigned int dtc_idx; - u8 dtcs_used; + s8 dtc_idx[CMN_MAX_DTCS]; u8 num_dns; u8 dtm_offset; bool wide_sel; @@ -598,6 +596,10 @@ struct arm_cmn_hw_event { #define for_each_hw_dn(hw, dn, i) \ for (i = 0, dn = hw->dn; i < hw->num_dns; i++, dn++) +/* @i is the DTC number, @idx is the counter index on that DTC */ +#define for_each_hw_dtc_idx(hw, i, idx) \ + for (int i = 0, idx; i < CMN_MAX_DTCS; i++) if ((idx = hw->dtc_idx[i]) >= 0) + static struct arm_cmn_hw_event *to_cmn_hw(struct perf_event *event) { BUILD_BUG_ON(sizeof(struct arm_cmn_hw_event) > offsetof(struct hw_perf_event, target)); @@ -1427,12 +1429,11 @@ static void arm_cmn_init_counter(struct perf_event *event) { struct arm_cmn *cmn = to_cmn(event->pmu); struct arm_cmn_hw_event *hw = to_cmn_hw(event); - unsigned int i, pmevcnt = CMN_DT_PMEVCNT(hw->dtc_idx); u64 count; - for (i = 0; hw->dtcs_used & (1U << i); i++) { - writel_relaxed(CMN_COUNTER_INIT, cmn->dtc[i].base + pmevcnt); - cmn->dtc[i].counters[hw->dtc_idx] = event; + for_each_hw_dtc_idx(hw, i, idx) { + writel_relaxed(CMN_COUNTER_INIT, cmn->dtc[i].base + CMN_DT_PMEVCNT(idx)); + cmn->dtc[i].counters[idx] = event; } count = arm_cmn_read_dtm(cmn, hw, false); @@ -1445,11 +1446,9 @@ static void arm_cmn_event_read(struct perf_event *event) struct arm_cmn_hw_event *hw = to_cmn_hw(event); u64 delta, new, prev; unsigned long flags; - unsigned int i; - if (hw->dtc_idx == CMN_DT_NUM_COUNTERS) { - i = __ffs(hw->dtcs_used); - delta = arm_cmn_read_cc(cmn->dtc + i); + if (CMN_EVENT_TYPE(event) == CMN_TYPE_DTC) { + delta = arm_cmn_read_cc(cmn->dtc + hw->dtc_idx[0]); local64_add(delta, &event->count); return; } @@ -1459,8 +1458,8 @@ static void arm_cmn_event_read(struct perf_event *event) delta = new - prev; local_irq_save(flags); - for (i = 0; hw->dtcs_used & (1U << i); i++) { - new = arm_cmn_read_counter(cmn->dtc + i, hw->dtc_idx); + for_each_hw_dtc_idx(hw, i, idx) { + new = arm_cmn_read_counter(cmn->dtc + i, idx); delta += new << 16; } local_irq_restore(flags); @@ -1516,7 +1515,7 @@ static void arm_cmn_event_start(struct perf_event *event, int flags) int i; if (type == CMN_TYPE_DTC) { - i = __ffs(hw->dtcs_used); + i = hw->dtc_idx[0]; writeq_relaxed(CMN_CC_INIT, cmn->dtc[i].base + CMN_DT_PMCCNTR); cmn->dtc[i].cc_active = true; } else if (type == CMN_TYPE_WP) { @@ -1547,7 +1546,7 @@ static void arm_cmn_event_stop(struct perf_event *event, int flags) int i; if (type == CMN_TYPE_DTC) { - i = __ffs(hw->dtcs_used); + i = hw->dtc_idx[0]; cmn->dtc[i].cc_active = false; } else if (type == CMN_TYPE_WP) { int wp_idx = arm_cmn_wp_idx(event); @@ -1571,7 +1570,7 @@ struct arm_cmn_val { u8 dtm_count[CMN_MAX_DTMS]; u8 occupid[CMN_MAX_DTMS][SEL_MAX]; u8 wp[CMN_MAX_DTMS][4]; - int dtc_count; + int dtc_count[CMN_MAX_DTCS]; bool cycles; }; @@ -1592,7 +1591,8 @@ static void arm_cmn_val_add_event(struct arm_cmn *cmn, struct arm_cmn_val *val, return; } - val->dtc_count++; + for_each_hw_dtc_idx(hw, dtc, idx) + val->dtc_count[dtc]++; for_each_hw_dn(hw, dn, i) { int wp_idx, dtm = dn->dtm, sel = hw->filter_sel; @@ -1639,8 +1639,9 @@ static int arm_cmn_validate_group(struct arm_cmn *cmn, struct perf_event *event) goto done; } - if (val->dtc_count == CMN_DT_NUM_COUNTERS) - goto done; + for (i = 0; i < CMN_MAX_DTCS; i++) + if (val->dtc_count[i] == CMN_DT_NUM_COUNTERS) + goto done; for_each_hw_dn(hw, dn, i) { int wp_idx, wp_cmb, dtm = dn->dtm, sel = hw->filter_sel; @@ -1733,12 +1734,19 @@ static int arm_cmn_event_init(struct perf_event *event) hw->dn = arm_cmn_node(cmn, type); if (!hw->dn) return -EINVAL; + + memset(hw->dtc_idx, -1, sizeof(hw->dtc_idx)); for (dn = hw->dn; dn->type == type; dn++) { if (bynodeid && dn->id != nodeid) { hw->dn++; continue; } hw->num_dns++; + if (dn->dtc < 0) + memset(hw->dtc_idx, 0, cmn->num_dtcs); + else + hw->dtc_idx[dn->dtc] = 0; + if (bynodeid) break; } @@ -1750,12 +1758,6 @@ static int arm_cmn_event_init(struct perf_event *event) nodeid, nid.x, nid.y, nid.port, nid.dev, type); return -EINVAL; } - /* - * Keep assuming non-cycles events count in all DTC domains; turns out - * it's hard to make a worthwhile optimisation around this, short of - * going all-in with domain-local counter allocation as well. - */ - hw->dtcs_used = (1U << cmn->num_dtcs) - 1; return arm_cmn_validate_group(cmn, event); } @@ -1781,46 +1783,48 @@ static void arm_cmn_event_clear(struct arm_cmn *cmn, struct perf_event *event, } memset(hw->dtm_idx, 0, sizeof(hw->dtm_idx)); - for (i = 0; hw->dtcs_used & (1U << i); i++) - cmn->dtc[i].counters[hw->dtc_idx] = NULL; + for_each_hw_dtc_idx(hw, j, idx) + cmn->dtc[j].counters[idx] = NULL; } static int arm_cmn_event_add(struct perf_event *event, int flags) { struct arm_cmn *cmn = to_cmn(event->pmu); struct arm_cmn_hw_event *hw = to_cmn_hw(event); - struct arm_cmn_dtc *dtc = &cmn->dtc[0]; struct arm_cmn_node *dn; enum cmn_node_type type = CMN_EVENT_TYPE(event); - unsigned int i, dtc_idx, input_sel; + unsigned int input_sel, i = 0; if (type == CMN_TYPE_DTC) { - i = 0; while (cmn->dtc[i].cycles) if (++i == cmn->num_dtcs) return -ENOSPC; cmn->dtc[i].cycles = event; - hw->dtc_idx = CMN_DT_NUM_COUNTERS; - hw->dtcs_used = 1U << i; + hw->dtc_idx[0] = i; if (flags & PERF_EF_START) arm_cmn_event_start(event, 0); return 0; } - /* Grab a free global counter first... */ - dtc_idx = 0; - while (dtc->counters[dtc_idx]) - if (++dtc_idx == CMN_DT_NUM_COUNTERS) - return -ENOSPC; - - hw->dtc_idx = dtc_idx; + /* Grab the global counters first... */ + for_each_hw_dtc_idx(hw, j, idx) { + if (cmn->part == PART_CMN600 && j > 0) { + idx = hw->dtc_idx[0]; + } else { + idx = 0; + while (cmn->dtc[j].counters[idx]) + if (++idx == CMN_DT_NUM_COUNTERS) + goto