diff options
Diffstat (limited to 'arch/arm64')
51 files changed, 1346 insertions, 687 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 950a56b71ff0..3e53441ee067 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -143,6 +143,8 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_REGS \ + if $(cc-option,-fpatchable-function-entry=2) select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD @@ -266,6 +268,10 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y +config ZONE_DMA + bool "Support DMA zone" if EXPERT + default y + config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y @@ -538,6 +544,16 @@ config ARM64_ERRATUM_1286807 invalidated has been observed by other observers. The workaround repeats the TLBI+DSB operation. +config ARM64_ERRATUM_1319367 + bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation" + default y + help + This option adds work arounds for ARM Cortex-A57 erratum 1319537 + and A72 erratum 1319367 + + Cortex-A57 and A72 cores could end-up with corrupted TLBs by + speculating an AT instruction during a guest context switch. + If unsure, say Y. config ARM64_ERRATUM_1463225 @@ -558,6 +574,22 @@ config ARM64_ERRATUM_1463225 If unsure, say Y. +config ARM64_ERRATUM_1542419 + bool "Neoverse-N1: workaround mis-ordering of instruction fetches" + default y + help + This option adds a workaround for ARM Neoverse-N1 erratum + 1542419. + + Affected Neoverse-N1 cores could execute a stale instruction when + modified by another CPU. The workaround depends on a firmware + counterpart. + + Workaround the issue by hiding the DIC feature from EL0. This + forces user-space to perform cache maintenance. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -616,6 +648,23 @@ config CAVIUM_ERRATUM_30115 If unsure, say Y. +config CAVIUM_TX2_ERRATUM_219 + bool "Cavium ThunderX2 erratum 219: PRFM between TTBR change and ISB fails" + default y + help + On Cavium ThunderX2, a load, store or prefetch instruction between a + TTBR update and the corresponding context synchronizing operation can + cause a spurious Data Abort to be delivered to any hardware thread in + the CPU core. + + Work around the issue by avoiding the problematic code sequence and + trapping KVM guest TTBRx_EL1 writes to EL2 when SMT is enabled. The + trap handler performs the corresponding register access, skips the + instruction and ensures context synchronization by virtue of the + exception return. + + If unsure, say Y. + config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" default y diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2c0238ce0551..1fbe24d4fdb6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -95,6 +95,11 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) KBUILD_LDS_MODULE += $(srctree)/arch/arm64/kernel/module.lds endif +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=2 +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index f74909ba29bd..a70575edae8e 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -74,14 +74,4 @@ alternative_if ARM64_ALT_PAN_NOT_UAO SET_PSTATE_PAN(0) alternative_else_nop_endif .endm - -/* - * Remove the address tag from a virtual address, if present. - */ - .macro clear_address_tag, dst, addr - tst \addr, #(1 << 55) - bic \dst, \addr, #(0xff << 56) - csel \dst, \dst, \addr, eq - .endm - #endif diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index e0e2b1946f42..7d9cc5ec4971 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -29,6 +29,18 @@ SB_BARRIER_INSN"nop\n", \ ARM64_HAS_SB)) +#ifdef CONFIG_ARM64_PSEUDO_NMI +#define pmr_sync() \ + do { \ + extern struct static_key_false gic_pmr_sync; \ + \ + if (static_branch_unlikely(&gic_pmr_sync)) \ + dsb(sy); \ + } while(0) +#else +#define pmr_sync() do {} while (0) +#endif + #define mb() dsb(sy) #define rmb() dsb(ld) #define wmb() dsb(st) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 43da6dd29592..806e9dc2a852 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -11,6 +11,7 @@ #define CTR_L1IP_MASK 3 #define CTR_DMINLINE_SHIFT 16 #define CTR_IMINLINE_SHIFT 0 +#define CTR_IMINLINE_MASK 0xf #define CTR_ERG_SHIFT 20 #define CTR_CWG_SHIFT 24 #define CTR_CWG_MASK 15 @@ -18,7 +19,7 @@ #define CTR_DIC_SHIFT 29 #define CTR_CACHE_MINLINE_MASK \ - (0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT) + (0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT) #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index f19fe4b9acc4..b92683871119 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -52,7 +52,11 @@ #define ARM64_HAS_IRQ_PRIO_MASKING 42 #define ARM64_HAS_DCPODP 43 #define ARM64_WORKAROUND_1463225 44 +#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 +#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 +#define ARM64_WORKAROUND_1542419 47 +#define ARM64_WORKAROUND_1319367 48 -#define ARM64_NCAPS 45 +#define ARM64_NCAPS 49 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 9cde5d2e768f..4261d55e8506 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -659,6 +659,20 @@ static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) default: return CONFIG_ARM64_PA_BITS; } } + +/* Check whether hardware update of the Access flag is supported */ +static inline bool cpu_has_hw_af(void) +{ + u64 mmfr1; + + if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) + return false; + + mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + return cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_HADBS_SHIFT); +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 063c964af705..72acd2db167f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -8,7 +8,9 @@ #include <linux/irqflags.h> #include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/ptrace.h> #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ PSR_I_BIT @@ -65,7 +67,7 @@ static inline void local_daif_restore(unsigned long flags) if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); - dsb(sy); + pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; @@ -109,4 +111,19 @@ static inline void local_daif_restore(unsigned long flags) trace_hardirqs_off(); } +/* + * Called by synchronous exception handlers to restore the DAIF bits that were + * modified by taking an exception. + */ +static inline void local_daif_inherit(struct pt_regs *regs) +{ + unsigned long flags = regs->pstate & DAIF_MASK; + + /* + * We can't use local_daif_restore(regs->pstate) here as + * system_has_prio_mask_debugging() won't restore the I bit if it can + * use the pmr instead. + */ + write_sysreg(flags, daif); +} #endif diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index a17393ff6677..4d5f3b5f50cd 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -8,14 +8,15 @@ #define __ASM_EXCEPTION_H #include <asm/esr.h> +#include <asm/kprobes.h> +#include <asm/ptrace.h> #include <linux/interrupt.h> -#define __exception __attribute__((section(".exception.text"))) #ifdef CONFIG_FUNCTION_GRAPH_TRACER #define __exception_irq_entry __irq_entry #else -#define __exception_irq_entry __exception +#define __exception_irq_entry __kprobes #endif static inline u32 disr_to_esr(u64 disr) @@ -31,5 +32,22 @@ static inline u32 disr_to_esr(u64 disr) } asmlinkage void enter_from_user_mode(void); +void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_undefinstr(struct pt_regs *regs); +asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, + struct pt_regs *regs); +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); +void do_sve_acc(unsigned int esr, struct pt_regs *regs); +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); +void do_sysinstr(unsigned int esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); +void do_cp15instr(unsigned int esr, struct pt_regs *regs); +void el0_svc_handler(struct pt_regs *regs); +void el0_svc_compat_handler(struct pt_regs *regs); +void do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, + struct pt_regs *regs); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index d48667b04c41..91fa4baa1a93 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -11,9 +11,20 @@ #include <asm/insn.h> #define HAVE_FUNCTION_GRAPH_FP_TEST + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#else #define MCOUNT_ADDR ((unsigned long)_mcount) +#endif + +/* The BL at the callsite's adjusted rec->ip */ #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE +#define FTRACE_PLT_IDX 0 +#define FTRACE_REGS_PLT_IDX 1 +#define NR_FTRACE_PLTS 2 + /* * Currently, gcc tends to save the link register after the local variables * on the stack. This causes the max stack tracer to report the function @@ -44,12 +55,24 @@ extern void return_to_handler(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* + * Adjust addr to point at the BL in the callsite. + * See ftrace_init_nop() for the callsite sequence. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return addr + AARCH64_INSN_SIZE; + /* * addr is the address of the mcount call instruction. * recordmcount does the necessary offset calculation. */ return addr; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #define ftrace_return_address(n) return_address(n) /* diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 39e7780bedd6..bb313dde58a4 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -440,6 +440,9 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type); +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant); u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type, enum aarch64_insn_variant variant, enum aarch64_insn_register Rn, diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 1a59f0ed1ae3..aa4b6521ef14 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -6,6 +6,7 @@ #define __ASM_IRQFLAGS_H #include <asm/alternative.h> +#include <asm/barrier.h> #include <asm/ptrace.h> #include <asm/sysreg.h> @@ -34,14 +35,14 @@ static inline void arch_local_irq_enable(void) } asm volatile(ALTERNATIVE( - "msr daifclr, #2 // arch_local_irq_enable\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", + "msr daifclr, #2 // arch_local_irq_enable", + __msr_s(SYS_ICC_PMR_EL1, "%0"), ARM64_HAS_IRQ_PRIO_MASKING) : : "r" ((unsigned long) GIC_PRIO_IRQON) : "memory"); + + pmr_sync(); } static inline void arch_local_irq_disable(void) @@ -116,14 +117,14 @@ static inline unsigned long arch_local_irq_save(void) static inline void arch_local_irq_restore(unsigned long flags) { asm