free_dtms; + } + hw->dtc_idx[j] = idx; + } - /* ...then the local counters to feed it. */ + /* ...then the local counters to feed them */ for_each_hw_dn(hw, dn, i) { struct arm_cmn_dtm *dtm = &cmn->dtms[dn->dtm] + hw->dtm_offset; - unsigned int dtm_idx, shift; + unsigned int dtm_idx, shift, d = max_t(int, dn->dtc, 0); u64 reg; dtm_idx = 0; @@ -1839,11 +1843,11 @@ static int arm_cmn_event_add(struct perf_event *event, int flags) tmp = dtm->wp_event[wp_idx ^ 1]; if (tmp >= 0 && CMN_EVENT_WP_COMBINE(event) != - CMN_EVENT_WP_COMBINE(dtc->counters[tmp])) + CMN_EVENT_WP_COMBINE(cmn->dtc[d].counters[tmp])) goto free_dtms; input_sel = CMN__PMEVCNT0_INPUT_SEL_WP + wp_idx; - dtm->wp_event[wp_idx] = dtc_idx; + dtm->wp_event[wp_idx] = hw->dtc_idx[d]; writel_relaxed(cfg, dtm->base + CMN_DTM_WPn_CONFIG(wp_idx)); } else { struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id); @@ -1863,7 +1867,7 @@ static int arm_cmn_event_add(struct perf_event *event, int flags) dtm->input_sel[dtm_idx] = input_sel; shift = CMN__PMEVCNTn_GLOBAL_NUM_SHIFT(dtm_idx); dtm->pmu_config_low &= ~(CMN__PMEVCNT0_GLOBAL_NUM << shift); - dtm->pmu_config_low |= FIELD_PREP(CMN__PMEVCNT0_GLOBAL_NUM, dtc_idx) << shift; + dtm->pmu_config_low |= FIELD_PREP(CMN__PMEVCNT0_GLOBAL_NUM, hw->dtc_idx[d]) << shift; dtm->pmu_config_low |= CMN__PMEVCNT_PAIRED(dtm_idx); reg = (u64)le32_to_cpu(dtm->pmu_config_high) << 32 | dtm->pmu_config_low; writeq_relaxed(reg, dtm->base + CMN_DTM_PMU_CONFIG); @@ -1891,7 +1895,7 @@ static void arm_cmn_event_del(struct perf_event *event, int flags) arm_cmn_event_stop(event, PERF_EF_UPDATE); if (type == CMN_TYPE_DTC) - cmn->dtc[__ffs(hw->dtcs_used)].cycles = NULL; + cmn->dtc[hw->dtc_idx[0]].cycles = NULL; else arm_cmn_event_clear(cmn, event, hw->num_dns); } @@ -2072,7 +2076,6 @@ static int arm_cmn_init_dtcs(struct arm_cmn *cmn) { struct arm_cmn_node *dn, *xp; int dtc_idx = 0; - u8 dtcs_present = (1 << cmn->num_dtcs) - 1; cmn->dtc = devm_kcalloc(cmn->dev, cmn->num_dtcs, sizeof(cmn->dtc[0]), GFP_KERNEL); if (!cmn->dtc) @@ -2082,23 +2085,26 @@ static int arm_cmn_init_dtcs(struct arm_cmn *cmn) cmn->xps = arm_cmn_node(cmn, CMN_TYPE_XP); + if (cmn->part == PART_CMN600 && cmn->num_dtcs > 1) { + /* We do at least know that a DTC's XP must be in that DTC's domain */ + dn = arm_cmn_node(cmn, CMN_TYPE_DTC); + for (int i = 0; i < cmn->num_dtcs; i++) + arm_cmn_node_to_xp(cmn, dn + i)->dtc = i; + } + for (dn = cmn->dns; dn->type; dn++) { - if (dn->type == CMN_TYPE_XP) { - dn->dtc &= dtcs_present; + if (dn->type == CMN_TYPE_XP) continue; - } xp = arm_cmn_node_to_xp(cmn, dn); + dn->dtc = xp->dtc; dn->dtm = xp->dtm; if (cmn->multi_dtm) dn->dtm += arm_cmn_nid(cmn, dn->id).port / 2; if (dn->type == CMN_TYPE_DTC) { - int err; - /* We do at least know that a DTC's XP must be in that DTC's domain */ - if (xp->dtc == 0xf) - xp->dtc = 1 << dtc_idx; - err = arm_cmn_init_dtc(cmn, dn, dtc_idx++); + int err = arm_cmn_init_dtc(cmn, dn, dtc_idx++); + if (err) return err; } @@ -2117,6 +2123,16 @@ static int arm_cmn_init_dtcs(struct arm_cmn *cmn) return 0; } +static unsigned int arm_cmn_dtc_domain(struct arm_cmn *cmn, void __iomem *xp_region) +{ + int offset = CMN_DTM_UNIT_INFO; + + if (cmn->part == PART_CMN650 || cmn->part == PART_CI700) + offset = CMN650_DTM_UNIT_INFO; + + return FIELD_GET(CMN_DTM_UNIT_INFO_DTC_DOMAIN, readl_relaxed(xp_region + offset)); +} + static void arm_cmn_init_node_info(struct arm_cmn *cmn, u32 offset, struct arm_cmn_node *node) { int level; @@ -2246,9 +2262,9 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) cmn->mesh_x = xp->logid; if (cmn->part == PART_CMN600) - xp->dtc = 0xf; + xp->dtc = -1; else - xp->dtc = 1 << readl_relaxed(xp_region + CMN_DTM_UNIT_INFO); + xp->dtc = arm_cmn_dtc_domain(cmn, xp_region); xp->dtm = dtm - cmn->dtms; arm_cmn_init_dtm(dtm++, xp, 0); diff --git a/drivers/perf/arm_cspmu/Kconfig b/drivers/perf/arm_cspmu/Kconfig index 25d25de..6f4e28f 100644 --- a/drivers/perf/arm_cspmu/Kconfig +++ b/drivers/perf/arm_cspmu/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # -# Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. config ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU tristate "ARM Coresight Architecture PMU" @@ -10,3 +10,20 @@ config ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU based on ARM CoreSight PMU architecture. Note that this PMU architecture does not have relationship with the ARM CoreSight Self-Hosted Tracing. + +config NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU + tristate "NVIDIA Coresight Architecture PMU" + depends on ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU + help + Provides NVIDIA specific attributes for performance monitoring unit + (PMU) devices based on ARM CoreSight PMU architecture. + +config AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU + tristate "Ampere Coresight Architecture PMU" + depends on ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU + help + Provides Ampere specific attributes for performance monitoring unit + (PMU) devices based on ARM CoreSight PMU architecture. + + In the first phase, the driver enables support on MCU PMU used in + AmpereOne SoC family. diff --git a/drivers/perf/arm_cspmu/Makefile b/drivers/perf/arm_cspmu/Makefile index fedb17d..220a734 100644 --- a/drivers/perf/arm_cspmu/Makefile +++ b/drivers/perf/arm_cspmu/Makefile @@ -1,6 +1,10 @@ -# Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. # # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu_module.o -arm_cspmu_module-y := arm_cspmu.o nvidia_cspmu.o + +arm_cspmu_module-y := arm_cspmu.o + +obj-$(CONFIG_NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += nvidia_cspmu.o +obj-$(CONFIG_AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += ampere_cspmu.o diff --git a/drivers/perf/arm_cspmu/ampere_cspmu.c b/drivers/perf/arm_cspmu/ampere_cspmu.c new file mode 100644 index 0000000..f146a45 --- /dev/null +++ b/drivers/perf/arm_cspmu/ampere_cspmu.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Ampere SoC PMU (Performance Monitor Unit) + * + * Copyright (c) 2023, Ampere Computing LLC + */ +#include +#include +#include + +#include "arm_cspmu.h" + +#define PMAUXR0 0xD80 +#define PMAUXR1 0xD84 +#define PMAUXR2 0xD88 +#define PMAUXR3 0xD8C + +#define to_ampere_cspmu_ctx(cspmu) ((struct ampere_cspmu_ctx *)(cspmu->impl.ctx)) + +struct ampere_cspmu_ctx { + const char *name; + struct attribute **event_attr; + struct attribute **format_attr; +}; + +static DEFINE_IDA(mcu_pmu_ida); + +#define SOC_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end) \ + static inline u32 get_##_name(const struct perf_event *event) \ + { \ + return FIELD_GET(GENMASK_ULL(_end, _start), \ + event->attr._config); \ + } \ + +SOC_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 8); +SOC_PMU_EVENT_ATTR_EXTRACTOR(threshold, config1, 0, 7); +SOC_PMU_EVENT_ATTR_EXTRACTOR(rank, config1, 8, 23); +SOC_PMU_EVENT_ATTR_EXTRACTOR(bank, config1, 24, 55); + +static struct attribute *ampereone_mcu_pmu_event_attrs[] = { + ARM_CSPMU_EVENT_ATTR(cycle_count, 0x00), + ARM_CSPMU_EVENT_ATTR(act_sent, 0x01), + ARM_CSPMU_EVENT_ATTR(pre_sent, 0x02), + ARM_CSPMU_EVENT_ATTR(rd_sent, 0x03), + ARM_CSPMU_EVENT_ATTR(rda_sent, 0x04), + ARM_CSPMU_EVENT_ATTR(wr_sent, 0x05), + ARM_CSPMU_EVENT_ATTR(wra_sent, 0x06), + ARM_CSPMU_EVENT_ATTR(pd_entry_vld, 0x07), + ARM_CSPMU_EVENT_ATTR(sref_entry_vld, 0x08), + ARM_CSPMU_EVENT_ATTR(prea_sent, 0x09), + ARM_CSPMU_EVENT_ATTR(pre_sb_sent, 0x0a), + ARM_CSPMU_EVENT_ATTR(ref_sent, 0x0b), + ARM_CSPMU_EVENT_ATTR(rfm_sent, 0x0c), + ARM_CSPMU_EVENT_ATTR(ref_sb_sent, 0x0d), + ARM_CSPMU_EVENT_ATTR(rfm_sb_sent, 0x0e), + ARM_CSPMU_EVENT_ATTR(rd_rda_sent, 0x0f), + ARM_CSPMU_EVENT_ATTR(wr_wra_sent, 0x10), + ARM_CSPMU_EVENT_ATTR(raw_hazard, 0x11), + ARM_CSPMU_EVENT_ATTR(war_hazard, 0x12), + ARM_CSPMU_EVENT_ATTR(waw_hazard, 0x13), + ARM_CSPMU_EVENT_ATTR(rar_hazard, 0x14), + ARM_CSPMU_EVENT_ATTR(raw_war_waw_hazard, 0x15), + ARM_CSPMU_EVENT_ATTR(hprd_lprd_wr_req_vld, 0x16), + ARM_CSPMU_EVENT_ATTR(lprd_req_vld, 0x17), + ARM_CSPMU_EVENT_ATTR(hprd_req_vld, 0x18), + ARM_CSPMU_EVENT_ATTR(hprd_lprd_req_vld, 0x19), + ARM_CSPMU_EVENT_ATTR(prefetch_tgt, 0x1a), + ARM_CSPMU_EVENT_ATTR(wr_req_vld, 0x1b), + ARM_CSPMU_EVENT_ATTR(partial_wr_req_vld, 0x1c), + ARM_CSPMU_EVENT_ATTR(rd_retry, 0x1d), + ARM_CSPMU_EVENT_ATTR(wr_retry, 0x1e), + ARM_CSPMU_EVENT_ATTR(retry_gnt, 0x1f), + ARM_CSPMU_EVENT_ATTR(rank_change, 0x20), + ARM_CSPMU_EVENT_ATTR(dir_change, 0x21), + ARM_CSPMU_EVENT_ATTR(rank_dir_change, 0x22), + ARM_CSPMU_EVENT_ATTR(rank_active, 0x23), + ARM_CSPMU_EVENT_ATTR(rank_idle, 0x24), + ARM_CSPMU_EVENT_ATTR(rank_pd, 0x25), + ARM_CSPMU_EVENT_ATTR(rank_sref, 0x26), + ARM_CSPMU_EVENT_ATTR(queue_fill_gt_thresh, 0x27), + ARM_CSPMU_EVENT_ATTR(queue_rds_gt_thresh, 0x28), + ARM_CSPMU_EVENT_ATTR(queue_wrs_gt_thresh, 0x29), + ARM_CSPMU_EVENT_ATTR(phy_updt_complt, 0x2a), + ARM_CSPMU_EVENT_ATTR(tz_fail, 0x2b), + ARM_CSPMU_EVENT_ATTR(dram_errc, 0x2c), + ARM_CSPMU_EVENT_ATTR(dram_errd, 0x2d), + ARM_CSPMU_EVENT_ATTR(read_data_return, 0x32), + ARM_CSPMU_EVENT_ATTR(chi_wr_data_delta, 0x33), + ARM_CSPMU_EVENT_ATTR(zq_start, 0x34), + ARM_CSPMU_EVENT_ATTR(zq_latch, 0x35), + ARM_CSPMU_EVENT_ATTR(wr_fifo_full, 0x36), + ARM_CSPMU_EVENT_ATTR(info_fifo_full, 0x37), + ARM_CSPMU_EVENT_ATTR(cmd_fifo_full, 0x38), + ARM_CSPMU_EVENT_ATTR(dfi_nop, 0x39), + ARM_CSPMU_EVENT_ATTR(dfi_cmd, 0x3a), + ARM_CSPMU_EVENT_ATTR(rd_run_len, 0x3b), + ARM_CSPMU_EVENT_ATTR(wr_run_len, 0x3c), + + ARM_CSPMU_EVENT_ATTR(cycles, ARM_CSPMU_EVT_CYCLES_DEFAULT), + NULL, +}; + +static struct attribute *ampereone_mcu_format_attrs[] = { + ARM_CSPMU_FORMAT_EVENT_ATTR, + ARM_CSPMU_FORMAT_ATTR(threshold, "config1:0-7"), + ARM_CSPMU_FORMAT_ATTR(rank, "config1:8-23"), + ARM_CSPMU_FORMAT_ATTR(bank, "config1:24-55"), + NULL, +}; + +static struct attribute ** +ampere_cspmu_get_event_attrs(const struct arm_cspmu *cspmu) +{ + const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu); + + return ctx->event_attr; +} + +static struct attribute ** +ampere_cspmu_get_format_attrs(const struct arm_cspmu *cspmu) +{ + const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu); + + return ctx->format_attr; +} + +static const char * +ampere_cspmu_get_name(const struct arm_cspmu *cspmu) +{ + const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu); + + return ctx->name; +} + +static u32 ampere_cspmu_event_filter(const struct perf_event *event) +{ + /* + * PMEVFILTR or PMCCFILTR aren't used in Ampere SoC PMU but are marked + * as RES0. Make sure, PMCCFILTR is written zero. + */ + return 0; +} + +static void ampere_cspmu_set_ev_filter(struct arm_cspmu *cspmu, + struct hw_perf_event *hwc, + u32 filter) +{ + struct perf_event *event; + unsigned int idx; + u32 threshold, rank, bank; + + /* + * At this point, all the events have the same filter settings. + * Therefore, take the first event and use its configuration. + */ + idx = find_first_bit(cspmu->hw_events.used_ctrs, + cspmu->cycle_counter_logical_idx); + + event = cspmu->hw_events.events[idx]; + + threshold = get_threshold(event); + rank = get_rank(event); + bank = get_bank(event); + + writel(threshold, cspmu->base0 + PMAUXR0); + writel(rank, cspmu->base0 + PMAUXR1); + writel(bank, cspmu->base0 + PMAUXR2); +} + +static int ampere_cspmu_validate_configs(struct