volatile(ALTERNATIVE( - "msr daif, %0\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", - ARM64_HAS_IRQ_PRIO_MASKING) + "msr daif, %0", + __msr_s(SYS_ICC_PMR_EL1, "%0"), + ARM64_HAS_IRQ_PRIO_MASKING) : : "r" (flags) : "memory"); + + pmr_sync(); } #endif /* __ASM_IRQFLAGS_H */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f656169db8c3..5ecb091c8576 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -600,8 +600,7 @@ static inline void kvm_arm_vhe_guest_enter(void) * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ - if (system_uses_irq_prio_masking()) - dsb(sy); + pmr_sync(); } static inline void kvm_arm_vhe_guest_exit(void) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b61b50bf68b1..a4f9ca5479b0 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -69,12 +69,6 @@ #define KERNEL_START _text #define KERNEL_END _end -#ifdef CONFIG_ARM64_VA_BITS_52 -#define MAX_USER_VA_BITS 52 -#else -#define MAX_USER_VA_BITS VA_BITS -#endif - /* * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual * address space for the shadow region respectively. They can bloat the stack @@ -215,12 +209,18 @@ static inline unsigned long kaslr_offset(void) * up with a tagged userland pointer. Clear the tag to get a sane pointer to * pass on to access_ok(), for instance. */ -#define untagged_addr(addr) \ +#define __untagged_addr(addr) \ ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) +#define untagged_addr(addr) ({ \ + u64 __addr = (__force u64)addr; \ + __addr &= __untagged_addr(__addr); \ + (__force __typeof__(addr))__addr; \ +}) + #ifdef CONFIG_KASAN_SW_TAGS #define __tag_shifted(tag) ((u64)(tag) << 56) -#define __tag_reset(addr) untagged_addr(addr) +#define __tag_reset(addr) __untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else #define __tag_shifted(tag) 0UL diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index f80e13cbf8ec..1e93de68c044 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -21,7 +21,7 @@ struct mod_arch_specific { struct mod_plt_sec init; /* for CONFIG_DYNAMIC_FTRACE */ - struct plt_entry *ftrace_trampoline; + struct plt_entry *ftrace_trampolines; }; #endif diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 3df60f97da1f..d9fbd433cc17 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -69,7 +69,7 @@ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT)) +#define PTRS_PER_PGD (1 << (VA_BITS - PGDIR_SHIFT)) /* * Section address mask and size definitions. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7576df00eb50..5716fe86e7b9 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -17,7 +17,7 @@ * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space - * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space + * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space * and fixed mappings */ #define VMALLOC_START (MODULES_END) @@ -876,15 +876,26 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) -#define kc_vaddr_to_offset(v) ((v) & ~PAGE_END) -#define kc_offset_to_vaddr(o) ((o) | PAGE_END) - #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) #else #define phys_to_ttbr(addr) (addr) #endif +/* + * On arm64 without hardware Access Flag, copying from user will fail because + * the pte is old and cannot be marked young. So we always end up with zeroed + * page after fork() + CoW for pfn mappings. We don't always have a + * hardware-managed access flag on arm64. + */ +static inline bool arch_faults_on_old_pte(void) +{ + WARN_ON(preemptible()); + + return !cpu_has_hw_af(); +} +#define arch_faults_on_old_pte arch_faults_on_old_pte + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5623685c7d13..5ba63204d078 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -9,7 +9,7 @@ #define __ASM_PROCESSOR_H #define KERNEL_DS UL(-1) -#define USER_DS ((UL(1) << MAX_USER_VA_BITS) - 1) +#define USER_DS ((UL(1) << VA_BITS) - 1) /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is @@ -26,10 +26,12 @@ #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> +#include <linux/thread_info.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> +#include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> @@ -214,6 +216,18 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, regs->sp = sp; } +static inline bool is_ttbr0_addr(unsigned long addr) +{ + /* entry assembly clears tags for TTBR0 addrs */ + return addr < TASK_SIZE; +} + +static inline bool is_ttbr1_addr(unsigned long addr) +{ + /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ + return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; +} + #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index 06d880b3526c..b383b4802a7b 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -66,24 +66,18 @@ struct pt_regs; } \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused); \ ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused) -#endif -#ifndef COND_SYSCALL #define COND_SYSCALL(name) \ asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs) \ { \ return sys_ni_syscall(); \ } -#endif -#ifndef SYS_NI #define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers); -#endif #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 972d196c7714..6e919fafb43d 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -212,7 +212,7 @@ #define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0) #define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0) -#define SYS_PAR_EL1_F BIT(1) +#define SYS_PAR_EL1_F BIT(0) #define SYS_PAR_EL1_FST GENMASK(6, 1) /*** Statistical Profiling Extension ***/ diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 59690613ac31..cee5928e1b7d 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -42,16 +42,6 @@ static inline int __in_irqentry_text(unsigned long ptr) ptr < (unsigned long)&__irqentry_text_end; } -static inline int in_exception_text(unsigned long ptr) -{ - int in; - - in = ptr >= (unsigned long)&__exception_text_start && - ptr < (unsigned long)&__exception_text_end; - - return in ? : __in_irqentry_text(ptr); -} - static inline int in_entry_text(unsigned long ptr) { return ptr >= (unsigned long)&__entry_text_start && diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 478491f07b4f..fc6488660f64 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -13,9 +13,9 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) # Object file lists. obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ - entry-fpsimd.o process.o ptrace.o setup.o signal.o \ - sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o cpu_ops.o insn.o \ + entry-common.o entry-fpsimd.o process.o ptrace.o \ + setup.o signal.o sys.o stacktrace.o time.o traps.o \ + io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 214685760e1c..a5bdce8af65b 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -56,6 +56,7 @@ int main(void) DEFINE(S_X24, offsetof(struct pt_regs, regs[24])); DEFINE(S_X26, offsetof(struct pt_regs, regs[26])); DEFINE(S_X28, offsetof(struct pt_regs, regs[28])); + DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index f593f4cffc0d..4f8187a4fc46 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -6,12 +6,12 @@ */ #include <linux/arm-smccc.h> -#include <linux/psci.h> #include <linux/types.h> #include <linux/cpu.h> #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/cpufeature.h> +#include <asm/smp_plat.h> static bool __maybe_unused is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) @@ -87,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, } static void -cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused) +cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap) { u64 mask = arm64_ftr_reg_ctrel0.strict_mask; + bool enable_uct_trap = false; /* Trap CTR_EL0 access on this CPU, only if it has a mismatch */ if ((read_cpuid_cachetype() & mask) != (arm64_ftr_reg_ctrel0.sys_val & mask)) + enable_uct_trap = true; + + /* ... or if the system is affected by an erratum */ + if (cap->capability == ARM64_WORKAROUND_1542419) + enable_uct_trap = true; + + if (enable_uct_trap) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); } @@ -166,9 +174,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, } #endif /* CONFIG_KVM_INDIRECT_VECTORS */ -#include <uapi/linux/psci.h> #include <linux/arm-smccc.h> -#include <linux/psci.h> static void call_smc_arch_workaround_1(void) { @@ -212,11 +218,8 @@ static int detect_harden_bp_fw(void) struct arm_smccc_res res; u32 midr = read_cpuid_id(); - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - return -1; - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); switch ((int)res.a0) { @@ -234,7 +237,7 @@ static int detect_harden_bp_fw(void) } break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); switch ((int)res.a0) { @@ -308,11 +311,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt, BUG_ON(nr_inst != 1); - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: insn = aarch64_insn_get_hvc_value(); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: insn = aarch64_insn_get_smc_value(); break; default: @@ -351,12 +354,12 @@ void arm64_set_ssbd_mitigation(bool state) return; } - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); break; @@ -390,20 +393,13 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, goto out_printmsg; } - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { - ssbd_state = ARM64_SSBD_UNKNOWN; - if (!this_cpu_safe) - __ssb_safe = false; - return false; - } - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_2, &res); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_2, &res); break; @@ -623,9 +619,45 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope) return (need_wa > 0); } -#ifdef CONFIG_HARDEN_EL2_VECTORS +static const __maybe_unused struct midr_range tx2_family_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), + MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), + {}, +}; + +static bool __maybe_unused +needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry, + int scope) +{ + int i; + + if (!is_affected_midr_range_list(entry, scope) || + !is_hyp_mode_available()) + return false; + + for_each_possible_cpu(i) { + if (MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0) != 0) + return true; + } + + return false; +} + +static bool __maybe_unused +has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT); + const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1); -static