perf_event *event, + struct perf_event *event2) +{ + if (get_threshold(event) != get_threshold(event2) || + get_rank(event) != get_rank(event2) || + get_bank(event) != get_bank(event2)) + return -EINVAL; + + return 0; +} + +static int ampere_cspmu_validate_event(struct arm_cspmu *cspmu, + struct perf_event *new) +{ + struct perf_event *curr, *leader = new->group_leader; + unsigned int idx; + int ret; + + ret = ampere_cspmu_validate_configs(new, leader); + if (ret) + return ret; + + /* We compare the global filter settings to the existing events */ + idx = find_first_bit(cspmu->hw_events.used_ctrs, + cspmu->cycle_counter_logical_idx); + + /* This is the first event, thus any configuration is fine */ + if (idx == cspmu->cycle_counter_logical_idx) + return 0; + + curr = cspmu->hw_events.events[idx]; + + return ampere_cspmu_validate_configs(curr, new); +} + +static char *ampere_cspmu_format_name(const struct arm_cspmu *cspmu, + const char *name_pattern) +{ + struct device *dev = cspmu->dev; + int id; + + id = ida_alloc(&mcu_pmu_ida, GFP_KERNEL); + if (id < 0) + return ERR_PTR(id); + + return devm_kasprintf(dev, GFP_KERNEL, name_pattern, id); +} + +static int ampere_cspmu_init_ops(struct arm_cspmu *cspmu) +{ + struct device *dev = cspmu->dev; + struct ampere_cspmu_ctx *ctx; + struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops; + + ctx = devm_kzalloc(dev, sizeof(struct ampere_cspmu_ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->event_attr = ampereone_mcu_pmu_event_attrs; + ctx->format_attr = ampereone_mcu_format_attrs; + ctx->name = ampere_cspmu_format_name(cspmu, "ampere_mcu_pmu_%d"); + if (IS_ERR_OR_NULL(ctx->name)) + return ctx->name ? PTR_ERR(ctx->name) : -ENOMEM; + + cspmu->impl.ctx = ctx; + + impl_ops->event_filter = ampere_cspmu_event_filter; + impl_ops->set_ev_filter = ampere_cspmu_set_ev_filter; + impl_ops->validate_event = ampere_cspmu_validate_event; + impl_ops->get_name = ampere_cspmu_get_name; + impl_ops->get_event_attrs = ampere_cspmu_get_event_attrs; + impl_ops->get_format_attrs = ampere_cspmu_get_format_attrs; + + return 0; +} + +/* Match all Ampere Coresight PMU devices */ +static const struct arm_cspmu_impl_match ampere_cspmu_param = { + .pmiidr_val = ARM_CSPMU_IMPL_ID_AMPERE, + .module = THIS_MODULE, + .impl_init_ops = ampere_cspmu_init_ops +}; + +static int __init ampere_cspmu_init(void) +{ + int ret; + + ret = arm_cspmu_impl_register(&ere_cspmu_param); + if (ret) + pr_err("ampere_cspmu backend registration error: %d\n", ret); + + return ret; +} + +static void __exit ampere_cspmu_exit(void) +{ + arm_cspmu_impl_unregister(&ere_cspmu_param); +} + +module_init(ampere_cspmu_init); +module_exit(ampere_cspmu_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c index f0e6d14..42b7204 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.c +++ b/drivers/perf/arm_cspmu/arm_cspmu.c @@ -16,7 +16,7 @@ * The user should refer to the vendor technical documentation to get details * about the supported events. * - * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. * */ @@ -26,11 +26,11 @@ #include #include #include +#include #include #include #include "arm_cspmu.h" -#include "nvidia_cspmu.h" #define PMUNAME "arm_cspmu" #define DRVNAME "arm-cs-arch-pmu" @@ -112,11 +112,13 @@ */ #define HILOHI_MAX_POLL 1000 -/* JEDEC-assigned JEP106 identification code */ -#define ARM_CSPMU_IMPL_ID_NVIDIA 0x36B - static unsigned long arm_cspmu_cpuhp_state; +static DEFINE_MUTEX(arm_cspmu_lock); + +static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu, + struct hw_perf_event *hwc, u32 filter); + static struct acpi_apmt_node *arm_cspmu_apmt_node(struct device *dev) { return *(struct acpi_apmt_node **)dev_get_platdata(dev); @@ -373,27 +375,45 @@ static struct attribute_group arm_cspmu_cpumask_attr_group = { .attrs = arm_cspmu_cpumask_attrs, }; -struct impl_match { - u32 pmiidr; - u32 mask; - int (*impl_init_ops)(struct arm_cspmu *cspmu); -}; - -static const struct impl_match impl_match[] = { +static struct arm_cspmu_impl_match impl_match[] = { { - .pmiidr = ARM_CSPMU_IMPL_ID_NVIDIA, - .mask = ARM_CSPMU_PMIIDR_IMPLEMENTER, - .impl_init_ops = nv_cspmu_init_ops + .module_name = "nvidia_cspmu", + .pmiidr_val = ARM_CSPMU_IMPL_ID_NVIDIA, + .pmiidr_mask = ARM_CSPMU_PMIIDR_IMPLEMENTER, + .module = NULL, + .impl_init_ops = NULL, }, - {} + { + .module_name = "ampere_cspmu", + .pmiidr_val = ARM_CSPMU_IMPL_ID_AMPERE, + .pmiidr_mask = ARM_CSPMU_PMIIDR_IMPLEMENTER, + .module = NULL, + .impl_init_ops = NULL, + }, + + {0} }; +static struct arm_cspmu_impl_match *arm_cspmu_impl_match_get(u32 pmiidr) +{ + struct arm_cspmu_impl_match *match = impl_match; + + for (; match->pmiidr_val; match++) { + u32 mask = match->pmiidr_mask; + + if ((match->pmiidr_val & mask) == (pmiidr & mask)) + return match; + } + + return NULL; +} + static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu) { - int ret; + int ret = 0; struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops; struct acpi_apmt_node *apmt_node = arm_cspmu_apmt_node(cspmu->dev); - const struct impl_match *match = impl_match; + struct arm_cspmu_impl_match *match; /* * Get PMU implementer and product id from APMT node. @@ -405,17 +425,36 @@ static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu) readl(cspmu->base0 + PMIIDR); /* Find implementer specific attribute ops. */ - for (; match->pmiidr; match++) { - const u32 mask = match->mask; + match = arm_cspmu_impl_match_get(cspmu->impl.pmiidr); + + /* Load implementer module and initialize the callbacks. */ + if (match) { + mutex_lock(&arm_cspmu_lock); + + if (match->impl_init_ops) { + /* Prevent unload until PMU registration is done. */ + if (try_module_get(match->module)) { + cspmu->impl.module = match->module; + cspmu->impl.match = match; + ret = match->impl_init_ops(cspmu); + if (ret) + module_put(match->module); + } else { + WARN(1, "arm_cspmu failed to get module: %s\n", + match->module_name); + ret = -EINVAL; + } + } else { + request_module_nowait(match->module_name); + ret = -EPROBE_DEFER; + } - if ((match->pmiidr & mask) == (cspmu->impl.pmiidr & mask)) { - ret = match->impl_init_ops(cspmu); - if (ret) - return ret; + mutex_unlock(&arm_cspmu_lock); - break; - } - } + if (ret) + return ret; + } else + cspmu->impl.module = THIS_MODULE; /* Use default callbacks if implementer doesn't provide one. */ CHECK_DEFAULT_IMPL_OPS(impl_ops, get_event_attrs); @@ -426,6 +465,7 @@ static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu) CHECK_DEFAULT_IMPL_OPS(impl_ops, event_type); CHECK_DEFAULT_IMPL_OPS(impl_ops, event_filter); CHECK_DEFAULT_IMPL_OPS(impl_ops, event_attr_is_visible); + CHECK_DEFAULT_IMPL_OPS(impl_ops, set_ev_filter); return 0; } @@ -478,11 +518,6 @@ arm_cspmu_alloc_attr_group(struct arm_cspmu *cspmu) struct attribute_group **attr_groups = NULL; struct device *dev = cspmu->dev; const struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops; - int ret; - - ret = arm_cspmu_init_impl_ops(cspmu); - if (ret) - return NULL; cspmu->identifier = impl_ops->get_identifier(cspmu); cspmu->name = impl_ops->get_name(cspmu); @@ -549,7 +584,7 @@ static void arm_cspmu_disable(struct pmu *pmu) static int arm_cspmu_get_event_idx(struct arm_cspmu_hw_events *hw_events, struct perf_event *event) { - int idx; + int idx, ret; struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu); if (supports_cycle_counter(cspmu)) { @@ -583,6 +618,12 @@ static int arm_cspmu_get_event_idx(struct arm_cspmu_hw_events *hw_events, if (idx >= cspmu->num_logical_ctrs) return -EAGAIN; + if (cspmu->impl.ops.validate_event) { + ret = cspmu->impl.ops.validate_event(cspmu, event); + if (ret) + return ret; + } + set_bit(idx, hw_events->used_ctrs); return idx; @@ -696,7 +737,10 @@ static void arm_cspmu_write_counter(struct perf_event *event, u64 val) if (use_64b_counter_reg(cspmu)) { offset = counter_offset(sizeof(u64), event->hw.idx); - writeq(val, cspmu->base1 + offset); + if (cspmu->has_atomic_dword) + writeq(val, cspmu->base1 + offset); + else + lo_hi_writeq(val, cspmu->base1 + offset); } else { offset = counter_offset(sizeof(u32), event->hw.idx); @@ -789,9 +833,9 @@ static inline void arm_cspmu_set_event(struct arm_cspmu *cspmu, writel(hwc->config, cspmu->base0 + offset); } -static inline void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu, - struct hw_perf_event *hwc, - u32 filter) +static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu, + struct hw_perf_event *hwc, + u32 filter) { u32 offset = PMEVFILTR + (4 * hwc->idx); @@ -823,7 +867,7 @@ static void arm_cspmu_start(struct perf_event *event, int pmu_flags) arm_cspmu_set_cc_filter(cspmu, filter); } else { arm_cspmu_set_event(cspmu, hwc); - arm_cspmu_set_ev_filter(cspmu, hwc, filter); + cspmu->impl.ops.set_ev_filter(cspmu, hwc, filter); } hwc->state = 0; @@ -1147,7 +1191,7 @@ static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu) cspmu->pmu = (struct pmu){ .task_ctx_nr = perf_invalid_context, - .module = THIS_MODULE, + .module = cspmu->impl.module, .pmu_enable = arm_cspmu_enable, .pmu_disable = arm_cspmu_disable, .event_init = arm_cspmu_event_init, @@ -1194,11 +1238,17 @@ static int arm_cspmu_device_probe(struct platform_device *pdev) if (ret) return ret; - ret = arm_cspmu_register_pmu(cspmu); + ret = arm_cspmu_init_impl_ops(cspmu); if (ret) return ret; - return 0; + ret = arm_cspmu_register_pmu(cspmu); + + /* Matches arm_cspmu_init_impl_ops() above. */ + if (cspmu->impl.module != THIS_MODULE) + module_put(cspmu->impl.module); + + return ret; } static int arm_cspmu_device_remove(struct platform_device *pdev) @@ -1298,6 +1348,75 @@ static void __exit arm_cspmu_exit(void) cpuhp_remove_multi_state(arm_cspmu_cpuhp_state); } +int arm_cspmu_impl_register(const struct arm_cspmu_impl_match *impl_match) +{ + struct arm_cspmu_impl_match *match; + int ret = 0; + + match = arm_cspmu_impl_match_get(impl_match->pmiidr_val); + + if (match) { + mutex_lock(&arm_cspmu_lock); + + if (!match->impl_init_ops) { + match->module = impl_match->module; + match->impl_init_ops = impl_match->impl_init_ops; + } else { + /* Broken match table may contain non-unique entries */ + WARN(1, "arm_cspmu backend already registered for module: %s, pmiidr: 0x%x, mask: 0x%x\n", + match->module_name, + match->pmiidr_val, + match->pmiidr_mask); + + ret = -EINVAL; + } + + mutex_unlock(&arm_cspmu_lock); + + if (!ret) + ret = driver_attach(&arm_cspmu_driver.driver); + } else { + pr_err("arm_cspmu reg failed, unable to find a match for pmiidr: 0x%x\n", + impl_match->pmiidr_val); + + ret = -EINVAL; + } + + return ret; +} +EXPORT_SYMBOL_GPL(arm_cspmu_impl_register); + +static int arm_cspmu_match_device(struct device *dev, const void *match) +{ + struct arm_cspmu *cspmu = platform_get_drvdata(to_platform_device(dev)); + + return (cspmu && cspmu->impl.match == match) ? 1 : 0; +} + +void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match) +{ + struct device *dev; + struct arm_cspmu_impl_match *match; + + match = arm_cspmu_impl_match_get(impl_match->pmiidr_val); + + if (WARN_ON(!match)) + return; + + /* Unbind the driver from all matching backend devices. */ + while ((dev = driver_find_device(&arm_cspmu_driver.driver, NULL, + match, arm_cspmu_match_device))) + device_release_driver(dev); + + mutex_lock(&arm_cspmu_lock); + + match->module = NULL; + match->impl_init_ops = NULL; + + mutex_unlock(&arm_cspmu_lock); +} +EXPORT_SYMBOL_GPL(arm_cspmu_impl_unregister); + module_init(arm_cspmu_init); module_exit(arm_cspmu_exit); diff --git a/drivers/perf/arm_cspmu/arm_cspmu.h b/drivers/perf/arm_cspmu/arm_cspmu.h index 83df53d..2fe7235 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.h +++ b/drivers/perf/arm_cspmu/arm_cspmu.