const struct midr_range arm64_harden_el2_vectors[] = { + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && has_dic; +} + +#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367) + +static const struct midr_range ca57_a72[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), {}, @@ -819,7 +851,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "EL2 vector hardening", .capability = ARM64_HARDEN_EL2_VECTORS, - ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors), + ERRATA_MIDR_RANGE_LIST(ca57_a72), }, #endif { @@ -852,6 +884,36 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_cortex_a76_erratum_1463225, }, #endif +#ifdef CONFIG_CAVIUM_TX2_ERRATUM_219 + { + .desc = "Cavium ThunderX2 erratum 219 (KVM guest sysreg trapping)", + .capability = ARM64_WORKAROUND_CAVIUM_TX2_219_TVM, + ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), + .matches = needs_tx2_tvm_workaround, + }, + { + .desc = "Cavium ThunderX2 erratum 219 (PRFM removal)", + .capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM, + ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1542419 + { + /* we depend on the firmware portion for correctness */ + .desc = "ARM erratum 1542419 (kernel portion)", + .capability = ARM64_WORKAROUND_1542419, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_neoverse_n1_erratum_1542419, + .cpu_enable = cpu_enable_trap_ctr_access, + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1319367 + { + .desc = "ARM erratum 1319367", + .capability = ARM64_WORKAROUND_1319367, + ERRATA_MIDR_RANGE_LIST(ca57_a72), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index cabebf1a7976..04cf64e9f0c9 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -176,11 +176,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -977,6 +982,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), { /* sentinel */ } }; char const *str = "kpti command line option"; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 05933c065732..56bba746da1c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -329,7 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_cntfrq = arch_timer_get_cntfrq(); /* * Use the effective value of the CTR_EL0 than the raw value - * exposed by the CPU. CTR_E0.IDC field value must be interpreted + * exposed by the CPU. CTR_EL0.IDC field value must be interpreted * with the CLIDR_EL1 fields to avoid triggering false warnings * when there is a mismatch across the CPUs. Keep track of the * effective value of the CTR_EL0 in our internal records for diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c new file mode 100644 index 000000000000..5dce5e56995a --- /dev/null +++ b/arch/arm64/kernel/entry-common.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Exception handling code + * + * Copyright (C) 2019 ARM Ltd. + */ + +#include <linux/context_tracking.h> +#include <linux/ptrace.h> +#include <linux/thread_info.h> + +#include <asm/cpufeature.h> +#include <asm/daifflags.h> +#include <asm/esr.h> +#include <asm/exception.h> +#include <asm/kprobes.h> +#include <asm/mmu.h> +#include <asm/sysreg.h> + +static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_abort); + +static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_pc); + +static void el1_undef(struct pt_regs *regs) +{ + local_daif_inherit(regs); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el1_undef); + +static void el1_inv(struct pt_regs *regs, unsigned long esr) +{ + local_daif_inherit(regs); + bad_mode(regs, 0, esr); +} +NOKPROBE_SYMBOL(el1_inv); + +static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * The CPU masked interrupts, and we are leaving them masked during + * do_debug_exception(). Update PMR as if we had called + * local_mask_daif(). + */ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + do_debug_exception(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_dbg); + +asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_DABT_CUR: + case ESR_ELx_EC_IABT_CUR: + el1_abort(regs, esr); + break; + /* + * We don't handle ESR_ELx_EC_SP_ALIGN, since we will have hit a + * recursive exception when trying to push the initial pt_regs. + */ + case ESR_ELx_EC_PC_ALIGN: + el1_pc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_UNKNOWN: + el1_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_CUR: + case ESR_ELx_EC_SOFTSTP_CUR: + case ESR_ELx_EC_WATCHPT_CUR: + case ESR_ELx_EC_BRK64: + el1_dbg(regs, esr); + break; + default: + el1_inv(regs, esr); + }; +} +NOKPROBE_SYMBOL(el1_sync_handler); + +static void notrace el0_da(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_da); + +static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * We've taken an instruction abort from userspace and not yet + * re-enabled IRQs. If the address is a kernel address, apply + * BP hardening prior to enabling IRQs and pre-emption. + */ + if (!is_ttbr0_addr(far)) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_ia); + +static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_acc); + +static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sve_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_sve_acc); + +static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_exc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_exc); + +static void notrace el0_sys(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sysinstr(esr, regs); +} +NOKPROBE_SYMBOL(el0_sys); + +static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + if (!is_ttbr0_addr(instruction_pointer(regs))) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_pc); + +static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX_NOIRQ); + do_sp_pc_abort(regs->sp, esr, regs); +} +NOKPROBE_SYMBOL(el0_sp); + +static void notrace el0_undef(struct pt_regs *regs) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el0_undef); + +static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + bad_el0_sync(regs, 0, esr); +} +NOKPROBE_SYMBOL(el0_inv); + +static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) +{ + /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ + unsigned long far = read_sysreg(far_el1); + + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + user_exit_irqoff(); + do_debug_exception(far, esr, regs); + local_daif_restore(DAIF_PROCCTX_NOIRQ); +} +NOKPROBE_SYMBOL(el0_dbg); + +static void notrace el0_svc(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc); + +asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC64: + el0_svc(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_SVE: + el0_sve_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC64: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_WFx: + el0_sys(regs, esr); + break; + case ESR_ELx_EC_SP_ALIGN: + el0_sp(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + el0_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BRK64: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_handler); + +#ifdef CONFIG_COMPAT +static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_cp15instr(esr, regs); +} +NOKPROBE_SYMBOL(el0_cp15); + +static void notrace el0_svc_compat(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_compat_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc_compat); + +asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC32: + el0_svc_compat(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC32: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + case ESR_ELx_EC_CP14_MR: + case ESR_ELx_EC_CP14_LS: + case ESR_ELx_EC_CP14_64: + el0_undef(regs); + break; + case ESR_ELx_EC_CP15_32: + case ESR_ELx_EC_CP15_64: + el0_cp15(regs, esr); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BKPT32: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_compat_handler); +#endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 33d003d80121..4fe1514fcbfd 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,10 +7,137 @@ */ #include <linux/linkage.h> +#include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/ftrace.h> #include <asm/insn.h> +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +/* + * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before + * the regular function prologue. For an enabled callsite, ftrace_init_nop() and + * ftrace_make_call() have patched those NOPs to: + * + * MOV X9, LR + * BL <entry> + * + * ... where <entry> is either ftrace_caller or ftrace_regs_caller. + * + * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are + * live, and x9-x18 are safe to clobber. + * + * We save the callsite's context into a pt_regs before invoking any ftrace + * callbacks. So that we can get a sensible backtrace, we create a stack record + * for the callsite and the ftrace entry assembly. This is not sufficient for + * reliable stacktrace: until we create the callsite stack record, its caller + * is missing from the LR and existing chain of frame records. + */ + .macro ftrace_regs_entry, allregs=0 + /* Make room for pt_regs, plus a callee frame */ + sub sp, sp, #(S_FRAME_SIZE + 16) + + /* Save function arguments (and x9 for simplicity) */ + stp x0, x1, [sp, #S_X0] + stp x2, x3, [sp, #S_X2] + stp x4, x5, [sp, #S_X4] + stp x6, x7, [sp, #S_X6] + stp x8, x9, [sp, #S_X8] + + /* Optionally save the callee-saved registers, always save the FP */ + .if \allregs == 1 + stp x10, x11, [sp, #S_X10] + stp x12, x13, [sp, #S_X12] + stp x14, x15, [sp, #S_X14] + stp x16, x17, [sp, #S_X16] + stp x18, x19, [sp, #S_X18] + stp x20, x21, [sp, #S_X20] + stp x22, x23, [sp, #S_X22] + stp x24, x25, [sp, #S_X24] + stp x26, x27, [sp, #S_X26] + stp x28, x29, [sp, #S_X28] + .else + str x29, [sp, #S_FP] + .endif + + /* Save the callsite's SP and LR */ + add x10, sp, #(S_FRAME_SIZE + 16) + stp x9, x10, [sp, #S_LR] + + /* Save the PC after the ftrace callsite */ + str x30, [sp, #S_PC] + + /* Create a frame record for the callsite above pt_regs */ + stp x29, x9, [sp, #S_FRAME_SIZE] + add x29, sp, #S_FRAME_SIZE + + /* Create our frame record within pt_regs. */ + stp x29, x30, [sp, #S_STACKFRAME] + add x29, sp, #S_STACKFRAME + .endm + +ENTRY(ftrace_regs_caller) + ftrace_regs_entry 1 + b ftrace_common +ENDPROC(ftrace_regs_caller) + +ENTRY(ftrace_caller) + ftrace_regs_entry 0 + b ftrace_common +ENDPROC(ftrace_caller) + +ENTRY(ftrace_common) + sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + mov x1, x9 // parent_ip (callsite's LR) + ldr_l x2, function_trace_op // op + mov x3, sp // regs + +GLOBAL(ftrace_call) + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); + nop // If enabled, this will be replaced + // "b ftrace_graph_caller" +#endif + +/* + * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved + * x19-x29 per the AAPCS, and we created frame records upon entry, so we need + * to restore x0-x8, x29, and x30. + */ +ftrace_common_return: + /* Restore function arguments */ + ldp x0, x1, [sp] + ldp x2, x3, [sp, #S_X2] + ldp x4, x5, [sp, #S_X4] + ldp x6, x7, [sp, #S_X6] + ldr x8, [sp, #S_X8] + + /* Restore the callsite's FP, LR, PC */ + ldr x29, [sp, #S_FP] + ldr x30, [sp, #S_LR] + ldr x9, [sp, #S_PC] + + /* Restore the callsite's SP */ + add sp, sp, #S_FRAME_SIZE + 16 + + ret x9 +ENDPROC(ftrace_common) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + ldr x0, [sp, #S_PC] + sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + add x1, sp, #S_LR // parent_ip (callsite's LR) + ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + bl prepare_ftrace_return + b ftrace_common_return +ENDPROC(ftrace_graph_caller) +#else +#endif + +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + /* * Gcc with -pg will put the following code in the beginning of each function: * mov x0, x30 @@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); mcount_exit ENDPROC(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE */ - -ENTRY(ftrace_stub) - ret -ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller) mcount_exit ENDPROC(ftrace_graph_caller) +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +ENTRY(ftrace_stub) + ret +ENDPROC(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * void return_to_handler(void) * diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index e304fe04b098..583f71abbe98 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -269,8 +269,10 @@ alternative_else_nop_endif alternative_if ARM64_HAS_IRQ_PRIO_MASKING ldr x20, [sp, #S_PMR_SAVE] msr_s SYS_ICC_PMR_EL1, x20 - /* Ensure priority change is seen by redistributor */ - dsb sy + mrs_s x21, SYS_ICC_CTLR_EL1 + tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE + dsb sy // Ensure priority change is seen by redistributor +.L__skip_pmr_sync\@: alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR @@ -578,76 +580,9 @@ ENDPROC(el1_error_invalid) .align 6 el1_sync: kernel_entry 1 - mrs x1, esr_el1 // read the syndrome register - lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 - b.eq el1_da - cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 - b.eq el1_ia - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - b.eq el1_undef - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el1_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1 - b.eq el1_undef - cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 - b.ge el1_dbg - b el1_inv - -el1_ia: - /* - * Fall through to the Data abort case - */ -el1_da: - /* - * Data abort handling - */ - mrs x3, far_el1 - inherit_daif pstate=x23, tmp=x2 - clear_address_tag x0, x3 - mov x2, sp // struct pt_regs - bl do_mem_abort - - kernel_exit 1 -el1_pc: - /* - * PC alignment exception handling. We don't handle SP alignment faults, - * since we will have hit a recursive exception when trying to push the - * initial pt_regs. - */ - mrs x0, far_el1 - inherit_daif pstate=x23, tmp=x2 - mov x2, sp - bl do_sp_pc_abort - ASM_BUG() -el1_undef: - /* - * Undefined instruction - */ - inherit_daif pstate=x23, tmp=x2 mov x0, sp - bl do_undefinstr + bl el1_sync_handler kernel_exit 1 -el1_dbg: - /* - * Debug exception handling - */ - cmp x24, #ESR_ELx_EC_BRK64 // if BRK64 - cinc x24, x24, eq // set bit '0' - tbz x24, #0, el1_inv // EL1 only - gic_prio_kentry_setup tmp=x3 - mrs x0, far_el1 - mov x2, sp // struct pt_regs - bl do_debug_exception - kernel_exit 1 -el1_inv: - // TODO: add support for undefined instructions in kernel mode - inherit_daif pstate=x23, tmp=x2 - mov x0, sp - mov x2, x1 - mov x1, #BAD_SYNC - bl bad_mode - ASM_BUG() ENDPROC(el1_sync) .align 6 @@ -680,7 +615,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING orr x24, x24, x0 alternative_else_nop_endif cbnz x24, 1f // preempt count != 0 || NMI return path - bl preempt_schedule_irq // irq en/disable is done inside + bl arm64_preempt_schedule_irq // irq en/disable is done inside 1: #endif @@ -714,71 +649,18 @@ ENDPROC(el1_irq) .align 6 el0_sync: kernel_entry 0 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC64 // SVC in 64-bit state - b.eq el0_svc - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_SVE // SVE access - b.eq el0_sve_acc - cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - ccmp x24, #ESR_ELx_EC_WFx, #4, ne - b.eq el0_sys - cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el0_sp - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv + mov x0, sp + bl el0_sync_handler + b ret_to_user #ifdef CONFIG_COMPAT .align 6 el0_sync_compat: kernel_entry 0, 32 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC32 // SVC in 32-bit state - b.eq el0_svc_compat - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP15_64 // CP15 MRRC/MCRR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP14_MR // CP14 MRC/MCR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_LS // CP14 LDC/STC trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_64 // CP14 MRRC/MCRR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv -el0_svc_compat: - gic_prio_kentry_setup tmp=x1 mov x0, sp - bl el0_svc_compat_handler + bl el0_sync_compat_handler b ret_to_user +ENDPROC(el0_sync) .align 6 el0_irq_compat: @@ -788,140 +670,8 @@ el0_irq_compat: el0_error_compat: kernel_entry 0, 32 b el0_error_naked - -el0_cp15: - /* - * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_cp15instr - b ret_to_user #endif -el0_da: - /* - * Data abort handling - */ - mrs x26, far_el1 - ct_user_exit_irqoff - enable_daif - clear_address_tag x0, x26 - mov x1, x25 - mov x2, sp - bl do_mem_abort - b ret_to_user -el0_ia: - /* - * Instruction abort handling - */ - mrs x26, far_el1 - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_el0_ia_bp_hardening - b ret_to_user -el0_fpsimd_acc: - /* - * Floating Point or Advanced SIMD access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_acc - b ret_to_user -el0_sve_acc: - /* - * Scalable Vector Extension access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sve_acc - b ret_to_user -el0_fpsimd_exc: - /* - * Floating Point, Advanced SIMD or SVE exception - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_exc - b ret_to_user -el0_sp: - ldr x26, [sp, #S_SP] - b el0_sp_pc -el0_pc: - mrs x26, far_el1 -el0_sp_pc: - /* - * Stack or PC alignment exception handling - */ - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_sp_pc_abort - b ret_to_user -el0_undef: - /* - * Undefined instruction - */ - ct_user_exit_irqoff - enable_daif - mov x0, sp - bl do_undefinstr - b ret_to_user -el0_sys: - /* - * System instructions, for trapped cache maintenance instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sysinstr - b ret_to_user -el0_dbg: - /* - * Debug exception handling - */ - tbnz x24, #0, el0_inv // EL0 only - mrs x24, far_el1 - gic_prio_kentry_setup tmp=x3 - ct_user_exit_irqoff - mov x0, x24 - mov x1, x25 - mov x2, sp - bl do_debug_exception - enable_da_f - b ret_to_user -el0_inv: - ct_user_exit_irqoff - enable_daif - mov x0, sp - mov x1, #BAD_SYNC - mov x2, x25 - bl bad_el0_sync - b ret_to_user -ENDPROC(el0_sync) - .align 6 el0_irq: kernel_entry 0 @@ -999,17 +749,6 @@ finish_ret_to_user: kernel_exit 0 ENDPROC(ret_to_user) -/* - * SVC handler. - */ - .align 6 -el0_svc: - gic_prio_kentry_setup tmp=x1 - mov x0, sp - bl el0_svc_handler - b ret_to_user -ENDPROC(el0_svc) - .popsection // .entry.text #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 @@ -1071,7 +810,9 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 #else ldr x30, =vectors #endif +alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM prfm plil1strm, [x30, #(1b - tramp_vectors)] +alternative_else_nop_endif msr vbar_el1, x30 add x30, x30, #(1b - tramp_vectors) isb diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 37d3912cfe06..3eb338f14386 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -920,7 +920,7 @@ void fpsimd_release_task(struct task_struct *dead_task) * would have disabled the SVE access trap for userspace during * ret_to_user, making an SVE access trap impossible in that case. */ -asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) +void do_sve_acc(unsigned int esr, struct pt_regs *regs) { /* Even if we chose not to use SVE, the hardware could still trap: */ if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { @@ -947,7 +947,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) /* * Trapped FP/ASIMD access. */ -asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) { /* TODO: implement lazy context saving/restoring */ WARN_ON(1); @@ -956,7 +956,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) /* * Raise a SIGFPE for the current process. */ -asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) { unsigned int si_code = FPE_FLTUNK; diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 06e56b470315..8618faa82e6d 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(pc, 0, new, false); } +static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) +{ +#ifdef CONFIG_ARM64_MODULE_PLTS + struct plt_entry *plt = mod->arch.ftrace_trampolines; + + if (addr == FTRACE_ADDR) + return &plt[FTRACE_PLT_IDX]; + if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS)) + return &plt[FTRACE_REGS_PLT_IDX]; +#endif + return NULL; +} + /* * Turn on the call to ftrace_caller() in instrumented function */ @@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline, *dst; struct module *mod; + struct plt_entry *plt; + + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; /* * On kernels that support module PLTs, the offset between the @@ -93,49 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (WARN_ON(!mod)) return -EINVAL; - /* - * There is only one ftrace trampoline per module. For now, - * this is not a problem since on arm64, all dynamic ftrace - * invocations are routed via ftrace_caller(). This will need - * to be revisited if support for multiple ftrace entry points - * is added in the future, but for now, the pr_err() below - * deals with a theoretical issue only. - * - * Note that PLTs are place relative, and plt_entries_equal() - * checks whether they point to the same target. Here, we need - * to check if the actual opcodes are in fact identical, - * regardless of the offset in memory so use memcmp() instead. - */ - dst = mod->arch.ftrace_trampoline; - trampoline = get_plt_entry(addr, dst); - if (memcmp(dst, &trampoline, sizeof(trampoline))) { - if (plt_entry_is_initialized(dst)) { - pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); - return -EINVAL; - } - - /* point the trampoline to our ftrace entry point */ - module_disable_ro(mod); - *dst = trampoline; - module_enable_ro(mod, true); - - /* - * Ensure updated trampoline is visible to instruction - * fetch before we patch in the branch. Although the - * architecture doesn't require an IPI in this case, - * Neoverse-N1 erratum #1542419 does require one - * if the TLB maintenance in module_enable_ro() is - * skipped due to rodata_enabled. It doesn't seem worth - * it to make it conditional given that this is - * certainly not a fast-path. - */ - flush_icache_range((unsigned long)&dst[0], - (unsigned long)&dst[1]); + plt = get_ftrace_plt(mod, addr); + if (!plt) { + pr_err("ftrace: no module PLT for %ps\n", (void *)addr); + return -EINVAL; } - addr = (unsigned long)dst; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ + + addr = (unsigned long)plt; } old = aarch64_insn_gen_nop(); @@ -144,6 +123,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + old = aarch64_insn_gen_branch_imm(pc, old_addr, + AARCH64_INSN_BRANCH_LINK); + new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); + + return ftrace_modify_code(pc, old, new, true); +} + +/* + * The compiler has inserted two NOPs before the regular function prologue. + * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live, + * and x9-x18 are free for our use. + * + * At runtime we want to be able to swing a single NOP <-> BL to enable or + * disable the ftrace call. The BL requires us to save the original LR value, + * so here we insert a <MOV X9, LR> over the first NOP so the instructions + * before the regular prologue are: + * + * | Compiled | Disabled | Enabled | + * +----------+------------+------------+ + * | NOP | MOV X9, LR | MOV X9, LR | + * | NOP | NOP | BL <entry> | + * + * The LR value will be recovered by ftrace_regs_entry, and restored into LR + * before returning to the regular function prologue. When a function is not + * being traced, the MOV is not harmful given x9 is not live per the AAPCS. + * + * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of + * the BL. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + unsigned long pc = rec->ip - AARCH64_INSN_SIZE; + u32 old, new; + + old = aarch64_insn_gen_nop(); + new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9, + AARCH64_INSN_REG_LR, + AARCH64_INSN_VARIANT_64BIT); + return ftrace_modify_code(pc, old, new, true); +} +#endif + /* * Turn off the call to ftrace_caller() in instrumented function */ @@ -156,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS u32 replaced; + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; + /* * 'mod' is only set at module load time, but if we end up * dealing with an out-of-range condition, we can assume it @@ -189,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return -EINVAL; validate = false; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ } else { old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index e0a7fce0e01c..a96b2921d22c 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -201,6 +201,7 @@ static int create_safe_exec_page(void *src_start, size_t length, gfp_t mask) { int rc = 0; + pgd_t *trans_pgd; pgd_t *pgdp; pud_t *pudp; pmd_t *pmdp; @@ -215,7 +216,13 @@ static int create_safe_exec_page(void *src_start, size_t length, memcpy((void *)dst, src_start, length); __flush_icache_range(dst, dst + length); - pgdp = pgd_offset_raw(allocator(mask), dst_addr); + trans_pgd = allocator(mask); + if (!trans_pgd) { + rc = -ENOMEM; + goto out; + } + + pgdp = pgd_offset_raw(trans_pgd, dst_addr); if (pgd_none(READ_ONCE(*pgdp))) { pudp = allocator(mask); if (!pudp) { diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index d801a7094076..513b29c3e735 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } +/* + * MOV (register) is architecturally an alias of ORR (shifted register) where + * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m> + */ +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant) +{ + return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR, + src, 0, variant, + AARCH64_INSN_LOGIC_ORR); +} + u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, enum aarch64_insn_adr_type type) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 416f537bf614..2a11a962e571 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -19,6 +19,14 @@ #include <asm/pgtable.h> #include <asm/sections.h> +enum kaslr_status { + KASLR_ENABLED, + KASLR_DISABLED_CMDLINE, + KASLR_DISABLED_NO_SEED, + KASLR_DISABLED_FDT_REMAP, +}; + +static enum kaslr_status __initdata kaslr_status; u64 __ro_after_init module_alloc_base; u16 __initdata memstart_offset_seed; @@ -91,15 +99,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ early_fixmap_init(); fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); - if (!fdt) + if (!fdt) { + kaslr_status = KASLR_DISABLED_FDT_REMAP; return 0; + } /* * Retrieve (and wipe) the seed from the FDT */ seed = get_kaslr_seed(fdt); - if (!seed) - return 0; /* * Check if 'nokaslr' appears on the command line, and @@ -107,8 +115,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ cmdline = kaslr_get_cmdline(fdt); str = strstr(cmdline, "nokaslr"); - if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) + if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) { + kaslr_status = KASLR_DISABLED_CMDLINE; + return 0; + } + + if (!seed) { + kaslr_status = KASLR_DISABLED_NO_SEED; return 0; + } /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable @@ -170,3 +185,24 @@ u64 __init kaslr_early_init(u64 dt_phys) return offset; } + +static int __init kaslr_init(void) +{ + switch (kaslr_status) { + case KASLR_ENABLED: + pr_info("KASLR enabled\n"); + break; + case KASLR_DISABLED_CMDLINE: + pr_info("KASLR disabled on command line\n"); + break; + case KASLR_DISABLED_NO_SEED: + pr_warn("KASLR disabled due to lack of seed\n"); + break; + case KASLR_DISABLED_FDT_REMAP: + pr_warn("KASLR disabled due to FDT remapping failure\n"); + break; + } + + return 0; +} +core_initcall(kaslr_init) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index b182442b87a3..65b08a74aec6 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -4,6 +4,7 @@ */ #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sort.h> @@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, tramp->sh_type = SHT_NOBITS; tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; tramp->sh_addralign = __alignof__(struct plt_entry); - tramp->sh_size = sizeof(struct plt_entry); + tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); } return 0; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 03ff15bffbb6..1cd1a4d0ed30 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -9,6 +9,7 @@ #include <linux/bitops.h> #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/gfp.h> #include <linux/kasan.h> #include <linux/kernel.h> @@ -470,22 +471,58 @@ overflow: return -ENOEXEC; } -int module_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *me) +static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) { const Elf_Shdr *s, *se; const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { - if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) - apply_alternatives_module((void *)s->sh_addr, s->sh_size); -#ifdef CONFIG_ARM64_MODULE_PLTS - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name)) - me->arch.ftrace_trampoline = (void *)s->sh_addr; -#endif + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; } + return NULL; +} + +static inline void __init_plt(struct plt_entry *plt, unsigned long addr) +{ + *plt = get_plt_entry(addr, plt); +} + +static int module_init_ftrace_plt(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) +{ +#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE) + const Elf_Shdr *s; + struct plt_entry *plts; + + s = find_section(hdr, sechdrs, ".text.ftrace_trampoline"); + if (!s) + return -ENOEXEC; + + plts = (void *)s->sh_addr; + + __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + __init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR); + + mod->arch.ftrace_trampolines = plts; +#endif return 0; } + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + s = find_section(hdr, sechdrs, ".altinstructions"); + if (s) + apply_alternatives_module((void *)s->sh_addr, s->sh_size); + + return module_init_ftrace_plt(hdr, sechdrs, me); +} diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index a0b4f1bca491..e40b65645c86 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -158,133 +158,74 @@ armv8pmu_events_sysfs_show(struct device *dev, return sprintf(page, "event=0x%03llx\n", pmu_attr->id); } -#define ARMV8_EVENT_ATTR(name, config) \ - PMU_EVENT_ATTR(name, armv8_event_attr_##name, \ - config, armv8pmu_events_sysfs_show) - -ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR); -ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL); -ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE); -ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL); -ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED); -ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED); -ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED); -ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN); -ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN); -ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED); -ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED); -ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED); -ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED); -ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED); -ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES); -ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED); -ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS); -ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE); -ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE); -ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB); -ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS); -ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR); -ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC); -ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED); -ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES); -/* Don't