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 * * ARM CoreSight Architecture PMU driver. - * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. * */ @@ -69,6 +69,10 @@ #define ARM_CSPMU_PMIIDR_IMPLEMENTER GENMASK(11, 0) #define ARM_CSPMU_PMIIDR_PRODUCTID GENMASK(31, 20) +/* JEDEC-assigned JEP106 identification code */ +#define ARM_CSPMU_IMPL_ID_NVIDIA 0x36B +#define ARM_CSPMU_IMPL_ID_AMPERE 0xA16 + struct arm_cspmu; /* This tracks the events assigned to each counter in the PMU. */ @@ -101,14 +105,34 @@ struct arm_cspmu_impl_ops { u32 (*event_type)(const struct perf_event *event); /* Decode filter value from configs */ u32 (*event_filter)(const struct perf_event *event); + /* Set event filter */ + void (*set_ev_filter)(struct arm_cspmu *cspmu, + struct hw_perf_event *hwc, u32 filter); + /* Implementation specific event validation */ + int (*validate_event)(struct arm_cspmu *cspmu, + struct perf_event *event); /* Hide/show unsupported events */ umode_t (*event_attr_is_visible)(struct kobject *kobj, struct attribute *attr, int unused); }; +/* Vendor/implementer registration parameter. */ +struct arm_cspmu_impl_match { + /* Backend module. */ + struct module *module; + const char *module_name; + /* PMIIDR value/mask. */ + u32 pmiidr_val; + u32 pmiidr_mask; + /* Callback to vendor backend to init arm_cspmu_impl::ops. */ + int (*impl_init_ops)(struct arm_cspmu *cspmu); +}; + /* Vendor/implementer descriptor. */ struct arm_cspmu_impl { u32 pmiidr; + struct module *module; + struct arm_cspmu_impl_match *match; struct arm_cspmu_impl_ops ops; void *ctx; }; @@ -147,4 +171,10 @@ ssize_t arm_cspmu_sysfs_format_show(struct device *dev, struct device_attribute *attr, char *buf); +/* Register vendor backend. */ +int arm_cspmu_impl_register(const struct arm_cspmu_impl_match *impl_match); + +/* Unregister vendor backend. */ +void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match); + #endif /* __ARM_CSPMU_H__ */ diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c index 72ef80c..0382b70 100644 --- a/drivers/perf/arm_cspmu/nvidia_cspmu.c +++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c @@ -1,14 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. * */ /* Support for NVIDIA specific attributes. */ +#include #include -#include "nvidia_cspmu.h" +#include "arm_cspmu.h" #define NV_PCIE_PORT_COUNT 10ULL #define NV_PCIE_FILTER_ID_MASK GENMASK_ULL(NV_PCIE_PORT_COUNT - 1, 0) @@ -351,7 +352,7 @@ static char *nv_cspmu_format_name(const struct arm_cspmu *cspmu, return name; } -int nv_cspmu_init_ops(struct arm_cspmu *cspmu) +static int nv_cspmu_init_ops(struct arm_cspmu *cspmu) { u32 prodid; struct nv_cspmu_ctx *ctx; @@ -395,6 +396,31 @@ int nv_cspmu_init_ops(struct arm_cspmu *cspmu) return 0; } -EXPORT_SYMBOL_GPL(nv_cspmu_init_ops); + +/* Match all NVIDIA Coresight PMU devices */ +static const struct arm_cspmu_impl_match nv_cspmu_param = { + .pmiidr_val = ARM_CSPMU_IMPL_ID_NVIDIA, + .module = THIS_MODULE, + .impl_init_ops = nv_cspmu_init_ops +}; + +static int __init nvidia_cspmu_init(void) +{ + int ret; + + ret = arm_cspmu_impl_register(&nv_cspmu_param); + if (ret) + pr_err("nvidia_cspmu backend registration error: %d\n", ret); + + return ret; +} + +static void __exit nvidia_cspmu_exit(void) +{ + arm_cspmu_impl_unregister(&nv_cspmu_param); +} + +module_init(nvidia_cspmu_init); +module_exit(nvidia_cspmu_exit); MODULE_LICENSE("GPL v2"); diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.h b/drivers/perf/arm_cspmu/nvidia_cspmu.h deleted file mode 100644 index 71e18f0..0000000 --- a/drivers/perf/arm_cspmu/nvidia_cspmu.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * - * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. - * - */ - -/* Support for NVIDIA specific attributes. */ - -#ifndef __NVIDIA_CSPMU_H__ -#define __NVIDIA_CSPMU_H__ - -#include "arm_cspmu.h" - -/* Allocate NVIDIA descriptor. */ -int nv_cspmu_init_ops(struct arm_cspmu *cspmu); - -#endif /* __NVIDIA_CSPMU_H__ */ diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index 8fcaa26..4f6923a 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -1126,7 +1126,7 @@ static void __armv8pmu_probe_pmu(void *info) pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); /* store PMMIR register for sysfs */ - if (is_pmuv3p4(pmuver) && (pmceid_raw[1] & BIT(31))) + if (is_pmuv3p4(pmuver)) cpu_pmu->reg_pmmir = read_pmmir(); else cpu_pmu->reg_pmmir = 0; @@ -1187,10 +1187,7 @@ static void armv8_pmu_register_sysctl_table(void) } static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, - int (*map_event)(struct perf_event *event), - const struct attribute_group *events, - const struct attribute_group *format, - const struct attribute_group *caps) + int (*map_event)(struct perf_event *event)) { int ret = armv8pmu_probe_pmu(cpu_pmu); if (ret) @@ -1212,27 +1209,17 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, cpu_pmu->name = name; cpu_pmu->map_event = map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ? - events : &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ? - format : &armv8_pmuv3_format_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ? - caps : &armv8_pmuv3_caps_attr_group; - + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &armv8_pmuv3_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &armv8_pmuv3_format_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = &armv8_pmuv3_caps_attr_group; armv8_pmu_register_sysctl_table(); return 0; } -static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name, - int (*map_event)(struct perf_event *event)) -{ - return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL); -} - #define PMUV3_INIT_SIMPLE(name) \ static int name##_pmu_init(struct arm_pmu *cpu_pmu) \ { \ - return armv8_pmu_init_nogroups(cpu_pmu, #name, armv8_pmuv3_map_event);\ + return armv8_pmu_init(cpu_pmu, #name, armv8_pmuv3_map_event); \ } PMUV3_INIT_SIMPLE(armv8_pmuv3) @@ -1263,44 +1250,37 @@ PMUV3_INIT_SIMPLE(armv8_nvidia_denver) static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu) { - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35", - armv8_a53_map_event); + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35", armv8_a53_map_event); } static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) { - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53", - armv8_a53_map_event); + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53", armv8_a53_map_event); } static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) { - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57", - armv8_a57_map_event); + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57", armv8_a57_map_event); } static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu) { - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72", - armv8_a57_map_event); + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72", armv8_a57_map_event); } static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu) { - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73", - armv8_a73_map_event); + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73", armv8_a73_map_event); } static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) { - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder", - armv8_thunder_map_event); + return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder", armv8_thunder_map_event); } static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) { - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan", - armv8_vulcan_map_event); + return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan", armv8_vulcan_map_event); } static const struct of_device_id armv8_pmu_of_device_ids[] = { diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c index 5a00adb..b90ba8a 100644 --- a/drivers/perf/hisilicon/hisi_pcie_pmu.c +++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c @@ -353,16 +353,15 @@ static int hisi_pcie_pmu_event_init(struct perf_event *event) struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - event->cpu = pcie_pmu->on_cpu; + /* Check the type first before going on, otherwise it's not our event */ + if (event->attr.type != event->pmu->type) + return -ENOENT; if (EXT_COUNTER_IS_USED(hisi_pcie_get_event(event))) hwc->event_base = HISI_PCIE_EXT_CNT; else hwc->event_base = HISI_PCIE_CNT; - if (event->attr.type != event->pmu->type) - return -ENOENT; - /* Sampling is not supported. */ if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) return -EOPNOTSUPP; @@ -373,6 +372,8 @@ static int hisi_pcie_pmu_event_init(struct perf_event *event) if (!hisi_pcie_pmu_validate_event_group(event)) return -EINVAL; + event->cpu = pcie_pmu->on_cpu; + return 0; } diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c index d941e74..797cf20 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c @@ -505,8 +505,8 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev) ret = perf_pmu_register(&pa_pmu->pmu, name, -1); if (ret) { dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret); - cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE, - &pa_pmu->node); + cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE, + &pa_pmu->node); return ret; } diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c index 6fe534a..e706ca5 100644 --- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c @@ -450,8 +450,8 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev) ret = perf_pmu_register(&sllc_pmu->pmu, name, -1); if (ret) { dev_err(sllc_pmu->dev, "PMU register failed, ret = %d\n", ret); - cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE, - &sllc_pmu->node); + cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE, + &sllc_pmu->node); return ret; } diff --git a/drivers/perf/hisilicon/hns3_pmu.c b/drivers/perf/hisilicon/hns3_pmu.c index e0457d8..16869bf 100644 --- a/drivers/perf/hisilicon/hns3_pmu.c +++ b/drivers/perf/hisilicon/hns3_pmu.c @@ -1556,8 +1556,8 @@ static int hns3_pmu_init_pmu(struct pci_dev *pdev, struct hns3_pmu *hns3_pmu) ret = perf_pmu_register(&hns3_pmu->pmu, hns3_pmu->pmu.name, -1); if (ret) { pci_err(pdev, "failed to register perf PMU, ret = %d.