expose the chain event in /sys, since it's useless in isolation */ -ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED); -ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND); -ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND); -ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB); -ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB); -ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE); -ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE); -ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL); -ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL); -ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB); -ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB); -ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS); -ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE); -ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS); -ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK); -ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK); -ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD); -ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD); -ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD); -ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP); -ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED); -ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE); -ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION); +#define ARMV8_EVENT_ATTR(name, config) \ + (&((struct perf_pmu_events_attr) { \ + .attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL), \ + .id = config, \ + }).attr.attr) static struct attribute *armv8_pmuv3_event_attrs[] = { - &armv8_event_attr_sw_incr.attr.attr, - &armv8_event_attr_l1i_cache_refill.attr.attr, - &armv8_event_attr_l1i_tlb_refill.attr.attr, - &armv8_event_attr_l1d_cache_refill.attr.attr, - &armv8_event_attr_l1d_cache.attr.attr, - &armv8_event_attr_l1d_tlb_refill.attr.attr, - &armv8_event_attr_ld_retired.attr.attr, - &armv8_event_attr_st_retired.attr.attr, - &armv8_event_attr_inst_retired.attr.attr, - &armv8_event_attr_exc_taken.attr.attr, - &armv8_event_attr_exc_return.attr.attr, - &armv8_event_attr_cid_write_retired.attr.attr, - &armv8_event_attr_pc_write_retired.attr.attr, - &armv8_event_attr_br_immed_retired.attr.attr, - &armv8_event_attr_br_return_retired.attr.attr, - &armv8_event_attr_unaligned_ldst_retired.attr.attr, - &armv8_event_attr_br_mis_pred.attr.attr, - &armv8_event_attr_cpu_cycles.attr.attr, - &armv8_event_attr_br_pred.attr.attr, - &armv8_event_attr_mem_access.attr.attr, - &armv8_event_attr_l1i_cache.attr.attr, - &armv8_event_attr_l1d_cache_wb.attr.attr, - &armv8_event_attr_l2d_cache.attr.attr, - &armv8_event_attr_l2d_cache_refill.attr.attr, - &armv8_event_attr_l2d_cache_wb.attr.attr, - &armv8_event_attr_bus_access.attr.attr, - &armv8_event_attr_memory_error.attr.attr, - &armv8_event_attr_inst_spec.attr.attr, - &armv8_event_attr_ttbr_write_retired.attr.attr, - &armv8_event_attr_bus_cycles.attr.attr, - &armv8_event_attr_l1d_cache_allocate.attr.attr, - &armv8_event_attr_l2d_cache_allocate.attr.attr, - &armv8_event_attr_br_retired.attr.attr, - &armv8_event_attr_br_mis_pred_retired.attr.attr, - &armv8_event_attr_stall_frontend.attr.attr, - &armv8_event_attr_stall_backend.attr.attr, - &armv8_event_attr_l1d_tlb.attr.attr, - &armv8_event_attr_l1i_tlb.attr.attr, - &armv8_event_attr_l2i_cache.attr.attr, - &armv8_event_attr_l2i_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache_allocate.attr.attr, - &armv8_event_attr_l3d_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache.attr.attr, - &armv8_event_attr_l3d_cache_wb.attr.attr, - &armv8_event_attr_l2d_tlb_refill.attr.attr, - &armv8_event_attr_l2i_tlb_refill.attr.attr, - &armv8_event_attr_l2d_tlb.attr.attr, - &armv8_event_attr_l2i_tlb.attr.attr, - &armv8_event_attr_remote_access.attr.attr, - &armv8_event_attr_ll_cache.attr.attr, - &armv8_event_attr_ll_cache_miss.attr.attr, - &armv8_event_attr_dtlb_walk.attr.attr, - &armv8_event_attr_itlb_walk.attr.attr, - &armv8_event_attr_ll_cache_rd.attr.attr, - &armv8_event_attr_ll_cache_miss_rd.attr.attr, - &armv8_event_attr_remote_access_rd.attr.attr, - &armv8_event_attr_sample_pop.attr.attr, - &armv8_event_attr_sample_feed.attr.attr, - &armv8_event_attr_sample_filtrate.attr.attr, - &armv8_event_attr_sample_collision.attr.attr, + ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), + ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), + ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE), + ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL), + ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED), + ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED), + ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED), + ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN), + ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN), + ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED), + ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED), + ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED), + ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED), + ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED), + ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES), + ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED), + ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS), + ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE), + ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE), + ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB), + ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS), + ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR), + ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC), + ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED), + ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES), + /* Don't expose the chain event in /sys, since it's useless in isolation */ + ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED), + ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND), + ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND), + ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB), + ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB), + ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE), + ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE), + ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL), + ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL), + ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB), + ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB), + ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS), + ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE), + ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS), + ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK), + ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK), + ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD), + ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD), + ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD), + ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP), + ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED), + ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE), + ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION), NULL, }; diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index c4452827419b..d1c95dcf1d78 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -455,10 +455,6 @@ int __init arch_populate_kprobe_blacklist(void) (unsigned long)__irqentry_text_end); if (ret) return ret; - ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start, - (unsigned long)__exception_text_end); - if (ret) - return ret; ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start, (unsigned long)__idmap_text_end); if (ret) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 1fb2819fc048..71f788cd2b18 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -17,6 +17,7 @@ #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/kernel.h> +#include <linux/lockdep.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/sysctl.h> @@ -44,6 +45,7 @@ #include <asm/alternative.h> #include <asm/arch_gicv3.h> #include <asm/compat.h> +#include <asm/cpufeature.h> #include <asm/cacheflush.h> #include <asm/exec.h> #include <asm/fpsimd.h> @@ -631,3 +633,19 @@ static int __init tagged_addr_init(void) core_initcall(tagged_addr_init); #endif /* CONFIG_ARM64_TAGGED_ADDR_ABI */ + +asmlinkage void __sched arm64_preempt_schedule_irq(void) +{ + lockdep_assert_irqs_disabled(); + + /* + * Preempting a task from an IRQ means we leave copies of PSTATE + * on the stack. cpufeature's enable calls may modify PSTATE, but + * resuming one of these preempted tasks would undo those changes. + * + * Only allow a task to be preempted once cpufeatures have been + * enabled. + */ + if (static_branch_likely(&arm64_const_caps_ready)) + preempt_schedule_irq(); +} diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index c9f72b2665f1..43ae4e0c968f 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu) static int cpu_psci_cpu_kill(unsigned int cpu) { - int err, i; + int err; + unsigned long start, end; if (!psci_ops.affinity_info) return 0; @@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu) * while it is dying. So, try again a few times. */ - for (i = 0; i < 10; i++) { + start = jiffies; + end = start + msecs_to_jiffies(100); + do { err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { - pr_info("CPU%d killed.