\n", ret); - cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE, - &hns3_pmu->node); + cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE, + &hns3_pmu->node); } return ret; @@ -1568,8 +1568,8 @@ static void hns3_pmu_uninit_pmu(struct pci_dev *pdev) struct hns3_pmu *hns3_pmu = pci_get_drvdata(pdev); perf_pmu_unregister(&hns3_pmu->pmu); - cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE, - &hns3_pmu->node); + cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE, + &hns3_pmu->node); } static int hns3_pmu_init_dev(struct pci_dev *pdev) diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c index 9972bfc..7ce3442 100644 --- a/drivers/perf/xgene_pmu.c +++ b/drivers/perf/xgene_pmu.c @@ -16,11 +16,9 @@ #include #include #include -#include -#include -#include #include #include +#include #include #include @@ -1731,6 +1729,12 @@ static const struct xgene_pmu_data xgene_pmu_v2_data = { .id = PCP_PMU_V2, }; +#ifdef CONFIG_ACPI +static const struct xgene_pmu_data xgene_pmu_v3_data = { + .id = PCP_PMU_V3, +}; +#endif + static const struct xgene_pmu_ops xgene_pmu_ops = { .mask_int = xgene_pmu_mask_int, .unmask_int = xgene_pmu_unmask_int, @@ -1773,9 +1777,9 @@ static const struct of_device_id xgene_pmu_of_match[] = { MODULE_DEVICE_TABLE(of, xgene_pmu_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id xgene_pmu_acpi_match[] = { - {"APMC0D5B", PCP_PMU_V1}, - {"APMC0D5C", PCP_PMU_V2}, - {"APMC0D83", PCP_PMU_V3}, + {"APMC0D5B", (kernel_ulong_t)&xgene_pmu_data}, + {"APMC0D5C", (kernel_ulong_t)&xgene_pmu_v2_data}, + {"APMC0D83", (kernel_ulong_t)&xgene_pmu_v3_data}, {}, }; MODULE_DEVICE_TABLE(acpi, xgene_pmu_acpi_match); @@ -1831,7 +1835,6 @@ static int xgene_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) static int xgene_pmu_probe(struct platform_device *pdev) { const struct xgene_pmu_data *dev_data; - const struct of_device_id *of_id; struct xgene_pmu *xgene_pmu; int irq, rc; int version; @@ -1850,24 +1853,10 @@ static int xgene_pmu_probe(struct platform_device *pdev) xgene_pmu->dev = &pdev->dev; platform_set_drvdata(pdev, xgene_pmu); - version = -EINVAL; - of_id = of_match_device(xgene_pmu_of_match, &pdev->dev); - if (of_id) { - dev_data = (const struct xgene_pmu_data *) of_id->data; - version = dev_data->id; - } - -#ifdef CONFIG_ACPI - if (ACPI_COMPANION(&pdev->dev)) { - const struct acpi_device_id *acpi_id; - - acpi_id = acpi_match_device(xgene_pmu_acpi_match, &pdev->dev); - if (acpi_id) - version = (int) acpi_id->driver_data; - } -#endif - if (version < 0) + dev_data = device_get_match_data(&pdev->dev); + if (!dev_data) return -ENODEV; + version = dev_data->id; if (version == PCP_PMU_V3) xgene_pmu->ops = &xgene_pmu_v3_ops; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index db3a33e..b887a82 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -256,6 +256,11 @@ acpi_table_parse_cedt(enum acpi_cedt_type id, int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); +static inline bool acpi_gicc_is_usable(struct acpi_madt_generic_interrupt *gicc) +{ + return gicc->flags & ACPI_MADT_ENABLED; +} + /* the following numa functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d246d32..d305db7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -172,6 +172,7 @@ enum cpuhp_state { CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, + CPUHP_AP_ARM_ARCH_TIMER_EVTSTRM_STARTING, CPUHP_AP_ARM_GLOBAL_TIMER_STARTING, CPUHP_AP_JCORE_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, @@ -189,6 +190,7 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, + CPUHP_AP_ARM_XEN_RUNSTATE_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index e3d2628..1189e77 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -81,6 +81,20 @@ static void lrcpc_sigill(void) asm volatile(".inst 0xb8bfc3e0" : : : ); } +static void lse128_sigill(void) +{ + u64 __attribute__ ((aligned (16))) mem[2] = { 10, 20 }; + register u64 *memp asm ("x0") = mem; + register u64 val0 asm ("x1") = 5; + register u64 val1 asm ("x2") = 4; + + /* SWPP X1, X2, [X0] */ + asm volatile(".inst 0x19228001" + : "+r" (memp), "+r" (val0), "+r" (val1) + : + : "cc", "memory"); +} + static void mops_sigill(void) { char dst[1], src[1]; @@ -226,6 +240,12 @@ static void sveaes_sigill(void) asm volatile(".inst 0x4522e400" : : : "z0"); } +static void sveb16b16_sigill(void) +{ + /* BFADD ZA.H[W0, 0], {Z0.H-Z1.H} */ + asm volatile(".inst 0xC1E41C00" : : : ); +} + static void svepmull_sigill(void) { /* PMULLB Z0.Q, Z0.D, Z0.D */ @@ -289,6 +309,19 @@ static void uscat_sigbus(void) asm volatile(".inst 0xb820003f" : : : ); } +static void lrcpc3_sigill(void) +{ + int data[2] = { 1, 2 }; + + register int *src asm ("x0") = data; + register int data0 asm ("w2") = 0; + register int data1 asm ("w3") = 0; + + /* LDIAPP w2, w3, [x0] */ + asm volatile(".inst 0x99431802" + : "=r" (data0), "=r" (data1) : "r" (src) :); +} + static const struct hwcap_data { const char *name; unsigned long at_hwcap; @@ -349,6 +382,13 @@ static const struct hwcap_data { .sigill_fn = ilrcpc_sigill, }, { + .name = "LRCPC3", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_LRCPC3, + .cpuinfo = "lrcpc3", + .sigill_fn = lrcpc3_sigill, + }, + { .name = "LSE", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_ATOMICS, @@ -365,6 +405,13 @@ static const struct hwcap_data { .sigbus_reliable = true, }, { + .name = "LSE128", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_LSE128, + .cpuinfo = "lse128", + .sigill_fn = lse128_sigill, + }, + { .name = "MOPS", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_MOPS, @@ -494,6 +541,13 @@ static const struct hwcap_data { .sigill_fn = sveaes_sigill, }, { + .name = "SVE2 B16B16", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SVE_B16B16, + .cpuinfo = "sveb16b16", + .sigill_fn = sveb16b16_sigill, + }, + { .name = "SVE2 PMULL", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SVEPMULL, diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index 4328895..547d077 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -473,6 +473,13 @@ function _start // mov x8, #__NR_sched_yield // Encourage preemption // svc #0 +#ifdef SSVE + mrs x0, S3_3_C4_C2_2 // SVCR should have ZA=0,SM=1 + and x1, x0, #3 + cmp x1, #1 + b.ne svcr_barf +#endif + mov x21, #0 0: mov x0, x21 bl check_zreg @@ -553,3 +560,15 @@ function vl_barf mov x1, #1 svc #0 endfunction + +function svcr_barf + mov x10, x0 + + puts "Bad SVCR: " + mov x0, x10 + bl putdecn + + mov x8, #__NR_exit + mov x1, #1 + svc #0 +endfunction