\n", cpu); + pr_info("CPU%d killed (polled %d ms)\n", cpu, + jiffies_to_msecs(jiffies - start)); return 0; } - msleep(10); - pr_info("Retrying again to check for CPU kill\n"); - } + usleep_range(100, 1000); + } while (time_before(jiffies, end)); pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", cpu, err); diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index ea94cf8f9dc6..d6259dac62b6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -2,6 +2,7 @@ // Copyright (C) 2017 Arm Ltd. #define pr_fmt(fmt) "sdei: " fmt +#include <linux/arm-smccc.h> #include <linux/arm_sdei.h> #include <linux/hardirq.h> #include <linux/irqflags.h> @@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit) return 0; } - sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; + sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 if (arm64_kernel_unmapped_at_el0()) { diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index f1cb64959427..3c18c2454089 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -8,6 +8,7 @@ */ #include <linux/compat.h> +#include <linux/cpufeature.h> #include <linux/personality.h> #include <linux/sched.h> #include <linux/sched/signal.h> @@ -17,6 +18,7 @@ #include <asm/cacheflush.h> #include <asm/system_misc.h> +#include <asm/tlbflush.h> #include <asm/unistd.h> static long @@ -30,6 +32,15 @@ __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)) { + /* + * The workaround requires an inner-shareable tlbi. + * We pick the reserved-ASID to minimise the impact. + */ + __tlbi(aside1is, __TLBI_VADDR(0, 0)); + dsb(ish); + } + ret = __flush_cache_user_range(start, start + chunk); if (ret) return ret; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 871c739f060a..9a9d98a443fc 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -154,14 +154,14 @@ static inline void sve_user_discard(void) sve_user_disable(); } -asmlinkage void el0_svc_handler(struct pt_regs *regs) +void el0_svc_handler(struct pt_regs *regs) { sve_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } #ifdef CONFIG_COMPAT -asmlinkage void el0_svc_compat_handler(struct pt_regs *regs) +void el0_svc_compat_handler(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls, compat_sys_call_table); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 34739e80211b..73caf35c2262 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -35,6 +35,7 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/insn.h> +#include <asm/kprobes.h> #include <asm/traps.h> #include <asm/smp.h> #include <asm/stack_pointer.h> @@ -393,7 +394,7 @@ void arm64_notify_segfault(unsigned long addr) force_signal_inject(SIGSEGV, code, addr); } -asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +void do_undefinstr(struct pt_regs *regs) { /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) @@ -405,6 +406,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) BUG_ON(!user_mode(regs)); force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc); } +NOKPROBE_SYMBOL(do_undefinstr); #define __user_cache_maint(insn, address, res) \ if (address >= user_addr_max()) { \ @@ -470,6 +472,15 @@ static void ctr_read_handler(unsigned int 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)) { + /* Hide DIC so that we can trap the unnecessary maintenance...*/ + val &= ~BIT(CTR_DIC_SHIFT); + + /* ... and fake IminLine to reduce the number of traps. */ + val &= ~CTR_IMINLINE_MASK; + val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK; + } + pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); @@ -667,7 +678,7 @@ static const struct sys64_hook cp15_64_hooks[] = { {}, }; -asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) +void do_cp15instr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook, *hook_base; @@ -705,9 +716,10 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_cp15instr); #endif -asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +void do_sysinstr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook; @@ -724,6 +736,7 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_sysinstr); static const char *esr_class_str[] = { [0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC", @@ -793,7 +806,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) * bad_el0_sync handles unexpected, but potentially recoverable synchronous * exceptions taken from EL0. Unlike bad_mode, this returns. */ -asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) { void __user *pc = (void __user *)instruction_pointer(regs); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index aa76f7259668..009057517bdd 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -111,9 +111,6 @@ SECTIONS } .text : { /* Real text segment */ _stext = .; /* Text and read-only data */ - __exception_text_start = .; - *(.exception.text) - __exception_text_end = .; IRQENTRY_TEXT SOFTIRQENTRY_TEXT ENTRY_TEXT diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 3d3815020e36..72fbbd86eb5e 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -12,7 +12,7 @@ #include <kvm/arm_psci.h> -#include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> @@ -118,12 +118,29 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) } write_sysreg(val, cptr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; + + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * configured and enabled. We can now restore the guest's S1 + * configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } } static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) { u64 hcr = vcpu->arch.hcr_el2; + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) + hcr |= HCR_TVM; + write_sysreg(hcr, hcr_el2); if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) @@ -156,6 +173,23 @@ static void __hyp_text __deactivate_traps_nvhe(void) { u64 mdcr_el2 = read_sysreg(mdcr_el2); + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * Set the TCR and SCTLR registers in the exact opposite + * sequence as __activate_traps_nvhe (first prevent walks, + * then force the MMU on). A generous sprinkling of isb() + * ensure that things happen in this exact order. + */ + val = read_sysreg_el1(SYS_TCR); + write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR); + isb(); + val = read_sysreg_el1(SYS_SCTLR); + write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR); + isb(); + } + __deactivate_traps_common(); mdcr_el2 &= MDCR_EL2_HPMN_MASK; @@ -174,8 +208,10 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) * the crucial bit is "On taking a vSError interrupt, * HCR_EL2.VSE is cleared to 0." */ - if (vcpu->arch.hcr_el2 & HCR_VSE) - vcpu->arch.hcr_el2 = read_sysreg(hcr_el2); + if (vcpu->arch.hcr_el2 & HCR_VSE) { + vcpu->arch.hcr_el2 &= ~HCR_VSE; + vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE; + } if (has_vhe()) deactivate_traps_vhe(); @@ -380,6 +416,61 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) return true; } +static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu)); + int rt = kvm_vcpu_sys_get_rt(vcpu); + u64 val = vcpu_get_reg(vcpu, rt); + + /* + * The normal sysreg handling code expects to see the traps, + * let's not do anything here. + */ + if (vcpu->arch.hcr_el2 & HCR_TVM) + return false; + + switch (sysreg) { + case SYS_SCTLR_EL1: + write_sysreg_el1(val, SYS_SCTLR); + break; + case SYS_TTBR0_EL1: + write_sysreg_el1(val, SYS_TTBR0); + break; + case SYS_TTBR1_EL1: + write_sysreg_el1(val, SYS_TTBR1); + break; + case SYS_TCR_EL1: + write_sysreg_el1(val, SYS_TCR); + break; + case SYS_ESR_EL1: + write_sysreg_el1(val, SYS_ESR); + break; + case SYS_FAR_EL1: + write_sysreg_el1(val, SYS_FAR); + break; + case SYS_AFSR0_EL1: + write_sysreg_el1(val, SYS_AFSR0); + break; + case SYS_AFSR1_EL1: + write_sysreg_el1(val, SYS_AFSR1); + break; + case SYS_MAIR_EL1: + write_sysreg_el1(val, SYS_MAIR); + break; + case SYS_AMAIR_EL1: + write_sysreg_el1(val, SYS_AMAIR); + break; + case SYS_CONTEXTIDR_EL1: + write_sysreg_el1(val, SYS_CONTEXTIDR); + break; + default: + return false; + } + + __kvm_skip_instr(vcpu); + return true; +} + /* * Return true when we were able to fixup the guest exit and should return to * the guest, false when we should restore the host state and return to the @@ -399,6 +490,11 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (*exit_code != ARM_EXCEPTION_TRAP) goto exit; + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && + kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 && + handle_tx2_tvm(vcpu)) + return true; + /* * We trap the first access to the FP/SIMD to save the host context * and restore the guest context lazily. @@ -592,7 +688,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) */ if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - dsb(sy); + pmr_sync(); } vcpu = kern_hyp_va(vcpu); @@ -605,18 +701,23 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_save_state_nvhe(host_ctxt); - __activate_vm(kern_hyp_va(vcpu->kvm)); - __activate_traps(vcpu); - - __hyp_vgic_restore_state(vcpu); - __timer_enable_traps(vcpu); - /* * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + * + * Also, and in order to be able to deal with erratum #1319537 (A57) + * and #1319367 (A72), we must ensure that all VM-related sysreg are + * restored before we enable S2 translation. */ __sysreg32_restore_state(vcpu); __sysreg_restore_state_nvhe(guest_ctxt); + + __activate_vm(kern_hyp_va(vcpu->kvm)); + __activate_traps(vcpu); + + __hyp_vgic_restore_state(vcpu); + __timer_enable_traps(vcpu); + __debug_switch_to_guest(vcpu); __set_guest_arch_workaround_state(vcpu); diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 7ddbc849b580..22b8128d19f6 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -117,12 +117,26 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + + if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } else if (!ctxt->__hyp_running_vcpu) { + /* + * Must only be done for guest registers, hence the context + * test. We're coming from the host, so SCTLR.M is already + * set. Pairs with __activate_traps_nvhe(). + */ + write_sysreg_el1((ctxt->sys_regs[TCR_EL1] | + TCR_EPD1_MASK | TCR_EPD0_MASK), + SYS_TCR); + isb(); + } + write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR); write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0); write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR); write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0); write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1); @@ -135,6 +149,23 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) && + ctxt->__hyp_running_vcpu) { + /* + * Must only be done for host registers, hence the context + * test. Pairs with __deactivate_traps_nvhe(). + */ + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * deconfigured and disabled. We can now restore the host's + * S1 configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } + write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR); write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR); diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index eb0efc5557f3..c2bc17ca6430 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -63,6 +63,22 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * For CPUs that are affected by ARM 1319367, we need to + * avoid a host Stage-1 walk while we have the guest's + * VMID set in the VTTBR in order to invalidate TLBs. + * We're guaranteed that the S1 MMU is enabled, so we can + * simply set the EPD bits to avoid any further TLB fill. + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + isb(); + } + __load_guest_stage2(kvm); isb(); } @@ -100,6 +116,13 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { write_sysreg(0, vttbr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + /* Ensure write of the host VMID */ + isb(); + /* Restore the host's TCR_EL1 */ + write_sysreg_el1(cxt->tcr, SYS_TCR); + } } static void __hyp_text __tlb_switch_to_host(struct kvm *kvm, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 855f2a7954e6..077b02a2d4d3 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -32,7 +32,8 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> -#include <asm/kasan.h> +#include <asm/kprobes.h> +#include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/pgtable.h> @@ -101,18 +102,6 @@ static void mem_abort_decode(unsigned int esr) data_abort_decode(esr); } -static inline bool is_ttbr0_addr(unsigned long addr) -{ - /* entry assembly clears tags for TTBR0 addrs */ - return addr < TASK_SIZE; -} - -static inline bool is_ttbr1_addr(unsigned long addr) -{ - /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ - return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; -} - static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ @@ -268,8 +257,12 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, par = read_sysreg(par_el1); local_irq_restore(flags); + /* + * If we now have a valid translation, treat the translation fault as + * spurious. + */ if (!(par & SYS_PAR_EL1_F)) - return false; + return true; /* * If we got a different type of fault from the AT instruction, @@ -314,6 +307,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; + else if (is_el1_instruction_abort(esr)) + msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { @@ -732,8 +727,7 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; -asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, - struct pt_regs *regs) +void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); @@ -749,43 +743,21 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, arm64_notify_die(inf->name, regs, inf->sig, inf->code, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_mem_abort); -asmlinkage void __exception do_el0_irq_bp_hardening(void) +void do_el0_irq_bp_hardening(void) { /* PC has already been checked in entry.S */ arm64_apply_bp_hardening(); } +NOKPROBE_SYMBOL(do_el0_irq_bp_hardening); -asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) -{ - /* - * We've taken an instruction abort from userspace and not yet - * re-enabled IRQs. If the address is a kernel address, apply - * BP hardening prior to enabling IRQs and pre-emption. - */ - if (!is_ttbr0_addr(addr)) - arm64_apply_bp_hardening(); - - local_daif_restore(DAIF_PROCCTX); - do_mem_abort(addr, esr, regs); -} - - -asmlinkage void __exception do_sp_pc_abort(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - if (user_mode(regs)) { - if (!is_ttbr0_addr(instruction_pointer(regs))) - arm64_apply_bp_hardening(); - local_daif_restore(DAIF_PROCCTX); - } - arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_sp_pc_abort); int __init early_brk64(unsigned long addr, unsigned int esr, struct pt_regs *regs); @@ -868,8 +840,7 @@ NOKPROBE_SYMBOL(debug_exception_exit); #ifdef CONFIG_ARM64_ERRATUM_1463225 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (user_mode(regs)) return 0; @@ -888,16 +859,15 @@ cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) return 1; } #else -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { return 0; } #endif /* CONFIG_ARM64_ERRATUM_1463225 */ +NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler); -asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, - unsigned int esr, - struct pt_regs *regs) +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, + struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 45c00a54909c..be9481cdf3b9 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -20,6 +20,7 @@ #include <linux/sort.h> #include <linux/of.h> #include <linux/of_fdt.h> +#include <linux/dma-direct.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/efi.h> @@ -41,6 +42,8 @@ #include <asm/tlb.h> #include <asm/alternative.h> +#define ARM64_ZONE_DMA_BITS 30 + /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() @@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset); struct page *vmemmap __ro_after_init; EXPORT_SYMBOL(vmemmap); +/* + * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of + * memory as some devices, namely the Raspberry Pi 4, have peripherals with + * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 + * bit addressable memory area. + */ phys_addr_t arm64_dma_phys_limit __ro_after_init; +static phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT, + crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void) { } #endif /* CONFIG_CRASH_DUMP */ + /* - * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It - * currently assumes that for memory starting above 4G, 32-bit devices will - * use a DMA offset. + * Return the maximum physical address for a zone with a given address size + * limit. It currently assumes that for memory starting above 4G, 32-bit + * devices will use a DMA offset. */ -static phys_addr_t __init max_zone_dma_phys(void) +static phys_addr_t __init max_zone_phys(unsigned int zone_bits) { - phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); - return min(offset + (1ULL << 32), memblock_end_of_DRAM()); + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits); + return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM()); } #ifdef CONFIG_NUMA @@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); +#endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys()); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); #endif max_zone_pfns[ZONE_NORMAL] = max; @@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { struct memblock_region *reg; unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; - unsigned long max_dma = min; + unsigned long max_dma32 = min; + unsigned long __maybe_unused max_dma = min; memset(zone_size, 0, sizeof(zone_size)); - /* 4GB maximum for 32-bit only capable devices */ -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA max_dma = PFN_DOWN(arm64_dma_phys_limit); - zone_size[ZONE_DMA32] = max_dma - min; + zone_size[ZONE_DMA] = max_dma - min; + max_dma32 = max_dma; +#endif +#ifdef CONFIG_ZONE_DMA32 + max_dma32 = PFN_DOWN(arm64_dma32_phys_limit); + zone_size[ZONE_DMA32] = max_dma32 - max_dma; #endif - zone_size[ZONE_NORMAL] = max - max_dma; + zone_size[ZONE_NORMAL] = max - max_dma32; memcpy(zhole_size, zone_size, sizeof(zhole_size)); @@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (start >= max) continue; - -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA if (start < max_dma) { - unsigned long dma_end = min(end, max_dma); - zhole_size[ZONE_DMA32] -= dma_end - start; + unsigned long dma_end = min_not_zero(end, max_dma); + zhole_size[ZONE_DMA] -= dma_end - start; } #endif - if (end > max_dma) { +#ifdef CONFIG_ZONE_DMA32 + if (start < max_dma32) { + unsigned long dma32_end = min(end, max_dma32); + unsigned long dma32_start = max(start, max_dma); + zhole_size[ZONE_DMA32] -= dma32_end - dma32_start; + } +#endif + if (end > max_dma32) { unsigned long normal_end = min(end, max); - unsigned long normal_start = max(start, max_dma); + unsigned long normal_start = max(start, max_dma32); zhole_size[ZONE_NORMAL] -= normal_end - normal_start; } } @@ -418,11 +443,15 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - /* 4GB maximum for 32-bit only capable devices */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) { + zone_dma_bits = ARM64_ZONE_DMA_BITS; + arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS); + } + if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma_phys_limit = max_zone_dma_phys(); + arm64_dma32_phys_limit = max_zone_phys(32); else - arm64_dma_phys_limit = PHYS_MASK + 1; + arm64_dma32_phys_limit = PHYS_MASK + 1; reserve_crashkernel(); @@ -430,7 +459,7 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - dma_contiguous_reserve(arm64_dma_phys_limit); + dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -534,7 +563,7 @@ static void __init free_unused_memmap(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; @@ -571,7 +600,7 @@ void free_initmem(void) { free_reserved_area(lm_alias(__init_begin), lm_alias(__init_end), - 0, "unused kernel"); + POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This * prevents the region from being reused for kernel modules, which @@ -580,18 +609,6 @@ void free_initmem(void) unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } -#ifdef CONFIG_BLK_DEV_INITRD -void __init free_initrd_mem(unsigned long start, unsigned long end) -{ - unsigned long aligned_start, aligned_end; - - aligned_start = __virt_to_phys(start) & PAGE_MASK; - aligned_end = PAGE_ALIGN(__virt_to_phys(end)); - memblock_free(aligned_start, aligned_end - aligned_start); - free_reserved_area((void *)start, (void *)end, 0, "initrd"); -} -#endif - /* * Dump out memory limit information on panic. */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 60c929f3683b..a9f541912289 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -338,7 +338,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys_addr_t (*pgtable_alloc)(int), int flags) { - unsigned long addr, length, end, next; + unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* @@ -350,9 +350,8 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys &= PAGE_MASK; addr = virt & PAGE_MASK; - length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); + end = PAGE_ALIGN(virt + size); - end = addr + length; do { next = pgd_addr_end(addr, end); alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, |